Upload 50 files
Browse files- adapter_config.json +28 -0
- adapter_model.bin +3 -0
- checkpoint-120/README.md +220 -0
- checkpoint-120/adapter_config.json +28 -0
- checkpoint-120/adapter_model.safetensors +3 -0
- checkpoint-120/optimizer.pt +3 -0
- checkpoint-120/rng_state.pth +3 -0
- checkpoint-120/scheduler.pt +3 -0
- checkpoint-120/trainer_state.json +739 -0
- checkpoint-120/training_args.bin +3 -0
- checkpoint-190/README.md +220 -0
- checkpoint-190/adapter_config.json +28 -0
- checkpoint-190/adapter_model.safetensors +3 -0
- checkpoint-190/optimizer.pt +3 -0
- checkpoint-190/rng_state.pth +3 -0
- checkpoint-190/scheduler.pt +3 -0
- checkpoint-190/trainer_state.json +1159 -0
- checkpoint-190/training_args.bin +3 -0
- checkpoint-200/README.md +220 -0
- checkpoint-200/adapter_config.json +28 -0
- checkpoint-200/adapter_model.safetensors +3 -0
- checkpoint-200/optimizer.pt +3 -0
- checkpoint-200/rng_state.pth +3 -0
- checkpoint-200/scheduler.pt +3 -0
- checkpoint-200/trainer_state.json +1219 -0
- checkpoint-200/training_args.bin +3 -0
- checkpoint-40/README.md +220 -0
- checkpoint-40/adapter_config.json +28 -0
- checkpoint-40/adapter_model.safetensors +3 -0
- checkpoint-40/optimizer.pt +3 -0
- checkpoint-40/rng_state.pth +3 -0
- checkpoint-40/scheduler.pt +3 -0
- checkpoint-40/trainer_state.json +259 -0
- checkpoint-40/training_args.bin +3 -0
- checkpoint-80/README.md +220 -0
- checkpoint-80/adapter_config.json +28 -0
- checkpoint-80/adapter_model.safetensors +3 -0
- checkpoint-80/optimizer.pt +3 -0
- checkpoint-80/rng_state.pth +3 -0
- checkpoint-80/scheduler.pt +3 -0
- checkpoint-80/trainer_state.json +499 -0
- checkpoint-80/training_args.bin +3 -0
- checkpoint-90/README.md +220 -0
- checkpoint-90/adapter_config.json +28 -0
- checkpoint-90/adapter_model.safetensors +3 -0
- checkpoint-90/optimizer.pt +3 -0
- checkpoint-90/rng_state.pth +3 -0
- checkpoint-90/scheduler.pt +3 -0
- checkpoint-90/trainer_state.json +559 -0
- checkpoint-90/training_args.bin +3 -0
adapter_config.json
ADDED
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "unsloth/llama-2-7b",
|
5 |
+
"bias": "none",
|
6 |
+
"fan_in_fan_out": false,
|
7 |
+
"inference_mode": true,
|
8 |
+
"init_lora_weights": true,
|
9 |
+
"layers_pattern": null,
|
10 |
+
"layers_to_transform": null,
|
11 |
+
"lora_alpha": 32,
|
12 |
+
"lora_dropout": 0,
|
13 |
+
"modules_to_save": null,
|
14 |
+
"peft_type": "LORA",
|
15 |
+
"r": 16,
|
16 |
+
"rank_pattern": {},
|
17 |
+
"revision": null,
|
18 |
+
"target_modules": [
|
19 |
+
"up_proj",
|
20 |
+
"o_proj",
|
21 |
+
"gate_proj",
|
22 |
+
"down_proj",
|
23 |
+
"q_proj",
|
24 |
+
"v_proj",
|
25 |
+
"k_proj"
|
26 |
+
],
|
27 |
+
"task_type": "CAUSAL_LM"
|
28 |
+
}
|
adapter_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f79513adcdbec489bcae5922568302801faa2dd8cb229d4f8a34888c07a6faab
|
3 |
+
size 160069834
|
checkpoint-120/README.md
ADDED
@@ -0,0 +1,220 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: peft
|
3 |
+
base_model: unsloth/llama-2-7b
|
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 |
+
|
201 |
+
|
202 |
+
## Training procedure
|
203 |
+
|
204 |
+
|
205 |
+
The following `bitsandbytes` quantization config was used during training:
|
206 |
+
- quant_method: bitsandbytes
|
207 |
+
- load_in_8bit: False
|
208 |
+
- load_in_4bit: True
|
209 |
+
- llm_int8_threshold: 6.0
|
210 |
+
- llm_int8_skip_modules: None
|
211 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
212 |
+
- llm_int8_has_fp16_weight: False
|
213 |
+
- bnb_4bit_quant_type: nf4
|
214 |
+
- bnb_4bit_use_double_quant: True
|
215 |
+
- bnb_4bit_compute_dtype: bfloat16
|
216 |
+
|
217 |
+
### Framework versions
|
218 |
+
|
219 |
+
|
220 |
+
- PEFT 0.6.2
|
checkpoint-120/adapter_config.json
ADDED
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "unsloth/llama-2-7b",
|
5 |
+
"bias": "none",
|
6 |
+
"fan_in_fan_out": false,
|
7 |
+
"inference_mode": true,
|
8 |
+
"init_lora_weights": true,
|
9 |
+
"layers_pattern": null,
|
10 |
+
"layers_to_transform": null,
|
11 |
+
"lora_alpha": 32,
|
12 |
+
"lora_dropout": 0,
|
13 |
+
"modules_to_save": null,
|
14 |
+
"peft_type": "LORA",
|
15 |
+
"r": 16,
|
16 |
+
"rank_pattern": {},
|
17 |
+
"revision": null,
|
18 |
+
"target_modules": [
|
19 |
+
"o_proj",
|
20 |
+
"up_proj",
|
21 |
+
"down_proj",
|
22 |
+
"q_proj",
|
23 |
+
"k_proj",
|
24 |
+
"v_proj",
|
25 |
+
"gate_proj"
|
26 |
+
],
|
27 |
+
"task_type": "CAUSAL_LM"
|
28 |
+
}
|
checkpoint-120/adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b794f816309a7ae9395e4659e941c80ca8a91b6e0b09e526a868ba9f3142d890
|
3 |
+
size 159967880
|
checkpoint-120/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2305266e1e6c759d565002fd6a4fc8d6a8c2c7f49e3864d55ce9feb771839611
|
3 |
+
size 80630612
|
checkpoint-120/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:203e9bfabd925cb4ec7129d24877156fcee87215187c35a867e358e56a9425a4
|
3 |
+
size 14244
|
checkpoint-120/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:65d56887428ca405cc745bbbbd7f519276e95c51982e722119e5f11f0b51d490
|
3 |
+
size 1064
|
checkpoint-120/trainer_state.json
ADDED
@@ -0,0 +1,739 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.28776978417266186,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 120,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.0,
|
13 |
+
"learning_rate": 0.00013,
|
14 |
+
"loss": 1.1241,
|
15 |
+
"step": 1
|
16 |
+
},
|
17 |
+
{
|
18 |
+
"epoch": 0.0,
|
19 |
+
"learning_rate": 0.00026,
|
20 |
+
"loss": 1.0107,
|
21 |
+
"step": 2
|
22 |
+
},
|
23 |
+
{
|
24 |
+
"epoch": 0.01,
|
25 |
+
"learning_rate": 0.00039,
|
26 |
+
"loss": 1.1086,
|
27 |
+
"step": 3
|
28 |
+
},
|
29 |
+
{
|
30 |
+
"epoch": 0.01,
|
31 |
+
"learning_rate": 0.00052,
|
32 |
+
"loss": 1.0044,
|
33 |
+
"step": 4
|
34 |
+
},
|
35 |
+
{
|
36 |
+
"epoch": 0.01,
|
37 |
+
"learning_rate": 0.00065,
|
38 |
+
"loss": 1.0496,
|
39 |
+
"step": 5
|
40 |
+
},
|
41 |
+
{
|
42 |
+
"epoch": 0.01,
|
43 |
+
"learning_rate": 0.0005933661039639299,
|
44 |
+
"loss": 1.0199,
|
45 |
+
"step": 6
|
46 |
+
},
|
47 |
+
{
|
48 |
+
"epoch": 0.02,
|
49 |
+
"learning_rate": 0.0005493502655735357,
|
50 |
+
"loss": 1.0198,
|
51 |
+
"step": 7
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.02,
|
55 |
+
"learning_rate": 0.0005138701197773616,
|
56 |
+
"loss": 0.969,
|
57 |
+
"step": 8
|
58 |
+
},
|
59 |
+
{
|
60 |
+
"epoch": 0.02,
|
61 |
+
"learning_rate": 0.0004844813951249544,
|
62 |
+
"loss": 0.9383,
|
63 |
+
"step": 9
|
64 |
+
},
|
65 |
+
{
|
66 |
+
"epoch": 0.02,
|
67 |
+
"learning_rate": 0.0004596194077712558,
|
68 |
+
"loss": 0.8776,
|
69 |
+
"step": 10
|
70 |
+
},
|
71 |
+
{
|
72 |
+
"epoch": 0.03,
|
73 |
+
"learning_rate": 0.0004382299106011073,
|
74 |
+
"loss": 1.0173,
|
75 |
+
"step": 11
|
76 |
+
},
|
77 |
+
{
|
78 |
+
"epoch": 0.03,
|
79 |
+
"learning_rate": 0.0004195731958391368,
|
80 |
+
"loss": 1.1173,
|
81 |
+
"step": 12
|
82 |
+
},
|
83 |
+
{
|
84 |
+
"epoch": 0.03,
|
85 |
+
"learning_rate": 0.0004031128874149274,
|
86 |
+
"loss": 1.0876,
|
87 |
+
"step": 13
|
88 |
+
},
|
89 |
+
{
|
90 |
+
"epoch": 0.03,
|
91 |
+
"learning_rate": 0.0003884492980336779,
|
92 |
+
"loss": 1.0524,
|
93 |
+
"step": 14
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 0.04,
|
97 |
+
"learning_rate": 0.0003752776749732568,
|
98 |
+
"loss": 0.8953,
|
99 |
+
"step": 15
|
100 |
+
},
|
101 |
+
{
|
102 |
+
"epoch": 0.04,
|
103 |
+
"learning_rate": 0.00036336104634371584,
|
104 |
+
"loss": 1.1335,
|
105 |
+
"step": 16
|
106 |
+
},
|
107 |
+
{
|
108 |
+
"epoch": 0.04,
|
109 |
+
"learning_rate": 0.00035251199395531623,
|
110 |
+
"loss": 0.9837,
|
111 |
+
"step": 17
|
112 |
+
},
|
113 |
+
{
|
114 |
+
"epoch": 0.04,
|
115 |
+
"learning_rate": 0.00034258007985157445,
|
116 |
+
"loss": 0.9707,
|
117 |
+
"step": 18
|
118 |
+
},
|
119 |
+
{
|
120 |
+
"epoch": 0.05,
|
121 |
+
"learning_rate": 0.0003334429644276751,
|
122 |
+
"loss": 0.9149,
|
123 |
+
"step": 19
|
124 |
+
},
|
125 |
+
{
|
126 |
+
"epoch": 0.05,
|
127 |
+
"learning_rate": 0.000325,
|
128 |
+
"loss": 1.0043,
|
129 |
+
"step": 20
|
130 |
+
},
|
131 |
+
{
|
132 |
+
"epoch": 0.05,
|
133 |
+
"learning_rate": 0.00031716752370827323,
|
134 |
+
"loss": 1.001,
|
135 |
+
"step": 21
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 0.05,
|
139 |
+
"learning_rate": 0.00030987534150481746,
|
140 |
+
"loss": 1.0395,
|
141 |
+
"step": 22
|
142 |
+
},
|
143 |
+
{
|
144 |
+
"epoch": 0.06,
|
145 |
+
"learning_rate": 0.000303064062678102,
|
146 |
+
"loss": 0.8718,
|
147 |
+
"step": 23
|
148 |
+
},
|
149 |
+
{
|
150 |
+
"epoch": 0.06,
|
151 |
+
"learning_rate": 0.00029668305198196496,
|
152 |
+
"loss": 1.1114,
|
153 |
+
"step": 24
|
154 |
+
},
|
155 |
+
{
|
156 |
+
"epoch": 0.06,
|
157 |
+
"learning_rate": 0.00029068883707497264,
|
158 |
+
"loss": 0.7765,
|
159 |
+
"step": 25
|
160 |
+
},
|
161 |
+
{
|
162 |
+
"epoch": 0.06,
|
163 |
+
"learning_rate": 0.0002850438562747845,
|
164 |
+
"loss": 0.9522,
|
165 |
+
"step": 26
|
166 |
+
},
|
167 |
+
{
|
168 |
+
"epoch": 0.06,
|
169 |
+
"learning_rate": 0.00027971546389275785,
|
170 |
+
"loss": 0.9588,
|
171 |
+
"step": 27
|
172 |
+
},
|
173 |
+
{
|
174 |
+
"epoch": 0.07,
|
175 |
+
"learning_rate": 0.00027467513278676785,
|
176 |
+
"loss": 1.0313,
|
177 |
+
"step": 28
|
178 |
+
},
|
179 |
+
{
|
180 |
+
"epoch": 0.07,
|
181 |
+
"learning_rate": 0.0002698978095246549,
|
182 |
+
"loss": 0.9338,
|
183 |
+
"step": 29
|
184 |
+
},
|
185 |
+
{
|
186 |
+
"epoch": 0.07,
|
187 |
+
"learning_rate": 0.000265361388801511,
|
188 |
+
"loss": 0.892,
|
189 |
+
"step": 30
|
190 |
+
},
|
191 |
+
{
|
192 |
+
"epoch": 0.07,
|
193 |
+
"learning_rate": 0.00026104628189331215,
|
194 |
+
"loss": 0.893,
|
195 |
+
"step": 31
|
196 |
+
},
|
197 |
+
{
|
198 |
+
"epoch": 0.08,
|
199 |
+
"learning_rate": 0.0002569350598886808,
|
200 |
+
"loss": 0.8983,
|
201 |
+
"step": 32
|
202 |
+
},
|
203 |
+
{
|
204 |
+
"epoch": 0.08,
|
205 |
+
"learning_rate": 0.00025301215685249496,
|
206 |
+
"loss": 0.9277,
|
207 |
+
"step": 33
|
208 |
+
},
|
209 |
+
{
|
210 |
+
"epoch": 0.08,
|
211 |
+
"learning_rate": 0.00024926362137539537,
|
212 |
+
"loss": 0.8962,
|
213 |
+
"step": 34
|
214 |
+
},
|
215 |
+
{
|
216 |
+
"epoch": 0.08,
|
217 |
+
"learning_rate": 0.00024567690745599767,
|
218 |
+
"loss": 0.9124,
|
219 |
+
"step": 35
|
220 |
+
},
|
221 |
+
{
|
222 |
+
"epoch": 0.09,
|
223 |
+
"learning_rate": 0.0002422406975624772,
|
224 |
+
"loss": 0.9535,
|
225 |
+
"step": 36
|
226 |
+
},
|
227 |
+
{
|
228 |
+
"epoch": 0.09,
|
229 |
+
"learning_rate": 0.00023894475218048754,
|
230 |
+
"loss": 0.9019,
|
231 |
+
"step": 37
|
232 |
+
},
|
233 |
+
{
|
234 |
+
"epoch": 0.09,
|
235 |
+
"learning_rate": 0.0002357797812857538,
|
236 |
+
"loss": 1.024,
|
237 |
+
"step": 38
|
238 |
+
},
|
239 |
+
{
|
240 |
+
"epoch": 0.09,
|
241 |
+
"learning_rate": 0.00023273733406281566,
|
242 |
+
"loss": 0.8549,
|
243 |
+
"step": 39
|
244 |
+
},
|
245 |
+
{
|
246 |
+
"epoch": 0.1,
|
247 |
+
"learning_rate": 0.0002298097038856279,
|
248 |
+
"loss": 1.0489,
|
249 |
+
"step": 40
|
250 |
+
},
|
251 |
+
{
|
252 |
+
"epoch": 0.1,
|
253 |
+
"learning_rate": 0.00022698984612511293,
|
254 |
+
"loss": 0.751,
|
255 |
+
"step": 41
|
256 |
+
},
|
257 |
+
{
|
258 |
+
"epoch": 0.1,
|
259 |
+
"learning_rate": 0.00022427130678626507,
|
260 |
+
"loss": 0.834,
|
261 |
+
"step": 42
|
262 |
+
},
|
263 |
+
{
|
264 |
+
"epoch": 0.1,
|
265 |
+
"learning_rate": 0.00022164816032790388,
|
266 |
+
"loss": 0.889,
|
267 |
+
"step": 43
|
268 |
+
},
|
269 |
+
{
|
270 |
+
"epoch": 0.11,
|
271 |
+
"learning_rate": 0.00021911495530055366,
|
272 |
+
"loss": 1.0103,
|
273 |
+
"step": 44
|
274 |
+
},
|
275 |
+
{
|
276 |
+
"epoch": 0.11,
|
277 |
+
"learning_rate": 0.00021666666666666666,
|
278 |
+
"loss": 0.8766,
|
279 |
+
"step": 45
|
280 |
+
},
|
281 |
+
{
|
282 |
+
"epoch": 0.11,
|
283 |
+
"learning_rate": 0.0002142986538536308,
|
284 |
+
"loss": 0.8181,
|
285 |
+
"step": 46
|
286 |
+
},
|
287 |
+
{
|
288 |
+
"epoch": 0.11,
|
289 |
+
"learning_rate": 0.0002120066237423687,
|
290 |
+
"loss": 0.8754,
|
291 |
+
"step": 47
|
292 |
+
},
|
293 |
+
{
|
294 |
+
"epoch": 0.12,
|
295 |
+
"learning_rate": 0.0002097865979195684,
|
296 |
+
"loss": 0.9038,
|
297 |
+
"step": 48
|
298 |
+
},
|
299 |
+
{
|
300 |
+
"epoch": 0.12,
|
301 |
+
"learning_rate": 0.00020763488362498048,
|
302 |
+
"loss": 0.8646,
|
303 |
+
"step": 49
|
304 |
+
},
|
305 |
+
{
|
306 |
+
"epoch": 0.12,
|
307 |
+
"learning_rate": 0.00020554804791094464,
|
308 |
+
"loss": 0.8836,
|
309 |
+
"step": 50
|
310 |
+
},
|
311 |
+
{
|
312 |
+
"epoch": 0.12,
|
313 |
+
"learning_rate": 0.0002035228946026736,
|
314 |
+
"loss": 0.9962,
|
315 |
+
"step": 51
|
316 |
+
},
|
317 |
+
{
|
318 |
+
"epoch": 0.12,
|
319 |
+
"learning_rate": 0.0002015564437074637,
|
320 |
+
"loss": 0.8835,
|
321 |
+
"step": 52
|
322 |
+
},
|
323 |
+
{
|
324 |
+
"epoch": 0.13,
|
325 |
+
"learning_rate": 0.00019964591297103414,
|
326 |
+
"loss": 0.9196,
|
327 |
+
"step": 53
|
328 |
+
},
|
329 |
+
{
|
330 |
+
"epoch": 0.13,
|
331 |
+
"learning_rate": 0.00019778870132130996,
|
332 |
+
"loss": 0.8995,
|
333 |
+
"step": 54
|
334 |
+
},
|
335 |
+
{
|
336 |
+
"epoch": 0.13,
|
337 |
+
"learning_rate": 0.00019598237397554634,
|
338 |
+
"loss": 1.0178,
|
339 |
+
"step": 55
|
340 |
+
},
|
341 |
+
{
|
342 |
+
"epoch": 0.13,
|
343 |
+
"learning_rate": 0.00019422464901683895,
|
344 |
+
"loss": 0.9395,
|
345 |
+
"step": 56
|
346 |
+
},
|
347 |
+
{
|
348 |
+
"epoch": 0.14,
|
349 |
+
"learning_rate": 0.00019251338527170498,
|
350 |
+
"loss": 0.9882,
|
351 |
+
"step": 57
|
352 |
+
},
|
353 |
+
{
|
354 |
+
"epoch": 0.14,
|
355 |
+
"learning_rate": 0.00019084657134227863,
|
356 |
+
"loss": 0.9274,
|
357 |
+
"step": 58
|
358 |
+
},
|
359 |
+
{
|
360 |
+
"epoch": 0.14,
|
361 |
+
"learning_rate": 0.00018922231566536414,
|
362 |
+
"loss": 0.9517,
|
363 |
+
"step": 59
|
364 |
+
},
|
365 |
+
{
|
366 |
+
"epoch": 0.14,
|
367 |
+
"learning_rate": 0.0001876388374866284,
|
368 |
+
"loss": 0.865,
|
369 |
+
"step": 60
|
370 |
+
},
|
371 |
+
{
|
372 |
+
"epoch": 0.15,
|
373 |
+
"learning_rate": 0.00018609445865200715,
|
374 |
+
"loss": 0.9314,
|
375 |
+
"step": 61
|
376 |
+
},
|
377 |
+
{
|
378 |
+
"epoch": 0.15,
|
379 |
+
"learning_rate": 0.00018458759613029606,
|
380 |
+
"loss": 0.9224,
|
381 |
+
"step": 62
|
382 |
+
},
|
383 |
+
{
|
384 |
+
"epoch": 0.15,
|
385 |
+
"learning_rate": 0.00018311675519117857,
|
386 |
+
"loss": 0.788,
|
387 |
+
"step": 63
|
388 |
+
},
|
389 |
+
{
|
390 |
+
"epoch": 0.15,
|
391 |
+
"learning_rate": 0.00018168052317185792,
|
392 |
+
"loss": 0.9739,
|
393 |
+
"step": 64
|
394 |
+
},
|
395 |
+
{
|
396 |
+
"epoch": 0.16,
|
397 |
+
"learning_rate": 0.00018027756377319947,
|
398 |
+
"loss": 0.9419,
|
399 |
+
"step": 65
|
400 |
+
},
|
401 |
+
{
|
402 |
+
"epoch": 0.16,
|
403 |
+
"learning_rate": 0.0001789066118330336,
|
404 |
+
"loss": 0.8772,
|
405 |
+
"step": 66
|
406 |
+
},
|
407 |
+
{
|
408 |
+
"epoch": 0.16,
|
409 |
+
"learning_rate": 0.00017756646853014972,
|
410 |
+
"loss": 0.8707,
|
411 |
+
"step": 67
|
412 |
+
},
|
413 |
+
{
|
414 |
+
"epoch": 0.16,
|
415 |
+
"learning_rate": 0.00017625599697765812,
|
416 |
+
"loss": 0.8089,
|
417 |
+
"step": 68
|
418 |
+
},
|
419 |
+
{
|
420 |
+
"epoch": 0.17,
|
421 |
+
"learning_rate": 0.00017497411816890378,
|
422 |
+
"loss": 0.9303,
|
423 |
+
"step": 69
|
424 |
+
},
|
425 |
+
{
|
426 |
+
"epoch": 0.17,
|
427 |
+
"learning_rate": 0.00017371980724307585,
|
428 |
+
"loss": 0.9161,
|
429 |
+
"step": 70
|
430 |
+
},
|
431 |
+
{
|
432 |
+
"epoch": 0.17,
|
433 |
+
"learning_rate": 0.00017249209004113945,
|
434 |
+
"loss": 0.9064,
|
435 |
+
"step": 71
|
436 |
+
},
|
437 |
+
{
|
438 |
+
"epoch": 0.17,
|
439 |
+
"learning_rate": 0.00017129003992578723,
|
440 |
+
"loss": 1.0988,
|
441 |
+
"step": 72
|
442 |
+
},
|
443 |
+
{
|
444 |
+
"epoch": 0.18,
|
445 |
+
"learning_rate": 0.00017011277484181944,
|
446 |
+
"loss": 0.9804,
|
447 |
+
"step": 73
|
448 |
+
},
|
449 |
+
{
|
450 |
+
"epoch": 0.18,
|
451 |
+
"learning_rate": 0.0001689594545957618,
|
452 |
+
"loss": 0.8382,
|
453 |
+
"step": 74
|
454 |
+
},
|
455 |
+
{
|
456 |
+
"epoch": 0.18,
|
457 |
+
"learning_rate": 0.00016782927833565472,
|
458 |
+
"loss": 0.9632,
|
459 |
+
"step": 75
|
460 |
+
},
|
461 |
+
{
|
462 |
+
"epoch": 0.18,
|
463 |
+
"learning_rate": 0.00016672148221383754,
|
464 |
+
"loss": 0.9494,
|
465 |
+
"step": 76
|
466 |
+
},
|
467 |
+
{
|
468 |
+
"epoch": 0.18,
|
469 |
+
"learning_rate": 0.00016563533721722828,
|
470 |
+
"loss": 0.9253,
|
471 |
+
"step": 77
|
472 |
+
},
|
473 |
+
{
|
474 |
+
"epoch": 0.19,
|
475 |
+
"learning_rate": 0.0001645701471510958,
|
476 |
+
"loss": 0.9143,
|
477 |
+
"step": 78
|
478 |
+
},
|
479 |
+
{
|
480 |
+
"epoch": 0.19,
|
481 |
+
"learning_rate": 0.00016352524676365398,
|
482 |
+
"loss": 0.8907,
|
483 |
+
"step": 79
|
484 |
+
},
|
485 |
+
{
|
486 |
+
"epoch": 0.19,
|
487 |
+
"learning_rate": 0.0001625,
|
488 |
+
"loss": 0.9748,
|
489 |
+
"step": 80
|
490 |
+
},
|
491 |
+
{
|
492 |
+
"epoch": 0.19,
|
493 |
+
"learning_rate": 0.00016149379837498482,
|
494 |
+
"loss": 0.893,
|
495 |
+
"step": 81
|
496 |
+
},
|
497 |
+
{
|
498 |
+
"epoch": 0.2,
|
499 |
+
"learning_rate": 0.00016050605945555833,
|
500 |
+
"loss": 0.839,
|
501 |
+
"step": 82
|
502 |
+
},
|
503 |
+
{
|
504 |
+
"epoch": 0.2,
|
505 |
+
"learning_rate": 0.0001595362254439902,
|
506 |
+
"loss": 0.9276,
|
507 |
+
"step": 83
|
508 |
+
},
|
509 |
+
{
|
510 |
+
"epoch": 0.2,
|
511 |
+
"learning_rate": 0.00015858376185413662,
|
512 |
+
"loss": 0.8758,
|
513 |
+
"step": 84
|
514 |
+
},
|
515 |
+
{
|
516 |
+
"epoch": 0.2,
|
517 |
+
"learning_rate": 0.00015764815627361642,
|
518 |
+
"loss": 0.9125,
|
519 |
+
"step": 85
|
520 |
+
},
|
521 |
+
{
|
522 |
+
"epoch": 0.21,
|
523 |
+
"learning_rate": 0.00015672891720538393,
|
524 |
+
"loss": 0.955,
|
525 |
+
"step": 86
|
526 |
+
},
|
527 |
+
{
|
528 |
+
"epoch": 0.21,
|
529 |
+
"learning_rate": 0.00015582557298274985,
|
530 |
+
"loss": 0.9104,
|
531 |
+
"step": 87
|
532 |
+
},
|
533 |
+
{
|
534 |
+
"epoch": 0.21,
|
535 |
+
"learning_rate": 0.00015493767075240873,
|
536 |
+
"loss": 0.8861,
|
537 |
+
"step": 88
|
538 |
+
},
|
539 |
+
{
|
540 |
+
"epoch": 0.21,
|
541 |
+
"learning_rate": 0.0001540647755204926,
|
542 |
+
"loss": 0.9693,
|
543 |
+
"step": 89
|
544 |
+
},
|
545 |
+
{
|
546 |
+
"epoch": 0.22,
|
547 |
+
"learning_rate": 0.0001532064692570853,
|
548 |
+
"loss": 0.7245,
|
549 |
+
"step": 90
|
550 |
+
},
|
551 |
+
{
|
552 |
+
"epoch": 0.22,
|
553 |
+
"learning_rate": 0.000152362350055011,
|
554 |
+
"loss": 0.7523,
|
555 |
+
"step": 91
|
556 |
+
},
|
557 |
+
{
|
558 |
+
"epoch": 0.22,
|
559 |
+
"learning_rate": 0.000151532031339051,
|
560 |
+
"loss": 0.8522,
|
561 |
+
"step": 92
|
562 |
+
},
|
563 |
+
{
|
564 |
+
"epoch": 0.22,
|
565 |
+
"learning_rate": 0.00015071514112205468,
|
566 |
+
"loss": 0.9273,
|
567 |
+
"step": 93
|
568 |
+
},
|
569 |
+
{
|
570 |
+
"epoch": 0.23,
|
571 |
+
"learning_rate": 0.0001499113213046938,
|
572 |
+
"loss": 1.0303,
|
573 |
+
"step": 94
|
574 |
+
},
|
575 |
+
{
|
576 |
+
"epoch": 0.23,
|
577 |
+
"learning_rate": 0.00014912022701586513,
|
578 |
+
"loss": 0.9273,
|
579 |
+
"step": 95
|
580 |
+
},
|
581 |
+
{
|
582 |
+
"epoch": 0.23,
|
583 |
+
"learning_rate": 0.00014834152599098248,
|
584 |
+
"loss": 0.9071,
|
585 |
+
"step": 96
|
586 |
+
},
|
587 |
+
{
|
588 |
+
"epoch": 0.23,
|
589 |
+
"learning_rate": 0.00014757489798561242,
|
590 |
+
"loss": 0.954,
|
591 |
+
"step": 97
|
592 |
+
},
|
593 |
+
{
|
594 |
+
"epoch": 0.24,
|
595 |
+
"learning_rate": 0.00014682003422210332,
|
596 |
+
"loss": 0.7897,
|
597 |
+
"step": 98
|
598 |
+
},
|
599 |
+
{
|
600 |
+
"epoch": 0.24,
|
601 |
+
"learning_rate": 0.00014607663686703578,
|
602 |
+
"loss": 0.9045,
|
603 |
+
"step": 99
|
604 |
+
},
|
605 |
+
{
|
606 |
+
"epoch": 0.24,
|
607 |
+
"learning_rate": 0.00014534441853748632,
|
608 |
+
"loss": 0.7919,
|
609 |
+
"step": 100
|
610 |
+
},
|
611 |
+
{
|
612 |
+
"epoch": 0.24,
|
613 |
+
"learning_rate": 0.00014462310183424506,
|
614 |
+
"loss": 0.7449,
|
615 |
+
"step": 101
|
616 |
+
},
|
617 |
+
{
|
618 |
+
"epoch": 0.24,
|
619 |
+
"learning_rate": 0.0001439124189002655,
|
620 |
+
"loss": 0.8953,
|
621 |
+
"step": 102
|
622 |
+
},
|
623 |
+
{
|
624 |
+
"epoch": 0.25,
|
625 |
+
"learning_rate": 0.0001432121110027503,
|
626 |
+
"loss": 0.974,
|
627 |
+
"step": 103
|
628 |
+
},
|
629 |
+
{
|
630 |
+
"epoch": 0.25,
|
631 |
+
"learning_rate": 0.00014252192813739225,
|
632 |
+
"loss": 0.959,
|
633 |
+
"step": 104
|
634 |
+
},
|
635 |
+
{
|
636 |
+
"epoch": 0.25,
|
637 |
+
"learning_rate": 0.00014184162865339505,
|
638 |
+
"loss": 0.8767,
|
639 |
+
"step": 105
|
640 |
+
},
|
641 |
+
{
|
642 |
+
"epoch": 0.25,
|
643 |
+
"learning_rate": 0.00014117097889799755,
|
644 |
+
"loss": 0.9206,
|
645 |
+
"step": 106
|
646 |
+
},
|
647 |
+
{
|
648 |
+
"epoch": 0.26,
|
649 |
+
"learning_rate": 0.000140509752879313,
|
650 |
+
"loss": 0.8096,
|
651 |
+
"step": 107
|
652 |
+
},
|
653 |
+
{
|
654 |
+
"epoch": 0.26,
|
655 |
+
"learning_rate": 0.00013985773194637893,
|
656 |
+
"loss": 0.9726,
|
657 |
+
"step": 108
|
658 |
+
},
|
659 |
+
{
|
660 |
+
"epoch": 0.26,
|
661 |
+
"learning_rate": 0.00013921470448538878,
|
662 |
+
"loss": 0.7764,
|
663 |
+
"step": 109
|
664 |
+
},
|
665 |
+
{
|
666 |
+
"epoch": 0.26,
|
667 |
+
"learning_rate": 0.00013858046563114675,
|
668 |
+
"loss": 0.8414,
|
669 |
+
"step": 110
|
670 |
+
},
|
671 |
+
{
|
672 |
+
"epoch": 0.27,
|
673 |
+
"learning_rate": 0.0001379548169928529,
|
674 |
+
"loss": 0.9365,
|
675 |
+
"step": 111
|
676 |
+
},
|
677 |
+
{
|
678 |
+
"epoch": 0.27,
|
679 |
+
"learning_rate": 0.00013733756639338393,
|
680 |
+
"loss": 0.9857,
|
681 |
+
"step": 112
|
682 |
+
},
|
683 |
+
{
|
684 |
+
"epoch": 0.27,
|
685 |
+
"learning_rate": 0.00013672852762129314,
|
686 |
+
"loss": 0.8209,
|
687 |
+
"step": 113
|
688 |
+
},
|
689 |
+
{
|
690 |
+
"epoch": 0.27,
|
691 |
+
"learning_rate": 0.00013612752019480102,
|
692 |
+
"loss": 0.9954,
|
693 |
+
"step": 114
|
694 |
+
},
|
695 |
+
{
|
696 |
+
"epoch": 0.28,
|
697 |
+
"learning_rate": 0.0001355343691370986,
|
698 |
+
"loss": 0.9425,
|
699 |
+
"step": 115
|
700 |
+
},
|
701 |
+
{
|
702 |
+
"epoch": 0.28,
|
703 |
+
"learning_rate": 0.00013494890476232745,
|
704 |
+
"loss": 0.9199,
|
705 |
+
"step": 116
|
706 |
+
},
|
707 |
+
{
|
708 |
+
"epoch": 0.28,
|
709 |
+
"learning_rate": 0.0001343709624716425,
|
710 |
+
"loss": 1.0011,
|
711 |
+
"step": 117
|
712 |
+
},
|
713 |
+
{
|
714 |
+
"epoch": 0.28,
|
715 |
+
"learning_rate": 0.00013380038255880045,
|
716 |
+
"loss": 0.9335,
|
717 |
+
"step": 118
|
718 |
+
},
|
719 |
+
{
|
720 |
+
"epoch": 0.29,
|
721 |
+
"learning_rate": 0.000133237010024753,
|
722 |
+
"loss": 1.0612,
|
723 |
+
"step": 119
|
724 |
+
},
|
725 |
+
{
|
726 |
+
"epoch": 0.29,
|
727 |
+
"learning_rate": 0.0001326806944007555,
|
728 |
+
"loss": 0.8794,
|
729 |
+
"step": 120
|
730 |
+
}
|
731 |
+
],
|
732 |
+
"logging_steps": 1,
|
733 |
+
"max_steps": 417,
|
734 |
+
"num_train_epochs": 1,
|
735 |
+
"save_steps": 10,
|
736 |
+
"total_flos": 3.891394643755008e+16,
|
737 |
+
"trial_name": null,
|
738 |
+
"trial_params": null
|
739 |
+
}
|
checkpoint-120/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:482256ef65b59af088490f9e3870f1b868a90992cd6294900bd43d13ef410480
|
3 |
+
size 4536
|
checkpoint-190/README.md
ADDED
@@ -0,0 +1,220 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: peft
|
3 |
+
base_model: unsloth/llama-2-7b
|
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 |
+
|
201 |
+
|
202 |
+
## Training procedure
|
203 |
+
|
204 |
+
|
205 |
+
The following `bitsandbytes` quantization config was used during training:
|
206 |
+
- quant_method: bitsandbytes
|
207 |
+
- load_in_8bit: False
|
208 |
+
- load_in_4bit: True
|
209 |
+
- llm_int8_threshold: 6.0
|
210 |
+
- llm_int8_skip_modules: None
|
211 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
212 |
+
- llm_int8_has_fp16_weight: False
|
213 |
+
- bnb_4bit_quant_type: nf4
|
214 |
+
- bnb_4bit_use_double_quant: True
|
215 |
+
- bnb_4bit_compute_dtype: bfloat16
|
216 |
+
|
217 |
+
### Framework versions
|
218 |
+
|
219 |
+
|
220 |
+
- PEFT 0.6.2
|
checkpoint-190/adapter_config.json
ADDED
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "unsloth/llama-2-7b",
|
5 |
+
"bias": "none",
|
6 |
+
"fan_in_fan_out": false,
|
7 |
+
"inference_mode": true,
|
8 |
+
"init_lora_weights": true,
|
9 |
+
"layers_pattern": null,
|
10 |
+
"layers_to_transform": null,
|
11 |
+
"lora_alpha": 32,
|
12 |
+
"lora_dropout": 0,
|
13 |
+
"modules_to_save": null,
|
14 |
+
"peft_type": "LORA",
|
15 |
+
"r": 16,
|
16 |
+
"rank_pattern": {},
|
17 |
+
"revision": null,
|
18 |
+
"target_modules": [
|
19 |
+
"o_proj",
|
20 |
+
"up_proj",
|
21 |
+
"down_proj",
|
22 |
+
"q_proj",
|
23 |
+
"k_proj",
|
24 |
+
"v_proj",
|
25 |
+
"gate_proj"
|
26 |
+
],
|
27 |
+
"task_type": "CAUSAL_LM"
|
28 |
+
}
|
checkpoint-190/adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6b1782493354a771246d082dc93657ab22db0ff3ddd5df17582fee11d00146f9
|
3 |
+
size 159967880
|
checkpoint-190/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:57486841c0688ed8ffaa2b58024863dbb4ba387677b7d20b6d188a9d6d450e01
|
3 |
+
size 80630612
|
checkpoint-190/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:203e9bfabd925cb4ec7129d24877156fcee87215187c35a867e358e56a9425a4
|
3 |
+
size 14244
|
checkpoint-190/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fdcbbcb76fd3462a8f7147c20ae6d636210dbe8343e20495ae55ada97cf0e38a
|
3 |
+
size 1064
|
checkpoint-190/trainer_state.json
ADDED
@@ -0,0 +1,1159 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.4556354916067146,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 190,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.0,
|
13 |
+
"learning_rate": 0.00013,
|
14 |
+
"loss": 1.1241,
|
15 |
+
"step": 1
|
16 |
+
},
|
17 |
+
{
|
18 |
+
"epoch": 0.0,
|
19 |
+
"learning_rate": 0.00026,
|
20 |
+
"loss": 1.0107,
|
21 |
+
"step": 2
|
22 |
+
},
|
23 |
+
{
|
24 |
+
"epoch": 0.01,
|
25 |
+
"learning_rate": 0.00039,
|
26 |
+
"loss": 1.1086,
|
27 |
+
"step": 3
|
28 |
+
},
|
29 |
+
{
|
30 |
+
"epoch": 0.01,
|
31 |
+
"learning_rate": 0.00052,
|
32 |
+
"loss": 1.0044,
|
33 |
+
"step": 4
|
34 |
+
},
|
35 |
+
{
|
36 |
+
"epoch": 0.01,
|
37 |
+
"learning_rate": 0.00065,
|
38 |
+
"loss": 1.0496,
|
39 |
+
"step": 5
|
40 |
+
},
|
41 |
+
{
|
42 |
+
"epoch": 0.01,
|
43 |
+
"learning_rate": 0.0005933661039639299,
|
44 |
+
"loss": 1.0199,
|
45 |
+
"step": 6
|
46 |
+
},
|
47 |
+
{
|
48 |
+
"epoch": 0.02,
|
49 |
+
"learning_rate": 0.0005493502655735357,
|
50 |
+
"loss": 1.0198,
|
51 |
+
"step": 7
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.02,
|
55 |
+
"learning_rate": 0.0005138701197773616,
|
56 |
+
"loss": 0.969,
|
57 |
+
"step": 8
|
58 |
+
},
|
59 |
+
{
|
60 |
+
"epoch": 0.02,
|
61 |
+
"learning_rate": 0.0004844813951249544,
|
62 |
+
"loss": 0.9383,
|
63 |
+
"step": 9
|
64 |
+
},
|
65 |
+
{
|
66 |
+
"epoch": 0.02,
|
67 |
+
"learning_rate": 0.0004596194077712558,
|
68 |
+
"loss": 0.8776,
|
69 |
+
"step": 10
|
70 |
+
},
|
71 |
+
{
|
72 |
+
"epoch": 0.03,
|
73 |
+
"learning_rate": 0.0004382299106011073,
|
74 |
+
"loss": 1.0173,
|
75 |
+
"step": 11
|
76 |
+
},
|
77 |
+
{
|
78 |
+
"epoch": 0.03,
|
79 |
+
"learning_rate": 0.0004195731958391368,
|
80 |
+
"loss": 1.1173,
|
81 |
+
"step": 12
|
82 |
+
},
|
83 |
+
{
|
84 |
+
"epoch": 0.03,
|
85 |
+
"learning_rate": 0.0004031128874149274,
|
86 |
+
"loss": 1.0876,
|
87 |
+
"step": 13
|
88 |
+
},
|
89 |
+
{
|
90 |
+
"epoch": 0.03,
|
91 |
+
"learning_rate": 0.0003884492980336779,
|
92 |
+
"loss": 1.0524,
|
93 |
+
"step": 14
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 0.04,
|
97 |
+
"learning_rate": 0.0003752776749732568,
|
98 |
+
"loss": 0.8953,
|
99 |
+
"step": 15
|
100 |
+
},
|
101 |
+
{
|
102 |
+
"epoch": 0.04,
|
103 |
+
"learning_rate": 0.00036336104634371584,
|
104 |
+
"loss": 1.1335,
|
105 |
+
"step": 16
|
106 |
+
},
|
107 |
+
{
|
108 |
+
"epoch": 0.04,
|
109 |
+
"learning_rate": 0.00035251199395531623,
|
110 |
+
"loss": 0.9837,
|
111 |
+
"step": 17
|
112 |
+
},
|
113 |
+
{
|
114 |
+
"epoch": 0.04,
|
115 |
+
"learning_rate": 0.00034258007985157445,
|
116 |
+
"loss": 0.9707,
|
117 |
+
"step": 18
|
118 |
+
},
|
119 |
+
{
|
120 |
+
"epoch": 0.05,
|
121 |
+
"learning_rate": 0.0003334429644276751,
|
122 |
+
"loss": 0.9149,
|
123 |
+
"step": 19
|
124 |
+
},
|
125 |
+
{
|
126 |
+
"epoch": 0.05,
|
127 |
+
"learning_rate": 0.000325,
|
128 |
+
"loss": 1.0043,
|
129 |
+
"step": 20
|
130 |
+
},
|
131 |
+
{
|
132 |
+
"epoch": 0.05,
|
133 |
+
"learning_rate": 0.00031716752370827323,
|
134 |
+
"loss": 1.001,
|
135 |
+
"step": 21
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 0.05,
|
139 |
+
"learning_rate": 0.00030987534150481746,
|
140 |
+
"loss": 1.0395,
|
141 |
+
"step": 22
|
142 |
+
},
|
143 |
+
{
|
144 |
+
"epoch": 0.06,
|
145 |
+
"learning_rate": 0.000303064062678102,
|
146 |
+
"loss": 0.8718,
|
147 |
+
"step": 23
|
148 |
+
},
|
149 |
+
{
|
150 |
+
"epoch": 0.06,
|
151 |
+
"learning_rate": 0.00029668305198196496,
|
152 |
+
"loss": 1.1114,
|
153 |
+
"step": 24
|
154 |
+
},
|
155 |
+
{
|
156 |
+
"epoch": 0.06,
|
157 |
+
"learning_rate": 0.00029068883707497264,
|
158 |
+
"loss": 0.7765,
|
159 |
+
"step": 25
|
160 |
+
},
|
161 |
+
{
|
162 |
+
"epoch": 0.06,
|
163 |
+
"learning_rate": 0.0002850438562747845,
|
164 |
+
"loss": 0.9522,
|
165 |
+
"step": 26
|
166 |
+
},
|
167 |
+
{
|
168 |
+
"epoch": 0.06,
|
169 |
+
"learning_rate": 0.00027971546389275785,
|
170 |
+
"loss": 0.9588,
|
171 |
+
"step": 27
|
172 |
+
},
|
173 |
+
{
|
174 |
+
"epoch": 0.07,
|
175 |
+
"learning_rate": 0.00027467513278676785,
|
176 |
+
"loss": 1.0313,
|
177 |
+
"step": 28
|
178 |
+
},
|
179 |
+
{
|
180 |
+
"epoch": 0.07,
|
181 |
+
"learning_rate": 0.0002698978095246549,
|
182 |
+
"loss": 0.9338,
|
183 |
+
"step": 29
|
184 |
+
},
|
185 |
+
{
|
186 |
+
"epoch": 0.07,
|
187 |
+
"learning_rate": 0.000265361388801511,
|
188 |
+
"loss": 0.892,
|
189 |
+
"step": 30
|
190 |
+
},
|
191 |
+
{
|
192 |
+
"epoch": 0.07,
|
193 |
+
"learning_rate": 0.00026104628189331215,
|
194 |
+
"loss": 0.893,
|
195 |
+
"step": 31
|
196 |
+
},
|
197 |
+
{
|
198 |
+
"epoch": 0.08,
|
199 |
+
"learning_rate": 0.0002569350598886808,
|
200 |
+
"loss": 0.8983,
|
201 |
+
"step": 32
|
202 |
+
},
|
203 |
+
{
|
204 |
+
"epoch": 0.08,
|
205 |
+
"learning_rate": 0.00025301215685249496,
|
206 |
+
"loss": 0.9277,
|
207 |
+
"step": 33
|
208 |
+
},
|
209 |
+
{
|
210 |
+
"epoch": 0.08,
|
211 |
+
"learning_rate": 0.00024926362137539537,
|
212 |
+
"loss": 0.8962,
|
213 |
+
"step": 34
|
214 |
+
},
|
215 |
+
{
|
216 |
+
"epoch": 0.08,
|
217 |
+
"learning_rate": 0.00024567690745599767,
|
218 |
+
"loss": 0.9124,
|
219 |
+
"step": 35
|
220 |
+
},
|
221 |
+
{
|
222 |
+
"epoch": 0.09,
|
223 |
+
"learning_rate": 0.0002422406975624772,
|
224 |
+
"loss": 0.9535,
|
225 |
+
"step": 36
|
226 |
+
},
|
227 |
+
{
|
228 |
+
"epoch": 0.09,
|
229 |
+
"learning_rate": 0.00023894475218048754,
|
230 |
+
"loss": 0.9019,
|
231 |
+
"step": 37
|
232 |
+
},
|
233 |
+
{
|
234 |
+
"epoch": 0.09,
|
235 |
+
"learning_rate": 0.0002357797812857538,
|
236 |
+
"loss": 1.024,
|
237 |
+
"step": 38
|
238 |
+
},
|
239 |
+
{
|
240 |
+
"epoch": 0.09,
|
241 |
+
"learning_rate": 0.00023273733406281566,
|
242 |
+
"loss": 0.8549,
|
243 |
+
"step": 39
|
244 |
+
},
|
245 |
+
{
|
246 |
+
"epoch": 0.1,
|
247 |
+
"learning_rate": 0.0002298097038856279,
|
248 |
+
"loss": 1.0489,
|
249 |
+
"step": 40
|
250 |
+
},
|
251 |
+
{
|
252 |
+
"epoch": 0.1,
|
253 |
+
"learning_rate": 0.00022698984612511293,
|
254 |
+
"loss": 0.751,
|
255 |
+
"step": 41
|
256 |
+
},
|
257 |
+
{
|
258 |
+
"epoch": 0.1,
|
259 |
+
"learning_rate": 0.00022427130678626507,
|
260 |
+
"loss": 0.834,
|
261 |
+
"step": 42
|
262 |
+
},
|
263 |
+
{
|
264 |
+
"epoch": 0.1,
|
265 |
+
"learning_rate": 0.00022164816032790388,
|
266 |
+
"loss": 0.889,
|
267 |
+
"step": 43
|
268 |
+
},
|
269 |
+
{
|
270 |
+
"epoch": 0.11,
|
271 |
+
"learning_rate": 0.00021911495530055366,
|
272 |
+
"loss": 1.0103,
|
273 |
+
"step": 44
|
274 |
+
},
|
275 |
+
{
|
276 |
+
"epoch": 0.11,
|
277 |
+
"learning_rate": 0.00021666666666666666,
|
278 |
+
"loss": 0.8766,
|
279 |
+
"step": 45
|
280 |
+
},
|
281 |
+
{
|
282 |
+
"epoch": 0.11,
|
283 |
+
"learning_rate": 0.0002142986538536308,
|
284 |
+
"loss": 0.8181,
|
285 |
+
"step": 46
|
286 |
+
},
|
287 |
+
{
|
288 |
+
"epoch": 0.11,
|
289 |
+
"learning_rate": 0.0002120066237423687,
|
290 |
+
"loss": 0.8754,
|
291 |
+
"step": 47
|
292 |
+
},
|
293 |
+
{
|
294 |
+
"epoch": 0.12,
|
295 |
+
"learning_rate": 0.0002097865979195684,
|
296 |
+
"loss": 0.9038,
|
297 |
+
"step": 48
|
298 |
+
},
|
299 |
+
{
|
300 |
+
"epoch": 0.12,
|
301 |
+
"learning_rate": 0.00020763488362498048,
|
302 |
+
"loss": 0.8646,
|
303 |
+
"step": 49
|
304 |
+
},
|
305 |
+
{
|
306 |
+
"epoch": 0.12,
|
307 |
+
"learning_rate": 0.00020554804791094464,
|
308 |
+
"loss": 0.8836,
|
309 |
+
"step": 50
|
310 |
+
},
|
311 |
+
{
|
312 |
+
"epoch": 0.12,
|
313 |
+
"learning_rate": 0.0002035228946026736,
|
314 |
+
"loss": 0.9962,
|
315 |
+
"step": 51
|
316 |
+
},
|
317 |
+
{
|
318 |
+
"epoch": 0.12,
|
319 |
+
"learning_rate": 0.0002015564437074637,
|
320 |
+
"loss": 0.8835,
|
321 |
+
"step": 52
|
322 |
+
},
|
323 |
+
{
|
324 |
+
"epoch": 0.13,
|
325 |
+
"learning_rate": 0.00019964591297103414,
|
326 |
+
"loss": 0.9196,
|
327 |
+
"step": 53
|
328 |
+
},
|
329 |
+
{
|
330 |
+
"epoch": 0.13,
|
331 |
+
"learning_rate": 0.00019778870132130996,
|
332 |
+
"loss": 0.8995,
|
333 |
+
"step": 54
|
334 |
+
},
|
335 |
+
{
|
336 |
+
"epoch": 0.13,
|
337 |
+
"learning_rate": 0.00019598237397554634,
|
338 |
+
"loss": 1.0178,
|
339 |
+
"step": 55
|
340 |
+
},
|
341 |
+
{
|
342 |
+
"epoch": 0.13,
|
343 |
+
"learning_rate": 0.00019422464901683895,
|
344 |
+
"loss": 0.9395,
|
345 |
+
"step": 56
|
346 |
+
},
|
347 |
+
{
|
348 |
+
"epoch": 0.14,
|
349 |
+
"learning_rate": 0.00019251338527170498,
|
350 |
+
"loss": 0.9882,
|
351 |
+
"step": 57
|
352 |
+
},
|
353 |
+
{
|
354 |
+
"epoch": 0.14,
|
355 |
+
"learning_rate": 0.00019084657134227863,
|
356 |
+
"loss": 0.9274,
|
357 |
+
"step": 58
|
358 |
+
},
|
359 |
+
{
|
360 |
+
"epoch": 0.14,
|
361 |
+
"learning_rate": 0.00018922231566536414,
|
362 |
+
"loss": 0.9517,
|
363 |
+
"step": 59
|
364 |
+
},
|
365 |
+
{
|
366 |
+
"epoch": 0.14,
|
367 |
+
"learning_rate": 0.0001876388374866284,
|
368 |
+
"loss": 0.865,
|
369 |
+
"step": 60
|
370 |
+
},
|
371 |
+
{
|
372 |
+
"epoch": 0.15,
|
373 |
+
"learning_rate": 0.00018609445865200715,
|
374 |
+
"loss": 0.9314,
|
375 |
+
"step": 61
|
376 |
+
},
|
377 |
+
{
|
378 |
+
"epoch": 0.15,
|
379 |
+
"learning_rate": 0.00018458759613029606,
|
380 |
+
"loss": 0.9224,
|
381 |
+
"step": 62
|
382 |
+
},
|
383 |
+
{
|
384 |
+
"epoch": 0.15,
|
385 |
+
"learning_rate": 0.00018311675519117857,
|
386 |
+
"loss": 0.788,
|
387 |
+
"step": 63
|
388 |
+
},
|
389 |
+
{
|
390 |
+
"epoch": 0.15,
|
391 |
+
"learning_rate": 0.00018168052317185792,
|
392 |
+
"loss": 0.9739,
|
393 |
+
"step": 64
|
394 |
+
},
|
395 |
+
{
|
396 |
+
"epoch": 0.16,
|
397 |
+
"learning_rate": 0.00018027756377319947,
|
398 |
+
"loss": 0.9419,
|
399 |
+
"step": 65
|
400 |
+
},
|
401 |
+
{
|
402 |
+
"epoch": 0.16,
|
403 |
+
"learning_rate": 0.0001789066118330336,
|
404 |
+
"loss": 0.8772,
|
405 |
+
"step": 66
|
406 |
+
},
|
407 |
+
{
|
408 |
+
"epoch": 0.16,
|
409 |
+
"learning_rate": 0.00017756646853014972,
|
410 |
+
"loss": 0.8707,
|
411 |
+
"step": 67
|
412 |
+
},
|
413 |
+
{
|
414 |
+
"epoch": 0.16,
|
415 |
+
"learning_rate": 0.00017625599697765812,
|
416 |
+
"loss": 0.8089,
|
417 |
+
"step": 68
|
418 |
+
},
|
419 |
+
{
|
420 |
+
"epoch": 0.17,
|
421 |
+
"learning_rate": 0.00017497411816890378,
|
422 |
+
"loss": 0.9303,
|
423 |
+
"step": 69
|
424 |
+
},
|
425 |
+
{
|
426 |
+
"epoch": 0.17,
|
427 |
+
"learning_rate": 0.00017371980724307585,
|
428 |
+
"loss": 0.9161,
|
429 |
+
"step": 70
|
430 |
+
},
|
431 |
+
{
|
432 |
+
"epoch": 0.17,
|
433 |
+
"learning_rate": 0.00017249209004113945,
|
434 |
+
"loss": 0.9064,
|
435 |
+
"step": 71
|
436 |
+
},
|
437 |
+
{
|
438 |
+
"epoch": 0.17,
|
439 |
+
"learning_rate": 0.00017129003992578723,
|
440 |
+
"loss": 1.0988,
|
441 |
+
"step": 72
|
442 |
+
},
|
443 |
+
{
|
444 |
+
"epoch": 0.18,
|
445 |
+
"learning_rate": 0.00017011277484181944,
|
446 |
+
"loss": 0.9804,
|
447 |
+
"step": 73
|
448 |
+
},
|
449 |
+
{
|
450 |
+
"epoch": 0.18,
|
451 |
+
"learning_rate": 0.0001689594545957618,
|
452 |
+
"loss": 0.8382,
|
453 |
+
"step": 74
|
454 |
+
},
|
455 |
+
{
|
456 |
+
"epoch": 0.18,
|
457 |
+
"learning_rate": 0.00016782927833565472,
|
458 |
+
"loss": 0.9632,
|
459 |
+
"step": 75
|
460 |
+
},
|
461 |
+
{
|
462 |
+
"epoch": 0.18,
|
463 |
+
"learning_rate": 0.00016672148221383754,
|
464 |
+
"loss": 0.9494,
|
465 |
+
"step": 76
|
466 |
+
},
|
467 |
+
{
|
468 |
+
"epoch": 0.18,
|
469 |
+
"learning_rate": 0.00016563533721722828,
|
470 |
+
"loss": 0.9253,
|
471 |
+
"step": 77
|
472 |
+
},
|
473 |
+
{
|
474 |
+
"epoch": 0.19,
|
475 |
+
"learning_rate": 0.0001645701471510958,
|
476 |
+
"loss": 0.9143,
|
477 |
+
"step": 78
|
478 |
+
},
|
479 |
+
{
|
480 |
+
"epoch": 0.19,
|
481 |
+
"learning_rate": 0.00016352524676365398,
|
482 |
+
"loss": 0.8907,
|
483 |
+
"step": 79
|
484 |
+
},
|
485 |
+
{
|
486 |
+
"epoch": 0.19,
|
487 |
+
"learning_rate": 0.0001625,
|
488 |
+
"loss": 0.9748,
|
489 |
+
"step": 80
|
490 |
+
},
|
491 |
+
{
|
492 |
+
"epoch": 0.19,
|
493 |
+
"learning_rate": 0.00016149379837498482,
|
494 |
+
"loss": 0.893,
|
495 |
+
"step": 81
|
496 |
+
},
|
497 |
+
{
|
498 |
+
"epoch": 0.2,
|
499 |
+
"learning_rate": 0.00016050605945555833,
|
500 |
+
"loss": 0.839,
|
501 |
+
"step": 82
|
502 |
+
},
|
503 |
+
{
|
504 |
+
"epoch": 0.2,
|
505 |
+
"learning_rate": 0.0001595362254439902,
|
506 |
+
"loss": 0.9276,
|
507 |
+
"step": 83
|
508 |
+
},
|
509 |
+
{
|
510 |
+
"epoch": 0.2,
|
511 |
+
"learning_rate": 0.00015858376185413662,
|
512 |
+
"loss": 0.8758,
|
513 |
+
"step": 84
|
514 |
+
},
|
515 |
+
{
|
516 |
+
"epoch": 0.2,
|
517 |
+
"learning_rate": 0.00015764815627361642,
|
518 |
+
"loss": 0.9125,
|
519 |
+
"step": 85
|
520 |
+
},
|
521 |
+
{
|
522 |
+
"epoch": 0.21,
|
523 |
+
"learning_rate": 0.00015672891720538393,
|
524 |
+
"loss": 0.955,
|
525 |
+
"step": 86
|
526 |
+
},
|
527 |
+
{
|
528 |
+
"epoch": 0.21,
|
529 |
+
"learning_rate": 0.00015582557298274985,
|
530 |
+
"loss": 0.9104,
|
531 |
+
"step": 87
|
532 |
+
},
|
533 |
+
{
|
534 |
+
"epoch": 0.21,
|
535 |
+
"learning_rate": 0.00015493767075240873,
|
536 |
+
"loss": 0.8861,
|
537 |
+
"step": 88
|
538 |
+
},
|
539 |
+
{
|
540 |
+
"epoch": 0.21,
|
541 |
+
"learning_rate": 0.0001540647755204926,
|
542 |
+
"loss": 0.9693,
|
543 |
+
"step": 89
|
544 |
+
},
|
545 |
+
{
|
546 |
+
"epoch": 0.22,
|
547 |
+
"learning_rate": 0.0001532064692570853,
|
548 |
+
"loss": 0.7245,
|
549 |
+
"step": 90
|
550 |
+
},
|
551 |
+
{
|
552 |
+
"epoch": 0.22,
|
553 |
+
"learning_rate": 0.000152362350055011,
|
554 |
+
"loss": 0.7523,
|
555 |
+
"step": 91
|
556 |
+
},
|
557 |
+
{
|
558 |
+
"epoch": 0.22,
|
559 |
+
"learning_rate": 0.000151532031339051,
|
560 |
+
"loss": 0.8522,
|
561 |
+
"step": 92
|
562 |
+
},
|
563 |
+
{
|
564 |
+
"epoch": 0.22,
|
565 |
+
"learning_rate": 0.00015071514112205468,
|
566 |
+
"loss": 0.9273,
|
567 |
+
"step": 93
|
568 |
+
},
|
569 |
+
{
|
570 |
+
"epoch": 0.23,
|
571 |
+
"learning_rate": 0.0001499113213046938,
|
572 |
+
"loss": 1.0303,
|
573 |
+
"step": 94
|
574 |
+
},
|
575 |
+
{
|
576 |
+
"epoch": 0.23,
|
577 |
+
"learning_rate": 0.00014912022701586513,
|
578 |
+
"loss": 0.9273,
|
579 |
+
"step": 95
|
580 |
+
},
|
581 |
+
{
|
582 |
+
"epoch": 0.23,
|
583 |
+
"learning_rate": 0.00014834152599098248,
|
584 |
+
"loss": 0.9071,
|
585 |
+
"step": 96
|
586 |
+
},
|
587 |
+
{
|
588 |
+
"epoch": 0.23,
|
589 |
+
"learning_rate": 0.00014757489798561242,
|
590 |
+
"loss": 0.954,
|
591 |
+
"step": 97
|
592 |
+
},
|
593 |
+
{
|
594 |
+
"epoch": 0.24,
|
595 |
+
"learning_rate": 0.00014682003422210332,
|
596 |
+
"loss": 0.7897,
|
597 |
+
"step": 98
|
598 |
+
},
|
599 |
+
{
|
600 |
+
"epoch": 0.24,
|
601 |
+
"learning_rate": 0.00014607663686703578,
|
602 |
+
"loss": 0.9045,
|
603 |
+
"step": 99
|
604 |
+
},
|
605 |
+
{
|
606 |
+
"epoch": 0.24,
|
607 |
+
"learning_rate": 0.00014534441853748632,
|
608 |
+
"loss": 0.7919,
|
609 |
+
"step": 100
|
610 |
+
},
|
611 |
+
{
|
612 |
+
"epoch": 0.24,
|
613 |
+
"learning_rate": 0.00014462310183424506,
|
614 |
+
"loss": 0.7449,
|
615 |
+
"step": 101
|
616 |
+
},
|
617 |
+
{
|
618 |
+
"epoch": 0.24,
|
619 |
+
"learning_rate": 0.0001439124189002655,
|
620 |
+
"loss": 0.8953,
|
621 |
+
"step": 102
|
622 |
+
},
|
623 |
+
{
|
624 |
+
"epoch": 0.25,
|
625 |
+
"learning_rate": 0.0001432121110027503,
|
626 |
+
"loss": 0.974,
|
627 |
+
"step": 103
|
628 |
+
},
|
629 |
+
{
|
630 |
+
"epoch": 0.25,
|
631 |
+
"learning_rate": 0.00014252192813739225,
|
632 |
+
"loss": 0.959,
|
633 |
+
"step": 104
|
634 |
+
},
|
635 |
+
{
|
636 |
+
"epoch": 0.25,
|
637 |
+
"learning_rate": 0.00014184162865339505,
|
638 |
+
"loss": 0.8767,
|
639 |
+
"step": 105
|
640 |
+
},
|
641 |
+
{
|
642 |
+
"epoch": 0.25,
|
643 |
+
"learning_rate": 0.00014117097889799755,
|
644 |
+
"loss": 0.9206,
|
645 |
+
"step": 106
|
646 |
+
},
|
647 |
+
{
|
648 |
+
"epoch": 0.26,
|
649 |
+
"learning_rate": 0.000140509752879313,
|
650 |
+
"loss": 0.8096,
|
651 |
+
"step": 107
|
652 |
+
},
|
653 |
+
{
|
654 |
+
"epoch": 0.26,
|
655 |
+
"learning_rate": 0.00013985773194637893,
|
656 |
+
"loss": 0.9726,
|
657 |
+
"step": 108
|
658 |
+
},
|
659 |
+
{
|
660 |
+
"epoch": 0.26,
|
661 |
+
"learning_rate": 0.00013921470448538878,
|
662 |
+
"loss": 0.7764,
|
663 |
+
"step": 109
|
664 |
+
},
|
665 |
+
{
|
666 |
+
"epoch": 0.26,
|
667 |
+
"learning_rate": 0.00013858046563114675,
|
668 |
+
"loss": 0.8414,
|
669 |
+
"step": 110
|
670 |
+
},
|
671 |
+
{
|
672 |
+
"epoch": 0.27,
|
673 |
+
"learning_rate": 0.0001379548169928529,
|
674 |
+
"loss": 0.9365,
|
675 |
+
"step": 111
|
676 |
+
},
|
677 |
+
{
|
678 |
+
"epoch": 0.27,
|
679 |
+
"learning_rate": 0.00013733756639338393,
|
680 |
+
"loss": 0.9857,
|
681 |
+
"step": 112
|
682 |
+
},
|
683 |
+
{
|
684 |
+
"epoch": 0.27,
|
685 |
+
"learning_rate": 0.00013672852762129314,
|
686 |
+
"loss": 0.8209,
|
687 |
+
"step": 113
|
688 |
+
},
|
689 |
+
{
|
690 |
+
"epoch": 0.27,
|
691 |
+
"learning_rate": 0.00013612752019480102,
|
692 |
+
"loss": 0.9954,
|
693 |
+
"step": 114
|
694 |
+
},
|
695 |
+
{
|
696 |
+
"epoch": 0.28,
|
697 |
+
"learning_rate": 0.0001355343691370986,
|
698 |
+
"loss": 0.9425,
|
699 |
+
"step": 115
|
700 |
+
},
|
701 |
+
{
|
702 |
+
"epoch": 0.28,
|
703 |
+
"learning_rate": 0.00013494890476232745,
|
704 |
+
"loss": 0.9199,
|
705 |
+
"step": 116
|
706 |
+
},
|
707 |
+
{
|
708 |
+
"epoch": 0.28,
|
709 |
+
"learning_rate": 0.0001343709624716425,
|
710 |
+
"loss": 1.0011,
|
711 |
+
"step": 117
|
712 |
+
},
|
713 |
+
{
|
714 |
+
"epoch": 0.28,
|
715 |
+
"learning_rate": 0.00013380038255880045,
|
716 |
+
"loss": 0.9335,
|
717 |
+
"step": 118
|
718 |
+
},
|
719 |
+
{
|
720 |
+
"epoch": 0.29,
|
721 |
+
"learning_rate": 0.000133237010024753,
|
722 |
+
"loss": 1.0612,
|
723 |
+
"step": 119
|
724 |
+
},
|
725 |
+
{
|
726 |
+
"epoch": 0.29,
|
727 |
+
"learning_rate": 0.0001326806944007555,
|
728 |
+
"loss": 0.8794,
|
729 |
+
"step": 120
|
730 |
+
},
|
731 |
+
{
|
732 |
+
"epoch": 0.29,
|
733 |
+
"learning_rate": 0.00013213128957953303,
|
734 |
+
"loss": 0.8557,
|
735 |
+
"step": 121
|
736 |
+
},
|
737 |
+
{
|
738 |
+
"epoch": 0.29,
|
739 |
+
"learning_rate": 0.00013158865365407385,
|
740 |
+
"loss": 0.931,
|
741 |
+
"step": 122
|
742 |
+
},
|
743 |
+
{
|
744 |
+
"epoch": 0.29,
|
745 |
+
"learning_rate": 0.00013105264876364566,
|
746 |
+
"loss": 0.9648,
|
747 |
+
"step": 123
|
748 |
+
},
|
749 |
+
{
|
750 |
+
"epoch": 0.3,
|
751 |
+
"learning_rate": 0.00013052314094665608,
|
752 |
+
"loss": 0.8448,
|
753 |
+
"step": 124
|
754 |
+
},
|
755 |
+
{
|
756 |
+
"epoch": 0.3,
|
757 |
+
"learning_rate": 0.00013,
|
758 |
+
"loss": 0.9247,
|
759 |
+
"step": 125
|
760 |
+
},
|
761 |
+
{
|
762 |
+
"epoch": 0.3,
|
763 |
+
"learning_rate": 0.0001294830993445593,
|
764 |
+
"loss": 0.9537,
|
765 |
+
"step": 126
|
766 |
+
},
|
767 |
+
{
|
768 |
+
"epoch": 0.3,
|
769 |
+
"learning_rate": 0.00012897231589653857,
|
770 |
+
"loss": 0.8049,
|
771 |
+
"step": 127
|
772 |
+
},
|
773 |
+
{
|
774 |
+
"epoch": 0.31,
|
775 |
+
"learning_rate": 0.0001284675299443404,
|
776 |
+
"loss": 0.8177,
|
777 |
+
"step": 128
|
778 |
+
},
|
779 |
+
{
|
780 |
+
"epoch": 0.31,
|
781 |
+
"learning_rate": 0.00012796862503070062,
|
782 |
+
"loss": 0.9717,
|
783 |
+
"step": 129
|
784 |
+
},
|
785 |
+
{
|
786 |
+
"epoch": 0.31,
|
787 |
+
"learning_rate": 0.00012747548783981962,
|
788 |
+
"loss": 0.8813,
|
789 |
+
"step": 130
|
790 |
+
},
|
791 |
+
{
|
792 |
+
"epoch": 0.31,
|
793 |
+
"learning_rate": 0.00012698800808924157,
|
794 |
+
"loss": 0.9708,
|
795 |
+
"step": 131
|
796 |
+
},
|
797 |
+
{
|
798 |
+
"epoch": 0.32,
|
799 |
+
"learning_rate": 0.00012650607842624748,
|
800 |
+
"loss": 0.8776,
|
801 |
+
"step": 132
|
802 |
+
},
|
803 |
+
{
|
804 |
+
"epoch": 0.32,
|
805 |
+
"learning_rate": 0.0001260295943285407,
|
806 |
+
"loss": 0.8564,
|
807 |
+
"step": 133
|
808 |
+
},
|
809 |
+
{
|
810 |
+
"epoch": 0.32,
|
811 |
+
"learning_rate": 0.00012555845400901656,
|
812 |
+
"loss": 0.8793,
|
813 |
+
"step": 134
|
814 |
+
},
|
815 |
+
{
|
816 |
+
"epoch": 0.32,
|
817 |
+
"learning_rate": 0.0001250925583244189,
|
818 |
+
"loss": 0.9288,
|
819 |
+
"step": 135
|
820 |
+
},
|
821 |
+
{
|
822 |
+
"epoch": 0.33,
|
823 |
+
"learning_rate": 0.00012463181068769768,
|
824 |
+
"loss": 0.9407,
|
825 |
+
"step": 136
|
826 |
+
},
|
827 |
+
{
|
828 |
+
"epoch": 0.33,
|
829 |
+
"learning_rate": 0.0001241761169838914,
|
830 |
+
"loss": 0.9746,
|
831 |
+
"step": 137
|
832 |
+
},
|
833 |
+
{
|
834 |
+
"epoch": 0.33,
|
835 |
+
"learning_rate": 0.00012372538548936814,
|
836 |
+
"loss": 1.0109,
|
837 |
+
"step": 138
|
838 |
+
},
|
839 |
+
{
|
840 |
+
"epoch": 0.33,
|
841 |
+
"learning_rate": 0.00012327952679426827,
|
842 |
+
"loss": 1.0695,
|
843 |
+
"step": 139
|
844 |
+
},
|
845 |
+
{
|
846 |
+
"epoch": 0.34,
|
847 |
+
"learning_rate": 0.00012283845372799884,
|
848 |
+
"loss": 0.9092,
|
849 |
+
"step": 140
|
850 |
+
},
|
851 |
+
{
|
852 |
+
"epoch": 0.34,
|
853 |
+
"learning_rate": 0.00012240208128764027,
|
854 |
+
"loss": 0.7535,
|
855 |
+
"step": 141
|
856 |
+
},
|
857 |
+
{
|
858 |
+
"epoch": 0.34,
|
859 |
+
"learning_rate": 0.00012197032656913024,
|
860 |
+
"loss": 0.7952,
|
861 |
+
"step": 142
|
862 |
+
},
|
863 |
+
{
|
864 |
+
"epoch": 0.34,
|
865 |
+
"learning_rate": 0.00012154310870109942,
|
866 |
+
"loss": 0.8747,
|
867 |
+
"step": 143
|
868 |
+
},
|
869 |
+
{
|
870 |
+
"epoch": 0.35,
|
871 |
+
"learning_rate": 0.0001211203487812386,
|
872 |
+
"loss": 0.823,
|
873 |
+
"step": 144
|
874 |
+
},
|
875 |
+
{
|
876 |
+
"epoch": 0.35,
|
877 |
+
"learning_rate": 0.0001207019698150837,
|
878 |
+
"loss": 0.838,
|
879 |
+
"step": 145
|
880 |
+
},
|
881 |
+
{
|
882 |
+
"epoch": 0.35,
|
883 |
+
"learning_rate": 0.00012028789665711085,
|
884 |
+
"loss": 0.8352,
|
885 |
+
"step": 146
|
886 |
+
},
|
887 |
+
{
|
888 |
+
"epoch": 0.35,
|
889 |
+
"learning_rate": 0.00011987805595403907,
|
890 |
+
"loss": 0.9483,
|
891 |
+
"step": 147
|
892 |
+
},
|
893 |
+
{
|
894 |
+
"epoch": 0.35,
|
895 |
+
"learning_rate": 0.00011947237609024377,
|
896 |
+
"loss": 0.8841,
|
897 |
+
"step": 148
|
898 |
+
},
|
899 |
+
{
|
900 |
+
"epoch": 0.36,
|
901 |
+
"learning_rate": 0.00011907078713518815,
|
902 |
+
"loss": 1.0176,
|
903 |
+
"step": 149
|
904 |
+
},
|
905 |
+
{
|
906 |
+
"epoch": 0.36,
|
907 |
+
"learning_rate": 0.00011867322079278597,
|
908 |
+
"loss": 0.9113,
|
909 |
+
"step": 150
|
910 |
+
},
|
911 |
+
{
|
912 |
+
"epoch": 0.36,
|
913 |
+
"learning_rate": 0.00011827961035261132,
|
914 |
+
"loss": 0.8683,
|
915 |
+
"step": 151
|
916 |
+
},
|
917 |
+
{
|
918 |
+
"epoch": 0.36,
|
919 |
+
"learning_rate": 0.0001178898906428769,
|
920 |
+
"loss": 0.8158,
|
921 |
+
"step": 152
|
922 |
+
},
|
923 |
+
{
|
924 |
+
"epoch": 0.37,
|
925 |
+
"learning_rate": 0.0001175039979851054,
|
926 |
+
"loss": 0.8146,
|
927 |
+
"step": 153
|
928 |
+
},
|
929 |
+
{
|
930 |
+
"epoch": 0.37,
|
931 |
+
"learning_rate": 0.00011712187015042266,
|
932 |
+
"loss": 0.8513,
|
933 |
+
"step": 154
|
934 |
+
},
|
935 |
+
{
|
936 |
+
"epoch": 0.37,
|
937 |
+
"learning_rate": 0.00011674344631740369,
|
938 |
+
"loss": 0.8071,
|
939 |
+
"step": 155
|
940 |
+
},
|
941 |
+
{
|
942 |
+
"epoch": 0.37,
|
943 |
+
"learning_rate": 0.00011636866703140783,
|
944 |
+
"loss": 0.8923,
|
945 |
+
"step": 156
|
946 |
+
},
|
947 |
+
{
|
948 |
+
"epoch": 0.38,
|
949 |
+
"learning_rate": 0.00011599747416534057,
|
950 |
+
"loss": 0.9082,
|
951 |
+
"step": 157
|
952 |
+
},
|
953 |
+
{
|
954 |
+
"epoch": 0.38,
|
955 |
+
"learning_rate": 0.00011562981088178324,
|
956 |
+
"loss": 0.8323,
|
957 |
+
"step": 158
|
958 |
+
},
|
959 |
+
{
|
960 |
+
"epoch": 0.38,
|
961 |
+
"learning_rate": 0.00011526562159643515,
|
962 |
+
"loss": 0.8079,
|
963 |
+
"step": 159
|
964 |
+
},
|
965 |
+
{
|
966 |
+
"epoch": 0.38,
|
967 |
+
"learning_rate": 0.00011490485194281395,
|
968 |
+
"loss": 0.8623,
|
969 |
+
"step": 160
|
970 |
+
},
|
971 |
+
{
|
972 |
+
"epoch": 0.39,
|
973 |
+
"learning_rate": 0.00011454744873816422,
|
974 |
+
"loss": 0.8465,
|
975 |
+
"step": 161
|
976 |
+
},
|
977 |
+
{
|
978 |
+
"epoch": 0.39,
|
979 |
+
"learning_rate": 0.0001141933599505248,
|
980 |
+
"loss": 0.9027,
|
981 |
+
"step": 162
|
982 |
+
},
|
983 |
+
{
|
984 |
+
"epoch": 0.39,
|
985 |
+
"learning_rate": 0.00011384253466690954,
|
986 |
+
"loss": 0.907,
|
987 |
+
"step": 163
|
988 |
+
},
|
989 |
+
{
|
990 |
+
"epoch": 0.39,
|
991 |
+
"learning_rate": 0.00011349492306255647,
|
992 |
+
"loss": 0.9152,
|
993 |
+
"step": 164
|
994 |
+
},
|
995 |
+
{
|
996 |
+
"epoch": 0.4,
|
997 |
+
"learning_rate": 0.0001131504763712036,
|
998 |
+
"loss": 0.7418,
|
999 |
+
"step": 165
|
1000 |
+
},
|
1001 |
+
{
|
1002 |
+
"epoch": 0.4,
|
1003 |
+
"learning_rate": 0.00011280914685635128,
|
1004 |
+
"loss": 0.8328,
|
1005 |
+
"step": 166
|
1006 |
+
},
|
1007 |
+
{
|
1008 |
+
"epoch": 0.4,
|
1009 |
+
"learning_rate": 0.0001124708877834722,
|
1010 |
+
"loss": 0.9287,
|
1011 |
+
"step": 167
|
1012 |
+
},
|
1013 |
+
{
|
1014 |
+
"epoch": 0.4,
|
1015 |
+
"learning_rate": 0.00011213565339313254,
|
1016 |
+
"loss": 0.7967,
|
1017 |
+
"step": 168
|
1018 |
+
},
|
1019 |
+
{
|
1020 |
+
"epoch": 0.41,
|
1021 |
+
"learning_rate": 0.00011180339887498949,
|
1022 |
+
"loss": 0.84,
|
1023 |
+
"step": 169
|
1024 |
+
},
|
1025 |
+
{
|
1026 |
+
"epoch": 0.41,
|
1027 |
+
"learning_rate": 0.00011147408034263073,
|
1028 |
+
"loss": 0.8149,
|
1029 |
+
"step": 170
|
1030 |
+
},
|
1031 |
+
{
|
1032 |
+
"epoch": 0.41,
|
1033 |
+
"learning_rate": 0.00011114765480922503,
|
1034 |
+
"loss": 0.8555,
|
1035 |
+
"step": 171
|
1036 |
+
},
|
1037 |
+
{
|
1038 |
+
"epoch": 0.41,
|
1039 |
+
"learning_rate": 0.00011082408016395194,
|
1040 |
+
"loss": 0.814,
|
1041 |
+
"step": 172
|
1042 |
+
},
|
1043 |
+
{
|
1044 |
+
"epoch": 0.41,
|
1045 |
+
"learning_rate": 0.00011050331514918246,
|
1046 |
+
"loss": 0.8139,
|
1047 |
+
"step": 173
|
1048 |
+
},
|
1049 |
+
{
|
1050 |
+
"epoch": 0.42,
|
1051 |
+
"learning_rate": 0.0001101853193383817,
|
1052 |
+
"loss": 0.885,
|
1053 |
+
"step": 174
|
1054 |
+
},
|
1055 |
+
{
|
1056 |
+
"epoch": 0.42,
|
1057 |
+
"learning_rate": 0.00010987005311470715,
|
1058 |
+
"loss": 0.7682,
|
1059 |
+
"step": 175
|
1060 |
+
},
|
1061 |
+
{
|
1062 |
+
"epoch": 0.42,
|
1063 |
+
"learning_rate": 0.00010955747765027683,
|
1064 |
+
"loss": 0.8266,
|
1065 |
+
"step": 176
|
1066 |
+
},
|
1067 |
+
{
|
1068 |
+
"epoch": 0.42,
|
1069 |
+
"learning_rate": 0.00010924755488608232,
|
1070 |
+
"loss": 0.8699,
|
1071 |
+
"step": 177
|
1072 |
+
},
|
1073 |
+
{
|
1074 |
+
"epoch": 0.43,
|
1075 |
+
"learning_rate": 0.00010894024751252352,
|
1076 |
+
"loss": 0.957,
|
1077 |
+
"step": 178
|
1078 |
+
},
|
1079 |
+
{
|
1080 |
+
"epoch": 0.43,
|
1081 |
+
"learning_rate": 0.00010863551895054227,
|
1082 |
+
"loss": 0.854,
|
1083 |
+
"step": 179
|
1084 |
+
},
|
1085 |
+
{
|
1086 |
+
"epoch": 0.43,
|
1087 |
+
"learning_rate": 0.00010833333333333333,
|
1088 |
+
"loss": 0.7239,
|
1089 |
+
"step": 180
|
1090 |
+
},
|
1091 |
+
{
|
1092 |
+
"epoch": 0.43,
|
1093 |
+
"learning_rate": 0.00010803365548861171,
|
1094 |
+
"loss": 0.7825,
|
1095 |
+
"step": 181
|
1096 |
+
},
|
1097 |
+
{
|
1098 |
+
"epoch": 0.44,
|
1099 |
+
"learning_rate": 0.00010773645092141682,
|
1100 |
+
"loss": 0.8531,
|
1101 |
+
"step": 182
|
1102 |
+
},
|
1103 |
+
{
|
1104 |
+
"epoch": 0.44,
|
1105 |
+
"learning_rate": 0.00010744168579743401,
|
1106 |
+
"loss": 0.7602,
|
1107 |
+
"step": 183
|
1108 |
+
},
|
1109 |
+
{
|
1110 |
+
"epoch": 0.44,
|
1111 |
+
"learning_rate": 0.0001071493269268154,
|
1112 |
+
"loss": 0.8768,
|
1113 |
+
"step": 184
|
1114 |
+
},
|
1115 |
+
{
|
1116 |
+
"epoch": 0.44,
|
1117 |
+
"learning_rate": 0.00010685934174848223,
|
1118 |
+
"loss": 0.8294,
|
1119 |
+
"step": 185
|
1120 |
+
},
|
1121 |
+
{
|
1122 |
+
"epoch": 0.45,
|
1123 |
+
"learning_rate": 0.00010657169831489234,
|
1124 |
+
"loss": 0.8872,
|
1125 |
+
"step": 186
|
1126 |
+
},
|
1127 |
+
{
|
1128 |
+
"epoch": 0.45,
|
1129 |
+
"learning_rate": 0.0001062863652772559,
|
1130 |
+
"loss": 0.7016,
|
1131 |
+
"step": 187
|
1132 |
+
},
|
1133 |
+
{
|
1134 |
+
"epoch": 0.45,
|
1135 |
+
"learning_rate": 0.00010600331187118435,
|
1136 |
+
"loss": 0.8942,
|
1137 |
+
"step": 188
|
1138 |
+
},
|
1139 |
+
{
|
1140 |
+
"epoch": 0.45,
|
1141 |
+
"learning_rate": 0.00010572250790275775,
|
1142 |
+
"loss": 0.7416,
|
1143 |
+
"step": 189
|
1144 |
+
},
|
1145 |
+
{
|
1146 |
+
"epoch": 0.46,
|
1147 |
+
"learning_rate": 0.00010544392373499565,
|
1148 |
+
"loss": 0.8104,
|
1149 |
+
"step": 190
|
1150 |
+
}
|
1151 |
+
],
|
1152 |
+
"logging_steps": 1,
|
1153 |
+
"max_steps": 417,
|
1154 |
+
"num_train_epochs": 1,
|
1155 |
+
"save_steps": 10,
|
1156 |
+
"total_flos": 6.162417152478413e+16,
|
1157 |
+
"trial_name": null,
|
1158 |
+
"trial_params": null
|
1159 |
+
}
|
checkpoint-190/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:482256ef65b59af088490f9e3870f1b868a90992cd6294900bd43d13ef410480
|
3 |
+
size 4536
|
checkpoint-200/README.md
ADDED
@@ -0,0 +1,220 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: peft
|
3 |
+
base_model: unsloth/llama-2-7b
|
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 |
+
|
201 |
+
|
202 |
+
## Training procedure
|
203 |
+
|
204 |
+
|
205 |
+
The following `bitsandbytes` quantization config was used during training:
|
206 |
+
- quant_method: bitsandbytes
|
207 |
+
- load_in_8bit: False
|
208 |
+
- load_in_4bit: True
|
209 |
+
- llm_int8_threshold: 6.0
|
210 |
+
- llm_int8_skip_modules: None
|
211 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
212 |
+
- llm_int8_has_fp16_weight: False
|
213 |
+
- bnb_4bit_quant_type: nf4
|
214 |
+
- bnb_4bit_use_double_quant: True
|
215 |
+
- bnb_4bit_compute_dtype: bfloat16
|
216 |
+
|
217 |
+
### Framework versions
|
218 |
+
|
219 |
+
|
220 |
+
- PEFT 0.6.2
|
checkpoint-200/adapter_config.json
ADDED
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "unsloth/llama-2-7b",
|
5 |
+
"bias": "none",
|
6 |
+
"fan_in_fan_out": false,
|
7 |
+
"inference_mode": true,
|
8 |
+
"init_lora_weights": true,
|
9 |
+
"layers_pattern": null,
|
10 |
+
"layers_to_transform": null,
|
11 |
+
"lora_alpha": 32,
|
12 |
+
"lora_dropout": 0,
|
13 |
+
"modules_to_save": null,
|
14 |
+
"peft_type": "LORA",
|
15 |
+
"r": 16,
|
16 |
+
"rank_pattern": {},
|
17 |
+
"revision": null,
|
18 |
+
"target_modules": [
|
19 |
+
"o_proj",
|
20 |
+
"up_proj",
|
21 |
+
"down_proj",
|
22 |
+
"q_proj",
|
23 |
+
"k_proj",
|
24 |
+
"v_proj",
|
25 |
+
"gate_proj"
|
26 |
+
],
|
27 |
+
"task_type": "CAUSAL_LM"
|
28 |
+
}
|
checkpoint-200/adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:79584014796fb14dcc8275c797d29df72f7b2dc5cc4b7b8a2fbfa29fdbc02ca3
|
3 |
+
size 159967880
|
checkpoint-200/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c1175f1558372bc8497b475ca5b1f9f8b7d3c06b01c5ddadbf6197f16fd66e4c
|
3 |
+
size 80630612
|
checkpoint-200/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:203e9bfabd925cb4ec7129d24877156fcee87215187c35a867e358e56a9425a4
|
3 |
+
size 14244
|
checkpoint-200/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:aa613265bd9842961d3a0187165a5848341c0e2d75f3b3120add96d3b9bbb5af
|
3 |
+
size 1064
|
checkpoint-200/trainer_state.json
ADDED
@@ -0,0 +1,1219 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.47961630695443647,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 200,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.0,
|
13 |
+
"learning_rate": 0.00013,
|
14 |
+
"loss": 1.1241,
|
15 |
+
"step": 1
|
16 |
+
},
|
17 |
+
{
|
18 |
+
"epoch": 0.0,
|
19 |
+
"learning_rate": 0.00026,
|
20 |
+
"loss": 1.0107,
|
21 |
+
"step": 2
|
22 |
+
},
|
23 |
+
{
|
24 |
+
"epoch": 0.01,
|
25 |
+
"learning_rate": 0.00039,
|
26 |
+
"loss": 1.1086,
|
27 |
+
"step": 3
|
28 |
+
},
|
29 |
+
{
|
30 |
+
"epoch": 0.01,
|
31 |
+
"learning_rate": 0.00052,
|
32 |
+
"loss": 1.0044,
|
33 |
+
"step": 4
|
34 |
+
},
|
35 |
+
{
|
36 |
+
"epoch": 0.01,
|
37 |
+
"learning_rate": 0.00065,
|
38 |
+
"loss": 1.0496,
|
39 |
+
"step": 5
|
40 |
+
},
|
41 |
+
{
|
42 |
+
"epoch": 0.01,
|
43 |
+
"learning_rate": 0.0005933661039639299,
|
44 |
+
"loss": 1.0199,
|
45 |
+
"step": 6
|
46 |
+
},
|
47 |
+
{
|
48 |
+
"epoch": 0.02,
|
49 |
+
"learning_rate": 0.0005493502655735357,
|
50 |
+
"loss": 1.0198,
|
51 |
+
"step": 7
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.02,
|
55 |
+
"learning_rate": 0.0005138701197773616,
|
56 |
+
"loss": 0.969,
|
57 |
+
"step": 8
|
58 |
+
},
|
59 |
+
{
|
60 |
+
"epoch": 0.02,
|
61 |
+
"learning_rate": 0.0004844813951249544,
|
62 |
+
"loss": 0.9383,
|
63 |
+
"step": 9
|
64 |
+
},
|
65 |
+
{
|
66 |
+
"epoch": 0.02,
|
67 |
+
"learning_rate": 0.0004596194077712558,
|
68 |
+
"loss": 0.8776,
|
69 |
+
"step": 10
|
70 |
+
},
|
71 |
+
{
|
72 |
+
"epoch": 0.03,
|
73 |
+
"learning_rate": 0.0004382299106011073,
|
74 |
+
"loss": 1.0173,
|
75 |
+
"step": 11
|
76 |
+
},
|
77 |
+
{
|
78 |
+
"epoch": 0.03,
|
79 |
+
"learning_rate": 0.0004195731958391368,
|
80 |
+
"loss": 1.1173,
|
81 |
+
"step": 12
|
82 |
+
},
|
83 |
+
{
|
84 |
+
"epoch": 0.03,
|
85 |
+
"learning_rate": 0.0004031128874149274,
|
86 |
+
"loss": 1.0876,
|
87 |
+
"step": 13
|
88 |
+
},
|
89 |
+
{
|
90 |
+
"epoch": 0.03,
|
91 |
+
"learning_rate": 0.0003884492980336779,
|
92 |
+
"loss": 1.0524,
|
93 |
+
"step": 14
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 0.04,
|
97 |
+
"learning_rate": 0.0003752776749732568,
|
98 |
+
"loss": 0.8953,
|
99 |
+
"step": 15
|
100 |
+
},
|
101 |
+
{
|
102 |
+
"epoch": 0.04,
|
103 |
+
"learning_rate": 0.00036336104634371584,
|
104 |
+
"loss": 1.1335,
|
105 |
+
"step": 16
|
106 |
+
},
|
107 |
+
{
|
108 |
+
"epoch": 0.04,
|
109 |
+
"learning_rate": 0.00035251199395531623,
|
110 |
+
"loss": 0.9837,
|
111 |
+
"step": 17
|
112 |
+
},
|
113 |
+
{
|
114 |
+
"epoch": 0.04,
|
115 |
+
"learning_rate": 0.00034258007985157445,
|
116 |
+
"loss": 0.9707,
|
117 |
+
"step": 18
|
118 |
+
},
|
119 |
+
{
|
120 |
+
"epoch": 0.05,
|
121 |
+
"learning_rate": 0.0003334429644276751,
|
122 |
+
"loss": 0.9149,
|
123 |
+
"step": 19
|
124 |
+
},
|
125 |
+
{
|
126 |
+
"epoch": 0.05,
|
127 |
+
"learning_rate": 0.000325,
|
128 |
+
"loss": 1.0043,
|
129 |
+
"step": 20
|
130 |
+
},
|
131 |
+
{
|
132 |
+
"epoch": 0.05,
|
133 |
+
"learning_rate": 0.00031716752370827323,
|
134 |
+
"loss": 1.001,
|
135 |
+
"step": 21
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 0.05,
|
139 |
+
"learning_rate": 0.00030987534150481746,
|
140 |
+
"loss": 1.0395,
|
141 |
+
"step": 22
|
142 |
+
},
|
143 |
+
{
|
144 |
+
"epoch": 0.06,
|
145 |
+
"learning_rate": 0.000303064062678102,
|
146 |
+
"loss": 0.8718,
|
147 |
+
"step": 23
|
148 |
+
},
|
149 |
+
{
|
150 |
+
"epoch": 0.06,
|
151 |
+
"learning_rate": 0.00029668305198196496,
|
152 |
+
"loss": 1.1114,
|
153 |
+
"step": 24
|
154 |
+
},
|
155 |
+
{
|
156 |
+
"epoch": 0.06,
|
157 |
+
"learning_rate": 0.00029068883707497264,
|
158 |
+
"loss": 0.7765,
|
159 |
+
"step": 25
|
160 |
+
},
|
161 |
+
{
|
162 |
+
"epoch": 0.06,
|
163 |
+
"learning_rate": 0.0002850438562747845,
|
164 |
+
"loss": 0.9522,
|
165 |
+
"step": 26
|
166 |
+
},
|
167 |
+
{
|
168 |
+
"epoch": 0.06,
|
169 |
+
"learning_rate": 0.00027971546389275785,
|
170 |
+
"loss": 0.9588,
|
171 |
+
"step": 27
|
172 |
+
},
|
173 |
+
{
|
174 |
+
"epoch": 0.07,
|
175 |
+
"learning_rate": 0.00027467513278676785,
|
176 |
+
"loss": 1.0313,
|
177 |
+
"step": 28
|
178 |
+
},
|
179 |
+
{
|
180 |
+
"epoch": 0.07,
|
181 |
+
"learning_rate": 0.0002698978095246549,
|
182 |
+
"loss": 0.9338,
|
183 |
+
"step": 29
|
184 |
+
},
|
185 |
+
{
|
186 |
+
"epoch": 0.07,
|
187 |
+
"learning_rate": 0.000265361388801511,
|
188 |
+
"loss": 0.892,
|
189 |
+
"step": 30
|
190 |
+
},
|
191 |
+
{
|
192 |
+
"epoch": 0.07,
|
193 |
+
"learning_rate": 0.00026104628189331215,
|
194 |
+
"loss": 0.893,
|
195 |
+
"step": 31
|
196 |
+
},
|
197 |
+
{
|
198 |
+
"epoch": 0.08,
|
199 |
+
"learning_rate": 0.0002569350598886808,
|
200 |
+
"loss": 0.8983,
|
201 |
+
"step": 32
|
202 |
+
},
|
203 |
+
{
|
204 |
+
"epoch": 0.08,
|
205 |
+
"learning_rate": 0.00025301215685249496,
|
206 |
+
"loss": 0.9277,
|
207 |
+
"step": 33
|
208 |
+
},
|
209 |
+
{
|
210 |
+
"epoch": 0.08,
|
211 |
+
"learning_rate": 0.00024926362137539537,
|
212 |
+
"loss": 0.8962,
|
213 |
+
"step": 34
|
214 |
+
},
|
215 |
+
{
|
216 |
+
"epoch": 0.08,
|
217 |
+
"learning_rate": 0.00024567690745599767,
|
218 |
+
"loss": 0.9124,
|
219 |
+
"step": 35
|
220 |
+
},
|
221 |
+
{
|
222 |
+
"epoch": 0.09,
|
223 |
+
"learning_rate": 0.0002422406975624772,
|
224 |
+
"loss": 0.9535,
|
225 |
+
"step": 36
|
226 |
+
},
|
227 |
+
{
|
228 |
+
"epoch": 0.09,
|
229 |
+
"learning_rate": 0.00023894475218048754,
|
230 |
+
"loss": 0.9019,
|
231 |
+
"step": 37
|
232 |
+
},
|
233 |
+
{
|
234 |
+
"epoch": 0.09,
|
235 |
+
"learning_rate": 0.0002357797812857538,
|
236 |
+
"loss": 1.024,
|
237 |
+
"step": 38
|
238 |
+
},
|
239 |
+
{
|
240 |
+
"epoch": 0.09,
|
241 |
+
"learning_rate": 0.00023273733406281566,
|
242 |
+
"loss": 0.8549,
|
243 |
+
"step": 39
|
244 |
+
},
|
245 |
+
{
|
246 |
+
"epoch": 0.1,
|
247 |
+
"learning_rate": 0.0002298097038856279,
|
248 |
+
"loss": 1.0489,
|
249 |
+
"step": 40
|
250 |
+
},
|
251 |
+
{
|
252 |
+
"epoch": 0.1,
|
253 |
+
"learning_rate": 0.00022698984612511293,
|
254 |
+
"loss": 0.751,
|
255 |
+
"step": 41
|
256 |
+
},
|
257 |
+
{
|
258 |
+
"epoch": 0.1,
|
259 |
+
"learning_rate": 0.00022427130678626507,
|
260 |
+
"loss": 0.834,
|
261 |
+
"step": 42
|
262 |
+
},
|
263 |
+
{
|
264 |
+
"epoch": 0.1,
|
265 |
+
"learning_rate": 0.00022164816032790388,
|
266 |
+
"loss": 0.889,
|
267 |
+
"step": 43
|
268 |
+
},
|
269 |
+
{
|
270 |
+
"epoch": 0.11,
|
271 |
+
"learning_rate": 0.00021911495530055366,
|
272 |
+
"loss": 1.0103,
|
273 |
+
"step": 44
|
274 |
+
},
|
275 |
+
{
|
276 |
+
"epoch": 0.11,
|
277 |
+
"learning_rate": 0.00021666666666666666,
|
278 |
+
"loss": 0.8766,
|
279 |
+
"step": 45
|
280 |
+
},
|
281 |
+
{
|
282 |
+
"epoch": 0.11,
|
283 |
+
"learning_rate": 0.0002142986538536308,
|
284 |
+
"loss": 0.8181,
|
285 |
+
"step": 46
|
286 |
+
},
|
287 |
+
{
|
288 |
+
"epoch": 0.11,
|
289 |
+
"learning_rate": 0.0002120066237423687,
|
290 |
+
"loss": 0.8754,
|
291 |
+
"step": 47
|
292 |
+
},
|
293 |
+
{
|
294 |
+
"epoch": 0.12,
|
295 |
+
"learning_rate": 0.0002097865979195684,
|
296 |
+
"loss": 0.9038,
|
297 |
+
"step": 48
|
298 |
+
},
|
299 |
+
{
|
300 |
+
"epoch": 0.12,
|
301 |
+
"learning_rate": 0.00020763488362498048,
|
302 |
+
"loss": 0.8646,
|
303 |
+
"step": 49
|
304 |
+
},
|
305 |
+
{
|
306 |
+
"epoch": 0.12,
|
307 |
+
"learning_rate": 0.00020554804791094464,
|
308 |
+
"loss": 0.8836,
|
309 |
+
"step": 50
|
310 |
+
},
|
311 |
+
{
|
312 |
+
"epoch": 0.12,
|
313 |
+
"learning_rate": 0.0002035228946026736,
|
314 |
+
"loss": 0.9962,
|
315 |
+
"step": 51
|
316 |
+
},
|
317 |
+
{
|
318 |
+
"epoch": 0.12,
|
319 |
+
"learning_rate": 0.0002015564437074637,
|
320 |
+
"loss": 0.8835,
|
321 |
+
"step": 52
|
322 |
+
},
|
323 |
+
{
|
324 |
+
"epoch": 0.13,
|
325 |
+
"learning_rate": 0.00019964591297103414,
|
326 |
+
"loss": 0.9196,
|
327 |
+
"step": 53
|
328 |
+
},
|
329 |
+
{
|
330 |
+
"epoch": 0.13,
|
331 |
+
"learning_rate": 0.00019778870132130996,
|
332 |
+
"loss": 0.8995,
|
333 |
+
"step": 54
|
334 |
+
},
|
335 |
+
{
|
336 |
+
"epoch": 0.13,
|
337 |
+
"learning_rate": 0.00019598237397554634,
|
338 |
+
"loss": 1.0178,
|
339 |
+
"step": 55
|
340 |
+
},
|
341 |
+
{
|
342 |
+
"epoch": 0.13,
|
343 |
+
"learning_rate": 0.00019422464901683895,
|
344 |
+
"loss": 0.9395,
|
345 |
+
"step": 56
|
346 |
+
},
|
347 |
+
{
|
348 |
+
"epoch": 0.14,
|
349 |
+
"learning_rate": 0.00019251338527170498,
|
350 |
+
"loss": 0.9882,
|
351 |
+
"step": 57
|
352 |
+
},
|
353 |
+
{
|
354 |
+
"epoch": 0.14,
|
355 |
+
"learning_rate": 0.00019084657134227863,
|
356 |
+
"loss": 0.9274,
|
357 |
+
"step": 58
|
358 |
+
},
|
359 |
+
{
|
360 |
+
"epoch": 0.14,
|
361 |
+
"learning_rate": 0.00018922231566536414,
|
362 |
+
"loss": 0.9517,
|
363 |
+
"step": 59
|
364 |
+
},
|
365 |
+
{
|
366 |
+
"epoch": 0.14,
|
367 |
+
"learning_rate": 0.0001876388374866284,
|
368 |
+
"loss": 0.865,
|
369 |
+
"step": 60
|
370 |
+
},
|
371 |
+
{
|
372 |
+
"epoch": 0.15,
|
373 |
+
"learning_rate": 0.00018609445865200715,
|
374 |
+
"loss": 0.9314,
|
375 |
+
"step": 61
|
376 |
+
},
|
377 |
+
{
|
378 |
+
"epoch": 0.15,
|
379 |
+
"learning_rate": 0.00018458759613029606,
|
380 |
+
"loss": 0.9224,
|
381 |
+
"step": 62
|
382 |
+
},
|
383 |
+
{
|
384 |
+
"epoch": 0.15,
|
385 |
+
"learning_rate": 0.00018311675519117857,
|
386 |
+
"loss": 0.788,
|
387 |
+
"step": 63
|
388 |
+
},
|
389 |
+
{
|
390 |
+
"epoch": 0.15,
|
391 |
+
"learning_rate": 0.00018168052317185792,
|
392 |
+
"loss": 0.9739,
|
393 |
+
"step": 64
|
394 |
+
},
|
395 |
+
{
|
396 |
+
"epoch": 0.16,
|
397 |
+
"learning_rate": 0.00018027756377319947,
|
398 |
+
"loss": 0.9419,
|
399 |
+
"step": 65
|
400 |
+
},
|
401 |
+
{
|
402 |
+
"epoch": 0.16,
|
403 |
+
"learning_rate": 0.0001789066118330336,
|
404 |
+
"loss": 0.8772,
|
405 |
+
"step": 66
|
406 |
+
},
|
407 |
+
{
|
408 |
+
"epoch": 0.16,
|
409 |
+
"learning_rate": 0.00017756646853014972,
|
410 |
+
"loss": 0.8707,
|
411 |
+
"step": 67
|
412 |
+
},
|
413 |
+
{
|
414 |
+
"epoch": 0.16,
|
415 |
+
"learning_rate": 0.00017625599697765812,
|
416 |
+
"loss": 0.8089,
|
417 |
+
"step": 68
|
418 |
+
},
|
419 |
+
{
|
420 |
+
"epoch": 0.17,
|
421 |
+
"learning_rate": 0.00017497411816890378,
|
422 |
+
"loss": 0.9303,
|
423 |
+
"step": 69
|
424 |
+
},
|
425 |
+
{
|
426 |
+
"epoch": 0.17,
|
427 |
+
"learning_rate": 0.00017371980724307585,
|
428 |
+
"loss": 0.9161,
|
429 |
+
"step": 70
|
430 |
+
},
|
431 |
+
{
|
432 |
+
"epoch": 0.17,
|
433 |
+
"learning_rate": 0.00017249209004113945,
|
434 |
+
"loss": 0.9064,
|
435 |
+
"step": 71
|
436 |
+
},
|
437 |
+
{
|
438 |
+
"epoch": 0.17,
|
439 |
+
"learning_rate": 0.00017129003992578723,
|
440 |
+
"loss": 1.0988,
|
441 |
+
"step": 72
|
442 |
+
},
|
443 |
+
{
|
444 |
+
"epoch": 0.18,
|
445 |
+
"learning_rate": 0.00017011277484181944,
|
446 |
+
"loss": 0.9804,
|
447 |
+
"step": 73
|
448 |
+
},
|
449 |
+
{
|
450 |
+
"epoch": 0.18,
|
451 |
+
"learning_rate": 0.0001689594545957618,
|
452 |
+
"loss": 0.8382,
|
453 |
+
"step": 74
|
454 |
+
},
|
455 |
+
{
|
456 |
+
"epoch": 0.18,
|
457 |
+
"learning_rate": 0.00016782927833565472,
|
458 |
+
"loss": 0.9632,
|
459 |
+
"step": 75
|
460 |
+
},
|
461 |
+
{
|
462 |
+
"epoch": 0.18,
|
463 |
+
"learning_rate": 0.00016672148221383754,
|
464 |
+
"loss": 0.9494,
|
465 |
+
"step": 76
|
466 |
+
},
|
467 |
+
{
|
468 |
+
"epoch": 0.18,
|
469 |
+
"learning_rate": 0.00016563533721722828,
|
470 |
+
"loss": 0.9253,
|
471 |
+
"step": 77
|
472 |
+
},
|
473 |
+
{
|
474 |
+
"epoch": 0.19,
|
475 |
+
"learning_rate": 0.0001645701471510958,
|
476 |
+
"loss": 0.9143,
|
477 |
+
"step": 78
|
478 |
+
},
|
479 |
+
{
|
480 |
+
"epoch": 0.19,
|
481 |
+
"learning_rate": 0.00016352524676365398,
|
482 |
+
"loss": 0.8907,
|
483 |
+
"step": 79
|
484 |
+
},
|
485 |
+
{
|
486 |
+
"epoch": 0.19,
|
487 |
+
"learning_rate": 0.0001625,
|
488 |
+
"loss": 0.9748,
|
489 |
+
"step": 80
|
490 |
+
},
|
491 |
+
{
|
492 |
+
"epoch": 0.19,
|
493 |
+
"learning_rate": 0.00016149379837498482,
|
494 |
+
"loss": 0.893,
|
495 |
+
"step": 81
|
496 |
+
},
|
497 |
+
{
|
498 |
+
"epoch": 0.2,
|
499 |
+
"learning_rate": 0.00016050605945555833,
|
500 |
+
"loss": 0.839,
|
501 |
+
"step": 82
|
502 |
+
},
|
503 |
+
{
|
504 |
+
"epoch": 0.2,
|
505 |
+
"learning_rate": 0.0001595362254439902,
|
506 |
+
"loss": 0.9276,
|
507 |
+
"step": 83
|
508 |
+
},
|
509 |
+
{
|
510 |
+
"epoch": 0.2,
|
511 |
+
"learning_rate": 0.00015858376185413662,
|
512 |
+
"loss": 0.8758,
|
513 |
+
"step": 84
|
514 |
+
},
|
515 |
+
{
|
516 |
+
"epoch": 0.2,
|
517 |
+
"learning_rate": 0.00015764815627361642,
|
518 |
+
"loss": 0.9125,
|
519 |
+
"step": 85
|
520 |
+
},
|
521 |
+
{
|
522 |
+
"epoch": 0.21,
|
523 |
+
"learning_rate": 0.00015672891720538393,
|
524 |
+
"loss": 0.955,
|
525 |
+
"step": 86
|
526 |
+
},
|
527 |
+
{
|
528 |
+
"epoch": 0.21,
|
529 |
+
"learning_rate": 0.00015582557298274985,
|
530 |
+
"loss": 0.9104,
|
531 |
+
"step": 87
|
532 |
+
},
|
533 |
+
{
|
534 |
+
"epoch": 0.21,
|
535 |
+
"learning_rate": 0.00015493767075240873,
|
536 |
+
"loss": 0.8861,
|
537 |
+
"step": 88
|
538 |
+
},
|
539 |
+
{
|
540 |
+
"epoch": 0.21,
|
541 |
+
"learning_rate": 0.0001540647755204926,
|
542 |
+
"loss": 0.9693,
|
543 |
+
"step": 89
|
544 |
+
},
|
545 |
+
{
|
546 |
+
"epoch": 0.22,
|
547 |
+
"learning_rate": 0.0001532064692570853,
|
548 |
+
"loss": 0.7245,
|
549 |
+
"step": 90
|
550 |
+
},
|
551 |
+
{
|
552 |
+
"epoch": 0.22,
|
553 |
+
"learning_rate": 0.000152362350055011,
|
554 |
+
"loss": 0.7523,
|
555 |
+
"step": 91
|
556 |
+
},
|
557 |
+
{
|
558 |
+
"epoch": 0.22,
|
559 |
+
"learning_rate": 0.000151532031339051,
|
560 |
+
"loss": 0.8522,
|
561 |
+
"step": 92
|
562 |
+
},
|
563 |
+
{
|
564 |
+
"epoch": 0.22,
|
565 |
+
"learning_rate": 0.00015071514112205468,
|
566 |
+
"loss": 0.9273,
|
567 |
+
"step": 93
|
568 |
+
},
|
569 |
+
{
|
570 |
+
"epoch": 0.23,
|
571 |
+
"learning_rate": 0.0001499113213046938,
|
572 |
+
"loss": 1.0303,
|
573 |
+
"step": 94
|
574 |
+
},
|
575 |
+
{
|
576 |
+
"epoch": 0.23,
|
577 |
+
"learning_rate": 0.00014912022701586513,
|
578 |
+
"loss": 0.9273,
|
579 |
+
"step": 95
|
580 |
+
},
|
581 |
+
{
|
582 |
+
"epoch": 0.23,
|
583 |
+
"learning_rate": 0.00014834152599098248,
|
584 |
+
"loss": 0.9071,
|
585 |
+
"step": 96
|
586 |
+
},
|
587 |
+
{
|
588 |
+
"epoch": 0.23,
|
589 |
+
"learning_rate": 0.00014757489798561242,
|
590 |
+
"loss": 0.954,
|
591 |
+
"step": 97
|
592 |
+
},
|
593 |
+
{
|
594 |
+
"epoch": 0.24,
|
595 |
+
"learning_rate": 0.00014682003422210332,
|
596 |
+
"loss": 0.7897,
|
597 |
+
"step": 98
|
598 |
+
},
|
599 |
+
{
|
600 |
+
"epoch": 0.24,
|
601 |
+
"learning_rate": 0.00014607663686703578,
|
602 |
+
"loss": 0.9045,
|
603 |
+
"step": 99
|
604 |
+
},
|
605 |
+
{
|
606 |
+
"epoch": 0.24,
|
607 |
+
"learning_rate": 0.00014534441853748632,
|
608 |
+
"loss": 0.7919,
|
609 |
+
"step": 100
|
610 |
+
},
|
611 |
+
{
|
612 |
+
"epoch": 0.24,
|
613 |
+
"learning_rate": 0.00014462310183424506,
|
614 |
+
"loss": 0.7449,
|
615 |
+
"step": 101
|
616 |
+
},
|
617 |
+
{
|
618 |
+
"epoch": 0.24,
|
619 |
+
"learning_rate": 0.0001439124189002655,
|
620 |
+
"loss": 0.8953,
|
621 |
+
"step": 102
|
622 |
+
},
|
623 |
+
{
|
624 |
+
"epoch": 0.25,
|
625 |
+
"learning_rate": 0.0001432121110027503,
|
626 |
+
"loss": 0.974,
|
627 |
+
"step": 103
|
628 |
+
},
|
629 |
+
{
|
630 |
+
"epoch": 0.25,
|
631 |
+
"learning_rate": 0.00014252192813739225,
|
632 |
+
"loss": 0.959,
|
633 |
+
"step": 104
|
634 |
+
},
|
635 |
+
{
|
636 |
+
"epoch": 0.25,
|
637 |
+
"learning_rate": 0.00014184162865339505,
|
638 |
+
"loss": 0.8767,
|
639 |
+
"step": 105
|
640 |
+
},
|
641 |
+
{
|
642 |
+
"epoch": 0.25,
|
643 |
+
"learning_rate": 0.00014117097889799755,
|
644 |
+
"loss": 0.9206,
|
645 |
+
"step": 106
|
646 |
+
},
|
647 |
+
{
|
648 |
+
"epoch": 0.26,
|
649 |
+
"learning_rate": 0.000140509752879313,
|
650 |
+
"loss": 0.8096,
|
651 |
+
"step": 107
|
652 |
+
},
|
653 |
+
{
|
654 |
+
"epoch": 0.26,
|
655 |
+
"learning_rate": 0.00013985773194637893,
|
656 |
+
"loss": 0.9726,
|
657 |
+
"step": 108
|
658 |
+
},
|
659 |
+
{
|
660 |
+
"epoch": 0.26,
|
661 |
+
"learning_rate": 0.00013921470448538878,
|
662 |
+
"loss": 0.7764,
|
663 |
+
"step": 109
|
664 |
+
},
|
665 |
+
{
|
666 |
+
"epoch": 0.26,
|
667 |
+
"learning_rate": 0.00013858046563114675,
|
668 |
+
"loss": 0.8414,
|
669 |
+
"step": 110
|
670 |
+
},
|
671 |
+
{
|
672 |
+
"epoch": 0.27,
|
673 |
+
"learning_rate": 0.0001379548169928529,
|
674 |
+
"loss": 0.9365,
|
675 |
+
"step": 111
|
676 |
+
},
|
677 |
+
{
|
678 |
+
"epoch": 0.27,
|
679 |
+
"learning_rate": 0.00013733756639338393,
|
680 |
+
"loss": 0.9857,
|
681 |
+
"step": 112
|
682 |
+
},
|
683 |
+
{
|
684 |
+
"epoch": 0.27,
|
685 |
+
"learning_rate": 0.00013672852762129314,
|
686 |
+
"loss": 0.8209,
|
687 |
+
"step": 113
|
688 |
+
},
|
689 |
+
{
|
690 |
+
"epoch": 0.27,
|
691 |
+
"learning_rate": 0.00013612752019480102,
|
692 |
+
"loss": 0.9954,
|
693 |
+
"step": 114
|
694 |
+
},
|
695 |
+
{
|
696 |
+
"epoch": 0.28,
|
697 |
+
"learning_rate": 0.0001355343691370986,
|
698 |
+
"loss": 0.9425,
|
699 |
+
"step": 115
|
700 |
+
},
|
701 |
+
{
|
702 |
+
"epoch": 0.28,
|
703 |
+
"learning_rate": 0.00013494890476232745,
|
704 |
+
"loss": 0.9199,
|
705 |
+
"step": 116
|
706 |
+
},
|
707 |
+
{
|
708 |
+
"epoch": 0.28,
|
709 |
+
"learning_rate": 0.0001343709624716425,
|
710 |
+
"loss": 1.0011,
|
711 |
+
"step": 117
|
712 |
+
},
|
713 |
+
{
|
714 |
+
"epoch": 0.28,
|
715 |
+
"learning_rate": 0.00013380038255880045,
|
716 |
+
"loss": 0.9335,
|
717 |
+
"step": 118
|
718 |
+
},
|
719 |
+
{
|
720 |
+
"epoch": 0.29,
|
721 |
+
"learning_rate": 0.000133237010024753,
|
722 |
+
"loss": 1.0612,
|
723 |
+
"step": 119
|
724 |
+
},
|
725 |
+
{
|
726 |
+
"epoch": 0.29,
|
727 |
+
"learning_rate": 0.0001326806944007555,
|
728 |
+
"loss": 0.8794,
|
729 |
+
"step": 120
|
730 |
+
},
|
731 |
+
{
|
732 |
+
"epoch": 0.29,
|
733 |
+
"learning_rate": 0.00013213128957953303,
|
734 |
+
"loss": 0.8557,
|
735 |
+
"step": 121
|
736 |
+
},
|
737 |
+
{
|
738 |
+
"epoch": 0.29,
|
739 |
+
"learning_rate": 0.00013158865365407385,
|
740 |
+
"loss": 0.931,
|
741 |
+
"step": 122
|
742 |
+
},
|
743 |
+
{
|
744 |
+
"epoch": 0.29,
|
745 |
+
"learning_rate": 0.00013105264876364566,
|
746 |
+
"loss": 0.9648,
|
747 |
+
"step": 123
|
748 |
+
},
|
749 |
+
{
|
750 |
+
"epoch": 0.3,
|
751 |
+
"learning_rate": 0.00013052314094665608,
|
752 |
+
"loss": 0.8448,
|
753 |
+
"step": 124
|
754 |
+
},
|
755 |
+
{
|
756 |
+
"epoch": 0.3,
|
757 |
+
"learning_rate": 0.00013,
|
758 |
+
"loss": 0.9247,
|
759 |
+
"step": 125
|
760 |
+
},
|
761 |
+
{
|
762 |
+
"epoch": 0.3,
|
763 |
+
"learning_rate": 0.0001294830993445593,
|
764 |
+
"loss": 0.9537,
|
765 |
+
"step": 126
|
766 |
+
},
|
767 |
+
{
|
768 |
+
"epoch": 0.3,
|
769 |
+
"learning_rate": 0.00012897231589653857,
|
770 |
+
"loss": 0.8049,
|
771 |
+
"step": 127
|
772 |
+
},
|
773 |
+
{
|
774 |
+
"epoch": 0.31,
|
775 |
+
"learning_rate": 0.0001284675299443404,
|
776 |
+
"loss": 0.8177,
|
777 |
+
"step": 128
|
778 |
+
},
|
779 |
+
{
|
780 |
+
"epoch": 0.31,
|
781 |
+
"learning_rate": 0.00012796862503070062,
|
782 |
+
"loss": 0.9717,
|
783 |
+
"step": 129
|
784 |
+
},
|
785 |
+
{
|
786 |
+
"epoch": 0.31,
|
787 |
+
"learning_rate": 0.00012747548783981962,
|
788 |
+
"loss": 0.8813,
|
789 |
+
"step": 130
|
790 |
+
},
|
791 |
+
{
|
792 |
+
"epoch": 0.31,
|
793 |
+
"learning_rate": 0.00012698800808924157,
|
794 |
+
"loss": 0.9708,
|
795 |
+
"step": 131
|
796 |
+
},
|
797 |
+
{
|
798 |
+
"epoch": 0.32,
|
799 |
+
"learning_rate": 0.00012650607842624748,
|
800 |
+
"loss": 0.8776,
|
801 |
+
"step": 132
|
802 |
+
},
|
803 |
+
{
|
804 |
+
"epoch": 0.32,
|
805 |
+
"learning_rate": 0.0001260295943285407,
|
806 |
+
"loss": 0.8564,
|
807 |
+
"step": 133
|
808 |
+
},
|
809 |
+
{
|
810 |
+
"epoch": 0.32,
|
811 |
+
"learning_rate": 0.00012555845400901656,
|
812 |
+
"loss": 0.8793,
|
813 |
+
"step": 134
|
814 |
+
},
|
815 |
+
{
|
816 |
+
"epoch": 0.32,
|
817 |
+
"learning_rate": 0.0001250925583244189,
|
818 |
+
"loss": 0.9288,
|
819 |
+
"step": 135
|
820 |
+
},
|
821 |
+
{
|
822 |
+
"epoch": 0.33,
|
823 |
+
"learning_rate": 0.00012463181068769768,
|
824 |
+
"loss": 0.9407,
|
825 |
+
"step": 136
|
826 |
+
},
|
827 |
+
{
|
828 |
+
"epoch": 0.33,
|
829 |
+
"learning_rate": 0.0001241761169838914,
|
830 |
+
"loss": 0.9746,
|
831 |
+
"step": 137
|
832 |
+
},
|
833 |
+
{
|
834 |
+
"epoch": 0.33,
|
835 |
+
"learning_rate": 0.00012372538548936814,
|
836 |
+
"loss": 1.0109,
|
837 |
+
"step": 138
|
838 |
+
},
|
839 |
+
{
|
840 |
+
"epoch": 0.33,
|
841 |
+
"learning_rate": 0.00012327952679426827,
|
842 |
+
"loss": 1.0695,
|
843 |
+
"step": 139
|
844 |
+
},
|
845 |
+
{
|
846 |
+
"epoch": 0.34,
|
847 |
+
"learning_rate": 0.00012283845372799884,
|
848 |
+
"loss": 0.9092,
|
849 |
+
"step": 140
|
850 |
+
},
|
851 |
+
{
|
852 |
+
"epoch": 0.34,
|
853 |
+
"learning_rate": 0.00012240208128764027,
|
854 |
+
"loss": 0.7535,
|
855 |
+
"step": 141
|
856 |
+
},
|
857 |
+
{
|
858 |
+
"epoch": 0.34,
|
859 |
+
"learning_rate": 0.00012197032656913024,
|
860 |
+
"loss": 0.7952,
|
861 |
+
"step": 142
|
862 |
+
},
|
863 |
+
{
|
864 |
+
"epoch": 0.34,
|
865 |
+
"learning_rate": 0.00012154310870109942,
|
866 |
+
"loss": 0.8747,
|
867 |
+
"step": 143
|
868 |
+
},
|
869 |
+
{
|
870 |
+
"epoch": 0.35,
|
871 |
+
"learning_rate": 0.0001211203487812386,
|
872 |
+
"loss": 0.823,
|
873 |
+
"step": 144
|
874 |
+
},
|
875 |
+
{
|
876 |
+
"epoch": 0.35,
|
877 |
+
"learning_rate": 0.0001207019698150837,
|
878 |
+
"loss": 0.838,
|
879 |
+
"step": 145
|
880 |
+
},
|
881 |
+
{
|
882 |
+
"epoch": 0.35,
|
883 |
+
"learning_rate": 0.00012028789665711085,
|
884 |
+
"loss": 0.8352,
|
885 |
+
"step": 146
|
886 |
+
},
|
887 |
+
{
|
888 |
+
"epoch": 0.35,
|
889 |
+
"learning_rate": 0.00011987805595403907,
|
890 |
+
"loss": 0.9483,
|
891 |
+
"step": 147
|
892 |
+
},
|
893 |
+
{
|
894 |
+
"epoch": 0.35,
|
895 |
+
"learning_rate": 0.00011947237609024377,
|
896 |
+
"loss": 0.8841,
|
897 |
+
"step": 148
|
898 |
+
},
|
899 |
+
{
|
900 |
+
"epoch": 0.36,
|
901 |
+
"learning_rate": 0.00011907078713518815,
|
902 |
+
"loss": 1.0176,
|
903 |
+
"step": 149
|
904 |
+
},
|
905 |
+
{
|
906 |
+
"epoch": 0.36,
|
907 |
+
"learning_rate": 0.00011867322079278597,
|
908 |
+
"loss": 0.9113,
|
909 |
+
"step": 150
|
910 |
+
},
|
911 |
+
{
|
912 |
+
"epoch": 0.36,
|
913 |
+
"learning_rate": 0.00011827961035261132,
|
914 |
+
"loss": 0.8683,
|
915 |
+
"step": 151
|
916 |
+
},
|
917 |
+
{
|
918 |
+
"epoch": 0.36,
|
919 |
+
"learning_rate": 0.0001178898906428769,
|
920 |
+
"loss": 0.8158,
|
921 |
+
"step": 152
|
922 |
+
},
|
923 |
+
{
|
924 |
+
"epoch": 0.37,
|
925 |
+
"learning_rate": 0.0001175039979851054,
|
926 |
+
"loss": 0.8146,
|
927 |
+
"step": 153
|
928 |
+
},
|
929 |
+
{
|
930 |
+
"epoch": 0.37,
|
931 |
+
"learning_rate": 0.00011712187015042266,
|
932 |
+
"loss": 0.8513,
|
933 |
+
"step": 154
|
934 |
+
},
|
935 |
+
{
|
936 |
+
"epoch": 0.37,
|
937 |
+
"learning_rate": 0.00011674344631740369,
|
938 |
+
"loss": 0.8071,
|
939 |
+
"step": 155
|
940 |
+
},
|
941 |
+
{
|
942 |
+
"epoch": 0.37,
|
943 |
+
"learning_rate": 0.00011636866703140783,
|
944 |
+
"loss": 0.8923,
|
945 |
+
"step": 156
|
946 |
+
},
|
947 |
+
{
|
948 |
+
"epoch": 0.38,
|
949 |
+
"learning_rate": 0.00011599747416534057,
|
950 |
+
"loss": 0.9082,
|
951 |
+
"step": 157
|
952 |
+
},
|
953 |
+
{
|
954 |
+
"epoch": 0.38,
|
955 |
+
"learning_rate": 0.00011562981088178324,
|
956 |
+
"loss": 0.8323,
|
957 |
+
"step": 158
|
958 |
+
},
|
959 |
+
{
|
960 |
+
"epoch": 0.38,
|
961 |
+
"learning_rate": 0.00011526562159643515,
|
962 |
+
"loss": 0.8079,
|
963 |
+
"step": 159
|
964 |
+
},
|
965 |
+
{
|
966 |
+
"epoch": 0.38,
|
967 |
+
"learning_rate": 0.00011490485194281395,
|
968 |
+
"loss": 0.8623,
|
969 |
+
"step": 160
|
970 |
+
},
|
971 |
+
{
|
972 |
+
"epoch": 0.39,
|
973 |
+
"learning_rate": 0.00011454744873816422,
|
974 |
+
"loss": 0.8465,
|
975 |
+
"step": 161
|
976 |
+
},
|
977 |
+
{
|
978 |
+
"epoch": 0.39,
|
979 |
+
"learning_rate": 0.0001141933599505248,
|
980 |
+
"loss": 0.9027,
|
981 |
+
"step": 162
|
982 |
+
},
|
983 |
+
{
|
984 |
+
"epoch": 0.39,
|
985 |
+
"learning_rate": 0.00011384253466690954,
|
986 |
+
"loss": 0.907,
|
987 |
+
"step": 163
|
988 |
+
},
|
989 |
+
{
|
990 |
+
"epoch": 0.39,
|
991 |
+
"learning_rate": 0.00011349492306255647,
|
992 |
+
"loss": 0.9152,
|
993 |
+
"step": 164
|
994 |
+
},
|
995 |
+
{
|
996 |
+
"epoch": 0.4,
|
997 |
+
"learning_rate": 0.0001131504763712036,
|
998 |
+
"loss": 0.7418,
|
999 |
+
"step": 165
|
1000 |
+
},
|
1001 |
+
{
|
1002 |
+
"epoch": 0.4,
|
1003 |
+
"learning_rate": 0.00011280914685635128,
|
1004 |
+
"loss": 0.8328,
|
1005 |
+
"step": 166
|
1006 |
+
},
|
1007 |
+
{
|
1008 |
+
"epoch": 0.4,
|
1009 |
+
"learning_rate": 0.0001124708877834722,
|
1010 |
+
"loss": 0.9287,
|
1011 |
+
"step": 167
|
1012 |
+
},
|
1013 |
+
{
|
1014 |
+
"epoch": 0.4,
|
1015 |
+
"learning_rate": 0.00011213565339313254,
|
1016 |
+
"loss": 0.7967,
|
1017 |
+
"step": 168
|
1018 |
+
},
|
1019 |
+
{
|
1020 |
+
"epoch": 0.41,
|
1021 |
+
"learning_rate": 0.00011180339887498949,
|
1022 |
+
"loss": 0.84,
|
1023 |
+
"step": 169
|
1024 |
+
},
|
1025 |
+
{
|
1026 |
+
"epoch": 0.41,
|
1027 |
+
"learning_rate": 0.00011147408034263073,
|
1028 |
+
"loss": 0.8149,
|
1029 |
+
"step": 170
|
1030 |
+
},
|
1031 |
+
{
|
1032 |
+
"epoch": 0.41,
|
1033 |
+
"learning_rate": 0.00011114765480922503,
|
1034 |
+
"loss": 0.8555,
|
1035 |
+
"step": 171
|
1036 |
+
},
|
1037 |
+
{
|
1038 |
+
"epoch": 0.41,
|
1039 |
+
"learning_rate": 0.00011082408016395194,
|
1040 |
+
"loss": 0.814,
|
1041 |
+
"step": 172
|
1042 |
+
},
|
1043 |
+
{
|
1044 |
+
"epoch": 0.41,
|
1045 |
+
"learning_rate": 0.00011050331514918246,
|
1046 |
+
"loss": 0.8139,
|
1047 |
+
"step": 173
|
1048 |
+
},
|
1049 |
+
{
|
1050 |
+
"epoch": 0.42,
|
1051 |
+
"learning_rate": 0.0001101853193383817,
|
1052 |
+
"loss": 0.885,
|
1053 |
+
"step": 174
|
1054 |
+
},
|
1055 |
+
{
|
1056 |
+
"epoch": 0.42,
|
1057 |
+
"learning_rate": 0.00010987005311470715,
|
1058 |
+
"loss": 0.7682,
|
1059 |
+
"step": 175
|
1060 |
+
},
|
1061 |
+
{
|
1062 |
+
"epoch": 0.42,
|
1063 |
+
"learning_rate": 0.00010955747765027683,
|
1064 |
+
"loss": 0.8266,
|
1065 |
+
"step": 176
|
1066 |
+
},
|
1067 |
+
{
|
1068 |
+
"epoch": 0.42,
|
1069 |
+
"learning_rate": 0.00010924755488608232,
|
1070 |
+
"loss": 0.8699,
|
1071 |
+
"step": 177
|
1072 |
+
},
|
1073 |
+
{
|
1074 |
+
"epoch": 0.43,
|
1075 |
+
"learning_rate": 0.00010894024751252352,
|
1076 |
+
"loss": 0.957,
|
1077 |
+
"step": 178
|
1078 |
+
},
|
1079 |
+
{
|
1080 |
+
"epoch": 0.43,
|
1081 |
+
"learning_rate": 0.00010863551895054227,
|
1082 |
+
"loss": 0.854,
|
1083 |
+
"step": 179
|
1084 |
+
},
|
1085 |
+
{
|
1086 |
+
"epoch": 0.43,
|
1087 |
+
"learning_rate": 0.00010833333333333333,
|
1088 |
+
"loss": 0.7239,
|
1089 |
+
"step": 180
|
1090 |
+
},
|
1091 |
+
{
|
1092 |
+
"epoch": 0.43,
|
1093 |
+
"learning_rate": 0.00010803365548861171,
|
1094 |
+
"loss": 0.7825,
|
1095 |
+
"step": 181
|
1096 |
+
},
|
1097 |
+
{
|
1098 |
+
"epoch": 0.44,
|
1099 |
+
"learning_rate": 0.00010773645092141682,
|
1100 |
+
"loss": 0.8531,
|
1101 |
+
"step": 182
|
1102 |
+
},
|
1103 |
+
{
|
1104 |
+
"epoch": 0.44,
|
1105 |
+
"learning_rate": 0.00010744168579743401,
|
1106 |
+
"loss": 0.7602,
|
1107 |
+
"step": 183
|
1108 |
+
},
|
1109 |
+
{
|
1110 |
+
"epoch": 0.44,
|
1111 |
+
"learning_rate": 0.0001071493269268154,
|
1112 |
+
"loss": 0.8768,
|
1113 |
+
"step": 184
|
1114 |
+
},
|
1115 |
+
{
|
1116 |
+
"epoch": 0.44,
|
1117 |
+
"learning_rate": 0.00010685934174848223,
|
1118 |
+
"loss": 0.8294,
|
1119 |
+
"step": 185
|
1120 |
+
},
|
1121 |
+
{
|
1122 |
+
"epoch": 0.45,
|
1123 |
+
"learning_rate": 0.00010657169831489234,
|
1124 |
+
"loss": 0.8872,
|
1125 |
+
"step": 186
|
1126 |
+
},
|
1127 |
+
{
|
1128 |
+
"epoch": 0.45,
|
1129 |
+
"learning_rate": 0.0001062863652772559,
|
1130 |
+
"loss": 0.7016,
|
1131 |
+
"step": 187
|
1132 |
+
},
|
1133 |
+
{
|
1134 |
+
"epoch": 0.45,
|
1135 |
+
"learning_rate": 0.00010600331187118435,
|
1136 |
+
"loss": 0.8942,
|
1137 |
+
"step": 188
|
1138 |
+
},
|
1139 |
+
{
|
1140 |
+
"epoch": 0.45,
|
1141 |
+
"learning_rate": 0.00010572250790275775,
|
1142 |
+
"loss": 0.7416,
|
1143 |
+
"step": 189
|
1144 |
+
},
|
1145 |
+
{
|
1146 |
+
"epoch": 0.46,
|
1147 |
+
"learning_rate": 0.00010544392373499565,
|
1148 |
+
"loss": 0.8104,
|
1149 |
+
"step": 190
|
1150 |
+
},
|
1151 |
+
{
|
1152 |
+
"epoch": 0.46,
|
1153 |
+
"learning_rate": 0.0001051675302747182,
|
1154 |
+
"loss": 0.8349,
|
1155 |
+
"step": 191
|
1156 |
+
},
|
1157 |
+
{
|
1158 |
+
"epoch": 0.46,
|
1159 |
+
"learning_rate": 0.0001048932989597842,
|
1160 |
+
"loss": 0.9013,
|
1161 |
+
"step": 192
|
1162 |
+
},
|
1163 |
+
{
|
1164 |
+
"epoch": 0.46,
|
1165 |
+
"learning_rate": 0.00010462120174669319,
|
1166 |
+
"loss": 0.7646,
|
1167 |
+
"step": 193
|
1168 |
+
},
|
1169 |
+
{
|
1170 |
+
"epoch": 0.47,
|
1171 |
+
"learning_rate": 0.00010435121109853953,
|
1172 |
+
"loss": 0.8087,
|
1173 |
+
"step": 194
|
1174 |
+
},
|
1175 |
+
{
|
1176 |
+
"epoch": 0.47,
|
1177 |
+
"learning_rate": 0.00010408329997330662,
|
1178 |
+
"loss": 0.9798,
|
1179 |
+
"step": 195
|
1180 |
+
},
|
1181 |
+
{
|
1182 |
+
"epoch": 0.47,
|
1183 |
+
"learning_rate": 0.00010381744181249024,
|
1184 |
+
"loss": 0.7266,
|
1185 |
+
"step": 196
|
1186 |
+
},
|
1187 |
+
{
|
1188 |
+
"epoch": 0.47,
|
1189 |
+
"learning_rate": 0.0001035536105300395,
|
1190 |
+
"loss": 0.8502,
|
1191 |
+
"step": 197
|
1192 |
+
},
|
1193 |
+
{
|
1194 |
+
"epoch": 0.47,
|
1195 |
+
"learning_rate": 0.00010329178050160582,
|
1196 |
+
"loss": 0.7797,
|
1197 |
+
"step": 198
|
1198 |
+
},
|
1199 |
+
{
|
1200 |
+
"epoch": 0.48,
|
1201 |
+
"learning_rate": 0.00010303192655408924,
|
1202 |
+
"loss": 0.7328,
|
1203 |
+
"step": 199
|
1204 |
+
},
|
1205 |
+
{
|
1206 |
+
"epoch": 0.48,
|
1207 |
+
"learning_rate": 0.00010277402395547232,
|
1208 |
+
"loss": 0.7916,
|
1209 |
+
"step": 200
|
1210 |
+
}
|
1211 |
+
],
|
1212 |
+
"logging_steps": 1,
|
1213 |
+
"max_steps": 417,
|
1214 |
+
"num_train_epochs": 1,
|
1215 |
+
"save_steps": 10,
|
1216 |
+
"total_flos": 6.487869967879373e+16,
|
1217 |
+
"trial_name": null,
|
1218 |
+
"trial_params": null
|
1219 |
+
}
|
checkpoint-200/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:482256ef65b59af088490f9e3870f1b868a90992cd6294900bd43d13ef410480
|
3 |
+
size 4536
|
checkpoint-40/README.md
ADDED
@@ -0,0 +1,220 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: peft
|
3 |
+
base_model: unsloth/llama-2-7b
|
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 |
+
|
201 |
+
|
202 |
+
## Training procedure
|
203 |
+
|
204 |
+
|
205 |
+
The following `bitsandbytes` quantization config was used during training:
|
206 |
+
- quant_method: bitsandbytes
|
207 |
+
- load_in_8bit: False
|
208 |
+
- load_in_4bit: True
|
209 |
+
- llm_int8_threshold: 6.0
|
210 |
+
- llm_int8_skip_modules: None
|
211 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
212 |
+
- llm_int8_has_fp16_weight: False
|
213 |
+
- bnb_4bit_quant_type: nf4
|
214 |
+
- bnb_4bit_use_double_quant: True
|
215 |
+
- bnb_4bit_compute_dtype: bfloat16
|
216 |
+
|
217 |
+
### Framework versions
|
218 |
+
|
219 |
+
|
220 |
+
- PEFT 0.6.2
|
checkpoint-40/adapter_config.json
ADDED
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "unsloth/llama-2-7b",
|
5 |
+
"bias": "none",
|
6 |
+
"fan_in_fan_out": false,
|
7 |
+
"inference_mode": true,
|
8 |
+
"init_lora_weights": true,
|
9 |
+
"layers_pattern": null,
|
10 |
+
"layers_to_transform": null,
|
11 |
+
"lora_alpha": 32,
|
12 |
+
"lora_dropout": 0,
|
13 |
+
"modules_to_save": null,
|
14 |
+
"peft_type": "LORA",
|
15 |
+
"r": 16,
|
16 |
+
"rank_pattern": {},
|
17 |
+
"revision": null,
|
18 |
+
"target_modules": [
|
19 |
+
"o_proj",
|
20 |
+
"up_proj",
|
21 |
+
"down_proj",
|
22 |
+
"q_proj",
|
23 |
+
"k_proj",
|
24 |
+
"v_proj",
|
25 |
+
"gate_proj"
|
26 |
+
],
|
27 |
+
"task_type": "CAUSAL_LM"
|
28 |
+
}
|
checkpoint-40/adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1d879b575ccbc5870446f4660d9f84e87e57d8943adb6905d66d7b2416a58cd2
|
3 |
+
size 159967880
|
checkpoint-40/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:abf198c2832597a6e8d36b6dbdbd6ba07ddd67e809dbe44b9c8cde5a9d16b77f
|
3 |
+
size 80630612
|
checkpoint-40/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:203e9bfabd925cb4ec7129d24877156fcee87215187c35a867e358e56a9425a4
|
3 |
+
size 14244
|
checkpoint-40/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d1a123c2e2869cfd4ae8b10396584d8f5b9752e5427db6f1a6efa11fcc47bfcd
|
3 |
+
size 1064
|
checkpoint-40/trainer_state.json
ADDED
@@ -0,0 +1,259 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.09592326139088729,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 40,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.0,
|
13 |
+
"learning_rate": 0.00013,
|
14 |
+
"loss": 1.1241,
|
15 |
+
"step": 1
|
16 |
+
},
|
17 |
+
{
|
18 |
+
"epoch": 0.0,
|
19 |
+
"learning_rate": 0.00026,
|
20 |
+
"loss": 1.0107,
|
21 |
+
"step": 2
|
22 |
+
},
|
23 |
+
{
|
24 |
+
"epoch": 0.01,
|
25 |
+
"learning_rate": 0.00039,
|
26 |
+
"loss": 1.1086,
|
27 |
+
"step": 3
|
28 |
+
},
|
29 |
+
{
|
30 |
+
"epoch": 0.01,
|
31 |
+
"learning_rate": 0.00052,
|
32 |
+
"loss": 1.0044,
|
33 |
+
"step": 4
|
34 |
+
},
|
35 |
+
{
|
36 |
+
"epoch": 0.01,
|
37 |
+
"learning_rate": 0.00065,
|
38 |
+
"loss": 1.0496,
|
39 |
+
"step": 5
|
40 |
+
},
|
41 |
+
{
|
42 |
+
"epoch": 0.01,
|
43 |
+
"learning_rate": 0.0005933661039639299,
|
44 |
+
"loss": 1.0199,
|
45 |
+
"step": 6
|
46 |
+
},
|
47 |
+
{
|
48 |
+
"epoch": 0.02,
|
49 |
+
"learning_rate": 0.0005493502655735357,
|
50 |
+
"loss": 1.0198,
|
51 |
+
"step": 7
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.02,
|
55 |
+
"learning_rate": 0.0005138701197773616,
|
56 |
+
"loss": 0.969,
|
57 |
+
"step": 8
|
58 |
+
},
|
59 |
+
{
|
60 |
+
"epoch": 0.02,
|
61 |
+
"learning_rate": 0.0004844813951249544,
|
62 |
+
"loss": 0.9383,
|
63 |
+
"step": 9
|
64 |
+
},
|
65 |
+
{
|
66 |
+
"epoch": 0.02,
|
67 |
+
"learning_rate": 0.0004596194077712558,
|
68 |
+
"loss": 0.8776,
|
69 |
+
"step": 10
|
70 |
+
},
|
71 |
+
{
|
72 |
+
"epoch": 0.03,
|
73 |
+
"learning_rate": 0.0004382299106011073,
|
74 |
+
"loss": 1.0173,
|
75 |
+
"step": 11
|
76 |
+
},
|
77 |
+
{
|
78 |
+
"epoch": 0.03,
|
79 |
+
"learning_rate": 0.0004195731958391368,
|
80 |
+
"loss": 1.1173,
|
81 |
+
"step": 12
|
82 |
+
},
|
83 |
+
{
|
84 |
+
"epoch": 0.03,
|
85 |
+
"learning_rate": 0.0004031128874149274,
|
86 |
+
"loss": 1.0876,
|
87 |
+
"step": 13
|
88 |
+
},
|
89 |
+
{
|
90 |
+
"epoch": 0.03,
|
91 |
+
"learning_rate": 0.0003884492980336779,
|
92 |
+
"loss": 1.0524,
|
93 |
+
"step": 14
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 0.04,
|
97 |
+
"learning_rate": 0.0003752776749732568,
|
98 |
+
"loss": 0.8953,
|
99 |
+
"step": 15
|
100 |
+
},
|
101 |
+
{
|
102 |
+
"epoch": 0.04,
|
103 |
+
"learning_rate": 0.00036336104634371584,
|
104 |
+
"loss": 1.1335,
|
105 |
+
"step": 16
|
106 |
+
},
|
107 |
+
{
|
108 |
+
"epoch": 0.04,
|
109 |
+
"learning_rate": 0.00035251199395531623,
|
110 |
+
"loss": 0.9837,
|
111 |
+
"step": 17
|
112 |
+
},
|
113 |
+
{
|
114 |
+
"epoch": 0.04,
|
115 |
+
"learning_rate": 0.00034258007985157445,
|
116 |
+
"loss": 0.9707,
|
117 |
+
"step": 18
|
118 |
+
},
|
119 |
+
{
|
120 |
+
"epoch": 0.05,
|
121 |
+
"learning_rate": 0.0003334429644276751,
|
122 |
+
"loss": 0.9149,
|
123 |
+
"step": 19
|
124 |
+
},
|
125 |
+
{
|
126 |
+
"epoch": 0.05,
|
127 |
+
"learning_rate": 0.000325,
|
128 |
+
"loss": 1.0043,
|
129 |
+
"step": 20
|
130 |
+
},
|
131 |
+
{
|
132 |
+
"epoch": 0.05,
|
133 |
+
"learning_rate": 0.00031716752370827323,
|
134 |
+
"loss": 1.001,
|
135 |
+
"step": 21
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 0.05,
|
139 |
+
"learning_rate": 0.00030987534150481746,
|
140 |
+
"loss": 1.0395,
|
141 |
+
"step": 22
|
142 |
+
},
|
143 |
+
{
|
144 |
+
"epoch": 0.06,
|
145 |
+
"learning_rate": 0.000303064062678102,
|
146 |
+
"loss": 0.8718,
|
147 |
+
"step": 23
|
148 |
+
},
|
149 |
+
{
|
150 |
+
"epoch": 0.06,
|
151 |
+
"learning_rate": 0.00029668305198196496,
|
152 |
+
"loss": 1.1114,
|
153 |
+
"step": 24
|
154 |
+
},
|
155 |
+
{
|
156 |
+
"epoch": 0.06,
|
157 |
+
"learning_rate": 0.00029068883707497264,
|
158 |
+
"loss": 0.7765,
|
159 |
+
"step": 25
|
160 |
+
},
|
161 |
+
{
|
162 |
+
"epoch": 0.06,
|
163 |
+
"learning_rate": 0.0002850438562747845,
|
164 |
+
"loss": 0.9522,
|
165 |
+
"step": 26
|
166 |
+
},
|
167 |
+
{
|
168 |
+
"epoch": 0.06,
|
169 |
+
"learning_rate": 0.00027971546389275785,
|
170 |
+
"loss": 0.9588,
|
171 |
+
"step": 27
|
172 |
+
},
|
173 |
+
{
|
174 |
+
"epoch": 0.07,
|
175 |
+
"learning_rate": 0.00027467513278676785,
|
176 |
+
"loss": 1.0313,
|
177 |
+
"step": 28
|
178 |
+
},
|
179 |
+
{
|
180 |
+
"epoch": 0.07,
|
181 |
+
"learning_rate": 0.0002698978095246549,
|
182 |
+
"loss": 0.9338,
|
183 |
+
"step": 29
|
184 |
+
},
|
185 |
+
{
|
186 |
+
"epoch": 0.07,
|
187 |
+
"learning_rate": 0.000265361388801511,
|
188 |
+
"loss": 0.892,
|
189 |
+
"step": 30
|
190 |
+
},
|
191 |
+
{
|
192 |
+
"epoch": 0.07,
|
193 |
+
"learning_rate": 0.00026104628189331215,
|
194 |
+
"loss": 0.893,
|
195 |
+
"step": 31
|
196 |
+
},
|
197 |
+
{
|
198 |
+
"epoch": 0.08,
|
199 |
+
"learning_rate": 0.0002569350598886808,
|
200 |
+
"loss": 0.8983,
|
201 |
+
"step": 32
|
202 |
+
},
|
203 |
+
{
|
204 |
+
"epoch": 0.08,
|
205 |
+
"learning_rate": 0.00025301215685249496,
|
206 |
+
"loss": 0.9277,
|
207 |
+
"step": 33
|
208 |
+
},
|
209 |
+
{
|
210 |
+
"epoch": 0.08,
|
211 |
+
"learning_rate": 0.00024926362137539537,
|
212 |
+
"loss": 0.8962,
|
213 |
+
"step": 34
|
214 |
+
},
|
215 |
+
{
|
216 |
+
"epoch": 0.08,
|
217 |
+
"learning_rate": 0.00024567690745599767,
|
218 |
+
"loss": 0.9124,
|
219 |
+
"step": 35
|
220 |
+
},
|
221 |
+
{
|
222 |
+
"epoch": 0.09,
|
223 |
+
"learning_rate": 0.0002422406975624772,
|
224 |
+
"loss": 0.9535,
|
225 |
+
"step": 36
|
226 |
+
},
|
227 |
+
{
|
228 |
+
"epoch": 0.09,
|
229 |
+
"learning_rate": 0.00023894475218048754,
|
230 |
+
"loss": 0.9019,
|
231 |
+
"step": 37
|
232 |
+
},
|
233 |
+
{
|
234 |
+
"epoch": 0.09,
|
235 |
+
"learning_rate": 0.0002357797812857538,
|
236 |
+
"loss": 1.024,
|
237 |
+
"step": 38
|
238 |
+
},
|
239 |
+
{
|
240 |
+
"epoch": 0.09,
|
241 |
+
"learning_rate": 0.00023273733406281566,
|
242 |
+
"loss": 0.8549,
|
243 |
+
"step": 39
|
244 |
+
},
|
245 |
+
{
|
246 |
+
"epoch": 0.1,
|
247 |
+
"learning_rate": 0.0002298097038856279,
|
248 |
+
"loss": 1.0489,
|
249 |
+
"step": 40
|
250 |
+
}
|
251 |
+
],
|
252 |
+
"logging_steps": 1,
|
253 |
+
"max_steps": 417,
|
254 |
+
"num_train_epochs": 1,
|
255 |
+
"save_steps": 10,
|
256 |
+
"total_flos": 1.2924943770845184e+16,
|
257 |
+
"trial_name": null,
|
258 |
+
"trial_params": null
|
259 |
+
}
|
checkpoint-40/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:482256ef65b59af088490f9e3870f1b868a90992cd6294900bd43d13ef410480
|
3 |
+
size 4536
|
checkpoint-80/README.md
ADDED
@@ -0,0 +1,220 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: peft
|
3 |
+
base_model: unsloth/llama-2-7b
|
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 |
+
|
201 |
+
|
202 |
+
## Training procedure
|
203 |
+
|
204 |
+
|
205 |
+
The following `bitsandbytes` quantization config was used during training:
|
206 |
+
- quant_method: bitsandbytes
|
207 |
+
- load_in_8bit: False
|
208 |
+
- load_in_4bit: True
|
209 |
+
- llm_int8_threshold: 6.0
|
210 |
+
- llm_int8_skip_modules: None
|
211 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
212 |
+
- llm_int8_has_fp16_weight: False
|
213 |
+
- bnb_4bit_quant_type: nf4
|
214 |
+
- bnb_4bit_use_double_quant: True
|
215 |
+
- bnb_4bit_compute_dtype: bfloat16
|
216 |
+
|
217 |
+
### Framework versions
|
218 |
+
|
219 |
+
|
220 |
+
- PEFT 0.6.2
|
checkpoint-80/adapter_config.json
ADDED
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "unsloth/llama-2-7b",
|
5 |
+
"bias": "none",
|
6 |
+
"fan_in_fan_out": false,
|
7 |
+
"inference_mode": true,
|
8 |
+
"init_lora_weights": true,
|
9 |
+
"layers_pattern": null,
|
10 |
+
"layers_to_transform": null,
|
11 |
+
"lora_alpha": 32,
|
12 |
+
"lora_dropout": 0,
|
13 |
+
"modules_to_save": null,
|
14 |
+
"peft_type": "LORA",
|
15 |
+
"r": 16,
|
16 |
+
"rank_pattern": {},
|
17 |
+
"revision": null,
|
18 |
+
"target_modules": [
|
19 |
+
"o_proj",
|
20 |
+
"up_proj",
|
21 |
+
"down_proj",
|
22 |
+
"q_proj",
|
23 |
+
"k_proj",
|
24 |
+
"v_proj",
|
25 |
+
"gate_proj"
|
26 |
+
],
|
27 |
+
"task_type": "CAUSAL_LM"
|
28 |
+
}
|
checkpoint-80/adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b9f21852fc41174f2b5b87cccc6d4a5d07a4660480a9d9fdd6ebc875883cf30d
|
3 |
+
size 159967880
|
checkpoint-80/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:53f79c6b8e0d8ad36a77715fff5512b2deddade328c167b641b9dfae8933876b
|
3 |
+
size 80630612
|
checkpoint-80/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:203e9bfabd925cb4ec7129d24877156fcee87215187c35a867e358e56a9425a4
|
3 |
+
size 14244
|
checkpoint-80/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:88790c0dfb035758d1c04e3296c3d510b282a3a11865d663fde0aa5d8dc72699
|
3 |
+
size 1064
|
checkpoint-80/trainer_state.json
ADDED
@@ -0,0 +1,499 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.19184652278177458,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 80,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.0,
|
13 |
+
"learning_rate": 0.00013,
|
14 |
+
"loss": 1.1241,
|
15 |
+
"step": 1
|
16 |
+
},
|
17 |
+
{
|
18 |
+
"epoch": 0.0,
|
19 |
+
"learning_rate": 0.00026,
|
20 |
+
"loss": 1.0107,
|
21 |
+
"step": 2
|
22 |
+
},
|
23 |
+
{
|
24 |
+
"epoch": 0.01,
|
25 |
+
"learning_rate": 0.00039,
|
26 |
+
"loss": 1.1086,
|
27 |
+
"step": 3
|
28 |
+
},
|
29 |
+
{
|
30 |
+
"epoch": 0.01,
|
31 |
+
"learning_rate": 0.00052,
|
32 |
+
"loss": 1.0044,
|
33 |
+
"step": 4
|
34 |
+
},
|
35 |
+
{
|
36 |
+
"epoch": 0.01,
|
37 |
+
"learning_rate": 0.00065,
|
38 |
+
"loss": 1.0496,
|
39 |
+
"step": 5
|
40 |
+
},
|
41 |
+
{
|
42 |
+
"epoch": 0.01,
|
43 |
+
"learning_rate": 0.0005933661039639299,
|
44 |
+
"loss": 1.0199,
|
45 |
+
"step": 6
|
46 |
+
},
|
47 |
+
{
|
48 |
+
"epoch": 0.02,
|
49 |
+
"learning_rate": 0.0005493502655735357,
|
50 |
+
"loss": 1.0198,
|
51 |
+
"step": 7
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.02,
|
55 |
+
"learning_rate": 0.0005138701197773616,
|
56 |
+
"loss": 0.969,
|
57 |
+
"step": 8
|
58 |
+
},
|
59 |
+
{
|
60 |
+
"epoch": 0.02,
|
61 |
+
"learning_rate": 0.0004844813951249544,
|
62 |
+
"loss": 0.9383,
|
63 |
+
"step": 9
|
64 |
+
},
|
65 |
+
{
|
66 |
+
"epoch": 0.02,
|
67 |
+
"learning_rate": 0.0004596194077712558,
|
68 |
+
"loss": 0.8776,
|
69 |
+
"step": 10
|
70 |
+
},
|
71 |
+
{
|
72 |
+
"epoch": 0.03,
|
73 |
+
"learning_rate": 0.0004382299106011073,
|
74 |
+
"loss": 1.0173,
|
75 |
+
"step": 11
|
76 |
+
},
|
77 |
+
{
|
78 |
+
"epoch": 0.03,
|
79 |
+
"learning_rate": 0.0004195731958391368,
|
80 |
+
"loss": 1.1173,
|
81 |
+
"step": 12
|
82 |
+
},
|
83 |
+
{
|
84 |
+
"epoch": 0.03,
|
85 |
+
"learning_rate": 0.0004031128874149274,
|
86 |
+
"loss": 1.0876,
|
87 |
+
"step": 13
|
88 |
+
},
|
89 |
+
{
|
90 |
+
"epoch": 0.03,
|
91 |
+
"learning_rate": 0.0003884492980336779,
|
92 |
+
"loss": 1.0524,
|
93 |
+
"step": 14
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 0.04,
|
97 |
+
"learning_rate": 0.0003752776749732568,
|
98 |
+
"loss": 0.8953,
|
99 |
+
"step": 15
|
100 |
+
},
|
101 |
+
{
|
102 |
+
"epoch": 0.04,
|
103 |
+
"learning_rate": 0.00036336104634371584,
|
104 |
+
"loss": 1.1335,
|
105 |
+
"step": 16
|
106 |
+
},
|
107 |
+
{
|
108 |
+
"epoch": 0.04,
|
109 |
+
"learning_rate": 0.00035251199395531623,
|
110 |
+
"loss": 0.9837,
|
111 |
+
"step": 17
|
112 |
+
},
|
113 |
+
{
|
114 |
+
"epoch": 0.04,
|
115 |
+
"learning_rate": 0.00034258007985157445,
|
116 |
+
"loss": 0.9707,
|
117 |
+
"step": 18
|
118 |
+
},
|
119 |
+
{
|
120 |
+
"epoch": 0.05,
|
121 |
+
"learning_rate": 0.0003334429644276751,
|
122 |
+
"loss": 0.9149,
|
123 |
+
"step": 19
|
124 |
+
},
|
125 |
+
{
|
126 |
+
"epoch": 0.05,
|
127 |
+
"learning_rate": 0.000325,
|
128 |
+
"loss": 1.0043,
|
129 |
+
"step": 20
|
130 |
+
},
|
131 |
+
{
|
132 |
+
"epoch": 0.05,
|
133 |
+
"learning_rate": 0.00031716752370827323,
|
134 |
+
"loss": 1.001,
|
135 |
+
"step": 21
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 0.05,
|
139 |
+
"learning_rate": 0.00030987534150481746,
|
140 |
+
"loss": 1.0395,
|
141 |
+
"step": 22
|
142 |
+
},
|
143 |
+
{
|
144 |
+
"epoch": 0.06,
|
145 |
+
"learning_rate": 0.000303064062678102,
|
146 |
+
"loss": 0.8718,
|
147 |
+
"step": 23
|
148 |
+
},
|
149 |
+
{
|
150 |
+
"epoch": 0.06,
|
151 |
+
"learning_rate": 0.00029668305198196496,
|
152 |
+
"loss": 1.1114,
|
153 |
+
"step": 24
|
154 |
+
},
|
155 |
+
{
|
156 |
+
"epoch": 0.06,
|
157 |
+
"learning_rate": 0.00029068883707497264,
|
158 |
+
"loss": 0.7765,
|
159 |
+
"step": 25
|
160 |
+
},
|
161 |
+
{
|
162 |
+
"epoch": 0.06,
|
163 |
+
"learning_rate": 0.0002850438562747845,
|
164 |
+
"loss": 0.9522,
|
165 |
+
"step": 26
|
166 |
+
},
|
167 |
+
{
|
168 |
+
"epoch": 0.06,
|
169 |
+
"learning_rate": 0.00027971546389275785,
|
170 |
+
"loss": 0.9588,
|
171 |
+
"step": 27
|
172 |
+
},
|
173 |
+
{
|
174 |
+
"epoch": 0.07,
|
175 |
+
"learning_rate": 0.00027467513278676785,
|
176 |
+
"loss": 1.0313,
|
177 |
+
"step": 28
|
178 |
+
},
|
179 |
+
{
|
180 |
+
"epoch": 0.07,
|
181 |
+
"learning_rate": 0.0002698978095246549,
|
182 |
+
"loss": 0.9338,
|
183 |
+
"step": 29
|
184 |
+
},
|
185 |
+
{
|
186 |
+
"epoch": 0.07,
|
187 |
+
"learning_rate": 0.000265361388801511,
|
188 |
+
"loss": 0.892,
|
189 |
+
"step": 30
|
190 |
+
},
|
191 |
+
{
|
192 |
+
"epoch": 0.07,
|
193 |
+
"learning_rate": 0.00026104628189331215,
|
194 |
+
"loss": 0.893,
|
195 |
+
"step": 31
|
196 |
+
},
|
197 |
+
{
|
198 |
+
"epoch": 0.08,
|
199 |
+
"learning_rate": 0.0002569350598886808,
|
200 |
+
"loss": 0.8983,
|
201 |
+
"step": 32
|
202 |
+
},
|
203 |
+
{
|
204 |
+
"epoch": 0.08,
|
205 |
+
"learning_rate": 0.00025301215685249496,
|
206 |
+
"loss": 0.9277,
|
207 |
+
"step": 33
|
208 |
+
},
|
209 |
+
{
|
210 |
+
"epoch": 0.08,
|
211 |
+
"learning_rate": 0.00024926362137539537,
|
212 |
+
"loss": 0.8962,
|
213 |
+
"step": 34
|
214 |
+
},
|
215 |
+
{
|
216 |
+
"epoch": 0.08,
|
217 |
+
"learning_rate": 0.00024567690745599767,
|
218 |
+
"loss": 0.9124,
|
219 |
+
"step": 35
|
220 |
+
},
|
221 |
+
{
|
222 |
+
"epoch": 0.09,
|
223 |
+
"learning_rate": 0.0002422406975624772,
|
224 |
+
"loss": 0.9535,
|
225 |
+
"step": 36
|
226 |
+
},
|
227 |
+
{
|
228 |
+
"epoch": 0.09,
|
229 |
+
"learning_rate": 0.00023894475218048754,
|
230 |
+
"loss": 0.9019,
|
231 |
+
"step": 37
|
232 |
+
},
|
233 |
+
{
|
234 |
+
"epoch": 0.09,
|
235 |
+
"learning_rate": 0.0002357797812857538,
|
236 |
+
"loss": 1.024,
|
237 |
+
"step": 38
|
238 |
+
},
|
239 |
+
{
|
240 |
+
"epoch": 0.09,
|
241 |
+
"learning_rate": 0.00023273733406281566,
|
242 |
+
"loss": 0.8549,
|
243 |
+
"step": 39
|
244 |
+
},
|
245 |
+
{
|
246 |
+
"epoch": 0.1,
|
247 |
+
"learning_rate": 0.0002298097038856279,
|
248 |
+
"loss": 1.0489,
|
249 |
+
"step": 40
|
250 |
+
},
|
251 |
+
{
|
252 |
+
"epoch": 0.1,
|
253 |
+
"learning_rate": 0.00022698984612511293,
|
254 |
+
"loss": 0.751,
|
255 |
+
"step": 41
|
256 |
+
},
|
257 |
+
{
|
258 |
+
"epoch": 0.1,
|
259 |
+
"learning_rate": 0.00022427130678626507,
|
260 |
+
"loss": 0.834,
|
261 |
+
"step": 42
|
262 |
+
},
|
263 |
+
{
|
264 |
+
"epoch": 0.1,
|
265 |
+
"learning_rate": 0.00022164816032790388,
|
266 |
+
"loss": 0.889,
|
267 |
+
"step": 43
|
268 |
+
},
|
269 |
+
{
|
270 |
+
"epoch": 0.11,
|
271 |
+
"learning_rate": 0.00021911495530055366,
|
272 |
+
"loss": 1.0103,
|
273 |
+
"step": 44
|
274 |
+
},
|
275 |
+
{
|
276 |
+
"epoch": 0.11,
|
277 |
+
"learning_rate": 0.00021666666666666666,
|
278 |
+
"loss": 0.8766,
|
279 |
+
"step": 45
|
280 |
+
},
|
281 |
+
{
|
282 |
+
"epoch": 0.11,
|
283 |
+
"learning_rate": 0.0002142986538536308,
|
284 |
+
"loss": 0.8181,
|
285 |
+
"step": 46
|
286 |
+
},
|
287 |
+
{
|
288 |
+
"epoch": 0.11,
|
289 |
+
"learning_rate": 0.0002120066237423687,
|
290 |
+
"loss": 0.8754,
|
291 |
+
"step": 47
|
292 |
+
},
|
293 |
+
{
|
294 |
+
"epoch": 0.12,
|
295 |
+
"learning_rate": 0.0002097865979195684,
|
296 |
+
"loss": 0.9038,
|
297 |
+
"step": 48
|
298 |
+
},
|
299 |
+
{
|
300 |
+
"epoch": 0.12,
|
301 |
+
"learning_rate": 0.00020763488362498048,
|
302 |
+
"loss": 0.8646,
|
303 |
+
"step": 49
|
304 |
+
},
|
305 |
+
{
|
306 |
+
"epoch": 0.12,
|
307 |
+
"learning_rate": 0.00020554804791094464,
|
308 |
+
"loss": 0.8836,
|
309 |
+
"step": 50
|
310 |
+
},
|
311 |
+
{
|
312 |
+
"epoch": 0.12,
|
313 |
+
"learning_rate": 0.0002035228946026736,
|
314 |
+
"loss": 0.9962,
|
315 |
+
"step": 51
|
316 |
+
},
|
317 |
+
{
|
318 |
+
"epoch": 0.12,
|
319 |
+
"learning_rate": 0.0002015564437074637,
|
320 |
+
"loss": 0.8835,
|
321 |
+
"step": 52
|
322 |
+
},
|
323 |
+
{
|
324 |
+
"epoch": 0.13,
|
325 |
+
"learning_rate": 0.00019964591297103414,
|
326 |
+
"loss": 0.9196,
|
327 |
+
"step": 53
|
328 |
+
},
|
329 |
+
{
|
330 |
+
"epoch": 0.13,
|
331 |
+
"learning_rate": 0.00019778870132130996,
|
332 |
+
"loss": 0.8995,
|
333 |
+
"step": 54
|
334 |
+
},
|
335 |
+
{
|
336 |
+
"epoch": 0.13,
|
337 |
+
"learning_rate": 0.00019598237397554634,
|
338 |
+
"loss": 1.0178,
|
339 |
+
"step": 55
|
340 |
+
},
|
341 |
+
{
|
342 |
+
"epoch": 0.13,
|
343 |
+
"learning_rate": 0.00019422464901683895,
|
344 |
+
"loss": 0.9395,
|
345 |
+
"step": 56
|
346 |
+
},
|
347 |
+
{
|
348 |
+
"epoch": 0.14,
|
349 |
+
"learning_rate": 0.00019251338527170498,
|
350 |
+
"loss": 0.9882,
|
351 |
+
"step": 57
|
352 |
+
},
|
353 |
+
{
|
354 |
+
"epoch": 0.14,
|
355 |
+
"learning_rate": 0.00019084657134227863,
|
356 |
+
"loss": 0.9274,
|
357 |
+
"step": 58
|
358 |
+
},
|
359 |
+
{
|
360 |
+
"epoch": 0.14,
|
361 |
+
"learning_rate": 0.00018922231566536414,
|
362 |
+
"loss": 0.9517,
|
363 |
+
"step": 59
|
364 |
+
},
|
365 |
+
{
|
366 |
+
"epoch": 0.14,
|
367 |
+
"learning_rate": 0.0001876388374866284,
|
368 |
+
"loss": 0.865,
|
369 |
+
"step": 60
|
370 |
+
},
|
371 |
+
{
|
372 |
+
"epoch": 0.15,
|
373 |
+
"learning_rate": 0.00018609445865200715,
|
374 |
+
"loss": 0.9314,
|
375 |
+
"step": 61
|
376 |
+
},
|
377 |
+
{
|
378 |
+
"epoch": 0.15,
|
379 |
+
"learning_rate": 0.00018458759613029606,
|
380 |
+
"loss": 0.9224,
|
381 |
+
"step": 62
|
382 |
+
},
|
383 |
+
{
|
384 |
+
"epoch": 0.15,
|
385 |
+
"learning_rate": 0.00018311675519117857,
|
386 |
+
"loss": 0.788,
|
387 |
+
"step": 63
|
388 |
+
},
|
389 |
+
{
|
390 |
+
"epoch": 0.15,
|
391 |
+
"learning_rate": 0.00018168052317185792,
|
392 |
+
"loss": 0.9739,
|
393 |
+
"step": 64
|
394 |
+
},
|
395 |
+
{
|
396 |
+
"epoch": 0.16,
|
397 |
+
"learning_rate": 0.00018027756377319947,
|
398 |
+
"loss": 0.9419,
|
399 |
+
"step": 65
|
400 |
+
},
|
401 |
+
{
|
402 |
+
"epoch": 0.16,
|
403 |
+
"learning_rate": 0.0001789066118330336,
|
404 |
+
"loss": 0.8772,
|
405 |
+
"step": 66
|
406 |
+
},
|
407 |
+
{
|
408 |
+
"epoch": 0.16,
|
409 |
+
"learning_rate": 0.00017756646853014972,
|
410 |
+
"loss": 0.8707,
|
411 |
+
"step": 67
|
412 |
+
},
|
413 |
+
{
|
414 |
+
"epoch": 0.16,
|
415 |
+
"learning_rate": 0.00017625599697765812,
|
416 |
+
"loss": 0.8089,
|
417 |
+
"step": 68
|
418 |
+
},
|
419 |
+
{
|
420 |
+
"epoch": 0.17,
|
421 |
+
"learning_rate": 0.00017497411816890378,
|
422 |
+
"loss": 0.9303,
|
423 |
+
"step": 69
|
424 |
+
},
|
425 |
+
{
|
426 |
+
"epoch": 0.17,
|
427 |
+
"learning_rate": 0.00017371980724307585,
|
428 |
+
"loss": 0.9161,
|
429 |
+
"step": 70
|
430 |
+
},
|
431 |
+
{
|
432 |
+
"epoch": 0.17,
|
433 |
+
"learning_rate": 0.00017249209004113945,
|
434 |
+
"loss": 0.9064,
|
435 |
+
"step": 71
|
436 |
+
},
|
437 |
+
{
|
438 |
+
"epoch": 0.17,
|
439 |
+
"learning_rate": 0.00017129003992578723,
|
440 |
+
"loss": 1.0988,
|
441 |
+
"step": 72
|
442 |
+
},
|
443 |
+
{
|
444 |
+
"epoch": 0.18,
|
445 |
+
"learning_rate": 0.00017011277484181944,
|
446 |
+
"loss": 0.9804,
|
447 |
+
"step": 73
|
448 |
+
},
|
449 |
+
{
|
450 |
+
"epoch": 0.18,
|
451 |
+
"learning_rate": 0.0001689594545957618,
|
452 |
+
"loss": 0.8382,
|
453 |
+
"step": 74
|
454 |
+
},
|
455 |
+
{
|
456 |
+
"epoch": 0.18,
|
457 |
+
"learning_rate": 0.00016782927833565472,
|
458 |
+
"loss": 0.9632,
|
459 |
+
"step": 75
|
460 |
+
},
|
461 |
+
{
|
462 |
+
"epoch": 0.18,
|
463 |
+
"learning_rate": 0.00016672148221383754,
|
464 |
+
"loss": 0.9494,
|
465 |
+
"step": 76
|
466 |
+
},
|
467 |
+
{
|
468 |
+
"epoch": 0.18,
|
469 |
+
"learning_rate": 0.00016563533721722828,
|
470 |
+
"loss": 0.9253,
|
471 |
+
"step": 77
|
472 |
+
},
|
473 |
+
{
|
474 |
+
"epoch": 0.19,
|
475 |
+
"learning_rate": 0.0001645701471510958,
|
476 |
+
"loss": 0.9143,
|
477 |
+
"step": 78
|
478 |
+
},
|
479 |
+
{
|
480 |
+
"epoch": 0.19,
|
481 |
+
"learning_rate": 0.00016352524676365398,
|
482 |
+
"loss": 0.8907,
|
483 |
+
"step": 79
|
484 |
+
},
|
485 |
+
{
|
486 |
+
"epoch": 0.19,
|
487 |
+
"learning_rate": 0.0001625,
|
488 |
+
"loss": 0.9748,
|
489 |
+
"step": 80
|
490 |
+
}
|
491 |
+
],
|
492 |
+
"logging_steps": 1,
|
493 |
+
"max_steps": 417,
|
494 |
+
"num_train_epochs": 1,
|
495 |
+
"save_steps": 10,
|
496 |
+
"total_flos": 2.5917530675871744e+16,
|
497 |
+
"trial_name": null,
|
498 |
+
"trial_params": null
|
499 |
+
}
|
checkpoint-80/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:482256ef65b59af088490f9e3870f1b868a90992cd6294900bd43d13ef410480
|
3 |
+
size 4536
|
checkpoint-90/README.md
ADDED
@@ -0,0 +1,220 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: peft
|
3 |
+
base_model: unsloth/llama-2-7b
|
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 |
+
|
201 |
+
|
202 |
+
## Training procedure
|
203 |
+
|
204 |
+
|
205 |
+
The following `bitsandbytes` quantization config was used during training:
|
206 |
+
- quant_method: bitsandbytes
|
207 |
+
- load_in_8bit: False
|
208 |
+
- load_in_4bit: True
|
209 |
+
- llm_int8_threshold: 6.0
|
210 |
+
- llm_int8_skip_modules: None
|
211 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
212 |
+
- llm_int8_has_fp16_weight: False
|
213 |
+
- bnb_4bit_quant_type: nf4
|
214 |
+
- bnb_4bit_use_double_quant: True
|
215 |
+
- bnb_4bit_compute_dtype: bfloat16
|
216 |
+
|
217 |
+
### Framework versions
|
218 |
+
|
219 |
+
|
220 |
+
- PEFT 0.6.2
|
checkpoint-90/adapter_config.json
ADDED
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "unsloth/llama-2-7b",
|
5 |
+
"bias": "none",
|
6 |
+
"fan_in_fan_out": false,
|
7 |
+
"inference_mode": true,
|
8 |
+
"init_lora_weights": true,
|
9 |
+
"layers_pattern": null,
|
10 |
+
"layers_to_transform": null,
|
11 |
+
"lora_alpha": 32,
|
12 |
+
"lora_dropout": 0,
|
13 |
+
"modules_to_save": null,
|
14 |
+
"peft_type": "LORA",
|
15 |
+
"r": 16,
|
16 |
+
"rank_pattern": {},
|
17 |
+
"revision": null,
|
18 |
+
"target_modules": [
|
19 |
+
"o_proj",
|
20 |
+
"up_proj",
|
21 |
+
"down_proj",
|
22 |
+
"q_proj",
|
23 |
+
"k_proj",
|
24 |
+
"v_proj",
|
25 |
+
"gate_proj"
|
26 |
+
],
|
27 |
+
"task_type": "CAUSAL_LM"
|
28 |
+
}
|
checkpoint-90/adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:351c23da56b4cc54ecd06069484fb435da7dbe8d494862dc600081ac95939f3e
|
3 |
+
size 159967880
|
checkpoint-90/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f6fe15fe30435e02f95eae519a4d54f175c25c64f13b10997c9d389880aa095f
|
3 |
+
size 80630612
|
checkpoint-90/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:203e9bfabd925cb4ec7129d24877156fcee87215187c35a867e358e56a9425a4
|
3 |
+
size 14244
|
checkpoint-90/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:422a39896586b55e3cf9fa259c2974dc0869f487be4c61f453a4bc7adf508043
|
3 |
+
size 1064
|
checkpoint-90/trainer_state.json
ADDED
@@ -0,0 +1,559 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.2158273381294964,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 90,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.0,
|
13 |
+
"learning_rate": 0.00013,
|
14 |
+
"loss": 1.1241,
|
15 |
+
"step": 1
|
16 |
+
},
|
17 |
+
{
|
18 |
+
"epoch": 0.0,
|
19 |
+
"learning_rate": 0.00026,
|
20 |
+
"loss": 1.0107,
|
21 |
+
"step": 2
|
22 |
+
},
|
23 |
+
{
|
24 |
+
"epoch": 0.01,
|
25 |
+
"learning_rate": 0.00039,
|
26 |
+
"loss": 1.1086,
|
27 |
+
"step": 3
|
28 |
+
},
|
29 |
+
{
|
30 |
+
"epoch": 0.01,
|
31 |
+
"learning_rate": 0.00052,
|
32 |
+
"loss": 1.0044,
|
33 |
+
"step": 4
|
34 |
+
},
|
35 |
+
{
|
36 |
+
"epoch": 0.01,
|
37 |
+
"learning_rate": 0.00065,
|
38 |
+
"loss": 1.0496,
|
39 |
+
"step": 5
|
40 |
+
},
|
41 |
+
{
|
42 |
+
"epoch": 0.01,
|
43 |
+
"learning_rate": 0.0005933661039639299,
|
44 |
+
"loss": 1.0199,
|
45 |
+
"step": 6
|
46 |
+
},
|
47 |
+
{
|
48 |
+
"epoch": 0.02,
|
49 |
+
"learning_rate": 0.0005493502655735357,
|
50 |
+
"loss": 1.0198,
|
51 |
+
"step": 7
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.02,
|
55 |
+
"learning_rate": 0.0005138701197773616,
|
56 |
+
"loss": 0.969,
|
57 |
+
"step": 8
|
58 |
+
},
|
59 |
+
{
|
60 |
+
"epoch": 0.02,
|
61 |
+
"learning_rate": 0.0004844813951249544,
|
62 |
+
"loss": 0.9383,
|
63 |
+
"step": 9
|
64 |
+
},
|
65 |
+
{
|
66 |
+
"epoch": 0.02,
|
67 |
+
"learning_rate": 0.0004596194077712558,
|
68 |
+
"loss": 0.8776,
|
69 |
+
"step": 10
|
70 |
+
},
|
71 |
+
{
|
72 |
+
"epoch": 0.03,
|
73 |
+
"learning_rate": 0.0004382299106011073,
|
74 |
+
"loss": 1.0173,
|
75 |
+
"step": 11
|
76 |
+
},
|
77 |
+
{
|
78 |
+
"epoch": 0.03,
|
79 |
+
"learning_rate": 0.0004195731958391368,
|
80 |
+
"loss": 1.1173,
|
81 |
+
"step": 12
|
82 |
+
},
|
83 |
+
{
|
84 |
+
"epoch": 0.03,
|
85 |
+
"learning_rate": 0.0004031128874149274,
|
86 |
+
"loss": 1.0876,
|
87 |
+
"step": 13
|
88 |
+
},
|
89 |
+
{
|
90 |
+
"epoch": 0.03,
|
91 |
+
"learning_rate": 0.0003884492980336779,
|
92 |
+
"loss": 1.0524,
|
93 |
+
"step": 14
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 0.04,
|
97 |
+
"learning_rate": 0.0003752776749732568,
|
98 |
+
"loss": 0.8953,
|
99 |
+
"step": 15
|
100 |
+
},
|
101 |
+
{
|
102 |
+
"epoch": 0.04,
|
103 |
+
"learning_rate": 0.00036336104634371584,
|
104 |
+
"loss": 1.1335,
|
105 |
+
"step": 16
|
106 |
+
},
|
107 |
+
{
|
108 |
+
"epoch": 0.04,
|
109 |
+
"learning_rate": 0.00035251199395531623,
|
110 |
+
"loss": 0.9837,
|
111 |
+
"step": 17
|
112 |
+
},
|
113 |
+
{
|
114 |
+
"epoch": 0.04,
|
115 |
+
"learning_rate": 0.00034258007985157445,
|
116 |
+
"loss": 0.9707,
|
117 |
+
"step": 18
|
118 |
+
},
|
119 |
+
{
|
120 |
+
"epoch": 0.05,
|
121 |
+
"learning_rate": 0.0003334429644276751,
|
122 |
+
"loss": 0.9149,
|
123 |
+
"step": 19
|
124 |
+
},
|
125 |
+
{
|
126 |
+
"epoch": 0.05,
|
127 |
+
"learning_rate": 0.000325,
|
128 |
+
"loss": 1.0043,
|
129 |
+
"step": 20
|
130 |
+
},
|
131 |
+
{
|
132 |
+
"epoch": 0.05,
|
133 |
+
"learning_rate": 0.00031716752370827323,
|
134 |
+
"loss": 1.001,
|
135 |
+
"step": 21
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 0.05,
|
139 |
+
"learning_rate": 0.00030987534150481746,
|
140 |
+
"loss": 1.0395,
|
141 |
+
"step": 22
|
142 |
+
},
|
143 |
+
{
|
144 |
+
"epoch": 0.06,
|
145 |
+
"learning_rate": 0.000303064062678102,
|
146 |
+
"loss": 0.8718,
|
147 |
+
"step": 23
|
148 |
+
},
|
149 |
+
{
|
150 |
+
"epoch": 0.06,
|
151 |
+
"learning_rate": 0.00029668305198196496,
|
152 |
+
"loss": 1.1114,
|
153 |
+
"step": 24
|
154 |
+
},
|
155 |
+
{
|
156 |
+
"epoch": 0.06,
|
157 |
+
"learning_rate": 0.00029068883707497264,
|
158 |
+
"loss": 0.7765,
|
159 |
+
"step": 25
|
160 |
+
},
|
161 |
+
{
|
162 |
+
"epoch": 0.06,
|
163 |
+
"learning_rate": 0.0002850438562747845,
|
164 |
+
"loss": 0.9522,
|
165 |
+
"step": 26
|
166 |
+
},
|
167 |
+
{
|
168 |
+
"epoch": 0.06,
|
169 |
+
"learning_rate": 0.00027971546389275785,
|
170 |
+
"loss": 0.9588,
|
171 |
+
"step": 27
|
172 |
+
},
|
173 |
+
{
|
174 |
+
"epoch": 0.07,
|
175 |
+
"learning_rate": 0.00027467513278676785,
|
176 |
+
"loss": 1.0313,
|
177 |
+
"step": 28
|
178 |
+
},
|
179 |
+
{
|
180 |
+
"epoch": 0.07,
|
181 |
+
"learning_rate": 0.0002698978095246549,
|
182 |
+
"loss": 0.9338,
|
183 |
+
"step": 29
|
184 |
+
},
|
185 |
+
{
|
186 |
+
"epoch": 0.07,
|
187 |
+
"learning_rate": 0.000265361388801511,
|
188 |
+
"loss": 0.892,
|
189 |
+
"step": 30
|
190 |
+
},
|
191 |
+
{
|
192 |
+
"epoch": 0.07,
|
193 |
+
"learning_rate": 0.00026104628189331215,
|
194 |
+
"loss": 0.893,
|
195 |
+
"step": 31
|
196 |
+
},
|
197 |
+
{
|
198 |
+
"epoch": 0.08,
|
199 |
+
"learning_rate": 0.0002569350598886808,
|
200 |
+
"loss": 0.8983,
|
201 |
+
"step": 32
|
202 |
+
},
|
203 |
+
{
|
204 |
+
"epoch": 0.08,
|
205 |
+
"learning_rate": 0.00025301215685249496,
|
206 |
+
"loss": 0.9277,
|
207 |
+
"step": 33
|
208 |
+
},
|
209 |
+
{
|
210 |
+
"epoch": 0.08,
|
211 |
+
"learning_rate": 0.00024926362137539537,
|
212 |
+
"loss": 0.8962,
|
213 |
+
"step": 34
|
214 |
+
},
|
215 |
+
{
|
216 |
+
"epoch": 0.08,
|
217 |
+
"learning_rate": 0.00024567690745599767,
|
218 |
+
"loss": 0.9124,
|
219 |
+
"step": 35
|
220 |
+
},
|
221 |
+
{
|
222 |
+
"epoch": 0.09,
|
223 |
+
"learning_rate": 0.0002422406975624772,
|
224 |
+
"loss": 0.9535,
|
225 |
+
"step": 36
|
226 |
+
},
|
227 |
+
{
|
228 |
+
"epoch": 0.09,
|
229 |
+
"learning_rate": 0.00023894475218048754,
|
230 |
+
"loss": 0.9019,
|
231 |
+
"step": 37
|
232 |
+
},
|
233 |
+
{
|
234 |
+
"epoch": 0.09,
|
235 |
+
"learning_rate": 0.0002357797812857538,
|
236 |
+
"loss": 1.024,
|
237 |
+
"step": 38
|
238 |
+
},
|
239 |
+
{
|
240 |
+
"epoch": 0.09,
|
241 |
+
"learning_rate": 0.00023273733406281566,
|
242 |
+
"loss": 0.8549,
|
243 |
+
"step": 39
|
244 |
+
},
|
245 |
+
{
|
246 |
+
"epoch": 0.1,
|
247 |
+
"learning_rate": 0.0002298097038856279,
|
248 |
+
"loss": 1.0489,
|
249 |
+
"step": 40
|
250 |
+
},
|
251 |
+
{
|
252 |
+
"epoch": 0.1,
|
253 |
+
"learning_rate": 0.00022698984612511293,
|
254 |
+
"loss": 0.751,
|
255 |
+
"step": 41
|
256 |
+
},
|
257 |
+
{
|
258 |
+
"epoch": 0.1,
|
259 |
+
"learning_rate": 0.00022427130678626507,
|
260 |
+
"loss": 0.834,
|
261 |
+
"step": 42
|
262 |
+
},
|
263 |
+
{
|
264 |
+
"epoch": 0.1,
|
265 |
+
"learning_rate": 0.00022164816032790388,
|
266 |
+
"loss": 0.889,
|
267 |
+
"step": 43
|
268 |
+
},
|
269 |
+
{
|
270 |
+
"epoch": 0.11,
|
271 |
+
"learning_rate": 0.00021911495530055366,
|
272 |
+
"loss": 1.0103,
|
273 |
+
"step": 44
|
274 |
+
},
|
275 |
+
{
|
276 |
+
"epoch": 0.11,
|
277 |
+
"learning_rate": 0.00021666666666666666,
|
278 |
+
"loss": 0.8766,
|
279 |
+
"step": 45
|
280 |
+
},
|
281 |
+
{
|
282 |
+
"epoch": 0.11,
|
283 |
+
"learning_rate": 0.0002142986538536308,
|
284 |
+
"loss": 0.8181,
|
285 |
+
"step": 46
|
286 |
+
},
|
287 |
+
{
|
288 |
+
"epoch": 0.11,
|
289 |
+
"learning_rate": 0.0002120066237423687,
|
290 |
+
"loss": 0.8754,
|
291 |
+
"step": 47
|
292 |
+
},
|
293 |
+
{
|
294 |
+
"epoch": 0.12,
|
295 |
+
"learning_rate": 0.0002097865979195684,
|
296 |
+
"loss": 0.9038,
|
297 |
+
"step": 48
|
298 |
+
},
|
299 |
+
{
|
300 |
+
"epoch": 0.12,
|
301 |
+
"learning_rate": 0.00020763488362498048,
|
302 |
+
"loss": 0.8646,
|
303 |
+
"step": 49
|
304 |
+
},
|
305 |
+
{
|
306 |
+
"epoch": 0.12,
|
307 |
+
"learning_rate": 0.00020554804791094464,
|
308 |
+
"loss": 0.8836,
|
309 |
+
"step": 50
|
310 |
+
},
|
311 |
+
{
|
312 |
+
"epoch": 0.12,
|
313 |
+
"learning_rate": 0.0002035228946026736,
|
314 |
+
"loss": 0.9962,
|
315 |
+
"step": 51
|
316 |
+
},
|
317 |
+
{
|
318 |
+
"epoch": 0.12,
|
319 |
+
"learning_rate": 0.0002015564437074637,
|
320 |
+
"loss": 0.8835,
|
321 |
+
"step": 52
|
322 |
+
},
|
323 |
+
{
|
324 |
+
"epoch": 0.13,
|
325 |
+
"learning_rate": 0.00019964591297103414,
|
326 |
+
"loss": 0.9196,
|
327 |
+
"step": 53
|
328 |
+
},
|
329 |
+
{
|
330 |
+
"epoch": 0.13,
|
331 |
+
"learning_rate": 0.00019778870132130996,
|
332 |
+
"loss": 0.8995,
|
333 |
+
"step": 54
|
334 |
+
},
|
335 |
+
{
|
336 |
+
"epoch": 0.13,
|
337 |
+
"learning_rate": 0.00019598237397554634,
|
338 |
+
"loss": 1.0178,
|
339 |
+
"step": 55
|
340 |
+
},
|
341 |
+
{
|
342 |
+
"epoch": 0.13,
|
343 |
+
"learning_rate": 0.00019422464901683895,
|
344 |
+
"loss": 0.9395,
|
345 |
+
"step": 56
|
346 |
+
},
|
347 |
+
{
|
348 |
+
"epoch": 0.14,
|
349 |
+
"learning_rate": 0.00019251338527170498,
|
350 |
+
"loss": 0.9882,
|
351 |
+
"step": 57
|
352 |
+
},
|
353 |
+
{
|
354 |
+
"epoch": 0.14,
|
355 |
+
"learning_rate": 0.00019084657134227863,
|
356 |
+
"loss": 0.9274,
|
357 |
+
"step": 58
|
358 |
+
},
|
359 |
+
{
|
360 |
+
"epoch": 0.14,
|
361 |
+
"learning_rate": 0.00018922231566536414,
|
362 |
+
"loss": 0.9517,
|
363 |
+
"step": 59
|
364 |
+
},
|
365 |
+
{
|
366 |
+
"epoch": 0.14,
|
367 |
+
"learning_rate": 0.0001876388374866284,
|
368 |
+
"loss": 0.865,
|
369 |
+
"step": 60
|
370 |
+
},
|
371 |
+
{
|
372 |
+
"epoch": 0.15,
|
373 |
+
"learning_rate": 0.00018609445865200715,
|
374 |
+
"loss": 0.9314,
|
375 |
+
"step": 61
|
376 |
+
},
|
377 |
+
{
|
378 |
+
"epoch": 0.15,
|
379 |
+
"learning_rate": 0.00018458759613029606,
|
380 |
+
"loss": 0.9224,
|
381 |
+
"step": 62
|
382 |
+
},
|
383 |
+
{
|
384 |
+
"epoch": 0.15,
|
385 |
+
"learning_rate": 0.00018311675519117857,
|
386 |
+
"loss": 0.788,
|
387 |
+
"step": 63
|
388 |
+
},
|
389 |
+
{
|
390 |
+
"epoch": 0.15,
|
391 |
+
"learning_rate": 0.00018168052317185792,
|
392 |
+
"loss": 0.9739,
|
393 |
+
"step": 64
|
394 |
+
},
|
395 |
+
{
|
396 |
+
"epoch": 0.16,
|
397 |
+
"learning_rate": 0.00018027756377319947,
|
398 |
+
"loss": 0.9419,
|
399 |
+
"step": 65
|
400 |
+
},
|
401 |
+
{
|
402 |
+
"epoch": 0.16,
|
403 |
+
"learning_rate": 0.0001789066118330336,
|
404 |
+
"loss": 0.8772,
|
405 |
+
"step": 66
|
406 |
+
},
|
407 |
+
{
|
408 |
+
"epoch": 0.16,
|
409 |
+
"learning_rate": 0.00017756646853014972,
|
410 |
+
"loss": 0.8707,
|
411 |
+
"step": 67
|
412 |
+
},
|
413 |
+
{
|
414 |
+
"epoch": 0.16,
|
415 |
+
"learning_rate": 0.00017625599697765812,
|
416 |
+
"loss": 0.8089,
|
417 |
+
"step": 68
|
418 |
+
},
|
419 |
+
{
|
420 |
+
"epoch": 0.17,
|
421 |
+
"learning_rate": 0.00017497411816890378,
|
422 |
+
"loss": 0.9303,
|
423 |
+
"step": 69
|
424 |
+
},
|
425 |
+
{
|
426 |
+
"epoch": 0.17,
|
427 |
+
"learning_rate": 0.00017371980724307585,
|
428 |
+
"loss": 0.9161,
|
429 |
+
"step": 70
|
430 |
+
},
|
431 |
+
{
|
432 |
+
"epoch": 0.17,
|
433 |
+
"learning_rate": 0.00017249209004113945,
|
434 |
+
"loss": 0.9064,
|
435 |
+
"step": 71
|
436 |
+
},
|
437 |
+
{
|
438 |
+
"epoch": 0.17,
|
439 |
+
"learning_rate": 0.00017129003992578723,
|
440 |
+
"loss": 1.0988,
|
441 |
+
"step": 72
|
442 |
+
},
|
443 |
+
{
|
444 |
+
"epoch": 0.18,
|
445 |
+
"learning_rate": 0.00017011277484181944,
|
446 |
+
"loss": 0.9804,
|
447 |
+
"step": 73
|
448 |
+
},
|
449 |
+
{
|
450 |
+
"epoch": 0.18,
|
451 |
+
"learning_rate": 0.0001689594545957618,
|
452 |
+
"loss": 0.8382,
|
453 |
+
"step": 74
|
454 |
+
},
|
455 |
+
{
|
456 |
+
"epoch": 0.18,
|
457 |
+
"learning_rate": 0.00016782927833565472,
|
458 |
+
"loss": 0.9632,
|
459 |
+
"step": 75
|
460 |
+
},
|
461 |
+
{
|
462 |
+
"epoch": 0.18,
|
463 |
+
"learning_rate": 0.00016672148221383754,
|
464 |
+
"loss": 0.9494,
|
465 |
+
"step": 76
|
466 |
+
},
|
467 |
+
{
|
468 |
+
"epoch": 0.18,
|
469 |
+
"learning_rate": 0.00016563533721722828,
|
470 |
+
"loss": 0.9253,
|
471 |
+
"step": 77
|
472 |
+
},
|
473 |
+
{
|
474 |
+
"epoch": 0.19,
|
475 |
+
"learning_rate": 0.0001645701471510958,
|
476 |
+
"loss": 0.9143,
|
477 |
+
"step": 78
|
478 |
+
},
|
479 |
+
{
|
480 |
+
"epoch": 0.19,
|
481 |
+
"learning_rate": 0.00016352524676365398,
|
482 |
+
"loss": 0.8907,
|
483 |
+
"step": 79
|
484 |
+
},
|
485 |
+
{
|
486 |
+
"epoch": 0.19,
|
487 |
+
"learning_rate": 0.0001625,
|
488 |
+
"loss": 0.9748,
|
489 |
+
"step": 80
|
490 |
+
},
|
491 |
+
{
|
492 |
+
"epoch": 0.19,
|
493 |
+
"learning_rate": 0.00016149379837498482,
|
494 |
+
"loss": 0.893,
|
495 |
+
"step": 81
|
496 |
+
},
|
497 |
+
{
|
498 |
+
"epoch": 0.2,
|
499 |
+
"learning_rate": 0.00016050605945555833,
|
500 |
+
"loss": 0.839,
|
501 |
+
"step": 82
|
502 |
+
},
|
503 |
+
{
|
504 |
+
"epoch": 0.2,
|
505 |
+
"learning_rate": 0.0001595362254439902,
|
506 |
+
"loss": 0.9276,
|
507 |
+
"step": 83
|
508 |
+
},
|
509 |
+
{
|
510 |
+
"epoch": 0.2,
|
511 |
+
"learning_rate": 0.00015858376185413662,
|
512 |
+
"loss": 0.8758,
|
513 |
+
"step": 84
|
514 |
+
},
|
515 |
+
{
|
516 |
+
"epoch": 0.2,
|
517 |
+
"learning_rate": 0.00015764815627361642,
|
518 |
+
"loss": 0.9125,
|
519 |
+
"step": 85
|
520 |
+
},
|
521 |
+
{
|
522 |
+
"epoch": 0.21,
|
523 |
+
"learning_rate": 0.00015672891720538393,
|
524 |
+
"loss": 0.955,
|
525 |
+
"step": 86
|
526 |
+
},
|
527 |
+
{
|
528 |
+
"epoch": 0.21,
|
529 |
+
"learning_rate": 0.00015582557298274985,
|
530 |
+
"loss": 0.9104,
|
531 |
+
"step": 87
|
532 |
+
},
|
533 |
+
{
|
534 |
+
"epoch": 0.21,
|
535 |
+
"learning_rate": 0.00015493767075240873,
|
536 |
+
"loss": 0.8861,
|
537 |
+
"step": 88
|
538 |
+
},
|
539 |
+
{
|
540 |
+
"epoch": 0.21,
|
541 |
+
"learning_rate": 0.0001540647755204926,
|
542 |
+
"loss": 0.9693,
|
543 |
+
"step": 89
|
544 |
+
},
|
545 |
+
{
|
546 |
+
"epoch": 0.22,
|
547 |
+
"learning_rate": 0.0001532064692570853,
|
548 |
+
"loss": 0.7245,
|
549 |
+
"step": 90
|
550 |
+
}
|
551 |
+
],
|
552 |
+
"logging_steps": 1,
|
553 |
+
"max_steps": 417,
|
554 |
+
"num_train_epochs": 1,
|
555 |
+
"save_steps": 10,
|
556 |
+
"total_flos": 2.9172058829881344e+16,
|
557 |
+
"trial_name": null,
|
558 |
+
"trial_params": null
|
559 |
+
}
|
checkpoint-90/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:482256ef65b59af088490f9e3870f1b868a90992cd6294900bd43d13ef410480
|
3 |
+
size 4536
|