trinhxuankhai
commited on
Commit
•
2f0f096
1
Parent(s):
ada1b59
Upload folder using huggingface_hub
Browse files- README.md +204 -0
- adapter_config.json +29 -0
- adapter_model.bin +3 -0
- qwen.tiktoken +0 -0
- special_tokens_map.json +3 -0
- tokenizer_config.json +12 -0
- trainer_state.json +374 -0
- training_args.bin +3 -0
README.md
ADDED
@@ -0,0 +1,204 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: peft
|
3 |
+
base_model: Qwen/Qwen-VL-Chat
|
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 |
+
### Framework versions
|
203 |
+
|
204 |
+
- PEFT 0.8.2
|
adapter_config.json
ADDED
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "Qwen/Qwen-VL-Chat",
|
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 |
+
"loftq_config": {},
|
12 |
+
"lora_alpha": 16,
|
13 |
+
"lora_dropout": 0.05,
|
14 |
+
"megatron_config": null,
|
15 |
+
"megatron_core": "megatron.core",
|
16 |
+
"modules_to_save": null,
|
17 |
+
"peft_type": "LORA",
|
18 |
+
"r": 64,
|
19 |
+
"rank_pattern": {},
|
20 |
+
"revision": null,
|
21 |
+
"target_modules": [
|
22 |
+
"attn.c_proj",
|
23 |
+
"w1",
|
24 |
+
"c_attn",
|
25 |
+
"w2"
|
26 |
+
],
|
27 |
+
"task_type": "CAUSAL_LM",
|
28 |
+
"use_rslora": false
|
29 |
+
}
|
adapter_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8b78beea85fcd5563f93a9218669ea9805767999bf972a2136a3844b08d6c94c
|
3 |
+
size 224482573
|
qwen.tiktoken
ADDED
The diff for this file is too large to render.
See raw diff
|
|
special_tokens_map.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"pad_token": "<|endoftext|>"
|
3 |
+
}
|
tokenizer_config.json
ADDED
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"auto_map": {
|
3 |
+
"AutoTokenizer": [
|
4 |
+
"Qwen/Qwen-VL-Chat--tokenization_qwen.QWenTokenizer",
|
5 |
+
null
|
6 |
+
]
|
7 |
+
},
|
8 |
+
"clean_up_tokenization_spaces": true,
|
9 |
+
"model_max_length": 1024,
|
10 |
+
"padding_side": "right",
|
11 |
+
"tokenizer_class": "QWenTokenizer"
|
12 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,374 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 4.827586206896552,
|
5 |
+
"eval_steps": 2,
|
6 |
+
"global_step": 35,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.14,
|
13 |
+
"learning_rate": 0.0001,
|
14 |
+
"loss": 0.7533,
|
15 |
+
"step": 1
|
16 |
+
},
|
17 |
+
{
|
18 |
+
"epoch": 0.28,
|
19 |
+
"learning_rate": 9.978670881475172e-05,
|
20 |
+
"loss": 0.8025,
|
21 |
+
"step": 2
|
22 |
+
},
|
23 |
+
{
|
24 |
+
"epoch": 0.28,
|
25 |
+
"eval_loss": 0.6696242094039917,
|
26 |
+
"eval_runtime": 44.2051,
|
27 |
+
"eval_samples_per_second": 1.968,
|
28 |
+
"eval_steps_per_second": 1.968,
|
29 |
+
"step": 2
|
30 |
+
},
|
31 |
+
{
|
32 |
+
"epoch": 0.41,
|
33 |
+
"learning_rate": 9.91486549841951e-05,
|
34 |
+
"loss": 0.6626,
|
35 |
+
"step": 3
|
36 |
+
},
|
37 |
+
{
|
38 |
+
"epoch": 0.55,
|
39 |
+
"learning_rate": 9.809128215864097e-05,
|
40 |
+
"loss": 0.6912,
|
41 |
+
"step": 4
|
42 |
+
},
|
43 |
+
{
|
44 |
+
"epoch": 0.55,
|
45 |
+
"eval_loss": 0.6283016800880432,
|
46 |
+
"eval_runtime": 44.1458,
|
47 |
+
"eval_samples_per_second": 1.971,
|
48 |
+
"eval_steps_per_second": 1.971,
|
49 |
+
"step": 4
|
50 |
+
},
|
51 |
+
{
|
52 |
+
"epoch": 0.69,
|
53 |
+
"learning_rate": 9.662361147021779e-05,
|
54 |
+
"loss": 0.5708,
|
55 |
+
"step": 5
|
56 |
+
},
|
57 |
+
{
|
58 |
+
"epoch": 0.83,
|
59 |
+
"learning_rate": 9.475816456775313e-05,
|
60 |
+
"loss": 0.6832,
|
61 |
+
"step": 6
|
62 |
+
},
|
63 |
+
{
|
64 |
+
"epoch": 0.83,
|
65 |
+
"eval_loss": 0.6122540235519409,
|
66 |
+
"eval_runtime": 44.1996,
|
67 |
+
"eval_samples_per_second": 1.968,
|
68 |
+
"eval_steps_per_second": 1.968,
|
69 |
+
"step": 6
|
70 |
+
},
|
71 |
+
{
|
72 |
+
"epoch": 0.97,
|
73 |
+
"learning_rate": 9.251085678648072e-05,
|
74 |
+
"loss": 0.601,
|
75 |
+
"step": 7
|
76 |
+
},
|
77 |
+
{
|
78 |
+
"epoch": 1.1,
|
79 |
+
"learning_rate": 8.9900861364012e-05,
|
80 |
+
"loss": 0.6154,
|
81 |
+
"step": 8
|
82 |
+
},
|
83 |
+
{
|
84 |
+
"epoch": 1.1,
|
85 |
+
"eval_loss": 0.6039846539497375,
|
86 |
+
"eval_runtime": 44.163,
|
87 |
+
"eval_samples_per_second": 1.97,
|
88 |
+
"eval_steps_per_second": 1.97,
|
89 |
+
"step": 8
|
90 |
+
},
|
91 |
+
{
|
92 |
+
"epoch": 1.24,
|
93 |
+
"learning_rate": 8.695044586103296e-05,
|
94 |
+
"loss": 0.5479,
|
95 |
+
"step": 9
|
96 |
+
},
|
97 |
+
{
|
98 |
+
"epoch": 1.38,
|
99 |
+
"learning_rate": 8.368478218232787e-05,
|
100 |
+
"loss": 0.5438,
|
101 |
+
"step": 10
|
102 |
+
},
|
103 |
+
{
|
104 |
+
"epoch": 1.38,
|
105 |
+
"eval_loss": 0.5960671901702881,
|
106 |
+
"eval_runtime": 44.0267,
|
107 |
+
"eval_samples_per_second": 1.976,
|
108 |
+
"eval_steps_per_second": 1.976,
|
109 |
+
"step": 10
|
110 |
+
},
|
111 |
+
{
|
112 |
+
"epoch": 1.52,
|
113 |
+
"learning_rate": 8.013173181896283e-05,
|
114 |
+
"loss": 0.6171,
|
115 |
+
"step": 11
|
116 |
+
},
|
117 |
+
{
|
118 |
+
"epoch": 1.66,
|
119 |
+
"learning_rate": 7.63216081438678e-05,
|
120 |
+
"loss": 0.5781,
|
121 |
+
"step": 12
|
122 |
+
},
|
123 |
+
{
|
124 |
+
"epoch": 1.66,
|
125 |
+
"eval_loss": 0.5879073143005371,
|
126 |
+
"eval_runtime": 43.9085,
|
127 |
+
"eval_samples_per_second": 1.981,
|
128 |
+
"eval_steps_per_second": 1.981,
|
129 |
+
"step": 12
|
130 |
+
},
|
131 |
+
{
|
132 |
+
"epoch": 1.79,
|
133 |
+
"learning_rate": 7.228691778882693e-05,
|
134 |
+
"loss": 0.5811,
|
135 |
+
"step": 13
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 1.93,
|
139 |
+
"learning_rate": 6.806208330935766e-05,
|
140 |
+
"loss": 0.4899,
|
141 |
+
"step": 14
|
142 |
+
},
|
143 |
+
{
|
144 |
+
"epoch": 1.93,
|
145 |
+
"eval_loss": 0.5821757912635803,
|
146 |
+
"eval_runtime": 43.9108,
|
147 |
+
"eval_samples_per_second": 1.981,
|
148 |
+
"eval_steps_per_second": 1.981,
|
149 |
+
"step": 14
|
150 |
+
},
|
151 |
+
{
|
152 |
+
"epoch": 2.07,
|
153 |
+
"learning_rate": 6.368314950360415e-05,
|
154 |
+
"loss": 0.4649,
|
155 |
+
"step": 15
|
156 |
+
},
|
157 |
+
{
|
158 |
+
"epoch": 2.21,
|
159 |
+
"learning_rate": 5.918747589082853e-05,
|
160 |
+
"loss": 0.5615,
|
161 |
+
"step": 16
|
162 |
+
},
|
163 |
+
{
|
164 |
+
"epoch": 2.21,
|
165 |
+
"eval_loss": 0.5788118839263916,
|
166 |
+
"eval_runtime": 43.9641,
|
167 |
+
"eval_samples_per_second": 1.979,
|
168 |
+
"eval_steps_per_second": 1.979,
|
169 |
+
"step": 16
|
170 |
+
},
|
171 |
+
{
|
172 |
+
"epoch": 2.34,
|
173 |
+
"learning_rate": 5.4613417973165106e-05,
|
174 |
+
"loss": 0.4919,
|
175 |
+
"step": 17
|
176 |
+
},
|
177 |
+
{
|
178 |
+
"epoch": 2.48,
|
179 |
+
"learning_rate": 5e-05,
|
180 |
+
"loss": 0.4755,
|
181 |
+
"step": 18
|
182 |
+
},
|
183 |
+
{
|
184 |
+
"epoch": 2.48,
|
185 |
+
"eval_loss": 0.5790432691574097,
|
186 |
+
"eval_runtime": 43.9953,
|
187 |
+
"eval_samples_per_second": 1.977,
|
188 |
+
"eval_steps_per_second": 1.977,
|
189 |
+
"step": 18
|
190 |
+
},
|
191 |
+
{
|
192 |
+
"epoch": 2.62,
|
193 |
+
"learning_rate": 4.5386582026834906e-05,
|
194 |
+
"loss": 0.4525,
|
195 |
+
"step": 19
|
196 |
+
},
|
197 |
+
{
|
198 |
+
"epoch": 2.76,
|
199 |
+
"learning_rate": 4.0812524109171476e-05,
|
200 |
+
"loss": 0.4665,
|
201 |
+
"step": 20
|
202 |
+
},
|
203 |
+
{
|
204 |
+
"epoch": 2.76,
|
205 |
+
"eval_loss": 0.5807910561561584,
|
206 |
+
"eval_runtime": 44.0437,
|
207 |
+
"eval_samples_per_second": 1.975,
|
208 |
+
"eval_steps_per_second": 1.975,
|
209 |
+
"step": 20
|
210 |
+
},
|
211 |
+
{
|
212 |
+
"epoch": 2.9,
|
213 |
+
"learning_rate": 3.631685049639586e-05,
|
214 |
+
"loss": 0.5079,
|
215 |
+
"step": 21
|
216 |
+
},
|
217 |
+
{
|
218 |
+
"epoch": 3.03,
|
219 |
+
"learning_rate": 3.1937916690642356e-05,
|
220 |
+
"loss": 0.4525,
|
221 |
+
"step": 22
|
222 |
+
},
|
223 |
+
{
|
224 |
+
"epoch": 3.03,
|
225 |
+
"eval_loss": 0.5798379182815552,
|
226 |
+
"eval_runtime": 44.0127,
|
227 |
+
"eval_samples_per_second": 1.977,
|
228 |
+
"eval_steps_per_second": 1.977,
|
229 |
+
"step": 22
|
230 |
+
},
|
231 |
+
{
|
232 |
+
"epoch": 3.17,
|
233 |
+
"learning_rate": 2.771308221117309e-05,
|
234 |
+
"loss": 0.4697,
|
235 |
+
"step": 23
|
236 |
+
},
|
237 |
+
{
|
238 |
+
"epoch": 3.31,
|
239 |
+
"learning_rate": 2.3678391856132204e-05,
|
240 |
+
"loss": 0.4508,
|
241 |
+
"step": 24
|
242 |
+
},
|
243 |
+
{
|
244 |
+
"epoch": 3.31,
|
245 |
+
"eval_loss": 0.5790860056877136,
|
246 |
+
"eval_runtime": 44.0414,
|
247 |
+
"eval_samples_per_second": 1.975,
|
248 |
+
"eval_steps_per_second": 1.975,
|
249 |
+
"step": 24
|
250 |
+
},
|
251 |
+
{
|
252 |
+
"epoch": 3.45,
|
253 |
+
"learning_rate": 1.9868268181037185e-05,
|
254 |
+
"loss": 0.4566,
|
255 |
+
"step": 25
|
256 |
+
},
|
257 |
+
{
|
258 |
+
"epoch": 3.59,
|
259 |
+
"learning_rate": 1.631521781767214e-05,
|
260 |
+
"loss": 0.4934,
|
261 |
+
"step": 26
|
262 |
+
},
|
263 |
+
{
|
264 |
+
"epoch": 3.59,
|
265 |
+
"eval_loss": 0.5790104269981384,
|
266 |
+
"eval_runtime": 44.0612,
|
267 |
+
"eval_samples_per_second": 1.975,
|
268 |
+
"eval_steps_per_second": 1.975,
|
269 |
+
"step": 26
|
270 |
+
},
|
271 |
+
{
|
272 |
+
"epoch": 3.72,
|
273 |
+
"learning_rate": 1.3049554138967051e-05,
|
274 |
+
"loss": 0.3934,
|
275 |
+
"step": 27
|
276 |
+
},
|
277 |
+
{
|
278 |
+
"epoch": 3.86,
|
279 |
+
"learning_rate": 1.0099138635988026e-05,
|
280 |
+
"loss": 0.4291,
|
281 |
+
"step": 28
|
282 |
+
},
|
283 |
+
{
|
284 |
+
"epoch": 3.86,
|
285 |
+
"eval_loss": 0.5794057846069336,
|
286 |
+
"eval_runtime": 44.0534,
|
287 |
+
"eval_samples_per_second": 1.975,
|
288 |
+
"eval_steps_per_second": 1.975,
|
289 |
+
"step": 28
|
290 |
+
},
|
291 |
+
{
|
292 |
+
"epoch": 4.0,
|
293 |
+
"learning_rate": 7.489143213519301e-06,
|
294 |
+
"loss": 0.4485,
|
295 |
+
"step": 29
|
296 |
+
},
|
297 |
+
{
|
298 |
+
"epoch": 4.14,
|
299 |
+
"learning_rate": 5.241835432246889e-06,
|
300 |
+
"loss": 0.4624,
|
301 |
+
"step": 30
|
302 |
+
},
|
303 |
+
{
|
304 |
+
"epoch": 4.14,
|
305 |
+
"eval_loss": 0.5792465806007385,
|
306 |
+
"eval_runtime": 44.0238,
|
307 |
+
"eval_samples_per_second": 1.976,
|
308 |
+
"eval_steps_per_second": 1.976,
|
309 |
+
"step": 30
|
310 |
+
},
|
311 |
+
{
|
312 |
+
"epoch": 4.28,
|
313 |
+
"learning_rate": 3.376388529782215e-06,
|
314 |
+
"loss": 0.449,
|
315 |
+
"step": 31
|
316 |
+
},
|
317 |
+
{
|
318 |
+
"epoch": 4.41,
|
319 |
+
"learning_rate": 1.908717841359048e-06,
|
320 |
+
"loss": 0.4353,
|
321 |
+
"step": 32
|
322 |
+
},
|
323 |
+
{
|
324 |
+
"epoch": 4.41,
|
325 |
+
"eval_loss": 0.579724907875061,
|
326 |
+
"eval_runtime": 43.9242,
|
327 |
+
"eval_samples_per_second": 1.981,
|
328 |
+
"eval_steps_per_second": 1.981,
|
329 |
+
"step": 32
|
330 |
+
},
|
331 |
+
{
|
332 |
+
"epoch": 4.55,
|
333 |
+
"learning_rate": 8.513450158049108e-07,
|
334 |
+
"loss": 0.4108,
|
335 |
+
"step": 33
|
336 |
+
},
|
337 |
+
{
|
338 |
+
"epoch": 4.69,
|
339 |
+
"learning_rate": 2.1329118524827662e-07,
|
340 |
+
"loss": 0.4546,
|
341 |
+
"step": 34
|
342 |
+
},
|
343 |
+
{
|
344 |
+
"epoch": 4.69,
|
345 |
+
"eval_loss": 0.5798984169960022,
|
346 |
+
"eval_runtime": 43.9248,
|
347 |
+
"eval_samples_per_second": 1.981,
|
348 |
+
"eval_steps_per_second": 1.981,
|
349 |
+
"step": 34
|
350 |
+
},
|
351 |
+
{
|
352 |
+
"epoch": 4.83,
|
353 |
+
"learning_rate": 0.0,
|
354 |
+
"loss": 0.4189,
|
355 |
+
"step": 35
|
356 |
+
},
|
357 |
+
{
|
358 |
+
"epoch": 4.83,
|
359 |
+
"step": 35,
|
360 |
+
"total_flos": 9.3962984585429e+16,
|
361 |
+
"train_loss": 0.5252525525433677,
|
362 |
+
"train_runtime": 2623.1378,
|
363 |
+
"train_samples_per_second": 0.66,
|
364 |
+
"train_steps_per_second": 0.013
|
365 |
+
}
|
366 |
+
],
|
367 |
+
"logging_steps": 1.0,
|
368 |
+
"max_steps": 35,
|
369 |
+
"num_train_epochs": 5,
|
370 |
+
"save_steps": 4,
|
371 |
+
"total_flos": 9.3962984585429e+16,
|
372 |
+
"trial_name": null,
|
373 |
+
"trial_params": null
|
374 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:014db1faf04fd670bfb2f795d2109fb3493541b330e4a093fc005b7a29a7a32d
|
3 |
+
size 4155
|