Upload folder using huggingface_hub
Browse files- README.md +238 -0
- adapter_config.json +23 -0
- adapter_model.bin +3 -0
- optimizer.pt +3 -0
- pytorch_model.bin +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +24 -0
- tokenizer.json +0 -0
- tokenizer.model +3 -0
- tokenizer_config.json +41 -0
- trainer_state.json +415 -0
- training_args.bin +3 -0
README.md
ADDED
@@ -0,0 +1,238 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: peft
|
3 |
+
base_model: mistralai/Mistral-7B-Instruct-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 |
+
- **Shared by [optional]:** [More Information Needed]
|
22 |
+
- **Model type:** [More Information Needed]
|
23 |
+
- **Language(s) (NLP):** [More Information Needed]
|
24 |
+
- **License:** [More Information Needed]
|
25 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
26 |
+
|
27 |
+
### Model Sources [optional]
|
28 |
+
|
29 |
+
<!-- Provide the basic links for the model. -->
|
30 |
+
|
31 |
+
- **Repository:** [More Information Needed]
|
32 |
+
- **Paper [optional]:** [More Information Needed]
|
33 |
+
- **Demo [optional]:** [More Information Needed]
|
34 |
+
|
35 |
+
## Uses
|
36 |
+
|
37 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
38 |
+
|
39 |
+
### Direct Use
|
40 |
+
|
41 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
42 |
+
|
43 |
+
[More Information Needed]
|
44 |
+
|
45 |
+
### Downstream Use [optional]
|
46 |
+
|
47 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
48 |
+
|
49 |
+
[More Information Needed]
|
50 |
+
|
51 |
+
### Out-of-Scope Use
|
52 |
+
|
53 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
54 |
+
|
55 |
+
[More Information Needed]
|
56 |
+
|
57 |
+
## Bias, Risks, and Limitations
|
58 |
+
|
59 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
60 |
+
|
61 |
+
[More Information Needed]
|
62 |
+
|
63 |
+
### Recommendations
|
64 |
+
|
65 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
66 |
+
|
67 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
68 |
+
|
69 |
+
## How to Get Started with the Model
|
70 |
+
|
71 |
+
Use the code below to get started with the model.
|
72 |
+
|
73 |
+
[More Information Needed]
|
74 |
+
|
75 |
+
## Training Details
|
76 |
+
|
77 |
+
### Training Data
|
78 |
+
|
79 |
+
<!-- This should link to a Data 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. -->
|
80 |
+
|
81 |
+
[More Information Needed]
|
82 |
+
|
83 |
+
### Training Procedure
|
84 |
+
|
85 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
86 |
+
|
87 |
+
#### Preprocessing [optional]
|
88 |
+
|
89 |
+
[More Information Needed]
|
90 |
+
|
91 |
+
|
92 |
+
#### Training Hyperparameters
|
93 |
+
|
94 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
95 |
+
|
96 |
+
#### Speeds, Sizes, Times [optional]
|
97 |
+
|
98 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
99 |
+
|
100 |
+
[More Information Needed]
|
101 |
+
|
102 |
+
## Evaluation
|
103 |
+
|
104 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
105 |
+
|
106 |
+
### Testing Data, Factors & Metrics
|
107 |
+
|
108 |
+
#### Testing Data
|
109 |
+
|
110 |
+
<!-- This should link to a Data Card if possible. -->
|
111 |
+
|
112 |
+
[More Information Needed]
|
113 |
+
|
114 |
+
#### Factors
|
115 |
+
|
116 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
117 |
+
|
118 |
+
[More Information Needed]
|
119 |
+
|
120 |
+
#### Metrics
|
121 |
+
|
122 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
123 |
+
|
124 |
+
[More Information Needed]
|
125 |
+
|
126 |
+
### Results
|
127 |
+
|
128 |
+
[More Information Needed]
|
129 |
+
|
130 |
+
#### Summary
|
131 |
+
|
132 |
+
|
133 |
+
|
134 |
+
## Model Examination [optional]
|
135 |
+
|
136 |
+
<!-- Relevant interpretability work for the model goes here -->
|
137 |
+
|
138 |
+
[More Information Needed]
|
139 |
+
|
140 |
+
## Environmental Impact
|
141 |
+
|
142 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
143 |
+
|
144 |
+
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).
|
145 |
+
|
146 |
+
- **Hardware Type:** [More Information Needed]
|
147 |
+
- **Hours used:** [More Information Needed]
|
148 |
+
- **Cloud Provider:** [More Information Needed]
|
149 |
+
- **Compute Region:** [More Information Needed]
|
150 |
+
- **Carbon Emitted:** [More Information Needed]
|
151 |
+
|
152 |
+
## Technical Specifications [optional]
|
153 |
+
|
154 |
+
### Model Architecture and Objective
|
155 |
+
|
156 |
+
[More Information Needed]
|
157 |
+
|
158 |
+
### Compute Infrastructure
|
159 |
+
|
160 |
+
[More Information Needed]
|
161 |
+
|
162 |
+
#### Hardware
|
163 |
+
|
164 |
+
[More Information Needed]
|
165 |
+
|
166 |
+
#### Software
|
167 |
+
|
168 |
+
[More Information Needed]
|
169 |
+
|
170 |
+
## Citation [optional]
|
171 |
+
|
172 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
173 |
+
|
174 |
+
**BibTeX:**
|
175 |
+
|
176 |
+
[More Information Needed]
|
177 |
+
|
178 |
+
**APA:**
|
179 |
+
|
180 |
+
[More Information Needed]
|
181 |
+
|
182 |
+
## Glossary [optional]
|
183 |
+
|
184 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
185 |
+
|
186 |
+
[More Information Needed]
|
187 |
+
|
188 |
+
## More Information [optional]
|
189 |
+
|
190 |
+
[More Information Needed]
|
191 |
+
|
192 |
+
## Model Card Authors [optional]
|
193 |
+
|
194 |
+
[More Information Needed]
|
195 |
+
|
196 |
+
## Model Card Contact
|
197 |
+
|
198 |
+
[More Information Needed]
|
199 |
+
|
200 |
+
|
201 |
+
## Training procedure
|
202 |
+
|
203 |
+
|
204 |
+
The following `bitsandbytes` quantization config was used during training:
|
205 |
+
- quant_method: bitsandbytes
|
206 |
+
- load_in_8bit: False
|
207 |
+
- load_in_4bit: True
|
208 |
+
- llm_int8_threshold: 6.0
|
209 |
+
- llm_int8_skip_modules: None
|
210 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
211 |
+
- llm_int8_has_fp16_weight: False
|
212 |
+
- bnb_4bit_quant_type: nf4
|
213 |
+
- bnb_4bit_use_double_quant: False
|
214 |
+
- bnb_4bit_compute_dtype: float16
|
215 |
+
|
216 |
+
### Framework versions
|
217 |
+
|
218 |
+
|
219 |
+
- PEFT 0.6.0
|
220 |
+
## Training procedure
|
221 |
+
|
222 |
+
|
223 |
+
The following `bitsandbytes` quantization config was used during training:
|
224 |
+
- quant_method: bitsandbytes
|
225 |
+
- load_in_8bit: False
|
226 |
+
- load_in_4bit: True
|
227 |
+
- llm_int8_threshold: 6.0
|
228 |
+
- llm_int8_skip_modules: None
|
229 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
230 |
+
- llm_int8_has_fp16_weight: False
|
231 |
+
- bnb_4bit_quant_type: nf4
|
232 |
+
- bnb_4bit_use_double_quant: False
|
233 |
+
- bnb_4bit_compute_dtype: float16
|
234 |
+
|
235 |
+
### Framework versions
|
236 |
+
|
237 |
+
|
238 |
+
- PEFT 0.6.0
|
adapter_config.json
ADDED
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "mistralai/Mistral-7B-Instruct-v0.1",
|
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": 0.1,
|
13 |
+
"modules_to_save": null,
|
14 |
+
"peft_type": "LORA",
|
15 |
+
"r": 16,
|
16 |
+
"rank_pattern": {},
|
17 |
+
"revision": null,
|
18 |
+
"target_modules": [
|
19 |
+
"v_proj",
|
20 |
+
"q_proj"
|
21 |
+
],
|
22 |
+
"task_type": "CAUSAL_LM"
|
23 |
+
}
|
adapter_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cc214d77e48fe37d5c7331fa5dff19e428628e7a225bd2fd06fc15bdc567cb4a
|
3 |
+
size 27308941
|
optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3ace0243825602015ca38c06f1ea093aa2c883e104b73e4c5c3e77bf2dc6a9a1
|
3 |
+
size 54633541
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c152074a486243089e4fc0fdee0a373a30fb0e0a6e40eb5fd0d36fdafc97a155
|
3 |
+
size 443
|
rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b994ea2fe7656eae3bdc78f867f4496e60d163ba755584eb603a60cd0866296c
|
3 |
+
size 14575
|
scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:88eaae226562ce5b360fdd68a9def1943a56b58b1d718c3a52e4fdc1c3e953a8
|
3 |
+
size 627
|
special_tokens_map.json
ADDED
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<s>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": {
|
10 |
+
"content": "</s>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": "</s>",
|
17 |
+
"unk_token": {
|
18 |
+
"content": "<unk>",
|
19 |
+
"lstrip": false,
|
20 |
+
"normalized": false,
|
21 |
+
"rstrip": false,
|
22 |
+
"single_word": false
|
23 |
+
}
|
24 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
|
3 |
+
size 493443
|
tokenizer_config.json
ADDED
@@ -0,0 +1,41 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"0": {
|
4 |
+
"content": "<unk>",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false,
|
9 |
+
"special": true
|
10 |
+
},
|
11 |
+
"1": {
|
12 |
+
"content": "<s>",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"2": {
|
20 |
+
"content": "</s>",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
}
|
27 |
+
},
|
28 |
+
"additional_special_tokens": [],
|
29 |
+
"bos_token": "<s>",
|
30 |
+
"chat_template": "{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if message['role'] == 'user' %}{{ '[INST] ' + message['content'] + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ message['content'] + eos_token + ' ' }}{% else %}{{ raise_exception('Only user and assistant roles are supported!') }}{% endif %}{% endfor %}",
|
31 |
+
"clean_up_tokenization_spaces": false,
|
32 |
+
"eos_token": "</s>",
|
33 |
+
"legacy": true,
|
34 |
+
"model_max_length": 1024,
|
35 |
+
"pad_token": "</s>",
|
36 |
+
"sp_model_kwargs": {},
|
37 |
+
"spaces_between_special_tokens": false,
|
38 |
+
"tokenizer_class": "LlamaTokenizer",
|
39 |
+
"unk_token": "<unk>",
|
40 |
+
"use_default_system_prompt": true
|
41 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,415 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 42.10526315789474,
|
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": 0.63,
|
13 |
+
"learning_rate": 0.0003,
|
14 |
+
"loss": 1.3677,
|
15 |
+
"step": 3
|
16 |
+
},
|
17 |
+
{
|
18 |
+
"epoch": 1.26,
|
19 |
+
"learning_rate": 0.0006,
|
20 |
+
"loss": 1.0177,
|
21 |
+
"step": 6
|
22 |
+
},
|
23 |
+
{
|
24 |
+
"epoch": 1.89,
|
25 |
+
"learning_rate": 0.0008,
|
26 |
+
"loss": 0.8893,
|
27 |
+
"step": 9
|
28 |
+
},
|
29 |
+
{
|
30 |
+
"epoch": 2.53,
|
31 |
+
"learning_rate": 0.001,
|
32 |
+
"loss": 1.0625,
|
33 |
+
"step": 12
|
34 |
+
},
|
35 |
+
{
|
36 |
+
"epoch": 3.16,
|
37 |
+
"learning_rate": 0.0013000000000000002,
|
38 |
+
"loss": 0.7547,
|
39 |
+
"step": 15
|
40 |
+
},
|
41 |
+
{
|
42 |
+
"epoch": 3.79,
|
43 |
+
"learning_rate": 0.0016,
|
44 |
+
"loss": 0.4742,
|
45 |
+
"step": 18
|
46 |
+
},
|
47 |
+
{
|
48 |
+
"epoch": 4.42,
|
49 |
+
"learning_rate": 0.0019,
|
50 |
+
"loss": 0.3748,
|
51 |
+
"step": 21
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 5.05,
|
55 |
+
"learning_rate": 0.001977777777777778,
|
56 |
+
"loss": 0.4516,
|
57 |
+
"step": 24
|
58 |
+
},
|
59 |
+
{
|
60 |
+
"epoch": 5.68,
|
61 |
+
"learning_rate": 0.0019555555555555554,
|
62 |
+
"loss": 0.3278,
|
63 |
+
"step": 27
|
64 |
+
},
|
65 |
+
{
|
66 |
+
"epoch": 6.32,
|
67 |
+
"learning_rate": 0.0019222222222222223,
|
68 |
+
"loss": 0.421,
|
69 |
+
"step": 30
|
70 |
+
},
|
71 |
+
{
|
72 |
+
"epoch": 6.95,
|
73 |
+
"learning_rate": 0.001888888888888889,
|
74 |
+
"loss": 0.2738,
|
75 |
+
"step": 33
|
76 |
+
},
|
77 |
+
{
|
78 |
+
"epoch": 7.58,
|
79 |
+
"learning_rate": 0.0018555555555555556,
|
80 |
+
"loss": 0.2307,
|
81 |
+
"step": 36
|
82 |
+
},
|
83 |
+
{
|
84 |
+
"epoch": 8.21,
|
85 |
+
"learning_rate": 0.0018222222222222223,
|
86 |
+
"loss": 0.2955,
|
87 |
+
"step": 39
|
88 |
+
},
|
89 |
+
{
|
90 |
+
"epoch": 8.84,
|
91 |
+
"learning_rate": 0.0018000000000000002,
|
92 |
+
"loss": 0.399,
|
93 |
+
"step": 42
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 9.47,
|
97 |
+
"learning_rate": 0.001788888888888889,
|
98 |
+
"loss": 0.6656,
|
99 |
+
"step": 45
|
100 |
+
},
|
101 |
+
{
|
102 |
+
"epoch": 10.11,
|
103 |
+
"learning_rate": 0.0017666666666666666,
|
104 |
+
"loss": 0.7389,
|
105 |
+
"step": 48
|
106 |
+
},
|
107 |
+
{
|
108 |
+
"epoch": 10.74,
|
109 |
+
"learning_rate": 0.0017333333333333335,
|
110 |
+
"loss": 0.1417,
|
111 |
+
"step": 51
|
112 |
+
},
|
113 |
+
{
|
114 |
+
"epoch": 11.37,
|
115 |
+
"learning_rate": 0.0017,
|
116 |
+
"loss": 0.2441,
|
117 |
+
"step": 54
|
118 |
+
},
|
119 |
+
{
|
120 |
+
"epoch": 12.0,
|
121 |
+
"learning_rate": 0.0016666666666666668,
|
122 |
+
"loss": 0.1786,
|
123 |
+
"step": 57
|
124 |
+
},
|
125 |
+
{
|
126 |
+
"epoch": 12.63,
|
127 |
+
"learning_rate": 0.0016333333333333334,
|
128 |
+
"loss": 0.0805,
|
129 |
+
"step": 60
|
130 |
+
},
|
131 |
+
{
|
132 |
+
"epoch": 13.26,
|
133 |
+
"learning_rate": 0.0016,
|
134 |
+
"loss": 0.1806,
|
135 |
+
"step": 63
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 13.89,
|
139 |
+
"learning_rate": 0.0015666666666666667,
|
140 |
+
"loss": 0.1011,
|
141 |
+
"step": 66
|
142 |
+
},
|
143 |
+
{
|
144 |
+
"epoch": 14.53,
|
145 |
+
"learning_rate": 0.0015333333333333334,
|
146 |
+
"loss": 0.08,
|
147 |
+
"step": 69
|
148 |
+
},
|
149 |
+
{
|
150 |
+
"epoch": 15.16,
|
151 |
+
"learning_rate": 0.0015,
|
152 |
+
"loss": 0.0982,
|
153 |
+
"step": 72
|
154 |
+
},
|
155 |
+
{
|
156 |
+
"epoch": 15.79,
|
157 |
+
"learning_rate": 0.0014666666666666667,
|
158 |
+
"loss": 0.1105,
|
159 |
+
"step": 75
|
160 |
+
},
|
161 |
+
{
|
162 |
+
"epoch": 16.42,
|
163 |
+
"learning_rate": 0.0014333333333333333,
|
164 |
+
"loss": 0.1103,
|
165 |
+
"step": 78
|
166 |
+
},
|
167 |
+
{
|
168 |
+
"epoch": 17.05,
|
169 |
+
"learning_rate": 0.0014,
|
170 |
+
"loss": 0.086,
|
171 |
+
"step": 81
|
172 |
+
},
|
173 |
+
{
|
174 |
+
"epoch": 17.68,
|
175 |
+
"learning_rate": 0.0013666666666666666,
|
176 |
+
"loss": 0.0764,
|
177 |
+
"step": 84
|
178 |
+
},
|
179 |
+
{
|
180 |
+
"epoch": 18.32,
|
181 |
+
"learning_rate": 0.0013333333333333333,
|
182 |
+
"loss": 0.0748,
|
183 |
+
"step": 87
|
184 |
+
},
|
185 |
+
{
|
186 |
+
"epoch": 18.95,
|
187 |
+
"learning_rate": 0.0013000000000000002,
|
188 |
+
"loss": 0.1183,
|
189 |
+
"step": 90
|
190 |
+
},
|
191 |
+
{
|
192 |
+
"epoch": 19.58,
|
193 |
+
"learning_rate": 0.0012666666666666666,
|
194 |
+
"loss": 0.059,
|
195 |
+
"step": 93
|
196 |
+
},
|
197 |
+
{
|
198 |
+
"epoch": 20.21,
|
199 |
+
"learning_rate": 0.0012333333333333335,
|
200 |
+
"loss": 0.0706,
|
201 |
+
"step": 96
|
202 |
+
},
|
203 |
+
{
|
204 |
+
"epoch": 20.84,
|
205 |
+
"learning_rate": 0.0012,
|
206 |
+
"loss": 0.0499,
|
207 |
+
"step": 99
|
208 |
+
},
|
209 |
+
{
|
210 |
+
"epoch": 21.47,
|
211 |
+
"learning_rate": 0.0011666666666666668,
|
212 |
+
"loss": 0.0406,
|
213 |
+
"step": 102
|
214 |
+
},
|
215 |
+
{
|
216 |
+
"epoch": 22.11,
|
217 |
+
"learning_rate": 0.0011333333333333334,
|
218 |
+
"loss": 0.0569,
|
219 |
+
"step": 105
|
220 |
+
},
|
221 |
+
{
|
222 |
+
"epoch": 22.74,
|
223 |
+
"learning_rate": 0.0011,
|
224 |
+
"loss": 0.0354,
|
225 |
+
"step": 108
|
226 |
+
},
|
227 |
+
{
|
228 |
+
"epoch": 23.37,
|
229 |
+
"learning_rate": 0.0010666666666666667,
|
230 |
+
"loss": 0.0362,
|
231 |
+
"step": 111
|
232 |
+
},
|
233 |
+
{
|
234 |
+
"epoch": 24.0,
|
235 |
+
"learning_rate": 0.0010333333333333334,
|
236 |
+
"loss": 0.0752,
|
237 |
+
"step": 114
|
238 |
+
},
|
239 |
+
{
|
240 |
+
"epoch": 24.63,
|
241 |
+
"learning_rate": 0.001,
|
242 |
+
"loss": 0.026,
|
243 |
+
"step": 117
|
244 |
+
},
|
245 |
+
{
|
246 |
+
"epoch": 25.26,
|
247 |
+
"learning_rate": 0.0009666666666666667,
|
248 |
+
"loss": 0.0418,
|
249 |
+
"step": 120
|
250 |
+
},
|
251 |
+
{
|
252 |
+
"epoch": 25.89,
|
253 |
+
"learning_rate": 0.0009333333333333333,
|
254 |
+
"loss": 0.0332,
|
255 |
+
"step": 123
|
256 |
+
},
|
257 |
+
{
|
258 |
+
"epoch": 26.53,
|
259 |
+
"learning_rate": 0.0009000000000000001,
|
260 |
+
"loss": 0.0245,
|
261 |
+
"step": 126
|
262 |
+
},
|
263 |
+
{
|
264 |
+
"epoch": 27.16,
|
265 |
+
"learning_rate": 0.0008666666666666667,
|
266 |
+
"loss": 0.036,
|
267 |
+
"step": 129
|
268 |
+
},
|
269 |
+
{
|
270 |
+
"epoch": 27.79,
|
271 |
+
"learning_rate": 0.0008333333333333334,
|
272 |
+
"loss": 0.0233,
|
273 |
+
"step": 132
|
274 |
+
},
|
275 |
+
{
|
276 |
+
"epoch": 28.42,
|
277 |
+
"learning_rate": 0.0008,
|
278 |
+
"loss": 0.0246,
|
279 |
+
"step": 135
|
280 |
+
},
|
281 |
+
{
|
282 |
+
"epoch": 29.05,
|
283 |
+
"learning_rate": 0.0007666666666666667,
|
284 |
+
"loss": 0.0249,
|
285 |
+
"step": 138
|
286 |
+
},
|
287 |
+
{
|
288 |
+
"epoch": 29.68,
|
289 |
+
"learning_rate": 0.0007333333333333333,
|
290 |
+
"loss": 0.0217,
|
291 |
+
"step": 141
|
292 |
+
},
|
293 |
+
{
|
294 |
+
"epoch": 30.32,
|
295 |
+
"learning_rate": 0.0007,
|
296 |
+
"loss": 0.0157,
|
297 |
+
"step": 144
|
298 |
+
},
|
299 |
+
{
|
300 |
+
"epoch": 30.95,
|
301 |
+
"learning_rate": 0.0006666666666666666,
|
302 |
+
"loss": 0.0185,
|
303 |
+
"step": 147
|
304 |
+
},
|
305 |
+
{
|
306 |
+
"epoch": 31.58,
|
307 |
+
"learning_rate": 0.0006333333333333333,
|
308 |
+
"loss": 0.0122,
|
309 |
+
"step": 150
|
310 |
+
},
|
311 |
+
{
|
312 |
+
"epoch": 32.21,
|
313 |
+
"learning_rate": 0.0006,
|
314 |
+
"loss": 0.0106,
|
315 |
+
"step": 153
|
316 |
+
},
|
317 |
+
{
|
318 |
+
"epoch": 32.84,
|
319 |
+
"learning_rate": 0.0005666666666666667,
|
320 |
+
"loss": 0.0143,
|
321 |
+
"step": 156
|
322 |
+
},
|
323 |
+
{
|
324 |
+
"epoch": 33.47,
|
325 |
+
"learning_rate": 0.0005333333333333334,
|
326 |
+
"loss": 0.0085,
|
327 |
+
"step": 159
|
328 |
+
},
|
329 |
+
{
|
330 |
+
"epoch": 34.11,
|
331 |
+
"learning_rate": 0.0005,
|
332 |
+
"loss": 0.011,
|
333 |
+
"step": 162
|
334 |
+
},
|
335 |
+
{
|
336 |
+
"epoch": 34.74,
|
337 |
+
"learning_rate": 0.00046666666666666666,
|
338 |
+
"loss": 0.0077,
|
339 |
+
"step": 165
|
340 |
+
},
|
341 |
+
{
|
342 |
+
"epoch": 35.37,
|
343 |
+
"learning_rate": 0.00043333333333333337,
|
344 |
+
"loss": 0.0075,
|
345 |
+
"step": 168
|
346 |
+
},
|
347 |
+
{
|
348 |
+
"epoch": 36.0,
|
349 |
+
"learning_rate": 0.0004,
|
350 |
+
"loss": 0.0062,
|
351 |
+
"step": 171
|
352 |
+
},
|
353 |
+
{
|
354 |
+
"epoch": 36.63,
|
355 |
+
"learning_rate": 0.00036666666666666667,
|
356 |
+
"loss": 0.0049,
|
357 |
+
"step": 174
|
358 |
+
},
|
359 |
+
{
|
360 |
+
"epoch": 37.26,
|
361 |
+
"learning_rate": 0.0003333333333333333,
|
362 |
+
"loss": 0.0057,
|
363 |
+
"step": 177
|
364 |
+
},
|
365 |
+
{
|
366 |
+
"epoch": 37.89,
|
367 |
+
"learning_rate": 0.0003,
|
368 |
+
"loss": 0.0068,
|
369 |
+
"step": 180
|
370 |
+
},
|
371 |
+
{
|
372 |
+
"epoch": 38.53,
|
373 |
+
"learning_rate": 0.0002666666666666667,
|
374 |
+
"loss": 0.0055,
|
375 |
+
"step": 183
|
376 |
+
},
|
377 |
+
{
|
378 |
+
"epoch": 39.16,
|
379 |
+
"learning_rate": 0.00023333333333333333,
|
380 |
+
"loss": 0.0046,
|
381 |
+
"step": 186
|
382 |
+
},
|
383 |
+
{
|
384 |
+
"epoch": 39.79,
|
385 |
+
"learning_rate": 0.0002,
|
386 |
+
"loss": 0.0053,
|
387 |
+
"step": 189
|
388 |
+
},
|
389 |
+
{
|
390 |
+
"epoch": 40.42,
|
391 |
+
"learning_rate": 0.00016666666666666666,
|
392 |
+
"loss": 0.004,
|
393 |
+
"step": 192
|
394 |
+
},
|
395 |
+
{
|
396 |
+
"epoch": 41.05,
|
397 |
+
"learning_rate": 0.00013333333333333334,
|
398 |
+
"loss": 0.005,
|
399 |
+
"step": 195
|
400 |
+
},
|
401 |
+
{
|
402 |
+
"epoch": 41.68,
|
403 |
+
"learning_rate": 0.0001,
|
404 |
+
"loss": 0.004,
|
405 |
+
"step": 198
|
406 |
+
}
|
407 |
+
],
|
408 |
+
"logging_steps": 3,
|
409 |
+
"max_steps": 200,
|
410 |
+
"num_train_epochs": 50,
|
411 |
+
"save_steps": 500,
|
412 |
+
"total_flos": 3.4983817248768e+16,
|
413 |
+
"trial_name": null,
|
414 |
+
"trial_params": null
|
415 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b693d54307355778cd50ca42649f72c3996ebbf8ed2fa012e475c50e84d49904
|
3 |
+
size 4027
|