Upload folder using huggingface_hub
Browse files- README.md +202 -0
- adapter_config.json +31 -0
- adapter_model.safetensors +3 -0
- optimizer.pt +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 +43 -0
- trainer_state.json +1043 -0
- training_args.bin +3 -0
README.md
ADDED
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
### Framework versions
|
201 |
+
|
202 |
+
- PEFT 0.10.0
|
adapter_config.json
ADDED
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
"layer_replication": null,
|
10 |
+
"layers_pattern": null,
|
11 |
+
"layers_to_transform": null,
|
12 |
+
"loftq_config": {},
|
13 |
+
"lora_alpha": 32,
|
14 |
+
"lora_dropout": 0.05,
|
15 |
+
"megatron_config": null,
|
16 |
+
"megatron_core": "megatron.core",
|
17 |
+
"modules_to_save": null,
|
18 |
+
"peft_type": "LORA",
|
19 |
+
"r": 16,
|
20 |
+
"rank_pattern": {},
|
21 |
+
"revision": null,
|
22 |
+
"target_modules": [
|
23 |
+
"k_proj",
|
24 |
+
"o_proj",
|
25 |
+
"q_proj",
|
26 |
+
"v_proj"
|
27 |
+
],
|
28 |
+
"task_type": "CAUSAL_LM",
|
29 |
+
"use_dora": false,
|
30 |
+
"use_rslora": false
|
31 |
+
}
|
adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ed929dd92c617acd4d7992e55d29830f13b015cfad300b5c34ec43450c2f845f
|
3 |
+
size 54560368
|
optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:17bf479721d47d280bd41043527056b2c87382d387b877657f7f558192cc5efc
|
3 |
+
size 109203770
|
rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:da36ab7162edaa976753eef071be28bcc74efa3bc88b528f89dfdc1207754a2a
|
3 |
+
size 14244
|
scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:38086b6a270732e89612151792ce22f14e0bd34937f42dfe8a8017e39426ee29
|
3 |
+
size 1064
|
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 +1,43 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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": 1000000000000000019884624838656,
|
37 |
+
"pad_token": "</s>",
|
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 +1,1043 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 8.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 146,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.0547945205479452,
|
13 |
+
"grad_norm": 1.6586511135101318,
|
14 |
+
"learning_rate": 1e-06,
|
15 |
+
"loss": 2.2379,
|
16 |
+
"step": 1
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.1095890410958904,
|
20 |
+
"grad_norm": 1.6110830307006836,
|
21 |
+
"learning_rate": 1e-06,
|
22 |
+
"loss": 2.2933,
|
23 |
+
"step": 2
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.1643835616438356,
|
27 |
+
"grad_norm": 1.5261093378067017,
|
28 |
+
"learning_rate": 1e-06,
|
29 |
+
"loss": 2.2564,
|
30 |
+
"step": 3
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 0.2191780821917808,
|
34 |
+
"grad_norm": 1.6366506814956665,
|
35 |
+
"learning_rate": 1e-06,
|
36 |
+
"loss": 2.2794,
|
37 |
+
"step": 4
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 0.273972602739726,
|
41 |
+
"grad_norm": 1.5530800819396973,
|
42 |
+
"learning_rate": 1e-06,
|
43 |
+
"loss": 2.2344,
|
44 |
+
"step": 5
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.3287671232876712,
|
48 |
+
"grad_norm": 1.5802958011627197,
|
49 |
+
"learning_rate": 1e-06,
|
50 |
+
"loss": 2.2363,
|
51 |
+
"step": 6
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.3835616438356164,
|
55 |
+
"grad_norm": 1.5483659505844116,
|
56 |
+
"learning_rate": 1e-06,
|
57 |
+
"loss": 2.256,
|
58 |
+
"step": 7
|
59 |
+
},
|
60 |
+
{
|
61 |
+
"epoch": 0.4383561643835616,
|
62 |
+
"grad_norm": 1.5273737907409668,
|
63 |
+
"learning_rate": 1e-06,
|
64 |
+
"loss": 2.2733,
|
65 |
+
"step": 8
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 0.4931506849315068,
|
69 |
+
"grad_norm": 1.534605860710144,
|
70 |
+
"learning_rate": 1e-06,
|
71 |
+
"loss": 2.223,
|
72 |
+
"step": 9
|
73 |
+
},
|
74 |
+
{
|
75 |
+
"epoch": 0.547945205479452,
|
76 |
+
"grad_norm": 1.5523834228515625,
|
77 |
+
"learning_rate": 1e-06,
|
78 |
+
"loss": 2.2755,
|
79 |
+
"step": 10
|
80 |
+
},
|
81 |
+
{
|
82 |
+
"epoch": 0.6027397260273972,
|
83 |
+
"grad_norm": 1.5962920188903809,
|
84 |
+
"learning_rate": 1e-06,
|
85 |
+
"loss": 2.2875,
|
86 |
+
"step": 11
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 0.6575342465753424,
|
90 |
+
"grad_norm": 1.5564601421356201,
|
91 |
+
"learning_rate": 1e-06,
|
92 |
+
"loss": 2.2716,
|
93 |
+
"step": 12
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 0.7123287671232876,
|
97 |
+
"grad_norm": 1.5305095911026,
|
98 |
+
"learning_rate": 1e-06,
|
99 |
+
"loss": 2.2485,
|
100 |
+
"step": 13
|
101 |
+
},
|
102 |
+
{
|
103 |
+
"epoch": 0.7671232876712328,
|
104 |
+
"grad_norm": 1.4675662517547607,
|
105 |
+
"learning_rate": 1e-06,
|
106 |
+
"loss": 2.2574,
|
107 |
+
"step": 14
|
108 |
+
},
|
109 |
+
{
|
110 |
+
"epoch": 0.821917808219178,
|
111 |
+
"grad_norm": 1.4668537378311157,
|
112 |
+
"learning_rate": 1e-06,
|
113 |
+
"loss": 2.2226,
|
114 |
+
"step": 15
|
115 |
+
},
|
116 |
+
{
|
117 |
+
"epoch": 0.8767123287671232,
|
118 |
+
"grad_norm": 1.5306854248046875,
|
119 |
+
"learning_rate": 1e-06,
|
120 |
+
"loss": 2.2798,
|
121 |
+
"step": 16
|
122 |
+
},
|
123 |
+
{
|
124 |
+
"epoch": 0.9315068493150684,
|
125 |
+
"grad_norm": 1.5047531127929688,
|
126 |
+
"learning_rate": 1e-06,
|
127 |
+
"loss": 2.2486,
|
128 |
+
"step": 17
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 0.9863013698630136,
|
132 |
+
"grad_norm": 1.4622173309326172,
|
133 |
+
"learning_rate": 1e-06,
|
134 |
+
"loss": 2.217,
|
135 |
+
"step": 18
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 1.0410958904109588,
|
139 |
+
"grad_norm": 1.5452288389205933,
|
140 |
+
"learning_rate": 1e-06,
|
141 |
+
"loss": 2.2271,
|
142 |
+
"step": 19
|
143 |
+
},
|
144 |
+
{
|
145 |
+
"epoch": 1.095890410958904,
|
146 |
+
"grad_norm": 1.4995627403259277,
|
147 |
+
"learning_rate": 1e-06,
|
148 |
+
"loss": 2.2222,
|
149 |
+
"step": 20
|
150 |
+
},
|
151 |
+
{
|
152 |
+
"epoch": 1.1506849315068493,
|
153 |
+
"grad_norm": 1.4030557870864868,
|
154 |
+
"learning_rate": 1e-06,
|
155 |
+
"loss": 2.2547,
|
156 |
+
"step": 21
|
157 |
+
},
|
158 |
+
{
|
159 |
+
"epoch": 1.2054794520547945,
|
160 |
+
"grad_norm": 1.4066240787506104,
|
161 |
+
"learning_rate": 1e-06,
|
162 |
+
"loss": 2.2279,
|
163 |
+
"step": 22
|
164 |
+
},
|
165 |
+
{
|
166 |
+
"epoch": 1.2602739726027397,
|
167 |
+
"grad_norm": 1.4491875171661377,
|
168 |
+
"learning_rate": 1e-06,
|
169 |
+
"loss": 2.2497,
|
170 |
+
"step": 23
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 1.3150684931506849,
|
174 |
+
"grad_norm": 1.3880819082260132,
|
175 |
+
"learning_rate": 1e-06,
|
176 |
+
"loss": 2.2593,
|
177 |
+
"step": 24
|
178 |
+
},
|
179 |
+
{
|
180 |
+
"epoch": 1.36986301369863,
|
181 |
+
"grad_norm": 1.471488118171692,
|
182 |
+
"learning_rate": 1e-06,
|
183 |
+
"loss": 2.2496,
|
184 |
+
"step": 25
|
185 |
+
},
|
186 |
+
{
|
187 |
+
"epoch": 1.4246575342465753,
|
188 |
+
"grad_norm": 1.388680338859558,
|
189 |
+
"learning_rate": 1e-06,
|
190 |
+
"loss": 2.2262,
|
191 |
+
"step": 26
|
192 |
+
},
|
193 |
+
{
|
194 |
+
"epoch": 1.4794520547945205,
|
195 |
+
"grad_norm": 1.4523004293441772,
|
196 |
+
"learning_rate": 1e-06,
|
197 |
+
"loss": 2.2535,
|
198 |
+
"step": 27
|
199 |
+
},
|
200 |
+
{
|
201 |
+
"epoch": 1.5342465753424657,
|
202 |
+
"grad_norm": 1.4338841438293457,
|
203 |
+
"learning_rate": 1e-06,
|
204 |
+
"loss": 2.2315,
|
205 |
+
"step": 28
|
206 |
+
},
|
207 |
+
{
|
208 |
+
"epoch": 1.589041095890411,
|
209 |
+
"grad_norm": 1.3985637426376343,
|
210 |
+
"learning_rate": 1e-06,
|
211 |
+
"loss": 2.262,
|
212 |
+
"step": 29
|
213 |
+
},
|
214 |
+
{
|
215 |
+
"epoch": 1.643835616438356,
|
216 |
+
"grad_norm": 1.3776822090148926,
|
217 |
+
"learning_rate": 1e-06,
|
218 |
+
"loss": 2.224,
|
219 |
+
"step": 30
|
220 |
+
},
|
221 |
+
{
|
222 |
+
"epoch": 1.6986301369863015,
|
223 |
+
"grad_norm": 1.3197417259216309,
|
224 |
+
"learning_rate": 1e-06,
|
225 |
+
"loss": 2.2009,
|
226 |
+
"step": 31
|
227 |
+
},
|
228 |
+
{
|
229 |
+
"epoch": 1.7534246575342465,
|
230 |
+
"grad_norm": 1.4159483909606934,
|
231 |
+
"learning_rate": 1e-06,
|
232 |
+
"loss": 2.2131,
|
233 |
+
"step": 32
|
234 |
+
},
|
235 |
+
{
|
236 |
+
"epoch": 1.808219178082192,
|
237 |
+
"grad_norm": 1.3864014148712158,
|
238 |
+
"learning_rate": 1e-06,
|
239 |
+
"loss": 2.2498,
|
240 |
+
"step": 33
|
241 |
+
},
|
242 |
+
{
|
243 |
+
"epoch": 1.8630136986301369,
|
244 |
+
"grad_norm": 1.3488203287124634,
|
245 |
+
"learning_rate": 1e-06,
|
246 |
+
"loss": 2.2147,
|
247 |
+
"step": 34
|
248 |
+
},
|
249 |
+
{
|
250 |
+
"epoch": 1.9178082191780823,
|
251 |
+
"grad_norm": 1.345689296722412,
|
252 |
+
"learning_rate": 1e-06,
|
253 |
+
"loss": 2.2383,
|
254 |
+
"step": 35
|
255 |
+
},
|
256 |
+
{
|
257 |
+
"epoch": 1.9726027397260273,
|
258 |
+
"grad_norm": 1.344303011894226,
|
259 |
+
"learning_rate": 1e-06,
|
260 |
+
"loss": 2.2159,
|
261 |
+
"step": 36
|
262 |
+
},
|
263 |
+
{
|
264 |
+
"epoch": 2.0273972602739727,
|
265 |
+
"grad_norm": 1.3895442485809326,
|
266 |
+
"learning_rate": 1e-06,
|
267 |
+
"loss": 2.2265,
|
268 |
+
"step": 37
|
269 |
+
},
|
270 |
+
{
|
271 |
+
"epoch": 2.0821917808219177,
|
272 |
+
"grad_norm": 1.3593428134918213,
|
273 |
+
"learning_rate": 1e-06,
|
274 |
+
"loss": 2.2063,
|
275 |
+
"step": 38
|
276 |
+
},
|
277 |
+
{
|
278 |
+
"epoch": 2.136986301369863,
|
279 |
+
"grad_norm": 1.3060978651046753,
|
280 |
+
"learning_rate": 1e-06,
|
281 |
+
"loss": 2.2572,
|
282 |
+
"step": 39
|
283 |
+
},
|
284 |
+
{
|
285 |
+
"epoch": 2.191780821917808,
|
286 |
+
"grad_norm": 1.3199517726898193,
|
287 |
+
"learning_rate": 1e-06,
|
288 |
+
"loss": 2.2099,
|
289 |
+
"step": 40
|
290 |
+
},
|
291 |
+
{
|
292 |
+
"epoch": 2.2465753424657535,
|
293 |
+
"grad_norm": 1.3381460905075073,
|
294 |
+
"learning_rate": 1e-06,
|
295 |
+
"loss": 2.2693,
|
296 |
+
"step": 41
|
297 |
+
},
|
298 |
+
{
|
299 |
+
"epoch": 2.3013698630136985,
|
300 |
+
"grad_norm": 1.334553599357605,
|
301 |
+
"learning_rate": 1e-06,
|
302 |
+
"loss": 2.2206,
|
303 |
+
"step": 42
|
304 |
+
},
|
305 |
+
{
|
306 |
+
"epoch": 2.356164383561644,
|
307 |
+
"grad_norm": 1.3222883939743042,
|
308 |
+
"learning_rate": 1e-06,
|
309 |
+
"loss": 2.1851,
|
310 |
+
"step": 43
|
311 |
+
},
|
312 |
+
{
|
313 |
+
"epoch": 2.410958904109589,
|
314 |
+
"grad_norm": 1.3213746547698975,
|
315 |
+
"learning_rate": 1e-06,
|
316 |
+
"loss": 2.2542,
|
317 |
+
"step": 44
|
318 |
+
},
|
319 |
+
{
|
320 |
+
"epoch": 2.4657534246575343,
|
321 |
+
"grad_norm": 1.3214170932769775,
|
322 |
+
"learning_rate": 1e-06,
|
323 |
+
"loss": 2.2319,
|
324 |
+
"step": 45
|
325 |
+
},
|
326 |
+
{
|
327 |
+
"epoch": 2.5205479452054793,
|
328 |
+
"grad_norm": 1.345453143119812,
|
329 |
+
"learning_rate": 1e-06,
|
330 |
+
"loss": 2.222,
|
331 |
+
"step": 46
|
332 |
+
},
|
333 |
+
{
|
334 |
+
"epoch": 2.5753424657534247,
|
335 |
+
"grad_norm": 1.2182488441467285,
|
336 |
+
"learning_rate": 1e-06,
|
337 |
+
"loss": 2.2069,
|
338 |
+
"step": 47
|
339 |
+
},
|
340 |
+
{
|
341 |
+
"epoch": 2.6301369863013697,
|
342 |
+
"grad_norm": 1.2841640710830688,
|
343 |
+
"learning_rate": 1e-06,
|
344 |
+
"loss": 2.2181,
|
345 |
+
"step": 48
|
346 |
+
},
|
347 |
+
{
|
348 |
+
"epoch": 2.684931506849315,
|
349 |
+
"grad_norm": 1.270230770111084,
|
350 |
+
"learning_rate": 1e-06,
|
351 |
+
"loss": 2.2097,
|
352 |
+
"step": 49
|
353 |
+
},
|
354 |
+
{
|
355 |
+
"epoch": 2.73972602739726,
|
356 |
+
"grad_norm": 1.213972806930542,
|
357 |
+
"learning_rate": 1e-06,
|
358 |
+
"loss": 2.218,
|
359 |
+
"step": 50
|
360 |
+
},
|
361 |
+
{
|
362 |
+
"epoch": 2.7945205479452055,
|
363 |
+
"grad_norm": 1.2877941131591797,
|
364 |
+
"learning_rate": 1e-06,
|
365 |
+
"loss": 2.2055,
|
366 |
+
"step": 51
|
367 |
+
},
|
368 |
+
{
|
369 |
+
"epoch": 2.8493150684931505,
|
370 |
+
"grad_norm": 1.273301601409912,
|
371 |
+
"learning_rate": 1e-06,
|
372 |
+
"loss": 2.1895,
|
373 |
+
"step": 52
|
374 |
+
},
|
375 |
+
{
|
376 |
+
"epoch": 2.904109589041096,
|
377 |
+
"grad_norm": 1.2318782806396484,
|
378 |
+
"learning_rate": 1e-06,
|
379 |
+
"loss": 2.2255,
|
380 |
+
"step": 53
|
381 |
+
},
|
382 |
+
{
|
383 |
+
"epoch": 2.958904109589041,
|
384 |
+
"grad_norm": 1.1937693357467651,
|
385 |
+
"learning_rate": 1e-06,
|
386 |
+
"loss": 2.1865,
|
387 |
+
"step": 54
|
388 |
+
},
|
389 |
+
{
|
390 |
+
"epoch": 3.0136986301369864,
|
391 |
+
"grad_norm": 1.1707606315612793,
|
392 |
+
"learning_rate": 1e-06,
|
393 |
+
"loss": 2.2179,
|
394 |
+
"step": 55
|
395 |
+
},
|
396 |
+
{
|
397 |
+
"epoch": 3.0684931506849313,
|
398 |
+
"grad_norm": 1.2074235677719116,
|
399 |
+
"learning_rate": 1e-06,
|
400 |
+
"loss": 2.155,
|
401 |
+
"step": 56
|
402 |
+
},
|
403 |
+
{
|
404 |
+
"epoch": 3.1232876712328768,
|
405 |
+
"grad_norm": 1.1725316047668457,
|
406 |
+
"learning_rate": 1e-06,
|
407 |
+
"loss": 2.2011,
|
408 |
+
"step": 57
|
409 |
+
},
|
410 |
+
{
|
411 |
+
"epoch": 3.1780821917808217,
|
412 |
+
"grad_norm": 1.1967130899429321,
|
413 |
+
"learning_rate": 1e-06,
|
414 |
+
"loss": 2.2155,
|
415 |
+
"step": 58
|
416 |
+
},
|
417 |
+
{
|
418 |
+
"epoch": 3.232876712328767,
|
419 |
+
"grad_norm": 1.1932190656661987,
|
420 |
+
"learning_rate": 1e-06,
|
421 |
+
"loss": 2.1858,
|
422 |
+
"step": 59
|
423 |
+
},
|
424 |
+
{
|
425 |
+
"epoch": 3.287671232876712,
|
426 |
+
"grad_norm": 1.19328773021698,
|
427 |
+
"learning_rate": 1e-06,
|
428 |
+
"loss": 2.2351,
|
429 |
+
"step": 60
|
430 |
+
},
|
431 |
+
{
|
432 |
+
"epoch": 3.3424657534246576,
|
433 |
+
"grad_norm": 1.1168928146362305,
|
434 |
+
"learning_rate": 1e-06,
|
435 |
+
"loss": 2.2022,
|
436 |
+
"step": 61
|
437 |
+
},
|
438 |
+
{
|
439 |
+
"epoch": 3.3972602739726026,
|
440 |
+
"grad_norm": 1.2043449878692627,
|
441 |
+
"learning_rate": 1e-06,
|
442 |
+
"loss": 2.1964,
|
443 |
+
"step": 62
|
444 |
+
},
|
445 |
+
{
|
446 |
+
"epoch": 3.452054794520548,
|
447 |
+
"grad_norm": 1.2224105596542358,
|
448 |
+
"learning_rate": 1e-06,
|
449 |
+
"loss": 2.1919,
|
450 |
+
"step": 63
|
451 |
+
},
|
452 |
+
{
|
453 |
+
"epoch": 3.506849315068493,
|
454 |
+
"grad_norm": 1.2362271547317505,
|
455 |
+
"learning_rate": 1e-06,
|
456 |
+
"loss": 2.199,
|
457 |
+
"step": 64
|
458 |
+
},
|
459 |
+
{
|
460 |
+
"epoch": 3.5616438356164384,
|
461 |
+
"grad_norm": 1.2123560905456543,
|
462 |
+
"learning_rate": 1e-06,
|
463 |
+
"loss": 2.2357,
|
464 |
+
"step": 65
|
465 |
+
},
|
466 |
+
{
|
467 |
+
"epoch": 3.616438356164384,
|
468 |
+
"grad_norm": 1.1854863166809082,
|
469 |
+
"learning_rate": 1e-06,
|
470 |
+
"loss": 2.1878,
|
471 |
+
"step": 66
|
472 |
+
},
|
473 |
+
{
|
474 |
+
"epoch": 3.671232876712329,
|
475 |
+
"grad_norm": 1.1320362091064453,
|
476 |
+
"learning_rate": 1e-06,
|
477 |
+
"loss": 2.1872,
|
478 |
+
"step": 67
|
479 |
+
},
|
480 |
+
{
|
481 |
+
"epoch": 3.7260273972602738,
|
482 |
+
"grad_norm": 1.1633937358856201,
|
483 |
+
"learning_rate": 1e-06,
|
484 |
+
"loss": 2.205,
|
485 |
+
"step": 68
|
486 |
+
},
|
487 |
+
{
|
488 |
+
"epoch": 3.780821917808219,
|
489 |
+
"grad_norm": 1.1435497999191284,
|
490 |
+
"learning_rate": 1e-06,
|
491 |
+
"loss": 2.1972,
|
492 |
+
"step": 69
|
493 |
+
},
|
494 |
+
{
|
495 |
+
"epoch": 3.8356164383561646,
|
496 |
+
"grad_norm": 1.1820743083953857,
|
497 |
+
"learning_rate": 1e-06,
|
498 |
+
"loss": 2.1961,
|
499 |
+
"step": 70
|
500 |
+
},
|
501 |
+
{
|
502 |
+
"epoch": 3.8904109589041096,
|
503 |
+
"grad_norm": 1.203647255897522,
|
504 |
+
"learning_rate": 1e-06,
|
505 |
+
"loss": 2.2149,
|
506 |
+
"step": 71
|
507 |
+
},
|
508 |
+
{
|
509 |
+
"epoch": 3.9452054794520546,
|
510 |
+
"grad_norm": 1.1167892217636108,
|
511 |
+
"learning_rate": 1e-06,
|
512 |
+
"loss": 2.197,
|
513 |
+
"step": 72
|
514 |
+
},
|
515 |
+
{
|
516 |
+
"epoch": 4.0,
|
517 |
+
"grad_norm": 1.0951488018035889,
|
518 |
+
"learning_rate": 1e-06,
|
519 |
+
"loss": 2.1898,
|
520 |
+
"step": 73
|
521 |
+
},
|
522 |
+
{
|
523 |
+
"epoch": 4.054794520547945,
|
524 |
+
"grad_norm": 1.1908702850341797,
|
525 |
+
"learning_rate": 1e-06,
|
526 |
+
"loss": 2.1973,
|
527 |
+
"step": 74
|
528 |
+
},
|
529 |
+
{
|
530 |
+
"epoch": 4.109589041095891,
|
531 |
+
"grad_norm": 1.0710009336471558,
|
532 |
+
"learning_rate": 1e-06,
|
533 |
+
"loss": 2.2014,
|
534 |
+
"step": 75
|
535 |
+
},
|
536 |
+
{
|
537 |
+
"epoch": 4.164383561643835,
|
538 |
+
"grad_norm": 1.1268314123153687,
|
539 |
+
"learning_rate": 1e-06,
|
540 |
+
"loss": 2.2125,
|
541 |
+
"step": 76
|
542 |
+
},
|
543 |
+
{
|
544 |
+
"epoch": 4.219178082191781,
|
545 |
+
"grad_norm": 1.0808967351913452,
|
546 |
+
"learning_rate": 1e-06,
|
547 |
+
"loss": 2.2184,
|
548 |
+
"step": 77
|
549 |
+
},
|
550 |
+
{
|
551 |
+
"epoch": 4.273972602739726,
|
552 |
+
"grad_norm": 1.0744292736053467,
|
553 |
+
"learning_rate": 1e-06,
|
554 |
+
"loss": 2.162,
|
555 |
+
"step": 78
|
556 |
+
},
|
557 |
+
{
|
558 |
+
"epoch": 4.328767123287671,
|
559 |
+
"grad_norm": 1.0902713537216187,
|
560 |
+
"learning_rate": 1e-06,
|
561 |
+
"loss": 2.2045,
|
562 |
+
"step": 79
|
563 |
+
},
|
564 |
+
{
|
565 |
+
"epoch": 4.383561643835616,
|
566 |
+
"grad_norm": 1.1404340267181396,
|
567 |
+
"learning_rate": 1e-06,
|
568 |
+
"loss": 2.1919,
|
569 |
+
"step": 80
|
570 |
+
},
|
571 |
+
{
|
572 |
+
"epoch": 4.438356164383562,
|
573 |
+
"grad_norm": 1.0819721221923828,
|
574 |
+
"learning_rate": 1e-06,
|
575 |
+
"loss": 2.1848,
|
576 |
+
"step": 81
|
577 |
+
},
|
578 |
+
{
|
579 |
+
"epoch": 4.493150684931507,
|
580 |
+
"grad_norm": 1.0939464569091797,
|
581 |
+
"learning_rate": 1e-06,
|
582 |
+
"loss": 2.197,
|
583 |
+
"step": 82
|
584 |
+
},
|
585 |
+
{
|
586 |
+
"epoch": 4.5479452054794525,
|
587 |
+
"grad_norm": 1.1371257305145264,
|
588 |
+
"learning_rate": 1e-06,
|
589 |
+
"loss": 2.1802,
|
590 |
+
"step": 83
|
591 |
+
},
|
592 |
+
{
|
593 |
+
"epoch": 4.602739726027397,
|
594 |
+
"grad_norm": 1.0913671255111694,
|
595 |
+
"learning_rate": 1e-06,
|
596 |
+
"loss": 2.182,
|
597 |
+
"step": 84
|
598 |
+
},
|
599 |
+
{
|
600 |
+
"epoch": 4.657534246575342,
|
601 |
+
"grad_norm": 1.0597493648529053,
|
602 |
+
"learning_rate": 1e-06,
|
603 |
+
"loss": 2.1663,
|
604 |
+
"step": 85
|
605 |
+
},
|
606 |
+
{
|
607 |
+
"epoch": 4.712328767123288,
|
608 |
+
"grad_norm": 1.040493130683899,
|
609 |
+
"learning_rate": 1e-06,
|
610 |
+
"loss": 2.1774,
|
611 |
+
"step": 86
|
612 |
+
},
|
613 |
+
{
|
614 |
+
"epoch": 4.767123287671232,
|
615 |
+
"grad_norm": 1.0556532144546509,
|
616 |
+
"learning_rate": 1e-06,
|
617 |
+
"loss": 2.2029,
|
618 |
+
"step": 87
|
619 |
+
},
|
620 |
+
{
|
621 |
+
"epoch": 4.821917808219178,
|
622 |
+
"grad_norm": 1.0801831483840942,
|
623 |
+
"learning_rate": 1e-06,
|
624 |
+
"loss": 2.1648,
|
625 |
+
"step": 88
|
626 |
+
},
|
627 |
+
{
|
628 |
+
"epoch": 4.876712328767123,
|
629 |
+
"grad_norm": 1.073749303817749,
|
630 |
+
"learning_rate": 1e-06,
|
631 |
+
"loss": 2.174,
|
632 |
+
"step": 89
|
633 |
+
},
|
634 |
+
{
|
635 |
+
"epoch": 4.931506849315069,
|
636 |
+
"grad_norm": 1.0210574865341187,
|
637 |
+
"learning_rate": 1e-06,
|
638 |
+
"loss": 2.1474,
|
639 |
+
"step": 90
|
640 |
+
},
|
641 |
+
{
|
642 |
+
"epoch": 4.986301369863014,
|
643 |
+
"grad_norm": 1.0152342319488525,
|
644 |
+
"learning_rate": 1e-06,
|
645 |
+
"loss": 2.1629,
|
646 |
+
"step": 91
|
647 |
+
},
|
648 |
+
{
|
649 |
+
"epoch": 5.041095890410959,
|
650 |
+
"grad_norm": 1.0388507843017578,
|
651 |
+
"learning_rate": 1e-06,
|
652 |
+
"loss": 2.1931,
|
653 |
+
"step": 92
|
654 |
+
},
|
655 |
+
{
|
656 |
+
"epoch": 5.095890410958904,
|
657 |
+
"grad_norm": 1.011426329612732,
|
658 |
+
"learning_rate": 1e-06,
|
659 |
+
"loss": 2.204,
|
660 |
+
"step": 93
|
661 |
+
},
|
662 |
+
{
|
663 |
+
"epoch": 5.1506849315068495,
|
664 |
+
"grad_norm": 1.0486528873443604,
|
665 |
+
"learning_rate": 1e-06,
|
666 |
+
"loss": 2.1908,
|
667 |
+
"step": 94
|
668 |
+
},
|
669 |
+
{
|
670 |
+
"epoch": 5.205479452054795,
|
671 |
+
"grad_norm": 0.9501799941062927,
|
672 |
+
"learning_rate": 1e-06,
|
673 |
+
"loss": 2.1823,
|
674 |
+
"step": 95
|
675 |
+
},
|
676 |
+
{
|
677 |
+
"epoch": 5.260273972602739,
|
678 |
+
"grad_norm": 1.0336531400680542,
|
679 |
+
"learning_rate": 1e-06,
|
680 |
+
"loss": 2.1965,
|
681 |
+
"step": 96
|
682 |
+
},
|
683 |
+
{
|
684 |
+
"epoch": 5.315068493150685,
|
685 |
+
"grad_norm": 1.0227267742156982,
|
686 |
+
"learning_rate": 1e-06,
|
687 |
+
"loss": 2.1896,
|
688 |
+
"step": 97
|
689 |
+
},
|
690 |
+
{
|
691 |
+
"epoch": 5.36986301369863,
|
692 |
+
"grad_norm": 1.0686023235321045,
|
693 |
+
"learning_rate": 1e-06,
|
694 |
+
"loss": 2.1496,
|
695 |
+
"step": 98
|
696 |
+
},
|
697 |
+
{
|
698 |
+
"epoch": 5.424657534246576,
|
699 |
+
"grad_norm": 0.9931809902191162,
|
700 |
+
"learning_rate": 1e-06,
|
701 |
+
"loss": 2.1474,
|
702 |
+
"step": 99
|
703 |
+
},
|
704 |
+
{
|
705 |
+
"epoch": 5.47945205479452,
|
706 |
+
"grad_norm": 0.9578049778938293,
|
707 |
+
"learning_rate": 1e-06,
|
708 |
+
"loss": 2.1488,
|
709 |
+
"step": 100
|
710 |
+
},
|
711 |
+
{
|
712 |
+
"epoch": 5.534246575342466,
|
713 |
+
"grad_norm": 0.9815987944602966,
|
714 |
+
"learning_rate": 1e-06,
|
715 |
+
"loss": 2.1755,
|
716 |
+
"step": 101
|
717 |
+
},
|
718 |
+
{
|
719 |
+
"epoch": 5.589041095890411,
|
720 |
+
"grad_norm": 0.9837309718132019,
|
721 |
+
"learning_rate": 1e-06,
|
722 |
+
"loss": 2.1559,
|
723 |
+
"step": 102
|
724 |
+
},
|
725 |
+
{
|
726 |
+
"epoch": 5.6438356164383565,
|
727 |
+
"grad_norm": 0.9334861040115356,
|
728 |
+
"learning_rate": 1e-06,
|
729 |
+
"loss": 2.1773,
|
730 |
+
"step": 103
|
731 |
+
},
|
732 |
+
{
|
733 |
+
"epoch": 5.698630136986301,
|
734 |
+
"grad_norm": 1.0627118349075317,
|
735 |
+
"learning_rate": 1e-06,
|
736 |
+
"loss": 2.2116,
|
737 |
+
"step": 104
|
738 |
+
},
|
739 |
+
{
|
740 |
+
"epoch": 5.7534246575342465,
|
741 |
+
"grad_norm": 0.9978325963020325,
|
742 |
+
"learning_rate": 1e-06,
|
743 |
+
"loss": 2.1413,
|
744 |
+
"step": 105
|
745 |
+
},
|
746 |
+
{
|
747 |
+
"epoch": 5.808219178082192,
|
748 |
+
"grad_norm": 0.9550198912620544,
|
749 |
+
"learning_rate": 1e-06,
|
750 |
+
"loss": 2.1535,
|
751 |
+
"step": 106
|
752 |
+
},
|
753 |
+
{
|
754 |
+
"epoch": 5.863013698630137,
|
755 |
+
"grad_norm": 0.9339421987533569,
|
756 |
+
"learning_rate": 1e-06,
|
757 |
+
"loss": 2.1504,
|
758 |
+
"step": 107
|
759 |
+
},
|
760 |
+
{
|
761 |
+
"epoch": 5.917808219178082,
|
762 |
+
"grad_norm": 0.9043423533439636,
|
763 |
+
"learning_rate": 1e-06,
|
764 |
+
"loss": 2.1469,
|
765 |
+
"step": 108
|
766 |
+
},
|
767 |
+
{
|
768 |
+
"epoch": 5.972602739726027,
|
769 |
+
"grad_norm": 0.921292781829834,
|
770 |
+
"learning_rate": 1e-06,
|
771 |
+
"loss": 2.1337,
|
772 |
+
"step": 109
|
773 |
+
},
|
774 |
+
{
|
775 |
+
"epoch": 6.027397260273973,
|
776 |
+
"grad_norm": 0.9245712757110596,
|
777 |
+
"learning_rate": 1e-06,
|
778 |
+
"loss": 2.1762,
|
779 |
+
"step": 110
|
780 |
+
},
|
781 |
+
{
|
782 |
+
"epoch": 6.082191780821918,
|
783 |
+
"grad_norm": 0.9610967636108398,
|
784 |
+
"learning_rate": 1e-06,
|
785 |
+
"loss": 2.1618,
|
786 |
+
"step": 111
|
787 |
+
},
|
788 |
+
{
|
789 |
+
"epoch": 6.136986301369863,
|
790 |
+
"grad_norm": 0.9136860370635986,
|
791 |
+
"learning_rate": 1e-06,
|
792 |
+
"loss": 2.1505,
|
793 |
+
"step": 112
|
794 |
+
},
|
795 |
+
{
|
796 |
+
"epoch": 6.191780821917808,
|
797 |
+
"grad_norm": 0.9340102672576904,
|
798 |
+
"learning_rate": 1e-06,
|
799 |
+
"loss": 2.1692,
|
800 |
+
"step": 113
|
801 |
+
},
|
802 |
+
{
|
803 |
+
"epoch": 6.2465753424657535,
|
804 |
+
"grad_norm": 0.8885300159454346,
|
805 |
+
"learning_rate": 1e-06,
|
806 |
+
"loss": 2.1494,
|
807 |
+
"step": 114
|
808 |
+
},
|
809 |
+
{
|
810 |
+
"epoch": 6.301369863013699,
|
811 |
+
"grad_norm": 0.917847216129303,
|
812 |
+
"learning_rate": 1e-06,
|
813 |
+
"loss": 2.1503,
|
814 |
+
"step": 115
|
815 |
+
},
|
816 |
+
{
|
817 |
+
"epoch": 6.3561643835616435,
|
818 |
+
"grad_norm": 0.9519619345664978,
|
819 |
+
"learning_rate": 1e-06,
|
820 |
+
"loss": 2.1766,
|
821 |
+
"step": 116
|
822 |
+
},
|
823 |
+
{
|
824 |
+
"epoch": 6.410958904109589,
|
825 |
+
"grad_norm": 0.8926482200622559,
|
826 |
+
"learning_rate": 1e-06,
|
827 |
+
"loss": 2.1493,
|
828 |
+
"step": 117
|
829 |
+
},
|
830 |
+
{
|
831 |
+
"epoch": 6.465753424657534,
|
832 |
+
"grad_norm": 0.817862868309021,
|
833 |
+
"learning_rate": 1e-06,
|
834 |
+
"loss": 2.166,
|
835 |
+
"step": 118
|
836 |
+
},
|
837 |
+
{
|
838 |
+
"epoch": 6.52054794520548,
|
839 |
+
"grad_norm": 0.8948012590408325,
|
840 |
+
"learning_rate": 1e-06,
|
841 |
+
"loss": 2.1346,
|
842 |
+
"step": 119
|
843 |
+
},
|
844 |
+
{
|
845 |
+
"epoch": 6.575342465753424,
|
846 |
+
"grad_norm": 0.9632709622383118,
|
847 |
+
"learning_rate": 1e-06,
|
848 |
+
"loss": 2.1427,
|
849 |
+
"step": 120
|
850 |
+
},
|
851 |
+
{
|
852 |
+
"epoch": 6.63013698630137,
|
853 |
+
"grad_norm": 0.9267117381095886,
|
854 |
+
"learning_rate": 1e-06,
|
855 |
+
"loss": 2.1581,
|
856 |
+
"step": 121
|
857 |
+
},
|
858 |
+
{
|
859 |
+
"epoch": 6.684931506849315,
|
860 |
+
"grad_norm": 0.9063679575920105,
|
861 |
+
"learning_rate": 1e-06,
|
862 |
+
"loss": 2.1453,
|
863 |
+
"step": 122
|
864 |
+
},
|
865 |
+
{
|
866 |
+
"epoch": 6.739726027397261,
|
867 |
+
"grad_norm": 0.9395270347595215,
|
868 |
+
"learning_rate": 1e-06,
|
869 |
+
"loss": 2.1515,
|
870 |
+
"step": 123
|
871 |
+
},
|
872 |
+
{
|
873 |
+
"epoch": 6.794520547945205,
|
874 |
+
"grad_norm": 0.9410396218299866,
|
875 |
+
"learning_rate": 1e-06,
|
876 |
+
"loss": 2.1518,
|
877 |
+
"step": 124
|
878 |
+
},
|
879 |
+
{
|
880 |
+
"epoch": 6.8493150684931505,
|
881 |
+
"grad_norm": 0.9229517579078674,
|
882 |
+
"learning_rate": 1e-06,
|
883 |
+
"loss": 2.1703,
|
884 |
+
"step": 125
|
885 |
+
},
|
886 |
+
{
|
887 |
+
"epoch": 6.904109589041096,
|
888 |
+
"grad_norm": 0.8469845652580261,
|
889 |
+
"learning_rate": 1e-06,
|
890 |
+
"loss": 2.1491,
|
891 |
+
"step": 126
|
892 |
+
},
|
893 |
+
{
|
894 |
+
"epoch": 6.958904109589041,
|
895 |
+
"grad_norm": 0.9080257415771484,
|
896 |
+
"learning_rate": 1e-06,
|
897 |
+
"loss": 2.1472,
|
898 |
+
"step": 127
|
899 |
+
},
|
900 |
+
{
|
901 |
+
"epoch": 7.013698630136986,
|
902 |
+
"grad_norm": 0.9071102142333984,
|
903 |
+
"learning_rate": 1e-06,
|
904 |
+
"loss": 2.1685,
|
905 |
+
"step": 128
|
906 |
+
},
|
907 |
+
{
|
908 |
+
"epoch": 7.068493150684931,
|
909 |
+
"grad_norm": 0.8933852910995483,
|
910 |
+
"learning_rate": 1e-06,
|
911 |
+
"loss": 2.1617,
|
912 |
+
"step": 129
|
913 |
+
},
|
914 |
+
{
|
915 |
+
"epoch": 7.123287671232877,
|
916 |
+
"grad_norm": 0.9227753281593323,
|
917 |
+
"learning_rate": 1e-06,
|
918 |
+
"loss": 2.1617,
|
919 |
+
"step": 130
|
920 |
+
},
|
921 |
+
{
|
922 |
+
"epoch": 7.178082191780822,
|
923 |
+
"grad_norm": 0.8686262965202332,
|
924 |
+
"learning_rate": 1e-06,
|
925 |
+
"loss": 2.1546,
|
926 |
+
"step": 131
|
927 |
+
},
|
928 |
+
{
|
929 |
+
"epoch": 7.232876712328767,
|
930 |
+
"grad_norm": 0.8385916948318481,
|
931 |
+
"learning_rate": 1e-06,
|
932 |
+
"loss": 2.1442,
|
933 |
+
"step": 132
|
934 |
+
},
|
935 |
+
{
|
936 |
+
"epoch": 7.287671232876712,
|
937 |
+
"grad_norm": 0.8217021822929382,
|
938 |
+
"learning_rate": 1e-06,
|
939 |
+
"loss": 2.1606,
|
940 |
+
"step": 133
|
941 |
+
},
|
942 |
+
{
|
943 |
+
"epoch": 7.342465753424658,
|
944 |
+
"grad_norm": 0.862777590751648,
|
945 |
+
"learning_rate": 1e-06,
|
946 |
+
"loss": 2.153,
|
947 |
+
"step": 134
|
948 |
+
},
|
949 |
+
{
|
950 |
+
"epoch": 7.397260273972603,
|
951 |
+
"grad_norm": 0.8956757187843323,
|
952 |
+
"learning_rate": 1e-06,
|
953 |
+
"loss": 2.1807,
|
954 |
+
"step": 135
|
955 |
+
},
|
956 |
+
{
|
957 |
+
"epoch": 7.4520547945205475,
|
958 |
+
"grad_norm": 0.781984806060791,
|
959 |
+
"learning_rate": 1e-06,
|
960 |
+
"loss": 2.1469,
|
961 |
+
"step": 136
|
962 |
+
},
|
963 |
+
{
|
964 |
+
"epoch": 7.506849315068493,
|
965 |
+
"grad_norm": 0.8100602030754089,
|
966 |
+
"learning_rate": 1e-06,
|
967 |
+
"loss": 2.107,
|
968 |
+
"step": 137
|
969 |
+
},
|
970 |
+
{
|
971 |
+
"epoch": 7.561643835616438,
|
972 |
+
"grad_norm": 0.8204404711723328,
|
973 |
+
"learning_rate": 1e-06,
|
974 |
+
"loss": 2.1477,
|
975 |
+
"step": 138
|
976 |
+
},
|
977 |
+
{
|
978 |
+
"epoch": 7.616438356164384,
|
979 |
+
"grad_norm": 0.8198928236961365,
|
980 |
+
"learning_rate": 1e-06,
|
981 |
+
"loss": 2.1514,
|
982 |
+
"step": 139
|
983 |
+
},
|
984 |
+
{
|
985 |
+
"epoch": 7.671232876712329,
|
986 |
+
"grad_norm": 0.8388807773590088,
|
987 |
+
"learning_rate": 1e-06,
|
988 |
+
"loss": 2.1265,
|
989 |
+
"step": 140
|
990 |
+
},
|
991 |
+
{
|
992 |
+
"epoch": 7.726027397260274,
|
993 |
+
"grad_norm": 0.8662092089653015,
|
994 |
+
"learning_rate": 1e-06,
|
995 |
+
"loss": 2.1316,
|
996 |
+
"step": 141
|
997 |
+
},
|
998 |
+
{
|
999 |
+
"epoch": 7.780821917808219,
|
1000 |
+
"grad_norm": 0.7682031393051147,
|
1001 |
+
"learning_rate": 1e-06,
|
1002 |
+
"loss": 2.1164,
|
1003 |
+
"step": 142
|
1004 |
+
},
|
1005 |
+
{
|
1006 |
+
"epoch": 7.835616438356165,
|
1007 |
+
"grad_norm": 0.796292781829834,
|
1008 |
+
"learning_rate": 1e-06,
|
1009 |
+
"loss": 2.1342,
|
1010 |
+
"step": 143
|
1011 |
+
},
|
1012 |
+
{
|
1013 |
+
"epoch": 7.890410958904109,
|
1014 |
+
"grad_norm": 0.8075994253158569,
|
1015 |
+
"learning_rate": 1e-06,
|
1016 |
+
"loss": 2.1221,
|
1017 |
+
"step": 144
|
1018 |
+
},
|
1019 |
+
{
|
1020 |
+
"epoch": 7.945205479452055,
|
1021 |
+
"grad_norm": 0.8507598638534546,
|
1022 |
+
"learning_rate": 1e-06,
|
1023 |
+
"loss": 2.1513,
|
1024 |
+
"step": 145
|
1025 |
+
},
|
1026 |
+
{
|
1027 |
+
"epoch": 8.0,
|
1028 |
+
"grad_norm": 0.768495500087738,
|
1029 |
+
"learning_rate": 1e-06,
|
1030 |
+
"loss": 2.1369,
|
1031 |
+
"step": 146
|
1032 |
+
}
|
1033 |
+
],
|
1034 |
+
"logging_steps": 1,
|
1035 |
+
"max_steps": 540,
|
1036 |
+
"num_input_tokens_seen": 0,
|
1037 |
+
"num_train_epochs": 30,
|
1038 |
+
"save_steps": 500,
|
1039 |
+
"total_flos": 1.0225056854153626e+17,
|
1040 |
+
"train_batch_size": 2,
|
1041 |
+
"trial_name": null,
|
1042 |
+
"trial_params": null
|
1043 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9878e4831c5c04dc6b7feec2819c9ae2ca129a83ad0ca3012c0b67edeb1c7852
|
3 |
+
size 5048
|