Commit
•
f8946de
1
Parent(s):
1431517
Upload folder using huggingface_hub
Browse files- README.md +80 -0
- adapter_config.json +28 -0
- adapter_model.bin +3 -0
- checkpoint-115/README.md +220 -0
- checkpoint-115/adapter_config.json +28 -0
- checkpoint-115/adapter_model.safetensors +3 -0
- checkpoint-115/optimizer.pt +3 -0
- checkpoint-115/rng_state.pth +3 -0
- checkpoint-115/scheduler.pt +3 -0
- checkpoint-115/trainer_state.json +869 -0
- checkpoint-115/training_args.bin +3 -0
- config.json +37 -0
- special_tokens_map.json +24 -0
- tokenizer.model +3 -0
- tokenizer_config.json +44 -0
README.md
ADDED
@@ -0,0 +1,80 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
base_model: mistralai/Mistral-7B-v0.1
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
model-index:
|
7 |
+
- name: storage/context
|
8 |
+
results: []
|
9 |
+
---
|
10 |
+
|
11 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
12 |
+
should probably proofread and complete it, then remove this comment. -->
|
13 |
+
|
14 |
+
[<img src="https://raw.githubusercontent.com/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/OpenAccess-AI-Collective/axolotl)
|
15 |
+
# storage/context
|
16 |
+
|
17 |
+
This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on the None dataset.
|
18 |
+
It achieves the following results on the evaluation set:
|
19 |
+
- Loss: 0.0253
|
20 |
+
|
21 |
+
## Model description
|
22 |
+
|
23 |
+
More information needed
|
24 |
+
|
25 |
+
## Intended uses & limitations
|
26 |
+
|
27 |
+
More information needed
|
28 |
+
|
29 |
+
## Training and evaluation data
|
30 |
+
|
31 |
+
More information needed
|
32 |
+
|
33 |
+
## Training procedure
|
34 |
+
|
35 |
+
### Training hyperparameters
|
36 |
+
|
37 |
+
The following hyperparameters were used during training:
|
38 |
+
- learning_rate: 0.0002
|
39 |
+
- train_batch_size: 4
|
40 |
+
- eval_batch_size: 4
|
41 |
+
- seed: 42
|
42 |
+
- gradient_accumulation_steps: 8
|
43 |
+
- total_train_batch_size: 32
|
44 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
45 |
+
- lr_scheduler_type: cosine
|
46 |
+
- lr_scheduler_warmup_steps: 10
|
47 |
+
- num_epochs: 1
|
48 |
+
|
49 |
+
### Training results
|
50 |
+
|
51 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
52 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
53 |
+
| 0.1557 | 0.01 | 1 | 0.1552 |
|
54 |
+
| 0.0936 | 0.05 | 6 | 0.0695 |
|
55 |
+
| 0.0447 | 0.1 | 12 | 0.0413 |
|
56 |
+
| 0.0347 | 0.16 | 18 | 0.0357 |
|
57 |
+
| 0.0314 | 0.21 | 24 | 0.0324 |
|
58 |
+
| 0.0306 | 0.26 | 30 | 0.0309 |
|
59 |
+
| 0.0276 | 0.31 | 36 | 0.0294 |
|
60 |
+
| 0.028 | 0.36 | 42 | 0.0284 |
|
61 |
+
| 0.0307 | 0.41 | 48 | 0.0281 |
|
62 |
+
| 0.0276 | 0.47 | 54 | 0.0274 |
|
63 |
+
| 0.0251 | 0.52 | 60 | 0.0267 |
|
64 |
+
| 0.0244 | 0.57 | 66 | 0.0269 |
|
65 |
+
| 0.0268 | 0.62 | 72 | 0.0263 |
|
66 |
+
| 0.0249 | 0.67 | 78 | 0.0262 |
|
67 |
+
| 0.0252 | 0.73 | 84 | 0.0258 |
|
68 |
+
| 0.0259 | 0.78 | 90 | 0.0257 |
|
69 |
+
| 0.0241 | 0.83 | 96 | 0.0255 |
|
70 |
+
| 0.0241 | 0.88 | 102 | 0.0254 |
|
71 |
+
| 0.0253 | 0.93 | 108 | 0.0254 |
|
72 |
+
| 0.0234 | 0.98 | 114 | 0.0253 |
|
73 |
+
|
74 |
+
|
75 |
+
### Framework versions
|
76 |
+
|
77 |
+
- Transformers 4.35.2
|
78 |
+
- Pytorch 2.0.1+cu118
|
79 |
+
- Datasets 2.15.0
|
80 |
+
- Tokenizers 0.15.0
|
adapter_config.json
ADDED
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "mistralai/Mistral-7B-v0.1",
|
5 |
+
"bias": "none",
|
6 |
+
"fan_in_fan_out": null,
|
7 |
+
"inference_mode": true,
|
8 |
+
"init_lora_weights": true,
|
9 |
+
"layers_pattern": null,
|
10 |
+
"layers_to_transform": null,
|
11 |
+
"lora_alpha": 16,
|
12 |
+
"lora_dropout": 0.05,
|
13 |
+
"modules_to_save": null,
|
14 |
+
"peft_type": "LORA",
|
15 |
+
"r": 32,
|
16 |
+
"rank_pattern": {},
|
17 |
+
"revision": null,
|
18 |
+
"target_modules": [
|
19 |
+
"gate_proj",
|
20 |
+
"up_proj",
|
21 |
+
"v_proj",
|
22 |
+
"down_proj",
|
23 |
+
"q_proj",
|
24 |
+
"o_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 sha256:7f7aff251962e566af132c2c8be3f0602cb39ce340933021cad6b77e0e16da7e
|
3 |
+
size 335705741
|
checkpoint-115/README.md
ADDED
@@ -0,0 +1,220 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: peft
|
3 |
+
base_model: mistralai/Mistral-7B-v0.1
|
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 0.6.0
|
checkpoint-115/adapter_config.json
ADDED
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "mistralai/Mistral-7B-v0.1",
|
5 |
+
"bias": "none",
|
6 |
+
"fan_in_fan_out": null,
|
7 |
+
"inference_mode": true,
|
8 |
+
"init_lora_weights": true,
|
9 |
+
"layers_pattern": null,
|
10 |
+
"layers_to_transform": null,
|
11 |
+
"lora_alpha": 16,
|
12 |
+
"lora_dropout": 0.05,
|
13 |
+
"modules_to_save": null,
|
14 |
+
"peft_type": "LORA",
|
15 |
+
"r": 32,
|
16 |
+
"rank_pattern": {},
|
17 |
+
"revision": null,
|
18 |
+
"target_modules": [
|
19 |
+
"gate_proj",
|
20 |
+
"up_proj",
|
21 |
+
"v_proj",
|
22 |
+
"down_proj",
|
23 |
+
"q_proj",
|
24 |
+
"o_proj",
|
25 |
+
"k_proj"
|
26 |
+
],
|
27 |
+
"task_type": "CAUSAL_LM"
|
28 |
+
}
|
checkpoint-115/adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d1777c612dee9704332f6b5e6de19b56828c5340942c3cd8e1f770a756435ef5
|
3 |
+
size 335604696
|
checkpoint-115/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e79b38f8a306b5f24834d316868eec9aa5340d171678d8aaf93a5c7a4cb9f2f0
|
3 |
+
size 168624287
|
checkpoint-115/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e5660081a238d8a1e0f45a0cef072d9be0c257dc89516b658a237c19ee1fc93b
|
3 |
+
size 14575
|
checkpoint-115/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fb96efe2b0789753cd0188d45c8c0349fe1de5b1e01ce6315f9fd82106d4c424
|
3 |
+
size 627
|
checkpoint-115/trainer_state.json
ADDED
@@ -0,0 +1,869 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.9935205183585313,
|
5 |
+
"eval_steps": 6,
|
6 |
+
"global_step": 115,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.01,
|
13 |
+
"learning_rate": 2e-05,
|
14 |
+
"loss": 0.1557,
|
15 |
+
"step": 1
|
16 |
+
},
|
17 |
+
{
|
18 |
+
"epoch": 0.01,
|
19 |
+
"eval_loss": 0.1552305519580841,
|
20 |
+
"eval_runtime": 32.8038,
|
21 |
+
"eval_samples_per_second": 8.536,
|
22 |
+
"eval_steps_per_second": 2.134,
|
23 |
+
"step": 1
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.02,
|
27 |
+
"learning_rate": 4e-05,
|
28 |
+
"loss": 0.1617,
|
29 |
+
"step": 2
|
30 |
+
},
|
31 |
+
{
|
32 |
+
"epoch": 0.03,
|
33 |
+
"learning_rate": 6e-05,
|
34 |
+
"loss": 0.1577,
|
35 |
+
"step": 3
|
36 |
+
},
|
37 |
+
{
|
38 |
+
"epoch": 0.03,
|
39 |
+
"learning_rate": 8e-05,
|
40 |
+
"loss": 0.1411,
|
41 |
+
"step": 4
|
42 |
+
},
|
43 |
+
{
|
44 |
+
"epoch": 0.04,
|
45 |
+
"learning_rate": 0.0001,
|
46 |
+
"loss": 0.1191,
|
47 |
+
"step": 5
|
48 |
+
},
|
49 |
+
{
|
50 |
+
"epoch": 0.05,
|
51 |
+
"learning_rate": 0.00012,
|
52 |
+
"loss": 0.0936,
|
53 |
+
"step": 6
|
54 |
+
},
|
55 |
+
{
|
56 |
+
"epoch": 0.05,
|
57 |
+
"eval_loss": 0.06945057213306427,
|
58 |
+
"eval_runtime": 32.8918,
|
59 |
+
"eval_samples_per_second": 8.513,
|
60 |
+
"eval_steps_per_second": 2.128,
|
61 |
+
"step": 6
|
62 |
+
},
|
63 |
+
{
|
64 |
+
"epoch": 0.06,
|
65 |
+
"learning_rate": 0.00014,
|
66 |
+
"loss": 0.0662,
|
67 |
+
"step": 7
|
68 |
+
},
|
69 |
+
{
|
70 |
+
"epoch": 0.07,
|
71 |
+
"learning_rate": 0.00016,
|
72 |
+
"loss": 0.0513,
|
73 |
+
"step": 8
|
74 |
+
},
|
75 |
+
{
|
76 |
+
"epoch": 0.08,
|
77 |
+
"learning_rate": 0.00018,
|
78 |
+
"loss": 0.0521,
|
79 |
+
"step": 9
|
80 |
+
},
|
81 |
+
{
|
82 |
+
"epoch": 0.09,
|
83 |
+
"learning_rate": 0.0002,
|
84 |
+
"loss": 0.0496,
|
85 |
+
"step": 10
|
86 |
+
},
|
87 |
+
{
|
88 |
+
"epoch": 0.1,
|
89 |
+
"learning_rate": 0.00019995524322835034,
|
90 |
+
"loss": 0.0537,
|
91 |
+
"step": 11
|
92 |
+
},
|
93 |
+
{
|
94 |
+
"epoch": 0.1,
|
95 |
+
"learning_rate": 0.0001998210129767735,
|
96 |
+
"loss": 0.0447,
|
97 |
+
"step": 12
|
98 |
+
},
|
99 |
+
{
|
100 |
+
"epoch": 0.1,
|
101 |
+
"eval_loss": 0.041263870894908905,
|
102 |
+
"eval_runtime": 32.8403,
|
103 |
+
"eval_samples_per_second": 8.526,
|
104 |
+
"eval_steps_per_second": 2.132,
|
105 |
+
"step": 12
|
106 |
+
},
|
107 |
+
{
|
108 |
+
"epoch": 0.11,
|
109 |
+
"learning_rate": 0.00019959742939952392,
|
110 |
+
"loss": 0.0405,
|
111 |
+
"step": 13
|
112 |
+
},
|
113 |
+
{
|
114 |
+
"epoch": 0.12,
|
115 |
+
"learning_rate": 0.00019928469263418374,
|
116 |
+
"loss": 0.0371,
|
117 |
+
"step": 14
|
118 |
+
},
|
119 |
+
{
|
120 |
+
"epoch": 0.13,
|
121 |
+
"learning_rate": 0.00019888308262251285,
|
122 |
+
"loss": 0.0365,
|
123 |
+
"step": 15
|
124 |
+
},
|
125 |
+
{
|
126 |
+
"epoch": 0.14,
|
127 |
+
"learning_rate": 0.00019839295885986296,
|
128 |
+
"loss": 0.0396,
|
129 |
+
"step": 16
|
130 |
+
},
|
131 |
+
{
|
132 |
+
"epoch": 0.15,
|
133 |
+
"learning_rate": 0.00019781476007338058,
|
134 |
+
"loss": 0.0415,
|
135 |
+
"step": 17
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 0.16,
|
139 |
+
"learning_rate": 0.00019714900382928675,
|
140 |
+
"loss": 0.0347,
|
141 |
+
"step": 18
|
142 |
+
},
|
143 |
+
{
|
144 |
+
"epoch": 0.16,
|
145 |
+
"eval_loss": 0.03573257848620415,
|
146 |
+
"eval_runtime": 32.8461,
|
147 |
+
"eval_samples_per_second": 8.525,
|
148 |
+
"eval_steps_per_second": 2.131,
|
149 |
+
"step": 18
|
150 |
+
},
|
151 |
+
{
|
152 |
+
"epoch": 0.16,
|
153 |
+
"learning_rate": 0.00019639628606958533,
|
154 |
+
"loss": 0.0319,
|
155 |
+
"step": 19
|
156 |
+
},
|
157 |
+
{
|
158 |
+
"epoch": 0.17,
|
159 |
+
"learning_rate": 0.0001955572805786141,
|
160 |
+
"loss": 0.0339,
|
161 |
+
"step": 20
|
162 |
+
},
|
163 |
+
{
|
164 |
+
"epoch": 0.18,
|
165 |
+
"learning_rate": 0.00019463273837991643,
|
166 |
+
"loss": 0.0313,
|
167 |
+
"step": 21
|
168 |
+
},
|
169 |
+
{
|
170 |
+
"epoch": 0.19,
|
171 |
+
"learning_rate": 0.00019362348706397373,
|
172 |
+
"loss": 0.0356,
|
173 |
+
"step": 22
|
174 |
+
},
|
175 |
+
{
|
176 |
+
"epoch": 0.2,
|
177 |
+
"learning_rate": 0.00019253043004739968,
|
178 |
+
"loss": 0.0347,
|
179 |
+
"step": 23
|
180 |
+
},
|
181 |
+
{
|
182 |
+
"epoch": 0.21,
|
183 |
+
"learning_rate": 0.0001913545457642601,
|
184 |
+
"loss": 0.0314,
|
185 |
+
"step": 24
|
186 |
+
},
|
187 |
+
{
|
188 |
+
"epoch": 0.21,
|
189 |
+
"eval_loss": 0.03238712623715401,
|
190 |
+
"eval_runtime": 32.8447,
|
191 |
+
"eval_samples_per_second": 8.525,
|
192 |
+
"eval_steps_per_second": 2.131,
|
193 |
+
"step": 24
|
194 |
+
},
|
195 |
+
{
|
196 |
+
"epoch": 0.22,
|
197 |
+
"learning_rate": 0.0001900968867902419,
|
198 |
+
"loss": 0.0309,
|
199 |
+
"step": 25
|
200 |
+
},
|
201 |
+
{
|
202 |
+
"epoch": 0.22,
|
203 |
+
"learning_rate": 0.00018875857890045543,
|
204 |
+
"loss": 0.033,
|
205 |
+
"step": 26
|
206 |
+
},
|
207 |
+
{
|
208 |
+
"epoch": 0.23,
|
209 |
+
"learning_rate": 0.00018734082006171299,
|
210 |
+
"loss": 0.0331,
|
211 |
+
"step": 27
|
212 |
+
},
|
213 |
+
{
|
214 |
+
"epoch": 0.24,
|
215 |
+
"learning_rate": 0.00018584487936018661,
|
216 |
+
"loss": 0.0304,
|
217 |
+
"step": 28
|
218 |
+
},
|
219 |
+
{
|
220 |
+
"epoch": 0.25,
|
221 |
+
"learning_rate": 0.0001842720958654039,
|
222 |
+
"loss": 0.0306,
|
223 |
+
"step": 29
|
224 |
+
},
|
225 |
+
{
|
226 |
+
"epoch": 0.26,
|
227 |
+
"learning_rate": 0.0001826238774315995,
|
228 |
+
"loss": 0.0306,
|
229 |
+
"step": 30
|
230 |
+
},
|
231 |
+
{
|
232 |
+
"epoch": 0.26,
|
233 |
+
"eval_loss": 0.030900534242391586,
|
234 |
+
"eval_runtime": 32.8989,
|
235 |
+
"eval_samples_per_second": 8.511,
|
236 |
+
"eval_steps_per_second": 2.128,
|
237 |
+
"step": 30
|
238 |
+
},
|
239 |
+
{
|
240 |
+
"epoch": 0.27,
|
241 |
+
"learning_rate": 0.00018090169943749476,
|
242 |
+
"loss": 0.0299,
|
243 |
+
"step": 31
|
244 |
+
},
|
245 |
+
{
|
246 |
+
"epoch": 0.28,
|
247 |
+
"learning_rate": 0.00017910710346563416,
|
248 |
+
"loss": 0.0307,
|
249 |
+
"step": 32
|
250 |
+
},
|
251 |
+
{
|
252 |
+
"epoch": 0.29,
|
253 |
+
"learning_rate": 0.00017724169592245995,
|
254 |
+
"loss": 0.0294,
|
255 |
+
"step": 33
|
256 |
+
},
|
257 |
+
{
|
258 |
+
"epoch": 0.29,
|
259 |
+
"learning_rate": 0.00017530714660036112,
|
260 |
+
"loss": 0.0283,
|
261 |
+
"step": 34
|
262 |
+
},
|
263 |
+
{
|
264 |
+
"epoch": 0.3,
|
265 |
+
"learning_rate": 0.00017330518718298264,
|
266 |
+
"loss": 0.0328,
|
267 |
+
"step": 35
|
268 |
+
},
|
269 |
+
{
|
270 |
+
"epoch": 0.31,
|
271 |
+
"learning_rate": 0.0001712376096951345,
|
272 |
+
"loss": 0.0276,
|
273 |
+
"step": 36
|
274 |
+
},
|
275 |
+
{
|
276 |
+
"epoch": 0.31,
|
277 |
+
"eval_loss": 0.02941257879137993,
|
278 |
+
"eval_runtime": 32.8187,
|
279 |
+
"eval_samples_per_second": 8.532,
|
280 |
+
"eval_steps_per_second": 2.133,
|
281 |
+
"step": 36
|
282 |
+
},
|
283 |
+
{
|
284 |
+
"epoch": 0.32,
|
285 |
+
"learning_rate": 0.00016910626489868649,
|
286 |
+
"loss": 0.0267,
|
287 |
+
"step": 37
|
288 |
+
},
|
289 |
+
{
|
290 |
+
"epoch": 0.33,
|
291 |
+
"learning_rate": 0.00016691306063588583,
|
292 |
+
"loss": 0.0293,
|
293 |
+
"step": 38
|
294 |
+
},
|
295 |
+
{
|
296 |
+
"epoch": 0.34,
|
297 |
+
"learning_rate": 0.00016465996012157995,
|
298 |
+
"loss": 0.0259,
|
299 |
+
"step": 39
|
300 |
+
},
|
301 |
+
{
|
302 |
+
"epoch": 0.35,
|
303 |
+
"learning_rate": 0.00016234898018587337,
|
304 |
+
"loss": 0.0286,
|
305 |
+
"step": 40
|
306 |
+
},
|
307 |
+
{
|
308 |
+
"epoch": 0.35,
|
309 |
+
"learning_rate": 0.00015998218946879138,
|
310 |
+
"loss": 0.0255,
|
311 |
+
"step": 41
|
312 |
+
},
|
313 |
+
{
|
314 |
+
"epoch": 0.36,
|
315 |
+
"learning_rate": 0.00015756170656856737,
|
316 |
+
"loss": 0.028,
|
317 |
+
"step": 42
|
318 |
+
},
|
319 |
+
{
|
320 |
+
"epoch": 0.36,
|
321 |
+
"eval_loss": 0.028368661180138588,
|
322 |
+
"eval_runtime": 32.9402,
|
323 |
+
"eval_samples_per_second": 8.5,
|
324 |
+
"eval_steps_per_second": 2.125,
|
325 |
+
"step": 42
|
326 |
+
},
|
327 |
+
{
|
328 |
+
"epoch": 0.37,
|
329 |
+
"learning_rate": 0.00015508969814521025,
|
330 |
+
"loss": 0.028,
|
331 |
+
"step": 43
|
332 |
+
},
|
333 |
+
{
|
334 |
+
"epoch": 0.38,
|
335 |
+
"learning_rate": 0.00015256837698105047,
|
336 |
+
"loss": 0.0279,
|
337 |
+
"step": 44
|
338 |
+
},
|
339 |
+
{
|
340 |
+
"epoch": 0.39,
|
341 |
+
"learning_rate": 0.00015000000000000001,
|
342 |
+
"loss": 0.0255,
|
343 |
+
"step": 45
|
344 |
+
},
|
345 |
+
{
|
346 |
+
"epoch": 0.4,
|
347 |
+
"learning_rate": 0.00014738686624729986,
|
348 |
+
"loss": 0.0283,
|
349 |
+
"step": 46
|
350 |
+
},
|
351 |
+
{
|
352 |
+
"epoch": 0.41,
|
353 |
+
"learning_rate": 0.00014473131483156327,
|
354 |
+
"loss": 0.0257,
|
355 |
+
"step": 47
|
356 |
+
},
|
357 |
+
{
|
358 |
+
"epoch": 0.41,
|
359 |
+
"learning_rate": 0.00014203572283095657,
|
360 |
+
"loss": 0.0307,
|
361 |
+
"step": 48
|
362 |
+
},
|
363 |
+
{
|
364 |
+
"epoch": 0.41,
|
365 |
+
"eval_loss": 0.028058379888534546,
|
366 |
+
"eval_runtime": 32.8234,
|
367 |
+
"eval_samples_per_second": 8.531,
|
368 |
+
"eval_steps_per_second": 2.133,
|
369 |
+
"step": 48
|
370 |
+
},
|
371 |
+
{
|
372 |
+
"epoch": 0.42,
|
373 |
+
"learning_rate": 0.00013930250316539238,
|
374 |
+
"loss": 0.0292,
|
375 |
+
"step": 49
|
376 |
+
},
|
377 |
+
{
|
378 |
+
"epoch": 0.43,
|
379 |
+
"learning_rate": 0.00013653410243663952,
|
380 |
+
"loss": 0.0267,
|
381 |
+
"step": 50
|
382 |
+
},
|
383 |
+
{
|
384 |
+
"epoch": 0.44,
|
385 |
+
"learning_rate": 0.00013373299873828303,
|
386 |
+
"loss": 0.0277,
|
387 |
+
"step": 51
|
388 |
+
},
|
389 |
+
{
|
390 |
+
"epoch": 0.45,
|
391 |
+
"learning_rate": 0.00013090169943749476,
|
392 |
+
"loss": 0.0285,
|
393 |
+
"step": 52
|
394 |
+
},
|
395 |
+
{
|
396 |
+
"epoch": 0.46,
|
397 |
+
"learning_rate": 0.00012804273893060028,
|
398 |
+
"loss": 0.0267,
|
399 |
+
"step": 53
|
400 |
+
},
|
401 |
+
{
|
402 |
+
"epoch": 0.47,
|
403 |
+
"learning_rate": 0.00012515867637445086,
|
404 |
+
"loss": 0.0276,
|
405 |
+
"step": 54
|
406 |
+
},
|
407 |
+
{
|
408 |
+
"epoch": 0.47,
|
409 |
+
"eval_loss": 0.027369534596800804,
|
410 |
+
"eval_runtime": 32.8389,
|
411 |
+
"eval_samples_per_second": 8.526,
|
412 |
+
"eval_steps_per_second": 2.132,
|
413 |
+
"step": 54
|
414 |
+
},
|
415 |
+
{
|
416 |
+
"epoch": 0.48,
|
417 |
+
"learning_rate": 0.00012225209339563145,
|
418 |
+
"loss": 0.0288,
|
419 |
+
"step": 55
|
420 |
+
},
|
421 |
+
{
|
422 |
+
"epoch": 0.48,
|
423 |
+
"learning_rate": 0.00011932559177955533,
|
424 |
+
"loss": 0.028,
|
425 |
+
"step": 56
|
426 |
+
},
|
427 |
+
{
|
428 |
+
"epoch": 0.49,
|
429 |
+
"learning_rate": 0.00011638179114151377,
|
430 |
+
"loss": 0.0264,
|
431 |
+
"step": 57
|
432 |
+
},
|
433 |
+
{
|
434 |
+
"epoch": 0.5,
|
435 |
+
"learning_rate": 0.00011342332658176555,
|
436 |
+
"loss": 0.0248,
|
437 |
+
"step": 58
|
438 |
+
},
|
439 |
+
{
|
440 |
+
"epoch": 0.51,
|
441 |
+
"learning_rate": 0.00011045284632676536,
|
442 |
+
"loss": 0.0261,
|
443 |
+
"step": 59
|
444 |
+
},
|
445 |
+
{
|
446 |
+
"epoch": 0.52,
|
447 |
+
"learning_rate": 0.00010747300935864243,
|
448 |
+
"loss": 0.0251,
|
449 |
+
"step": 60
|
450 |
+
},
|
451 |
+
{
|
452 |
+
"epoch": 0.52,
|
453 |
+
"eval_loss": 0.026654452085494995,
|
454 |
+
"eval_runtime": 32.8756,
|
455 |
+
"eval_samples_per_second": 8.517,
|
456 |
+
"eval_steps_per_second": 2.129,
|
457 |
+
"step": 60
|
458 |
+
},
|
459 |
+
{
|
460 |
+
"epoch": 0.53,
|
461 |
+
"learning_rate": 0.00010448648303505151,
|
462 |
+
"loss": 0.028,
|
463 |
+
"step": 61
|
464 |
+
},
|
465 |
+
{
|
466 |
+
"epoch": 0.54,
|
467 |
+
"learning_rate": 0.00010149594070152638,
|
468 |
+
"loss": 0.0274,
|
469 |
+
"step": 62
|
470 |
+
},
|
471 |
+
{
|
472 |
+
"epoch": 0.54,
|
473 |
+
"learning_rate": 9.850405929847366e-05,
|
474 |
+
"loss": 0.0252,
|
475 |
+
"step": 63
|
476 |
+
},
|
477 |
+
{
|
478 |
+
"epoch": 0.55,
|
479 |
+
"learning_rate": 9.551351696494854e-05,
|
480 |
+
"loss": 0.0277,
|
481 |
+
"step": 64
|
482 |
+
},
|
483 |
+
{
|
484 |
+
"epoch": 0.56,
|
485 |
+
"learning_rate": 9.252699064135758e-05,
|
486 |
+
"loss": 0.0285,
|
487 |
+
"step": 65
|
488 |
+
},
|
489 |
+
{
|
490 |
+
"epoch": 0.57,
|
491 |
+
"learning_rate": 8.954715367323468e-05,
|
492 |
+
"loss": 0.0244,
|
493 |
+
"step": 66
|
494 |
+
},
|
495 |
+
{
|
496 |
+
"epoch": 0.57,
|
497 |
+
"eval_loss": 0.02685328759253025,
|
498 |
+
"eval_runtime": 32.8937,
|
499 |
+
"eval_samples_per_second": 8.512,
|
500 |
+
"eval_steps_per_second": 2.128,
|
501 |
+
"step": 66
|
502 |
+
},
|
503 |
+
{
|
504 |
+
"epoch": 0.58,
|
505 |
+
"learning_rate": 8.657667341823448e-05,
|
506 |
+
"loss": 0.0241,
|
507 |
+
"step": 67
|
508 |
+
},
|
509 |
+
{
|
510 |
+
"epoch": 0.59,
|
511 |
+
"learning_rate": 8.361820885848624e-05,
|
512 |
+
"loss": 0.0242,
|
513 |
+
"step": 68
|
514 |
+
},
|
515 |
+
{
|
516 |
+
"epoch": 0.6,
|
517 |
+
"learning_rate": 8.067440822044469e-05,
|
518 |
+
"loss": 0.0253,
|
519 |
+
"step": 69
|
520 |
+
},
|
521 |
+
{
|
522 |
+
"epoch": 0.6,
|
523 |
+
"learning_rate": 7.774790660436858e-05,
|
524 |
+
"loss": 0.0286,
|
525 |
+
"step": 70
|
526 |
+
},
|
527 |
+
{
|
528 |
+
"epoch": 0.61,
|
529 |
+
"learning_rate": 7.484132362554915e-05,
|
530 |
+
"loss": 0.0259,
|
531 |
+
"step": 71
|
532 |
+
},
|
533 |
+
{
|
534 |
+
"epoch": 0.62,
|
535 |
+
"learning_rate": 7.195726106939974e-05,
|
536 |
+
"loss": 0.0268,
|
537 |
+
"step": 72
|
538 |
+
},
|
539 |
+
{
|
540 |
+
"epoch": 0.62,
|
541 |
+
"eval_loss": 0.026269590482115746,
|
542 |
+
"eval_runtime": 32.8623,
|
543 |
+
"eval_samples_per_second": 8.52,
|
544 |
+
"eval_steps_per_second": 2.13,
|
545 |
+
"step": 72
|
546 |
+
},
|
547 |
+
{
|
548 |
+
"epoch": 0.63,
|
549 |
+
"learning_rate": 6.909830056250527e-05,
|
550 |
+
"loss": 0.0274,
|
551 |
+
"step": 73
|
552 |
+
},
|
553 |
+
{
|
554 |
+
"epoch": 0.64,
|
555 |
+
"learning_rate": 6.626700126171702e-05,
|
556 |
+
"loss": 0.0245,
|
557 |
+
"step": 74
|
558 |
+
},
|
559 |
+
{
|
560 |
+
"epoch": 0.65,
|
561 |
+
"learning_rate": 6.34658975633605e-05,
|
562 |
+
"loss": 0.0251,
|
563 |
+
"step": 75
|
564 |
+
},
|
565 |
+
{
|
566 |
+
"epoch": 0.66,
|
567 |
+
"learning_rate": 6.069749683460765e-05,
|
568 |
+
"loss": 0.0271,
|
569 |
+
"step": 76
|
570 |
+
},
|
571 |
+
{
|
572 |
+
"epoch": 0.67,
|
573 |
+
"learning_rate": 5.796427716904347e-05,
|
574 |
+
"loss": 0.0255,
|
575 |
+
"step": 77
|
576 |
+
},
|
577 |
+
{
|
578 |
+
"epoch": 0.67,
|
579 |
+
"learning_rate": 5.526868516843673e-05,
|
580 |
+
"loss": 0.0249,
|
581 |
+
"step": 78
|
582 |
+
},
|
583 |
+
{
|
584 |
+
"epoch": 0.67,
|
585 |
+
"eval_loss": 0.026168059557676315,
|
586 |
+
"eval_runtime": 32.8573,
|
587 |
+
"eval_samples_per_second": 8.522,
|
588 |
+
"eval_steps_per_second": 2.13,
|
589 |
+
"step": 78
|
590 |
+
},
|
591 |
+
{
|
592 |
+
"epoch": 0.68,
|
593 |
+
"learning_rate": 5.261313375270014e-05,
|
594 |
+
"loss": 0.027,
|
595 |
+
"step": 79
|
596 |
+
},
|
597 |
+
{
|
598 |
+
"epoch": 0.69,
|
599 |
+
"learning_rate": 5.000000000000002e-05,
|
600 |
+
"loss": 0.0241,
|
601 |
+
"step": 80
|
602 |
+
},
|
603 |
+
{
|
604 |
+
"epoch": 0.7,
|
605 |
+
"learning_rate": 4.743162301894952e-05,
|
606 |
+
"loss": 0.0245,
|
607 |
+
"step": 81
|
608 |
+
},
|
609 |
+
{
|
610 |
+
"epoch": 0.71,
|
611 |
+
"learning_rate": 4.491030185478976e-05,
|
612 |
+
"loss": 0.0233,
|
613 |
+
"step": 82
|
614 |
+
},
|
615 |
+
{
|
616 |
+
"epoch": 0.72,
|
617 |
+
"learning_rate": 4.2438293431432665e-05,
|
618 |
+
"loss": 0.0261,
|
619 |
+
"step": 83
|
620 |
+
},
|
621 |
+
{
|
622 |
+
"epoch": 0.73,
|
623 |
+
"learning_rate": 4.001781053120863e-05,
|
624 |
+
"loss": 0.0252,
|
625 |
+
"step": 84
|
626 |
+
},
|
627 |
+
{
|
628 |
+
"epoch": 0.73,
|
629 |
+
"eval_loss": 0.02580336295068264,
|
630 |
+
"eval_runtime": 32.827,
|
631 |
+
"eval_samples_per_second": 8.53,
|
632 |
+
"eval_steps_per_second": 2.132,
|
633 |
+
"step": 84
|
634 |
+
},
|
635 |
+
{
|
636 |
+
"epoch": 0.73,
|
637 |
+
"learning_rate": 3.7651019814126654e-05,
|
638 |
+
"loss": 0.0246,
|
639 |
+
"step": 85
|
640 |
+
},
|
641 |
+
{
|
642 |
+
"epoch": 0.74,
|
643 |
+
"learning_rate": 3.534003987842005e-05,
|
644 |
+
"loss": 0.0229,
|
645 |
+
"step": 86
|
646 |
+
},
|
647 |
+
{
|
648 |
+
"epoch": 0.75,
|
649 |
+
"learning_rate": 3.308693936411421e-05,
|
650 |
+
"loss": 0.025,
|
651 |
+
"step": 87
|
652 |
+
},
|
653 |
+
{
|
654 |
+
"epoch": 0.76,
|
655 |
+
"learning_rate": 3.089373510131354e-05,
|
656 |
+
"loss": 0.0247,
|
657 |
+
"step": 88
|
658 |
+
},
|
659 |
+
{
|
660 |
+
"epoch": 0.77,
|
661 |
+
"learning_rate": 2.876239030486554e-05,
|
662 |
+
"loss": 0.0251,
|
663 |
+
"step": 89
|
664 |
+
},
|
665 |
+
{
|
666 |
+
"epoch": 0.78,
|
667 |
+
"learning_rate": 2.669481281701739e-05,
|
668 |
+
"loss": 0.0259,
|
669 |
+
"step": 90
|
670 |
+
},
|
671 |
+
{
|
672 |
+
"epoch": 0.78,
|
673 |
+
"eval_loss": 0.02568827196955681,
|
674 |
+
"eval_runtime": 32.8573,
|
675 |
+
"eval_samples_per_second": 8.522,
|
676 |
+
"eval_steps_per_second": 2.13,
|
677 |
+
"step": 90
|
678 |
+
},
|
679 |
+
{
|
680 |
+
"epoch": 0.79,
|
681 |
+
"learning_rate": 2.4692853399638917e-05,
|
682 |
+
"loss": 0.0283,
|
683 |
+
"step": 91
|
684 |
+
},
|
685 |
+
{
|
686 |
+
"epoch": 0.79,
|
687 |
+
"learning_rate": 2.275830407754006e-05,
|
688 |
+
"loss": 0.0245,
|
689 |
+
"step": 92
|
690 |
+
},
|
691 |
+
{
|
692 |
+
"epoch": 0.8,
|
693 |
+
"learning_rate": 2.0892896534365904e-05,
|
694 |
+
"loss": 0.0308,
|
695 |
+
"step": 93
|
696 |
+
},
|
697 |
+
{
|
698 |
+
"epoch": 0.81,
|
699 |
+
"learning_rate": 1.9098300562505266e-05,
|
700 |
+
"loss": 0.0239,
|
701 |
+
"step": 94
|
702 |
+
},
|
703 |
+
{
|
704 |
+
"epoch": 0.82,
|
705 |
+
"learning_rate": 1.7376122568400532e-05,
|
706 |
+
"loss": 0.0238,
|
707 |
+
"step": 95
|
708 |
+
},
|
709 |
+
{
|
710 |
+
"epoch": 0.83,
|
711 |
+
"learning_rate": 1.5727904134596083e-05,
|
712 |
+
"loss": 0.0241,
|
713 |
+
"step": 96
|
714 |
+
},
|
715 |
+
{
|
716 |
+
"epoch": 0.83,
|
717 |
+
"eval_loss": 0.025526922196149826,
|
718 |
+
"eval_runtime": 32.8676,
|
719 |
+
"eval_samples_per_second": 8.519,
|
720 |
+
"eval_steps_per_second": 2.13,
|
721 |
+
"step": 96
|
722 |
+
},
|
723 |
+
{
|
724 |
+
"epoch": 0.84,
|
725 |
+
"learning_rate": 1.415512063981339e-05,
|
726 |
+
"loss": 0.0261,
|
727 |
+
"step": 97
|
728 |
+
},
|
729 |
+
{
|
730 |
+
"epoch": 0.85,
|
731 |
+
"learning_rate": 1.2659179938287035e-05,
|
732 |
+
"loss": 0.0246,
|
733 |
+
"step": 98
|
734 |
+
},
|
735 |
+
{
|
736 |
+
"epoch": 0.86,
|
737 |
+
"learning_rate": 1.124142109954459e-05,
|
738 |
+
"loss": 0.0295,
|
739 |
+
"step": 99
|
740 |
+
},
|
741 |
+
{
|
742 |
+
"epoch": 0.86,
|
743 |
+
"learning_rate": 9.903113209758096e-06,
|
744 |
+
"loss": 0.025,
|
745 |
+
"step": 100
|
746 |
+
},
|
747 |
+
{
|
748 |
+
"epoch": 0.87,
|
749 |
+
"learning_rate": 8.645454235739903e-06,
|
750 |
+
"loss": 0.0235,
|
751 |
+
"step": 101
|
752 |
+
},
|
753 |
+
{
|
754 |
+
"epoch": 0.88,
|
755 |
+
"learning_rate": 7.46956995260033e-06,
|
756 |
+
"loss": 0.0241,
|
757 |
+
"step": 102
|
758 |
+
},
|
759 |
+
{
|
760 |
+
"epoch": 0.88,
|
761 |
+
"eval_loss": 0.025442615151405334,
|
762 |
+
"eval_runtime": 32.9063,
|
763 |
+
"eval_samples_per_second": 8.509,
|
764 |
+
"eval_steps_per_second": 2.127,
|
765 |
+
"step": 102
|
766 |
+
},
|
767 |
+
{
|
768 |
+
"epoch": 0.89,
|
769 |
+
"learning_rate": 6.37651293602628e-06,
|
770 |
+
"loss": 0.0237,
|
771 |
+
"step": 103
|
772 |
+
},
|
773 |
+
{
|
774 |
+
"epoch": 0.9,
|
775 |
+
"learning_rate": 5.367261620083575e-06,
|
776 |
+
"loss": 0.0243,
|
777 |
+
"step": 104
|
778 |
+
},
|
779 |
+
{
|
780 |
+
"epoch": 0.91,
|
781 |
+
"learning_rate": 4.442719421385922e-06,
|
782 |
+
"loss": 0.0241,
|
783 |
+
"step": 105
|
784 |
+
},
|
785 |
+
{
|
786 |
+
"epoch": 0.92,
|
787 |
+
"learning_rate": 3.6037139304146762e-06,
|
788 |
+
"loss": 0.0237,
|
789 |
+
"step": 106
|
790 |
+
},
|
791 |
+
{
|
792 |
+
"epoch": 0.92,
|
793 |
+
"learning_rate": 2.8509961707132494e-06,
|
794 |
+
"loss": 0.0251,
|
795 |
+
"step": 107
|
796 |
+
},
|
797 |
+
{
|
798 |
+
"epoch": 0.93,
|
799 |
+
"learning_rate": 2.1852399266194314e-06,
|
800 |
+
"loss": 0.0253,
|
801 |
+
"step": 108
|
802 |
+
},
|
803 |
+
{
|
804 |
+
"epoch": 0.93,
|
805 |
+
"eval_loss": 0.025354694575071335,
|
806 |
+
"eval_runtime": 32.8944,
|
807 |
+
"eval_samples_per_second": 8.512,
|
808 |
+
"eval_steps_per_second": 2.128,
|
809 |
+
"step": 108
|
810 |
+
},
|
811 |
+
{
|
812 |
+
"epoch": 0.94,
|
813 |
+
"learning_rate": 1.6070411401370334e-06,
|
814 |
+
"loss": 0.024,
|
815 |
+
"step": 109
|
816 |
+
},
|
817 |
+
{
|
818 |
+
"epoch": 0.95,
|
819 |
+
"learning_rate": 1.1169173774871478e-06,
|
820 |
+
"loss": 0.0238,
|
821 |
+
"step": 110
|
822 |
+
},
|
823 |
+
{
|
824 |
+
"epoch": 0.96,
|
825 |
+
"learning_rate": 7.153073658162646e-07,
|
826 |
+
"loss": 0.0232,
|
827 |
+
"step": 111
|
828 |
+
},
|
829 |
+
{
|
830 |
+
"epoch": 0.97,
|
831 |
+
"learning_rate": 4.025706004760932e-07,
|
832 |
+
"loss": 0.0243,
|
833 |
+
"step": 112
|
834 |
+
},
|
835 |
+
{
|
836 |
+
"epoch": 0.98,
|
837 |
+
"learning_rate": 1.7898702322648453e-07,
|
838 |
+
"loss": 0.0256,
|
839 |
+
"step": 113
|
840 |
+
},
|
841 |
+
{
|
842 |
+
"epoch": 0.98,
|
843 |
+
"learning_rate": 4.475677164966774e-08,
|
844 |
+
"loss": 0.0234,
|
845 |
+
"step": 114
|
846 |
+
},
|
847 |
+
{
|
848 |
+
"epoch": 0.98,
|
849 |
+
"eval_loss": 0.02534579671919346,
|
850 |
+
"eval_runtime": 32.8785,
|
851 |
+
"eval_samples_per_second": 8.516,
|
852 |
+
"eval_steps_per_second": 2.129,
|
853 |
+
"step": 114
|
854 |
+
},
|
855 |
+
{
|
856 |
+
"epoch": 0.99,
|
857 |
+
"learning_rate": 0.0,
|
858 |
+
"loss": 0.0243,
|
859 |
+
"step": 115
|
860 |
+
}
|
861 |
+
],
|
862 |
+
"logging_steps": 1,
|
863 |
+
"max_steps": 115,
|
864 |
+
"num_train_epochs": 1,
|
865 |
+
"save_steps": 500,
|
866 |
+
"total_flos": 1.3013449078053274e+18,
|
867 |
+
"trial_name": null,
|
868 |
+
"trial_params": null
|
869 |
+
}
|
checkpoint-115/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7e601afb4ba598a882f22ab2a398aeb04c074e05d11b89f5425167bcfe214e66
|
3 |
+
size 4603
|
config.json
ADDED
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "mistralai/Mistral-7B-v0.1",
|
3 |
+
"architectures": [
|
4 |
+
"MistralForCausalLM"
|
5 |
+
],
|
6 |
+
"bos_token_id": 1,
|
7 |
+
"eos_token_id": 2,
|
8 |
+
"hidden_act": "silu",
|
9 |
+
"hidden_size": 4096,
|
10 |
+
"initializer_range": 0.02,
|
11 |
+
"intermediate_size": 14336,
|
12 |
+
"max_position_embeddings": 32768,
|
13 |
+
"model_type": "mistral",
|
14 |
+
"num_attention_heads": 32,
|
15 |
+
"num_hidden_layers": 32,
|
16 |
+
"num_key_value_heads": 8,
|
17 |
+
"quantization_config": {
|
18 |
+
"bnb_4bit_compute_dtype": "bfloat16",
|
19 |
+
"bnb_4bit_quant_type": "nf4",
|
20 |
+
"bnb_4bit_use_double_quant": true,
|
21 |
+
"llm_int8_enable_fp32_cpu_offload": false,
|
22 |
+
"llm_int8_has_fp16_weight": false,
|
23 |
+
"llm_int8_skip_modules": null,
|
24 |
+
"llm_int8_threshold": 6.0,
|
25 |
+
"load_in_4bit": true,
|
26 |
+
"load_in_8bit": false,
|
27 |
+
"quant_method": "bitsandbytes"
|
28 |
+
},
|
29 |
+
"rms_norm_eps": 1e-05,
|
30 |
+
"rope_theta": 10000.0,
|
31 |
+
"sliding_window": 4096,
|
32 |
+
"tie_word_embeddings": false,
|
33 |
+
"torch_dtype": "bfloat16",
|
34 |
+
"transformers_version": "4.35.2",
|
35 |
+
"use_cache": false,
|
36 |
+
"vocab_size": 32000
|
37 |
+
}
|
special_tokens_map.json
ADDED
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<s>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": {
|
10 |
+
"content": "</s>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": "</s>",
|
17 |
+
"unk_token": {
|
18 |
+
"content": "<unk>",
|
19 |
+
"lstrip": false,
|
20 |
+
"normalized": false,
|
21 |
+
"rstrip": false,
|
22 |
+
"single_word": false
|
23 |
+
}
|
24 |
+
}
|
tokenizer.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
|
3 |
+
size 493443
|
tokenizer_config.json
ADDED
@@ -0,0 +1,44 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": true,
|
3 |
+
"add_eos_token": false,
|
4 |
+
"added_tokens_decoder": {
|
5 |
+
"0": {
|
6 |
+
"content": "<unk>",
|
7 |
+
"lstrip": false,
|
8 |
+
"normalized": false,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false,
|
11 |
+
"special": true
|
12 |
+
},
|
13 |
+
"1": {
|
14 |
+
"content": "<s>",
|
15 |
+
"lstrip": false,
|
16 |
+
"normalized": false,
|
17 |
+
"rstrip": false,
|
18 |
+
"single_word": false,
|
19 |
+
"special": true
|
20 |
+
},
|
21 |
+
"2": {
|
22 |
+
"content": "</s>",
|
23 |
+
"lstrip": false,
|
24 |
+
"normalized": false,
|
25 |
+
"rstrip": false,
|
26 |
+
"single_word": false,
|
27 |
+
"special": true
|
28 |
+
}
|
29 |
+
},
|
30 |
+
"additional_special_tokens": [],
|
31 |
+
"bos_token": "<s>",
|
32 |
+
"clean_up_tokenization_spaces": false,
|
33 |
+
"eos_token": "</s>",
|
34 |
+
"legacy": true,
|
35 |
+
"model_max_length": 1000000000000000019884624838656,
|
36 |
+
"pad_token": "</s>",
|
37 |
+
"sp_model_kwargs": {},
|
38 |
+
"spaces_between_special_tokens": false,
|
39 |
+
"tokenizer_class": "LlamaTokenizer",
|
40 |
+
"trust_remote_code": false,
|
41 |
+
"unk_token": "<unk>",
|
42 |
+
"use_default_system_prompt": true,
|
43 |
+
"use_fast": true
|
44 |
+
}
|