Upload folder using huggingface_hub
Browse files- .ipynb_checkpoints/README-checkpoint.md +202 -0
- README.md +199 -9
- adapter_config.json +26 -6
- adapter_model.safetensors +3 -0
- checkpoint-500/.ipynb_checkpoints/trainer_state-checkpoint.json +3545 -0
- checkpoint-500/README.md +202 -0
- checkpoint-500/adapter_config.json +37 -0
- checkpoint-500/adapter_model.safetensors +3 -0
- checkpoint-500/optimizer.pt +3 -0
- checkpoint-500/rng_state.pth +3 -0
- checkpoint-500/scheduler.pt +3 -0
- checkpoint-500/special_tokens_map.json +24 -0
- checkpoint-500/tokenizer.json +0 -0
- checkpoint-500/tokenizer.model +3 -0
- checkpoint-500/tokenizer_config.json +42 -0
- checkpoint-500/trainer_state.json +3545 -0
- checkpoint-500/training_args.bin +3 -0
- runs/Nov04_00-07-37_autodl-container-4be511b1ae-46466da0/events.out.tfevents.1730650101.autodl-container-4be511b1ae-46466da0.1254.0 +3 -0
- runs/Nov04_00-10-37_autodl-container-4be511b1ae-46466da0/events.out.tfevents.1730650280.autodl-container-4be511b1ae-46466da0.1417.0 +3 -0
- runs/Oct22_22-32-37_autodl-container-4be511b1ae-46466da0/events.out.tfevents.1729607600.autodl-container-4be511b1ae-46466da0.1125.0 +3 -0
- runs/Oct22_23-34-53_autodl-container-4be511b1ae-46466da0/events.out.tfevents.1729611338.autodl-container-4be511b1ae-46466da0.845.0 +3 -0
- runs/Oct24_22-55-18_autodl-container-4be511b1ae-46466da0/events.out.tfevents.1729781767.autodl-container-4be511b1ae-46466da0.884.0 +3 -0
- runs/Oct25_00-15-00_autodl-container-4be511b1ae-46466da0/events.out.tfevents.1729786546.autodl-container-4be511b1ae-46466da0.861.0 +3 -0
- special_tokens_map.json +24 -0
- tokenizer.json +0 -0
- tokenizer.model +3 -0
- tokenizer_config.json +42 -0
- trainer_state.json +0 -0
- training_args.bin +3 -0
.ipynb_checkpoints/README-checkpoint.md
ADDED
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
base_model: HIT-SCIR/Chinese-Mixtral-8x7B
|
3 |
+
library_name: peft
|
4 |
+
---
|
5 |
+
|
6 |
+
# Model Card for Model ID
|
7 |
+
|
8 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
9 |
+
|
10 |
+
|
11 |
+
|
12 |
+
## Model Details
|
13 |
+
|
14 |
+
### Model Description
|
15 |
+
|
16 |
+
<!-- Provide a longer summary of what this model is. -->
|
17 |
+
|
18 |
+
|
19 |
+
|
20 |
+
- **Developed by:** [More Information Needed]
|
21 |
+
- **Funded by [optional]:** [More Information Needed]
|
22 |
+
- **Shared by [optional]:** [More Information Needed]
|
23 |
+
- **Model type:** [More Information Needed]
|
24 |
+
- **Language(s) (NLP):** [More Information Needed]
|
25 |
+
- **License:** [More Information Needed]
|
26 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
27 |
+
|
28 |
+
### Model Sources [optional]
|
29 |
+
|
30 |
+
<!-- Provide the basic links for the model. -->
|
31 |
+
|
32 |
+
- **Repository:** [More Information Needed]
|
33 |
+
- **Paper [optional]:** [More Information Needed]
|
34 |
+
- **Demo [optional]:** [More Information Needed]
|
35 |
+
|
36 |
+
## Uses
|
37 |
+
|
38 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
39 |
+
|
40 |
+
### Direct Use
|
41 |
+
|
42 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
43 |
+
|
44 |
+
[More Information Needed]
|
45 |
+
|
46 |
+
### Downstream Use [optional]
|
47 |
+
|
48 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
49 |
+
|
50 |
+
[More Information Needed]
|
51 |
+
|
52 |
+
### Out-of-Scope Use
|
53 |
+
|
54 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
55 |
+
|
56 |
+
[More Information Needed]
|
57 |
+
|
58 |
+
## Bias, Risks, and Limitations
|
59 |
+
|
60 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
61 |
+
|
62 |
+
[More Information Needed]
|
63 |
+
|
64 |
+
### Recommendations
|
65 |
+
|
66 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
67 |
+
|
68 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
69 |
+
|
70 |
+
## How to Get Started with the Model
|
71 |
+
|
72 |
+
Use the code below to get started with the model.
|
73 |
+
|
74 |
+
[More Information Needed]
|
75 |
+
|
76 |
+
## Training Details
|
77 |
+
|
78 |
+
### Training Data
|
79 |
+
|
80 |
+
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
81 |
+
|
82 |
+
[More Information Needed]
|
83 |
+
|
84 |
+
### Training Procedure
|
85 |
+
|
86 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
87 |
+
|
88 |
+
#### Preprocessing [optional]
|
89 |
+
|
90 |
+
[More Information Needed]
|
91 |
+
|
92 |
+
|
93 |
+
#### Training Hyperparameters
|
94 |
+
|
95 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
96 |
+
|
97 |
+
#### Speeds, Sizes, Times [optional]
|
98 |
+
|
99 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
100 |
+
|
101 |
+
[More Information Needed]
|
102 |
+
|
103 |
+
## Evaluation
|
104 |
+
|
105 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
106 |
+
|
107 |
+
### Testing Data, Factors & Metrics
|
108 |
+
|
109 |
+
#### Testing Data
|
110 |
+
|
111 |
+
<!-- This should link to a Dataset Card if possible. -->
|
112 |
+
|
113 |
+
[More Information Needed]
|
114 |
+
|
115 |
+
#### Factors
|
116 |
+
|
117 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
118 |
+
|
119 |
+
[More Information Needed]
|
120 |
+
|
121 |
+
#### Metrics
|
122 |
+
|
123 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
124 |
+
|
125 |
+
[More Information Needed]
|
126 |
+
|
127 |
+
### Results
|
128 |
+
|
129 |
+
[More Information Needed]
|
130 |
+
|
131 |
+
#### Summary
|
132 |
+
|
133 |
+
|
134 |
+
|
135 |
+
## Model Examination [optional]
|
136 |
+
|
137 |
+
<!-- Relevant interpretability work for the model goes here -->
|
138 |
+
|
139 |
+
[More Information Needed]
|
140 |
+
|
141 |
+
## Environmental Impact
|
142 |
+
|
143 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
144 |
+
|
145 |
+
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
146 |
+
|
147 |
+
- **Hardware Type:** [More Information Needed]
|
148 |
+
- **Hours used:** [More Information Needed]
|
149 |
+
- **Cloud Provider:** [More Information Needed]
|
150 |
+
- **Compute Region:** [More Information Needed]
|
151 |
+
- **Carbon Emitted:** [More Information Needed]
|
152 |
+
|
153 |
+
## Technical Specifications [optional]
|
154 |
+
|
155 |
+
### Model Architecture and Objective
|
156 |
+
|
157 |
+
[More Information Needed]
|
158 |
+
|
159 |
+
### Compute Infrastructure
|
160 |
+
|
161 |
+
[More Information Needed]
|
162 |
+
|
163 |
+
#### Hardware
|
164 |
+
|
165 |
+
[More Information Needed]
|
166 |
+
|
167 |
+
#### Software
|
168 |
+
|
169 |
+
[More Information Needed]
|
170 |
+
|
171 |
+
## Citation [optional]
|
172 |
+
|
173 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
174 |
+
|
175 |
+
**BibTeX:**
|
176 |
+
|
177 |
+
[More Information Needed]
|
178 |
+
|
179 |
+
**APA:**
|
180 |
+
|
181 |
+
[More Information Needed]
|
182 |
+
|
183 |
+
## Glossary [optional]
|
184 |
+
|
185 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
186 |
+
|
187 |
+
[More Information Needed]
|
188 |
+
|
189 |
+
## More Information [optional]
|
190 |
+
|
191 |
+
[More Information Needed]
|
192 |
+
|
193 |
+
## Model Card Authors [optional]
|
194 |
+
|
195 |
+
[More Information Needed]
|
196 |
+
|
197 |
+
## Model Card Contact
|
198 |
+
|
199 |
+
[More Information Needed]
|
200 |
+
### Framework versions
|
201 |
+
|
202 |
+
- PEFT 0.13.2
|
README.md
CHANGED
@@ -1,12 +1,202 @@
|
|
1 |
---
|
2 |
-
|
3 |
-
|
4 |
-
colorFrom: gray
|
5 |
-
colorTo: gray
|
6 |
-
sdk: gradio
|
7 |
-
sdk_version: 3.40.1
|
8 |
-
app_file: app.py
|
9 |
-
pinned: false
|
10 |
---
|
11 |
|
12 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
---
|
2 |
+
base_model: HIT-SCIR/Chinese-Mixtral-8x7B
|
3 |
+
library_name: peft
|
|
|
|
|
|
|
|
|
|
|
|
|
4 |
---
|
5 |
|
6 |
+
# Model Card for Model ID
|
7 |
+
|
8 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
9 |
+
|
10 |
+
|
11 |
+
|
12 |
+
## Model Details
|
13 |
+
|
14 |
+
### Model Description
|
15 |
+
|
16 |
+
<!-- Provide a longer summary of what this model is. -->
|
17 |
+
|
18 |
+
|
19 |
+
|
20 |
+
- **Developed by:** [More Information Needed]
|
21 |
+
- **Funded by [optional]:** [More Information Needed]
|
22 |
+
- **Shared by [optional]:** [More Information Needed]
|
23 |
+
- **Model type:** [More Information Needed]
|
24 |
+
- **Language(s) (NLP):** [More Information Needed]
|
25 |
+
- **License:** [More Information Needed]
|
26 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
27 |
+
|
28 |
+
### Model Sources [optional]
|
29 |
+
|
30 |
+
<!-- Provide the basic links for the model. -->
|
31 |
+
|
32 |
+
- **Repository:** [More Information Needed]
|
33 |
+
- **Paper [optional]:** [More Information Needed]
|
34 |
+
- **Demo [optional]:** [More Information Needed]
|
35 |
+
|
36 |
+
## Uses
|
37 |
+
|
38 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
39 |
+
|
40 |
+
### Direct Use
|
41 |
+
|
42 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
43 |
+
|
44 |
+
[More Information Needed]
|
45 |
+
|
46 |
+
### Downstream Use [optional]
|
47 |
+
|
48 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
49 |
+
|
50 |
+
[More Information Needed]
|
51 |
+
|
52 |
+
### Out-of-Scope Use
|
53 |
+
|
54 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
55 |
+
|
56 |
+
[More Information Needed]
|
57 |
+
|
58 |
+
## Bias, Risks, and Limitations
|
59 |
+
|
60 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
61 |
+
|
62 |
+
[More Information Needed]
|
63 |
+
|
64 |
+
### Recommendations
|
65 |
+
|
66 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
67 |
+
|
68 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
69 |
+
|
70 |
+
## How to Get Started with the Model
|
71 |
+
|
72 |
+
Use the code below to get started with the model.
|
73 |
+
|
74 |
+
[More Information Needed]
|
75 |
+
|
76 |
+
## Training Details
|
77 |
+
|
78 |
+
### Training Data
|
79 |
+
|
80 |
+
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
81 |
+
|
82 |
+
[More Information Needed]
|
83 |
+
|
84 |
+
### Training Procedure
|
85 |
+
|
86 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
87 |
+
|
88 |
+
#### Preprocessing [optional]
|
89 |
+
|
90 |
+
[More Information Needed]
|
91 |
+
|
92 |
+
|
93 |
+
#### Training Hyperparameters
|
94 |
+
|
95 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
96 |
+
|
97 |
+
#### Speeds, Sizes, Times [optional]
|
98 |
+
|
99 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
100 |
+
|
101 |
+
[More Information Needed]
|
102 |
+
|
103 |
+
## Evaluation
|
104 |
+
|
105 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
106 |
+
|
107 |
+
### Testing Data, Factors & Metrics
|
108 |
+
|
109 |
+
#### Testing Data
|
110 |
+
|
111 |
+
<!-- This should link to a Dataset Card if possible. -->
|
112 |
+
|
113 |
+
[More Information Needed]
|
114 |
+
|
115 |
+
#### Factors
|
116 |
+
|
117 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
118 |
+
|
119 |
+
[More Information Needed]
|
120 |
+
|
121 |
+
#### Metrics
|
122 |
+
|
123 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
124 |
+
|
125 |
+
[More Information Needed]
|
126 |
+
|
127 |
+
### Results
|
128 |
+
|
129 |
+
[More Information Needed]
|
130 |
+
|
131 |
+
#### Summary
|
132 |
+
|
133 |
+
|
134 |
+
|
135 |
+
## Model Examination [optional]
|
136 |
+
|
137 |
+
<!-- Relevant interpretability work for the model goes here -->
|
138 |
+
|
139 |
+
[More Information Needed]
|
140 |
+
|
141 |
+
## Environmental Impact
|
142 |
+
|
143 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
144 |
+
|
145 |
+
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
146 |
+
|
147 |
+
- **Hardware Type:** [More Information Needed]
|
148 |
+
- **Hours used:** [More Information Needed]
|
149 |
+
- **Cloud Provider:** [More Information Needed]
|
150 |
+
- **Compute Region:** [More Information Needed]
|
151 |
+
- **Carbon Emitted:** [More Information Needed]
|
152 |
+
|
153 |
+
## Technical Specifications [optional]
|
154 |
+
|
155 |
+
### Model Architecture and Objective
|
156 |
+
|
157 |
+
[More Information Needed]
|
158 |
+
|
159 |
+
### Compute Infrastructure
|
160 |
+
|
161 |
+
[More Information Needed]
|
162 |
+
|
163 |
+
#### Hardware
|
164 |
+
|
165 |
+
[More Information Needed]
|
166 |
+
|
167 |
+
#### Software
|
168 |
+
|
169 |
+
[More Information Needed]
|
170 |
+
|
171 |
+
## Citation [optional]
|
172 |
+
|
173 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
174 |
+
|
175 |
+
**BibTeX:**
|
176 |
+
|
177 |
+
[More Information Needed]
|
178 |
+
|
179 |
+
**APA:**
|
180 |
+
|
181 |
+
[More Information Needed]
|
182 |
+
|
183 |
+
## Glossary [optional]
|
184 |
+
|
185 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
186 |
+
|
187 |
+
[More Information Needed]
|
188 |
+
|
189 |
+
## More Information [optional]
|
190 |
+
|
191 |
+
[More Information Needed]
|
192 |
+
|
193 |
+
## Model Card Authors [optional]
|
194 |
+
|
195 |
+
[More Information Needed]
|
196 |
+
|
197 |
+
## Model Card Contact
|
198 |
+
|
199 |
+
[More Information Needed]
|
200 |
+
### Framework versions
|
201 |
+
|
202 |
+
- PEFT 0.13.2
|
adapter_config.json
CHANGED
@@ -1,17 +1,37 @@
|
|
1 |
{
|
2 |
-
"
|
|
|
|
|
3 |
"bias": "none",
|
4 |
"fan_in_fan_out": false,
|
5 |
"inference_mode": true,
|
6 |
"init_lora_weights": true,
|
7 |
-
"
|
|
|
|
|
|
|
|
|
8 |
"lora_dropout": 0.05,
|
9 |
-
"
|
|
|
|
|
|
|
|
|
|
|
10 |
"peft_type": "LORA",
|
11 |
-
"r":
|
|
|
|
|
12 |
"target_modules": [
|
|
|
|
|
|
|
13 |
"q_proj",
|
14 |
-
"v_proj"
|
|
|
|
|
15 |
],
|
16 |
-
"task_type": "CAUSAL_LM"
|
|
|
|
|
17 |
}
|
|
|
1 |
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "HIT-SCIR/Chinese-Mixtral-8x7B",
|
5 |
"bias": "none",
|
6 |
"fan_in_fan_out": false,
|
7 |
"inference_mode": true,
|
8 |
"init_lora_weights": true,
|
9 |
+
"layer_replication": null,
|
10 |
+
"layers_pattern": null,
|
11 |
+
"layers_to_transform": null,
|
12 |
+
"loftq_config": {},
|
13 |
+
"lora_alpha": 128,
|
14 |
"lora_dropout": 0.05,
|
15 |
+
"megatron_config": null,
|
16 |
+
"megatron_core": "megatron.core",
|
17 |
+
"modules_to_save": [
|
18 |
+
"embed_tokens",
|
19 |
+
"lm_head"
|
20 |
+
],
|
21 |
"peft_type": "LORA",
|
22 |
+
"r": 64,
|
23 |
+
"rank_pattern": {},
|
24 |
+
"revision": null,
|
25 |
"target_modules": [
|
26 |
+
"o_proj",
|
27 |
+
"w3",
|
28 |
+
"w2",
|
29 |
"q_proj",
|
30 |
+
"v_proj",
|
31 |
+
"k_proj",
|
32 |
+
"w1"
|
33 |
],
|
34 |
+
"task_type": "CAUSAL_LM",
|
35 |
+
"use_dora": false,
|
36 |
+
"use_rslora": false
|
37 |
}
|
adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:11c4730bc0c2a58c07e2e01fd966dd2e2883400bd7cd38a127a5ed75da1d0c71
|
3 |
+
size 2855150432
|
checkpoint-500/.ipynb_checkpoints/trainer_state-checkpoint.json
ADDED
@@ -0,0 +1,3545 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.6620762711864406,
|
5 |
+
"eval_steps": 200,
|
6 |
+
"global_step": 500,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.0013241525423728813,
|
13 |
+
"grad_norm": 26.125,
|
14 |
+
"learning_rate": 2.6315789473684213e-07,
|
15 |
+
"loss": 3.7676,
|
16 |
+
"step": 1
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.0013241525423728813,
|
20 |
+
"eval_AskDoctor-Chinese_loss": 3.761261463165283,
|
21 |
+
"eval_AskDoctor-Chinese_runtime": 15.9737,
|
22 |
+
"eval_AskDoctor-Chinese_samples_per_second": 1.878,
|
23 |
+
"eval_AskDoctor-Chinese_steps_per_second": 1.878,
|
24 |
+
"step": 1
|
25 |
+
},
|
26 |
+
{
|
27 |
+
"epoch": 0.0026483050847457626,
|
28 |
+
"grad_norm": 27.375,
|
29 |
+
"learning_rate": 5.263157894736843e-07,
|
30 |
+
"loss": 3.8885,
|
31 |
+
"step": 2
|
32 |
+
},
|
33 |
+
{
|
34 |
+
"epoch": 0.003972457627118644,
|
35 |
+
"grad_norm": 28.125,
|
36 |
+
"learning_rate": 7.894736842105263e-07,
|
37 |
+
"loss": 3.8601,
|
38 |
+
"step": 3
|
39 |
+
},
|
40 |
+
{
|
41 |
+
"epoch": 0.005296610169491525,
|
42 |
+
"grad_norm": 26.25,
|
43 |
+
"learning_rate": 1.0526315789473685e-06,
|
44 |
+
"loss": 3.8192,
|
45 |
+
"step": 4
|
46 |
+
},
|
47 |
+
{
|
48 |
+
"epoch": 0.0066207627118644065,
|
49 |
+
"grad_norm": 29.0,
|
50 |
+
"learning_rate": 1.3157894736842106e-06,
|
51 |
+
"loss": 3.7572,
|
52 |
+
"step": 5
|
53 |
+
},
|
54 |
+
{
|
55 |
+
"epoch": 0.007944915254237288,
|
56 |
+
"grad_norm": 30.5,
|
57 |
+
"learning_rate": 1.5789473684210526e-06,
|
58 |
+
"loss": 3.9407,
|
59 |
+
"step": 6
|
60 |
+
},
|
61 |
+
{
|
62 |
+
"epoch": 0.009269067796610169,
|
63 |
+
"grad_norm": 30.25,
|
64 |
+
"learning_rate": 1.8421052631578948e-06,
|
65 |
+
"loss": 3.9034,
|
66 |
+
"step": 7
|
67 |
+
},
|
68 |
+
{
|
69 |
+
"epoch": 0.01059322033898305,
|
70 |
+
"grad_norm": 30.5,
|
71 |
+
"learning_rate": 2.105263157894737e-06,
|
72 |
+
"loss": 3.7951,
|
73 |
+
"step": 8
|
74 |
+
},
|
75 |
+
{
|
76 |
+
"epoch": 0.011917372881355932,
|
77 |
+
"grad_norm": 26.0,
|
78 |
+
"learning_rate": 2.368421052631579e-06,
|
79 |
+
"loss": 3.7,
|
80 |
+
"step": 9
|
81 |
+
},
|
82 |
+
{
|
83 |
+
"epoch": 0.013241525423728813,
|
84 |
+
"grad_norm": 28.625,
|
85 |
+
"learning_rate": 2.631578947368421e-06,
|
86 |
+
"loss": 3.6931,
|
87 |
+
"step": 10
|
88 |
+
},
|
89 |
+
{
|
90 |
+
"epoch": 0.014565677966101694,
|
91 |
+
"grad_norm": 25.125,
|
92 |
+
"learning_rate": 2.8947368421052634e-06,
|
93 |
+
"loss": 3.5419,
|
94 |
+
"step": 11
|
95 |
+
},
|
96 |
+
{
|
97 |
+
"epoch": 0.015889830508474576,
|
98 |
+
"grad_norm": 25.5,
|
99 |
+
"learning_rate": 3.157894736842105e-06,
|
100 |
+
"loss": 3.6584,
|
101 |
+
"step": 12
|
102 |
+
},
|
103 |
+
{
|
104 |
+
"epoch": 0.017213983050847457,
|
105 |
+
"grad_norm": 23.875,
|
106 |
+
"learning_rate": 3.421052631578948e-06,
|
107 |
+
"loss": 3.5614,
|
108 |
+
"step": 13
|
109 |
+
},
|
110 |
+
{
|
111 |
+
"epoch": 0.018538135593220338,
|
112 |
+
"grad_norm": 23.875,
|
113 |
+
"learning_rate": 3.6842105263157896e-06,
|
114 |
+
"loss": 3.5783,
|
115 |
+
"step": 14
|
116 |
+
},
|
117 |
+
{
|
118 |
+
"epoch": 0.01986228813559322,
|
119 |
+
"grad_norm": 23.25,
|
120 |
+
"learning_rate": 3.947368421052632e-06,
|
121 |
+
"loss": 3.5407,
|
122 |
+
"step": 15
|
123 |
+
},
|
124 |
+
{
|
125 |
+
"epoch": 0.0211864406779661,
|
126 |
+
"grad_norm": 22.0,
|
127 |
+
"learning_rate": 4.210526315789474e-06,
|
128 |
+
"loss": 3.3536,
|
129 |
+
"step": 16
|
130 |
+
},
|
131 |
+
{
|
132 |
+
"epoch": 0.022510593220338982,
|
133 |
+
"grad_norm": 20.0,
|
134 |
+
"learning_rate": 4.473684210526316e-06,
|
135 |
+
"loss": 3.2685,
|
136 |
+
"step": 17
|
137 |
+
},
|
138 |
+
{
|
139 |
+
"epoch": 0.023834745762711863,
|
140 |
+
"grad_norm": 19.5,
|
141 |
+
"learning_rate": 4.736842105263158e-06,
|
142 |
+
"loss": 3.3136,
|
143 |
+
"step": 18
|
144 |
+
},
|
145 |
+
{
|
146 |
+
"epoch": 0.025158898305084745,
|
147 |
+
"grad_norm": 18.875,
|
148 |
+
"learning_rate": 5e-06,
|
149 |
+
"loss": 3.3371,
|
150 |
+
"step": 19
|
151 |
+
},
|
152 |
+
{
|
153 |
+
"epoch": 0.026483050847457626,
|
154 |
+
"grad_norm": 26.125,
|
155 |
+
"learning_rate": 5.263157894736842e-06,
|
156 |
+
"loss": 3.2935,
|
157 |
+
"step": 20
|
158 |
+
},
|
159 |
+
{
|
160 |
+
"epoch": 0.027807203389830507,
|
161 |
+
"grad_norm": 18.375,
|
162 |
+
"learning_rate": 5.526315789473685e-06,
|
163 |
+
"loss": 3.1542,
|
164 |
+
"step": 21
|
165 |
+
},
|
166 |
+
{
|
167 |
+
"epoch": 0.02913135593220339,
|
168 |
+
"grad_norm": 16.125,
|
169 |
+
"learning_rate": 5.789473684210527e-06,
|
170 |
+
"loss": 3.0697,
|
171 |
+
"step": 22
|
172 |
+
},
|
173 |
+
{
|
174 |
+
"epoch": 0.03045550847457627,
|
175 |
+
"grad_norm": 17.75,
|
176 |
+
"learning_rate": 6.0526315789473685e-06,
|
177 |
+
"loss": 3.0135,
|
178 |
+
"step": 23
|
179 |
+
},
|
180 |
+
{
|
181 |
+
"epoch": 0.03177966101694915,
|
182 |
+
"grad_norm": 16.5,
|
183 |
+
"learning_rate": 6.31578947368421e-06,
|
184 |
+
"loss": 2.9917,
|
185 |
+
"step": 24
|
186 |
+
},
|
187 |
+
{
|
188 |
+
"epoch": 0.033103813559322036,
|
189 |
+
"grad_norm": 14.5625,
|
190 |
+
"learning_rate": 6.578947368421054e-06,
|
191 |
+
"loss": 2.9261,
|
192 |
+
"step": 25
|
193 |
+
},
|
194 |
+
{
|
195 |
+
"epoch": 0.034427966101694914,
|
196 |
+
"grad_norm": 20.375,
|
197 |
+
"learning_rate": 6.842105263157896e-06,
|
198 |
+
"loss": 2.8072,
|
199 |
+
"step": 26
|
200 |
+
},
|
201 |
+
{
|
202 |
+
"epoch": 0.0357521186440678,
|
203 |
+
"grad_norm": 13.375,
|
204 |
+
"learning_rate": 7.1052631578947375e-06,
|
205 |
+
"loss": 2.876,
|
206 |
+
"step": 27
|
207 |
+
},
|
208 |
+
{
|
209 |
+
"epoch": 0.037076271186440676,
|
210 |
+
"grad_norm": 12.5,
|
211 |
+
"learning_rate": 7.368421052631579e-06,
|
212 |
+
"loss": 2.7867,
|
213 |
+
"step": 28
|
214 |
+
},
|
215 |
+
{
|
216 |
+
"epoch": 0.03840042372881356,
|
217 |
+
"grad_norm": 14.625,
|
218 |
+
"learning_rate": 7.631578947368423e-06,
|
219 |
+
"loss": 2.6454,
|
220 |
+
"step": 29
|
221 |
+
},
|
222 |
+
{
|
223 |
+
"epoch": 0.03972457627118644,
|
224 |
+
"grad_norm": 16.625,
|
225 |
+
"learning_rate": 7.894736842105265e-06,
|
226 |
+
"loss": 2.6395,
|
227 |
+
"step": 30
|
228 |
+
},
|
229 |
+
{
|
230 |
+
"epoch": 0.041048728813559324,
|
231 |
+
"grad_norm": 10.1875,
|
232 |
+
"learning_rate": 8.157894736842106e-06,
|
233 |
+
"loss": 2.5909,
|
234 |
+
"step": 31
|
235 |
+
},
|
236 |
+
{
|
237 |
+
"epoch": 0.0423728813559322,
|
238 |
+
"grad_norm": 12.4375,
|
239 |
+
"learning_rate": 8.421052631578948e-06,
|
240 |
+
"loss": 2.5511,
|
241 |
+
"step": 32
|
242 |
+
},
|
243 |
+
{
|
244 |
+
"epoch": 0.043697033898305086,
|
245 |
+
"grad_norm": 10.375,
|
246 |
+
"learning_rate": 8.68421052631579e-06,
|
247 |
+
"loss": 2.4177,
|
248 |
+
"step": 33
|
249 |
+
},
|
250 |
+
{
|
251 |
+
"epoch": 0.045021186440677964,
|
252 |
+
"grad_norm": 8.5625,
|
253 |
+
"learning_rate": 8.947368421052632e-06,
|
254 |
+
"loss": 2.4405,
|
255 |
+
"step": 34
|
256 |
+
},
|
257 |
+
{
|
258 |
+
"epoch": 0.04634533898305085,
|
259 |
+
"grad_norm": 8.5625,
|
260 |
+
"learning_rate": 9.210526315789474e-06,
|
261 |
+
"loss": 2.5073,
|
262 |
+
"step": 35
|
263 |
+
},
|
264 |
+
{
|
265 |
+
"epoch": 0.04766949152542373,
|
266 |
+
"grad_norm": 7.625,
|
267 |
+
"learning_rate": 9.473684210526315e-06,
|
268 |
+
"loss": 2.4031,
|
269 |
+
"step": 36
|
270 |
+
},
|
271 |
+
{
|
272 |
+
"epoch": 0.04899364406779661,
|
273 |
+
"grad_norm": 9.375,
|
274 |
+
"learning_rate": 9.736842105263159e-06,
|
275 |
+
"loss": 2.4698,
|
276 |
+
"step": 37
|
277 |
+
},
|
278 |
+
{
|
279 |
+
"epoch": 0.05031779661016949,
|
280 |
+
"grad_norm": 6.75,
|
281 |
+
"learning_rate": 1e-05,
|
282 |
+
"loss": 2.4379,
|
283 |
+
"step": 38
|
284 |
+
},
|
285 |
+
{
|
286 |
+
"epoch": 0.051641949152542374,
|
287 |
+
"grad_norm": 7.59375,
|
288 |
+
"learning_rate": 9.999952004474853e-06,
|
289 |
+
"loss": 2.3739,
|
290 |
+
"step": 39
|
291 |
+
},
|
292 |
+
{
|
293 |
+
"epoch": 0.05296610169491525,
|
294 |
+
"grad_norm": 6.375,
|
295 |
+
"learning_rate": 9.999808018820836e-06,
|
296 |
+
"loss": 2.433,
|
297 |
+
"step": 40
|
298 |
+
},
|
299 |
+
{
|
300 |
+
"epoch": 0.05429025423728814,
|
301 |
+
"grad_norm": 5.96875,
|
302 |
+
"learning_rate": 9.999568045802216e-06,
|
303 |
+
"loss": 2.4569,
|
304 |
+
"step": 41
|
305 |
+
},
|
306 |
+
{
|
307 |
+
"epoch": 0.055614406779661014,
|
308 |
+
"grad_norm": 5.59375,
|
309 |
+
"learning_rate": 9.99923209002605e-06,
|
310 |
+
"loss": 2.3297,
|
311 |
+
"step": 42
|
312 |
+
},
|
313 |
+
{
|
314 |
+
"epoch": 0.0569385593220339,
|
315 |
+
"grad_norm": 5.5,
|
316 |
+
"learning_rate": 9.998800157942083e-06,
|
317 |
+
"loss": 2.3064,
|
318 |
+
"step": 43
|
319 |
+
},
|
320 |
+
{
|
321 |
+
"epoch": 0.05826271186440678,
|
322 |
+
"grad_norm": 5.375,
|
323 |
+
"learning_rate": 9.99827225784264e-06,
|
324 |
+
"loss": 2.2746,
|
325 |
+
"step": 44
|
326 |
+
},
|
327 |
+
{
|
328 |
+
"epoch": 0.05958686440677966,
|
329 |
+
"grad_norm": 4.9375,
|
330 |
+
"learning_rate": 9.997648399862457e-06,
|
331 |
+
"loss": 2.2981,
|
332 |
+
"step": 45
|
333 |
+
},
|
334 |
+
{
|
335 |
+
"epoch": 0.06091101694915254,
|
336 |
+
"grad_norm": 5.5625,
|
337 |
+
"learning_rate": 9.99692859597849e-06,
|
338 |
+
"loss": 2.0856,
|
339 |
+
"step": 46
|
340 |
+
},
|
341 |
+
{
|
342 |
+
"epoch": 0.062235169491525424,
|
343 |
+
"grad_norm": 5.71875,
|
344 |
+
"learning_rate": 9.996112860009689e-06,
|
345 |
+
"loss": 2.1083,
|
346 |
+
"step": 47
|
347 |
+
},
|
348 |
+
{
|
349 |
+
"epoch": 0.0635593220338983,
|
350 |
+
"grad_norm": 5.53125,
|
351 |
+
"learning_rate": 9.995201207616718e-06,
|
352 |
+
"loss": 2.1841,
|
353 |
+
"step": 48
|
354 |
+
},
|
355 |
+
{
|
356 |
+
"epoch": 0.06488347457627118,
|
357 |
+
"grad_norm": 4.65625,
|
358 |
+
"learning_rate": 9.994193656301676e-06,
|
359 |
+
"loss": 2.3351,
|
360 |
+
"step": 49
|
361 |
+
},
|
362 |
+
{
|
363 |
+
"epoch": 0.06620762711864407,
|
364 |
+
"grad_norm": 5.1875,
|
365 |
+
"learning_rate": 9.993090225407743e-06,
|
366 |
+
"loss": 2.2625,
|
367 |
+
"step": 50
|
368 |
+
},
|
369 |
+
{
|
370 |
+
"epoch": 0.06753177966101695,
|
371 |
+
"grad_norm": 13.0625,
|
372 |
+
"learning_rate": 9.991890936118817e-06,
|
373 |
+
"loss": 2.1591,
|
374 |
+
"step": 51
|
375 |
+
},
|
376 |
+
{
|
377 |
+
"epoch": 0.06885593220338983,
|
378 |
+
"grad_norm": 4.53125,
|
379 |
+
"learning_rate": 9.990595811459109e-06,
|
380 |
+
"loss": 2.2935,
|
381 |
+
"step": 52
|
382 |
+
},
|
383 |
+
{
|
384 |
+
"epoch": 0.0701800847457627,
|
385 |
+
"grad_norm": 4.46875,
|
386 |
+
"learning_rate": 9.98920487629269e-06,
|
387 |
+
"loss": 2.4604,
|
388 |
+
"step": 53
|
389 |
+
},
|
390 |
+
{
|
391 |
+
"epoch": 0.0715042372881356,
|
392 |
+
"grad_norm": 4.5625,
|
393 |
+
"learning_rate": 9.987718157323026e-06,
|
394 |
+
"loss": 2.249,
|
395 |
+
"step": 54
|
396 |
+
},
|
397 |
+
{
|
398 |
+
"epoch": 0.07282838983050847,
|
399 |
+
"grad_norm": 4.59375,
|
400 |
+
"learning_rate": 9.986135683092461e-06,
|
401 |
+
"loss": 2.2686,
|
402 |
+
"step": 55
|
403 |
+
},
|
404 |
+
{
|
405 |
+
"epoch": 0.07415254237288135,
|
406 |
+
"grad_norm": 4.21875,
|
407 |
+
"learning_rate": 9.98445748398167e-06,
|
408 |
+
"loss": 2.291,
|
409 |
+
"step": 56
|
410 |
+
},
|
411 |
+
{
|
412 |
+
"epoch": 0.07547669491525423,
|
413 |
+
"grad_norm": 4.28125,
|
414 |
+
"learning_rate": 9.982683592209069e-06,
|
415 |
+
"loss": 2.1275,
|
416 |
+
"step": 57
|
417 |
+
},
|
418 |
+
{
|
419 |
+
"epoch": 0.07680084745762712,
|
420 |
+
"grad_norm": 12.875,
|
421 |
+
"learning_rate": 9.980814041830203e-06,
|
422 |
+
"loss": 2.1489,
|
423 |
+
"step": 58
|
424 |
+
},
|
425 |
+
{
|
426 |
+
"epoch": 0.078125,
|
427 |
+
"grad_norm": 4.375,
|
428 |
+
"learning_rate": 9.978848868737099e-06,
|
429 |
+
"loss": 2.271,
|
430 |
+
"step": 59
|
431 |
+
},
|
432 |
+
{
|
433 |
+
"epoch": 0.07944915254237288,
|
434 |
+
"grad_norm": 4.84375,
|
435 |
+
"learning_rate": 9.976788110657558e-06,
|
436 |
+
"loss": 2.3377,
|
437 |
+
"step": 60
|
438 |
+
},
|
439 |
+
{
|
440 |
+
"epoch": 0.08077330508474577,
|
441 |
+
"grad_norm": 4.09375,
|
442 |
+
"learning_rate": 9.974631807154447e-06,
|
443 |
+
"loss": 2.3359,
|
444 |
+
"step": 61
|
445 |
+
},
|
446 |
+
{
|
447 |
+
"epoch": 0.08209745762711865,
|
448 |
+
"grad_norm": 4.25,
|
449 |
+
"learning_rate": 9.972379999624935e-06,
|
450 |
+
"loss": 2.2142,
|
451 |
+
"step": 62
|
452 |
+
},
|
453 |
+
{
|
454 |
+
"epoch": 0.08342161016949153,
|
455 |
+
"grad_norm": 12.375,
|
456 |
+
"learning_rate": 9.970032731299697e-06,
|
457 |
+
"loss": 2.1888,
|
458 |
+
"step": 63
|
459 |
+
},
|
460 |
+
{
|
461 |
+
"epoch": 0.0847457627118644,
|
462 |
+
"grad_norm": 4.15625,
|
463 |
+
"learning_rate": 9.967590047242082e-06,
|
464 |
+
"loss": 2.3571,
|
465 |
+
"step": 64
|
466 |
+
},
|
467 |
+
{
|
468 |
+
"epoch": 0.0860699152542373,
|
469 |
+
"grad_norm": 4.25,
|
470 |
+
"learning_rate": 9.96505199434725e-06,
|
471 |
+
"loss": 2.1241,
|
472 |
+
"step": 65
|
473 |
+
},
|
474 |
+
{
|
475 |
+
"epoch": 0.08739406779661017,
|
476 |
+
"grad_norm": 4.65625,
|
477 |
+
"learning_rate": 9.962418621341275e-06,
|
478 |
+
"loss": 2.0733,
|
479 |
+
"step": 66
|
480 |
+
},
|
481 |
+
{
|
482 |
+
"epoch": 0.08871822033898305,
|
483 |
+
"grad_norm": 9.75,
|
484 |
+
"learning_rate": 9.959689978780207e-06,
|
485 |
+
"loss": 2.1612,
|
486 |
+
"step": 67
|
487 |
+
},
|
488 |
+
{
|
489 |
+
"epoch": 0.09004237288135593,
|
490 |
+
"grad_norm": 4.4375,
|
491 |
+
"learning_rate": 9.956866119049095e-06,
|
492 |
+
"loss": 2.1519,
|
493 |
+
"step": 68
|
494 |
+
},
|
495 |
+
{
|
496 |
+
"epoch": 0.09136652542372882,
|
497 |
+
"grad_norm": 9.125,
|
498 |
+
"learning_rate": 9.953947096360996e-06,
|
499 |
+
"loss": 2.1352,
|
500 |
+
"step": 69
|
501 |
+
},
|
502 |
+
{
|
503 |
+
"epoch": 0.0926906779661017,
|
504 |
+
"grad_norm": 4.25,
|
505 |
+
"learning_rate": 9.950932966755917e-06,
|
506 |
+
"loss": 2.1954,
|
507 |
+
"step": 70
|
508 |
+
},
|
509 |
+
{
|
510 |
+
"epoch": 0.09401483050847458,
|
511 |
+
"grad_norm": 4.03125,
|
512 |
+
"learning_rate": 9.947823788099754e-06,
|
513 |
+
"loss": 2.1761,
|
514 |
+
"step": 71
|
515 |
+
},
|
516 |
+
{
|
517 |
+
"epoch": 0.09533898305084745,
|
518 |
+
"grad_norm": 3.921875,
|
519 |
+
"learning_rate": 9.94461962008317e-06,
|
520 |
+
"loss": 2.1397,
|
521 |
+
"step": 72
|
522 |
+
},
|
523 |
+
{
|
524 |
+
"epoch": 0.09666313559322035,
|
525 |
+
"grad_norm": 4.625,
|
526 |
+
"learning_rate": 9.941320524220455e-06,
|
527 |
+
"loss": 2.1281,
|
528 |
+
"step": 73
|
529 |
+
},
|
530 |
+
{
|
531 |
+
"epoch": 0.09798728813559322,
|
532 |
+
"grad_norm": 7.96875,
|
533 |
+
"learning_rate": 9.937926563848345e-06,
|
534 |
+
"loss": 1.8948,
|
535 |
+
"step": 74
|
536 |
+
},
|
537 |
+
{
|
538 |
+
"epoch": 0.0993114406779661,
|
539 |
+
"grad_norm": 4.75,
|
540 |
+
"learning_rate": 9.934437804124807e-06,
|
541 |
+
"loss": 2.3239,
|
542 |
+
"step": 75
|
543 |
+
},
|
544 |
+
{
|
545 |
+
"epoch": 0.10063559322033898,
|
546 |
+
"grad_norm": 3.984375,
|
547 |
+
"learning_rate": 9.93085431202778e-06,
|
548 |
+
"loss": 2.3193,
|
549 |
+
"step": 76
|
550 |
+
},
|
551 |
+
{
|
552 |
+
"epoch": 0.10195974576271187,
|
553 |
+
"grad_norm": 4.34375,
|
554 |
+
"learning_rate": 9.9271761563539e-06,
|
555 |
+
"loss": 2.0956,
|
556 |
+
"step": 77
|
557 |
+
},
|
558 |
+
{
|
559 |
+
"epoch": 0.10328389830508475,
|
560 |
+
"grad_norm": 4.65625,
|
561 |
+
"learning_rate": 9.92340340771717e-06,
|
562 |
+
"loss": 2.3226,
|
563 |
+
"step": 78
|
564 |
+
},
|
565 |
+
{
|
566 |
+
"epoch": 0.10460805084745763,
|
567 |
+
"grad_norm": 4.6875,
|
568 |
+
"learning_rate": 9.919536138547611e-06,
|
569 |
+
"loss": 2.1505,
|
570 |
+
"step": 79
|
571 |
+
},
|
572 |
+
{
|
573 |
+
"epoch": 0.1059322033898305,
|
574 |
+
"grad_norm": 6.1875,
|
575 |
+
"learning_rate": 9.915574423089872e-06,
|
576 |
+
"loss": 2.0939,
|
577 |
+
"step": 80
|
578 |
+
},
|
579 |
+
{
|
580 |
+
"epoch": 0.1072563559322034,
|
581 |
+
"grad_norm": 12.75,
|
582 |
+
"learning_rate": 9.911518337401792e-06,
|
583 |
+
"loss": 2.2263,
|
584 |
+
"step": 81
|
585 |
+
},
|
586 |
+
{
|
587 |
+
"epoch": 0.10858050847457627,
|
588 |
+
"grad_norm": 4.03125,
|
589 |
+
"learning_rate": 9.907367959352964e-06,
|
590 |
+
"loss": 2.1133,
|
591 |
+
"step": 82
|
592 |
+
},
|
593 |
+
{
|
594 |
+
"epoch": 0.10990466101694915,
|
595 |
+
"grad_norm": 3.984375,
|
596 |
+
"learning_rate": 9.903123368623216e-06,
|
597 |
+
"loss": 2.1183,
|
598 |
+
"step": 83
|
599 |
+
},
|
600 |
+
{
|
601 |
+
"epoch": 0.11122881355932203,
|
602 |
+
"grad_norm": 4.46875,
|
603 |
+
"learning_rate": 9.898784646701087e-06,
|
604 |
+
"loss": 2.1461,
|
605 |
+
"step": 84
|
606 |
+
},
|
607 |
+
{
|
608 |
+
"epoch": 0.11255296610169492,
|
609 |
+
"grad_norm": 4.53125,
|
610 |
+
"learning_rate": 9.894351876882277e-06,
|
611 |
+
"loss": 2.1963,
|
612 |
+
"step": 85
|
613 |
+
},
|
614 |
+
{
|
615 |
+
"epoch": 0.1138771186440678,
|
616 |
+
"grad_norm": 5.09375,
|
617 |
+
"learning_rate": 9.889825144268029e-06,
|
618 |
+
"loss": 2.1679,
|
619 |
+
"step": 86
|
620 |
+
},
|
621 |
+
{
|
622 |
+
"epoch": 0.11520127118644068,
|
623 |
+
"grad_norm": 4.34375,
|
624 |
+
"learning_rate": 9.88520453576351e-06,
|
625 |
+
"loss": 2.1925,
|
626 |
+
"step": 87
|
627 |
+
},
|
628 |
+
{
|
629 |
+
"epoch": 0.11652542372881355,
|
630 |
+
"grad_norm": 4.0625,
|
631 |
+
"learning_rate": 9.88049014007613e-06,
|
632 |
+
"loss": 2.1166,
|
633 |
+
"step": 88
|
634 |
+
},
|
635 |
+
{
|
636 |
+
"epoch": 0.11784957627118645,
|
637 |
+
"grad_norm": 3.796875,
|
638 |
+
"learning_rate": 9.875682047713847e-06,
|
639 |
+
"loss": 2.0244,
|
640 |
+
"step": 89
|
641 |
+
},
|
642 |
+
{
|
643 |
+
"epoch": 0.11917372881355932,
|
644 |
+
"grad_norm": 4.125,
|
645 |
+
"learning_rate": 9.87078035098343e-06,
|
646 |
+
"loss": 2.1427,
|
647 |
+
"step": 90
|
648 |
+
},
|
649 |
+
{
|
650 |
+
"epoch": 0.1204978813559322,
|
651 |
+
"grad_norm": 4.25,
|
652 |
+
"learning_rate": 9.865785143988684e-06,
|
653 |
+
"loss": 2.2495,
|
654 |
+
"step": 91
|
655 |
+
},
|
656 |
+
{
|
657 |
+
"epoch": 0.12182203389830508,
|
658 |
+
"grad_norm": 4.21875,
|
659 |
+
"learning_rate": 9.860696522628638e-06,
|
660 |
+
"loss": 2.1213,
|
661 |
+
"step": 92
|
662 |
+
},
|
663 |
+
{
|
664 |
+
"epoch": 0.12314618644067797,
|
665 |
+
"grad_norm": 4.40625,
|
666 |
+
"learning_rate": 9.855514584595719e-06,
|
667 |
+
"loss": 2.1922,
|
668 |
+
"step": 93
|
669 |
+
},
|
670 |
+
{
|
671 |
+
"epoch": 0.12447033898305085,
|
672 |
+
"grad_norm": 4.21875,
|
673 |
+
"learning_rate": 9.850239429373855e-06,
|
674 |
+
"loss": 2.16,
|
675 |
+
"step": 94
|
676 |
+
},
|
677 |
+
{
|
678 |
+
"epoch": 0.12579449152542374,
|
679 |
+
"grad_norm": 4.1875,
|
680 |
+
"learning_rate": 9.84487115823659e-06,
|
681 |
+
"loss": 2.1521,
|
682 |
+
"step": 95
|
683 |
+
},
|
684 |
+
{
|
685 |
+
"epoch": 0.1271186440677966,
|
686 |
+
"grad_norm": 4.375,
|
687 |
+
"learning_rate": 9.839409874245118e-06,
|
688 |
+
"loss": 2.1293,
|
689 |
+
"step": 96
|
690 |
+
},
|
691 |
+
{
|
692 |
+
"epoch": 0.1284427966101695,
|
693 |
+
"grad_norm": 8.6875,
|
694 |
+
"learning_rate": 9.833855682246319e-06,
|
695 |
+
"loss": 2.1652,
|
696 |
+
"step": 97
|
697 |
+
},
|
698 |
+
{
|
699 |
+
"epoch": 0.12976694915254236,
|
700 |
+
"grad_norm": 4.03125,
|
701 |
+
"learning_rate": 9.828208688870736e-06,
|
702 |
+
"loss": 2.0963,
|
703 |
+
"step": 98
|
704 |
+
},
|
705 |
+
{
|
706 |
+
"epoch": 0.13109110169491525,
|
707 |
+
"grad_norm": 4.3125,
|
708 |
+
"learning_rate": 9.822469002530531e-06,
|
709 |
+
"loss": 2.1573,
|
710 |
+
"step": 99
|
711 |
+
},
|
712 |
+
{
|
713 |
+
"epoch": 0.13241525423728814,
|
714 |
+
"grad_norm": 3.75,
|
715 |
+
"learning_rate": 9.816636733417413e-06,
|
716 |
+
"loss": 2.1625,
|
717 |
+
"step": 100
|
718 |
+
},
|
719 |
+
{
|
720 |
+
"epoch": 0.133739406779661,
|
721 |
+
"grad_norm": 4.25,
|
722 |
+
"learning_rate": 9.810711993500506e-06,
|
723 |
+
"loss": 2.1151,
|
724 |
+
"step": 101
|
725 |
+
},
|
726 |
+
{
|
727 |
+
"epoch": 0.1350635593220339,
|
728 |
+
"grad_norm": 4.125,
|
729 |
+
"learning_rate": 9.804694896524215e-06,
|
730 |
+
"loss": 2.0776,
|
731 |
+
"step": 102
|
732 |
+
},
|
733 |
+
{
|
734 |
+
"epoch": 0.1363877118644068,
|
735 |
+
"grad_norm": 4.15625,
|
736 |
+
"learning_rate": 9.79858555800603e-06,
|
737 |
+
"loss": 2.0534,
|
738 |
+
"step": 103
|
739 |
+
},
|
740 |
+
{
|
741 |
+
"epoch": 0.13771186440677965,
|
742 |
+
"grad_norm": 3.953125,
|
743 |
+
"learning_rate": 9.792384095234312e-06,
|
744 |
+
"loss": 1.994,
|
745 |
+
"step": 104
|
746 |
+
},
|
747 |
+
{
|
748 |
+
"epoch": 0.13903601694915255,
|
749 |
+
"grad_norm": 4.5,
|
750 |
+
"learning_rate": 9.78609062726605e-06,
|
751 |
+
"loss": 1.9252,
|
752 |
+
"step": 105
|
753 |
+
},
|
754 |
+
{
|
755 |
+
"epoch": 0.1403601694915254,
|
756 |
+
"grad_norm": 3.90625,
|
757 |
+
"learning_rate": 9.779705274924563e-06,
|
758 |
+
"loss": 2.1531,
|
759 |
+
"step": 106
|
760 |
+
},
|
761 |
+
{
|
762 |
+
"epoch": 0.1416843220338983,
|
763 |
+
"grad_norm": 3.828125,
|
764 |
+
"learning_rate": 9.773228160797187e-06,
|
765 |
+
"loss": 2.1426,
|
766 |
+
"step": 107
|
767 |
+
},
|
768 |
+
{
|
769 |
+
"epoch": 0.1430084745762712,
|
770 |
+
"grad_norm": 3.796875,
|
771 |
+
"learning_rate": 9.766659409232918e-06,
|
772 |
+
"loss": 2.1032,
|
773 |
+
"step": 108
|
774 |
+
},
|
775 |
+
{
|
776 |
+
"epoch": 0.14433262711864406,
|
777 |
+
"grad_norm": 4.09375,
|
778 |
+
"learning_rate": 9.759999146340031e-06,
|
779 |
+
"loss": 2.0202,
|
780 |
+
"step": 109
|
781 |
+
},
|
782 |
+
{
|
783 |
+
"epoch": 0.14565677966101695,
|
784 |
+
"grad_norm": 4.59375,
|
785 |
+
"learning_rate": 9.753247499983649e-06,
|
786 |
+
"loss": 2.0955,
|
787 |
+
"step": 110
|
788 |
+
},
|
789 |
+
{
|
790 |
+
"epoch": 0.14698093220338984,
|
791 |
+
"grad_norm": 4.03125,
|
792 |
+
"learning_rate": 9.7464045997833e-06,
|
793 |
+
"loss": 2.019,
|
794 |
+
"step": 111
|
795 |
+
},
|
796 |
+
{
|
797 |
+
"epoch": 0.1483050847457627,
|
798 |
+
"grad_norm": 4.625,
|
799 |
+
"learning_rate": 9.739470577110417e-06,
|
800 |
+
"loss": 2.1751,
|
801 |
+
"step": 112
|
802 |
+
},
|
803 |
+
{
|
804 |
+
"epoch": 0.1496292372881356,
|
805 |
+
"grad_norm": 4.125,
|
806 |
+
"learning_rate": 9.732445565085823e-06,
|
807 |
+
"loss": 2.0698,
|
808 |
+
"step": 113
|
809 |
+
},
|
810 |
+
{
|
811 |
+
"epoch": 0.15095338983050846,
|
812 |
+
"grad_norm": 4.03125,
|
813 |
+
"learning_rate": 9.725329698577177e-06,
|
814 |
+
"loss": 2.1954,
|
815 |
+
"step": 114
|
816 |
+
},
|
817 |
+
{
|
818 |
+
"epoch": 0.15227754237288135,
|
819 |
+
"grad_norm": 4.15625,
|
820 |
+
"learning_rate": 9.718123114196381e-06,
|
821 |
+
"loss": 2.1319,
|
822 |
+
"step": 115
|
823 |
+
},
|
824 |
+
{
|
825 |
+
"epoch": 0.15360169491525424,
|
826 |
+
"grad_norm": 3.921875,
|
827 |
+
"learning_rate": 9.71082595029695e-06,
|
828 |
+
"loss": 2.0517,
|
829 |
+
"step": 116
|
830 |
+
},
|
831 |
+
{
|
832 |
+
"epoch": 0.1549258474576271,
|
833 |
+
"grad_norm": 4.3125,
|
834 |
+
"learning_rate": 9.703438346971373e-06,
|
835 |
+
"loss": 2.243,
|
836 |
+
"step": 117
|
837 |
+
},
|
838 |
+
{
|
839 |
+
"epoch": 0.15625,
|
840 |
+
"grad_norm": 4.15625,
|
841 |
+
"learning_rate": 9.69596044604841e-06,
|
842 |
+
"loss": 2.2454,
|
843 |
+
"step": 118
|
844 |
+
},
|
845 |
+
{
|
846 |
+
"epoch": 0.1575741525423729,
|
847 |
+
"grad_norm": 4.0625,
|
848 |
+
"learning_rate": 9.688392391090374e-06,
|
849 |
+
"loss": 2.0891,
|
850 |
+
"step": 119
|
851 |
+
},
|
852 |
+
{
|
853 |
+
"epoch": 0.15889830508474576,
|
854 |
+
"grad_norm": 4.3125,
|
855 |
+
"learning_rate": 9.680734327390374e-06,
|
856 |
+
"loss": 2.1075,
|
857 |
+
"step": 120
|
858 |
+
},
|
859 |
+
{
|
860 |
+
"epoch": 0.16022245762711865,
|
861 |
+
"grad_norm": 4.125,
|
862 |
+
"learning_rate": 9.672986401969523e-06,
|
863 |
+
"loss": 2.0766,
|
864 |
+
"step": 121
|
865 |
+
},
|
866 |
+
{
|
867 |
+
"epoch": 0.16154661016949154,
|
868 |
+
"grad_norm": 3.71875,
|
869 |
+
"learning_rate": 9.665148763574123e-06,
|
870 |
+
"loss": 1.9083,
|
871 |
+
"step": 122
|
872 |
+
},
|
873 |
+
{
|
874 |
+
"epoch": 0.1628707627118644,
|
875 |
+
"grad_norm": 3.9375,
|
876 |
+
"learning_rate": 9.657221562672803e-06,
|
877 |
+
"loss": 1.9674,
|
878 |
+
"step": 123
|
879 |
+
},
|
880 |
+
{
|
881 |
+
"epoch": 0.1641949152542373,
|
882 |
+
"grad_norm": 3.78125,
|
883 |
+
"learning_rate": 9.64920495145363e-06,
|
884 |
+
"loss": 2.2366,
|
885 |
+
"step": 124
|
886 |
+
},
|
887 |
+
{
|
888 |
+
"epoch": 0.16551906779661016,
|
889 |
+
"grad_norm": 4.21875,
|
890 |
+
"learning_rate": 9.64109908382119e-06,
|
891 |
+
"loss": 2.1767,
|
892 |
+
"step": 125
|
893 |
+
},
|
894 |
+
{
|
895 |
+
"epoch": 0.16684322033898305,
|
896 |
+
"grad_norm": 4.1875,
|
897 |
+
"learning_rate": 9.632904115393633e-06,
|
898 |
+
"loss": 2.0395,
|
899 |
+
"step": 126
|
900 |
+
},
|
901 |
+
{
|
902 |
+
"epoch": 0.16816737288135594,
|
903 |
+
"grad_norm": 4.09375,
|
904 |
+
"learning_rate": 9.624620203499683e-06,
|
905 |
+
"loss": 2.2272,
|
906 |
+
"step": 127
|
907 |
+
},
|
908 |
+
{
|
909 |
+
"epoch": 0.1694915254237288,
|
910 |
+
"grad_norm": 3.8125,
|
911 |
+
"learning_rate": 9.616247507175624e-06,
|
912 |
+
"loss": 2.094,
|
913 |
+
"step": 128
|
914 |
+
},
|
915 |
+
{
|
916 |
+
"epoch": 0.1708156779661017,
|
917 |
+
"grad_norm": 3.78125,
|
918 |
+
"learning_rate": 9.607786187162234e-06,
|
919 |
+
"loss": 2.1253,
|
920 |
+
"step": 129
|
921 |
+
},
|
922 |
+
{
|
923 |
+
"epoch": 0.1721398305084746,
|
924 |
+
"grad_norm": 4.40625,
|
925 |
+
"learning_rate": 9.599236405901715e-06,
|
926 |
+
"loss": 2.2173,
|
927 |
+
"step": 130
|
928 |
+
},
|
929 |
+
{
|
930 |
+
"epoch": 0.17346398305084745,
|
931 |
+
"grad_norm": 3.90625,
|
932 |
+
"learning_rate": 9.590598327534563e-06,
|
933 |
+
"loss": 2.0337,
|
934 |
+
"step": 131
|
935 |
+
},
|
936 |
+
{
|
937 |
+
"epoch": 0.17478813559322035,
|
938 |
+
"grad_norm": 4.0625,
|
939 |
+
"learning_rate": 9.581872117896423e-06,
|
940 |
+
"loss": 2.0791,
|
941 |
+
"step": 132
|
942 |
+
},
|
943 |
+
{
|
944 |
+
"epoch": 0.1761122881355932,
|
945 |
+
"grad_norm": 3.859375,
|
946 |
+
"learning_rate": 9.573057944514897e-06,
|
947 |
+
"loss": 2.0358,
|
948 |
+
"step": 133
|
949 |
+
},
|
950 |
+
{
|
951 |
+
"epoch": 0.1774364406779661,
|
952 |
+
"grad_norm": 4.28125,
|
953 |
+
"learning_rate": 9.56415597660634e-06,
|
954 |
+
"loss": 1.8235,
|
955 |
+
"step": 134
|
956 |
+
},
|
957 |
+
{
|
958 |
+
"epoch": 0.178760593220339,
|
959 |
+
"grad_norm": 4.46875,
|
960 |
+
"learning_rate": 9.555166385072599e-06,
|
961 |
+
"loss": 2.154,
|
962 |
+
"step": 135
|
963 |
+
},
|
964 |
+
{
|
965 |
+
"epoch": 0.18008474576271186,
|
966 |
+
"grad_norm": 3.953125,
|
967 |
+
"learning_rate": 9.546089342497743e-06,
|
968 |
+
"loss": 2.1079,
|
969 |
+
"step": 136
|
970 |
+
},
|
971 |
+
{
|
972 |
+
"epoch": 0.18140889830508475,
|
973 |
+
"grad_norm": 3.84375,
|
974 |
+
"learning_rate": 9.536925023144742e-06,
|
975 |
+
"loss": 2.1117,
|
976 |
+
"step": 137
|
977 |
+
},
|
978 |
+
{
|
979 |
+
"epoch": 0.18273305084745764,
|
980 |
+
"grad_norm": 4.0625,
|
981 |
+
"learning_rate": 9.527673602952123e-06,
|
982 |
+
"loss": 2.0338,
|
983 |
+
"step": 138
|
984 |
+
},
|
985 |
+
{
|
986 |
+
"epoch": 0.1840572033898305,
|
987 |
+
"grad_norm": 4.09375,
|
988 |
+
"learning_rate": 9.518335259530594e-06,
|
989 |
+
"loss": 2.2235,
|
990 |
+
"step": 139
|
991 |
+
},
|
992 |
+
{
|
993 |
+
"epoch": 0.1853813559322034,
|
994 |
+
"grad_norm": 4.84375,
|
995 |
+
"learning_rate": 9.508910172159635e-06,
|
996 |
+
"loss": 1.9275,
|
997 |
+
"step": 140
|
998 |
+
},
|
999 |
+
{
|
1000 |
+
"epoch": 0.18670550847457626,
|
1001 |
+
"grad_norm": 4.25,
|
1002 |
+
"learning_rate": 9.499398521784051e-06,
|
1003 |
+
"loss": 2.0549,
|
1004 |
+
"step": 141
|
1005 |
+
},
|
1006 |
+
{
|
1007 |
+
"epoch": 0.18802966101694915,
|
1008 |
+
"grad_norm": 4.71875,
|
1009 |
+
"learning_rate": 9.489800491010507e-06,
|
1010 |
+
"loss": 1.9433,
|
1011 |
+
"step": 142
|
1012 |
+
},
|
1013 |
+
{
|
1014 |
+
"epoch": 0.18935381355932204,
|
1015 |
+
"grad_norm": 3.96875,
|
1016 |
+
"learning_rate": 9.48011626410401e-06,
|
1017 |
+
"loss": 2.2499,
|
1018 |
+
"step": 143
|
1019 |
+
},
|
1020 |
+
{
|
1021 |
+
"epoch": 0.1906779661016949,
|
1022 |
+
"grad_norm": 3.8125,
|
1023 |
+
"learning_rate": 9.470346026984387e-06,
|
1024 |
+
"loss": 2.1125,
|
1025 |
+
"step": 144
|
1026 |
+
},
|
1027 |
+
{
|
1028 |
+
"epoch": 0.1920021186440678,
|
1029 |
+
"grad_norm": 4.34375,
|
1030 |
+
"learning_rate": 9.4604899672227e-06,
|
1031 |
+
"loss": 2.1017,
|
1032 |
+
"step": 145
|
1033 |
+
},
|
1034 |
+
{
|
1035 |
+
"epoch": 0.1933262711864407,
|
1036 |
+
"grad_norm": 4.09375,
|
1037 |
+
"learning_rate": 9.450548274037652e-06,
|
1038 |
+
"loss": 2.038,
|
1039 |
+
"step": 146
|
1040 |
+
},
|
1041 |
+
{
|
1042 |
+
"epoch": 0.19465042372881355,
|
1043 |
+
"grad_norm": 4.375,
|
1044 |
+
"learning_rate": 9.440521138291962e-06,
|
1045 |
+
"loss": 2.1801,
|
1046 |
+
"step": 147
|
1047 |
+
},
|
1048 |
+
{
|
1049 |
+
"epoch": 0.19597457627118645,
|
1050 |
+
"grad_norm": 3.734375,
|
1051 |
+
"learning_rate": 9.430408752488687e-06,
|
1052 |
+
"loss": 2.1859,
|
1053 |
+
"step": 148
|
1054 |
+
},
|
1055 |
+
{
|
1056 |
+
"epoch": 0.1972987288135593,
|
1057 |
+
"grad_norm": 4.34375,
|
1058 |
+
"learning_rate": 9.420211310767534e-06,
|
1059 |
+
"loss": 2.074,
|
1060 |
+
"step": 149
|
1061 |
+
},
|
1062 |
+
{
|
1063 |
+
"epoch": 0.1986228813559322,
|
1064 |
+
"grad_norm": 4.8125,
|
1065 |
+
"learning_rate": 9.409929008901126e-06,
|
1066 |
+
"loss": 2.067,
|
1067 |
+
"step": 150
|
1068 |
+
},
|
1069 |
+
{
|
1070 |
+
"epoch": 0.1999470338983051,
|
1071 |
+
"grad_norm": 3.671875,
|
1072 |
+
"learning_rate": 9.399562044291261e-06,
|
1073 |
+
"loss": 1.9712,
|
1074 |
+
"step": 151
|
1075 |
+
},
|
1076 |
+
{
|
1077 |
+
"epoch": 0.20127118644067796,
|
1078 |
+
"grad_norm": 3.96875,
|
1079 |
+
"learning_rate": 9.389110615965102e-06,
|
1080 |
+
"loss": 2.0511,
|
1081 |
+
"step": 152
|
1082 |
+
},
|
1083 |
+
{
|
1084 |
+
"epoch": 0.20259533898305085,
|
1085 |
+
"grad_norm": 4.0,
|
1086 |
+
"learning_rate": 9.378574924571362e-06,
|
1087 |
+
"loss": 2.0218,
|
1088 |
+
"step": 153
|
1089 |
+
},
|
1090 |
+
{
|
1091 |
+
"epoch": 0.20391949152542374,
|
1092 |
+
"grad_norm": 4.09375,
|
1093 |
+
"learning_rate": 9.367955172376462e-06,
|
1094 |
+
"loss": 1.9664,
|
1095 |
+
"step": 154
|
1096 |
+
},
|
1097 |
+
{
|
1098 |
+
"epoch": 0.2052436440677966,
|
1099 |
+
"grad_norm": 3.859375,
|
1100 |
+
"learning_rate": 9.35725156326063e-06,
|
1101 |
+
"loss": 2.0343,
|
1102 |
+
"step": 155
|
1103 |
+
},
|
1104 |
+
{
|
1105 |
+
"epoch": 0.2065677966101695,
|
1106 |
+
"grad_norm": 3.984375,
|
1107 |
+
"learning_rate": 9.346464302714008e-06,
|
1108 |
+
"loss": 2.2163,
|
1109 |
+
"step": 156
|
1110 |
+
},
|
1111 |
+
{
|
1112 |
+
"epoch": 0.20789194915254236,
|
1113 |
+
"grad_norm": 3.609375,
|
1114 |
+
"learning_rate": 9.335593597832686e-06,
|
1115 |
+
"loss": 2.2098,
|
1116 |
+
"step": 157
|
1117 |
+
},
|
1118 |
+
{
|
1119 |
+
"epoch": 0.20921610169491525,
|
1120 |
+
"grad_norm": 3.90625,
|
1121 |
+
"learning_rate": 9.324639657314742e-06,
|
1122 |
+
"loss": 2.0961,
|
1123 |
+
"step": 158
|
1124 |
+
},
|
1125 |
+
{
|
1126 |
+
"epoch": 0.21054025423728814,
|
1127 |
+
"grad_norm": 3.984375,
|
1128 |
+
"learning_rate": 9.313602691456224e-06,
|
1129 |
+
"loss": 2.1141,
|
1130 |
+
"step": 159
|
1131 |
+
},
|
1132 |
+
{
|
1133 |
+
"epoch": 0.211864406779661,
|
1134 |
+
"grad_norm": 3.96875,
|
1135 |
+
"learning_rate": 9.302482912147126e-06,
|
1136 |
+
"loss": 2.0155,
|
1137 |
+
"step": 160
|
1138 |
+
},
|
1139 |
+
{
|
1140 |
+
"epoch": 0.2131885593220339,
|
1141 |
+
"grad_norm": 3.953125,
|
1142 |
+
"learning_rate": 9.291280532867301e-06,
|
1143 |
+
"loss": 1.9736,
|
1144 |
+
"step": 161
|
1145 |
+
},
|
1146 |
+
{
|
1147 |
+
"epoch": 0.2145127118644068,
|
1148 |
+
"grad_norm": 3.734375,
|
1149 |
+
"learning_rate": 9.279995768682383e-06,
|
1150 |
+
"loss": 2.0853,
|
1151 |
+
"step": 162
|
1152 |
+
},
|
1153 |
+
{
|
1154 |
+
"epoch": 0.21583686440677965,
|
1155 |
+
"grad_norm": 4.125,
|
1156 |
+
"learning_rate": 9.268628836239646e-06,
|
1157 |
+
"loss": 2.1189,
|
1158 |
+
"step": 163
|
1159 |
+
},
|
1160 |
+
{
|
1161 |
+
"epoch": 0.21716101694915255,
|
1162 |
+
"grad_norm": 3.796875,
|
1163 |
+
"learning_rate": 9.257179953763846e-06,
|
1164 |
+
"loss": 2.0597,
|
1165 |
+
"step": 164
|
1166 |
+
},
|
1167 |
+
{
|
1168 |
+
"epoch": 0.2184851694915254,
|
1169 |
+
"grad_norm": 4.21875,
|
1170 |
+
"learning_rate": 9.245649341053033e-06,
|
1171 |
+
"loss": 2.0406,
|
1172 |
+
"step": 165
|
1173 |
+
},
|
1174 |
+
{
|
1175 |
+
"epoch": 0.2198093220338983,
|
1176 |
+
"grad_norm": 3.96875,
|
1177 |
+
"learning_rate": 9.234037219474332e-06,
|
1178 |
+
"loss": 2.0314,
|
1179 |
+
"step": 166
|
1180 |
+
},
|
1181 |
+
{
|
1182 |
+
"epoch": 0.2211334745762712,
|
1183 |
+
"grad_norm": 4.0,
|
1184 |
+
"learning_rate": 9.222343811959694e-06,
|
1185 |
+
"loss": 2.1392,
|
1186 |
+
"step": 167
|
1187 |
+
},
|
1188 |
+
{
|
1189 |
+
"epoch": 0.22245762711864406,
|
1190 |
+
"grad_norm": 3.78125,
|
1191 |
+
"learning_rate": 9.21056934300161e-06,
|
1192 |
+
"loss": 2.0291,
|
1193 |
+
"step": 168
|
1194 |
+
},
|
1195 |
+
{
|
1196 |
+
"epoch": 0.22378177966101695,
|
1197 |
+
"grad_norm": 3.78125,
|
1198 |
+
"learning_rate": 9.198714038648811e-06,
|
1199 |
+
"loss": 2.1251,
|
1200 |
+
"step": 169
|
1201 |
+
},
|
1202 |
+
{
|
1203 |
+
"epoch": 0.22510593220338984,
|
1204 |
+
"grad_norm": 4.25,
|
1205 |
+
"learning_rate": 9.186778126501916e-06,
|
1206 |
+
"loss": 1.9912,
|
1207 |
+
"step": 170
|
1208 |
+
},
|
1209 |
+
{
|
1210 |
+
"epoch": 0.2264300847457627,
|
1211 |
+
"grad_norm": 4.0,
|
1212 |
+
"learning_rate": 9.17476183570908e-06,
|
1213 |
+
"loss": 2.0754,
|
1214 |
+
"step": 171
|
1215 |
+
},
|
1216 |
+
{
|
1217 |
+
"epoch": 0.2277542372881356,
|
1218 |
+
"grad_norm": 4.15625,
|
1219 |
+
"learning_rate": 9.162665396961573e-06,
|
1220 |
+
"loss": 2.0376,
|
1221 |
+
"step": 172
|
1222 |
+
},
|
1223 |
+
{
|
1224 |
+
"epoch": 0.22907838983050846,
|
1225 |
+
"grad_norm": 4.15625,
|
1226 |
+
"learning_rate": 9.150489042489368e-06,
|
1227 |
+
"loss": 1.984,
|
1228 |
+
"step": 173
|
1229 |
+
},
|
1230 |
+
{
|
1231 |
+
"epoch": 0.23040254237288135,
|
1232 |
+
"grad_norm": 3.984375,
|
1233 |
+
"learning_rate": 9.138233006056679e-06,
|
1234 |
+
"loss": 2.0155,
|
1235 |
+
"step": 174
|
1236 |
+
},
|
1237 |
+
{
|
1238 |
+
"epoch": 0.23172669491525424,
|
1239 |
+
"grad_norm": 4.125,
|
1240 |
+
"learning_rate": 9.125897522957461e-06,
|
1241 |
+
"loss": 2.1034,
|
1242 |
+
"step": 175
|
1243 |
+
},
|
1244 |
+
{
|
1245 |
+
"epoch": 0.2330508474576271,
|
1246 |
+
"grad_norm": 3.84375,
|
1247 |
+
"learning_rate": 9.113482830010918e-06,
|
1248 |
+
"loss": 2.1072,
|
1249 |
+
"step": 176
|
1250 |
+
},
|
1251 |
+
{
|
1252 |
+
"epoch": 0.234375,
|
1253 |
+
"grad_norm": 5.28125,
|
1254 |
+
"learning_rate": 9.100989165556928e-06,
|
1255 |
+
"loss": 2.1256,
|
1256 |
+
"step": 177
|
1257 |
+
},
|
1258 |
+
{
|
1259 |
+
"epoch": 0.2356991525423729,
|
1260 |
+
"grad_norm": 4.3125,
|
1261 |
+
"learning_rate": 9.088416769451485e-06,
|
1262 |
+
"loss": 2.0479,
|
1263 |
+
"step": 178
|
1264 |
+
},
|
1265 |
+
{
|
1266 |
+
"epoch": 0.23702330508474576,
|
1267 |
+
"grad_norm": 4.0,
|
1268 |
+
"learning_rate": 9.075765883062093e-06,
|
1269 |
+
"loss": 2.075,
|
1270 |
+
"step": 179
|
1271 |
+
},
|
1272 |
+
{
|
1273 |
+
"epoch": 0.23834745762711865,
|
1274 |
+
"grad_norm": 3.8125,
|
1275 |
+
"learning_rate": 9.063036749263127e-06,
|
1276 |
+
"loss": 1.9578,
|
1277 |
+
"step": 180
|
1278 |
+
},
|
1279 |
+
{
|
1280 |
+
"epoch": 0.23967161016949154,
|
1281 |
+
"grad_norm": 3.796875,
|
1282 |
+
"learning_rate": 9.050229612431168e-06,
|
1283 |
+
"loss": 2.2268,
|
1284 |
+
"step": 181
|
1285 |
+
},
|
1286 |
+
{
|
1287 |
+
"epoch": 0.2409957627118644,
|
1288 |
+
"grad_norm": 4.0625,
|
1289 |
+
"learning_rate": 9.037344718440321e-06,
|
1290 |
+
"loss": 2.2065,
|
1291 |
+
"step": 182
|
1292 |
+
},
|
1293 |
+
{
|
1294 |
+
"epoch": 0.2423199152542373,
|
1295 |
+
"grad_norm": 4.75,
|
1296 |
+
"learning_rate": 9.02438231465749e-06,
|
1297 |
+
"loss": 1.9338,
|
1298 |
+
"step": 183
|
1299 |
+
},
|
1300 |
+
{
|
1301 |
+
"epoch": 0.24364406779661016,
|
1302 |
+
"grad_norm": 4.0625,
|
1303 |
+
"learning_rate": 9.011342649937623e-06,
|
1304 |
+
"loss": 2.0992,
|
1305 |
+
"step": 184
|
1306 |
+
},
|
1307 |
+
{
|
1308 |
+
"epoch": 0.24496822033898305,
|
1309 |
+
"grad_norm": 4.625,
|
1310 |
+
"learning_rate": 8.99822597461894e-06,
|
1311 |
+
"loss": 2.0273,
|
1312 |
+
"step": 185
|
1313 |
+
},
|
1314 |
+
{
|
1315 |
+
"epoch": 0.24629237288135594,
|
1316 |
+
"grad_norm": 4.59375,
|
1317 |
+
"learning_rate": 8.985032540518133e-06,
|
1318 |
+
"loss": 2.0654,
|
1319 |
+
"step": 186
|
1320 |
+
},
|
1321 |
+
{
|
1322 |
+
"epoch": 0.2476165254237288,
|
1323 |
+
"grad_norm": 4.34375,
|
1324 |
+
"learning_rate": 8.971762600925519e-06,
|
1325 |
+
"loss": 2.1202,
|
1326 |
+
"step": 187
|
1327 |
+
},
|
1328 |
+
{
|
1329 |
+
"epoch": 0.2489406779661017,
|
1330 |
+
"grad_norm": 3.75,
|
1331 |
+
"learning_rate": 8.958416410600188e-06,
|
1332 |
+
"loss": 2.0589,
|
1333 |
+
"step": 188
|
1334 |
+
},
|
1335 |
+
{
|
1336 |
+
"epoch": 0.2502648305084746,
|
1337 |
+
"grad_norm": 4.0625,
|
1338 |
+
"learning_rate": 8.944994225765104e-06,
|
1339 |
+
"loss": 1.9044,
|
1340 |
+
"step": 189
|
1341 |
+
},
|
1342 |
+
{
|
1343 |
+
"epoch": 0.2515889830508475,
|
1344 |
+
"grad_norm": 4.375,
|
1345 |
+
"learning_rate": 8.931496304102192e-06,
|
1346 |
+
"loss": 2.0083,
|
1347 |
+
"step": 190
|
1348 |
+
},
|
1349 |
+
{
|
1350 |
+
"epoch": 0.2529131355932203,
|
1351 |
+
"grad_norm": 3.859375,
|
1352 |
+
"learning_rate": 8.917922904747385e-06,
|
1353 |
+
"loss": 1.9487,
|
1354 |
+
"step": 191
|
1355 |
+
},
|
1356 |
+
{
|
1357 |
+
"epoch": 0.2542372881355932,
|
1358 |
+
"grad_norm": 3.734375,
|
1359 |
+
"learning_rate": 8.904274288285657e-06,
|
1360 |
+
"loss": 1.9682,
|
1361 |
+
"step": 192
|
1362 |
+
},
|
1363 |
+
{
|
1364 |
+
"epoch": 0.2555614406779661,
|
1365 |
+
"grad_norm": 4.21875,
|
1366 |
+
"learning_rate": 8.890550716746013e-06,
|
1367 |
+
"loss": 1.8554,
|
1368 |
+
"step": 193
|
1369 |
+
},
|
1370 |
+
{
|
1371 |
+
"epoch": 0.256885593220339,
|
1372 |
+
"grad_norm": 3.921875,
|
1373 |
+
"learning_rate": 8.876752453596462e-06,
|
1374 |
+
"loss": 2.0785,
|
1375 |
+
"step": 194
|
1376 |
+
},
|
1377 |
+
{
|
1378 |
+
"epoch": 0.2582097457627119,
|
1379 |
+
"grad_norm": 3.796875,
|
1380 |
+
"learning_rate": 8.862879763738962e-06,
|
1381 |
+
"loss": 2.0384,
|
1382 |
+
"step": 195
|
1383 |
+
},
|
1384 |
+
{
|
1385 |
+
"epoch": 0.2595338983050847,
|
1386 |
+
"grad_norm": 3.828125,
|
1387 |
+
"learning_rate": 8.84893291350432e-06,
|
1388 |
+
"loss": 2.163,
|
1389 |
+
"step": 196
|
1390 |
+
},
|
1391 |
+
{
|
1392 |
+
"epoch": 0.2608580508474576,
|
1393 |
+
"grad_norm": 4.125,
|
1394 |
+
"learning_rate": 8.834912170647102e-06,
|
1395 |
+
"loss": 2.0237,
|
1396 |
+
"step": 197
|
1397 |
+
},
|
1398 |
+
{
|
1399 |
+
"epoch": 0.2621822033898305,
|
1400 |
+
"grad_norm": 4.0625,
|
1401 |
+
"learning_rate": 8.820817804340471e-06,
|
1402 |
+
"loss": 2.0215,
|
1403 |
+
"step": 198
|
1404 |
+
},
|
1405 |
+
{
|
1406 |
+
"epoch": 0.2635063559322034,
|
1407 |
+
"grad_norm": 3.671875,
|
1408 |
+
"learning_rate": 8.806650085171036e-06,
|
1409 |
+
"loss": 2.0454,
|
1410 |
+
"step": 199
|
1411 |
+
},
|
1412 |
+
{
|
1413 |
+
"epoch": 0.2648305084745763,
|
1414 |
+
"grad_norm": 3.78125,
|
1415 |
+
"learning_rate": 8.792409285133644e-06,
|
1416 |
+
"loss": 2.0006,
|
1417 |
+
"step": 200
|
1418 |
+
},
|
1419 |
+
{
|
1420 |
+
"epoch": 0.2648305084745763,
|
1421 |
+
"eval_AskDoctor-Chinese_loss": 2.021162986755371,
|
1422 |
+
"eval_AskDoctor-Chinese_runtime": 16.0254,
|
1423 |
+
"eval_AskDoctor-Chinese_samples_per_second": 1.872,
|
1424 |
+
"eval_AskDoctor-Chinese_steps_per_second": 1.872,
|
1425 |
+
"step": 200
|
1426 |
+
},
|
1427 |
+
{
|
1428 |
+
"epoch": 0.2661546610169492,
|
1429 |
+
"grad_norm": 3.921875,
|
1430 |
+
"learning_rate": 8.778095677626164e-06,
|
1431 |
+
"loss": 1.9454,
|
1432 |
+
"step": 201
|
1433 |
+
},
|
1434 |
+
{
|
1435 |
+
"epoch": 0.267478813559322,
|
1436 |
+
"grad_norm": 3.765625,
|
1437 |
+
"learning_rate": 8.763709537444241e-06,
|
1438 |
+
"loss": 2.1055,
|
1439 |
+
"step": 202
|
1440 |
+
},
|
1441 |
+
{
|
1442 |
+
"epoch": 0.2688029661016949,
|
1443 |
+
"grad_norm": 4.59375,
|
1444 |
+
"learning_rate": 8.749251140776016e-06,
|
1445 |
+
"loss": 1.9506,
|
1446 |
+
"step": 203
|
1447 |
+
},
|
1448 |
+
{
|
1449 |
+
"epoch": 0.2701271186440678,
|
1450 |
+
"grad_norm": 3.9375,
|
1451 |
+
"learning_rate": 8.734720765196826e-06,
|
1452 |
+
"loss": 2.2382,
|
1453 |
+
"step": 204
|
1454 |
+
},
|
1455 |
+
{
|
1456 |
+
"epoch": 0.2714512711864407,
|
1457 |
+
"grad_norm": 4.96875,
|
1458 |
+
"learning_rate": 8.720118689663872e-06,
|
1459 |
+
"loss": 1.9558,
|
1460 |
+
"step": 205
|
1461 |
+
},
|
1462 |
+
{
|
1463 |
+
"epoch": 0.2727754237288136,
|
1464 |
+
"grad_norm": 3.84375,
|
1465 |
+
"learning_rate": 8.705445194510868e-06,
|
1466 |
+
"loss": 2.0589,
|
1467 |
+
"step": 206
|
1468 |
+
},
|
1469 |
+
{
|
1470 |
+
"epoch": 0.2740995762711864,
|
1471 |
+
"grad_norm": 4.84375,
|
1472 |
+
"learning_rate": 8.690700561442658e-06,
|
1473 |
+
"loss": 1.8821,
|
1474 |
+
"step": 207
|
1475 |
+
},
|
1476 |
+
{
|
1477 |
+
"epoch": 0.2754237288135593,
|
1478 |
+
"grad_norm": 3.84375,
|
1479 |
+
"learning_rate": 8.675885073529802e-06,
|
1480 |
+
"loss": 1.9863,
|
1481 |
+
"step": 208
|
1482 |
+
},
|
1483 |
+
{
|
1484 |
+
"epoch": 0.2767478813559322,
|
1485 |
+
"grad_norm": 3.84375,
|
1486 |
+
"learning_rate": 8.660999015203152e-06,
|
1487 |
+
"loss": 2.0464,
|
1488 |
+
"step": 209
|
1489 |
+
},
|
1490 |
+
{
|
1491 |
+
"epoch": 0.2780720338983051,
|
1492 |
+
"grad_norm": 3.9375,
|
1493 |
+
"learning_rate": 8.64604267224838e-06,
|
1494 |
+
"loss": 2.1284,
|
1495 |
+
"step": 210
|
1496 |
+
},
|
1497 |
+
{
|
1498 |
+
"epoch": 0.279396186440678,
|
1499 |
+
"grad_norm": 4.21875,
|
1500 |
+
"learning_rate": 8.631016331800501e-06,
|
1501 |
+
"loss": 1.9782,
|
1502 |
+
"step": 211
|
1503 |
+
},
|
1504 |
+
{
|
1505 |
+
"epoch": 0.2807203389830508,
|
1506 |
+
"grad_norm": 3.84375,
|
1507 |
+
"learning_rate": 8.615920282338355e-06,
|
1508 |
+
"loss": 2.0504,
|
1509 |
+
"step": 212
|
1510 |
+
},
|
1511 |
+
{
|
1512 |
+
"epoch": 0.2820444915254237,
|
1513 |
+
"grad_norm": 3.859375,
|
1514 |
+
"learning_rate": 8.600754813679072e-06,
|
1515 |
+
"loss": 2.0384,
|
1516 |
+
"step": 213
|
1517 |
+
},
|
1518 |
+
{
|
1519 |
+
"epoch": 0.2833686440677966,
|
1520 |
+
"grad_norm": 4.1875,
|
1521 |
+
"learning_rate": 8.585520216972503e-06,
|
1522 |
+
"loss": 2.0057,
|
1523 |
+
"step": 214
|
1524 |
+
},
|
1525 |
+
{
|
1526 |
+
"epoch": 0.2846927966101695,
|
1527 |
+
"grad_norm": 3.765625,
|
1528 |
+
"learning_rate": 8.570216784695637e-06,
|
1529 |
+
"loss": 2.1141,
|
1530 |
+
"step": 215
|
1531 |
+
},
|
1532 |
+
{
|
1533 |
+
"epoch": 0.2860169491525424,
|
1534 |
+
"grad_norm": 4.1875,
|
1535 |
+
"learning_rate": 8.55484481064698e-06,
|
1536 |
+
"loss": 1.9975,
|
1537 |
+
"step": 216
|
1538 |
+
},
|
1539 |
+
{
|
1540 |
+
"epoch": 0.2873411016949153,
|
1541 |
+
"grad_norm": 4.03125,
|
1542 |
+
"learning_rate": 8.539404589940924e-06,
|
1543 |
+
"loss": 1.9758,
|
1544 |
+
"step": 217
|
1545 |
+
},
|
1546 |
+
{
|
1547 |
+
"epoch": 0.2886652542372881,
|
1548 |
+
"grad_norm": 6.0625,
|
1549 |
+
"learning_rate": 8.52389641900206e-06,
|
1550 |
+
"loss": 1.8848,
|
1551 |
+
"step": 218
|
1552 |
+
},
|
1553 |
+
{
|
1554 |
+
"epoch": 0.289989406779661,
|
1555 |
+
"grad_norm": 3.734375,
|
1556 |
+
"learning_rate": 8.50832059555952e-06,
|
1557 |
+
"loss": 2.09,
|
1558 |
+
"step": 219
|
1559 |
+
},
|
1560 |
+
{
|
1561 |
+
"epoch": 0.2913135593220339,
|
1562 |
+
"grad_norm": 3.984375,
|
1563 |
+
"learning_rate": 8.492677418641231e-06,
|
1564 |
+
"loss": 1.824,
|
1565 |
+
"step": 220
|
1566 |
+
},
|
1567 |
+
{
|
1568 |
+
"epoch": 0.2926377118644068,
|
1569 |
+
"grad_norm": 3.90625,
|
1570 |
+
"learning_rate": 8.476967188568187e-06,
|
1571 |
+
"loss": 2.1443,
|
1572 |
+
"step": 221
|
1573 |
+
},
|
1574 |
+
{
|
1575 |
+
"epoch": 0.2939618644067797,
|
1576 |
+
"grad_norm": 3.796875,
|
1577 |
+
"learning_rate": 8.461190206948691e-06,
|
1578 |
+
"loss": 2.1238,
|
1579 |
+
"step": 222
|
1580 |
+
},
|
1581 |
+
{
|
1582 |
+
"epoch": 0.2952860169491525,
|
1583 |
+
"grad_norm": 4.0625,
|
1584 |
+
"learning_rate": 8.445346776672546e-06,
|
1585 |
+
"loss": 2.1187,
|
1586 |
+
"step": 223
|
1587 |
+
},
|
1588 |
+
{
|
1589 |
+
"epoch": 0.2966101694915254,
|
1590 |
+
"grad_norm": 3.65625,
|
1591 |
+
"learning_rate": 8.429437201905254e-06,
|
1592 |
+
"loss": 2.2054,
|
1593 |
+
"step": 224
|
1594 |
+
},
|
1595 |
+
{
|
1596 |
+
"epoch": 0.2979343220338983,
|
1597 |
+
"grad_norm": 3.5,
|
1598 |
+
"learning_rate": 8.413461788082175e-06,
|
1599 |
+
"loss": 2.0788,
|
1600 |
+
"step": 225
|
1601 |
+
},
|
1602 |
+
{
|
1603 |
+
"epoch": 0.2992584745762712,
|
1604 |
+
"grad_norm": 3.5625,
|
1605 |
+
"learning_rate": 8.39742084190266e-06,
|
1606 |
+
"loss": 2.1441,
|
1607 |
+
"step": 226
|
1608 |
+
},
|
1609 |
+
{
|
1610 |
+
"epoch": 0.3005826271186441,
|
1611 |
+
"grad_norm": 7.3125,
|
1612 |
+
"learning_rate": 8.38131467132416e-06,
|
1613 |
+
"loss": 1.9429,
|
1614 |
+
"step": 227
|
1615 |
+
},
|
1616 |
+
{
|
1617 |
+
"epoch": 0.3019067796610169,
|
1618 |
+
"grad_norm": 7.375,
|
1619 |
+
"learning_rate": 8.365143585556326e-06,
|
1620 |
+
"loss": 1.9466,
|
1621 |
+
"step": 228
|
1622 |
+
},
|
1623 |
+
{
|
1624 |
+
"epoch": 0.3032309322033898,
|
1625 |
+
"grad_norm": 4.625,
|
1626 |
+
"learning_rate": 8.348907895055055e-06,
|
1627 |
+
"loss": 1.9793,
|
1628 |
+
"step": 229
|
1629 |
+
},
|
1630 |
+
{
|
1631 |
+
"epoch": 0.3045550847457627,
|
1632 |
+
"grad_norm": 4.09375,
|
1633 |
+
"learning_rate": 8.332607911516545e-06,
|
1634 |
+
"loss": 2.0855,
|
1635 |
+
"step": 230
|
1636 |
+
},
|
1637 |
+
{
|
1638 |
+
"epoch": 0.3058792372881356,
|
1639 |
+
"grad_norm": 4.125,
|
1640 |
+
"learning_rate": 8.316243947871306e-06,
|
1641 |
+
"loss": 2.1595,
|
1642 |
+
"step": 231
|
1643 |
+
},
|
1644 |
+
{
|
1645 |
+
"epoch": 0.3072033898305085,
|
1646 |
+
"grad_norm": 3.953125,
|
1647 |
+
"learning_rate": 8.299816318278146e-06,
|
1648 |
+
"loss": 1.9467,
|
1649 |
+
"step": 232
|
1650 |
+
},
|
1651 |
+
{
|
1652 |
+
"epoch": 0.3085275423728814,
|
1653 |
+
"grad_norm": 3.75,
|
1654 |
+
"learning_rate": 8.283325338118154e-06,
|
1655 |
+
"loss": 1.9687,
|
1656 |
+
"step": 233
|
1657 |
+
},
|
1658 |
+
{
|
1659 |
+
"epoch": 0.3098516949152542,
|
1660 |
+
"grad_norm": 3.875,
|
1661 |
+
"learning_rate": 8.266771323988624e-06,
|
1662 |
+
"loss": 2.0397,
|
1663 |
+
"step": 234
|
1664 |
+
},
|
1665 |
+
{
|
1666 |
+
"epoch": 0.3111758474576271,
|
1667 |
+
"grad_norm": 3.890625,
|
1668 |
+
"learning_rate": 8.250154593697002e-06,
|
1669 |
+
"loss": 2.1581,
|
1670 |
+
"step": 235
|
1671 |
+
},
|
1672 |
+
{
|
1673 |
+
"epoch": 0.3125,
|
1674 |
+
"grad_norm": 3.640625,
|
1675 |
+
"learning_rate": 8.233475466254766e-06,
|
1676 |
+
"loss": 1.9687,
|
1677 |
+
"step": 236
|
1678 |
+
},
|
1679 |
+
{
|
1680 |
+
"epoch": 0.3138241525423729,
|
1681 |
+
"grad_norm": 3.828125,
|
1682 |
+
"learning_rate": 8.216734261871305e-06,
|
1683 |
+
"loss": 2.081,
|
1684 |
+
"step": 237
|
1685 |
+
},
|
1686 |
+
{
|
1687 |
+
"epoch": 0.3151483050847458,
|
1688 |
+
"grad_norm": 3.984375,
|
1689 |
+
"learning_rate": 8.199931301947782e-06,
|
1690 |
+
"loss": 1.9637,
|
1691 |
+
"step": 238
|
1692 |
+
},
|
1693 |
+
{
|
1694 |
+
"epoch": 0.3164724576271186,
|
1695 |
+
"grad_norm": 6.96875,
|
1696 |
+
"learning_rate": 8.183066909070946e-06,
|
1697 |
+
"loss": 1.9271,
|
1698 |
+
"step": 239
|
1699 |
+
},
|
1700 |
+
{
|
1701 |
+
"epoch": 0.3177966101694915,
|
1702 |
+
"grad_norm": 3.9375,
|
1703 |
+
"learning_rate": 8.16614140700696e-06,
|
1704 |
+
"loss": 1.9426,
|
1705 |
+
"step": 240
|
1706 |
+
},
|
1707 |
+
{
|
1708 |
+
"epoch": 0.3191207627118644,
|
1709 |
+
"grad_norm": 4.03125,
|
1710 |
+
"learning_rate": 8.149155120695163e-06,
|
1711 |
+
"loss": 1.8951,
|
1712 |
+
"step": 241
|
1713 |
+
},
|
1714 |
+
{
|
1715 |
+
"epoch": 0.3204449152542373,
|
1716 |
+
"grad_norm": 3.84375,
|
1717 |
+
"learning_rate": 8.132108376241849e-06,
|
1718 |
+
"loss": 2.1779,
|
1719 |
+
"step": 242
|
1720 |
+
},
|
1721 |
+
{
|
1722 |
+
"epoch": 0.3217690677966102,
|
1723 |
+
"grad_norm": 3.921875,
|
1724 |
+
"learning_rate": 8.115001500914e-06,
|
1725 |
+
"loss": 2.1942,
|
1726 |
+
"step": 243
|
1727 |
+
},
|
1728 |
+
{
|
1729 |
+
"epoch": 0.3230932203389831,
|
1730 |
+
"grad_norm": 3.90625,
|
1731 |
+
"learning_rate": 8.097834823133002e-06,
|
1732 |
+
"loss": 1.9011,
|
1733 |
+
"step": 244
|
1734 |
+
},
|
1735 |
+
{
|
1736 |
+
"epoch": 0.3244173728813559,
|
1737 |
+
"grad_norm": 4.15625,
|
1738 |
+
"learning_rate": 8.08060867246834e-06,
|
1739 |
+
"loss": 1.9409,
|
1740 |
+
"step": 245
|
1741 |
+
},
|
1742 |
+
{
|
1743 |
+
"epoch": 0.3257415254237288,
|
1744 |
+
"grad_norm": 4.96875,
|
1745 |
+
"learning_rate": 8.063323379631274e-06,
|
1746 |
+
"loss": 1.9138,
|
1747 |
+
"step": 246
|
1748 |
+
},
|
1749 |
+
{
|
1750 |
+
"epoch": 0.3270656779661017,
|
1751 |
+
"grad_norm": 3.875,
|
1752 |
+
"learning_rate": 8.045979276468486e-06,
|
1753 |
+
"loss": 2.182,
|
1754 |
+
"step": 247
|
1755 |
+
},
|
1756 |
+
{
|
1757 |
+
"epoch": 0.3283898305084746,
|
1758 |
+
"grad_norm": 3.90625,
|
1759 |
+
"learning_rate": 8.028576695955711e-06,
|
1760 |
+
"loss": 2.0034,
|
1761 |
+
"step": 248
|
1762 |
+
},
|
1763 |
+
{
|
1764 |
+
"epoch": 0.3297139830508475,
|
1765 |
+
"grad_norm": 3.6875,
|
1766 |
+
"learning_rate": 8.011115972191347e-06,
|
1767 |
+
"loss": 2.1779,
|
1768 |
+
"step": 249
|
1769 |
+
},
|
1770 |
+
{
|
1771 |
+
"epoch": 0.3310381355932203,
|
1772 |
+
"grad_norm": 5.25,
|
1773 |
+
"learning_rate": 7.993597440390035e-06,
|
1774 |
+
"loss": 1.8994,
|
1775 |
+
"step": 250
|
1776 |
+
},
|
1777 |
+
{
|
1778 |
+
"epoch": 0.3323622881355932,
|
1779 |
+
"grad_norm": 3.765625,
|
1780 |
+
"learning_rate": 7.976021436876232e-06,
|
1781 |
+
"loss": 2.0865,
|
1782 |
+
"step": 251
|
1783 |
+
},
|
1784 |
+
{
|
1785 |
+
"epoch": 0.3336864406779661,
|
1786 |
+
"grad_norm": 3.90625,
|
1787 |
+
"learning_rate": 7.958388299077739e-06,
|
1788 |
+
"loss": 2.1092,
|
1789 |
+
"step": 252
|
1790 |
+
},
|
1791 |
+
{
|
1792 |
+
"epoch": 0.335010593220339,
|
1793 |
+
"grad_norm": 4.0,
|
1794 |
+
"learning_rate": 7.940698365519246e-06,
|
1795 |
+
"loss": 2.0966,
|
1796 |
+
"step": 253
|
1797 |
+
},
|
1798 |
+
{
|
1799 |
+
"epoch": 0.3363347457627119,
|
1800 |
+
"grad_norm": 3.625,
|
1801 |
+
"learning_rate": 7.92295197581581e-06,
|
1802 |
+
"loss": 2.0216,
|
1803 |
+
"step": 254
|
1804 |
+
},
|
1805 |
+
{
|
1806 |
+
"epoch": 0.3376588983050847,
|
1807 |
+
"grad_norm": 3.796875,
|
1808 |
+
"learning_rate": 7.905149470666348e-06,
|
1809 |
+
"loss": 2.036,
|
1810 |
+
"step": 255
|
1811 |
+
},
|
1812 |
+
{
|
1813 |
+
"epoch": 0.3389830508474576,
|
1814 |
+
"grad_norm": 4.625,
|
1815 |
+
"learning_rate": 7.887291191847098e-06,
|
1816 |
+
"loss": 2.0037,
|
1817 |
+
"step": 256
|
1818 |
+
},
|
1819 |
+
{
|
1820 |
+
"epoch": 0.3403072033898305,
|
1821 |
+
"grad_norm": 4.0625,
|
1822 |
+
"learning_rate": 7.869377482205042e-06,
|
1823 |
+
"loss": 2.0473,
|
1824 |
+
"step": 257
|
1825 |
+
},
|
1826 |
+
{
|
1827 |
+
"epoch": 0.3416313559322034,
|
1828 |
+
"grad_norm": 4.125,
|
1829 |
+
"learning_rate": 7.851408685651342e-06,
|
1830 |
+
"loss": 2.0279,
|
1831 |
+
"step": 258
|
1832 |
+
},
|
1833 |
+
{
|
1834 |
+
"epoch": 0.3429555084745763,
|
1835 |
+
"grad_norm": 3.9375,
|
1836 |
+
"learning_rate": 7.833385147154733e-06,
|
1837 |
+
"loss": 2.1209,
|
1838 |
+
"step": 259
|
1839 |
+
},
|
1840 |
+
{
|
1841 |
+
"epoch": 0.3442796610169492,
|
1842 |
+
"grad_norm": 3.96875,
|
1843 |
+
"learning_rate": 7.815307212734888e-06,
|
1844 |
+
"loss": 2.0669,
|
1845 |
+
"step": 260
|
1846 |
+
},
|
1847 |
+
{
|
1848 |
+
"epoch": 0.345603813559322,
|
1849 |
+
"grad_norm": 3.71875,
|
1850 |
+
"learning_rate": 7.797175229455793e-06,
|
1851 |
+
"loss": 2.033,
|
1852 |
+
"step": 261
|
1853 |
+
},
|
1854 |
+
{
|
1855 |
+
"epoch": 0.3469279661016949,
|
1856 |
+
"grad_norm": 4.46875,
|
1857 |
+
"learning_rate": 7.778989545419068e-06,
|
1858 |
+
"loss": 2.0184,
|
1859 |
+
"step": 262
|
1860 |
+
},
|
1861 |
+
{
|
1862 |
+
"epoch": 0.3482521186440678,
|
1863 |
+
"grad_norm": 3.765625,
|
1864 |
+
"learning_rate": 7.7607505097573e-06,
|
1865 |
+
"loss": 2.2567,
|
1866 |
+
"step": 263
|
1867 |
+
},
|
1868 |
+
{
|
1869 |
+
"epoch": 0.3495762711864407,
|
1870 |
+
"grad_norm": 3.6875,
|
1871 |
+
"learning_rate": 7.742458472627321e-06,
|
1872 |
+
"loss": 2.0145,
|
1873 |
+
"step": 264
|
1874 |
+
},
|
1875 |
+
{
|
1876 |
+
"epoch": 0.3509004237288136,
|
1877 |
+
"grad_norm": 3.953125,
|
1878 |
+
"learning_rate": 7.724113785203506e-06,
|
1879 |
+
"loss": 1.94,
|
1880 |
+
"step": 265
|
1881 |
+
},
|
1882 |
+
{
|
1883 |
+
"epoch": 0.3522245762711864,
|
1884 |
+
"grad_norm": 3.78125,
|
1885 |
+
"learning_rate": 7.705716799671019e-06,
|
1886 |
+
"loss": 2.0266,
|
1887 |
+
"step": 266
|
1888 |
+
},
|
1889 |
+
{
|
1890 |
+
"epoch": 0.3535487288135593,
|
1891 |
+
"grad_norm": 3.953125,
|
1892 |
+
"learning_rate": 7.687267869219052e-06,
|
1893 |
+
"loss": 1.9502,
|
1894 |
+
"step": 267
|
1895 |
+
},
|
1896 |
+
{
|
1897 |
+
"epoch": 0.3548728813559322,
|
1898 |
+
"grad_norm": 3.953125,
|
1899 |
+
"learning_rate": 7.668767348034044e-06,
|
1900 |
+
"loss": 2.1102,
|
1901 |
+
"step": 268
|
1902 |
+
},
|
1903 |
+
{
|
1904 |
+
"epoch": 0.3561970338983051,
|
1905 |
+
"grad_norm": 3.90625,
|
1906 |
+
"learning_rate": 7.650215591292888e-06,
|
1907 |
+
"loss": 1.8979,
|
1908 |
+
"step": 269
|
1909 |
+
},
|
1910 |
+
{
|
1911 |
+
"epoch": 0.357521186440678,
|
1912 |
+
"grad_norm": 4.125,
|
1913 |
+
"learning_rate": 7.631612955156111e-06,
|
1914 |
+
"loss": 1.9134,
|
1915 |
+
"step": 270
|
1916 |
+
},
|
1917 |
+
{
|
1918 |
+
"epoch": 0.3588453389830508,
|
1919 |
+
"grad_norm": 3.84375,
|
1920 |
+
"learning_rate": 7.6129597967610244e-06,
|
1921 |
+
"loss": 2.0089,
|
1922 |
+
"step": 271
|
1923 |
+
},
|
1924 |
+
{
|
1925 |
+
"epoch": 0.3601694915254237,
|
1926 |
+
"grad_norm": 3.890625,
|
1927 |
+
"learning_rate": 7.594256474214883e-06,
|
1928 |
+
"loss": 1.9536,
|
1929 |
+
"step": 272
|
1930 |
+
},
|
1931 |
+
{
|
1932 |
+
"epoch": 0.3614936440677966,
|
1933 |
+
"grad_norm": 3.984375,
|
1934 |
+
"learning_rate": 7.5755033465880024e-06,
|
1935 |
+
"loss": 2.0965,
|
1936 |
+
"step": 273
|
1937 |
+
},
|
1938 |
+
{
|
1939 |
+
"epoch": 0.3628177966101695,
|
1940 |
+
"grad_norm": 4.28125,
|
1941 |
+
"learning_rate": 7.556700773906866e-06,
|
1942 |
+
"loss": 2.0323,
|
1943 |
+
"step": 274
|
1944 |
+
},
|
1945 |
+
{
|
1946 |
+
"epoch": 0.3641419491525424,
|
1947 |
+
"grad_norm": 3.8125,
|
1948 |
+
"learning_rate": 7.537849117147212e-06,
|
1949 |
+
"loss": 2.0372,
|
1950 |
+
"step": 275
|
1951 |
+
},
|
1952 |
+
{
|
1953 |
+
"epoch": 0.3654661016949153,
|
1954 |
+
"grad_norm": 3.640625,
|
1955 |
+
"learning_rate": 7.5189487382271095e-06,
|
1956 |
+
"loss": 2.0669,
|
1957 |
+
"step": 276
|
1958 |
+
},
|
1959 |
+
{
|
1960 |
+
"epoch": 0.3667902542372881,
|
1961 |
+
"grad_norm": 3.703125,
|
1962 |
+
"learning_rate": 7.500000000000001e-06,
|
1963 |
+
"loss": 1.9949,
|
1964 |
+
"step": 277
|
1965 |
+
},
|
1966 |
+
{
|
1967 |
+
"epoch": 0.368114406779661,
|
1968 |
+
"grad_norm": 3.703125,
|
1969 |
+
"learning_rate": 7.481003266247745e-06,
|
1970 |
+
"loss": 2.1448,
|
1971 |
+
"step": 278
|
1972 |
+
},
|
1973 |
+
{
|
1974 |
+
"epoch": 0.3694385593220339,
|
1975 |
+
"grad_norm": 3.90625,
|
1976 |
+
"learning_rate": 7.461958901673625e-06,
|
1977 |
+
"loss": 2.0343,
|
1978 |
+
"step": 279
|
1979 |
+
},
|
1980 |
+
{
|
1981 |
+
"epoch": 0.3707627118644068,
|
1982 |
+
"grad_norm": 4.25,
|
1983 |
+
"learning_rate": 7.4428672718953535e-06,
|
1984 |
+
"loss": 2.0603,
|
1985 |
+
"step": 280
|
1986 |
+
},
|
1987 |
+
{
|
1988 |
+
"epoch": 0.3720868644067797,
|
1989 |
+
"grad_norm": 3.640625,
|
1990 |
+
"learning_rate": 7.4237287434380485e-06,
|
1991 |
+
"loss": 1.9779,
|
1992 |
+
"step": 281
|
1993 |
+
},
|
1994 |
+
{
|
1995 |
+
"epoch": 0.3734110169491525,
|
1996 |
+
"grad_norm": 3.78125,
|
1997 |
+
"learning_rate": 7.404543683727201e-06,
|
1998 |
+
"loss": 2.1302,
|
1999 |
+
"step": 282
|
2000 |
+
},
|
2001 |
+
{
|
2002 |
+
"epoch": 0.3747351694915254,
|
2003 |
+
"grad_norm": 6.15625,
|
2004 |
+
"learning_rate": 7.385312461081616e-06,
|
2005 |
+
"loss": 1.9677,
|
2006 |
+
"step": 283
|
2007 |
+
},
|
2008 |
+
{
|
2009 |
+
"epoch": 0.3760593220338983,
|
2010 |
+
"grad_norm": 7.6875,
|
2011 |
+
"learning_rate": 7.366035444706346e-06,
|
2012 |
+
"loss": 1.969,
|
2013 |
+
"step": 284
|
2014 |
+
},
|
2015 |
+
{
|
2016 |
+
"epoch": 0.3773834745762712,
|
2017 |
+
"grad_norm": 3.953125,
|
2018 |
+
"learning_rate": 7.346713004685602e-06,
|
2019 |
+
"loss": 2.0783,
|
2020 |
+
"step": 285
|
2021 |
+
},
|
2022 |
+
{
|
2023 |
+
"epoch": 0.3787076271186441,
|
2024 |
+
"grad_norm": 3.875,
|
2025 |
+
"learning_rate": 7.3273455119756445e-06,
|
2026 |
+
"loss": 2.134,
|
2027 |
+
"step": 286
|
2028 |
+
},
|
2029 |
+
{
|
2030 |
+
"epoch": 0.3800317796610169,
|
2031 |
+
"grad_norm": 4.125,
|
2032 |
+
"learning_rate": 7.307933338397667e-06,
|
2033 |
+
"loss": 2.0337,
|
2034 |
+
"step": 287
|
2035 |
+
},
|
2036 |
+
{
|
2037 |
+
"epoch": 0.3813559322033898,
|
2038 |
+
"grad_norm": 3.59375,
|
2039 |
+
"learning_rate": 7.288476856630656e-06,
|
2040 |
+
"loss": 2.2021,
|
2041 |
+
"step": 288
|
2042 |
+
},
|
2043 |
+
{
|
2044 |
+
"epoch": 0.3826800847457627,
|
2045 |
+
"grad_norm": 3.765625,
|
2046 |
+
"learning_rate": 7.268976440204236e-06,
|
2047 |
+
"loss": 2.0299,
|
2048 |
+
"step": 289
|
2049 |
+
},
|
2050 |
+
{
|
2051 |
+
"epoch": 0.3840042372881356,
|
2052 |
+
"grad_norm": 4.15625,
|
2053 |
+
"learning_rate": 7.249432463491498e-06,
|
2054 |
+
"loss": 1.9574,
|
2055 |
+
"step": 290
|
2056 |
+
},
|
2057 |
+
{
|
2058 |
+
"epoch": 0.3853283898305085,
|
2059 |
+
"grad_norm": 3.734375,
|
2060 |
+
"learning_rate": 7.229845301701811e-06,
|
2061 |
+
"loss": 2.2027,
|
2062 |
+
"step": 291
|
2063 |
+
},
|
2064 |
+
{
|
2065 |
+
"epoch": 0.3866525423728814,
|
2066 |
+
"grad_norm": 3.578125,
|
2067 |
+
"learning_rate": 7.2102153308736225e-06,
|
2068 |
+
"loss": 2.1389,
|
2069 |
+
"step": 292
|
2070 |
+
},
|
2071 |
+
{
|
2072 |
+
"epoch": 0.3879766949152542,
|
2073 |
+
"grad_norm": 3.796875,
|
2074 |
+
"learning_rate": 7.190542927867234e-06,
|
2075 |
+
"loss": 1.8233,
|
2076 |
+
"step": 293
|
2077 |
+
},
|
2078 |
+
{
|
2079 |
+
"epoch": 0.3893008474576271,
|
2080 |
+
"grad_norm": 3.984375,
|
2081 |
+
"learning_rate": 7.1708284703575734e-06,
|
2082 |
+
"loss": 1.9075,
|
2083 |
+
"step": 294
|
2084 |
+
},
|
2085 |
+
{
|
2086 |
+
"epoch": 0.390625,
|
2087 |
+
"grad_norm": 4.5625,
|
2088 |
+
"learning_rate": 7.1510723368269376e-06,
|
2089 |
+
"loss": 1.8944,
|
2090 |
+
"step": 295
|
2091 |
+
},
|
2092 |
+
{
|
2093 |
+
"epoch": 0.3919491525423729,
|
2094 |
+
"grad_norm": 4.0,
|
2095 |
+
"learning_rate": 7.131274906557725e-06,
|
2096 |
+
"loss": 2.1448,
|
2097 |
+
"step": 296
|
2098 |
+
},
|
2099 |
+
{
|
2100 |
+
"epoch": 0.3932733050847458,
|
2101 |
+
"grad_norm": 4.34375,
|
2102 |
+
"learning_rate": 7.111436559625162e-06,
|
2103 |
+
"loss": 2.0403,
|
2104 |
+
"step": 297
|
2105 |
+
},
|
2106 |
+
{
|
2107 |
+
"epoch": 0.3945974576271186,
|
2108 |
+
"grad_norm": 3.90625,
|
2109 |
+
"learning_rate": 7.091557676890001e-06,
|
2110 |
+
"loss": 1.982,
|
2111 |
+
"step": 298
|
2112 |
+
},
|
2113 |
+
{
|
2114 |
+
"epoch": 0.3959216101694915,
|
2115 |
+
"grad_norm": 4.5,
|
2116 |
+
"learning_rate": 7.0716386399912075e-06,
|
2117 |
+
"loss": 2.1055,
|
2118 |
+
"step": 299
|
2119 |
+
},
|
2120 |
+
{
|
2121 |
+
"epoch": 0.3972457627118644,
|
2122 |
+
"grad_norm": 3.515625,
|
2123 |
+
"learning_rate": 7.051679831338638e-06,
|
2124 |
+
"loss": 1.8751,
|
2125 |
+
"step": 300
|
2126 |
+
},
|
2127 |
+
{
|
2128 |
+
"epoch": 0.3985699152542373,
|
2129 |
+
"grad_norm": 3.765625,
|
2130 |
+
"learning_rate": 7.03168163410569e-06,
|
2131 |
+
"loss": 2.0518,
|
2132 |
+
"step": 301
|
2133 |
+
},
|
2134 |
+
{
|
2135 |
+
"epoch": 0.3998940677966102,
|
2136 |
+
"grad_norm": 3.8125,
|
2137 |
+
"learning_rate": 7.0116444322219575e-06,
|
2138 |
+
"loss": 1.9739,
|
2139 |
+
"step": 302
|
2140 |
+
},
|
2141 |
+
{
|
2142 |
+
"epoch": 0.4012182203389831,
|
2143 |
+
"grad_norm": 3.578125,
|
2144 |
+
"learning_rate": 6.991568610365851e-06,
|
2145 |
+
"loss": 2.0927,
|
2146 |
+
"step": 303
|
2147 |
+
},
|
2148 |
+
{
|
2149 |
+
"epoch": 0.4025423728813559,
|
2150 |
+
"grad_norm": 4.4375,
|
2151 |
+
"learning_rate": 6.971454553957216e-06,
|
2152 |
+
"loss": 2.0478,
|
2153 |
+
"step": 304
|
2154 |
+
},
|
2155 |
+
{
|
2156 |
+
"epoch": 0.4038665254237288,
|
2157 |
+
"grad_norm": 4.15625,
|
2158 |
+
"learning_rate": 6.95130264914993e-06,
|
2159 |
+
"loss": 2.0242,
|
2160 |
+
"step": 305
|
2161 |
+
},
|
2162 |
+
{
|
2163 |
+
"epoch": 0.4051906779661017,
|
2164 |
+
"grad_norm": 3.65625,
|
2165 |
+
"learning_rate": 6.931113282824498e-06,
|
2166 |
+
"loss": 2.1597,
|
2167 |
+
"step": 306
|
2168 |
+
},
|
2169 |
+
{
|
2170 |
+
"epoch": 0.4065148305084746,
|
2171 |
+
"grad_norm": 3.734375,
|
2172 |
+
"learning_rate": 6.910886842580612e-06,
|
2173 |
+
"loss": 1.9689,
|
2174 |
+
"step": 307
|
2175 |
+
},
|
2176 |
+
{
|
2177 |
+
"epoch": 0.4078389830508475,
|
2178 |
+
"grad_norm": 3.640625,
|
2179 |
+
"learning_rate": 6.890623716729724e-06,
|
2180 |
+
"loss": 2.1267,
|
2181 |
+
"step": 308
|
2182 |
+
},
|
2183 |
+
{
|
2184 |
+
"epoch": 0.4091631355932203,
|
2185 |
+
"grad_norm": 3.796875,
|
2186 |
+
"learning_rate": 6.870324294287578e-06,
|
2187 |
+
"loss": 2.0548,
|
2188 |
+
"step": 309
|
2189 |
+
},
|
2190 |
+
{
|
2191 |
+
"epoch": 0.4104872881355932,
|
2192 |
+
"grad_norm": 3.703125,
|
2193 |
+
"learning_rate": 6.8499889649667516e-06,
|
2194 |
+
"loss": 2.2051,
|
2195 |
+
"step": 310
|
2196 |
+
},
|
2197 |
+
{
|
2198 |
+
"epoch": 0.4118114406779661,
|
2199 |
+
"grad_norm": 3.765625,
|
2200 |
+
"learning_rate": 6.829618119169169e-06,
|
2201 |
+
"loss": 1.9724,
|
2202 |
+
"step": 311
|
2203 |
+
},
|
2204 |
+
{
|
2205 |
+
"epoch": 0.413135593220339,
|
2206 |
+
"grad_norm": 4.09375,
|
2207 |
+
"learning_rate": 6.809212147978605e-06,
|
2208 |
+
"loss": 2.0979,
|
2209 |
+
"step": 312
|
2210 |
+
},
|
2211 |
+
{
|
2212 |
+
"epoch": 0.4144597457627119,
|
2213 |
+
"grad_norm": 3.953125,
|
2214 |
+
"learning_rate": 6.788771443153183e-06,
|
2215 |
+
"loss": 2.1663,
|
2216 |
+
"step": 313
|
2217 |
+
},
|
2218 |
+
{
|
2219 |
+
"epoch": 0.4157838983050847,
|
2220 |
+
"grad_norm": 4.03125,
|
2221 |
+
"learning_rate": 6.768296397117848e-06,
|
2222 |
+
"loss": 1.9478,
|
2223 |
+
"step": 314
|
2224 |
+
},
|
2225 |
+
{
|
2226 |
+
"epoch": 0.4171080508474576,
|
2227 |
+
"grad_norm": 4.03125,
|
2228 |
+
"learning_rate": 6.7477874029568345e-06,
|
2229 |
+
"loss": 2.0767,
|
2230 |
+
"step": 315
|
2231 |
+
},
|
2232 |
+
{
|
2233 |
+
"epoch": 0.4184322033898305,
|
2234 |
+
"grad_norm": 5.875,
|
2235 |
+
"learning_rate": 6.7272448544061184e-06,
|
2236 |
+
"loss": 2.0509,
|
2237 |
+
"step": 316
|
2238 |
+
},
|
2239 |
+
{
|
2240 |
+
"epoch": 0.4197563559322034,
|
2241 |
+
"grad_norm": 3.921875,
|
2242 |
+
"learning_rate": 6.706669145845863e-06,
|
2243 |
+
"loss": 2.0612,
|
2244 |
+
"step": 317
|
2245 |
+
},
|
2246 |
+
{
|
2247 |
+
"epoch": 0.4210805084745763,
|
2248 |
+
"grad_norm": 5.09375,
|
2249 |
+
"learning_rate": 6.686060672292847e-06,
|
2250 |
+
"loss": 1.9404,
|
2251 |
+
"step": 318
|
2252 |
+
},
|
2253 |
+
{
|
2254 |
+
"epoch": 0.4224046610169492,
|
2255 |
+
"grad_norm": 4.0,
|
2256 |
+
"learning_rate": 6.6654198293928695e-06,
|
2257 |
+
"loss": 2.0939,
|
2258 |
+
"step": 319
|
2259 |
+
},
|
2260 |
+
{
|
2261 |
+
"epoch": 0.423728813559322,
|
2262 |
+
"grad_norm": 4.84375,
|
2263 |
+
"learning_rate": 6.6447470134131685e-06,
|
2264 |
+
"loss": 1.9003,
|
2265 |
+
"step": 320
|
2266 |
+
},
|
2267 |
+
{
|
2268 |
+
"epoch": 0.4250529661016949,
|
2269 |
+
"grad_norm": 4.0,
|
2270 |
+
"learning_rate": 6.624042621234814e-06,
|
2271 |
+
"loss": 2.1884,
|
2272 |
+
"step": 321
|
2273 |
+
},
|
2274 |
+
{
|
2275 |
+
"epoch": 0.4263771186440678,
|
2276 |
+
"grad_norm": 3.734375,
|
2277 |
+
"learning_rate": 6.603307050345069e-06,
|
2278 |
+
"loss": 1.9816,
|
2279 |
+
"step": 322
|
2280 |
+
},
|
2281 |
+
{
|
2282 |
+
"epoch": 0.4277012711864407,
|
2283 |
+
"grad_norm": 3.828125,
|
2284 |
+
"learning_rate": 6.5825406988297815e-06,
|
2285 |
+
"loss": 1.9909,
|
2286 |
+
"step": 323
|
2287 |
+
},
|
2288 |
+
{
|
2289 |
+
"epoch": 0.4290254237288136,
|
2290 |
+
"grad_norm": 4.03125,
|
2291 |
+
"learning_rate": 6.561743965365732e-06,
|
2292 |
+
"loss": 2.1602,
|
2293 |
+
"step": 324
|
2294 |
+
},
|
2295 |
+
{
|
2296 |
+
"epoch": 0.4303495762711864,
|
2297 |
+
"grad_norm": 3.625,
|
2298 |
+
"learning_rate": 6.540917249212976e-06,
|
2299 |
+
"loss": 2.2546,
|
2300 |
+
"step": 325
|
2301 |
+
},
|
2302 |
+
{
|
2303 |
+
"epoch": 0.4316737288135593,
|
2304 |
+
"grad_norm": 3.734375,
|
2305 |
+
"learning_rate": 6.520060950207186e-06,
|
2306 |
+
"loss": 2.1109,
|
2307 |
+
"step": 326
|
2308 |
+
},
|
2309 |
+
{
|
2310 |
+
"epoch": 0.4329978813559322,
|
2311 |
+
"grad_norm": 3.6875,
|
2312 |
+
"learning_rate": 6.4991754687519695e-06,
|
2313 |
+
"loss": 1.9424,
|
2314 |
+
"step": 327
|
2315 |
+
},
|
2316 |
+
{
|
2317 |
+
"epoch": 0.4343220338983051,
|
2318 |
+
"grad_norm": 4.03125,
|
2319 |
+
"learning_rate": 6.478261205811188e-06,
|
2320 |
+
"loss": 1.9637,
|
2321 |
+
"step": 328
|
2322 |
+
},
|
2323 |
+
{
|
2324 |
+
"epoch": 0.435646186440678,
|
2325 |
+
"grad_norm": 4.1875,
|
2326 |
+
"learning_rate": 6.457318562901257e-06,
|
2327 |
+
"loss": 1.9564,
|
2328 |
+
"step": 329
|
2329 |
+
},
|
2330 |
+
{
|
2331 |
+
"epoch": 0.4369703389830508,
|
2332 |
+
"grad_norm": 3.734375,
|
2333 |
+
"learning_rate": 6.43634794208343e-06,
|
2334 |
+
"loss": 2.1901,
|
2335 |
+
"step": 330
|
2336 |
+
},
|
2337 |
+
{
|
2338 |
+
"epoch": 0.4382944915254237,
|
2339 |
+
"grad_norm": 4.0625,
|
2340 |
+
"learning_rate": 6.415349745956093e-06,
|
2341 |
+
"loss": 1.8634,
|
2342 |
+
"step": 331
|
2343 |
+
},
|
2344 |
+
{
|
2345 |
+
"epoch": 0.4396186440677966,
|
2346 |
+
"grad_norm": 4.1875,
|
2347 |
+
"learning_rate": 6.394324377647028e-06,
|
2348 |
+
"loss": 1.9514,
|
2349 |
+
"step": 332
|
2350 |
+
},
|
2351 |
+
{
|
2352 |
+
"epoch": 0.4409427966101695,
|
2353 |
+
"grad_norm": 3.953125,
|
2354 |
+
"learning_rate": 6.373272240805668e-06,
|
2355 |
+
"loss": 1.8502,
|
2356 |
+
"step": 333
|
2357 |
+
},
|
2358 |
+
{
|
2359 |
+
"epoch": 0.4422669491525424,
|
2360 |
+
"grad_norm": 3.78125,
|
2361 |
+
"learning_rate": 6.35219373959536e-06,
|
2362 |
+
"loss": 1.9593,
|
2363 |
+
"step": 334
|
2364 |
+
},
|
2365 |
+
{
|
2366 |
+
"epoch": 0.4435911016949153,
|
2367 |
+
"grad_norm": 3.765625,
|
2368 |
+
"learning_rate": 6.331089278685599e-06,
|
2369 |
+
"loss": 2.057,
|
2370 |
+
"step": 335
|
2371 |
+
},
|
2372 |
+
{
|
2373 |
+
"epoch": 0.4449152542372881,
|
2374 |
+
"grad_norm": 4.84375,
|
2375 |
+
"learning_rate": 6.30995926324426e-06,
|
2376 |
+
"loss": 1.9964,
|
2377 |
+
"step": 336
|
2378 |
+
},
|
2379 |
+
{
|
2380 |
+
"epoch": 0.446239406779661,
|
2381 |
+
"grad_norm": 3.796875,
|
2382 |
+
"learning_rate": 6.2888040989298136e-06,
|
2383 |
+
"loss": 2.2322,
|
2384 |
+
"step": 337
|
2385 |
+
},
|
2386 |
+
{
|
2387 |
+
"epoch": 0.4475635593220339,
|
2388 |
+
"grad_norm": 3.84375,
|
2389 |
+
"learning_rate": 6.267624191883551e-06,
|
2390 |
+
"loss": 1.9032,
|
2391 |
+
"step": 338
|
2392 |
+
},
|
2393 |
+
{
|
2394 |
+
"epoch": 0.4488877118644068,
|
2395 |
+
"grad_norm": 3.90625,
|
2396 |
+
"learning_rate": 6.246419948721777e-06,
|
2397 |
+
"loss": 2.026,
|
2398 |
+
"step": 339
|
2399 |
+
},
|
2400 |
+
{
|
2401 |
+
"epoch": 0.4502118644067797,
|
2402 |
+
"grad_norm": 3.625,
|
2403 |
+
"learning_rate": 6.2251917765280056e-06,
|
2404 |
+
"loss": 2.1106,
|
2405 |
+
"step": 340
|
2406 |
+
},
|
2407 |
+
{
|
2408 |
+
"epoch": 0.4515360169491525,
|
2409 |
+
"grad_norm": 3.859375,
|
2410 |
+
"learning_rate": 6.203940082845144e-06,
|
2411 |
+
"loss": 1.8843,
|
2412 |
+
"step": 341
|
2413 |
+
},
|
2414 |
+
{
|
2415 |
+
"epoch": 0.4528601694915254,
|
2416 |
+
"grad_norm": 4.0,
|
2417 |
+
"learning_rate": 6.182665275667674e-06,
|
2418 |
+
"loss": 1.8529,
|
2419 |
+
"step": 342
|
2420 |
+
},
|
2421 |
+
{
|
2422 |
+
"epoch": 0.4541843220338983,
|
2423 |
+
"grad_norm": 3.859375,
|
2424 |
+
"learning_rate": 6.161367763433812e-06,
|
2425 |
+
"loss": 2.0598,
|
2426 |
+
"step": 343
|
2427 |
+
},
|
2428 |
+
{
|
2429 |
+
"epoch": 0.4555084745762712,
|
2430 |
+
"grad_norm": 3.859375,
|
2431 |
+
"learning_rate": 6.140047955017672e-06,
|
2432 |
+
"loss": 2.0318,
|
2433 |
+
"step": 344
|
2434 |
+
},
|
2435 |
+
{
|
2436 |
+
"epoch": 0.4568326271186441,
|
2437 |
+
"grad_norm": 4.09375,
|
2438 |
+
"learning_rate": 6.118706259721414e-06,
|
2439 |
+
"loss": 2.0361,
|
2440 |
+
"step": 345
|
2441 |
+
},
|
2442 |
+
{
|
2443 |
+
"epoch": 0.4581567796610169,
|
2444 |
+
"grad_norm": 3.984375,
|
2445 |
+
"learning_rate": 6.097343087267386e-06,
|
2446 |
+
"loss": 2.0142,
|
2447 |
+
"step": 346
|
2448 |
+
},
|
2449 |
+
{
|
2450 |
+
"epoch": 0.4594809322033898,
|
2451 |
+
"grad_norm": 4.09375,
|
2452 |
+
"learning_rate": 6.075958847790262e-06,
|
2453 |
+
"loss": 2.0354,
|
2454 |
+
"step": 347
|
2455 |
+
},
|
2456 |
+
{
|
2457 |
+
"epoch": 0.4608050847457627,
|
2458 |
+
"grad_norm": 3.765625,
|
2459 |
+
"learning_rate": 6.054553951829163e-06,
|
2460 |
+
"loss": 1.9838,
|
2461 |
+
"step": 348
|
2462 |
+
},
|
2463 |
+
{
|
2464 |
+
"epoch": 0.4621292372881356,
|
2465 |
+
"grad_norm": 4.03125,
|
2466 |
+
"learning_rate": 6.033128810319779e-06,
|
2467 |
+
"loss": 1.9332,
|
2468 |
+
"step": 349
|
2469 |
+
},
|
2470 |
+
{
|
2471 |
+
"epoch": 0.4634533898305085,
|
2472 |
+
"grad_norm": 3.75,
|
2473 |
+
"learning_rate": 6.011683834586474e-06,
|
2474 |
+
"loss": 2.0284,
|
2475 |
+
"step": 350
|
2476 |
+
},
|
2477 |
+
{
|
2478 |
+
"epoch": 0.4647775423728814,
|
2479 |
+
"grad_norm": 3.703125,
|
2480 |
+
"learning_rate": 5.9902194363344014e-06,
|
2481 |
+
"loss": 1.9933,
|
2482 |
+
"step": 351
|
2483 |
+
},
|
2484 |
+
{
|
2485 |
+
"epoch": 0.4661016949152542,
|
2486 |
+
"grad_norm": 3.96875,
|
2487 |
+
"learning_rate": 5.968736027641584e-06,
|
2488 |
+
"loss": 1.9212,
|
2489 |
+
"step": 352
|
2490 |
+
},
|
2491 |
+
{
|
2492 |
+
"epoch": 0.4674258474576271,
|
2493 |
+
"grad_norm": 4.3125,
|
2494 |
+
"learning_rate": 5.947234020951015e-06,
|
2495 |
+
"loss": 1.9715,
|
2496 |
+
"step": 353
|
2497 |
+
},
|
2498 |
+
{
|
2499 |
+
"epoch": 0.46875,
|
2500 |
+
"grad_norm": 4.0625,
|
2501 |
+
"learning_rate": 5.925713829062737e-06,
|
2502 |
+
"loss": 2.116,
|
2503 |
+
"step": 354
|
2504 |
+
},
|
2505 |
+
{
|
2506 |
+
"epoch": 0.4700741525423729,
|
2507 |
+
"grad_norm": 4.0,
|
2508 |
+
"learning_rate": 5.904175865125915e-06,
|
2509 |
+
"loss": 1.8785,
|
2510 |
+
"step": 355
|
2511 |
+
},
|
2512 |
+
{
|
2513 |
+
"epoch": 0.4713983050847458,
|
2514 |
+
"grad_norm": 3.8125,
|
2515 |
+
"learning_rate": 5.882620542630901e-06,
|
2516 |
+
"loss": 2.1109,
|
2517 |
+
"step": 356
|
2518 |
+
},
|
2519 |
+
{
|
2520 |
+
"epoch": 0.4727224576271186,
|
2521 |
+
"grad_norm": 4.0625,
|
2522 |
+
"learning_rate": 5.86104827540131e-06,
|
2523 |
+
"loss": 2.046,
|
2524 |
+
"step": 357
|
2525 |
+
},
|
2526 |
+
{
|
2527 |
+
"epoch": 0.4740466101694915,
|
2528 |
+
"grad_norm": 3.890625,
|
2529 |
+
"learning_rate": 5.839459477586056e-06,
|
2530 |
+
"loss": 1.931,
|
2531 |
+
"step": 358
|
2532 |
+
},
|
2533 |
+
{
|
2534 |
+
"epoch": 0.4753707627118644,
|
2535 |
+
"grad_norm": 4.0,
|
2536 |
+
"learning_rate": 5.817854563651415e-06,
|
2537 |
+
"loss": 1.9138,
|
2538 |
+
"step": 359
|
2539 |
+
},
|
2540 |
+
{
|
2541 |
+
"epoch": 0.4766949152542373,
|
2542 |
+
"grad_norm": 3.90625,
|
2543 |
+
"learning_rate": 5.796233948373061e-06,
|
2544 |
+
"loss": 2.0626,
|
2545 |
+
"step": 360
|
2546 |
+
},
|
2547 |
+
{
|
2548 |
+
"epoch": 0.4780190677966102,
|
2549 |
+
"grad_norm": 3.6875,
|
2550 |
+
"learning_rate": 5.7745980468281116e-06,
|
2551 |
+
"loss": 1.9901,
|
2552 |
+
"step": 361
|
2553 |
+
},
|
2554 |
+
{
|
2555 |
+
"epoch": 0.4793432203389831,
|
2556 |
+
"grad_norm": 3.515625,
|
2557 |
+
"learning_rate": 5.752947274387147e-06,
|
2558 |
+
"loss": 2.1562,
|
2559 |
+
"step": 362
|
2560 |
+
},
|
2561 |
+
{
|
2562 |
+
"epoch": 0.4806673728813559,
|
2563 |
+
"grad_norm": 4.03125,
|
2564 |
+
"learning_rate": 5.731282046706247e-06,
|
2565 |
+
"loss": 1.9464,
|
2566 |
+
"step": 363
|
2567 |
+
},
|
2568 |
+
{
|
2569 |
+
"epoch": 0.4819915254237288,
|
2570 |
+
"grad_norm": 3.875,
|
2571 |
+
"learning_rate": 5.709602779718999e-06,
|
2572 |
+
"loss": 1.9471,
|
2573 |
+
"step": 364
|
2574 |
+
},
|
2575 |
+
{
|
2576 |
+
"epoch": 0.4833156779661017,
|
2577 |
+
"grad_norm": 3.640625,
|
2578 |
+
"learning_rate": 5.687909889628529e-06,
|
2579 |
+
"loss": 1.9786,
|
2580 |
+
"step": 365
|
2581 |
+
},
|
2582 |
+
{
|
2583 |
+
"epoch": 0.4846398305084746,
|
2584 |
+
"grad_norm": 3.796875,
|
2585 |
+
"learning_rate": 5.666203792899496e-06,
|
2586 |
+
"loss": 2.0612,
|
2587 |
+
"step": 366
|
2588 |
+
},
|
2589 |
+
{
|
2590 |
+
"epoch": 0.4859639830508475,
|
2591 |
+
"grad_norm": 3.84375,
|
2592 |
+
"learning_rate": 5.644484906250104e-06,
|
2593 |
+
"loss": 1.9507,
|
2594 |
+
"step": 367
|
2595 |
+
},
|
2596 |
+
{
|
2597 |
+
"epoch": 0.4872881355932203,
|
2598 |
+
"grad_norm": 3.984375,
|
2599 |
+
"learning_rate": 5.622753646644102e-06,
|
2600 |
+
"loss": 1.8828,
|
2601 |
+
"step": 368
|
2602 |
+
},
|
2603 |
+
{
|
2604 |
+
"epoch": 0.4886122881355932,
|
2605 |
+
"grad_norm": 3.671875,
|
2606 |
+
"learning_rate": 5.601010431282777e-06,
|
2607 |
+
"loss": 1.9527,
|
2608 |
+
"step": 369
|
2609 |
+
},
|
2610 |
+
{
|
2611 |
+
"epoch": 0.4899364406779661,
|
2612 |
+
"grad_norm": 3.90625,
|
2613 |
+
"learning_rate": 5.579255677596944e-06,
|
2614 |
+
"loss": 2.0724,
|
2615 |
+
"step": 370
|
2616 |
+
},
|
2617 |
+
{
|
2618 |
+
"epoch": 0.491260593220339,
|
2619 |
+
"grad_norm": 3.890625,
|
2620 |
+
"learning_rate": 5.557489803238934e-06,
|
2621 |
+
"loss": 1.9829,
|
2622 |
+
"step": 371
|
2623 |
+
},
|
2624 |
+
{
|
2625 |
+
"epoch": 0.4925847457627119,
|
2626 |
+
"grad_norm": 3.75,
|
2627 |
+
"learning_rate": 5.535713226074576e-06,
|
2628 |
+
"loss": 1.9163,
|
2629 |
+
"step": 372
|
2630 |
+
},
|
2631 |
+
{
|
2632 |
+
"epoch": 0.4939088983050847,
|
2633 |
+
"grad_norm": 3.90625,
|
2634 |
+
"learning_rate": 5.513926364175172e-06,
|
2635 |
+
"loss": 2.0671,
|
2636 |
+
"step": 373
|
2637 |
+
},
|
2638 |
+
{
|
2639 |
+
"epoch": 0.4952330508474576,
|
2640 |
+
"grad_norm": 3.75,
|
2641 |
+
"learning_rate": 5.492129635809473e-06,
|
2642 |
+
"loss": 2.0903,
|
2643 |
+
"step": 374
|
2644 |
+
},
|
2645 |
+
{
|
2646 |
+
"epoch": 0.4965572033898305,
|
2647 |
+
"grad_norm": 4.125,
|
2648 |
+
"learning_rate": 5.47032345943565e-06,
|
2649 |
+
"loss": 2.0251,
|
2650 |
+
"step": 375
|
2651 |
+
},
|
2652 |
+
{
|
2653 |
+
"epoch": 0.4978813559322034,
|
2654 |
+
"grad_norm": 3.65625,
|
2655 |
+
"learning_rate": 5.4485082536932564e-06,
|
2656 |
+
"loss": 2.0114,
|
2657 |
+
"step": 376
|
2658 |
+
},
|
2659 |
+
{
|
2660 |
+
"epoch": 0.4992055084745763,
|
2661 |
+
"grad_norm": 3.734375,
|
2662 |
+
"learning_rate": 5.426684437395196e-06,
|
2663 |
+
"loss": 1.9574,
|
2664 |
+
"step": 377
|
2665 |
+
},
|
2666 |
+
{
|
2667 |
+
"epoch": 0.5005296610169492,
|
2668 |
+
"grad_norm": 4.25,
|
2669 |
+
"learning_rate": 5.404852429519678e-06,
|
2670 |
+
"loss": 1.9259,
|
2671 |
+
"step": 378
|
2672 |
+
},
|
2673 |
+
{
|
2674 |
+
"epoch": 0.501853813559322,
|
2675 |
+
"grad_norm": 4.03125,
|
2676 |
+
"learning_rate": 5.383012649202173e-06,
|
2677 |
+
"loss": 1.9558,
|
2678 |
+
"step": 379
|
2679 |
+
},
|
2680 |
+
{
|
2681 |
+
"epoch": 0.503177966101695,
|
2682 |
+
"grad_norm": 3.96875,
|
2683 |
+
"learning_rate": 5.361165515727374e-06,
|
2684 |
+
"loss": 2.0474,
|
2685 |
+
"step": 380
|
2686 |
+
},
|
2687 |
+
{
|
2688 |
+
"epoch": 0.5045021186440678,
|
2689 |
+
"grad_norm": 3.890625,
|
2690 |
+
"learning_rate": 5.3393114485211394e-06,
|
2691 |
+
"loss": 2.0343,
|
2692 |
+
"step": 381
|
2693 |
+
},
|
2694 |
+
{
|
2695 |
+
"epoch": 0.5058262711864406,
|
2696 |
+
"grad_norm": 3.84375,
|
2697 |
+
"learning_rate": 5.31745086714244e-06,
|
2698 |
+
"loss": 1.9331,
|
2699 |
+
"step": 382
|
2700 |
+
},
|
2701 |
+
{
|
2702 |
+
"epoch": 0.5071504237288136,
|
2703 |
+
"grad_norm": 4.0,
|
2704 |
+
"learning_rate": 5.295584191275308e-06,
|
2705 |
+
"loss": 1.8745,
|
2706 |
+
"step": 383
|
2707 |
+
},
|
2708 |
+
{
|
2709 |
+
"epoch": 0.5084745762711864,
|
2710 |
+
"grad_norm": 3.8125,
|
2711 |
+
"learning_rate": 5.273711840720783e-06,
|
2712 |
+
"loss": 1.9222,
|
2713 |
+
"step": 384
|
2714 |
+
},
|
2715 |
+
{
|
2716 |
+
"epoch": 0.5097987288135594,
|
2717 |
+
"grad_norm": 4.0,
|
2718 |
+
"learning_rate": 5.251834235388845e-06,
|
2719 |
+
"loss": 2.1023,
|
2720 |
+
"step": 385
|
2721 |
+
},
|
2722 |
+
{
|
2723 |
+
"epoch": 0.5111228813559322,
|
2724 |
+
"grad_norm": 3.96875,
|
2725 |
+
"learning_rate": 5.229951795290353e-06,
|
2726 |
+
"loss": 1.9507,
|
2727 |
+
"step": 386
|
2728 |
+
},
|
2729 |
+
{
|
2730 |
+
"epoch": 0.512447033898305,
|
2731 |
+
"grad_norm": 3.75,
|
2732 |
+
"learning_rate": 5.208064940528994e-06,
|
2733 |
+
"loss": 2.0536,
|
2734 |
+
"step": 387
|
2735 |
+
},
|
2736 |
+
{
|
2737 |
+
"epoch": 0.513771186440678,
|
2738 |
+
"grad_norm": 3.6875,
|
2739 |
+
"learning_rate": 5.1861740912932e-06,
|
2740 |
+
"loss": 2.0979,
|
2741 |
+
"step": 388
|
2742 |
+
},
|
2743 |
+
{
|
2744 |
+
"epoch": 0.5150953389830508,
|
2745 |
+
"grad_norm": 3.75,
|
2746 |
+
"learning_rate": 5.164279667848094e-06,
|
2747 |
+
"loss": 2.0845,
|
2748 |
+
"step": 389
|
2749 |
+
},
|
2750 |
+
{
|
2751 |
+
"epoch": 0.5164194915254238,
|
2752 |
+
"grad_norm": 4.09375,
|
2753 |
+
"learning_rate": 5.142382090527415e-06,
|
2754 |
+
"loss": 2.0602,
|
2755 |
+
"step": 390
|
2756 |
+
},
|
2757 |
+
{
|
2758 |
+
"epoch": 0.5177436440677966,
|
2759 |
+
"grad_norm": 3.953125,
|
2760 |
+
"learning_rate": 5.1204817797254545e-06,
|
2761 |
+
"loss": 1.883,
|
2762 |
+
"step": 391
|
2763 |
+
},
|
2764 |
+
{
|
2765 |
+
"epoch": 0.5190677966101694,
|
2766 |
+
"grad_norm": 3.75,
|
2767 |
+
"learning_rate": 5.0985791558889785e-06,
|
2768 |
+
"loss": 2.131,
|
2769 |
+
"step": 392
|
2770 |
+
},
|
2771 |
+
{
|
2772 |
+
"epoch": 0.5203919491525424,
|
2773 |
+
"grad_norm": 3.90625,
|
2774 |
+
"learning_rate": 5.07667463950916e-06,
|
2775 |
+
"loss": 2.0166,
|
2776 |
+
"step": 393
|
2777 |
+
},
|
2778 |
+
{
|
2779 |
+
"epoch": 0.5217161016949152,
|
2780 |
+
"grad_norm": 3.703125,
|
2781 |
+
"learning_rate": 5.054768651113506e-06,
|
2782 |
+
"loss": 1.9136,
|
2783 |
+
"step": 394
|
2784 |
+
},
|
2785 |
+
{
|
2786 |
+
"epoch": 0.5230402542372882,
|
2787 |
+
"grad_norm": 4.15625,
|
2788 |
+
"learning_rate": 5.032861611257783e-06,
|
2789 |
+
"loss": 2.0923,
|
2790 |
+
"step": 395
|
2791 |
+
},
|
2792 |
+
{
|
2793 |
+
"epoch": 0.524364406779661,
|
2794 |
+
"grad_norm": 3.8125,
|
2795 |
+
"learning_rate": 5.0109539405179456e-06,
|
2796 |
+
"loss": 2.1243,
|
2797 |
+
"step": 396
|
2798 |
+
},
|
2799 |
+
{
|
2800 |
+
"epoch": 0.5256885593220338,
|
2801 |
+
"grad_norm": 3.703125,
|
2802 |
+
"learning_rate": 4.989046059482055e-06,
|
2803 |
+
"loss": 2.0784,
|
2804 |
+
"step": 397
|
2805 |
+
},
|
2806 |
+
{
|
2807 |
+
"epoch": 0.5270127118644068,
|
2808 |
+
"grad_norm": 3.765625,
|
2809 |
+
"learning_rate": 4.967138388742218e-06,
|
2810 |
+
"loss": 1.8999,
|
2811 |
+
"step": 398
|
2812 |
+
},
|
2813 |
+
{
|
2814 |
+
"epoch": 0.5283368644067796,
|
2815 |
+
"grad_norm": 3.734375,
|
2816 |
+
"learning_rate": 4.945231348886495e-06,
|
2817 |
+
"loss": 2.0906,
|
2818 |
+
"step": 399
|
2819 |
+
},
|
2820 |
+
{
|
2821 |
+
"epoch": 0.5296610169491526,
|
2822 |
+
"grad_norm": 3.828125,
|
2823 |
+
"learning_rate": 4.923325360490841e-06,
|
2824 |
+
"loss": 1.9295,
|
2825 |
+
"step": 400
|
2826 |
+
},
|
2827 |
+
{
|
2828 |
+
"epoch": 0.5296610169491526,
|
2829 |
+
"eval_AskDoctor-Chinese_loss": 1.9834351539611816,
|
2830 |
+
"eval_AskDoctor-Chinese_runtime": 15.9925,
|
2831 |
+
"eval_AskDoctor-Chinese_samples_per_second": 1.876,
|
2832 |
+
"eval_AskDoctor-Chinese_steps_per_second": 1.876,
|
2833 |
+
"step": 400
|
2834 |
+
},
|
2835 |
+
{
|
2836 |
+
"epoch": 0.5309851694915254,
|
2837 |
+
"grad_norm": 4.03125,
|
2838 |
+
"learning_rate": 4.9014208441110215e-06,
|
2839 |
+
"loss": 2.0197,
|
2840 |
+
"step": 401
|
2841 |
+
},
|
2842 |
+
{
|
2843 |
+
"epoch": 0.5323093220338984,
|
2844 |
+
"grad_norm": 3.75,
|
2845 |
+
"learning_rate": 4.879518220274546e-06,
|
2846 |
+
"loss": 2.0886,
|
2847 |
+
"step": 402
|
2848 |
+
},
|
2849 |
+
{
|
2850 |
+
"epoch": 0.5336334745762712,
|
2851 |
+
"grad_norm": 4.5,
|
2852 |
+
"learning_rate": 4.8576179094725855e-06,
|
2853 |
+
"loss": 1.9252,
|
2854 |
+
"step": 403
|
2855 |
+
},
|
2856 |
+
{
|
2857 |
+
"epoch": 0.534957627118644,
|
2858 |
+
"grad_norm": 3.859375,
|
2859 |
+
"learning_rate": 4.835720332151907e-06,
|
2860 |
+
"loss": 2.0754,
|
2861 |
+
"step": 404
|
2862 |
+
},
|
2863 |
+
{
|
2864 |
+
"epoch": 0.536281779661017,
|
2865 |
+
"grad_norm": 3.6875,
|
2866 |
+
"learning_rate": 4.813825908706802e-06,
|
2867 |
+
"loss": 2.1356,
|
2868 |
+
"step": 405
|
2869 |
+
},
|
2870 |
+
{
|
2871 |
+
"epoch": 0.5376059322033898,
|
2872 |
+
"grad_norm": 3.8125,
|
2873 |
+
"learning_rate": 4.791935059471007e-06,
|
2874 |
+
"loss": 2.0131,
|
2875 |
+
"step": 406
|
2876 |
+
},
|
2877 |
+
{
|
2878 |
+
"epoch": 0.5389300847457628,
|
2879 |
+
"grad_norm": 3.734375,
|
2880 |
+
"learning_rate": 4.770048204709648e-06,
|
2881 |
+
"loss": 1.8858,
|
2882 |
+
"step": 407
|
2883 |
+
},
|
2884 |
+
{
|
2885 |
+
"epoch": 0.5402542372881356,
|
2886 |
+
"grad_norm": 6.34375,
|
2887 |
+
"learning_rate": 4.748165764611157e-06,
|
2888 |
+
"loss": 1.9881,
|
2889 |
+
"step": 408
|
2890 |
+
},
|
2891 |
+
{
|
2892 |
+
"epoch": 0.5415783898305084,
|
2893 |
+
"grad_norm": 3.734375,
|
2894 |
+
"learning_rate": 4.726288159279218e-06,
|
2895 |
+
"loss": 2.0027,
|
2896 |
+
"step": 409
|
2897 |
+
},
|
2898 |
+
{
|
2899 |
+
"epoch": 0.5429025423728814,
|
2900 |
+
"grad_norm": 3.9375,
|
2901 |
+
"learning_rate": 4.7044158087246926e-06,
|
2902 |
+
"loss": 2.1449,
|
2903 |
+
"step": 410
|
2904 |
+
},
|
2905 |
+
{
|
2906 |
+
"epoch": 0.5442266949152542,
|
2907 |
+
"grad_norm": 3.609375,
|
2908 |
+
"learning_rate": 4.682549132857562e-06,
|
2909 |
+
"loss": 2.0456,
|
2910 |
+
"step": 411
|
2911 |
+
},
|
2912 |
+
{
|
2913 |
+
"epoch": 0.5455508474576272,
|
2914 |
+
"grad_norm": 3.96875,
|
2915 |
+
"learning_rate": 4.660688551478861e-06,
|
2916 |
+
"loss": 2.2308,
|
2917 |
+
"step": 412
|
2918 |
+
},
|
2919 |
+
{
|
2920 |
+
"epoch": 0.546875,
|
2921 |
+
"grad_norm": 3.875,
|
2922 |
+
"learning_rate": 4.6388344842726266e-06,
|
2923 |
+
"loss": 2.0734,
|
2924 |
+
"step": 413
|
2925 |
+
},
|
2926 |
+
{
|
2927 |
+
"epoch": 0.5481991525423728,
|
2928 |
+
"grad_norm": 3.84375,
|
2929 |
+
"learning_rate": 4.616987350797827e-06,
|
2930 |
+
"loss": 2.0188,
|
2931 |
+
"step": 414
|
2932 |
+
},
|
2933 |
+
{
|
2934 |
+
"epoch": 0.5495233050847458,
|
2935 |
+
"grad_norm": 3.578125,
|
2936 |
+
"learning_rate": 4.595147570480324e-06,
|
2937 |
+
"loss": 2.1403,
|
2938 |
+
"step": 415
|
2939 |
+
},
|
2940 |
+
{
|
2941 |
+
"epoch": 0.5508474576271186,
|
2942 |
+
"grad_norm": 5.75,
|
2943 |
+
"learning_rate": 4.573315562604804e-06,
|
2944 |
+
"loss": 1.8386,
|
2945 |
+
"step": 416
|
2946 |
+
},
|
2947 |
+
{
|
2948 |
+
"epoch": 0.5521716101694916,
|
2949 |
+
"grad_norm": 3.671875,
|
2950 |
+
"learning_rate": 4.551491746306744e-06,
|
2951 |
+
"loss": 2.0066,
|
2952 |
+
"step": 417
|
2953 |
+
},
|
2954 |
+
{
|
2955 |
+
"epoch": 0.5534957627118644,
|
2956 |
+
"grad_norm": 4.0625,
|
2957 |
+
"learning_rate": 4.529676540564351e-06,
|
2958 |
+
"loss": 1.9468,
|
2959 |
+
"step": 418
|
2960 |
+
},
|
2961 |
+
{
|
2962 |
+
"epoch": 0.5548199152542372,
|
2963 |
+
"grad_norm": 3.9375,
|
2964 |
+
"learning_rate": 4.5078703641905275e-06,
|
2965 |
+
"loss": 2.0946,
|
2966 |
+
"step": 419
|
2967 |
+
},
|
2968 |
+
{
|
2969 |
+
"epoch": 0.5561440677966102,
|
2970 |
+
"grad_norm": 3.625,
|
2971 |
+
"learning_rate": 4.486073635824831e-06,
|
2972 |
+
"loss": 2.206,
|
2973 |
+
"step": 420
|
2974 |
+
},
|
2975 |
+
{
|
2976 |
+
"epoch": 0.557468220338983,
|
2977 |
+
"grad_norm": 3.734375,
|
2978 |
+
"learning_rate": 4.464286773925426e-06,
|
2979 |
+
"loss": 1.977,
|
2980 |
+
"step": 421
|
2981 |
+
},
|
2982 |
+
{
|
2983 |
+
"epoch": 0.558792372881356,
|
2984 |
+
"grad_norm": 3.765625,
|
2985 |
+
"learning_rate": 4.442510196761068e-06,
|
2986 |
+
"loss": 1.8473,
|
2987 |
+
"step": 422
|
2988 |
+
},
|
2989 |
+
{
|
2990 |
+
"epoch": 0.5601165254237288,
|
2991 |
+
"grad_norm": 3.65625,
|
2992 |
+
"learning_rate": 4.420744322403058e-06,
|
2993 |
+
"loss": 2.1905,
|
2994 |
+
"step": 423
|
2995 |
+
},
|
2996 |
+
{
|
2997 |
+
"epoch": 0.5614406779661016,
|
2998 |
+
"grad_norm": 3.71875,
|
2999 |
+
"learning_rate": 4.398989568717226e-06,
|
3000 |
+
"loss": 2.0168,
|
3001 |
+
"step": 424
|
3002 |
+
},
|
3003 |
+
{
|
3004 |
+
"epoch": 0.5627648305084746,
|
3005 |
+
"grad_norm": 4.84375,
|
3006 |
+
"learning_rate": 4.377246353355899e-06,
|
3007 |
+
"loss": 1.9603,
|
3008 |
+
"step": 425
|
3009 |
+
},
|
3010 |
+
{
|
3011 |
+
"epoch": 0.5640889830508474,
|
3012 |
+
"grad_norm": 3.703125,
|
3013 |
+
"learning_rate": 4.355515093749897e-06,
|
3014 |
+
"loss": 1.9786,
|
3015 |
+
"step": 426
|
3016 |
+
},
|
3017 |
+
{
|
3018 |
+
"epoch": 0.5654131355932204,
|
3019 |
+
"grad_norm": 3.703125,
|
3020 |
+
"learning_rate": 4.333796207100505e-06,
|
3021 |
+
"loss": 1.9911,
|
3022 |
+
"step": 427
|
3023 |
+
},
|
3024 |
+
{
|
3025 |
+
"epoch": 0.5667372881355932,
|
3026 |
+
"grad_norm": 5.25,
|
3027 |
+
"learning_rate": 4.312090110371473e-06,
|
3028 |
+
"loss": 1.9617,
|
3029 |
+
"step": 428
|
3030 |
+
},
|
3031 |
+
{
|
3032 |
+
"epoch": 0.5680614406779662,
|
3033 |
+
"grad_norm": 3.921875,
|
3034 |
+
"learning_rate": 4.290397220281002e-06,
|
3035 |
+
"loss": 1.9384,
|
3036 |
+
"step": 429
|
3037 |
+
},
|
3038 |
+
{
|
3039 |
+
"epoch": 0.569385593220339,
|
3040 |
+
"grad_norm": 3.84375,
|
3041 |
+
"learning_rate": 4.268717953293755e-06,
|
3042 |
+
"loss": 2.1731,
|
3043 |
+
"step": 430
|
3044 |
+
},
|
3045 |
+
{
|
3046 |
+
"epoch": 0.5707097457627118,
|
3047 |
+
"grad_norm": 3.796875,
|
3048 |
+
"learning_rate": 4.247052725612853e-06,
|
3049 |
+
"loss": 1.8694,
|
3050 |
+
"step": 431
|
3051 |
+
},
|
3052 |
+
{
|
3053 |
+
"epoch": 0.5720338983050848,
|
3054 |
+
"grad_norm": 3.90625,
|
3055 |
+
"learning_rate": 4.22540195317189e-06,
|
3056 |
+
"loss": 1.8741,
|
3057 |
+
"step": 432
|
3058 |
+
},
|
3059 |
+
{
|
3060 |
+
"epoch": 0.5733580508474576,
|
3061 |
+
"grad_norm": 3.6875,
|
3062 |
+
"learning_rate": 4.203766051626939e-06,
|
3063 |
+
"loss": 1.9796,
|
3064 |
+
"step": 433
|
3065 |
+
},
|
3066 |
+
{
|
3067 |
+
"epoch": 0.5746822033898306,
|
3068 |
+
"grad_norm": 4.0,
|
3069 |
+
"learning_rate": 4.182145436348587e-06,
|
3070 |
+
"loss": 1.9154,
|
3071 |
+
"step": 434
|
3072 |
+
},
|
3073 |
+
{
|
3074 |
+
"epoch": 0.5760063559322034,
|
3075 |
+
"grad_norm": 3.6875,
|
3076 |
+
"learning_rate": 4.160540522413947e-06,
|
3077 |
+
"loss": 1.9181,
|
3078 |
+
"step": 435
|
3079 |
+
},
|
3080 |
+
{
|
3081 |
+
"epoch": 0.5773305084745762,
|
3082 |
+
"grad_norm": 3.6875,
|
3083 |
+
"learning_rate": 4.138951724598692e-06,
|
3084 |
+
"loss": 2.0523,
|
3085 |
+
"step": 436
|
3086 |
+
},
|
3087 |
+
{
|
3088 |
+
"epoch": 0.5786546610169492,
|
3089 |
+
"grad_norm": 3.8125,
|
3090 |
+
"learning_rate": 4.1173794573691e-06,
|
3091 |
+
"loss": 1.8367,
|
3092 |
+
"step": 437
|
3093 |
+
},
|
3094 |
+
{
|
3095 |
+
"epoch": 0.579978813559322,
|
3096 |
+
"grad_norm": 3.96875,
|
3097 |
+
"learning_rate": 4.095824134874087e-06,
|
3098 |
+
"loss": 2.0884,
|
3099 |
+
"step": 438
|
3100 |
+
},
|
3101 |
+
{
|
3102 |
+
"epoch": 0.581302966101695,
|
3103 |
+
"grad_norm": 4.03125,
|
3104 |
+
"learning_rate": 4.074286170937265e-06,
|
3105 |
+
"loss": 2.0347,
|
3106 |
+
"step": 439
|
3107 |
+
},
|
3108 |
+
{
|
3109 |
+
"epoch": 0.5826271186440678,
|
3110 |
+
"grad_norm": 4.0625,
|
3111 |
+
"learning_rate": 4.052765979048986e-06,
|
3112 |
+
"loss": 2.0196,
|
3113 |
+
"step": 440
|
3114 |
+
},
|
3115 |
+
{
|
3116 |
+
"epoch": 0.5839512711864406,
|
3117 |
+
"grad_norm": 3.734375,
|
3118 |
+
"learning_rate": 4.031263972358419e-06,
|
3119 |
+
"loss": 1.9662,
|
3120 |
+
"step": 441
|
3121 |
+
},
|
3122 |
+
{
|
3123 |
+
"epoch": 0.5852754237288136,
|
3124 |
+
"grad_norm": 3.6875,
|
3125 |
+
"learning_rate": 4.009780563665601e-06,
|
3126 |
+
"loss": 1.9913,
|
3127 |
+
"step": 442
|
3128 |
+
},
|
3129 |
+
{
|
3130 |
+
"epoch": 0.5865995762711864,
|
3131 |
+
"grad_norm": 3.90625,
|
3132 |
+
"learning_rate": 3.988316165413528e-06,
|
3133 |
+
"loss": 2.0734,
|
3134 |
+
"step": 443
|
3135 |
+
},
|
3136 |
+
{
|
3137 |
+
"epoch": 0.5879237288135594,
|
3138 |
+
"grad_norm": 3.71875,
|
3139 |
+
"learning_rate": 3.966871189680223e-06,
|
3140 |
+
"loss": 1.9153,
|
3141 |
+
"step": 444
|
3142 |
+
},
|
3143 |
+
{
|
3144 |
+
"epoch": 0.5892478813559322,
|
3145 |
+
"grad_norm": 3.96875,
|
3146 |
+
"learning_rate": 3.945446048170839e-06,
|
3147 |
+
"loss": 1.9798,
|
3148 |
+
"step": 445
|
3149 |
+
},
|
3150 |
+
{
|
3151 |
+
"epoch": 0.590572033898305,
|
3152 |
+
"grad_norm": 3.8125,
|
3153 |
+
"learning_rate": 3.924041152209739e-06,
|
3154 |
+
"loss": 1.9039,
|
3155 |
+
"step": 446
|
3156 |
+
},
|
3157 |
+
{
|
3158 |
+
"epoch": 0.591896186440678,
|
3159 |
+
"grad_norm": 4.4375,
|
3160 |
+
"learning_rate": 3.902656912732616e-06,
|
3161 |
+
"loss": 1.9863,
|
3162 |
+
"step": 447
|
3163 |
+
},
|
3164 |
+
{
|
3165 |
+
"epoch": 0.5932203389830508,
|
3166 |
+
"grad_norm": 3.984375,
|
3167 |
+
"learning_rate": 3.881293740278588e-06,
|
3168 |
+
"loss": 1.9465,
|
3169 |
+
"step": 448
|
3170 |
+
},
|
3171 |
+
{
|
3172 |
+
"epoch": 0.5945444915254238,
|
3173 |
+
"grad_norm": 3.71875,
|
3174 |
+
"learning_rate": 3.859952044982329e-06,
|
3175 |
+
"loss": 2.0645,
|
3176 |
+
"step": 449
|
3177 |
+
},
|
3178 |
+
{
|
3179 |
+
"epoch": 0.5958686440677966,
|
3180 |
+
"grad_norm": 3.828125,
|
3181 |
+
"learning_rate": 3.83863223656619e-06,
|
3182 |
+
"loss": 2.0472,
|
3183 |
+
"step": 450
|
3184 |
+
},
|
3185 |
+
{
|
3186 |
+
"epoch": 0.5971927966101694,
|
3187 |
+
"grad_norm": 3.671875,
|
3188 |
+
"learning_rate": 3.8173347243323275e-06,
|
3189 |
+
"loss": 1.8184,
|
3190 |
+
"step": 451
|
3191 |
+
},
|
3192 |
+
{
|
3193 |
+
"epoch": 0.5985169491525424,
|
3194 |
+
"grad_norm": 4.0625,
|
3195 |
+
"learning_rate": 3.7960599171548572e-06,
|
3196 |
+
"loss": 1.9835,
|
3197 |
+
"step": 452
|
3198 |
+
},
|
3199 |
+
{
|
3200 |
+
"epoch": 0.5998411016949152,
|
3201 |
+
"grad_norm": 3.671875,
|
3202 |
+
"learning_rate": 3.774808223471996e-06,
|
3203 |
+
"loss": 1.9712,
|
3204 |
+
"step": 453
|
3205 |
+
},
|
3206 |
+
{
|
3207 |
+
"epoch": 0.6011652542372882,
|
3208 |
+
"grad_norm": 3.703125,
|
3209 |
+
"learning_rate": 3.7535800512782254e-06,
|
3210 |
+
"loss": 2.0324,
|
3211 |
+
"step": 454
|
3212 |
+
},
|
3213 |
+
{
|
3214 |
+
"epoch": 0.602489406779661,
|
3215 |
+
"grad_norm": 3.59375,
|
3216 |
+
"learning_rate": 3.732375808116451e-06,
|
3217 |
+
"loss": 2.1901,
|
3218 |
+
"step": 455
|
3219 |
+
},
|
3220 |
+
{
|
3221 |
+
"epoch": 0.6038135593220338,
|
3222 |
+
"grad_norm": 3.625,
|
3223 |
+
"learning_rate": 3.711195901070188e-06,
|
3224 |
+
"loss": 2.031,
|
3225 |
+
"step": 456
|
3226 |
+
},
|
3227 |
+
{
|
3228 |
+
"epoch": 0.6051377118644068,
|
3229 |
+
"grad_norm": 3.78125,
|
3230 |
+
"learning_rate": 3.690040736755742e-06,
|
3231 |
+
"loss": 2.0682,
|
3232 |
+
"step": 457
|
3233 |
+
},
|
3234 |
+
{
|
3235 |
+
"epoch": 0.6064618644067796,
|
3236 |
+
"grad_norm": 3.78125,
|
3237 |
+
"learning_rate": 3.6689107213144025e-06,
|
3238 |
+
"loss": 2.1191,
|
3239 |
+
"step": 458
|
3240 |
+
},
|
3241 |
+
{
|
3242 |
+
"epoch": 0.6077860169491526,
|
3243 |
+
"grad_norm": 3.65625,
|
3244 |
+
"learning_rate": 3.6478062604046406e-06,
|
3245 |
+
"loss": 1.921,
|
3246 |
+
"step": 459
|
3247 |
+
},
|
3248 |
+
{
|
3249 |
+
"epoch": 0.6091101694915254,
|
3250 |
+
"grad_norm": 6.03125,
|
3251 |
+
"learning_rate": 3.626727759194334e-06,
|
3252 |
+
"loss": 2.0207,
|
3253 |
+
"step": 460
|
3254 |
+
},
|
3255 |
+
{
|
3256 |
+
"epoch": 0.6104343220338984,
|
3257 |
+
"grad_norm": 3.59375,
|
3258 |
+
"learning_rate": 3.6056756223529734e-06,
|
3259 |
+
"loss": 2.1463,
|
3260 |
+
"step": 461
|
3261 |
+
},
|
3262 |
+
{
|
3263 |
+
"epoch": 0.6117584745762712,
|
3264 |
+
"grad_norm": 4.1875,
|
3265 |
+
"learning_rate": 3.5846502540439076e-06,
|
3266 |
+
"loss": 1.9282,
|
3267 |
+
"step": 462
|
3268 |
+
},
|
3269 |
+
{
|
3270 |
+
"epoch": 0.613082627118644,
|
3271 |
+
"grad_norm": 3.53125,
|
3272 |
+
"learning_rate": 3.5636520579165704e-06,
|
3273 |
+
"loss": 2.1905,
|
3274 |
+
"step": 463
|
3275 |
+
},
|
3276 |
+
{
|
3277 |
+
"epoch": 0.614406779661017,
|
3278 |
+
"grad_norm": 3.515625,
|
3279 |
+
"learning_rate": 3.542681437098745e-06,
|
3280 |
+
"loss": 2.1518,
|
3281 |
+
"step": 464
|
3282 |
+
},
|
3283 |
+
{
|
3284 |
+
"epoch": 0.6157309322033898,
|
3285 |
+
"grad_norm": 3.8125,
|
3286 |
+
"learning_rate": 3.5217387941888117e-06,
|
3287 |
+
"loss": 2.0076,
|
3288 |
+
"step": 465
|
3289 |
+
},
|
3290 |
+
{
|
3291 |
+
"epoch": 0.6170550847457628,
|
3292 |
+
"grad_norm": 3.765625,
|
3293 |
+
"learning_rate": 3.5008245312480326e-06,
|
3294 |
+
"loss": 2.1018,
|
3295 |
+
"step": 466
|
3296 |
+
},
|
3297 |
+
{
|
3298 |
+
"epoch": 0.6183792372881356,
|
3299 |
+
"grad_norm": 4.09375,
|
3300 |
+
"learning_rate": 3.479939049792817e-06,
|
3301 |
+
"loss": 1.8781,
|
3302 |
+
"step": 467
|
3303 |
+
},
|
3304 |
+
{
|
3305 |
+
"epoch": 0.6197033898305084,
|
3306 |
+
"grad_norm": 3.78125,
|
3307 |
+
"learning_rate": 3.4590827507870257e-06,
|
3308 |
+
"loss": 2.0801,
|
3309 |
+
"step": 468
|
3310 |
+
},
|
3311 |
+
{
|
3312 |
+
"epoch": 0.6210275423728814,
|
3313 |
+
"grad_norm": 4.375,
|
3314 |
+
"learning_rate": 3.4382560346342707e-06,
|
3315 |
+
"loss": 2.211,
|
3316 |
+
"step": 469
|
3317 |
+
},
|
3318 |
+
{
|
3319 |
+
"epoch": 0.6223516949152542,
|
3320 |
+
"grad_norm": 3.828125,
|
3321 |
+
"learning_rate": 3.4174593011702197e-06,
|
3322 |
+
"loss": 1.8481,
|
3323 |
+
"step": 470
|
3324 |
+
},
|
3325 |
+
{
|
3326 |
+
"epoch": 0.6236758474576272,
|
3327 |
+
"grad_norm": 3.671875,
|
3328 |
+
"learning_rate": 3.396692949654933e-06,
|
3329 |
+
"loss": 2.0414,
|
3330 |
+
"step": 471
|
3331 |
+
},
|
3332 |
+
{
|
3333 |
+
"epoch": 0.625,
|
3334 |
+
"grad_norm": 3.984375,
|
3335 |
+
"learning_rate": 3.3759573787651877e-06,
|
3336 |
+
"loss": 2.094,
|
3337 |
+
"step": 472
|
3338 |
+
},
|
3339 |
+
{
|
3340 |
+
"epoch": 0.6263241525423728,
|
3341 |
+
"grad_norm": 3.734375,
|
3342 |
+
"learning_rate": 3.3552529865868323e-06,
|
3343 |
+
"loss": 2.0496,
|
3344 |
+
"step": 473
|
3345 |
+
},
|
3346 |
+
{
|
3347 |
+
"epoch": 0.6276483050847458,
|
3348 |
+
"grad_norm": 3.84375,
|
3349 |
+
"learning_rate": 3.3345801706071325e-06,
|
3350 |
+
"loss": 2.113,
|
3351 |
+
"step": 474
|
3352 |
+
},
|
3353 |
+
{
|
3354 |
+
"epoch": 0.6289724576271186,
|
3355 |
+
"grad_norm": 4.03125,
|
3356 |
+
"learning_rate": 3.3139393277071554e-06,
|
3357 |
+
"loss": 1.8577,
|
3358 |
+
"step": 475
|
3359 |
+
},
|
3360 |
+
{
|
3361 |
+
"epoch": 0.6302966101694916,
|
3362 |
+
"grad_norm": 5.21875,
|
3363 |
+
"learning_rate": 3.2933308541541365e-06,
|
3364 |
+
"loss": 2.059,
|
3365 |
+
"step": 476
|
3366 |
+
},
|
3367 |
+
{
|
3368 |
+
"epoch": 0.6316207627118644,
|
3369 |
+
"grad_norm": 3.5625,
|
3370 |
+
"learning_rate": 3.2727551455938832e-06,
|
3371 |
+
"loss": 2.1471,
|
3372 |
+
"step": 477
|
3373 |
+
},
|
3374 |
+
{
|
3375 |
+
"epoch": 0.6329449152542372,
|
3376 |
+
"grad_norm": 3.953125,
|
3377 |
+
"learning_rate": 3.252212597043167e-06,
|
3378 |
+
"loss": 2.0538,
|
3379 |
+
"step": 478
|
3380 |
+
},
|
3381 |
+
{
|
3382 |
+
"epoch": 0.6342690677966102,
|
3383 |
+
"grad_norm": 3.8125,
|
3384 |
+
"learning_rate": 3.2317036028821523e-06,
|
3385 |
+
"loss": 1.9275,
|
3386 |
+
"step": 479
|
3387 |
+
},
|
3388 |
+
{
|
3389 |
+
"epoch": 0.635593220338983,
|
3390 |
+
"grad_norm": 4.125,
|
3391 |
+
"learning_rate": 3.2112285568468166e-06,
|
3392 |
+
"loss": 1.9979,
|
3393 |
+
"step": 480
|
3394 |
+
},
|
3395 |
+
{
|
3396 |
+
"epoch": 0.636917372881356,
|
3397 |
+
"grad_norm": 3.796875,
|
3398 |
+
"learning_rate": 3.190787852021396e-06,
|
3399 |
+
"loss": 2.1286,
|
3400 |
+
"step": 481
|
3401 |
+
},
|
3402 |
+
{
|
3403 |
+
"epoch": 0.6382415254237288,
|
3404 |
+
"grad_norm": 3.78125,
|
3405 |
+
"learning_rate": 3.1703818808308327e-06,
|
3406 |
+
"loss": 2.007,
|
3407 |
+
"step": 482
|
3408 |
+
},
|
3409 |
+
{
|
3410 |
+
"epoch": 0.6395656779661016,
|
3411 |
+
"grad_norm": 3.859375,
|
3412 |
+
"learning_rate": 3.1500110350332492e-06,
|
3413 |
+
"loss": 1.9457,
|
3414 |
+
"step": 483
|
3415 |
+
},
|
3416 |
+
{
|
3417 |
+
"epoch": 0.6408898305084746,
|
3418 |
+
"grad_norm": 4.09375,
|
3419 |
+
"learning_rate": 3.1296757057124243e-06,
|
3420 |
+
"loss": 1.9245,
|
3421 |
+
"step": 484
|
3422 |
+
},
|
3423 |
+
{
|
3424 |
+
"epoch": 0.6422139830508474,
|
3425 |
+
"grad_norm": 4.125,
|
3426 |
+
"learning_rate": 3.1093762832702775e-06,
|
3427 |
+
"loss": 2.0545,
|
3428 |
+
"step": 485
|
3429 |
+
},
|
3430 |
+
{
|
3431 |
+
"epoch": 0.6435381355932204,
|
3432 |
+
"grad_norm": 3.859375,
|
3433 |
+
"learning_rate": 3.08911315741939e-06,
|
3434 |
+
"loss": 2.0104,
|
3435 |
+
"step": 486
|
3436 |
+
},
|
3437 |
+
{
|
3438 |
+
"epoch": 0.6448622881355932,
|
3439 |
+
"grad_norm": 3.515625,
|
3440 |
+
"learning_rate": 3.0688867171755043e-06,
|
3441 |
+
"loss": 2.0609,
|
3442 |
+
"step": 487
|
3443 |
+
},
|
3444 |
+
{
|
3445 |
+
"epoch": 0.6461864406779662,
|
3446 |
+
"grad_norm": 3.609375,
|
3447 |
+
"learning_rate": 3.048697350850073e-06,
|
3448 |
+
"loss": 2.0671,
|
3449 |
+
"step": 488
|
3450 |
+
},
|
3451 |
+
{
|
3452 |
+
"epoch": 0.647510593220339,
|
3453 |
+
"grad_norm": 3.96875,
|
3454 |
+
"learning_rate": 3.0285454460427855e-06,
|
3455 |
+
"loss": 1.9852,
|
3456 |
+
"step": 489
|
3457 |
+
},
|
3458 |
+
{
|
3459 |
+
"epoch": 0.6488347457627118,
|
3460 |
+
"grad_norm": 3.859375,
|
3461 |
+
"learning_rate": 3.0084313896341504e-06,
|
3462 |
+
"loss": 1.9553,
|
3463 |
+
"step": 490
|
3464 |
+
},
|
3465 |
+
{
|
3466 |
+
"epoch": 0.6501588983050848,
|
3467 |
+
"grad_norm": 3.625,
|
3468 |
+
"learning_rate": 2.988355567778043e-06,
|
3469 |
+
"loss": 2.1243,
|
3470 |
+
"step": 491
|
3471 |
+
},
|
3472 |
+
{
|
3473 |
+
"epoch": 0.6514830508474576,
|
3474 |
+
"grad_norm": 4.09375,
|
3475 |
+
"learning_rate": 2.9683183658943106e-06,
|
3476 |
+
"loss": 2.137,
|
3477 |
+
"step": 492
|
3478 |
+
},
|
3479 |
+
{
|
3480 |
+
"epoch": 0.6528072033898306,
|
3481 |
+
"grad_norm": 3.9375,
|
3482 |
+
"learning_rate": 2.9483201686613626e-06,
|
3483 |
+
"loss": 1.9655,
|
3484 |
+
"step": 493
|
3485 |
+
},
|
3486 |
+
{
|
3487 |
+
"epoch": 0.6541313559322034,
|
3488 |
+
"grad_norm": 4.03125,
|
3489 |
+
"learning_rate": 2.9283613600087933e-06,
|
3490 |
+
"loss": 2.0074,
|
3491 |
+
"step": 494
|
3492 |
+
},
|
3493 |
+
{
|
3494 |
+
"epoch": 0.6554555084745762,
|
3495 |
+
"grad_norm": 3.84375,
|
3496 |
+
"learning_rate": 2.9084423231099985e-06,
|
3497 |
+
"loss": 1.8278,
|
3498 |
+
"step": 495
|
3499 |
+
},
|
3500 |
+
{
|
3501 |
+
"epoch": 0.6567796610169492,
|
3502 |
+
"grad_norm": 3.765625,
|
3503 |
+
"learning_rate": 2.8885634403748397e-06,
|
3504 |
+
"loss": 2.0682,
|
3505 |
+
"step": 496
|
3506 |
+
},
|
3507 |
+
{
|
3508 |
+
"epoch": 0.658103813559322,
|
3509 |
+
"grad_norm": 3.796875,
|
3510 |
+
"learning_rate": 2.8687250934422774e-06,
|
3511 |
+
"loss": 2.0537,
|
3512 |
+
"step": 497
|
3513 |
+
},
|
3514 |
+
{
|
3515 |
+
"epoch": 0.659427966101695,
|
3516 |
+
"grad_norm": 3.828125,
|
3517 |
+
"learning_rate": 2.8489276631730633e-06,
|
3518 |
+
"loss": 1.848,
|
3519 |
+
"step": 498
|
3520 |
+
},
|
3521 |
+
{
|
3522 |
+
"epoch": 0.6607521186440678,
|
3523 |
+
"grad_norm": 3.765625,
|
3524 |
+
"learning_rate": 2.8291715296424282e-06,
|
3525 |
+
"loss": 1.9693,
|
3526 |
+
"step": 499
|
3527 |
+
},
|
3528 |
+
{
|
3529 |
+
"epoch": 0.6620762711864406,
|
3530 |
+
"grad_norm": 3.59375,
|
3531 |
+
"learning_rate": 2.809457072132766e-06,
|
3532 |
+
"loss": 1.8889,
|
3533 |
+
"step": 500
|
3534 |
+
}
|
3535 |
+
],
|
3536 |
+
"logging_steps": 1.0,
|
3537 |
+
"max_steps": 755,
|
3538 |
+
"num_input_tokens_seen": 0,
|
3539 |
+
"num_train_epochs": 1,
|
3540 |
+
"save_steps": 500,
|
3541 |
+
"total_flos": 8.160964319714918e+17,
|
3542 |
+
"train_batch_size": 1,
|
3543 |
+
"trial_name": null,
|
3544 |
+
"trial_params": null
|
3545 |
+
}
|
checkpoint-500/README.md
ADDED
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
base_model: HIT-SCIR/Chinese-Mixtral-8x7B
|
3 |
+
library_name: peft
|
4 |
+
---
|
5 |
+
|
6 |
+
# Model Card for Model ID
|
7 |
+
|
8 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
9 |
+
|
10 |
+
|
11 |
+
|
12 |
+
## Model Details
|
13 |
+
|
14 |
+
### Model Description
|
15 |
+
|
16 |
+
<!-- Provide a longer summary of what this model is. -->
|
17 |
+
|
18 |
+
|
19 |
+
|
20 |
+
- **Developed by:** [More Information Needed]
|
21 |
+
- **Funded by [optional]:** [More Information Needed]
|
22 |
+
- **Shared by [optional]:** [More Information Needed]
|
23 |
+
- **Model type:** [More Information Needed]
|
24 |
+
- **Language(s) (NLP):** [More Information Needed]
|
25 |
+
- **License:** [More Information Needed]
|
26 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
27 |
+
|
28 |
+
### Model Sources [optional]
|
29 |
+
|
30 |
+
<!-- Provide the basic links for the model. -->
|
31 |
+
|
32 |
+
- **Repository:** [More Information Needed]
|
33 |
+
- **Paper [optional]:** [More Information Needed]
|
34 |
+
- **Demo [optional]:** [More Information Needed]
|
35 |
+
|
36 |
+
## Uses
|
37 |
+
|
38 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
39 |
+
|
40 |
+
### Direct Use
|
41 |
+
|
42 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
43 |
+
|
44 |
+
[More Information Needed]
|
45 |
+
|
46 |
+
### Downstream Use [optional]
|
47 |
+
|
48 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
49 |
+
|
50 |
+
[More Information Needed]
|
51 |
+
|
52 |
+
### Out-of-Scope Use
|
53 |
+
|
54 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
55 |
+
|
56 |
+
[More Information Needed]
|
57 |
+
|
58 |
+
## Bias, Risks, and Limitations
|
59 |
+
|
60 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
61 |
+
|
62 |
+
[More Information Needed]
|
63 |
+
|
64 |
+
### Recommendations
|
65 |
+
|
66 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
67 |
+
|
68 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
69 |
+
|
70 |
+
## How to Get Started with the Model
|
71 |
+
|
72 |
+
Use the code below to get started with the model.
|
73 |
+
|
74 |
+
[More Information Needed]
|
75 |
+
|
76 |
+
## Training Details
|
77 |
+
|
78 |
+
### Training Data
|
79 |
+
|
80 |
+
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
81 |
+
|
82 |
+
[More Information Needed]
|
83 |
+
|
84 |
+
### Training Procedure
|
85 |
+
|
86 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
87 |
+
|
88 |
+
#### Preprocessing [optional]
|
89 |
+
|
90 |
+
[More Information Needed]
|
91 |
+
|
92 |
+
|
93 |
+
#### Training Hyperparameters
|
94 |
+
|
95 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
96 |
+
|
97 |
+
#### Speeds, Sizes, Times [optional]
|
98 |
+
|
99 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
100 |
+
|
101 |
+
[More Information Needed]
|
102 |
+
|
103 |
+
## Evaluation
|
104 |
+
|
105 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
106 |
+
|
107 |
+
### Testing Data, Factors & Metrics
|
108 |
+
|
109 |
+
#### Testing Data
|
110 |
+
|
111 |
+
<!-- This should link to a Dataset Card if possible. -->
|
112 |
+
|
113 |
+
[More Information Needed]
|
114 |
+
|
115 |
+
#### Factors
|
116 |
+
|
117 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
118 |
+
|
119 |
+
[More Information Needed]
|
120 |
+
|
121 |
+
#### Metrics
|
122 |
+
|
123 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
124 |
+
|
125 |
+
[More Information Needed]
|
126 |
+
|
127 |
+
### Results
|
128 |
+
|
129 |
+
[More Information Needed]
|
130 |
+
|
131 |
+
#### Summary
|
132 |
+
|
133 |
+
|
134 |
+
|
135 |
+
## Model Examination [optional]
|
136 |
+
|
137 |
+
<!-- Relevant interpretability work for the model goes here -->
|
138 |
+
|
139 |
+
[More Information Needed]
|
140 |
+
|
141 |
+
## Environmental Impact
|
142 |
+
|
143 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
144 |
+
|
145 |
+
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
146 |
+
|
147 |
+
- **Hardware Type:** [More Information Needed]
|
148 |
+
- **Hours used:** [More Information Needed]
|
149 |
+
- **Cloud Provider:** [More Information Needed]
|
150 |
+
- **Compute Region:** [More Information Needed]
|
151 |
+
- **Carbon Emitted:** [More Information Needed]
|
152 |
+
|
153 |
+
## Technical Specifications [optional]
|
154 |
+
|
155 |
+
### Model Architecture and Objective
|
156 |
+
|
157 |
+
[More Information Needed]
|
158 |
+
|
159 |
+
### Compute Infrastructure
|
160 |
+
|
161 |
+
[More Information Needed]
|
162 |
+
|
163 |
+
#### Hardware
|
164 |
+
|
165 |
+
[More Information Needed]
|
166 |
+
|
167 |
+
#### Software
|
168 |
+
|
169 |
+
[More Information Needed]
|
170 |
+
|
171 |
+
## Citation [optional]
|
172 |
+
|
173 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
174 |
+
|
175 |
+
**BibTeX:**
|
176 |
+
|
177 |
+
[More Information Needed]
|
178 |
+
|
179 |
+
**APA:**
|
180 |
+
|
181 |
+
[More Information Needed]
|
182 |
+
|
183 |
+
## Glossary [optional]
|
184 |
+
|
185 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
186 |
+
|
187 |
+
[More Information Needed]
|
188 |
+
|
189 |
+
## More Information [optional]
|
190 |
+
|
191 |
+
[More Information Needed]
|
192 |
+
|
193 |
+
## Model Card Authors [optional]
|
194 |
+
|
195 |
+
[More Information Needed]
|
196 |
+
|
197 |
+
## Model Card Contact
|
198 |
+
|
199 |
+
[More Information Needed]
|
200 |
+
### Framework versions
|
201 |
+
|
202 |
+
- PEFT 0.13.2
|
checkpoint-500/adapter_config.json
ADDED
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "HIT-SCIR/Chinese-Mixtral-8x7B",
|
5 |
+
"bias": "none",
|
6 |
+
"fan_in_fan_out": false,
|
7 |
+
"inference_mode": true,
|
8 |
+
"init_lora_weights": true,
|
9 |
+
"layer_replication": null,
|
10 |
+
"layers_pattern": null,
|
11 |
+
"layers_to_transform": null,
|
12 |
+
"loftq_config": {},
|
13 |
+
"lora_alpha": 128,
|
14 |
+
"lora_dropout": 0.05,
|
15 |
+
"megatron_config": null,
|
16 |
+
"megatron_core": "megatron.core",
|
17 |
+
"modules_to_save": [
|
18 |
+
"embed_tokens",
|
19 |
+
"lm_head"
|
20 |
+
],
|
21 |
+
"peft_type": "LORA",
|
22 |
+
"r": 64,
|
23 |
+
"rank_pattern": {},
|
24 |
+
"revision": null,
|
25 |
+
"target_modules": [
|
26 |
+
"o_proj",
|
27 |
+
"w3",
|
28 |
+
"w2",
|
29 |
+
"q_proj",
|
30 |
+
"v_proj",
|
31 |
+
"k_proj",
|
32 |
+
"w1"
|
33 |
+
],
|
34 |
+
"task_type": "CAUSAL_LM",
|
35 |
+
"use_dora": false,
|
36 |
+
"use_rslora": false
|
37 |
+
}
|
checkpoint-500/adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:869c0a29e5f213301cae4a40e2ebda015e5c8827060d3fd10889de1700fe3452
|
3 |
+
size 2855150432
|
checkpoint-500/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:037904cde69c61f1defddcc37e3182d35e750584d21f2a458611b2990c3c8e78
|
3 |
+
size 5711286983
|
checkpoint-500/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f56cd52d1f16d6557e3de3a7f4fa135a846ad195683a8b9fa440e0c50a897dad
|
3 |
+
size 14575
|
checkpoint-500/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e76413f7f5adb64ff2a38f8e8eb48d92ecc3f523c077caa6e0f44e59f3b3cc97
|
3 |
+
size 627
|
checkpoint-500/special_tokens_map.json
ADDED
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<s>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": {
|
10 |
+
"content": "</s>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": "</s>",
|
17 |
+
"unk_token": {
|
18 |
+
"content": "<unk>",
|
19 |
+
"lstrip": false,
|
20 |
+
"normalized": false,
|
21 |
+
"rstrip": false,
|
22 |
+
"single_word": false
|
23 |
+
}
|
24 |
+
}
|
checkpoint-500/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-500/tokenizer.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:86840d604f9e18ebbdc35aa937cfc2486fe774534ceea0fd3f667a72bc7584b2
|
3 |
+
size 925420
|
checkpoint-500/tokenizer_config.json
ADDED
@@ -0,0 +1,42 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": true,
|
3 |
+
"add_eos_token": false,
|
4 |
+
"added_tokens_decoder": {
|
5 |
+
"0": {
|
6 |
+
"content": "<unk>",
|
7 |
+
"lstrip": false,
|
8 |
+
"normalized": false,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false,
|
11 |
+
"special": true
|
12 |
+
},
|
13 |
+
"1": {
|
14 |
+
"content": "<s>",
|
15 |
+
"lstrip": false,
|
16 |
+
"normalized": false,
|
17 |
+
"rstrip": false,
|
18 |
+
"single_word": false,
|
19 |
+
"special": true
|
20 |
+
},
|
21 |
+
"2": {
|
22 |
+
"content": "</s>",
|
23 |
+
"lstrip": false,
|
24 |
+
"normalized": false,
|
25 |
+
"rstrip": false,
|
26 |
+
"single_word": false,
|
27 |
+
"special": true
|
28 |
+
}
|
29 |
+
},
|
30 |
+
"additional_special_tokens": [],
|
31 |
+
"bos_token": "<s>",
|
32 |
+
"clean_up_tokenization_spaces": false,
|
33 |
+
"eos_token": "</s>",
|
34 |
+
"legacy": true,
|
35 |
+
"model_max_length": 1000000000000000019884624838656,
|
36 |
+
"pad_token": "</s>",
|
37 |
+
"sp_model_kwargs": {},
|
38 |
+
"spaces_between_special_tokens": false,
|
39 |
+
"tokenizer_class": "LlamaTokenizer",
|
40 |
+
"unk_token": "<unk>",
|
41 |
+
"use_default_system_prompt": false
|
42 |
+
}
|
checkpoint-500/trainer_state.json
ADDED
@@ -0,0 +1,3545 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.6620762711864406,
|
5 |
+
"eval_steps": 200,
|
6 |
+
"global_step": 500,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.0013241525423728813,
|
13 |
+
"grad_norm": 26.125,
|
14 |
+
"learning_rate": 2.6315789473684213e-07,
|
15 |
+
"loss": 3.7676,
|
16 |
+
"step": 1
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.0013241525423728813,
|
20 |
+
"eval_AskDoctor-Chinese_loss": 3.761261463165283,
|
21 |
+
"eval_AskDoctor-Chinese_runtime": 15.9737,
|
22 |
+
"eval_AskDoctor-Chinese_samples_per_second": 1.878,
|
23 |
+
"eval_AskDoctor-Chinese_steps_per_second": 1.878,
|
24 |
+
"step": 1
|
25 |
+
},
|
26 |
+
{
|
27 |
+
"epoch": 0.0026483050847457626,
|
28 |
+
"grad_norm": 27.375,
|
29 |
+
"learning_rate": 5.263157894736843e-07,
|
30 |
+
"loss": 3.8885,
|
31 |
+
"step": 2
|
32 |
+
},
|
33 |
+
{
|
34 |
+
"epoch": 0.003972457627118644,
|
35 |
+
"grad_norm": 28.125,
|
36 |
+
"learning_rate": 7.894736842105263e-07,
|
37 |
+
"loss": 3.8601,
|
38 |
+
"step": 3
|
39 |
+
},
|
40 |
+
{
|
41 |
+
"epoch": 0.005296610169491525,
|
42 |
+
"grad_norm": 26.25,
|
43 |
+
"learning_rate": 1.0526315789473685e-06,
|
44 |
+
"loss": 3.8192,
|
45 |
+
"step": 4
|
46 |
+
},
|
47 |
+
{
|
48 |
+
"epoch": 0.0066207627118644065,
|
49 |
+
"grad_norm": 29.0,
|
50 |
+
"learning_rate": 1.3157894736842106e-06,
|
51 |
+
"loss": 3.7572,
|
52 |
+
"step": 5
|
53 |
+
},
|
54 |
+
{
|
55 |
+
"epoch": 0.007944915254237288,
|
56 |
+
"grad_norm": 30.5,
|
57 |
+
"learning_rate": 1.5789473684210526e-06,
|
58 |
+
"loss": 3.9407,
|
59 |
+
"step": 6
|
60 |
+
},
|
61 |
+
{
|
62 |
+
"epoch": 0.009269067796610169,
|
63 |
+
"grad_norm": 30.25,
|
64 |
+
"learning_rate": 1.8421052631578948e-06,
|
65 |
+
"loss": 3.9034,
|
66 |
+
"step": 7
|
67 |
+
},
|
68 |
+
{
|
69 |
+
"epoch": 0.01059322033898305,
|
70 |
+
"grad_norm": 30.5,
|
71 |
+
"learning_rate": 2.105263157894737e-06,
|
72 |
+
"loss": 3.7951,
|
73 |
+
"step": 8
|
74 |
+
},
|
75 |
+
{
|
76 |
+
"epoch": 0.011917372881355932,
|
77 |
+
"grad_norm": 26.0,
|
78 |
+
"learning_rate": 2.368421052631579e-06,
|
79 |
+
"loss": 3.7,
|
80 |
+
"step": 9
|
81 |
+
},
|
82 |
+
{
|
83 |
+
"epoch": 0.013241525423728813,
|
84 |
+
"grad_norm": 28.625,
|
85 |
+
"learning_rate": 2.631578947368421e-06,
|
86 |
+
"loss": 3.6931,
|
87 |
+
"step": 10
|
88 |
+
},
|
89 |
+
{
|
90 |
+
"epoch": 0.014565677966101694,
|
91 |
+
"grad_norm": 25.125,
|
92 |
+
"learning_rate": 2.8947368421052634e-06,
|
93 |
+
"loss": 3.5419,
|
94 |
+
"step": 11
|
95 |
+
},
|
96 |
+
{
|
97 |
+
"epoch": 0.015889830508474576,
|
98 |
+
"grad_norm": 25.5,
|
99 |
+
"learning_rate": 3.157894736842105e-06,
|
100 |
+
"loss": 3.6584,
|
101 |
+
"step": 12
|
102 |
+
},
|
103 |
+
{
|
104 |
+
"epoch": 0.017213983050847457,
|
105 |
+
"grad_norm": 23.875,
|
106 |
+
"learning_rate": 3.421052631578948e-06,
|
107 |
+
"loss": 3.5614,
|
108 |
+
"step": 13
|
109 |
+
},
|
110 |
+
{
|
111 |
+
"epoch": 0.018538135593220338,
|
112 |
+
"grad_norm": 23.875,
|
113 |
+
"learning_rate": 3.6842105263157896e-06,
|
114 |
+
"loss": 3.5783,
|
115 |
+
"step": 14
|
116 |
+
},
|
117 |
+
{
|
118 |
+
"epoch": 0.01986228813559322,
|
119 |
+
"grad_norm": 23.25,
|
120 |
+
"learning_rate": 3.947368421052632e-06,
|
121 |
+
"loss": 3.5407,
|
122 |
+
"step": 15
|
123 |
+
},
|
124 |
+
{
|
125 |
+
"epoch": 0.0211864406779661,
|
126 |
+
"grad_norm": 22.0,
|
127 |
+
"learning_rate": 4.210526315789474e-06,
|
128 |
+
"loss": 3.3536,
|
129 |
+
"step": 16
|
130 |
+
},
|
131 |
+
{
|
132 |
+
"epoch": 0.022510593220338982,
|
133 |
+
"grad_norm": 20.0,
|
134 |
+
"learning_rate": 4.473684210526316e-06,
|
135 |
+
"loss": 3.2685,
|
136 |
+
"step": 17
|
137 |
+
},
|
138 |
+
{
|
139 |
+
"epoch": 0.023834745762711863,
|
140 |
+
"grad_norm": 19.5,
|
141 |
+
"learning_rate": 4.736842105263158e-06,
|
142 |
+
"loss": 3.3136,
|
143 |
+
"step": 18
|
144 |
+
},
|
145 |
+
{
|
146 |
+
"epoch": 0.025158898305084745,
|
147 |
+
"grad_norm": 18.875,
|
148 |
+
"learning_rate": 5e-06,
|
149 |
+
"loss": 3.3371,
|
150 |
+
"step": 19
|
151 |
+
},
|
152 |
+
{
|
153 |
+
"epoch": 0.026483050847457626,
|
154 |
+
"grad_norm": 26.125,
|
155 |
+
"learning_rate": 5.263157894736842e-06,
|
156 |
+
"loss": 3.2935,
|
157 |
+
"step": 20
|
158 |
+
},
|
159 |
+
{
|
160 |
+
"epoch": 0.027807203389830507,
|
161 |
+
"grad_norm": 18.375,
|
162 |
+
"learning_rate": 5.526315789473685e-06,
|
163 |
+
"loss": 3.1542,
|
164 |
+
"step": 21
|
165 |
+
},
|
166 |
+
{
|
167 |
+
"epoch": 0.02913135593220339,
|
168 |
+
"grad_norm": 16.125,
|
169 |
+
"learning_rate": 5.789473684210527e-06,
|
170 |
+
"loss": 3.0697,
|
171 |
+
"step": 22
|
172 |
+
},
|
173 |
+
{
|
174 |
+
"epoch": 0.03045550847457627,
|
175 |
+
"grad_norm": 17.75,
|
176 |
+
"learning_rate": 6.0526315789473685e-06,
|
177 |
+
"loss": 3.0135,
|
178 |
+
"step": 23
|
179 |
+
},
|
180 |
+
{
|
181 |
+
"epoch": 0.03177966101694915,
|
182 |
+
"grad_norm": 16.5,
|
183 |
+
"learning_rate": 6.31578947368421e-06,
|
184 |
+
"loss": 2.9917,
|
185 |
+
"step": 24
|
186 |
+
},
|
187 |
+
{
|
188 |
+
"epoch": 0.033103813559322036,
|
189 |
+
"grad_norm": 14.5625,
|
190 |
+
"learning_rate": 6.578947368421054e-06,
|
191 |
+
"loss": 2.9261,
|
192 |
+
"step": 25
|
193 |
+
},
|
194 |
+
{
|
195 |
+
"epoch": 0.034427966101694914,
|
196 |
+
"grad_norm": 20.375,
|
197 |
+
"learning_rate": 6.842105263157896e-06,
|
198 |
+
"loss": 2.8072,
|
199 |
+
"step": 26
|
200 |
+
},
|
201 |
+
{
|
202 |
+
"epoch": 0.0357521186440678,
|
203 |
+
"grad_norm": 13.375,
|
204 |
+
"learning_rate": 7.1052631578947375e-06,
|
205 |
+
"loss": 2.876,
|
206 |
+
"step": 27
|
207 |
+
},
|
208 |
+
{
|
209 |
+
"epoch": 0.037076271186440676,
|
210 |
+
"grad_norm": 12.5,
|
211 |
+
"learning_rate": 7.368421052631579e-06,
|
212 |
+
"loss": 2.7867,
|
213 |
+
"step": 28
|
214 |
+
},
|
215 |
+
{
|
216 |
+
"epoch": 0.03840042372881356,
|
217 |
+
"grad_norm": 14.625,
|
218 |
+
"learning_rate": 7.631578947368423e-06,
|
219 |
+
"loss": 2.6454,
|
220 |
+
"step": 29
|
221 |
+
},
|
222 |
+
{
|
223 |
+
"epoch": 0.03972457627118644,
|
224 |
+
"grad_norm": 16.625,
|
225 |
+
"learning_rate": 7.894736842105265e-06,
|
226 |
+
"loss": 2.6395,
|
227 |
+
"step": 30
|
228 |
+
},
|
229 |
+
{
|
230 |
+
"epoch": 0.041048728813559324,
|
231 |
+
"grad_norm": 10.1875,
|
232 |
+
"learning_rate": 8.157894736842106e-06,
|
233 |
+
"loss": 2.5909,
|
234 |
+
"step": 31
|
235 |
+
},
|
236 |
+
{
|
237 |
+
"epoch": 0.0423728813559322,
|
238 |
+
"grad_norm": 12.4375,
|
239 |
+
"learning_rate": 8.421052631578948e-06,
|
240 |
+
"loss": 2.5511,
|
241 |
+
"step": 32
|
242 |
+
},
|
243 |
+
{
|
244 |
+
"epoch": 0.043697033898305086,
|
245 |
+
"grad_norm": 10.375,
|
246 |
+
"learning_rate": 8.68421052631579e-06,
|
247 |
+
"loss": 2.4177,
|
248 |
+
"step": 33
|
249 |
+
},
|
250 |
+
{
|
251 |
+
"epoch": 0.045021186440677964,
|
252 |
+
"grad_norm": 8.5625,
|
253 |
+
"learning_rate": 8.947368421052632e-06,
|
254 |
+
"loss": 2.4405,
|
255 |
+
"step": 34
|
256 |
+
},
|
257 |
+
{
|
258 |
+
"epoch": 0.04634533898305085,
|
259 |
+
"grad_norm": 8.5625,
|
260 |
+
"learning_rate": 9.210526315789474e-06,
|
261 |
+
"loss": 2.5073,
|
262 |
+
"step": 35
|
263 |
+
},
|
264 |
+
{
|
265 |
+
"epoch": 0.04766949152542373,
|
266 |
+
"grad_norm": 7.625,
|
267 |
+
"learning_rate": 9.473684210526315e-06,
|
268 |
+
"loss": 2.4031,
|
269 |
+
"step": 36
|
270 |
+
},
|
271 |
+
{
|
272 |
+
"epoch": 0.04899364406779661,
|
273 |
+
"grad_norm": 9.375,
|
274 |
+
"learning_rate": 9.736842105263159e-06,
|
275 |
+
"loss": 2.4698,
|
276 |
+
"step": 37
|
277 |
+
},
|
278 |
+
{
|
279 |
+
"epoch": 0.05031779661016949,
|
280 |
+
"grad_norm": 6.75,
|
281 |
+
"learning_rate": 1e-05,
|
282 |
+
"loss": 2.4379,
|
283 |
+
"step": 38
|
284 |
+
},
|
285 |
+
{
|
286 |
+
"epoch": 0.051641949152542374,
|
287 |
+
"grad_norm": 7.59375,
|
288 |
+
"learning_rate": 9.999952004474853e-06,
|
289 |
+
"loss": 2.3739,
|
290 |
+
"step": 39
|
291 |
+
},
|
292 |
+
{
|
293 |
+
"epoch": 0.05296610169491525,
|
294 |
+
"grad_norm": 6.375,
|
295 |
+
"learning_rate": 9.999808018820836e-06,
|
296 |
+
"loss": 2.433,
|
297 |
+
"step": 40
|
298 |
+
},
|
299 |
+
{
|
300 |
+
"epoch": 0.05429025423728814,
|
301 |
+
"grad_norm": 5.96875,
|
302 |
+
"learning_rate": 9.999568045802216e-06,
|
303 |
+
"loss": 2.4569,
|
304 |
+
"step": 41
|
305 |
+
},
|
306 |
+
{
|
307 |
+
"epoch": 0.055614406779661014,
|
308 |
+
"grad_norm": 5.59375,
|
309 |
+
"learning_rate": 9.99923209002605e-06,
|
310 |
+
"loss": 2.3297,
|
311 |
+
"step": 42
|
312 |
+
},
|
313 |
+
{
|
314 |
+
"epoch": 0.0569385593220339,
|
315 |
+
"grad_norm": 5.5,
|
316 |
+
"learning_rate": 9.998800157942083e-06,
|
317 |
+
"loss": 2.3064,
|
318 |
+
"step": 43
|
319 |
+
},
|
320 |
+
{
|
321 |
+
"epoch": 0.05826271186440678,
|
322 |
+
"grad_norm": 5.375,
|
323 |
+
"learning_rate": 9.99827225784264e-06,
|
324 |
+
"loss": 2.2746,
|
325 |
+
"step": 44
|
326 |
+
},
|
327 |
+
{
|
328 |
+
"epoch": 0.05958686440677966,
|
329 |
+
"grad_norm": 4.9375,
|
330 |
+
"learning_rate": 9.997648399862457e-06,
|
331 |
+
"loss": 2.2981,
|
332 |
+
"step": 45
|
333 |
+
},
|
334 |
+
{
|
335 |
+
"epoch": 0.06091101694915254,
|
336 |
+
"grad_norm": 5.5625,
|
337 |
+
"learning_rate": 9.99692859597849e-06,
|
338 |
+
"loss": 2.0856,
|
339 |
+
"step": 46
|
340 |
+
},
|
341 |
+
{
|
342 |
+
"epoch": 0.062235169491525424,
|
343 |
+
"grad_norm": 5.71875,
|
344 |
+
"learning_rate": 9.996112860009689e-06,
|
345 |
+
"loss": 2.1083,
|
346 |
+
"step": 47
|
347 |
+
},
|
348 |
+
{
|
349 |
+
"epoch": 0.0635593220338983,
|
350 |
+
"grad_norm": 5.53125,
|
351 |
+
"learning_rate": 9.995201207616718e-06,
|
352 |
+
"loss": 2.1841,
|
353 |
+
"step": 48
|
354 |
+
},
|
355 |
+
{
|
356 |
+
"epoch": 0.06488347457627118,
|
357 |
+
"grad_norm": 4.65625,
|
358 |
+
"learning_rate": 9.994193656301676e-06,
|
359 |
+
"loss": 2.3351,
|
360 |
+
"step": 49
|
361 |
+
},
|
362 |
+
{
|
363 |
+
"epoch": 0.06620762711864407,
|
364 |
+
"grad_norm": 5.1875,
|
365 |
+
"learning_rate": 9.993090225407743e-06,
|
366 |
+
"loss": 2.2625,
|
367 |
+
"step": 50
|
368 |
+
},
|
369 |
+
{
|
370 |
+
"epoch": 0.06753177966101695,
|
371 |
+
"grad_norm": 13.0625,
|
372 |
+
"learning_rate": 9.991890936118817e-06,
|
373 |
+
"loss": 2.1591,
|
374 |
+
"step": 51
|
375 |
+
},
|
376 |
+
{
|
377 |
+
"epoch": 0.06885593220338983,
|
378 |
+
"grad_norm": 4.53125,
|
379 |
+
"learning_rate": 9.990595811459109e-06,
|
380 |
+
"loss": 2.2935,
|
381 |
+
"step": 52
|
382 |
+
},
|
383 |
+
{
|
384 |
+
"epoch": 0.0701800847457627,
|
385 |
+
"grad_norm": 4.46875,
|
386 |
+
"learning_rate": 9.98920487629269e-06,
|
387 |
+
"loss": 2.4604,
|
388 |
+
"step": 53
|
389 |
+
},
|
390 |
+
{
|
391 |
+
"epoch": 0.0715042372881356,
|
392 |
+
"grad_norm": 4.5625,
|
393 |
+
"learning_rate": 9.987718157323026e-06,
|
394 |
+
"loss": 2.249,
|
395 |
+
"step": 54
|
396 |
+
},
|
397 |
+
{
|
398 |
+
"epoch": 0.07282838983050847,
|
399 |
+
"grad_norm": 4.59375,
|
400 |
+
"learning_rate": 9.986135683092461e-06,
|
401 |
+
"loss": 2.2686,
|
402 |
+
"step": 55
|
403 |
+
},
|
404 |
+
{
|
405 |
+
"epoch": 0.07415254237288135,
|
406 |
+
"grad_norm": 4.21875,
|
407 |
+
"learning_rate": 9.98445748398167e-06,
|
408 |
+
"loss": 2.291,
|
409 |
+
"step": 56
|
410 |
+
},
|
411 |
+
{
|
412 |
+
"epoch": 0.07547669491525423,
|
413 |
+
"grad_norm": 4.28125,
|
414 |
+
"learning_rate": 9.982683592209069e-06,
|
415 |
+
"loss": 2.1275,
|
416 |
+
"step": 57
|
417 |
+
},
|
418 |
+
{
|
419 |
+
"epoch": 0.07680084745762712,
|
420 |
+
"grad_norm": 12.875,
|
421 |
+
"learning_rate": 9.980814041830203e-06,
|
422 |
+
"loss": 2.1489,
|
423 |
+
"step": 58
|
424 |
+
},
|
425 |
+
{
|
426 |
+
"epoch": 0.078125,
|
427 |
+
"grad_norm": 4.375,
|
428 |
+
"learning_rate": 9.978848868737099e-06,
|
429 |
+
"loss": 2.271,
|
430 |
+
"step": 59
|
431 |
+
},
|
432 |
+
{
|
433 |
+
"epoch": 0.07944915254237288,
|
434 |
+
"grad_norm": 4.84375,
|
435 |
+
"learning_rate": 9.976788110657558e-06,
|
436 |
+
"loss": 2.3377,
|
437 |
+
"step": 60
|
438 |
+
},
|
439 |
+
{
|
440 |
+
"epoch": 0.08077330508474577,
|
441 |
+
"grad_norm": 4.09375,
|
442 |
+
"learning_rate": 9.974631807154447e-06,
|
443 |
+
"loss": 2.3359,
|
444 |
+
"step": 61
|
445 |
+
},
|
446 |
+
{
|
447 |
+
"epoch": 0.08209745762711865,
|
448 |
+
"grad_norm": 4.25,
|
449 |
+
"learning_rate": 9.972379999624935e-06,
|
450 |
+
"loss": 2.2142,
|
451 |
+
"step": 62
|
452 |
+
},
|
453 |
+
{
|
454 |
+
"epoch": 0.08342161016949153,
|
455 |
+
"grad_norm": 12.375,
|
456 |
+
"learning_rate": 9.970032731299697e-06,
|
457 |
+
"loss": 2.1888,
|
458 |
+
"step": 63
|
459 |
+
},
|
460 |
+
{
|
461 |
+
"epoch": 0.0847457627118644,
|
462 |
+
"grad_norm": 4.15625,
|
463 |
+
"learning_rate": 9.967590047242082e-06,
|
464 |
+
"loss": 2.3571,
|
465 |
+
"step": 64
|
466 |
+
},
|
467 |
+
{
|
468 |
+
"epoch": 0.0860699152542373,
|
469 |
+
"grad_norm": 4.25,
|
470 |
+
"learning_rate": 9.96505199434725e-06,
|
471 |
+
"loss": 2.1241,
|
472 |
+
"step": 65
|
473 |
+
},
|
474 |
+
{
|
475 |
+
"epoch": 0.08739406779661017,
|
476 |
+
"grad_norm": 4.65625,
|
477 |
+
"learning_rate": 9.962418621341275e-06,
|
478 |
+
"loss": 2.0733,
|
479 |
+
"step": 66
|
480 |
+
},
|
481 |
+
{
|
482 |
+
"epoch": 0.08871822033898305,
|
483 |
+
"grad_norm": 9.75,
|
484 |
+
"learning_rate": 9.959689978780207e-06,
|
485 |
+
"loss": 2.1612,
|
486 |
+
"step": 67
|
487 |
+
},
|
488 |
+
{
|
489 |
+
"epoch": 0.09004237288135593,
|
490 |
+
"grad_norm": 4.4375,
|
491 |
+
"learning_rate": 9.956866119049095e-06,
|
492 |
+
"loss": 2.1519,
|
493 |
+
"step": 68
|
494 |
+
},
|
495 |
+
{
|
496 |
+
"epoch": 0.09136652542372882,
|
497 |
+
"grad_norm": 9.125,
|
498 |
+
"learning_rate": 9.953947096360996e-06,
|
499 |
+
"loss": 2.1352,
|
500 |
+
"step": 69
|
501 |
+
},
|
502 |
+
{
|
503 |
+
"epoch": 0.0926906779661017,
|
504 |
+
"grad_norm": 4.25,
|
505 |
+
"learning_rate": 9.950932966755917e-06,
|
506 |
+
"loss": 2.1954,
|
507 |
+
"step": 70
|
508 |
+
},
|
509 |
+
{
|
510 |
+
"epoch": 0.09401483050847458,
|
511 |
+
"grad_norm": 4.03125,
|
512 |
+
"learning_rate": 9.947823788099754e-06,
|
513 |
+
"loss": 2.1761,
|
514 |
+
"step": 71
|
515 |
+
},
|
516 |
+
{
|
517 |
+
"epoch": 0.09533898305084745,
|
518 |
+
"grad_norm": 3.921875,
|
519 |
+
"learning_rate": 9.94461962008317e-06,
|
520 |
+
"loss": 2.1397,
|
521 |
+
"step": 72
|
522 |
+
},
|
523 |
+
{
|
524 |
+
"epoch": 0.09666313559322035,
|
525 |
+
"grad_norm": 4.625,
|
526 |
+
"learning_rate": 9.941320524220455e-06,
|
527 |
+
"loss": 2.1281,
|
528 |
+
"step": 73
|
529 |
+
},
|
530 |
+
{
|
531 |
+
"epoch": 0.09798728813559322,
|
532 |
+
"grad_norm": 7.96875,
|
533 |
+
"learning_rate": 9.937926563848345e-06,
|
534 |
+
"loss": 1.8948,
|
535 |
+
"step": 74
|
536 |
+
},
|
537 |
+
{
|
538 |
+
"epoch": 0.0993114406779661,
|
539 |
+
"grad_norm": 4.75,
|
540 |
+
"learning_rate": 9.934437804124807e-06,
|
541 |
+
"loss": 2.3239,
|
542 |
+
"step": 75
|
543 |
+
},
|
544 |
+
{
|
545 |
+
"epoch": 0.10063559322033898,
|
546 |
+
"grad_norm": 3.984375,
|
547 |
+
"learning_rate": 9.93085431202778e-06,
|
548 |
+
"loss": 2.3193,
|
549 |
+
"step": 76
|
550 |
+
},
|
551 |
+
{
|
552 |
+
"epoch": 0.10195974576271187,
|
553 |
+
"grad_norm": 4.34375,
|
554 |
+
"learning_rate": 9.9271761563539e-06,
|
555 |
+
"loss": 2.0956,
|
556 |
+
"step": 77
|
557 |
+
},
|
558 |
+
{
|
559 |
+
"epoch": 0.10328389830508475,
|
560 |
+
"grad_norm": 4.65625,
|
561 |
+
"learning_rate": 9.92340340771717e-06,
|
562 |
+
"loss": 2.3226,
|
563 |
+
"step": 78
|
564 |
+
},
|
565 |
+
{
|
566 |
+
"epoch": 0.10460805084745763,
|
567 |
+
"grad_norm": 4.6875,
|
568 |
+
"learning_rate": 9.919536138547611e-06,
|
569 |
+
"loss": 2.1505,
|
570 |
+
"step": 79
|
571 |
+
},
|
572 |
+
{
|
573 |
+
"epoch": 0.1059322033898305,
|
574 |
+
"grad_norm": 6.1875,
|
575 |
+
"learning_rate": 9.915574423089872e-06,
|
576 |
+
"loss": 2.0939,
|
577 |
+
"step": 80
|
578 |
+
},
|
579 |
+
{
|
580 |
+
"epoch": 0.1072563559322034,
|
581 |
+
"grad_norm": 12.75,
|
582 |
+
"learning_rate": 9.911518337401792e-06,
|
583 |
+
"loss": 2.2263,
|
584 |
+
"step": 81
|
585 |
+
},
|
586 |
+
{
|
587 |
+
"epoch": 0.10858050847457627,
|
588 |
+
"grad_norm": 4.03125,
|
589 |
+
"learning_rate": 9.907367959352964e-06,
|
590 |
+
"loss": 2.1133,
|
591 |
+
"step": 82
|
592 |
+
},
|
593 |
+
{
|
594 |
+
"epoch": 0.10990466101694915,
|
595 |
+
"grad_norm": 3.984375,
|
596 |
+
"learning_rate": 9.903123368623216e-06,
|
597 |
+
"loss": 2.1183,
|
598 |
+
"step": 83
|
599 |
+
},
|
600 |
+
{
|
601 |
+
"epoch": 0.11122881355932203,
|
602 |
+
"grad_norm": 4.46875,
|
603 |
+
"learning_rate": 9.898784646701087e-06,
|
604 |
+
"loss": 2.1461,
|
605 |
+
"step": 84
|
606 |
+
},
|
607 |
+
{
|
608 |
+
"epoch": 0.11255296610169492,
|
609 |
+
"grad_norm": 4.53125,
|
610 |
+
"learning_rate": 9.894351876882277e-06,
|
611 |
+
"loss": 2.1963,
|
612 |
+
"step": 85
|
613 |
+
},
|
614 |
+
{
|
615 |
+
"epoch": 0.1138771186440678,
|
616 |
+
"grad_norm": 5.09375,
|
617 |
+
"learning_rate": 9.889825144268029e-06,
|
618 |
+
"loss": 2.1679,
|
619 |
+
"step": 86
|
620 |
+
},
|
621 |
+
{
|
622 |
+
"epoch": 0.11520127118644068,
|
623 |
+
"grad_norm": 4.34375,
|
624 |
+
"learning_rate": 9.88520453576351e-06,
|
625 |
+
"loss": 2.1925,
|
626 |
+
"step": 87
|
627 |
+
},
|
628 |
+
{
|
629 |
+
"epoch": 0.11652542372881355,
|
630 |
+
"grad_norm": 4.0625,
|
631 |
+
"learning_rate": 9.88049014007613e-06,
|
632 |
+
"loss": 2.1166,
|
633 |
+
"step": 88
|
634 |
+
},
|
635 |
+
{
|
636 |
+
"epoch": 0.11784957627118645,
|
637 |
+
"grad_norm": 3.796875,
|
638 |
+
"learning_rate": 9.875682047713847e-06,
|
639 |
+
"loss": 2.0244,
|
640 |
+
"step": 89
|
641 |
+
},
|
642 |
+
{
|
643 |
+
"epoch": 0.11917372881355932,
|
644 |
+
"grad_norm": 4.125,
|
645 |
+
"learning_rate": 9.87078035098343e-06,
|
646 |
+
"loss": 2.1427,
|
647 |
+
"step": 90
|
648 |
+
},
|
649 |
+
{
|
650 |
+
"epoch": 0.1204978813559322,
|
651 |
+
"grad_norm": 4.25,
|
652 |
+
"learning_rate": 9.865785143988684e-06,
|
653 |
+
"loss": 2.2495,
|
654 |
+
"step": 91
|
655 |
+
},
|
656 |
+
{
|
657 |
+
"epoch": 0.12182203389830508,
|
658 |
+
"grad_norm": 4.21875,
|
659 |
+
"learning_rate": 9.860696522628638e-06,
|
660 |
+
"loss": 2.1213,
|
661 |
+
"step": 92
|
662 |
+
},
|
663 |
+
{
|
664 |
+
"epoch": 0.12314618644067797,
|
665 |
+
"grad_norm": 4.40625,
|
666 |
+
"learning_rate": 9.855514584595719e-06,
|
667 |
+
"loss": 2.1922,
|
668 |
+
"step": 93
|
669 |
+
},
|
670 |
+
{
|
671 |
+
"epoch": 0.12447033898305085,
|
672 |
+
"grad_norm": 4.21875,
|
673 |
+
"learning_rate": 9.850239429373855e-06,
|
674 |
+
"loss": 2.16,
|
675 |
+
"step": 94
|
676 |
+
},
|
677 |
+
{
|
678 |
+
"epoch": 0.12579449152542374,
|
679 |
+
"grad_norm": 4.1875,
|
680 |
+
"learning_rate": 9.84487115823659e-06,
|
681 |
+
"loss": 2.1521,
|
682 |
+
"step": 95
|
683 |
+
},
|
684 |
+
{
|
685 |
+
"epoch": 0.1271186440677966,
|
686 |
+
"grad_norm": 4.375,
|
687 |
+
"learning_rate": 9.839409874245118e-06,
|
688 |
+
"loss": 2.1293,
|
689 |
+
"step": 96
|
690 |
+
},
|
691 |
+
{
|
692 |
+
"epoch": 0.1284427966101695,
|
693 |
+
"grad_norm": 8.6875,
|
694 |
+
"learning_rate": 9.833855682246319e-06,
|
695 |
+
"loss": 2.1652,
|
696 |
+
"step": 97
|
697 |
+
},
|
698 |
+
{
|
699 |
+
"epoch": 0.12976694915254236,
|
700 |
+
"grad_norm": 4.03125,
|
701 |
+
"learning_rate": 9.828208688870736e-06,
|
702 |
+
"loss": 2.0963,
|
703 |
+
"step": 98
|
704 |
+
},
|
705 |
+
{
|
706 |
+
"epoch": 0.13109110169491525,
|
707 |
+
"grad_norm": 4.3125,
|
708 |
+
"learning_rate": 9.822469002530531e-06,
|
709 |
+
"loss": 2.1573,
|
710 |
+
"step": 99
|
711 |
+
},
|
712 |
+
{
|
713 |
+
"epoch": 0.13241525423728814,
|
714 |
+
"grad_norm": 3.75,
|
715 |
+
"learning_rate": 9.816636733417413e-06,
|
716 |
+
"loss": 2.1625,
|
717 |
+
"step": 100
|
718 |
+
},
|
719 |
+
{
|
720 |
+
"epoch": 0.133739406779661,
|
721 |
+
"grad_norm": 4.25,
|
722 |
+
"learning_rate": 9.810711993500506e-06,
|
723 |
+
"loss": 2.1151,
|
724 |
+
"step": 101
|
725 |
+
},
|
726 |
+
{
|
727 |
+
"epoch": 0.1350635593220339,
|
728 |
+
"grad_norm": 4.125,
|
729 |
+
"learning_rate": 9.804694896524215e-06,
|
730 |
+
"loss": 2.0776,
|
731 |
+
"step": 102
|
732 |
+
},
|
733 |
+
{
|
734 |
+
"epoch": 0.1363877118644068,
|
735 |
+
"grad_norm": 4.15625,
|
736 |
+
"learning_rate": 9.79858555800603e-06,
|
737 |
+
"loss": 2.0534,
|
738 |
+
"step": 103
|
739 |
+
},
|
740 |
+
{
|
741 |
+
"epoch": 0.13771186440677965,
|
742 |
+
"grad_norm": 3.953125,
|
743 |
+
"learning_rate": 9.792384095234312e-06,
|
744 |
+
"loss": 1.994,
|
745 |
+
"step": 104
|
746 |
+
},
|
747 |
+
{
|
748 |
+
"epoch": 0.13903601694915255,
|
749 |
+
"grad_norm": 4.5,
|
750 |
+
"learning_rate": 9.78609062726605e-06,
|
751 |
+
"loss": 1.9252,
|
752 |
+
"step": 105
|
753 |
+
},
|
754 |
+
{
|
755 |
+
"epoch": 0.1403601694915254,
|
756 |
+
"grad_norm": 3.90625,
|
757 |
+
"learning_rate": 9.779705274924563e-06,
|
758 |
+
"loss": 2.1531,
|
759 |
+
"step": 106
|
760 |
+
},
|
761 |
+
{
|
762 |
+
"epoch": 0.1416843220338983,
|
763 |
+
"grad_norm": 3.828125,
|
764 |
+
"learning_rate": 9.773228160797187e-06,
|
765 |
+
"loss": 2.1426,
|
766 |
+
"step": 107
|
767 |
+
},
|
768 |
+
{
|
769 |
+
"epoch": 0.1430084745762712,
|
770 |
+
"grad_norm": 3.796875,
|
771 |
+
"learning_rate": 9.766659409232918e-06,
|
772 |
+
"loss": 2.1032,
|
773 |
+
"step": 108
|
774 |
+
},
|
775 |
+
{
|
776 |
+
"epoch": 0.14433262711864406,
|
777 |
+
"grad_norm": 4.09375,
|
778 |
+
"learning_rate": 9.759999146340031e-06,
|
779 |
+
"loss": 2.0202,
|
780 |
+
"step": 109
|
781 |
+
},
|
782 |
+
{
|
783 |
+
"epoch": 0.14565677966101695,
|
784 |
+
"grad_norm": 4.59375,
|
785 |
+
"learning_rate": 9.753247499983649e-06,
|
786 |
+
"loss": 2.0955,
|
787 |
+
"step": 110
|
788 |
+
},
|
789 |
+
{
|
790 |
+
"epoch": 0.14698093220338984,
|
791 |
+
"grad_norm": 4.03125,
|
792 |
+
"learning_rate": 9.7464045997833e-06,
|
793 |
+
"loss": 2.019,
|
794 |
+
"step": 111
|
795 |
+
},
|
796 |
+
{
|
797 |
+
"epoch": 0.1483050847457627,
|
798 |
+
"grad_norm": 4.625,
|
799 |
+
"learning_rate": 9.739470577110417e-06,
|
800 |
+
"loss": 2.1751,
|
801 |
+
"step": 112
|
802 |
+
},
|
803 |
+
{
|
804 |
+
"epoch": 0.1496292372881356,
|
805 |
+
"grad_norm": 4.125,
|
806 |
+
"learning_rate": 9.732445565085823e-06,
|
807 |
+
"loss": 2.0698,
|
808 |
+
"step": 113
|
809 |
+
},
|
810 |
+
{
|
811 |
+
"epoch": 0.15095338983050846,
|
812 |
+
"grad_norm": 4.03125,
|
813 |
+
"learning_rate": 9.725329698577177e-06,
|
814 |
+
"loss": 2.1954,
|
815 |
+
"step": 114
|
816 |
+
},
|
817 |
+
{
|
818 |
+
"epoch": 0.15227754237288135,
|
819 |
+
"grad_norm": 4.15625,
|
820 |
+
"learning_rate": 9.718123114196381e-06,
|
821 |
+
"loss": 2.1319,
|
822 |
+
"step": 115
|
823 |
+
},
|
824 |
+
{
|
825 |
+
"epoch": 0.15360169491525424,
|
826 |
+
"grad_norm": 3.921875,
|
827 |
+
"learning_rate": 9.71082595029695e-06,
|
828 |
+
"loss": 2.0517,
|
829 |
+
"step": 116
|
830 |
+
},
|
831 |
+
{
|
832 |
+
"epoch": 0.1549258474576271,
|
833 |
+
"grad_norm": 4.3125,
|
834 |
+
"learning_rate": 9.703438346971373e-06,
|
835 |
+
"loss": 2.243,
|
836 |
+
"step": 117
|
837 |
+
},
|
838 |
+
{
|
839 |
+
"epoch": 0.15625,
|
840 |
+
"grad_norm": 4.15625,
|
841 |
+
"learning_rate": 9.69596044604841e-06,
|
842 |
+
"loss": 2.2454,
|
843 |
+
"step": 118
|
844 |
+
},
|
845 |
+
{
|
846 |
+
"epoch": 0.1575741525423729,
|
847 |
+
"grad_norm": 4.0625,
|
848 |
+
"learning_rate": 9.688392391090374e-06,
|
849 |
+
"loss": 2.0891,
|
850 |
+
"step": 119
|
851 |
+
},
|
852 |
+
{
|
853 |
+
"epoch": 0.15889830508474576,
|
854 |
+
"grad_norm": 4.3125,
|
855 |
+
"learning_rate": 9.680734327390374e-06,
|
856 |
+
"loss": 2.1075,
|
857 |
+
"step": 120
|
858 |
+
},
|
859 |
+
{
|
860 |
+
"epoch": 0.16022245762711865,
|
861 |
+
"grad_norm": 4.125,
|
862 |
+
"learning_rate": 9.672986401969523e-06,
|
863 |
+
"loss": 2.0766,
|
864 |
+
"step": 121
|
865 |
+
},
|
866 |
+
{
|
867 |
+
"epoch": 0.16154661016949154,
|
868 |
+
"grad_norm": 3.71875,
|
869 |
+
"learning_rate": 9.665148763574123e-06,
|
870 |
+
"loss": 1.9083,
|
871 |
+
"step": 122
|
872 |
+
},
|
873 |
+
{
|
874 |
+
"epoch": 0.1628707627118644,
|
875 |
+
"grad_norm": 3.9375,
|
876 |
+
"learning_rate": 9.657221562672803e-06,
|
877 |
+
"loss": 1.9674,
|
878 |
+
"step": 123
|
879 |
+
},
|
880 |
+
{
|
881 |
+
"epoch": 0.1641949152542373,
|
882 |
+
"grad_norm": 3.78125,
|
883 |
+
"learning_rate": 9.64920495145363e-06,
|
884 |
+
"loss": 2.2366,
|
885 |
+
"step": 124
|
886 |
+
},
|
887 |
+
{
|
888 |
+
"epoch": 0.16551906779661016,
|
889 |
+
"grad_norm": 4.21875,
|
890 |
+
"learning_rate": 9.64109908382119e-06,
|
891 |
+
"loss": 2.1767,
|
892 |
+
"step": 125
|
893 |
+
},
|
894 |
+
{
|
895 |
+
"epoch": 0.16684322033898305,
|
896 |
+
"grad_norm": 4.1875,
|
897 |
+
"learning_rate": 9.632904115393633e-06,
|
898 |
+
"loss": 2.0395,
|
899 |
+
"step": 126
|
900 |
+
},
|
901 |
+
{
|
902 |
+
"epoch": 0.16816737288135594,
|
903 |
+
"grad_norm": 4.09375,
|
904 |
+
"learning_rate": 9.624620203499683e-06,
|
905 |
+
"loss": 2.2272,
|
906 |
+
"step": 127
|
907 |
+
},
|
908 |
+
{
|
909 |
+
"epoch": 0.1694915254237288,
|
910 |
+
"grad_norm": 3.8125,
|
911 |
+
"learning_rate": 9.616247507175624e-06,
|
912 |
+
"loss": 2.094,
|
913 |
+
"step": 128
|
914 |
+
},
|
915 |
+
{
|
916 |
+
"epoch": 0.1708156779661017,
|
917 |
+
"grad_norm": 3.78125,
|
918 |
+
"learning_rate": 9.607786187162234e-06,
|
919 |
+
"loss": 2.1253,
|
920 |
+
"step": 129
|
921 |
+
},
|
922 |
+
{
|
923 |
+
"epoch": 0.1721398305084746,
|
924 |
+
"grad_norm": 4.40625,
|
925 |
+
"learning_rate": 9.599236405901715e-06,
|
926 |
+
"loss": 2.2173,
|
927 |
+
"step": 130
|
928 |
+
},
|
929 |
+
{
|
930 |
+
"epoch": 0.17346398305084745,
|
931 |
+
"grad_norm": 3.90625,
|
932 |
+
"learning_rate": 9.590598327534563e-06,
|
933 |
+
"loss": 2.0337,
|
934 |
+
"step": 131
|
935 |
+
},
|
936 |
+
{
|
937 |
+
"epoch": 0.17478813559322035,
|
938 |
+
"grad_norm": 4.0625,
|
939 |
+
"learning_rate": 9.581872117896423e-06,
|
940 |
+
"loss": 2.0791,
|
941 |
+
"step": 132
|
942 |
+
},
|
943 |
+
{
|
944 |
+
"epoch": 0.1761122881355932,
|
945 |
+
"grad_norm": 3.859375,
|
946 |
+
"learning_rate": 9.573057944514897e-06,
|
947 |
+
"loss": 2.0358,
|
948 |
+
"step": 133
|
949 |
+
},
|
950 |
+
{
|
951 |
+
"epoch": 0.1774364406779661,
|
952 |
+
"grad_norm": 4.28125,
|
953 |
+
"learning_rate": 9.56415597660634e-06,
|
954 |
+
"loss": 1.8235,
|
955 |
+
"step": 134
|
956 |
+
},
|
957 |
+
{
|
958 |
+
"epoch": 0.178760593220339,
|
959 |
+
"grad_norm": 4.46875,
|
960 |
+
"learning_rate": 9.555166385072599e-06,
|
961 |
+
"loss": 2.154,
|
962 |
+
"step": 135
|
963 |
+
},
|
964 |
+
{
|
965 |
+
"epoch": 0.18008474576271186,
|
966 |
+
"grad_norm": 3.953125,
|
967 |
+
"learning_rate": 9.546089342497743e-06,
|
968 |
+
"loss": 2.1079,
|
969 |
+
"step": 136
|
970 |
+
},
|
971 |
+
{
|
972 |
+
"epoch": 0.18140889830508475,
|
973 |
+
"grad_norm": 3.84375,
|
974 |
+
"learning_rate": 9.536925023144742e-06,
|
975 |
+
"loss": 2.1117,
|
976 |
+
"step": 137
|
977 |
+
},
|
978 |
+
{
|
979 |
+
"epoch": 0.18273305084745764,
|
980 |
+
"grad_norm": 4.0625,
|
981 |
+
"learning_rate": 9.527673602952123e-06,
|
982 |
+
"loss": 2.0338,
|
983 |
+
"step": 138
|
984 |
+
},
|
985 |
+
{
|
986 |
+
"epoch": 0.1840572033898305,
|
987 |
+
"grad_norm": 4.09375,
|
988 |
+
"learning_rate": 9.518335259530594e-06,
|
989 |
+
"loss": 2.2235,
|
990 |
+
"step": 139
|
991 |
+
},
|
992 |
+
{
|
993 |
+
"epoch": 0.1853813559322034,
|
994 |
+
"grad_norm": 4.84375,
|
995 |
+
"learning_rate": 9.508910172159635e-06,
|
996 |
+
"loss": 1.9275,
|
997 |
+
"step": 140
|
998 |
+
},
|
999 |
+
{
|
1000 |
+
"epoch": 0.18670550847457626,
|
1001 |
+
"grad_norm": 4.25,
|
1002 |
+
"learning_rate": 9.499398521784051e-06,
|
1003 |
+
"loss": 2.0549,
|
1004 |
+
"step": 141
|
1005 |
+
},
|
1006 |
+
{
|
1007 |
+
"epoch": 0.18802966101694915,
|
1008 |
+
"grad_norm": 4.71875,
|
1009 |
+
"learning_rate": 9.489800491010507e-06,
|
1010 |
+
"loss": 1.9433,
|
1011 |
+
"step": 142
|
1012 |
+
},
|
1013 |
+
{
|
1014 |
+
"epoch": 0.18935381355932204,
|
1015 |
+
"grad_norm": 3.96875,
|
1016 |
+
"learning_rate": 9.48011626410401e-06,
|
1017 |
+
"loss": 2.2499,
|
1018 |
+
"step": 143
|
1019 |
+
},
|
1020 |
+
{
|
1021 |
+
"epoch": 0.1906779661016949,
|
1022 |
+
"grad_norm": 3.8125,
|
1023 |
+
"learning_rate": 9.470346026984387e-06,
|
1024 |
+
"loss": 2.1125,
|
1025 |
+
"step": 144
|
1026 |
+
},
|
1027 |
+
{
|
1028 |
+
"epoch": 0.1920021186440678,
|
1029 |
+
"grad_norm": 4.34375,
|
1030 |
+
"learning_rate": 9.4604899672227e-06,
|
1031 |
+
"loss": 2.1017,
|
1032 |
+
"step": 145
|
1033 |
+
},
|
1034 |
+
{
|
1035 |
+
"epoch": 0.1933262711864407,
|
1036 |
+
"grad_norm": 4.09375,
|
1037 |
+
"learning_rate": 9.450548274037652e-06,
|
1038 |
+
"loss": 2.038,
|
1039 |
+
"step": 146
|
1040 |
+
},
|
1041 |
+
{
|
1042 |
+
"epoch": 0.19465042372881355,
|
1043 |
+
"grad_norm": 4.375,
|
1044 |
+
"learning_rate": 9.440521138291962e-06,
|
1045 |
+
"loss": 2.1801,
|
1046 |
+
"step": 147
|
1047 |
+
},
|
1048 |
+
{
|
1049 |
+
"epoch": 0.19597457627118645,
|
1050 |
+
"grad_norm": 3.734375,
|
1051 |
+
"learning_rate": 9.430408752488687e-06,
|
1052 |
+
"loss": 2.1859,
|
1053 |
+
"step": 148
|
1054 |
+
},
|
1055 |
+
{
|
1056 |
+
"epoch": 0.1972987288135593,
|
1057 |
+
"grad_norm": 4.34375,
|
1058 |
+
"learning_rate": 9.420211310767534e-06,
|
1059 |
+
"loss": 2.074,
|
1060 |
+
"step": 149
|
1061 |
+
},
|
1062 |
+
{
|
1063 |
+
"epoch": 0.1986228813559322,
|
1064 |
+
"grad_norm": 4.8125,
|
1065 |
+
"learning_rate": 9.409929008901126e-06,
|
1066 |
+
"loss": 2.067,
|
1067 |
+
"step": 150
|
1068 |
+
},
|
1069 |
+
{
|
1070 |
+
"epoch": 0.1999470338983051,
|
1071 |
+
"grad_norm": 3.671875,
|
1072 |
+
"learning_rate": 9.399562044291261e-06,
|
1073 |
+
"loss": 1.9712,
|
1074 |
+
"step": 151
|
1075 |
+
},
|
1076 |
+
{
|
1077 |
+
"epoch": 0.20127118644067796,
|
1078 |
+
"grad_norm": 3.96875,
|
1079 |
+
"learning_rate": 9.389110615965102e-06,
|
1080 |
+
"loss": 2.0511,
|
1081 |
+
"step": 152
|
1082 |
+
},
|
1083 |
+
{
|
1084 |
+
"epoch": 0.20259533898305085,
|
1085 |
+
"grad_norm": 4.0,
|
1086 |
+
"learning_rate": 9.378574924571362e-06,
|
1087 |
+
"loss": 2.0218,
|
1088 |
+
"step": 153
|
1089 |
+
},
|
1090 |
+
{
|
1091 |
+
"epoch": 0.20391949152542374,
|
1092 |
+
"grad_norm": 4.09375,
|
1093 |
+
"learning_rate": 9.367955172376462e-06,
|
1094 |
+
"loss": 1.9664,
|
1095 |
+
"step": 154
|
1096 |
+
},
|
1097 |
+
{
|
1098 |
+
"epoch": 0.2052436440677966,
|
1099 |
+
"grad_norm": 3.859375,
|
1100 |
+
"learning_rate": 9.35725156326063e-06,
|
1101 |
+
"loss": 2.0343,
|
1102 |
+
"step": 155
|
1103 |
+
},
|
1104 |
+
{
|
1105 |
+
"epoch": 0.2065677966101695,
|
1106 |
+
"grad_norm": 3.984375,
|
1107 |
+
"learning_rate": 9.346464302714008e-06,
|
1108 |
+
"loss": 2.2163,
|
1109 |
+
"step": 156
|
1110 |
+
},
|
1111 |
+
{
|
1112 |
+
"epoch": 0.20789194915254236,
|
1113 |
+
"grad_norm": 3.609375,
|
1114 |
+
"learning_rate": 9.335593597832686e-06,
|
1115 |
+
"loss": 2.2098,
|
1116 |
+
"step": 157
|
1117 |
+
},
|
1118 |
+
{
|
1119 |
+
"epoch": 0.20921610169491525,
|
1120 |
+
"grad_norm": 3.90625,
|
1121 |
+
"learning_rate": 9.324639657314742e-06,
|
1122 |
+
"loss": 2.0961,
|
1123 |
+
"step": 158
|
1124 |
+
},
|
1125 |
+
{
|
1126 |
+
"epoch": 0.21054025423728814,
|
1127 |
+
"grad_norm": 3.984375,
|
1128 |
+
"learning_rate": 9.313602691456224e-06,
|
1129 |
+
"loss": 2.1141,
|
1130 |
+
"step": 159
|
1131 |
+
},
|
1132 |
+
{
|
1133 |
+
"epoch": 0.211864406779661,
|
1134 |
+
"grad_norm": 3.96875,
|
1135 |
+
"learning_rate": 9.302482912147126e-06,
|
1136 |
+
"loss": 2.0155,
|
1137 |
+
"step": 160
|
1138 |
+
},
|
1139 |
+
{
|
1140 |
+
"epoch": 0.2131885593220339,
|
1141 |
+
"grad_norm": 3.953125,
|
1142 |
+
"learning_rate": 9.291280532867301e-06,
|
1143 |
+
"loss": 1.9736,
|
1144 |
+
"step": 161
|
1145 |
+
},
|
1146 |
+
{
|
1147 |
+
"epoch": 0.2145127118644068,
|
1148 |
+
"grad_norm": 3.734375,
|
1149 |
+
"learning_rate": 9.279995768682383e-06,
|
1150 |
+
"loss": 2.0853,
|
1151 |
+
"step": 162
|
1152 |
+
},
|
1153 |
+
{
|
1154 |
+
"epoch": 0.21583686440677965,
|
1155 |
+
"grad_norm": 4.125,
|
1156 |
+
"learning_rate": 9.268628836239646e-06,
|
1157 |
+
"loss": 2.1189,
|
1158 |
+
"step": 163
|
1159 |
+
},
|
1160 |
+
{
|
1161 |
+
"epoch": 0.21716101694915255,
|
1162 |
+
"grad_norm": 3.796875,
|
1163 |
+
"learning_rate": 9.257179953763846e-06,
|
1164 |
+
"loss": 2.0597,
|
1165 |
+
"step": 164
|
1166 |
+
},
|
1167 |
+
{
|
1168 |
+
"epoch": 0.2184851694915254,
|
1169 |
+
"grad_norm": 4.21875,
|
1170 |
+
"learning_rate": 9.245649341053033e-06,
|
1171 |
+
"loss": 2.0406,
|
1172 |
+
"step": 165
|
1173 |
+
},
|
1174 |
+
{
|
1175 |
+
"epoch": 0.2198093220338983,
|
1176 |
+
"grad_norm": 3.96875,
|
1177 |
+
"learning_rate": 9.234037219474332e-06,
|
1178 |
+
"loss": 2.0314,
|
1179 |
+
"step": 166
|
1180 |
+
},
|
1181 |
+
{
|
1182 |
+
"epoch": 0.2211334745762712,
|
1183 |
+
"grad_norm": 4.0,
|
1184 |
+
"learning_rate": 9.222343811959694e-06,
|
1185 |
+
"loss": 2.1392,
|
1186 |
+
"step": 167
|
1187 |
+
},
|
1188 |
+
{
|
1189 |
+
"epoch": 0.22245762711864406,
|
1190 |
+
"grad_norm": 3.78125,
|
1191 |
+
"learning_rate": 9.21056934300161e-06,
|
1192 |
+
"loss": 2.0291,
|
1193 |
+
"step": 168
|
1194 |
+
},
|
1195 |
+
{
|
1196 |
+
"epoch": 0.22378177966101695,
|
1197 |
+
"grad_norm": 3.78125,
|
1198 |
+
"learning_rate": 9.198714038648811e-06,
|
1199 |
+
"loss": 2.1251,
|
1200 |
+
"step": 169
|
1201 |
+
},
|
1202 |
+
{
|
1203 |
+
"epoch": 0.22510593220338984,
|
1204 |
+
"grad_norm": 4.25,
|
1205 |
+
"learning_rate": 9.186778126501916e-06,
|
1206 |
+
"loss": 1.9912,
|
1207 |
+
"step": 170
|
1208 |
+
},
|
1209 |
+
{
|
1210 |
+
"epoch": 0.2264300847457627,
|
1211 |
+
"grad_norm": 4.0,
|
1212 |
+
"learning_rate": 9.17476183570908e-06,
|
1213 |
+
"loss": 2.0754,
|
1214 |
+
"step": 171
|
1215 |
+
},
|
1216 |
+
{
|
1217 |
+
"epoch": 0.2277542372881356,
|
1218 |
+
"grad_norm": 4.15625,
|
1219 |
+
"learning_rate": 9.162665396961573e-06,
|
1220 |
+
"loss": 2.0376,
|
1221 |
+
"step": 172
|
1222 |
+
},
|
1223 |
+
{
|
1224 |
+
"epoch": 0.22907838983050846,
|
1225 |
+
"grad_norm": 4.15625,
|
1226 |
+
"learning_rate": 9.150489042489368e-06,
|
1227 |
+
"loss": 1.984,
|
1228 |
+
"step": 173
|
1229 |
+
},
|
1230 |
+
{
|
1231 |
+
"epoch": 0.23040254237288135,
|
1232 |
+
"grad_norm": 3.984375,
|
1233 |
+
"learning_rate": 9.138233006056679e-06,
|
1234 |
+
"loss": 2.0155,
|
1235 |
+
"step": 174
|
1236 |
+
},
|
1237 |
+
{
|
1238 |
+
"epoch": 0.23172669491525424,
|
1239 |
+
"grad_norm": 4.125,
|
1240 |
+
"learning_rate": 9.125897522957461e-06,
|
1241 |
+
"loss": 2.1034,
|
1242 |
+
"step": 175
|
1243 |
+
},
|
1244 |
+
{
|
1245 |
+
"epoch": 0.2330508474576271,
|
1246 |
+
"grad_norm": 3.84375,
|
1247 |
+
"learning_rate": 9.113482830010918e-06,
|
1248 |
+
"loss": 2.1072,
|
1249 |
+
"step": 176
|
1250 |
+
},
|
1251 |
+
{
|
1252 |
+
"epoch": 0.234375,
|
1253 |
+
"grad_norm": 5.28125,
|
1254 |
+
"learning_rate": 9.100989165556928e-06,
|
1255 |
+
"loss": 2.1256,
|
1256 |
+
"step": 177
|
1257 |
+
},
|
1258 |
+
{
|
1259 |
+
"epoch": 0.2356991525423729,
|
1260 |
+
"grad_norm": 4.3125,
|
1261 |
+
"learning_rate": 9.088416769451485e-06,
|
1262 |
+
"loss": 2.0479,
|
1263 |
+
"step": 178
|
1264 |
+
},
|
1265 |
+
{
|
1266 |
+
"epoch": 0.23702330508474576,
|
1267 |
+
"grad_norm": 4.0,
|
1268 |
+
"learning_rate": 9.075765883062093e-06,
|
1269 |
+
"loss": 2.075,
|
1270 |
+
"step": 179
|
1271 |
+
},
|
1272 |
+
{
|
1273 |
+
"epoch": 0.23834745762711865,
|
1274 |
+
"grad_norm": 3.8125,
|
1275 |
+
"learning_rate": 9.063036749263127e-06,
|
1276 |
+
"loss": 1.9578,
|
1277 |
+
"step": 180
|
1278 |
+
},
|
1279 |
+
{
|
1280 |
+
"epoch": 0.23967161016949154,
|
1281 |
+
"grad_norm": 3.796875,
|
1282 |
+
"learning_rate": 9.050229612431168e-06,
|
1283 |
+
"loss": 2.2268,
|
1284 |
+
"step": 181
|
1285 |
+
},
|
1286 |
+
{
|
1287 |
+
"epoch": 0.2409957627118644,
|
1288 |
+
"grad_norm": 4.0625,
|
1289 |
+
"learning_rate": 9.037344718440321e-06,
|
1290 |
+
"loss": 2.2065,
|
1291 |
+
"step": 182
|
1292 |
+
},
|
1293 |
+
{
|
1294 |
+
"epoch": 0.2423199152542373,
|
1295 |
+
"grad_norm": 4.75,
|
1296 |
+
"learning_rate": 9.02438231465749e-06,
|
1297 |
+
"loss": 1.9338,
|
1298 |
+
"step": 183
|
1299 |
+
},
|
1300 |
+
{
|
1301 |
+
"epoch": 0.24364406779661016,
|
1302 |
+
"grad_norm": 4.0625,
|
1303 |
+
"learning_rate": 9.011342649937623e-06,
|
1304 |
+
"loss": 2.0992,
|
1305 |
+
"step": 184
|
1306 |
+
},
|
1307 |
+
{
|
1308 |
+
"epoch": 0.24496822033898305,
|
1309 |
+
"grad_norm": 4.625,
|
1310 |
+
"learning_rate": 8.99822597461894e-06,
|
1311 |
+
"loss": 2.0273,
|
1312 |
+
"step": 185
|
1313 |
+
},
|
1314 |
+
{
|
1315 |
+
"epoch": 0.24629237288135594,
|
1316 |
+
"grad_norm": 4.59375,
|
1317 |
+
"learning_rate": 8.985032540518133e-06,
|
1318 |
+
"loss": 2.0654,
|
1319 |
+
"step": 186
|
1320 |
+
},
|
1321 |
+
{
|
1322 |
+
"epoch": 0.2476165254237288,
|
1323 |
+
"grad_norm": 4.34375,
|
1324 |
+
"learning_rate": 8.971762600925519e-06,
|
1325 |
+
"loss": 2.1202,
|
1326 |
+
"step": 187
|
1327 |
+
},
|
1328 |
+
{
|
1329 |
+
"epoch": 0.2489406779661017,
|
1330 |
+
"grad_norm": 3.75,
|
1331 |
+
"learning_rate": 8.958416410600188e-06,
|
1332 |
+
"loss": 2.0589,
|
1333 |
+
"step": 188
|
1334 |
+
},
|
1335 |
+
{
|
1336 |
+
"epoch": 0.2502648305084746,
|
1337 |
+
"grad_norm": 4.0625,
|
1338 |
+
"learning_rate": 8.944994225765104e-06,
|
1339 |
+
"loss": 1.9044,
|
1340 |
+
"step": 189
|
1341 |
+
},
|
1342 |
+
{
|
1343 |
+
"epoch": 0.2515889830508475,
|
1344 |
+
"grad_norm": 4.375,
|
1345 |
+
"learning_rate": 8.931496304102192e-06,
|
1346 |
+
"loss": 2.0083,
|
1347 |
+
"step": 190
|
1348 |
+
},
|
1349 |
+
{
|
1350 |
+
"epoch": 0.2529131355932203,
|
1351 |
+
"grad_norm": 3.859375,
|
1352 |
+
"learning_rate": 8.917922904747385e-06,
|
1353 |
+
"loss": 1.9487,
|
1354 |
+
"step": 191
|
1355 |
+
},
|
1356 |
+
{
|
1357 |
+
"epoch": 0.2542372881355932,
|
1358 |
+
"grad_norm": 3.734375,
|
1359 |
+
"learning_rate": 8.904274288285657e-06,
|
1360 |
+
"loss": 1.9682,
|
1361 |
+
"step": 192
|
1362 |
+
},
|
1363 |
+
{
|
1364 |
+
"epoch": 0.2555614406779661,
|
1365 |
+
"grad_norm": 4.21875,
|
1366 |
+
"learning_rate": 8.890550716746013e-06,
|
1367 |
+
"loss": 1.8554,
|
1368 |
+
"step": 193
|
1369 |
+
},
|
1370 |
+
{
|
1371 |
+
"epoch": 0.256885593220339,
|
1372 |
+
"grad_norm": 3.921875,
|
1373 |
+
"learning_rate": 8.876752453596462e-06,
|
1374 |
+
"loss": 2.0785,
|
1375 |
+
"step": 194
|
1376 |
+
},
|
1377 |
+
{
|
1378 |
+
"epoch": 0.2582097457627119,
|
1379 |
+
"grad_norm": 3.796875,
|
1380 |
+
"learning_rate": 8.862879763738962e-06,
|
1381 |
+
"loss": 2.0384,
|
1382 |
+
"step": 195
|
1383 |
+
},
|
1384 |
+
{
|
1385 |
+
"epoch": 0.2595338983050847,
|
1386 |
+
"grad_norm": 3.828125,
|
1387 |
+
"learning_rate": 8.84893291350432e-06,
|
1388 |
+
"loss": 2.163,
|
1389 |
+
"step": 196
|
1390 |
+
},
|
1391 |
+
{
|
1392 |
+
"epoch": 0.2608580508474576,
|
1393 |
+
"grad_norm": 4.125,
|
1394 |
+
"learning_rate": 8.834912170647102e-06,
|
1395 |
+
"loss": 2.0237,
|
1396 |
+
"step": 197
|
1397 |
+
},
|
1398 |
+
{
|
1399 |
+
"epoch": 0.2621822033898305,
|
1400 |
+
"grad_norm": 4.0625,
|
1401 |
+
"learning_rate": 8.820817804340471e-06,
|
1402 |
+
"loss": 2.0215,
|
1403 |
+
"step": 198
|
1404 |
+
},
|
1405 |
+
{
|
1406 |
+
"epoch": 0.2635063559322034,
|
1407 |
+
"grad_norm": 3.671875,
|
1408 |
+
"learning_rate": 8.806650085171036e-06,
|
1409 |
+
"loss": 2.0454,
|
1410 |
+
"step": 199
|
1411 |
+
},
|
1412 |
+
{
|
1413 |
+
"epoch": 0.2648305084745763,
|
1414 |
+
"grad_norm": 3.78125,
|
1415 |
+
"learning_rate": 8.792409285133644e-06,
|
1416 |
+
"loss": 2.0006,
|
1417 |
+
"step": 200
|
1418 |
+
},
|
1419 |
+
{
|
1420 |
+
"epoch": 0.2648305084745763,
|
1421 |
+
"eval_AskDoctor-Chinese_loss": 2.021162986755371,
|
1422 |
+
"eval_AskDoctor-Chinese_runtime": 16.0254,
|
1423 |
+
"eval_AskDoctor-Chinese_samples_per_second": 1.872,
|
1424 |
+
"eval_AskDoctor-Chinese_steps_per_second": 1.872,
|
1425 |
+
"step": 200
|
1426 |
+
},
|
1427 |
+
{
|
1428 |
+
"epoch": 0.2661546610169492,
|
1429 |
+
"grad_norm": 3.921875,
|
1430 |
+
"learning_rate": 8.778095677626164e-06,
|
1431 |
+
"loss": 1.9454,
|
1432 |
+
"step": 201
|
1433 |
+
},
|
1434 |
+
{
|
1435 |
+
"epoch": 0.267478813559322,
|
1436 |
+
"grad_norm": 3.765625,
|
1437 |
+
"learning_rate": 8.763709537444241e-06,
|
1438 |
+
"loss": 2.1055,
|
1439 |
+
"step": 202
|
1440 |
+
},
|
1441 |
+
{
|
1442 |
+
"epoch": 0.2688029661016949,
|
1443 |
+
"grad_norm": 4.59375,
|
1444 |
+
"learning_rate": 8.749251140776016e-06,
|
1445 |
+
"loss": 1.9506,
|
1446 |
+
"step": 203
|
1447 |
+
},
|
1448 |
+
{
|
1449 |
+
"epoch": 0.2701271186440678,
|
1450 |
+
"grad_norm": 3.9375,
|
1451 |
+
"learning_rate": 8.734720765196826e-06,
|
1452 |
+
"loss": 2.2382,
|
1453 |
+
"step": 204
|
1454 |
+
},
|
1455 |
+
{
|
1456 |
+
"epoch": 0.2714512711864407,
|
1457 |
+
"grad_norm": 4.96875,
|
1458 |
+
"learning_rate": 8.720118689663872e-06,
|
1459 |
+
"loss": 1.9558,
|
1460 |
+
"step": 205
|
1461 |
+
},
|
1462 |
+
{
|
1463 |
+
"epoch": 0.2727754237288136,
|
1464 |
+
"grad_norm": 3.84375,
|
1465 |
+
"learning_rate": 8.705445194510868e-06,
|
1466 |
+
"loss": 2.0589,
|
1467 |
+
"step": 206
|
1468 |
+
},
|
1469 |
+
{
|
1470 |
+
"epoch": 0.2740995762711864,
|
1471 |
+
"grad_norm": 4.84375,
|
1472 |
+
"learning_rate": 8.690700561442658e-06,
|
1473 |
+
"loss": 1.8821,
|
1474 |
+
"step": 207
|
1475 |
+
},
|
1476 |
+
{
|
1477 |
+
"epoch": 0.2754237288135593,
|
1478 |
+
"grad_norm": 3.84375,
|
1479 |
+
"learning_rate": 8.675885073529802e-06,
|
1480 |
+
"loss": 1.9863,
|
1481 |
+
"step": 208
|
1482 |
+
},
|
1483 |
+
{
|
1484 |
+
"epoch": 0.2767478813559322,
|
1485 |
+
"grad_norm": 3.84375,
|
1486 |
+
"learning_rate": 8.660999015203152e-06,
|
1487 |
+
"loss": 2.0464,
|
1488 |
+
"step": 209
|
1489 |
+
},
|
1490 |
+
{
|
1491 |
+
"epoch": 0.2780720338983051,
|
1492 |
+
"grad_norm": 3.9375,
|
1493 |
+
"learning_rate": 8.64604267224838e-06,
|
1494 |
+
"loss": 2.1284,
|
1495 |
+
"step": 210
|
1496 |
+
},
|
1497 |
+
{
|
1498 |
+
"epoch": 0.279396186440678,
|
1499 |
+
"grad_norm": 4.21875,
|
1500 |
+
"learning_rate": 8.631016331800501e-06,
|
1501 |
+
"loss": 1.9782,
|
1502 |
+
"step": 211
|
1503 |
+
},
|
1504 |
+
{
|
1505 |
+
"epoch": 0.2807203389830508,
|
1506 |
+
"grad_norm": 3.84375,
|
1507 |
+
"learning_rate": 8.615920282338355e-06,
|
1508 |
+
"loss": 2.0504,
|
1509 |
+
"step": 212
|
1510 |
+
},
|
1511 |
+
{
|
1512 |
+
"epoch": 0.2820444915254237,
|
1513 |
+
"grad_norm": 3.859375,
|
1514 |
+
"learning_rate": 8.600754813679072e-06,
|
1515 |
+
"loss": 2.0384,
|
1516 |
+
"step": 213
|
1517 |
+
},
|
1518 |
+
{
|
1519 |
+
"epoch": 0.2833686440677966,
|
1520 |
+
"grad_norm": 4.1875,
|
1521 |
+
"learning_rate": 8.585520216972503e-06,
|
1522 |
+
"loss": 2.0057,
|
1523 |
+
"step": 214
|
1524 |
+
},
|
1525 |
+
{
|
1526 |
+
"epoch": 0.2846927966101695,
|
1527 |
+
"grad_norm": 3.765625,
|
1528 |
+
"learning_rate": 8.570216784695637e-06,
|
1529 |
+
"loss": 2.1141,
|
1530 |
+
"step": 215
|
1531 |
+
},
|
1532 |
+
{
|
1533 |
+
"epoch": 0.2860169491525424,
|
1534 |
+
"grad_norm": 4.1875,
|
1535 |
+
"learning_rate": 8.55484481064698e-06,
|
1536 |
+
"loss": 1.9975,
|
1537 |
+
"step": 216
|
1538 |
+
},
|
1539 |
+
{
|
1540 |
+
"epoch": 0.2873411016949153,
|
1541 |
+
"grad_norm": 4.03125,
|
1542 |
+
"learning_rate": 8.539404589940924e-06,
|
1543 |
+
"loss": 1.9758,
|
1544 |
+
"step": 217
|
1545 |
+
},
|
1546 |
+
{
|
1547 |
+
"epoch": 0.2886652542372881,
|
1548 |
+
"grad_norm": 6.0625,
|
1549 |
+
"learning_rate": 8.52389641900206e-06,
|
1550 |
+
"loss": 1.8848,
|
1551 |
+
"step": 218
|
1552 |
+
},
|
1553 |
+
{
|
1554 |
+
"epoch": 0.289989406779661,
|
1555 |
+
"grad_norm": 3.734375,
|
1556 |
+
"learning_rate": 8.50832059555952e-06,
|
1557 |
+
"loss": 2.09,
|
1558 |
+
"step": 219
|
1559 |
+
},
|
1560 |
+
{
|
1561 |
+
"epoch": 0.2913135593220339,
|
1562 |
+
"grad_norm": 3.984375,
|
1563 |
+
"learning_rate": 8.492677418641231e-06,
|
1564 |
+
"loss": 1.824,
|
1565 |
+
"step": 220
|
1566 |
+
},
|
1567 |
+
{
|
1568 |
+
"epoch": 0.2926377118644068,
|
1569 |
+
"grad_norm": 3.90625,
|
1570 |
+
"learning_rate": 8.476967188568187e-06,
|
1571 |
+
"loss": 2.1443,
|
1572 |
+
"step": 221
|
1573 |
+
},
|
1574 |
+
{
|
1575 |
+
"epoch": 0.2939618644067797,
|
1576 |
+
"grad_norm": 3.796875,
|
1577 |
+
"learning_rate": 8.461190206948691e-06,
|
1578 |
+
"loss": 2.1238,
|
1579 |
+
"step": 222
|
1580 |
+
},
|
1581 |
+
{
|
1582 |
+
"epoch": 0.2952860169491525,
|
1583 |
+
"grad_norm": 4.0625,
|
1584 |
+
"learning_rate": 8.445346776672546e-06,
|
1585 |
+
"loss": 2.1187,
|
1586 |
+
"step": 223
|
1587 |
+
},
|
1588 |
+
{
|
1589 |
+
"epoch": 0.2966101694915254,
|
1590 |
+
"grad_norm": 3.65625,
|
1591 |
+
"learning_rate": 8.429437201905254e-06,
|
1592 |
+
"loss": 2.2054,
|
1593 |
+
"step": 224
|
1594 |
+
},
|
1595 |
+
{
|
1596 |
+
"epoch": 0.2979343220338983,
|
1597 |
+
"grad_norm": 3.5,
|
1598 |
+
"learning_rate": 8.413461788082175e-06,
|
1599 |
+
"loss": 2.0788,
|
1600 |
+
"step": 225
|
1601 |
+
},
|
1602 |
+
{
|
1603 |
+
"epoch": 0.2992584745762712,
|
1604 |
+
"grad_norm": 3.5625,
|
1605 |
+
"learning_rate": 8.39742084190266e-06,
|
1606 |
+
"loss": 2.1441,
|
1607 |
+
"step": 226
|
1608 |
+
},
|
1609 |
+
{
|
1610 |
+
"epoch": 0.3005826271186441,
|
1611 |
+
"grad_norm": 7.3125,
|
1612 |
+
"learning_rate": 8.38131467132416e-06,
|
1613 |
+
"loss": 1.9429,
|
1614 |
+
"step": 227
|
1615 |
+
},
|
1616 |
+
{
|
1617 |
+
"epoch": 0.3019067796610169,
|
1618 |
+
"grad_norm": 7.375,
|
1619 |
+
"learning_rate": 8.365143585556326e-06,
|
1620 |
+
"loss": 1.9466,
|
1621 |
+
"step": 228
|
1622 |
+
},
|
1623 |
+
{
|
1624 |
+
"epoch": 0.3032309322033898,
|
1625 |
+
"grad_norm": 4.625,
|
1626 |
+
"learning_rate": 8.348907895055055e-06,
|
1627 |
+
"loss": 1.9793,
|
1628 |
+
"step": 229
|
1629 |
+
},
|
1630 |
+
{
|
1631 |
+
"epoch": 0.3045550847457627,
|
1632 |
+
"grad_norm": 4.09375,
|
1633 |
+
"learning_rate": 8.332607911516545e-06,
|
1634 |
+
"loss": 2.0855,
|
1635 |
+
"step": 230
|
1636 |
+
},
|
1637 |
+
{
|
1638 |
+
"epoch": 0.3058792372881356,
|
1639 |
+
"grad_norm": 4.125,
|
1640 |
+
"learning_rate": 8.316243947871306e-06,
|
1641 |
+
"loss": 2.1595,
|
1642 |
+
"step": 231
|
1643 |
+
},
|
1644 |
+
{
|
1645 |
+
"epoch": 0.3072033898305085,
|
1646 |
+
"grad_norm": 3.953125,
|
1647 |
+
"learning_rate": 8.299816318278146e-06,
|
1648 |
+
"loss": 1.9467,
|
1649 |
+
"step": 232
|
1650 |
+
},
|
1651 |
+
{
|
1652 |
+
"epoch": 0.3085275423728814,
|
1653 |
+
"grad_norm": 3.75,
|
1654 |
+
"learning_rate": 8.283325338118154e-06,
|
1655 |
+
"loss": 1.9687,
|
1656 |
+
"step": 233
|
1657 |
+
},
|
1658 |
+
{
|
1659 |
+
"epoch": 0.3098516949152542,
|
1660 |
+
"grad_norm": 3.875,
|
1661 |
+
"learning_rate": 8.266771323988624e-06,
|
1662 |
+
"loss": 2.0397,
|
1663 |
+
"step": 234
|
1664 |
+
},
|
1665 |
+
{
|
1666 |
+
"epoch": 0.3111758474576271,
|
1667 |
+
"grad_norm": 3.890625,
|
1668 |
+
"learning_rate": 8.250154593697002e-06,
|
1669 |
+
"loss": 2.1581,
|
1670 |
+
"step": 235
|
1671 |
+
},
|
1672 |
+
{
|
1673 |
+
"epoch": 0.3125,
|
1674 |
+
"grad_norm": 3.640625,
|
1675 |
+
"learning_rate": 8.233475466254766e-06,
|
1676 |
+
"loss": 1.9687,
|
1677 |
+
"step": 236
|
1678 |
+
},
|
1679 |
+
{
|
1680 |
+
"epoch": 0.3138241525423729,
|
1681 |
+
"grad_norm": 3.828125,
|
1682 |
+
"learning_rate": 8.216734261871305e-06,
|
1683 |
+
"loss": 2.081,
|
1684 |
+
"step": 237
|
1685 |
+
},
|
1686 |
+
{
|
1687 |
+
"epoch": 0.3151483050847458,
|
1688 |
+
"grad_norm": 3.984375,
|
1689 |
+
"learning_rate": 8.199931301947782e-06,
|
1690 |
+
"loss": 1.9637,
|
1691 |
+
"step": 238
|
1692 |
+
},
|
1693 |
+
{
|
1694 |
+
"epoch": 0.3164724576271186,
|
1695 |
+
"grad_norm": 6.96875,
|
1696 |
+
"learning_rate": 8.183066909070946e-06,
|
1697 |
+
"loss": 1.9271,
|
1698 |
+
"step": 239
|
1699 |
+
},
|
1700 |
+
{
|
1701 |
+
"epoch": 0.3177966101694915,
|
1702 |
+
"grad_norm": 3.9375,
|
1703 |
+
"learning_rate": 8.16614140700696e-06,
|
1704 |
+
"loss": 1.9426,
|
1705 |
+
"step": 240
|
1706 |
+
},
|
1707 |
+
{
|
1708 |
+
"epoch": 0.3191207627118644,
|
1709 |
+
"grad_norm": 4.03125,
|
1710 |
+
"learning_rate": 8.149155120695163e-06,
|
1711 |
+
"loss": 1.8951,
|
1712 |
+
"step": 241
|
1713 |
+
},
|
1714 |
+
{
|
1715 |
+
"epoch": 0.3204449152542373,
|
1716 |
+
"grad_norm": 3.84375,
|
1717 |
+
"learning_rate": 8.132108376241849e-06,
|
1718 |
+
"loss": 2.1779,
|
1719 |
+
"step": 242
|
1720 |
+
},
|
1721 |
+
{
|
1722 |
+
"epoch": 0.3217690677966102,
|
1723 |
+
"grad_norm": 3.921875,
|
1724 |
+
"learning_rate": 8.115001500914e-06,
|
1725 |
+
"loss": 2.1942,
|
1726 |
+
"step": 243
|
1727 |
+
},
|
1728 |
+
{
|
1729 |
+
"epoch": 0.3230932203389831,
|
1730 |
+
"grad_norm": 3.90625,
|
1731 |
+
"learning_rate": 8.097834823133002e-06,
|
1732 |
+
"loss": 1.9011,
|
1733 |
+
"step": 244
|
1734 |
+
},
|
1735 |
+
{
|
1736 |
+
"epoch": 0.3244173728813559,
|
1737 |
+
"grad_norm": 4.15625,
|
1738 |
+
"learning_rate": 8.08060867246834e-06,
|
1739 |
+
"loss": 1.9409,
|
1740 |
+
"step": 245
|
1741 |
+
},
|
1742 |
+
{
|
1743 |
+
"epoch": 0.3257415254237288,
|
1744 |
+
"grad_norm": 4.96875,
|
1745 |
+
"learning_rate": 8.063323379631274e-06,
|
1746 |
+
"loss": 1.9138,
|
1747 |
+
"step": 246
|
1748 |
+
},
|
1749 |
+
{
|
1750 |
+
"epoch": 0.3270656779661017,
|
1751 |
+
"grad_norm": 3.875,
|
1752 |
+
"learning_rate": 8.045979276468486e-06,
|
1753 |
+
"loss": 2.182,
|
1754 |
+
"step": 247
|
1755 |
+
},
|
1756 |
+
{
|
1757 |
+
"epoch": 0.3283898305084746,
|
1758 |
+
"grad_norm": 3.90625,
|
1759 |
+
"learning_rate": 8.028576695955711e-06,
|
1760 |
+
"loss": 2.0034,
|
1761 |
+
"step": 248
|
1762 |
+
},
|
1763 |
+
{
|
1764 |
+
"epoch": 0.3297139830508475,
|
1765 |
+
"grad_norm": 3.6875,
|
1766 |
+
"learning_rate": 8.011115972191347e-06,
|
1767 |
+
"loss": 2.1779,
|
1768 |
+
"step": 249
|
1769 |
+
},
|
1770 |
+
{
|
1771 |
+
"epoch": 0.3310381355932203,
|
1772 |
+
"grad_norm": 5.25,
|
1773 |
+
"learning_rate": 7.993597440390035e-06,
|
1774 |
+
"loss": 1.8994,
|
1775 |
+
"step": 250
|
1776 |
+
},
|
1777 |
+
{
|
1778 |
+
"epoch": 0.3323622881355932,
|
1779 |
+
"grad_norm": 3.765625,
|
1780 |
+
"learning_rate": 7.976021436876232e-06,
|
1781 |
+
"loss": 2.0865,
|
1782 |
+
"step": 251
|
1783 |
+
},
|
1784 |
+
{
|
1785 |
+
"epoch": 0.3336864406779661,
|
1786 |
+
"grad_norm": 3.90625,
|
1787 |
+
"learning_rate": 7.958388299077739e-06,
|
1788 |
+
"loss": 2.1092,
|
1789 |
+
"step": 252
|
1790 |
+
},
|
1791 |
+
{
|
1792 |
+
"epoch": 0.335010593220339,
|
1793 |
+
"grad_norm": 4.0,
|
1794 |
+
"learning_rate": 7.940698365519246e-06,
|
1795 |
+
"loss": 2.0966,
|
1796 |
+
"step": 253
|
1797 |
+
},
|
1798 |
+
{
|
1799 |
+
"epoch": 0.3363347457627119,
|
1800 |
+
"grad_norm": 3.625,
|
1801 |
+
"learning_rate": 7.92295197581581e-06,
|
1802 |
+
"loss": 2.0216,
|
1803 |
+
"step": 254
|
1804 |
+
},
|
1805 |
+
{
|
1806 |
+
"epoch": 0.3376588983050847,
|
1807 |
+
"grad_norm": 3.796875,
|
1808 |
+
"learning_rate": 7.905149470666348e-06,
|
1809 |
+
"loss": 2.036,
|
1810 |
+
"step": 255
|
1811 |
+
},
|
1812 |
+
{
|
1813 |
+
"epoch": 0.3389830508474576,
|
1814 |
+
"grad_norm": 4.625,
|
1815 |
+
"learning_rate": 7.887291191847098e-06,
|
1816 |
+
"loss": 2.0037,
|
1817 |
+
"step": 256
|
1818 |
+
},
|
1819 |
+
{
|
1820 |
+
"epoch": 0.3403072033898305,
|
1821 |
+
"grad_norm": 4.0625,
|
1822 |
+
"learning_rate": 7.869377482205042e-06,
|
1823 |
+
"loss": 2.0473,
|
1824 |
+
"step": 257
|
1825 |
+
},
|
1826 |
+
{
|
1827 |
+
"epoch": 0.3416313559322034,
|
1828 |
+
"grad_norm": 4.125,
|
1829 |
+
"learning_rate": 7.851408685651342e-06,
|
1830 |
+
"loss": 2.0279,
|
1831 |
+
"step": 258
|
1832 |
+
},
|
1833 |
+
{
|
1834 |
+
"epoch": 0.3429555084745763,
|
1835 |
+
"grad_norm": 3.9375,
|
1836 |
+
"learning_rate": 7.833385147154733e-06,
|
1837 |
+
"loss": 2.1209,
|
1838 |
+
"step": 259
|
1839 |
+
},
|
1840 |
+
{
|
1841 |
+
"epoch": 0.3442796610169492,
|
1842 |
+
"grad_norm": 3.96875,
|
1843 |
+
"learning_rate": 7.815307212734888e-06,
|
1844 |
+
"loss": 2.0669,
|
1845 |
+
"step": 260
|
1846 |
+
},
|
1847 |
+
{
|
1848 |
+
"epoch": 0.345603813559322,
|
1849 |
+
"grad_norm": 3.71875,
|
1850 |
+
"learning_rate": 7.797175229455793e-06,
|
1851 |
+
"loss": 2.033,
|
1852 |
+
"step": 261
|
1853 |
+
},
|
1854 |
+
{
|
1855 |
+
"epoch": 0.3469279661016949,
|
1856 |
+
"grad_norm": 4.46875,
|
1857 |
+
"learning_rate": 7.778989545419068e-06,
|
1858 |
+
"loss": 2.0184,
|
1859 |
+
"step": 262
|
1860 |
+
},
|
1861 |
+
{
|
1862 |
+
"epoch": 0.3482521186440678,
|
1863 |
+
"grad_norm": 3.765625,
|
1864 |
+
"learning_rate": 7.7607505097573e-06,
|
1865 |
+
"loss": 2.2567,
|
1866 |
+
"step": 263
|
1867 |
+
},
|
1868 |
+
{
|
1869 |
+
"epoch": 0.3495762711864407,
|
1870 |
+
"grad_norm": 3.6875,
|
1871 |
+
"learning_rate": 7.742458472627321e-06,
|
1872 |
+
"loss": 2.0145,
|
1873 |
+
"step": 264
|
1874 |
+
},
|
1875 |
+
{
|
1876 |
+
"epoch": 0.3509004237288136,
|
1877 |
+
"grad_norm": 3.953125,
|
1878 |
+
"learning_rate": 7.724113785203506e-06,
|
1879 |
+
"loss": 1.94,
|
1880 |
+
"step": 265
|
1881 |
+
},
|
1882 |
+
{
|
1883 |
+
"epoch": 0.3522245762711864,
|
1884 |
+
"grad_norm": 3.78125,
|
1885 |
+
"learning_rate": 7.705716799671019e-06,
|
1886 |
+
"loss": 2.0266,
|
1887 |
+
"step": 266
|
1888 |
+
},
|
1889 |
+
{
|
1890 |
+
"epoch": 0.3535487288135593,
|
1891 |
+
"grad_norm": 3.953125,
|
1892 |
+
"learning_rate": 7.687267869219052e-06,
|
1893 |
+
"loss": 1.9502,
|
1894 |
+
"step": 267
|
1895 |
+
},
|
1896 |
+
{
|
1897 |
+
"epoch": 0.3548728813559322,
|
1898 |
+
"grad_norm": 3.953125,
|
1899 |
+
"learning_rate": 7.668767348034044e-06,
|
1900 |
+
"loss": 2.1102,
|
1901 |
+
"step": 268
|
1902 |
+
},
|
1903 |
+
{
|
1904 |
+
"epoch": 0.3561970338983051,
|
1905 |
+
"grad_norm": 3.90625,
|
1906 |
+
"learning_rate": 7.650215591292888e-06,
|
1907 |
+
"loss": 1.8979,
|
1908 |
+
"step": 269
|
1909 |
+
},
|
1910 |
+
{
|
1911 |
+
"epoch": 0.357521186440678,
|
1912 |
+
"grad_norm": 4.125,
|
1913 |
+
"learning_rate": 7.631612955156111e-06,
|
1914 |
+
"loss": 1.9134,
|
1915 |
+
"step": 270
|
1916 |
+
},
|
1917 |
+
{
|
1918 |
+
"epoch": 0.3588453389830508,
|
1919 |
+
"grad_norm": 3.84375,
|
1920 |
+
"learning_rate": 7.6129597967610244e-06,
|
1921 |
+
"loss": 2.0089,
|
1922 |
+
"step": 271
|
1923 |
+
},
|
1924 |
+
{
|
1925 |
+
"epoch": 0.3601694915254237,
|
1926 |
+
"grad_norm": 3.890625,
|
1927 |
+
"learning_rate": 7.594256474214883e-06,
|
1928 |
+
"loss": 1.9536,
|
1929 |
+
"step": 272
|
1930 |
+
},
|
1931 |
+
{
|
1932 |
+
"epoch": 0.3614936440677966,
|
1933 |
+
"grad_norm": 3.984375,
|
1934 |
+
"learning_rate": 7.5755033465880024e-06,
|
1935 |
+
"loss": 2.0965,
|
1936 |
+
"step": 273
|
1937 |
+
},
|
1938 |
+
{
|
1939 |
+
"epoch": 0.3628177966101695,
|
1940 |
+
"grad_norm": 4.28125,
|
1941 |
+
"learning_rate": 7.556700773906866e-06,
|
1942 |
+
"loss": 2.0323,
|
1943 |
+
"step": 274
|
1944 |
+
},
|
1945 |
+
{
|
1946 |
+
"epoch": 0.3641419491525424,
|
1947 |
+
"grad_norm": 3.8125,
|
1948 |
+
"learning_rate": 7.537849117147212e-06,
|
1949 |
+
"loss": 2.0372,
|
1950 |
+
"step": 275
|
1951 |
+
},
|
1952 |
+
{
|
1953 |
+
"epoch": 0.3654661016949153,
|
1954 |
+
"grad_norm": 3.640625,
|
1955 |
+
"learning_rate": 7.5189487382271095e-06,
|
1956 |
+
"loss": 2.0669,
|
1957 |
+
"step": 276
|
1958 |
+
},
|
1959 |
+
{
|
1960 |
+
"epoch": 0.3667902542372881,
|
1961 |
+
"grad_norm": 3.703125,
|
1962 |
+
"learning_rate": 7.500000000000001e-06,
|
1963 |
+
"loss": 1.9949,
|
1964 |
+
"step": 277
|
1965 |
+
},
|
1966 |
+
{
|
1967 |
+
"epoch": 0.368114406779661,
|
1968 |
+
"grad_norm": 3.703125,
|
1969 |
+
"learning_rate": 7.481003266247745e-06,
|
1970 |
+
"loss": 2.1448,
|
1971 |
+
"step": 278
|
1972 |
+
},
|
1973 |
+
{
|
1974 |
+
"epoch": 0.3694385593220339,
|
1975 |
+
"grad_norm": 3.90625,
|
1976 |
+
"learning_rate": 7.461958901673625e-06,
|
1977 |
+
"loss": 2.0343,
|
1978 |
+
"step": 279
|
1979 |
+
},
|
1980 |
+
{
|
1981 |
+
"epoch": 0.3707627118644068,
|
1982 |
+
"grad_norm": 4.25,
|
1983 |
+
"learning_rate": 7.4428672718953535e-06,
|
1984 |
+
"loss": 2.0603,
|
1985 |
+
"step": 280
|
1986 |
+
},
|
1987 |
+
{
|
1988 |
+
"epoch": 0.3720868644067797,
|
1989 |
+
"grad_norm": 3.640625,
|
1990 |
+
"learning_rate": 7.4237287434380485e-06,
|
1991 |
+
"loss": 1.9779,
|
1992 |
+
"step": 281
|
1993 |
+
},
|
1994 |
+
{
|
1995 |
+
"epoch": 0.3734110169491525,
|
1996 |
+
"grad_norm": 3.78125,
|
1997 |
+
"learning_rate": 7.404543683727201e-06,
|
1998 |
+
"loss": 2.1302,
|
1999 |
+
"step": 282
|
2000 |
+
},
|
2001 |
+
{
|
2002 |
+
"epoch": 0.3747351694915254,
|
2003 |
+
"grad_norm": 6.15625,
|
2004 |
+
"learning_rate": 7.385312461081616e-06,
|
2005 |
+
"loss": 1.9677,
|
2006 |
+
"step": 283
|
2007 |
+
},
|
2008 |
+
{
|
2009 |
+
"epoch": 0.3760593220338983,
|
2010 |
+
"grad_norm": 7.6875,
|
2011 |
+
"learning_rate": 7.366035444706346e-06,
|
2012 |
+
"loss": 1.969,
|
2013 |
+
"step": 284
|
2014 |
+
},
|
2015 |
+
{
|
2016 |
+
"epoch": 0.3773834745762712,
|
2017 |
+
"grad_norm": 3.953125,
|
2018 |
+
"learning_rate": 7.346713004685602e-06,
|
2019 |
+
"loss": 2.0783,
|
2020 |
+
"step": 285
|
2021 |
+
},
|
2022 |
+
{
|
2023 |
+
"epoch": 0.3787076271186441,
|
2024 |
+
"grad_norm": 3.875,
|
2025 |
+
"learning_rate": 7.3273455119756445e-06,
|
2026 |
+
"loss": 2.134,
|
2027 |
+
"step": 286
|
2028 |
+
},
|
2029 |
+
{
|
2030 |
+
"epoch": 0.3800317796610169,
|
2031 |
+
"grad_norm": 4.125,
|
2032 |
+
"learning_rate": 7.307933338397667e-06,
|
2033 |
+
"loss": 2.0337,
|
2034 |
+
"step": 287
|
2035 |
+
},
|
2036 |
+
{
|
2037 |
+
"epoch": 0.3813559322033898,
|
2038 |
+
"grad_norm": 3.59375,
|
2039 |
+
"learning_rate": 7.288476856630656e-06,
|
2040 |
+
"loss": 2.2021,
|
2041 |
+
"step": 288
|
2042 |
+
},
|
2043 |
+
{
|
2044 |
+
"epoch": 0.3826800847457627,
|
2045 |
+
"grad_norm": 3.765625,
|
2046 |
+
"learning_rate": 7.268976440204236e-06,
|
2047 |
+
"loss": 2.0299,
|
2048 |
+
"step": 289
|
2049 |
+
},
|
2050 |
+
{
|
2051 |
+
"epoch": 0.3840042372881356,
|
2052 |
+
"grad_norm": 4.15625,
|
2053 |
+
"learning_rate": 7.249432463491498e-06,
|
2054 |
+
"loss": 1.9574,
|
2055 |
+
"step": 290
|
2056 |
+
},
|
2057 |
+
{
|
2058 |
+
"epoch": 0.3853283898305085,
|
2059 |
+
"grad_norm": 3.734375,
|
2060 |
+
"learning_rate": 7.229845301701811e-06,
|
2061 |
+
"loss": 2.2027,
|
2062 |
+
"step": 291
|
2063 |
+
},
|
2064 |
+
{
|
2065 |
+
"epoch": 0.3866525423728814,
|
2066 |
+
"grad_norm": 3.578125,
|
2067 |
+
"learning_rate": 7.2102153308736225e-06,
|
2068 |
+
"loss": 2.1389,
|
2069 |
+
"step": 292
|
2070 |
+
},
|
2071 |
+
{
|
2072 |
+
"epoch": 0.3879766949152542,
|
2073 |
+
"grad_norm": 3.796875,
|
2074 |
+
"learning_rate": 7.190542927867234e-06,
|
2075 |
+
"loss": 1.8233,
|
2076 |
+
"step": 293
|
2077 |
+
},
|
2078 |
+
{
|
2079 |
+
"epoch": 0.3893008474576271,
|
2080 |
+
"grad_norm": 3.984375,
|
2081 |
+
"learning_rate": 7.1708284703575734e-06,
|
2082 |
+
"loss": 1.9075,
|
2083 |
+
"step": 294
|
2084 |
+
},
|
2085 |
+
{
|
2086 |
+
"epoch": 0.390625,
|
2087 |
+
"grad_norm": 4.5625,
|
2088 |
+
"learning_rate": 7.1510723368269376e-06,
|
2089 |
+
"loss": 1.8944,
|
2090 |
+
"step": 295
|
2091 |
+
},
|
2092 |
+
{
|
2093 |
+
"epoch": 0.3919491525423729,
|
2094 |
+
"grad_norm": 4.0,
|
2095 |
+
"learning_rate": 7.131274906557725e-06,
|
2096 |
+
"loss": 2.1448,
|
2097 |
+
"step": 296
|
2098 |
+
},
|
2099 |
+
{
|
2100 |
+
"epoch": 0.3932733050847458,
|
2101 |
+
"grad_norm": 4.34375,
|
2102 |
+
"learning_rate": 7.111436559625162e-06,
|
2103 |
+
"loss": 2.0403,
|
2104 |
+
"step": 297
|
2105 |
+
},
|
2106 |
+
{
|
2107 |
+
"epoch": 0.3945974576271186,
|
2108 |
+
"grad_norm": 3.90625,
|
2109 |
+
"learning_rate": 7.091557676890001e-06,
|
2110 |
+
"loss": 1.982,
|
2111 |
+
"step": 298
|
2112 |
+
},
|
2113 |
+
{
|
2114 |
+
"epoch": 0.3959216101694915,
|
2115 |
+
"grad_norm": 4.5,
|
2116 |
+
"learning_rate": 7.0716386399912075e-06,
|
2117 |
+
"loss": 2.1055,
|
2118 |
+
"step": 299
|
2119 |
+
},
|
2120 |
+
{
|
2121 |
+
"epoch": 0.3972457627118644,
|
2122 |
+
"grad_norm": 3.515625,
|
2123 |
+
"learning_rate": 7.051679831338638e-06,
|
2124 |
+
"loss": 1.8751,
|
2125 |
+
"step": 300
|
2126 |
+
},
|
2127 |
+
{
|
2128 |
+
"epoch": 0.3985699152542373,
|
2129 |
+
"grad_norm": 3.765625,
|
2130 |
+
"learning_rate": 7.03168163410569e-06,
|
2131 |
+
"loss": 2.0518,
|
2132 |
+
"step": 301
|
2133 |
+
},
|
2134 |
+
{
|
2135 |
+
"epoch": 0.3998940677966102,
|
2136 |
+
"grad_norm": 3.8125,
|
2137 |
+
"learning_rate": 7.0116444322219575e-06,
|
2138 |
+
"loss": 1.9739,
|
2139 |
+
"step": 302
|
2140 |
+
},
|
2141 |
+
{
|
2142 |
+
"epoch": 0.4012182203389831,
|
2143 |
+
"grad_norm": 3.578125,
|
2144 |
+
"learning_rate": 6.991568610365851e-06,
|
2145 |
+
"loss": 2.0927,
|
2146 |
+
"step": 303
|
2147 |
+
},
|
2148 |
+
{
|
2149 |
+
"epoch": 0.4025423728813559,
|
2150 |
+
"grad_norm": 4.4375,
|
2151 |
+
"learning_rate": 6.971454553957216e-06,
|
2152 |
+
"loss": 2.0478,
|
2153 |
+
"step": 304
|
2154 |
+
},
|
2155 |
+
{
|
2156 |
+
"epoch": 0.4038665254237288,
|
2157 |
+
"grad_norm": 4.15625,
|
2158 |
+
"learning_rate": 6.95130264914993e-06,
|
2159 |
+
"loss": 2.0242,
|
2160 |
+
"step": 305
|
2161 |
+
},
|
2162 |
+
{
|
2163 |
+
"epoch": 0.4051906779661017,
|
2164 |
+
"grad_norm": 3.65625,
|
2165 |
+
"learning_rate": 6.931113282824498e-06,
|
2166 |
+
"loss": 2.1597,
|
2167 |
+
"step": 306
|
2168 |
+
},
|
2169 |
+
{
|
2170 |
+
"epoch": 0.4065148305084746,
|
2171 |
+
"grad_norm": 3.734375,
|
2172 |
+
"learning_rate": 6.910886842580612e-06,
|
2173 |
+
"loss": 1.9689,
|
2174 |
+
"step": 307
|
2175 |
+
},
|
2176 |
+
{
|
2177 |
+
"epoch": 0.4078389830508475,
|
2178 |
+
"grad_norm": 3.640625,
|
2179 |
+
"learning_rate": 6.890623716729724e-06,
|
2180 |
+
"loss": 2.1267,
|
2181 |
+
"step": 308
|
2182 |
+
},
|
2183 |
+
{
|
2184 |
+
"epoch": 0.4091631355932203,
|
2185 |
+
"grad_norm": 3.796875,
|
2186 |
+
"learning_rate": 6.870324294287578e-06,
|
2187 |
+
"loss": 2.0548,
|
2188 |
+
"step": 309
|
2189 |
+
},
|
2190 |
+
{
|
2191 |
+
"epoch": 0.4104872881355932,
|
2192 |
+
"grad_norm": 3.703125,
|
2193 |
+
"learning_rate": 6.8499889649667516e-06,
|
2194 |
+
"loss": 2.2051,
|
2195 |
+
"step": 310
|
2196 |
+
},
|
2197 |
+
{
|
2198 |
+
"epoch": 0.4118114406779661,
|
2199 |
+
"grad_norm": 3.765625,
|
2200 |
+
"learning_rate": 6.829618119169169e-06,
|
2201 |
+
"loss": 1.9724,
|
2202 |
+
"step": 311
|
2203 |
+
},
|
2204 |
+
{
|
2205 |
+
"epoch": 0.413135593220339,
|
2206 |
+
"grad_norm": 4.09375,
|
2207 |
+
"learning_rate": 6.809212147978605e-06,
|
2208 |
+
"loss": 2.0979,
|
2209 |
+
"step": 312
|
2210 |
+
},
|
2211 |
+
{
|
2212 |
+
"epoch": 0.4144597457627119,
|
2213 |
+
"grad_norm": 3.953125,
|
2214 |
+
"learning_rate": 6.788771443153183e-06,
|
2215 |
+
"loss": 2.1663,
|
2216 |
+
"step": 313
|
2217 |
+
},
|
2218 |
+
{
|
2219 |
+
"epoch": 0.4157838983050847,
|
2220 |
+
"grad_norm": 4.03125,
|
2221 |
+
"learning_rate": 6.768296397117848e-06,
|
2222 |
+
"loss": 1.9478,
|
2223 |
+
"step": 314
|
2224 |
+
},
|
2225 |
+
{
|
2226 |
+
"epoch": 0.4171080508474576,
|
2227 |
+
"grad_norm": 4.03125,
|
2228 |
+
"learning_rate": 6.7477874029568345e-06,
|
2229 |
+
"loss": 2.0767,
|
2230 |
+
"step": 315
|
2231 |
+
},
|
2232 |
+
{
|
2233 |
+
"epoch": 0.4184322033898305,
|
2234 |
+
"grad_norm": 5.875,
|
2235 |
+
"learning_rate": 6.7272448544061184e-06,
|
2236 |
+
"loss": 2.0509,
|
2237 |
+
"step": 316
|
2238 |
+
},
|
2239 |
+
{
|
2240 |
+
"epoch": 0.4197563559322034,
|
2241 |
+
"grad_norm": 3.921875,
|
2242 |
+
"learning_rate": 6.706669145845863e-06,
|
2243 |
+
"loss": 2.0612,
|
2244 |
+
"step": 317
|
2245 |
+
},
|
2246 |
+
{
|
2247 |
+
"epoch": 0.4210805084745763,
|
2248 |
+
"grad_norm": 5.09375,
|
2249 |
+
"learning_rate": 6.686060672292847e-06,
|
2250 |
+
"loss": 1.9404,
|
2251 |
+
"step": 318
|
2252 |
+
},
|
2253 |
+
{
|
2254 |
+
"epoch": 0.4224046610169492,
|
2255 |
+
"grad_norm": 4.0,
|
2256 |
+
"learning_rate": 6.6654198293928695e-06,
|
2257 |
+
"loss": 2.0939,
|
2258 |
+
"step": 319
|
2259 |
+
},
|
2260 |
+
{
|
2261 |
+
"epoch": 0.423728813559322,
|
2262 |
+
"grad_norm": 4.84375,
|
2263 |
+
"learning_rate": 6.6447470134131685e-06,
|
2264 |
+
"loss": 1.9003,
|
2265 |
+
"step": 320
|
2266 |
+
},
|
2267 |
+
{
|
2268 |
+
"epoch": 0.4250529661016949,
|
2269 |
+
"grad_norm": 4.0,
|
2270 |
+
"learning_rate": 6.624042621234814e-06,
|
2271 |
+
"loss": 2.1884,
|
2272 |
+
"step": 321
|
2273 |
+
},
|
2274 |
+
{
|
2275 |
+
"epoch": 0.4263771186440678,
|
2276 |
+
"grad_norm": 3.734375,
|
2277 |
+
"learning_rate": 6.603307050345069e-06,
|
2278 |
+
"loss": 1.9816,
|
2279 |
+
"step": 322
|
2280 |
+
},
|
2281 |
+
{
|
2282 |
+
"epoch": 0.4277012711864407,
|
2283 |
+
"grad_norm": 3.828125,
|
2284 |
+
"learning_rate": 6.5825406988297815e-06,
|
2285 |
+
"loss": 1.9909,
|
2286 |
+
"step": 323
|
2287 |
+
},
|
2288 |
+
{
|
2289 |
+
"epoch": 0.4290254237288136,
|
2290 |
+
"grad_norm": 4.03125,
|
2291 |
+
"learning_rate": 6.561743965365732e-06,
|
2292 |
+
"loss": 2.1602,
|
2293 |
+
"step": 324
|
2294 |
+
},
|
2295 |
+
{
|
2296 |
+
"epoch": 0.4303495762711864,
|
2297 |
+
"grad_norm": 3.625,
|
2298 |
+
"learning_rate": 6.540917249212976e-06,
|
2299 |
+
"loss": 2.2546,
|
2300 |
+
"step": 325
|
2301 |
+
},
|
2302 |
+
{
|
2303 |
+
"epoch": 0.4316737288135593,
|
2304 |
+
"grad_norm": 3.734375,
|
2305 |
+
"learning_rate": 6.520060950207186e-06,
|
2306 |
+
"loss": 2.1109,
|
2307 |
+
"step": 326
|
2308 |
+
},
|
2309 |
+
{
|
2310 |
+
"epoch": 0.4329978813559322,
|
2311 |
+
"grad_norm": 3.6875,
|
2312 |
+
"learning_rate": 6.4991754687519695e-06,
|
2313 |
+
"loss": 1.9424,
|
2314 |
+
"step": 327
|
2315 |
+
},
|
2316 |
+
{
|
2317 |
+
"epoch": 0.4343220338983051,
|
2318 |
+
"grad_norm": 4.03125,
|
2319 |
+
"learning_rate": 6.478261205811188e-06,
|
2320 |
+
"loss": 1.9637,
|
2321 |
+
"step": 328
|
2322 |
+
},
|
2323 |
+
{
|
2324 |
+
"epoch": 0.435646186440678,
|
2325 |
+
"grad_norm": 4.1875,
|
2326 |
+
"learning_rate": 6.457318562901257e-06,
|
2327 |
+
"loss": 1.9564,
|
2328 |
+
"step": 329
|
2329 |
+
},
|
2330 |
+
{
|
2331 |
+
"epoch": 0.4369703389830508,
|
2332 |
+
"grad_norm": 3.734375,
|
2333 |
+
"learning_rate": 6.43634794208343e-06,
|
2334 |
+
"loss": 2.1901,
|
2335 |
+
"step": 330
|
2336 |
+
},
|
2337 |
+
{
|
2338 |
+
"epoch": 0.4382944915254237,
|
2339 |
+
"grad_norm": 4.0625,
|
2340 |
+
"learning_rate": 6.415349745956093e-06,
|
2341 |
+
"loss": 1.8634,
|
2342 |
+
"step": 331
|
2343 |
+
},
|
2344 |
+
{
|
2345 |
+
"epoch": 0.4396186440677966,
|
2346 |
+
"grad_norm": 4.1875,
|
2347 |
+
"learning_rate": 6.394324377647028e-06,
|
2348 |
+
"loss": 1.9514,
|
2349 |
+
"step": 332
|
2350 |
+
},
|
2351 |
+
{
|
2352 |
+
"epoch": 0.4409427966101695,
|
2353 |
+
"grad_norm": 3.953125,
|
2354 |
+
"learning_rate": 6.373272240805668e-06,
|
2355 |
+
"loss": 1.8502,
|
2356 |
+
"step": 333
|
2357 |
+
},
|
2358 |
+
{
|
2359 |
+
"epoch": 0.4422669491525424,
|
2360 |
+
"grad_norm": 3.78125,
|
2361 |
+
"learning_rate": 6.35219373959536e-06,
|
2362 |
+
"loss": 1.9593,
|
2363 |
+
"step": 334
|
2364 |
+
},
|
2365 |
+
{
|
2366 |
+
"epoch": 0.4435911016949153,
|
2367 |
+
"grad_norm": 3.765625,
|
2368 |
+
"learning_rate": 6.331089278685599e-06,
|
2369 |
+
"loss": 2.057,
|
2370 |
+
"step": 335
|
2371 |
+
},
|
2372 |
+
{
|
2373 |
+
"epoch": 0.4449152542372881,
|
2374 |
+
"grad_norm": 4.84375,
|
2375 |
+
"learning_rate": 6.30995926324426e-06,
|
2376 |
+
"loss": 1.9964,
|
2377 |
+
"step": 336
|
2378 |
+
},
|
2379 |
+
{
|
2380 |
+
"epoch": 0.446239406779661,
|
2381 |
+
"grad_norm": 3.796875,
|
2382 |
+
"learning_rate": 6.2888040989298136e-06,
|
2383 |
+
"loss": 2.2322,
|
2384 |
+
"step": 337
|
2385 |
+
},
|
2386 |
+
{
|
2387 |
+
"epoch": 0.4475635593220339,
|
2388 |
+
"grad_norm": 3.84375,
|
2389 |
+
"learning_rate": 6.267624191883551e-06,
|
2390 |
+
"loss": 1.9032,
|
2391 |
+
"step": 338
|
2392 |
+
},
|
2393 |
+
{
|
2394 |
+
"epoch": 0.4488877118644068,
|
2395 |
+
"grad_norm": 3.90625,
|
2396 |
+
"learning_rate": 6.246419948721777e-06,
|
2397 |
+
"loss": 2.026,
|
2398 |
+
"step": 339
|
2399 |
+
},
|
2400 |
+
{
|
2401 |
+
"epoch": 0.4502118644067797,
|
2402 |
+
"grad_norm": 3.625,
|
2403 |
+
"learning_rate": 6.2251917765280056e-06,
|
2404 |
+
"loss": 2.1106,
|
2405 |
+
"step": 340
|
2406 |
+
},
|
2407 |
+
{
|
2408 |
+
"epoch": 0.4515360169491525,
|
2409 |
+
"grad_norm": 3.859375,
|
2410 |
+
"learning_rate": 6.203940082845144e-06,
|
2411 |
+
"loss": 1.8843,
|
2412 |
+
"step": 341
|
2413 |
+
},
|
2414 |
+
{
|
2415 |
+
"epoch": 0.4528601694915254,
|
2416 |
+
"grad_norm": 4.0,
|
2417 |
+
"learning_rate": 6.182665275667674e-06,
|
2418 |
+
"loss": 1.8529,
|
2419 |
+
"step": 342
|
2420 |
+
},
|
2421 |
+
{
|
2422 |
+
"epoch": 0.4541843220338983,
|
2423 |
+
"grad_norm": 3.859375,
|
2424 |
+
"learning_rate": 6.161367763433812e-06,
|
2425 |
+
"loss": 2.0598,
|
2426 |
+
"step": 343
|
2427 |
+
},
|
2428 |
+
{
|
2429 |
+
"epoch": 0.4555084745762712,
|
2430 |
+
"grad_norm": 3.859375,
|
2431 |
+
"learning_rate": 6.140047955017672e-06,
|
2432 |
+
"loss": 2.0318,
|
2433 |
+
"step": 344
|
2434 |
+
},
|
2435 |
+
{
|
2436 |
+
"epoch": 0.4568326271186441,
|
2437 |
+
"grad_norm": 4.09375,
|
2438 |
+
"learning_rate": 6.118706259721414e-06,
|
2439 |
+
"loss": 2.0361,
|
2440 |
+
"step": 345
|
2441 |
+
},
|
2442 |
+
{
|
2443 |
+
"epoch": 0.4581567796610169,
|
2444 |
+
"grad_norm": 3.984375,
|
2445 |
+
"learning_rate": 6.097343087267386e-06,
|
2446 |
+
"loss": 2.0142,
|
2447 |
+
"step": 346
|
2448 |
+
},
|
2449 |
+
{
|
2450 |
+
"epoch": 0.4594809322033898,
|
2451 |
+
"grad_norm": 4.09375,
|
2452 |
+
"learning_rate": 6.075958847790262e-06,
|
2453 |
+
"loss": 2.0354,
|
2454 |
+
"step": 347
|
2455 |
+
},
|
2456 |
+
{
|
2457 |
+
"epoch": 0.4608050847457627,
|
2458 |
+
"grad_norm": 3.765625,
|
2459 |
+
"learning_rate": 6.054553951829163e-06,
|
2460 |
+
"loss": 1.9838,
|
2461 |
+
"step": 348
|
2462 |
+
},
|
2463 |
+
{
|
2464 |
+
"epoch": 0.4621292372881356,
|
2465 |
+
"grad_norm": 4.03125,
|
2466 |
+
"learning_rate": 6.033128810319779e-06,
|
2467 |
+
"loss": 1.9332,
|
2468 |
+
"step": 349
|
2469 |
+
},
|
2470 |
+
{
|
2471 |
+
"epoch": 0.4634533898305085,
|
2472 |
+
"grad_norm": 3.75,
|
2473 |
+
"learning_rate": 6.011683834586474e-06,
|
2474 |
+
"loss": 2.0284,
|
2475 |
+
"step": 350
|
2476 |
+
},
|
2477 |
+
{
|
2478 |
+
"epoch": 0.4647775423728814,
|
2479 |
+
"grad_norm": 3.703125,
|
2480 |
+
"learning_rate": 5.9902194363344014e-06,
|
2481 |
+
"loss": 1.9933,
|
2482 |
+
"step": 351
|
2483 |
+
},
|
2484 |
+
{
|
2485 |
+
"epoch": 0.4661016949152542,
|
2486 |
+
"grad_norm": 3.96875,
|
2487 |
+
"learning_rate": 5.968736027641584e-06,
|
2488 |
+
"loss": 1.9212,
|
2489 |
+
"step": 352
|
2490 |
+
},
|
2491 |
+
{
|
2492 |
+
"epoch": 0.4674258474576271,
|
2493 |
+
"grad_norm": 4.3125,
|
2494 |
+
"learning_rate": 5.947234020951015e-06,
|
2495 |
+
"loss": 1.9715,
|
2496 |
+
"step": 353
|
2497 |
+
},
|
2498 |
+
{
|
2499 |
+
"epoch": 0.46875,
|
2500 |
+
"grad_norm": 4.0625,
|
2501 |
+
"learning_rate": 5.925713829062737e-06,
|
2502 |
+
"loss": 2.116,
|
2503 |
+
"step": 354
|
2504 |
+
},
|
2505 |
+
{
|
2506 |
+
"epoch": 0.4700741525423729,
|
2507 |
+
"grad_norm": 4.0,
|
2508 |
+
"learning_rate": 5.904175865125915e-06,
|
2509 |
+
"loss": 1.8785,
|
2510 |
+
"step": 355
|
2511 |
+
},
|
2512 |
+
{
|
2513 |
+
"epoch": 0.4713983050847458,
|
2514 |
+
"grad_norm": 3.8125,
|
2515 |
+
"learning_rate": 5.882620542630901e-06,
|
2516 |
+
"loss": 2.1109,
|
2517 |
+
"step": 356
|
2518 |
+
},
|
2519 |
+
{
|
2520 |
+
"epoch": 0.4727224576271186,
|
2521 |
+
"grad_norm": 4.0625,
|
2522 |
+
"learning_rate": 5.86104827540131e-06,
|
2523 |
+
"loss": 2.046,
|
2524 |
+
"step": 357
|
2525 |
+
},
|
2526 |
+
{
|
2527 |
+
"epoch": 0.4740466101694915,
|
2528 |
+
"grad_norm": 3.890625,
|
2529 |
+
"learning_rate": 5.839459477586056e-06,
|
2530 |
+
"loss": 1.931,
|
2531 |
+
"step": 358
|
2532 |
+
},
|
2533 |
+
{
|
2534 |
+
"epoch": 0.4753707627118644,
|
2535 |
+
"grad_norm": 4.0,
|
2536 |
+
"learning_rate": 5.817854563651415e-06,
|
2537 |
+
"loss": 1.9138,
|
2538 |
+
"step": 359
|
2539 |
+
},
|
2540 |
+
{
|
2541 |
+
"epoch": 0.4766949152542373,
|
2542 |
+
"grad_norm": 3.90625,
|
2543 |
+
"learning_rate": 5.796233948373061e-06,
|
2544 |
+
"loss": 2.0626,
|
2545 |
+
"step": 360
|
2546 |
+
},
|
2547 |
+
{
|
2548 |
+
"epoch": 0.4780190677966102,
|
2549 |
+
"grad_norm": 3.6875,
|
2550 |
+
"learning_rate": 5.7745980468281116e-06,
|
2551 |
+
"loss": 1.9901,
|
2552 |
+
"step": 361
|
2553 |
+
},
|
2554 |
+
{
|
2555 |
+
"epoch": 0.4793432203389831,
|
2556 |
+
"grad_norm": 3.515625,
|
2557 |
+
"learning_rate": 5.752947274387147e-06,
|
2558 |
+
"loss": 2.1562,
|
2559 |
+
"step": 362
|
2560 |
+
},
|
2561 |
+
{
|
2562 |
+
"epoch": 0.4806673728813559,
|
2563 |
+
"grad_norm": 4.03125,
|
2564 |
+
"learning_rate": 5.731282046706247e-06,
|
2565 |
+
"loss": 1.9464,
|
2566 |
+
"step": 363
|
2567 |
+
},
|
2568 |
+
{
|
2569 |
+
"epoch": 0.4819915254237288,
|
2570 |
+
"grad_norm": 3.875,
|
2571 |
+
"learning_rate": 5.709602779718999e-06,
|
2572 |
+
"loss": 1.9471,
|
2573 |
+
"step": 364
|
2574 |
+
},
|
2575 |
+
{
|
2576 |
+
"epoch": 0.4833156779661017,
|
2577 |
+
"grad_norm": 3.640625,
|
2578 |
+
"learning_rate": 5.687909889628529e-06,
|
2579 |
+
"loss": 1.9786,
|
2580 |
+
"step": 365
|
2581 |
+
},
|
2582 |
+
{
|
2583 |
+
"epoch": 0.4846398305084746,
|
2584 |
+
"grad_norm": 3.796875,
|
2585 |
+
"learning_rate": 5.666203792899496e-06,
|
2586 |
+
"loss": 2.0612,
|
2587 |
+
"step": 366
|
2588 |
+
},
|
2589 |
+
{
|
2590 |
+
"epoch": 0.4859639830508475,
|
2591 |
+
"grad_norm": 3.84375,
|
2592 |
+
"learning_rate": 5.644484906250104e-06,
|
2593 |
+
"loss": 1.9507,
|
2594 |
+
"step": 367
|
2595 |
+
},
|
2596 |
+
{
|
2597 |
+
"epoch": 0.4872881355932203,
|
2598 |
+
"grad_norm": 3.984375,
|
2599 |
+
"learning_rate": 5.622753646644102e-06,
|
2600 |
+
"loss": 1.8828,
|
2601 |
+
"step": 368
|
2602 |
+
},
|
2603 |
+
{
|
2604 |
+
"epoch": 0.4886122881355932,
|
2605 |
+
"grad_norm": 3.671875,
|
2606 |
+
"learning_rate": 5.601010431282777e-06,
|
2607 |
+
"loss": 1.9527,
|
2608 |
+
"step": 369
|
2609 |
+
},
|
2610 |
+
{
|
2611 |
+
"epoch": 0.4899364406779661,
|
2612 |
+
"grad_norm": 3.90625,
|
2613 |
+
"learning_rate": 5.579255677596944e-06,
|
2614 |
+
"loss": 2.0724,
|
2615 |
+
"step": 370
|
2616 |
+
},
|
2617 |
+
{
|
2618 |
+
"epoch": 0.491260593220339,
|
2619 |
+
"grad_norm": 3.890625,
|
2620 |
+
"learning_rate": 5.557489803238934e-06,
|
2621 |
+
"loss": 1.9829,
|
2622 |
+
"step": 371
|
2623 |
+
},
|
2624 |
+
{
|
2625 |
+
"epoch": 0.4925847457627119,
|
2626 |
+
"grad_norm": 3.75,
|
2627 |
+
"learning_rate": 5.535713226074576e-06,
|
2628 |
+
"loss": 1.9163,
|
2629 |
+
"step": 372
|
2630 |
+
},
|
2631 |
+
{
|
2632 |
+
"epoch": 0.4939088983050847,
|
2633 |
+
"grad_norm": 3.90625,
|
2634 |
+
"learning_rate": 5.513926364175172e-06,
|
2635 |
+
"loss": 2.0671,
|
2636 |
+
"step": 373
|
2637 |
+
},
|
2638 |
+
{
|
2639 |
+
"epoch": 0.4952330508474576,
|
2640 |
+
"grad_norm": 3.75,
|
2641 |
+
"learning_rate": 5.492129635809473e-06,
|
2642 |
+
"loss": 2.0903,
|
2643 |
+
"step": 374
|
2644 |
+
},
|
2645 |
+
{
|
2646 |
+
"epoch": 0.4965572033898305,
|
2647 |
+
"grad_norm": 4.125,
|
2648 |
+
"learning_rate": 5.47032345943565e-06,
|
2649 |
+
"loss": 2.0251,
|
2650 |
+
"step": 375
|
2651 |
+
},
|
2652 |
+
{
|
2653 |
+
"epoch": 0.4978813559322034,
|
2654 |
+
"grad_norm": 3.65625,
|
2655 |
+
"learning_rate": 5.4485082536932564e-06,
|
2656 |
+
"loss": 2.0114,
|
2657 |
+
"step": 376
|
2658 |
+
},
|
2659 |
+
{
|
2660 |
+
"epoch": 0.4992055084745763,
|
2661 |
+
"grad_norm": 3.734375,
|
2662 |
+
"learning_rate": 5.426684437395196e-06,
|
2663 |
+
"loss": 1.9574,
|
2664 |
+
"step": 377
|
2665 |
+
},
|
2666 |
+
{
|
2667 |
+
"epoch": 0.5005296610169492,
|
2668 |
+
"grad_norm": 4.25,
|
2669 |
+
"learning_rate": 5.404852429519678e-06,
|
2670 |
+
"loss": 1.9259,
|
2671 |
+
"step": 378
|
2672 |
+
},
|
2673 |
+
{
|
2674 |
+
"epoch": 0.501853813559322,
|
2675 |
+
"grad_norm": 4.03125,
|
2676 |
+
"learning_rate": 5.383012649202173e-06,
|
2677 |
+
"loss": 1.9558,
|
2678 |
+
"step": 379
|
2679 |
+
},
|
2680 |
+
{
|
2681 |
+
"epoch": 0.503177966101695,
|
2682 |
+
"grad_norm": 3.96875,
|
2683 |
+
"learning_rate": 5.361165515727374e-06,
|
2684 |
+
"loss": 2.0474,
|
2685 |
+
"step": 380
|
2686 |
+
},
|
2687 |
+
{
|
2688 |
+
"epoch": 0.5045021186440678,
|
2689 |
+
"grad_norm": 3.890625,
|
2690 |
+
"learning_rate": 5.3393114485211394e-06,
|
2691 |
+
"loss": 2.0343,
|
2692 |
+
"step": 381
|
2693 |
+
},
|
2694 |
+
{
|
2695 |
+
"epoch": 0.5058262711864406,
|
2696 |
+
"grad_norm": 3.84375,
|
2697 |
+
"learning_rate": 5.31745086714244e-06,
|
2698 |
+
"loss": 1.9331,
|
2699 |
+
"step": 382
|
2700 |
+
},
|
2701 |
+
{
|
2702 |
+
"epoch": 0.5071504237288136,
|
2703 |
+
"grad_norm": 4.0,
|
2704 |
+
"learning_rate": 5.295584191275308e-06,
|
2705 |
+
"loss": 1.8745,
|
2706 |
+
"step": 383
|
2707 |
+
},
|
2708 |
+
{
|
2709 |
+
"epoch": 0.5084745762711864,
|
2710 |
+
"grad_norm": 3.8125,
|
2711 |
+
"learning_rate": 5.273711840720783e-06,
|
2712 |
+
"loss": 1.9222,
|
2713 |
+
"step": 384
|
2714 |
+
},
|
2715 |
+
{
|
2716 |
+
"epoch": 0.5097987288135594,
|
2717 |
+
"grad_norm": 4.0,
|
2718 |
+
"learning_rate": 5.251834235388845e-06,
|
2719 |
+
"loss": 2.1023,
|
2720 |
+
"step": 385
|
2721 |
+
},
|
2722 |
+
{
|
2723 |
+
"epoch": 0.5111228813559322,
|
2724 |
+
"grad_norm": 3.96875,
|
2725 |
+
"learning_rate": 5.229951795290353e-06,
|
2726 |
+
"loss": 1.9507,
|
2727 |
+
"step": 386
|
2728 |
+
},
|
2729 |
+
{
|
2730 |
+
"epoch": 0.512447033898305,
|
2731 |
+
"grad_norm": 3.75,
|
2732 |
+
"learning_rate": 5.208064940528994e-06,
|
2733 |
+
"loss": 2.0536,
|
2734 |
+
"step": 387
|
2735 |
+
},
|
2736 |
+
{
|
2737 |
+
"epoch": 0.513771186440678,
|
2738 |
+
"grad_norm": 3.6875,
|
2739 |
+
"learning_rate": 5.1861740912932e-06,
|
2740 |
+
"loss": 2.0979,
|
2741 |
+
"step": 388
|
2742 |
+
},
|
2743 |
+
{
|
2744 |
+
"epoch": 0.5150953389830508,
|
2745 |
+
"grad_norm": 3.75,
|
2746 |
+
"learning_rate": 5.164279667848094e-06,
|
2747 |
+
"loss": 2.0845,
|
2748 |
+
"step": 389
|
2749 |
+
},
|
2750 |
+
{
|
2751 |
+
"epoch": 0.5164194915254238,
|
2752 |
+
"grad_norm": 4.09375,
|
2753 |
+
"learning_rate": 5.142382090527415e-06,
|
2754 |
+
"loss": 2.0602,
|
2755 |
+
"step": 390
|
2756 |
+
},
|
2757 |
+
{
|
2758 |
+
"epoch": 0.5177436440677966,
|
2759 |
+
"grad_norm": 3.953125,
|
2760 |
+
"learning_rate": 5.1204817797254545e-06,
|
2761 |
+
"loss": 1.883,
|
2762 |
+
"step": 391
|
2763 |
+
},
|
2764 |
+
{
|
2765 |
+
"epoch": 0.5190677966101694,
|
2766 |
+
"grad_norm": 3.75,
|
2767 |
+
"learning_rate": 5.0985791558889785e-06,
|
2768 |
+
"loss": 2.131,
|
2769 |
+
"step": 392
|
2770 |
+
},
|
2771 |
+
{
|
2772 |
+
"epoch": 0.5203919491525424,
|
2773 |
+
"grad_norm": 3.90625,
|
2774 |
+
"learning_rate": 5.07667463950916e-06,
|
2775 |
+
"loss": 2.0166,
|
2776 |
+
"step": 393
|
2777 |
+
},
|
2778 |
+
{
|
2779 |
+
"epoch": 0.5217161016949152,
|
2780 |
+
"grad_norm": 3.703125,
|
2781 |
+
"learning_rate": 5.054768651113506e-06,
|
2782 |
+
"loss": 1.9136,
|
2783 |
+
"step": 394
|
2784 |
+
},
|
2785 |
+
{
|
2786 |
+
"epoch": 0.5230402542372882,
|
2787 |
+
"grad_norm": 4.15625,
|
2788 |
+
"learning_rate": 5.032861611257783e-06,
|
2789 |
+
"loss": 2.0923,
|
2790 |
+
"step": 395
|
2791 |
+
},
|
2792 |
+
{
|
2793 |
+
"epoch": 0.524364406779661,
|
2794 |
+
"grad_norm": 3.8125,
|
2795 |
+
"learning_rate": 5.0109539405179456e-06,
|
2796 |
+
"loss": 2.1243,
|
2797 |
+
"step": 396
|
2798 |
+
},
|
2799 |
+
{
|
2800 |
+
"epoch": 0.5256885593220338,
|
2801 |
+
"grad_norm": 3.703125,
|
2802 |
+
"learning_rate": 4.989046059482055e-06,
|
2803 |
+
"loss": 2.0784,
|
2804 |
+
"step": 397
|
2805 |
+
},
|
2806 |
+
{
|
2807 |
+
"epoch": 0.5270127118644068,
|
2808 |
+
"grad_norm": 3.765625,
|
2809 |
+
"learning_rate": 4.967138388742218e-06,
|
2810 |
+
"loss": 1.8999,
|
2811 |
+
"step": 398
|
2812 |
+
},
|
2813 |
+
{
|
2814 |
+
"epoch": 0.5283368644067796,
|
2815 |
+
"grad_norm": 3.734375,
|
2816 |
+
"learning_rate": 4.945231348886495e-06,
|
2817 |
+
"loss": 2.0906,
|
2818 |
+
"step": 399
|
2819 |
+
},
|
2820 |
+
{
|
2821 |
+
"epoch": 0.5296610169491526,
|
2822 |
+
"grad_norm": 3.828125,
|
2823 |
+
"learning_rate": 4.923325360490841e-06,
|
2824 |
+
"loss": 1.9295,
|
2825 |
+
"step": 400
|
2826 |
+
},
|
2827 |
+
{
|
2828 |
+
"epoch": 0.5296610169491526,
|
2829 |
+
"eval_AskDoctor-Chinese_loss": 1.9834351539611816,
|
2830 |
+
"eval_AskDoctor-Chinese_runtime": 15.9925,
|
2831 |
+
"eval_AskDoctor-Chinese_samples_per_second": 1.876,
|
2832 |
+
"eval_AskDoctor-Chinese_steps_per_second": 1.876,
|
2833 |
+
"step": 400
|
2834 |
+
},
|
2835 |
+
{
|
2836 |
+
"epoch": 0.5309851694915254,
|
2837 |
+
"grad_norm": 4.03125,
|
2838 |
+
"learning_rate": 4.9014208441110215e-06,
|
2839 |
+
"loss": 2.0197,
|
2840 |
+
"step": 401
|
2841 |
+
},
|
2842 |
+
{
|
2843 |
+
"epoch": 0.5323093220338984,
|
2844 |
+
"grad_norm": 3.75,
|
2845 |
+
"learning_rate": 4.879518220274546e-06,
|
2846 |
+
"loss": 2.0886,
|
2847 |
+
"step": 402
|
2848 |
+
},
|
2849 |
+
{
|
2850 |
+
"epoch": 0.5336334745762712,
|
2851 |
+
"grad_norm": 4.5,
|
2852 |
+
"learning_rate": 4.8576179094725855e-06,
|
2853 |
+
"loss": 1.9252,
|
2854 |
+
"step": 403
|
2855 |
+
},
|
2856 |
+
{
|
2857 |
+
"epoch": 0.534957627118644,
|
2858 |
+
"grad_norm": 3.859375,
|
2859 |
+
"learning_rate": 4.835720332151907e-06,
|
2860 |
+
"loss": 2.0754,
|
2861 |
+
"step": 404
|
2862 |
+
},
|
2863 |
+
{
|
2864 |
+
"epoch": 0.536281779661017,
|
2865 |
+
"grad_norm": 3.6875,
|
2866 |
+
"learning_rate": 4.813825908706802e-06,
|
2867 |
+
"loss": 2.1356,
|
2868 |
+
"step": 405
|
2869 |
+
},
|
2870 |
+
{
|
2871 |
+
"epoch": 0.5376059322033898,
|
2872 |
+
"grad_norm": 3.8125,
|
2873 |
+
"learning_rate": 4.791935059471007e-06,
|
2874 |
+
"loss": 2.0131,
|
2875 |
+
"step": 406
|
2876 |
+
},
|
2877 |
+
{
|
2878 |
+
"epoch": 0.5389300847457628,
|
2879 |
+
"grad_norm": 3.734375,
|
2880 |
+
"learning_rate": 4.770048204709648e-06,
|
2881 |
+
"loss": 1.8858,
|
2882 |
+
"step": 407
|
2883 |
+
},
|
2884 |
+
{
|
2885 |
+
"epoch": 0.5402542372881356,
|
2886 |
+
"grad_norm": 6.34375,
|
2887 |
+
"learning_rate": 4.748165764611157e-06,
|
2888 |
+
"loss": 1.9881,
|
2889 |
+
"step": 408
|
2890 |
+
},
|
2891 |
+
{
|
2892 |
+
"epoch": 0.5415783898305084,
|
2893 |
+
"grad_norm": 3.734375,
|
2894 |
+
"learning_rate": 4.726288159279218e-06,
|
2895 |
+
"loss": 2.0027,
|
2896 |
+
"step": 409
|
2897 |
+
},
|
2898 |
+
{
|
2899 |
+
"epoch": 0.5429025423728814,
|
2900 |
+
"grad_norm": 3.9375,
|
2901 |
+
"learning_rate": 4.7044158087246926e-06,
|
2902 |
+
"loss": 2.1449,
|
2903 |
+
"step": 410
|
2904 |
+
},
|
2905 |
+
{
|
2906 |
+
"epoch": 0.5442266949152542,
|
2907 |
+
"grad_norm": 3.609375,
|
2908 |
+
"learning_rate": 4.682549132857562e-06,
|
2909 |
+
"loss": 2.0456,
|
2910 |
+
"step": 411
|
2911 |
+
},
|
2912 |
+
{
|
2913 |
+
"epoch": 0.5455508474576272,
|
2914 |
+
"grad_norm": 3.96875,
|
2915 |
+
"learning_rate": 4.660688551478861e-06,
|
2916 |
+
"loss": 2.2308,
|
2917 |
+
"step": 412
|
2918 |
+
},
|
2919 |
+
{
|
2920 |
+
"epoch": 0.546875,
|
2921 |
+
"grad_norm": 3.875,
|
2922 |
+
"learning_rate": 4.6388344842726266e-06,
|
2923 |
+
"loss": 2.0734,
|
2924 |
+
"step": 413
|
2925 |
+
},
|
2926 |
+
{
|
2927 |
+
"epoch": 0.5481991525423728,
|
2928 |
+
"grad_norm": 3.84375,
|
2929 |
+
"learning_rate": 4.616987350797827e-06,
|
2930 |
+
"loss": 2.0188,
|
2931 |
+
"step": 414
|
2932 |
+
},
|
2933 |
+
{
|
2934 |
+
"epoch": 0.5495233050847458,
|
2935 |
+
"grad_norm": 3.578125,
|
2936 |
+
"learning_rate": 4.595147570480324e-06,
|
2937 |
+
"loss": 2.1403,
|
2938 |
+
"step": 415
|
2939 |
+
},
|
2940 |
+
{
|
2941 |
+
"epoch": 0.5508474576271186,
|
2942 |
+
"grad_norm": 5.75,
|
2943 |
+
"learning_rate": 4.573315562604804e-06,
|
2944 |
+
"loss": 1.8386,
|
2945 |
+
"step": 416
|
2946 |
+
},
|
2947 |
+
{
|
2948 |
+
"epoch": 0.5521716101694916,
|
2949 |
+
"grad_norm": 3.671875,
|
2950 |
+
"learning_rate": 4.551491746306744e-06,
|
2951 |
+
"loss": 2.0066,
|
2952 |
+
"step": 417
|
2953 |
+
},
|
2954 |
+
{
|
2955 |
+
"epoch": 0.5534957627118644,
|
2956 |
+
"grad_norm": 4.0625,
|
2957 |
+
"learning_rate": 4.529676540564351e-06,
|
2958 |
+
"loss": 1.9468,
|
2959 |
+
"step": 418
|
2960 |
+
},
|
2961 |
+
{
|
2962 |
+
"epoch": 0.5548199152542372,
|
2963 |
+
"grad_norm": 3.9375,
|
2964 |
+
"learning_rate": 4.5078703641905275e-06,
|
2965 |
+
"loss": 2.0946,
|
2966 |
+
"step": 419
|
2967 |
+
},
|
2968 |
+
{
|
2969 |
+
"epoch": 0.5561440677966102,
|
2970 |
+
"grad_norm": 3.625,
|
2971 |
+
"learning_rate": 4.486073635824831e-06,
|
2972 |
+
"loss": 2.206,
|
2973 |
+
"step": 420
|
2974 |
+
},
|
2975 |
+
{
|
2976 |
+
"epoch": 0.557468220338983,
|
2977 |
+
"grad_norm": 3.734375,
|
2978 |
+
"learning_rate": 4.464286773925426e-06,
|
2979 |
+
"loss": 1.977,
|
2980 |
+
"step": 421
|
2981 |
+
},
|
2982 |
+
{
|
2983 |
+
"epoch": 0.558792372881356,
|
2984 |
+
"grad_norm": 3.765625,
|
2985 |
+
"learning_rate": 4.442510196761068e-06,
|
2986 |
+
"loss": 1.8473,
|
2987 |
+
"step": 422
|
2988 |
+
},
|
2989 |
+
{
|
2990 |
+
"epoch": 0.5601165254237288,
|
2991 |
+
"grad_norm": 3.65625,
|
2992 |
+
"learning_rate": 4.420744322403058e-06,
|
2993 |
+
"loss": 2.1905,
|
2994 |
+
"step": 423
|
2995 |
+
},
|
2996 |
+
{
|
2997 |
+
"epoch": 0.5614406779661016,
|
2998 |
+
"grad_norm": 3.71875,
|
2999 |
+
"learning_rate": 4.398989568717226e-06,
|
3000 |
+
"loss": 2.0168,
|
3001 |
+
"step": 424
|
3002 |
+
},
|
3003 |
+
{
|
3004 |
+
"epoch": 0.5627648305084746,
|
3005 |
+
"grad_norm": 4.84375,
|
3006 |
+
"learning_rate": 4.377246353355899e-06,
|
3007 |
+
"loss": 1.9603,
|
3008 |
+
"step": 425
|
3009 |
+
},
|
3010 |
+
{
|
3011 |
+
"epoch": 0.5640889830508474,
|
3012 |
+
"grad_norm": 3.703125,
|
3013 |
+
"learning_rate": 4.355515093749897e-06,
|
3014 |
+
"loss": 1.9786,
|
3015 |
+
"step": 426
|
3016 |
+
},
|
3017 |
+
{
|
3018 |
+
"epoch": 0.5654131355932204,
|
3019 |
+
"grad_norm": 3.703125,
|
3020 |
+
"learning_rate": 4.333796207100505e-06,
|
3021 |
+
"loss": 1.9911,
|
3022 |
+
"step": 427
|
3023 |
+
},
|
3024 |
+
{
|
3025 |
+
"epoch": 0.5667372881355932,
|
3026 |
+
"grad_norm": 5.25,
|
3027 |
+
"learning_rate": 4.312090110371473e-06,
|
3028 |
+
"loss": 1.9617,
|
3029 |
+
"step": 428
|
3030 |
+
},
|
3031 |
+
{
|
3032 |
+
"epoch": 0.5680614406779662,
|
3033 |
+
"grad_norm": 3.921875,
|
3034 |
+
"learning_rate": 4.290397220281002e-06,
|
3035 |
+
"loss": 1.9384,
|
3036 |
+
"step": 429
|
3037 |
+
},
|
3038 |
+
{
|
3039 |
+
"epoch": 0.569385593220339,
|
3040 |
+
"grad_norm": 3.84375,
|
3041 |
+
"learning_rate": 4.268717953293755e-06,
|
3042 |
+
"loss": 2.1731,
|
3043 |
+
"step": 430
|
3044 |
+
},
|
3045 |
+
{
|
3046 |
+
"epoch": 0.5707097457627118,
|
3047 |
+
"grad_norm": 3.796875,
|
3048 |
+
"learning_rate": 4.247052725612853e-06,
|
3049 |
+
"loss": 1.8694,
|
3050 |
+
"step": 431
|
3051 |
+
},
|
3052 |
+
{
|
3053 |
+
"epoch": 0.5720338983050848,
|
3054 |
+
"grad_norm": 3.90625,
|
3055 |
+
"learning_rate": 4.22540195317189e-06,
|
3056 |
+
"loss": 1.8741,
|
3057 |
+
"step": 432
|
3058 |
+
},
|
3059 |
+
{
|
3060 |
+
"epoch": 0.5733580508474576,
|
3061 |
+
"grad_norm": 3.6875,
|
3062 |
+
"learning_rate": 4.203766051626939e-06,
|
3063 |
+
"loss": 1.9796,
|
3064 |
+
"step": 433
|
3065 |
+
},
|
3066 |
+
{
|
3067 |
+
"epoch": 0.5746822033898306,
|
3068 |
+
"grad_norm": 4.0,
|
3069 |
+
"learning_rate": 4.182145436348587e-06,
|
3070 |
+
"loss": 1.9154,
|
3071 |
+
"step": 434
|
3072 |
+
},
|
3073 |
+
{
|
3074 |
+
"epoch": 0.5760063559322034,
|
3075 |
+
"grad_norm": 3.6875,
|
3076 |
+
"learning_rate": 4.160540522413947e-06,
|
3077 |
+
"loss": 1.9181,
|
3078 |
+
"step": 435
|
3079 |
+
},
|
3080 |
+
{
|
3081 |
+
"epoch": 0.5773305084745762,
|
3082 |
+
"grad_norm": 3.6875,
|
3083 |
+
"learning_rate": 4.138951724598692e-06,
|
3084 |
+
"loss": 2.0523,
|
3085 |
+
"step": 436
|
3086 |
+
},
|
3087 |
+
{
|
3088 |
+
"epoch": 0.5786546610169492,
|
3089 |
+
"grad_norm": 3.8125,
|
3090 |
+
"learning_rate": 4.1173794573691e-06,
|
3091 |
+
"loss": 1.8367,
|
3092 |
+
"step": 437
|
3093 |
+
},
|
3094 |
+
{
|
3095 |
+
"epoch": 0.579978813559322,
|
3096 |
+
"grad_norm": 3.96875,
|
3097 |
+
"learning_rate": 4.095824134874087e-06,
|
3098 |
+
"loss": 2.0884,
|
3099 |
+
"step": 438
|
3100 |
+
},
|
3101 |
+
{
|
3102 |
+
"epoch": 0.581302966101695,
|
3103 |
+
"grad_norm": 4.03125,
|
3104 |
+
"learning_rate": 4.074286170937265e-06,
|
3105 |
+
"loss": 2.0347,
|
3106 |
+
"step": 439
|
3107 |
+
},
|
3108 |
+
{
|
3109 |
+
"epoch": 0.5826271186440678,
|
3110 |
+
"grad_norm": 4.0625,
|
3111 |
+
"learning_rate": 4.052765979048986e-06,
|
3112 |
+
"loss": 2.0196,
|
3113 |
+
"step": 440
|
3114 |
+
},
|
3115 |
+
{
|
3116 |
+
"epoch": 0.5839512711864406,
|
3117 |
+
"grad_norm": 3.734375,
|
3118 |
+
"learning_rate": 4.031263972358419e-06,
|
3119 |
+
"loss": 1.9662,
|
3120 |
+
"step": 441
|
3121 |
+
},
|
3122 |
+
{
|
3123 |
+
"epoch": 0.5852754237288136,
|
3124 |
+
"grad_norm": 3.6875,
|
3125 |
+
"learning_rate": 4.009780563665601e-06,
|
3126 |
+
"loss": 1.9913,
|
3127 |
+
"step": 442
|
3128 |
+
},
|
3129 |
+
{
|
3130 |
+
"epoch": 0.5865995762711864,
|
3131 |
+
"grad_norm": 3.90625,
|
3132 |
+
"learning_rate": 3.988316165413528e-06,
|
3133 |
+
"loss": 2.0734,
|
3134 |
+
"step": 443
|
3135 |
+
},
|
3136 |
+
{
|
3137 |
+
"epoch": 0.5879237288135594,
|
3138 |
+
"grad_norm": 3.71875,
|
3139 |
+
"learning_rate": 3.966871189680223e-06,
|
3140 |
+
"loss": 1.9153,
|
3141 |
+
"step": 444
|
3142 |
+
},
|
3143 |
+
{
|
3144 |
+
"epoch": 0.5892478813559322,
|
3145 |
+
"grad_norm": 3.96875,
|
3146 |
+
"learning_rate": 3.945446048170839e-06,
|
3147 |
+
"loss": 1.9798,
|
3148 |
+
"step": 445
|
3149 |
+
},
|
3150 |
+
{
|
3151 |
+
"epoch": 0.590572033898305,
|
3152 |
+
"grad_norm": 3.8125,
|
3153 |
+
"learning_rate": 3.924041152209739e-06,
|
3154 |
+
"loss": 1.9039,
|
3155 |
+
"step": 446
|
3156 |
+
},
|
3157 |
+
{
|
3158 |
+
"epoch": 0.591896186440678,
|
3159 |
+
"grad_norm": 4.4375,
|
3160 |
+
"learning_rate": 3.902656912732616e-06,
|
3161 |
+
"loss": 1.9863,
|
3162 |
+
"step": 447
|
3163 |
+
},
|
3164 |
+
{
|
3165 |
+
"epoch": 0.5932203389830508,
|
3166 |
+
"grad_norm": 3.984375,
|
3167 |
+
"learning_rate": 3.881293740278588e-06,
|
3168 |
+
"loss": 1.9465,
|
3169 |
+
"step": 448
|
3170 |
+
},
|
3171 |
+
{
|
3172 |
+
"epoch": 0.5945444915254238,
|
3173 |
+
"grad_norm": 3.71875,
|
3174 |
+
"learning_rate": 3.859952044982329e-06,
|
3175 |
+
"loss": 2.0645,
|
3176 |
+
"step": 449
|
3177 |
+
},
|
3178 |
+
{
|
3179 |
+
"epoch": 0.5958686440677966,
|
3180 |
+
"grad_norm": 3.828125,
|
3181 |
+
"learning_rate": 3.83863223656619e-06,
|
3182 |
+
"loss": 2.0472,
|
3183 |
+
"step": 450
|
3184 |
+
},
|
3185 |
+
{
|
3186 |
+
"epoch": 0.5971927966101694,
|
3187 |
+
"grad_norm": 3.671875,
|
3188 |
+
"learning_rate": 3.8173347243323275e-06,
|
3189 |
+
"loss": 1.8184,
|
3190 |
+
"step": 451
|
3191 |
+
},
|
3192 |
+
{
|
3193 |
+
"epoch": 0.5985169491525424,
|
3194 |
+
"grad_norm": 4.0625,
|
3195 |
+
"learning_rate": 3.7960599171548572e-06,
|
3196 |
+
"loss": 1.9835,
|
3197 |
+
"step": 452
|
3198 |
+
},
|
3199 |
+
{
|
3200 |
+
"epoch": 0.5998411016949152,
|
3201 |
+
"grad_norm": 3.671875,
|
3202 |
+
"learning_rate": 3.774808223471996e-06,
|
3203 |
+
"loss": 1.9712,
|
3204 |
+
"step": 453
|
3205 |
+
},
|
3206 |
+
{
|
3207 |
+
"epoch": 0.6011652542372882,
|
3208 |
+
"grad_norm": 3.703125,
|
3209 |
+
"learning_rate": 3.7535800512782254e-06,
|
3210 |
+
"loss": 2.0324,
|
3211 |
+
"step": 454
|
3212 |
+
},
|
3213 |
+
{
|
3214 |
+
"epoch": 0.602489406779661,
|
3215 |
+
"grad_norm": 3.59375,
|
3216 |
+
"learning_rate": 3.732375808116451e-06,
|
3217 |
+
"loss": 2.1901,
|
3218 |
+
"step": 455
|
3219 |
+
},
|
3220 |
+
{
|
3221 |
+
"epoch": 0.6038135593220338,
|
3222 |
+
"grad_norm": 3.625,
|
3223 |
+
"learning_rate": 3.711195901070188e-06,
|
3224 |
+
"loss": 2.031,
|
3225 |
+
"step": 456
|
3226 |
+
},
|
3227 |
+
{
|
3228 |
+
"epoch": 0.6051377118644068,
|
3229 |
+
"grad_norm": 3.78125,
|
3230 |
+
"learning_rate": 3.690040736755742e-06,
|
3231 |
+
"loss": 2.0682,
|
3232 |
+
"step": 457
|
3233 |
+
},
|
3234 |
+
{
|
3235 |
+
"epoch": 0.6064618644067796,
|
3236 |
+
"grad_norm": 3.78125,
|
3237 |
+
"learning_rate": 3.6689107213144025e-06,
|
3238 |
+
"loss": 2.1191,
|
3239 |
+
"step": 458
|
3240 |
+
},
|
3241 |
+
{
|
3242 |
+
"epoch": 0.6077860169491526,
|
3243 |
+
"grad_norm": 3.65625,
|
3244 |
+
"learning_rate": 3.6478062604046406e-06,
|
3245 |
+
"loss": 1.921,
|
3246 |
+
"step": 459
|
3247 |
+
},
|
3248 |
+
{
|
3249 |
+
"epoch": 0.6091101694915254,
|
3250 |
+
"grad_norm": 6.03125,
|
3251 |
+
"learning_rate": 3.626727759194334e-06,
|
3252 |
+
"loss": 2.0207,
|
3253 |
+
"step": 460
|
3254 |
+
},
|
3255 |
+
{
|
3256 |
+
"epoch": 0.6104343220338984,
|
3257 |
+
"grad_norm": 3.59375,
|
3258 |
+
"learning_rate": 3.6056756223529734e-06,
|
3259 |
+
"loss": 2.1463,
|
3260 |
+
"step": 461
|
3261 |
+
},
|
3262 |
+
{
|
3263 |
+
"epoch": 0.6117584745762712,
|
3264 |
+
"grad_norm": 4.1875,
|
3265 |
+
"learning_rate": 3.5846502540439076e-06,
|
3266 |
+
"loss": 1.9282,
|
3267 |
+
"step": 462
|
3268 |
+
},
|
3269 |
+
{
|
3270 |
+
"epoch": 0.613082627118644,
|
3271 |
+
"grad_norm": 3.53125,
|
3272 |
+
"learning_rate": 3.5636520579165704e-06,
|
3273 |
+
"loss": 2.1905,
|
3274 |
+
"step": 463
|
3275 |
+
},
|
3276 |
+
{
|
3277 |
+
"epoch": 0.614406779661017,
|
3278 |
+
"grad_norm": 3.515625,
|
3279 |
+
"learning_rate": 3.542681437098745e-06,
|
3280 |
+
"loss": 2.1518,
|
3281 |
+
"step": 464
|
3282 |
+
},
|
3283 |
+
{
|
3284 |
+
"epoch": 0.6157309322033898,
|
3285 |
+
"grad_norm": 3.8125,
|
3286 |
+
"learning_rate": 3.5217387941888117e-06,
|
3287 |
+
"loss": 2.0076,
|
3288 |
+
"step": 465
|
3289 |
+
},
|
3290 |
+
{
|
3291 |
+
"epoch": 0.6170550847457628,
|
3292 |
+
"grad_norm": 3.765625,
|
3293 |
+
"learning_rate": 3.5008245312480326e-06,
|
3294 |
+
"loss": 2.1018,
|
3295 |
+
"step": 466
|
3296 |
+
},
|
3297 |
+
{
|
3298 |
+
"epoch": 0.6183792372881356,
|
3299 |
+
"grad_norm": 4.09375,
|
3300 |
+
"learning_rate": 3.479939049792817e-06,
|
3301 |
+
"loss": 1.8781,
|
3302 |
+
"step": 467
|
3303 |
+
},
|
3304 |
+
{
|
3305 |
+
"epoch": 0.6197033898305084,
|
3306 |
+
"grad_norm": 3.78125,
|
3307 |
+
"learning_rate": 3.4590827507870257e-06,
|
3308 |
+
"loss": 2.0801,
|
3309 |
+
"step": 468
|
3310 |
+
},
|
3311 |
+
{
|
3312 |
+
"epoch": 0.6210275423728814,
|
3313 |
+
"grad_norm": 4.375,
|
3314 |
+
"learning_rate": 3.4382560346342707e-06,
|
3315 |
+
"loss": 2.211,
|
3316 |
+
"step": 469
|
3317 |
+
},
|
3318 |
+
{
|
3319 |
+
"epoch": 0.6223516949152542,
|
3320 |
+
"grad_norm": 3.828125,
|
3321 |
+
"learning_rate": 3.4174593011702197e-06,
|
3322 |
+
"loss": 1.8481,
|
3323 |
+
"step": 470
|
3324 |
+
},
|
3325 |
+
{
|
3326 |
+
"epoch": 0.6236758474576272,
|
3327 |
+
"grad_norm": 3.671875,
|
3328 |
+
"learning_rate": 3.396692949654933e-06,
|
3329 |
+
"loss": 2.0414,
|
3330 |
+
"step": 471
|
3331 |
+
},
|
3332 |
+
{
|
3333 |
+
"epoch": 0.625,
|
3334 |
+
"grad_norm": 3.984375,
|
3335 |
+
"learning_rate": 3.3759573787651877e-06,
|
3336 |
+
"loss": 2.094,
|
3337 |
+
"step": 472
|
3338 |
+
},
|
3339 |
+
{
|
3340 |
+
"epoch": 0.6263241525423728,
|
3341 |
+
"grad_norm": 3.734375,
|
3342 |
+
"learning_rate": 3.3552529865868323e-06,
|
3343 |
+
"loss": 2.0496,
|
3344 |
+
"step": 473
|
3345 |
+
},
|
3346 |
+
{
|
3347 |
+
"epoch": 0.6276483050847458,
|
3348 |
+
"grad_norm": 3.84375,
|
3349 |
+
"learning_rate": 3.3345801706071325e-06,
|
3350 |
+
"loss": 2.113,
|
3351 |
+
"step": 474
|
3352 |
+
},
|
3353 |
+
{
|
3354 |
+
"epoch": 0.6289724576271186,
|
3355 |
+
"grad_norm": 4.03125,
|
3356 |
+
"learning_rate": 3.3139393277071554e-06,
|
3357 |
+
"loss": 1.8577,
|
3358 |
+
"step": 475
|
3359 |
+
},
|
3360 |
+
{
|
3361 |
+
"epoch": 0.6302966101694916,
|
3362 |
+
"grad_norm": 5.21875,
|
3363 |
+
"learning_rate": 3.2933308541541365e-06,
|
3364 |
+
"loss": 2.059,
|
3365 |
+
"step": 476
|
3366 |
+
},
|
3367 |
+
{
|
3368 |
+
"epoch": 0.6316207627118644,
|
3369 |
+
"grad_norm": 3.5625,
|
3370 |
+
"learning_rate": 3.2727551455938832e-06,
|
3371 |
+
"loss": 2.1471,
|
3372 |
+
"step": 477
|
3373 |
+
},
|
3374 |
+
{
|
3375 |
+
"epoch": 0.6329449152542372,
|
3376 |
+
"grad_norm": 3.953125,
|
3377 |
+
"learning_rate": 3.252212597043167e-06,
|
3378 |
+
"loss": 2.0538,
|
3379 |
+
"step": 478
|
3380 |
+
},
|
3381 |
+
{
|
3382 |
+
"epoch": 0.6342690677966102,
|
3383 |
+
"grad_norm": 3.8125,
|
3384 |
+
"learning_rate": 3.2317036028821523e-06,
|
3385 |
+
"loss": 1.9275,
|
3386 |
+
"step": 479
|
3387 |
+
},
|
3388 |
+
{
|
3389 |
+
"epoch": 0.635593220338983,
|
3390 |
+
"grad_norm": 4.125,
|
3391 |
+
"learning_rate": 3.2112285568468166e-06,
|
3392 |
+
"loss": 1.9979,
|
3393 |
+
"step": 480
|
3394 |
+
},
|
3395 |
+
{
|
3396 |
+
"epoch": 0.636917372881356,
|
3397 |
+
"grad_norm": 3.796875,
|
3398 |
+
"learning_rate": 3.190787852021396e-06,
|
3399 |
+
"loss": 2.1286,
|
3400 |
+
"step": 481
|
3401 |
+
},
|
3402 |
+
{
|
3403 |
+
"epoch": 0.6382415254237288,
|
3404 |
+
"grad_norm": 3.78125,
|
3405 |
+
"learning_rate": 3.1703818808308327e-06,
|
3406 |
+
"loss": 2.007,
|
3407 |
+
"step": 482
|
3408 |
+
},
|
3409 |
+
{
|
3410 |
+
"epoch": 0.6395656779661016,
|
3411 |
+
"grad_norm": 3.859375,
|
3412 |
+
"learning_rate": 3.1500110350332492e-06,
|
3413 |
+
"loss": 1.9457,
|
3414 |
+
"step": 483
|
3415 |
+
},
|
3416 |
+
{
|
3417 |
+
"epoch": 0.6408898305084746,
|
3418 |
+
"grad_norm": 4.09375,
|
3419 |
+
"learning_rate": 3.1296757057124243e-06,
|
3420 |
+
"loss": 1.9245,
|
3421 |
+
"step": 484
|
3422 |
+
},
|
3423 |
+
{
|
3424 |
+
"epoch": 0.6422139830508474,
|
3425 |
+
"grad_norm": 4.125,
|
3426 |
+
"learning_rate": 3.1093762832702775e-06,
|
3427 |
+
"loss": 2.0545,
|
3428 |
+
"step": 485
|
3429 |
+
},
|
3430 |
+
{
|
3431 |
+
"epoch": 0.6435381355932204,
|
3432 |
+
"grad_norm": 3.859375,
|
3433 |
+
"learning_rate": 3.08911315741939e-06,
|
3434 |
+
"loss": 2.0104,
|
3435 |
+
"step": 486
|
3436 |
+
},
|
3437 |
+
{
|
3438 |
+
"epoch": 0.6448622881355932,
|
3439 |
+
"grad_norm": 3.515625,
|
3440 |
+
"learning_rate": 3.0688867171755043e-06,
|
3441 |
+
"loss": 2.0609,
|
3442 |
+
"step": 487
|
3443 |
+
},
|
3444 |
+
{
|
3445 |
+
"epoch": 0.6461864406779662,
|
3446 |
+
"grad_norm": 3.609375,
|
3447 |
+
"learning_rate": 3.048697350850073e-06,
|
3448 |
+
"loss": 2.0671,
|
3449 |
+
"step": 488
|
3450 |
+
},
|
3451 |
+
{
|
3452 |
+
"epoch": 0.647510593220339,
|
3453 |
+
"grad_norm": 3.96875,
|
3454 |
+
"learning_rate": 3.0285454460427855e-06,
|
3455 |
+
"loss": 1.9852,
|
3456 |
+
"step": 489
|
3457 |
+
},
|
3458 |
+
{
|
3459 |
+
"epoch": 0.6488347457627118,
|
3460 |
+
"grad_norm": 3.859375,
|
3461 |
+
"learning_rate": 3.0084313896341504e-06,
|
3462 |
+
"loss": 1.9553,
|
3463 |
+
"step": 490
|
3464 |
+
},
|
3465 |
+
{
|
3466 |
+
"epoch": 0.6501588983050848,
|
3467 |
+
"grad_norm": 3.625,
|
3468 |
+
"learning_rate": 2.988355567778043e-06,
|
3469 |
+
"loss": 2.1243,
|
3470 |
+
"step": 491
|
3471 |
+
},
|
3472 |
+
{
|
3473 |
+
"epoch": 0.6514830508474576,
|
3474 |
+
"grad_norm": 4.09375,
|
3475 |
+
"learning_rate": 2.9683183658943106e-06,
|
3476 |
+
"loss": 2.137,
|
3477 |
+
"step": 492
|
3478 |
+
},
|
3479 |
+
{
|
3480 |
+
"epoch": 0.6528072033898306,
|
3481 |
+
"grad_norm": 3.9375,
|
3482 |
+
"learning_rate": 2.9483201686613626e-06,
|
3483 |
+
"loss": 1.9655,
|
3484 |
+
"step": 493
|
3485 |
+
},
|
3486 |
+
{
|
3487 |
+
"epoch": 0.6541313559322034,
|
3488 |
+
"grad_norm": 4.03125,
|
3489 |
+
"learning_rate": 2.9283613600087933e-06,
|
3490 |
+
"loss": 2.0074,
|
3491 |
+
"step": 494
|
3492 |
+
},
|
3493 |
+
{
|
3494 |
+
"epoch": 0.6554555084745762,
|
3495 |
+
"grad_norm": 3.84375,
|
3496 |
+
"learning_rate": 2.9084423231099985e-06,
|
3497 |
+
"loss": 1.8278,
|
3498 |
+
"step": 495
|
3499 |
+
},
|
3500 |
+
{
|
3501 |
+
"epoch": 0.6567796610169492,
|
3502 |
+
"grad_norm": 3.765625,
|
3503 |
+
"learning_rate": 2.8885634403748397e-06,
|
3504 |
+
"loss": 2.0682,
|
3505 |
+
"step": 496
|
3506 |
+
},
|
3507 |
+
{
|
3508 |
+
"epoch": 0.658103813559322,
|
3509 |
+
"grad_norm": 3.796875,
|
3510 |
+
"learning_rate": 2.8687250934422774e-06,
|
3511 |
+
"loss": 2.0537,
|
3512 |
+
"step": 497
|
3513 |
+
},
|
3514 |
+
{
|
3515 |
+
"epoch": 0.659427966101695,
|
3516 |
+
"grad_norm": 3.828125,
|
3517 |
+
"learning_rate": 2.8489276631730633e-06,
|
3518 |
+
"loss": 1.848,
|
3519 |
+
"step": 498
|
3520 |
+
},
|
3521 |
+
{
|
3522 |
+
"epoch": 0.6607521186440678,
|
3523 |
+
"grad_norm": 3.765625,
|
3524 |
+
"learning_rate": 2.8291715296424282e-06,
|
3525 |
+
"loss": 1.9693,
|
3526 |
+
"step": 499
|
3527 |
+
},
|
3528 |
+
{
|
3529 |
+
"epoch": 0.6620762711864406,
|
3530 |
+
"grad_norm": 3.59375,
|
3531 |
+
"learning_rate": 2.809457072132766e-06,
|
3532 |
+
"loss": 1.8889,
|
3533 |
+
"step": 500
|
3534 |
+
}
|
3535 |
+
],
|
3536 |
+
"logging_steps": 1.0,
|
3537 |
+
"max_steps": 755,
|
3538 |
+
"num_input_tokens_seen": 0,
|
3539 |
+
"num_train_epochs": 1,
|
3540 |
+
"save_steps": 500,
|
3541 |
+
"total_flos": 8.160964319714918e+17,
|
3542 |
+
"train_batch_size": 1,
|
3543 |
+
"trial_name": null,
|
3544 |
+
"trial_params": null
|
3545 |
+
}
|
checkpoint-500/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e4a38fdf60b76588af096750bbe9aaedc3af8741d50294007e445669596c4965
|
3 |
+
size 4795
|
runs/Nov04_00-07-37_autodl-container-4be511b1ae-46466da0/events.out.tfevents.1730650101.autodl-container-4be511b1ae-46466da0.1254.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9cbe92b0608194dcfc686d3060d8d44817abdb0db75b77f92e6265f6090dc95c
|
3 |
+
size 6132
|
runs/Nov04_00-10-37_autodl-container-4be511b1ae-46466da0/events.out.tfevents.1730650280.autodl-container-4be511b1ae-46466da0.1417.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:65c3815b016f07b0a159e1e69ba89689f2b131302f99c65551c47538d07ae952
|
3 |
+
size 166125
|
runs/Oct22_22-32-37_autodl-container-4be511b1ae-46466da0/events.out.tfevents.1729607600.autodl-container-4be511b1ae-46466da0.1125.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8f4ae517793a3a798c168af0c271eece4ae08242e800ca790773c7b44d43c318
|
3 |
+
size 5587
|
runs/Oct22_23-34-53_autodl-container-4be511b1ae-46466da0/events.out.tfevents.1729611338.autodl-container-4be511b1ae-46466da0.845.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dbe983cfb6a4cd519e08c76fcde0c25ac6f4a9e123d77186333b45cd3421d5b2
|
3 |
+
size 6480
|
runs/Oct24_22-55-18_autodl-container-4be511b1ae-46466da0/events.out.tfevents.1729781767.autodl-container-4be511b1ae-46466da0.884.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:964818c5a6a0f9ad9ffdc163513f1aecf5e93e8085e18cdef57af9d773cb5fd7
|
3 |
+
size 33058
|
runs/Oct25_00-15-00_autodl-container-4be511b1ae-46466da0/events.out.tfevents.1729786546.autodl-container-4be511b1ae-46466da0.861.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9fe28e2030fb22a514c8f4ee9189302480a9425839adf63579efc3f5c4ec5c2e
|
3 |
+
size 6753
|
special_tokens_map.json
ADDED
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<s>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": {
|
10 |
+
"content": "</s>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": "</s>",
|
17 |
+
"unk_token": {
|
18 |
+
"content": "<unk>",
|
19 |
+
"lstrip": false,
|
20 |
+
"normalized": false,
|
21 |
+
"rstrip": false,
|
22 |
+
"single_word": false
|
23 |
+
}
|
24 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:86840d604f9e18ebbdc35aa937cfc2486fe774534ceea0fd3f667a72bc7584b2
|
3 |
+
size 925420
|
tokenizer_config.json
ADDED
@@ -0,0 +1,42 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": true,
|
3 |
+
"add_eos_token": false,
|
4 |
+
"added_tokens_decoder": {
|
5 |
+
"0": {
|
6 |
+
"content": "<unk>",
|
7 |
+
"lstrip": false,
|
8 |
+
"normalized": false,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false,
|
11 |
+
"special": true
|
12 |
+
},
|
13 |
+
"1": {
|
14 |
+
"content": "<s>",
|
15 |
+
"lstrip": false,
|
16 |
+
"normalized": false,
|
17 |
+
"rstrip": false,
|
18 |
+
"single_word": false,
|
19 |
+
"special": true
|
20 |
+
},
|
21 |
+
"2": {
|
22 |
+
"content": "</s>",
|
23 |
+
"lstrip": false,
|
24 |
+
"normalized": false,
|
25 |
+
"rstrip": false,
|
26 |
+
"single_word": false,
|
27 |
+
"special": true
|
28 |
+
}
|
29 |
+
},
|
30 |
+
"additional_special_tokens": [],
|
31 |
+
"bos_token": "<s>",
|
32 |
+
"clean_up_tokenization_spaces": false,
|
33 |
+
"eos_token": "</s>",
|
34 |
+
"legacy": true,
|
35 |
+
"model_max_length": 1000000000000000019884624838656,
|
36 |
+
"pad_token": "</s>",
|
37 |
+
"sp_model_kwargs": {},
|
38 |
+
"spaces_between_special_tokens": false,
|
39 |
+
"tokenizer_class": "LlamaTokenizer",
|
40 |
+
"unk_token": "<unk>",
|
41 |
+
"use_default_system_prompt": false
|
42 |
+
}
|
trainer_state.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e4a38fdf60b76588af096750bbe9aaedc3af8741d50294007e445669596c4965
|
3 |
+
size 4795
|