Upload folder using huggingface_hub
Browse files- README.md +204 -0
- adapter_config.json +32 -0
- adapter_model.safetensors +3 -0
- special_tokens_map.json +24 -0
- tokenizer.json +0 -0
- tokenizer_config.json +43 -0
- trainer_state.json +888 -0
- training_args.bin +3 -0
README.md
ADDED
@@ -0,0 +1,204 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: peft
|
3 |
+
base_model: mistralai/Mistral-7b-Instruct-v0.2
|
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 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "mistralai/Mistral-7b-Instruct-v0.2",
|
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": 16,
|
19 |
+
"rank_pattern": {},
|
20 |
+
"revision": null,
|
21 |
+
"target_modules": [
|
22 |
+
"gate_proj",
|
23 |
+
"v_proj",
|
24 |
+
"o_proj",
|
25 |
+
"k_proj",
|
26 |
+
"up_proj",
|
27 |
+
"down_proj",
|
28 |
+
"q_proj"
|
29 |
+
],
|
30 |
+
"task_type": "CAUSAL_LM",
|
31 |
+
"use_rslora": false
|
32 |
+
}
|
adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a79748882fe671c49e659e4f7428e64b794c2b8008716aa97a869d720db83fdf
|
3 |
+
size 83946192
|
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": "<unk>",
|
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_config.json
ADDED
@@ -0,0 +1,43 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
"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 %}",
|
33 |
+
"clean_up_tokenization_spaces": false,
|
34 |
+
"eos_token": "</s>",
|
35 |
+
"legacy": true,
|
36 |
+
"model_max_length": 8192,
|
37 |
+
"pad_token": "<unk>",
|
38 |
+
"sp_model_kwargs": {},
|
39 |
+
"spaces_between_special_tokens": false,
|
40 |
+
"tokenizer_class": "LlamaTokenizer",
|
41 |
+
"unk_token": "<unk>",
|
42 |
+
"use_default_system_prompt": false
|
43 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,888 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 1.0,
|
5 |
+
"eval_steps": 21,
|
6 |
+
"global_step": 135,
|
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": 9.998646205897309e-05,
|
14 |
+
"loss": 0.6057,
|
15 |
+
"step": 1
|
16 |
+
},
|
17 |
+
{
|
18 |
+
"epoch": 0.01,
|
19 |
+
"learning_rate": 9.994585556692624e-05,
|
20 |
+
"loss": 0.4662,
|
21 |
+
"step": 2
|
22 |
+
},
|
23 |
+
{
|
24 |
+
"epoch": 0.02,
|
25 |
+
"learning_rate": 9.987820251299122e-05,
|
26 |
+
"loss": 0.3514,
|
27 |
+
"step": 3
|
28 |
+
},
|
29 |
+
{
|
30 |
+
"epoch": 0.03,
|
31 |
+
"learning_rate": 9.978353953249022e-05,
|
32 |
+
"loss": 0.2457,
|
33 |
+
"step": 4
|
34 |
+
},
|
35 |
+
{
|
36 |
+
"epoch": 0.04,
|
37 |
+
"learning_rate": 9.966191788709716e-05,
|
38 |
+
"loss": 0.2152,
|
39 |
+
"step": 5
|
40 |
+
},
|
41 |
+
{
|
42 |
+
"epoch": 0.04,
|
43 |
+
"learning_rate": 9.951340343707852e-05,
|
44 |
+
"loss": 0.1948,
|
45 |
+
"step": 6
|
46 |
+
},
|
47 |
+
{
|
48 |
+
"epoch": 0.05,
|
49 |
+
"learning_rate": 9.933807660562898e-05,
|
50 |
+
"loss": 0.177,
|
51 |
+
"step": 7
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.06,
|
55 |
+
"learning_rate": 9.913603233532067e-05,
|
56 |
+
"loss": 0.1568,
|
57 |
+
"step": 8
|
58 |
+
},
|
59 |
+
{
|
60 |
+
"epoch": 0.07,
|
61 |
+
"learning_rate": 9.890738003669029e-05,
|
62 |
+
"loss": 0.123,
|
63 |
+
"step": 9
|
64 |
+
},
|
65 |
+
{
|
66 |
+
"epoch": 0.07,
|
67 |
+
"learning_rate": 9.865224352899119e-05,
|
68 |
+
"loss": 0.1174,
|
69 |
+
"step": 10
|
70 |
+
},
|
71 |
+
{
|
72 |
+
"epoch": 0.08,
|
73 |
+
"learning_rate": 9.837076097314319e-05,
|
74 |
+
"loss": 0.0905,
|
75 |
+
"step": 11
|
76 |
+
},
|
77 |
+
{
|
78 |
+
"epoch": 0.09,
|
79 |
+
"learning_rate": 9.806308479691595e-05,
|
80 |
+
"loss": 0.1101,
|
81 |
+
"step": 12
|
82 |
+
},
|
83 |
+
{
|
84 |
+
"epoch": 0.1,
|
85 |
+
"learning_rate": 9.77293816123866e-05,
|
86 |
+
"loss": 0.0767,
|
87 |
+
"step": 13
|
88 |
+
},
|
89 |
+
{
|
90 |
+
"epoch": 0.1,
|
91 |
+
"learning_rate": 9.736983212571646e-05,
|
92 |
+
"loss": 0.067,
|
93 |
+
"step": 14
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 0.11,
|
97 |
+
"learning_rate": 9.698463103929542e-05,
|
98 |
+
"loss": 0.0757,
|
99 |
+
"step": 15
|
100 |
+
},
|
101 |
+
{
|
102 |
+
"epoch": 0.12,
|
103 |
+
"learning_rate": 9.657398694630712e-05,
|
104 |
+
"loss": 0.0656,
|
105 |
+
"step": 16
|
106 |
+
},
|
107 |
+
{
|
108 |
+
"epoch": 0.13,
|
109 |
+
"learning_rate": 9.613812221777212e-05,
|
110 |
+
"loss": 0.0603,
|
111 |
+
"step": 17
|
112 |
+
},
|
113 |
+
{
|
114 |
+
"epoch": 0.13,
|
115 |
+
"learning_rate": 9.567727288213005e-05,
|
116 |
+
"loss": 0.0526,
|
117 |
+
"step": 18
|
118 |
+
},
|
119 |
+
{
|
120 |
+
"epoch": 0.14,
|
121 |
+
"learning_rate": 9.519168849742604e-05,
|
122 |
+
"loss": 0.0786,
|
123 |
+
"step": 19
|
124 |
+
},
|
125 |
+
{
|
126 |
+
"epoch": 0.15,
|
127 |
+
"learning_rate": 9.468163201617062e-05,
|
128 |
+
"loss": 0.0736,
|
129 |
+
"step": 20
|
130 |
+
},
|
131 |
+
{
|
132 |
+
"epoch": 0.16,
|
133 |
+
"learning_rate": 9.414737964294636e-05,
|
134 |
+
"loss": 0.0678,
|
135 |
+
"step": 21
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 0.16,
|
139 |
+
"eval_loss": 0.06099913641810417,
|
140 |
+
"eval_runtime": 21.2148,
|
141 |
+
"eval_samples_per_second": 1.414,
|
142 |
+
"eval_steps_per_second": 0.707,
|
143 |
+
"step": 21
|
144 |
+
},
|
145 |
+
{
|
146 |
+
"epoch": 0.16,
|
147 |
+
"learning_rate": 9.358922068483812e-05,
|
148 |
+
"loss": 0.0372,
|
149 |
+
"step": 22
|
150 |
+
},
|
151 |
+
{
|
152 |
+
"epoch": 0.17,
|
153 |
+
"learning_rate": 9.300745739476829e-05,
|
154 |
+
"loss": 0.0709,
|
155 |
+
"step": 23
|
156 |
+
},
|
157 |
+
{
|
158 |
+
"epoch": 0.18,
|
159 |
+
"learning_rate": 9.24024048078213e-05,
|
160 |
+
"loss": 0.0753,
|
161 |
+
"step": 24
|
162 |
+
},
|
163 |
+
{
|
164 |
+
"epoch": 0.19,
|
165 |
+
"learning_rate": 9.177439057064683e-05,
|
166 |
+
"loss": 0.0436,
|
167 |
+
"step": 25
|
168 |
+
},
|
169 |
+
{
|
170 |
+
"epoch": 0.19,
|
171 |
+
"learning_rate": 9.112375476403312e-05,
|
172 |
+
"loss": 0.0538,
|
173 |
+
"step": 26
|
174 |
+
},
|
175 |
+
{
|
176 |
+
"epoch": 0.2,
|
177 |
+
"learning_rate": 9.045084971874738e-05,
|
178 |
+
"loss": 0.0491,
|
179 |
+
"step": 27
|
180 |
+
},
|
181 |
+
{
|
182 |
+
"epoch": 0.21,
|
183 |
+
"learning_rate": 8.97560398247424e-05,
|
184 |
+
"loss": 0.0532,
|
185 |
+
"step": 28
|
186 |
+
},
|
187 |
+
{
|
188 |
+
"epoch": 0.21,
|
189 |
+
"learning_rate": 8.903970133383297e-05,
|
190 |
+
"loss": 0.0394,
|
191 |
+
"step": 29
|
192 |
+
},
|
193 |
+
{
|
194 |
+
"epoch": 0.22,
|
195 |
+
"learning_rate": 8.83022221559489e-05,
|
196 |
+
"loss": 0.0319,
|
197 |
+
"step": 30
|
198 |
+
},
|
199 |
+
{
|
200 |
+
"epoch": 0.23,
|
201 |
+
"learning_rate": 8.754400164907497e-05,
|
202 |
+
"loss": 0.053,
|
203 |
+
"step": 31
|
204 |
+
},
|
205 |
+
{
|
206 |
+
"epoch": 0.24,
|
207 |
+
"learning_rate": 8.676545040299145e-05,
|
208 |
+
"loss": 0.0409,
|
209 |
+
"step": 32
|
210 |
+
},
|
211 |
+
{
|
212 |
+
"epoch": 0.24,
|
213 |
+
"learning_rate": 8.596699001693255e-05,
|
214 |
+
"loss": 0.0456,
|
215 |
+
"step": 33
|
216 |
+
},
|
217 |
+
{
|
218 |
+
"epoch": 0.25,
|
219 |
+
"learning_rate": 8.51490528712831e-05,
|
220 |
+
"loss": 0.0354,
|
221 |
+
"step": 34
|
222 |
+
},
|
223 |
+
{
|
224 |
+
"epoch": 0.26,
|
225 |
+
"learning_rate": 8.43120818934367e-05,
|
226 |
+
"loss": 0.0324,
|
227 |
+
"step": 35
|
228 |
+
},
|
229 |
+
{
|
230 |
+
"epoch": 0.27,
|
231 |
+
"learning_rate": 8.345653031794292e-05,
|
232 |
+
"loss": 0.0279,
|
233 |
+
"step": 36
|
234 |
+
},
|
235 |
+
{
|
236 |
+
"epoch": 0.27,
|
237 |
+
"learning_rate": 8.258286144107276e-05,
|
238 |
+
"loss": 0.0309,
|
239 |
+
"step": 37
|
240 |
+
},
|
241 |
+
{
|
242 |
+
"epoch": 0.28,
|
243 |
+
"learning_rate": 8.169154836993551e-05,
|
244 |
+
"loss": 0.0374,
|
245 |
+
"step": 38
|
246 |
+
},
|
247 |
+
{
|
248 |
+
"epoch": 0.29,
|
249 |
+
"learning_rate": 8.07830737662829e-05,
|
250 |
+
"loss": 0.0465,
|
251 |
+
"step": 39
|
252 |
+
},
|
253 |
+
{
|
254 |
+
"epoch": 0.3,
|
255 |
+
"learning_rate": 7.985792958513931e-05,
|
256 |
+
"loss": 0.0213,
|
257 |
+
"step": 40
|
258 |
+
},
|
259 |
+
{
|
260 |
+
"epoch": 0.3,
|
261 |
+
"learning_rate": 7.891661680839932e-05,
|
262 |
+
"loss": 0.0263,
|
263 |
+
"step": 41
|
264 |
+
},
|
265 |
+
{
|
266 |
+
"epoch": 0.31,
|
267 |
+
"learning_rate": 7.795964517353735e-05,
|
268 |
+
"loss": 0.0177,
|
269 |
+
"step": 42
|
270 |
+
},
|
271 |
+
{
|
272 |
+
"epoch": 0.31,
|
273 |
+
"eval_loss": 0.021131165325641632,
|
274 |
+
"eval_runtime": 21.1467,
|
275 |
+
"eval_samples_per_second": 1.419,
|
276 |
+
"eval_steps_per_second": 0.709,
|
277 |
+
"step": 42
|
278 |
+
},
|
279 |
+
{
|
280 |
+
"epoch": 0.32,
|
281 |
+
"learning_rate": 7.698753289757565e-05,
|
282 |
+
"loss": 0.0155,
|
283 |
+
"step": 43
|
284 |
+
},
|
285 |
+
{
|
286 |
+
"epoch": 0.33,
|
287 |
+
"learning_rate": 7.600080639646077e-05,
|
288 |
+
"loss": 0.0158,
|
289 |
+
"step": 44
|
290 |
+
},
|
291 |
+
{
|
292 |
+
"epoch": 0.33,
|
293 |
+
"learning_rate": 7.500000000000001e-05,
|
294 |
+
"loss": 0.0342,
|
295 |
+
"step": 45
|
296 |
+
},
|
297 |
+
{
|
298 |
+
"epoch": 0.34,
|
299 |
+
"learning_rate": 7.398565566251232e-05,
|
300 |
+
"loss": 0.0175,
|
301 |
+
"step": 46
|
302 |
+
},
|
303 |
+
{
|
304 |
+
"epoch": 0.35,
|
305 |
+
"learning_rate": 7.295832266935059e-05,
|
306 |
+
"loss": 0.0215,
|
307 |
+
"step": 47
|
308 |
+
},
|
309 |
+
{
|
310 |
+
"epoch": 0.36,
|
311 |
+
"learning_rate": 7.191855733945387e-05,
|
312 |
+
"loss": 0.013,
|
313 |
+
"step": 48
|
314 |
+
},
|
315 |
+
{
|
316 |
+
"epoch": 0.36,
|
317 |
+
"learning_rate": 7.08669227240909e-05,
|
318 |
+
"loss": 0.0136,
|
319 |
+
"step": 49
|
320 |
+
},
|
321 |
+
{
|
322 |
+
"epoch": 0.37,
|
323 |
+
"learning_rate": 6.980398830195785e-05,
|
324 |
+
"loss": 0.0204,
|
325 |
+
"step": 50
|
326 |
+
},
|
327 |
+
{
|
328 |
+
"epoch": 0.38,
|
329 |
+
"learning_rate": 6.873032967079561e-05,
|
330 |
+
"loss": 0.0166,
|
331 |
+
"step": 51
|
332 |
+
},
|
333 |
+
{
|
334 |
+
"epoch": 0.39,
|
335 |
+
"learning_rate": 6.764652823569344e-05,
|
336 |
+
"loss": 0.0082,
|
337 |
+
"step": 52
|
338 |
+
},
|
339 |
+
{
|
340 |
+
"epoch": 0.39,
|
341 |
+
"learning_rate": 6.65531708942479e-05,
|
342 |
+
"loss": 0.011,
|
343 |
+
"step": 53
|
344 |
+
},
|
345 |
+
{
|
346 |
+
"epoch": 0.4,
|
347 |
+
"learning_rate": 6.545084971874738e-05,
|
348 |
+
"loss": 0.0167,
|
349 |
+
"step": 54
|
350 |
+
},
|
351 |
+
{
|
352 |
+
"epoch": 0.41,
|
353 |
+
"learning_rate": 6.434016163555452e-05,
|
354 |
+
"loss": 0.0077,
|
355 |
+
"step": 55
|
356 |
+
},
|
357 |
+
{
|
358 |
+
"epoch": 0.41,
|
359 |
+
"learning_rate": 6.322170810186012e-05,
|
360 |
+
"loss": 0.0087,
|
361 |
+
"step": 56
|
362 |
+
},
|
363 |
+
{
|
364 |
+
"epoch": 0.42,
|
365 |
+
"learning_rate": 6.209609477998338e-05,
|
366 |
+
"loss": 0.0097,
|
367 |
+
"step": 57
|
368 |
+
},
|
369 |
+
{
|
370 |
+
"epoch": 0.43,
|
371 |
+
"learning_rate": 6.096393120939516e-05,
|
372 |
+
"loss": 0.0096,
|
373 |
+
"step": 58
|
374 |
+
},
|
375 |
+
{
|
376 |
+
"epoch": 0.44,
|
377 |
+
"learning_rate": 5.982583047664151e-05,
|
378 |
+
"loss": 0.0049,
|
379 |
+
"step": 59
|
380 |
+
},
|
381 |
+
{
|
382 |
+
"epoch": 0.44,
|
383 |
+
"learning_rate": 5.868240888334653e-05,
|
384 |
+
"loss": 0.0127,
|
385 |
+
"step": 60
|
386 |
+
},
|
387 |
+
{
|
388 |
+
"epoch": 0.45,
|
389 |
+
"learning_rate": 5.753428561247416e-05,
|
390 |
+
"loss": 0.0064,
|
391 |
+
"step": 61
|
392 |
+
},
|
393 |
+
{
|
394 |
+
"epoch": 0.46,
|
395 |
+
"learning_rate": 5.6382082393029746e-05,
|
396 |
+
"loss": 0.0068,
|
397 |
+
"step": 62
|
398 |
+
},
|
399 |
+
{
|
400 |
+
"epoch": 0.47,
|
401 |
+
"learning_rate": 5.522642316338268e-05,
|
402 |
+
"loss": 0.0121,
|
403 |
+
"step": 63
|
404 |
+
},
|
405 |
+
{
|
406 |
+
"epoch": 0.47,
|
407 |
+
"eval_loss": 0.013300704769790173,
|
408 |
+
"eval_runtime": 21.1421,
|
409 |
+
"eval_samples_per_second": 1.419,
|
410 |
+
"eval_steps_per_second": 0.709,
|
411 |
+
"step": 63
|
412 |
+
},
|
413 |
+
{
|
414 |
+
"epoch": 0.47,
|
415 |
+
"learning_rate": 5.4067933733392915e-05,
|
416 |
+
"loss": 0.0037,
|
417 |
+
"step": 64
|
418 |
+
},
|
419 |
+
{
|
420 |
+
"epoch": 0.48,
|
421 |
+
"learning_rate": 5.290724144552379e-05,
|
422 |
+
"loss": 0.0112,
|
423 |
+
"step": 65
|
424 |
+
},
|
425 |
+
{
|
426 |
+
"epoch": 0.49,
|
427 |
+
"learning_rate": 5.174497483512506e-05,
|
428 |
+
"loss": 0.0091,
|
429 |
+
"step": 66
|
430 |
+
},
|
431 |
+
{
|
432 |
+
"epoch": 0.5,
|
433 |
+
"learning_rate": 5.0581763290069865e-05,
|
434 |
+
"loss": 0.0175,
|
435 |
+
"step": 67
|
436 |
+
},
|
437 |
+
{
|
438 |
+
"epoch": 0.5,
|
439 |
+
"learning_rate": 4.941823670993016e-05,
|
440 |
+
"loss": 0.009,
|
441 |
+
"step": 68
|
442 |
+
},
|
443 |
+
{
|
444 |
+
"epoch": 0.51,
|
445 |
+
"learning_rate": 4.825502516487497e-05,
|
446 |
+
"loss": 0.0055,
|
447 |
+
"step": 69
|
448 |
+
},
|
449 |
+
{
|
450 |
+
"epoch": 0.52,
|
451 |
+
"learning_rate": 4.709275855447621e-05,
|
452 |
+
"loss": 0.0276,
|
453 |
+
"step": 70
|
454 |
+
},
|
455 |
+
{
|
456 |
+
"epoch": 0.53,
|
457 |
+
"learning_rate": 4.593206626660709e-05,
|
458 |
+
"loss": 0.013,
|
459 |
+
"step": 71
|
460 |
+
},
|
461 |
+
{
|
462 |
+
"epoch": 0.53,
|
463 |
+
"learning_rate": 4.477357683661734e-05,
|
464 |
+
"loss": 0.0102,
|
465 |
+
"step": 72
|
466 |
+
},
|
467 |
+
{
|
468 |
+
"epoch": 0.54,
|
469 |
+
"learning_rate": 4.361791760697027e-05,
|
470 |
+
"loss": 0.0095,
|
471 |
+
"step": 73
|
472 |
+
},
|
473 |
+
{
|
474 |
+
"epoch": 0.55,
|
475 |
+
"learning_rate": 4.246571438752585e-05,
|
476 |
+
"loss": 0.0077,
|
477 |
+
"step": 74
|
478 |
+
},
|
479 |
+
{
|
480 |
+
"epoch": 0.56,
|
481 |
+
"learning_rate": 4.131759111665349e-05,
|
482 |
+
"loss": 0.006,
|
483 |
+
"step": 75
|
484 |
+
},
|
485 |
+
{
|
486 |
+
"epoch": 0.56,
|
487 |
+
"learning_rate": 4.017416952335849e-05,
|
488 |
+
"loss": 0.0054,
|
489 |
+
"step": 76
|
490 |
+
},
|
491 |
+
{
|
492 |
+
"epoch": 0.57,
|
493 |
+
"learning_rate": 3.903606879060483e-05,
|
494 |
+
"loss": 0.0114,
|
495 |
+
"step": 77
|
496 |
+
},
|
497 |
+
{
|
498 |
+
"epoch": 0.58,
|
499 |
+
"learning_rate": 3.790390522001662e-05,
|
500 |
+
"loss": 0.0044,
|
501 |
+
"step": 78
|
502 |
+
},
|
503 |
+
{
|
504 |
+
"epoch": 0.59,
|
505 |
+
"learning_rate": 3.67782918981399e-05,
|
506 |
+
"loss": 0.0072,
|
507 |
+
"step": 79
|
508 |
+
},
|
509 |
+
{
|
510 |
+
"epoch": 0.59,
|
511 |
+
"learning_rate": 3.5659838364445505e-05,
|
512 |
+
"loss": 0.0047,
|
513 |
+
"step": 80
|
514 |
+
},
|
515 |
+
{
|
516 |
+
"epoch": 0.6,
|
517 |
+
"learning_rate": 3.4549150281252636e-05,
|
518 |
+
"loss": 0.0058,
|
519 |
+
"step": 81
|
520 |
+
},
|
521 |
+
{
|
522 |
+
"epoch": 0.61,
|
523 |
+
"learning_rate": 3.34468291057521e-05,
|
524 |
+
"loss": 0.0095,
|
525 |
+
"step": 82
|
526 |
+
},
|
527 |
+
{
|
528 |
+
"epoch": 0.61,
|
529 |
+
"learning_rate": 3.235347176430656e-05,
|
530 |
+
"loss": 0.0008,
|
531 |
+
"step": 83
|
532 |
+
},
|
533 |
+
{
|
534 |
+
"epoch": 0.62,
|
535 |
+
"learning_rate": 3.12696703292044e-05,
|
536 |
+
"loss": 0.0079,
|
537 |
+
"step": 84
|
538 |
+
},
|
539 |
+
{
|
540 |
+
"epoch": 0.62,
|
541 |
+
"eval_loss": 0.006422529462724924,
|
542 |
+
"eval_runtime": 21.1401,
|
543 |
+
"eval_samples_per_second": 1.419,
|
544 |
+
"eval_steps_per_second": 0.71,
|
545 |
+
"step": 84
|
546 |
+
},
|
547 |
+
{
|
548 |
+
"epoch": 0.63,
|
549 |
+
"learning_rate": 3.019601169804216e-05,
|
550 |
+
"loss": 0.009,
|
551 |
+
"step": 85
|
552 |
+
},
|
553 |
+
{
|
554 |
+
"epoch": 0.64,
|
555 |
+
"learning_rate": 2.9133077275909108e-05,
|
556 |
+
"loss": 0.006,
|
557 |
+
"step": 86
|
558 |
+
},
|
559 |
+
{
|
560 |
+
"epoch": 0.64,
|
561 |
+
"learning_rate": 2.8081442660546125e-05,
|
562 |
+
"loss": 0.0089,
|
563 |
+
"step": 87
|
564 |
+
},
|
565 |
+
{
|
566 |
+
"epoch": 0.65,
|
567 |
+
"learning_rate": 2.7041677330649407e-05,
|
568 |
+
"loss": 0.0053,
|
569 |
+
"step": 88
|
570 |
+
},
|
571 |
+
{
|
572 |
+
"epoch": 0.66,
|
573 |
+
"learning_rate": 2.6014344337487707e-05,
|
574 |
+
"loss": 0.0047,
|
575 |
+
"step": 89
|
576 |
+
},
|
577 |
+
{
|
578 |
+
"epoch": 0.67,
|
579 |
+
"learning_rate": 2.500000000000001e-05,
|
580 |
+
"loss": 0.0054,
|
581 |
+
"step": 90
|
582 |
+
},
|
583 |
+
{
|
584 |
+
"epoch": 0.67,
|
585 |
+
"learning_rate": 2.399919360353923e-05,
|
586 |
+
"loss": 0.0014,
|
587 |
+
"step": 91
|
588 |
+
},
|
589 |
+
{
|
590 |
+
"epoch": 0.68,
|
591 |
+
"learning_rate": 2.3012467102424373e-05,
|
592 |
+
"loss": 0.0077,
|
593 |
+
"step": 92
|
594 |
+
},
|
595 |
+
{
|
596 |
+
"epoch": 0.69,
|
597 |
+
"learning_rate": 2.2040354826462668e-05,
|
598 |
+
"loss": 0.0116,
|
599 |
+
"step": 93
|
600 |
+
},
|
601 |
+
{
|
602 |
+
"epoch": 0.7,
|
603 |
+
"learning_rate": 2.1083383191600674e-05,
|
604 |
+
"loss": 0.0017,
|
605 |
+
"step": 94
|
606 |
+
},
|
607 |
+
{
|
608 |
+
"epoch": 0.7,
|
609 |
+
"learning_rate": 2.0142070414860704e-05,
|
610 |
+
"loss": 0.0073,
|
611 |
+
"step": 95
|
612 |
+
},
|
613 |
+
{
|
614 |
+
"epoch": 0.71,
|
615 |
+
"learning_rate": 1.9216926233717085e-05,
|
616 |
+
"loss": 0.0056,
|
617 |
+
"step": 96
|
618 |
+
},
|
619 |
+
{
|
620 |
+
"epoch": 0.72,
|
621 |
+
"learning_rate": 1.8308451630064484e-05,
|
622 |
+
"loss": 0.0025,
|
623 |
+
"step": 97
|
624 |
+
},
|
625 |
+
{
|
626 |
+
"epoch": 0.73,
|
627 |
+
"learning_rate": 1.7417138558927244e-05,
|
628 |
+
"loss": 0.0029,
|
629 |
+
"step": 98
|
630 |
+
},
|
631 |
+
{
|
632 |
+
"epoch": 0.73,
|
633 |
+
"learning_rate": 1.6543469682057106e-05,
|
634 |
+
"loss": 0.0026,
|
635 |
+
"step": 99
|
636 |
+
},
|
637 |
+
{
|
638 |
+
"epoch": 0.74,
|
639 |
+
"learning_rate": 1.5687918106563326e-05,
|
640 |
+
"loss": 0.0034,
|
641 |
+
"step": 100
|
642 |
+
},
|
643 |
+
{
|
644 |
+
"epoch": 0.75,
|
645 |
+
"learning_rate": 1.4850947128716913e-05,
|
646 |
+
"loss": 0.0007,
|
647 |
+
"step": 101
|
648 |
+
},
|
649 |
+
{
|
650 |
+
"epoch": 0.76,
|
651 |
+
"learning_rate": 1.4033009983067452e-05,
|
652 |
+
"loss": 0.0022,
|
653 |
+
"step": 102
|
654 |
+
},
|
655 |
+
{
|
656 |
+
"epoch": 0.76,
|
657 |
+
"learning_rate": 1.3234549597008571e-05,
|
658 |
+
"loss": 0.005,
|
659 |
+
"step": 103
|
660 |
+
},
|
661 |
+
{
|
662 |
+
"epoch": 0.77,
|
663 |
+
"learning_rate": 1.245599835092504e-05,
|
664 |
+
"loss": 0.0043,
|
665 |
+
"step": 104
|
666 |
+
},
|
667 |
+
{
|
668 |
+
"epoch": 0.78,
|
669 |
+
"learning_rate": 1.1697777844051105e-05,
|
670 |
+
"loss": 0.0024,
|
671 |
+
"step": 105
|
672 |
+
},
|
673 |
+
{
|
674 |
+
"epoch": 0.78,
|
675 |
+
"eval_loss": 0.0036511807702481747,
|
676 |
+
"eval_runtime": 21.148,
|
677 |
+
"eval_samples_per_second": 1.419,
|
678 |
+
"eval_steps_per_second": 0.709,
|
679 |
+
"step": 105
|
680 |
+
},
|
681 |
+
{
|
682 |
+
"epoch": 0.79,
|
683 |
+
"learning_rate": 1.096029866616704e-05,
|
684 |
+
"loss": 0.0027,
|
685 |
+
"step": 106
|
686 |
+
},
|
687 |
+
{
|
688 |
+
"epoch": 0.79,
|
689 |
+
"learning_rate": 1.0243960175257606e-05,
|
690 |
+
"loss": 0.006,
|
691 |
+
"step": 107
|
692 |
+
},
|
693 |
+
{
|
694 |
+
"epoch": 0.8,
|
695 |
+
"learning_rate": 9.549150281252633e-06,
|
696 |
+
"loss": 0.0029,
|
697 |
+
"step": 108
|
698 |
+
},
|
699 |
+
{
|
700 |
+
"epoch": 0.81,
|
701 |
+
"learning_rate": 8.876245235966885e-06,
|
702 |
+
"loss": 0.0016,
|
703 |
+
"step": 109
|
704 |
+
},
|
705 |
+
{
|
706 |
+
"epoch": 0.81,
|
707 |
+
"learning_rate": 8.225609429353187e-06,
|
708 |
+
"loss": 0.0044,
|
709 |
+
"step": 110
|
710 |
+
},
|
711 |
+
{
|
712 |
+
"epoch": 0.82,
|
713 |
+
"learning_rate": 7.597595192178702e-06,
|
714 |
+
"loss": 0.002,
|
715 |
+
"step": 111
|
716 |
+
},
|
717 |
+
{
|
718 |
+
"epoch": 0.83,
|
719 |
+
"learning_rate": 6.992542605231739e-06,
|
720 |
+
"loss": 0.0054,
|
721 |
+
"step": 112
|
722 |
+
},
|
723 |
+
{
|
724 |
+
"epoch": 0.84,
|
725 |
+
"learning_rate": 6.410779315161886e-06,
|
726 |
+
"loss": 0.0081,
|
727 |
+
"step": 113
|
728 |
+
},
|
729 |
+
{
|
730 |
+
"epoch": 0.84,
|
731 |
+
"learning_rate": 5.852620357053651e-06,
|
732 |
+
"loss": 0.0078,
|
733 |
+
"step": 114
|
734 |
+
},
|
735 |
+
{
|
736 |
+
"epoch": 0.85,
|
737 |
+
"learning_rate": 5.318367983829392e-06,
|
738 |
+
"loss": 0.0013,
|
739 |
+
"step": 115
|
740 |
+
},
|
741 |
+
{
|
742 |
+
"epoch": 0.86,
|
743 |
+
"learning_rate": 4.8083115025739756e-06,
|
744 |
+
"loss": 0.0027,
|
745 |
+
"step": 116
|
746 |
+
},
|
747 |
+
{
|
748 |
+
"epoch": 0.87,
|
749 |
+
"learning_rate": 4.322727117869951e-06,
|
750 |
+
"loss": 0.005,
|
751 |
+
"step": 117
|
752 |
+
},
|
753 |
+
{
|
754 |
+
"epoch": 0.87,
|
755 |
+
"learning_rate": 3.861877782227885e-06,
|
756 |
+
"loss": 0.0018,
|
757 |
+
"step": 118
|
758 |
+
},
|
759 |
+
{
|
760 |
+
"epoch": 0.88,
|
761 |
+
"learning_rate": 3.426013053692878e-06,
|
762 |
+
"loss": 0.0019,
|
763 |
+
"step": 119
|
764 |
+
},
|
765 |
+
{
|
766 |
+
"epoch": 0.89,
|
767 |
+
"learning_rate": 3.0153689607045845e-06,
|
768 |
+
"loss": 0.0038,
|
769 |
+
"step": 120
|
770 |
+
},
|
771 |
+
{
|
772 |
+
"epoch": 0.9,
|
773 |
+
"learning_rate": 2.63016787428354e-06,
|
774 |
+
"loss": 0.0005,
|
775 |
+
"step": 121
|
776 |
+
},
|
777 |
+
{
|
778 |
+
"epoch": 0.9,
|
779 |
+
"learning_rate": 2.2706183876134045e-06,
|
780 |
+
"loss": 0.0067,
|
781 |
+
"step": 122
|
782 |
+
},
|
783 |
+
{
|
784 |
+
"epoch": 0.91,
|
785 |
+
"learning_rate": 1.9369152030840556e-06,
|
786 |
+
"loss": 0.0069,
|
787 |
+
"step": 123
|
788 |
+
},
|
789 |
+
{
|
790 |
+
"epoch": 0.92,
|
791 |
+
"learning_rate": 1.6292390268568104e-06,
|
792 |
+
"loss": 0.0041,
|
793 |
+
"step": 124
|
794 |
+
},
|
795 |
+
{
|
796 |
+
"epoch": 0.93,
|
797 |
+
"learning_rate": 1.3477564710088098e-06,
|
798 |
+
"loss": 0.0055,
|
799 |
+
"step": 125
|
800 |
+
},
|
801 |
+
{
|
802 |
+
"epoch": 0.93,
|
803 |
+
"learning_rate": 1.0926199633097157e-06,
|
804 |
+
"loss": 0.0015,
|
805 |
+
"step": 126
|
806 |
+
},
|
807 |
+
{
|
808 |
+
"epoch": 0.93,
|
809 |
+
"eval_loss": 0.0034059311728924513,
|
810 |
+
"eval_runtime": 21.1425,
|
811 |
+
"eval_samples_per_second": 1.419,
|
812 |
+
"eval_steps_per_second": 0.709,
|
813 |
+
"step": 126
|
814 |
+
},
|
815 |
+
{
|
816 |
+
"epoch": 0.94,
|
817 |
+
"learning_rate": 8.639676646793382e-07,
|
818 |
+
"loss": 0.0045,
|
819 |
+
"step": 127
|
820 |
+
},
|
821 |
+
{
|
822 |
+
"epoch": 0.95,
|
823 |
+
"learning_rate": 6.61923394371039e-07,
|
824 |
+
"loss": 0.0035,
|
825 |
+
"step": 128
|
826 |
+
},
|
827 |
+
{
|
828 |
+
"epoch": 0.96,
|
829 |
+
"learning_rate": 4.865965629214819e-07,
|
830 |
+
"loss": 0.0009,
|
831 |
+
"step": 129
|
832 |
+
},
|
833 |
+
{
|
834 |
+
"epoch": 0.96,
|
835 |
+
"learning_rate": 3.380821129028489e-07,
|
836 |
+
"loss": 0.0048,
|
837 |
+
"step": 130
|
838 |
+
},
|
839 |
+
{
|
840 |
+
"epoch": 0.97,
|
841 |
+
"learning_rate": 2.1646046750978254e-07,
|
842 |
+
"loss": 0.001,
|
843 |
+
"step": 131
|
844 |
+
},
|
845 |
+
{
|
846 |
+
"epoch": 0.98,
|
847 |
+
"learning_rate": 1.2179748700879012e-07,
|
848 |
+
"loss": 0.0015,
|
849 |
+
"step": 132
|
850 |
+
},
|
851 |
+
{
|
852 |
+
"epoch": 0.99,
|
853 |
+
"learning_rate": 5.4144433073771707e-08,
|
854 |
+
"loss": 0.006,
|
855 |
+
"step": 133
|
856 |
+
},
|
857 |
+
{
|
858 |
+
"epoch": 0.99,
|
859 |
+
"learning_rate": 1.3537941026914303e-08,
|
860 |
+
"loss": 0.0023,
|
861 |
+
"step": 134
|
862 |
+
},
|
863 |
+
{
|
864 |
+
"epoch": 1.0,
|
865 |
+
"learning_rate": 0.0,
|
866 |
+
"loss": 0.0054,
|
867 |
+
"step": 135
|
868 |
+
},
|
869 |
+
{
|
870 |
+
"epoch": 1.0,
|
871 |
+
"step": 135,
|
872 |
+
"total_flos": 9.492248232198144e+16,
|
873 |
+
"train_loss": 0.03722052312180124,
|
874 |
+
"train_runtime": 798.3612,
|
875 |
+
"train_samples_per_second": 0.338,
|
876 |
+
"train_steps_per_second": 0.169
|
877 |
+
}
|
878 |
+
],
|
879 |
+
"logging_steps": 1.0,
|
880 |
+
"max_steps": 135,
|
881 |
+
"num_input_tokens_seen": 0,
|
882 |
+
"num_train_epochs": 1,
|
883 |
+
"save_steps": 10000,
|
884 |
+
"total_flos": 9.492248232198144e+16,
|
885 |
+
"train_batch_size": 2,
|
886 |
+
"trial_name": null,
|
887 |
+
"trial_params": null
|
888 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0d2ce9473a28d9856d8069effa5ed5eccc00a3de948d9e6d6d914a1a3f6e4b15
|
3 |
+
size 6072
|