Upload folder using huggingface_hub
Browse files- README.md +200 -1
- adapter_config.json +29 -0
- adapter_model.safetensors +3 -0
- added_tokens.json +40 -0
- merges.txt +0 -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_config.json +326 -0
- trainer_state.json +553 -0
- training_args.bin +3 -0
- vocab.json +0 -0
README.md
CHANGED
@@ -1,3 +1,202 @@
|
|
1 |
---
|
2 |
-
|
|
|
3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
---
|
2 |
+
library_name: peft
|
3 |
+
base_model: microsoft/phi-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 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "microsoft/phi-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": 16,
|
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 |
+
"Wqkv",
|
24 |
+
"out_proj"
|
25 |
+
],
|
26 |
+
"task_type": "CAUSAL_LM",
|
27 |
+
"use_dora": false,
|
28 |
+
"use_rslora": false
|
29 |
+
}
|
adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6e343f8cb19ccc96d6a74b7eb27c26b5adb83a96f6906f847bfea63063113100
|
3 |
+
size 31474080
|
added_tokens.json
ADDED
@@ -0,0 +1,40 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"\t\t": 50294,
|
3 |
+
"\t\t\t": 50293,
|
4 |
+
"\t\t\t\t": 50292,
|
5 |
+
"\t\t\t\t\t": 50291,
|
6 |
+
"\t\t\t\t\t\t": 50290,
|
7 |
+
"\t\t\t\t\t\t\t": 50289,
|
8 |
+
"\t\t\t\t\t\t\t\t": 50288,
|
9 |
+
"\t\t\t\t\t\t\t\t\t": 50287,
|
10 |
+
" ": 50286,
|
11 |
+
" ": 50285,
|
12 |
+
" ": 50284,
|
13 |
+
" ": 50283,
|
14 |
+
" ": 50282,
|
15 |
+
" ": 50281,
|
16 |
+
" ": 50280,
|
17 |
+
" ": 50279,
|
18 |
+
" ": 50278,
|
19 |
+
" ": 50277,
|
20 |
+
" ": 50276,
|
21 |
+
" ": 50275,
|
22 |
+
" ": 50274,
|
23 |
+
" ": 50273,
|
24 |
+
" ": 50272,
|
25 |
+
" ": 50271,
|
26 |
+
" ": 50270,
|
27 |
+
" ": 50269,
|
28 |
+
" ": 50268,
|
29 |
+
" ": 50267,
|
30 |
+
" ": 50266,
|
31 |
+
" ": 50265,
|
32 |
+
" ": 50264,
|
33 |
+
" ": 50263,
|
34 |
+
" ": 50262,
|
35 |
+
" ": 50261,
|
36 |
+
" ": 50260,
|
37 |
+
" ": 50259,
|
38 |
+
" ": 50258,
|
39 |
+
" ": 50257
|
40 |
+
}
|
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bfb2087680ffbbdefad43de5490f81bf7ce7174b921d64dc54476f90fef8ebb4
|
3 |
+
size 15905466
|
rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:703e60956f0bf6395c0e46c587abfc40096395ca196e4a5ac0e14feaaa7aed17
|
3 |
+
size 14244
|
scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:af6bfe3e16f1cd6ce6060933584de7f848398eab6aa97f52668c7943aa75097d
|
3 |
+
size 1064
|
special_tokens_map.json
ADDED
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<|endoftext|>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": {
|
10 |
+
"content": "<|endoftext|>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": "<|endoftext|>",
|
17 |
+
"unk_token": {
|
18 |
+
"content": "<|endoftext|>",
|
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 +1,326 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_eos_token": true,
|
3 |
+
"add_prefix_space": false,
|
4 |
+
"added_tokens_decoder": {
|
5 |
+
"50256": {
|
6 |
+
"content": "<|endoftext|>",
|
7 |
+
"lstrip": false,
|
8 |
+
"normalized": false,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false,
|
11 |
+
"special": true
|
12 |
+
},
|
13 |
+
"50257": {
|
14 |
+
"content": " ",
|
15 |
+
"lstrip": false,
|
16 |
+
"normalized": true,
|
17 |
+
"rstrip": false,
|
18 |
+
"single_word": false,
|
19 |
+
"special": false
|
20 |
+
},
|
21 |
+
"50258": {
|
22 |
+
"content": " ",
|
23 |
+
"lstrip": false,
|
24 |
+
"normalized": true,
|
25 |
+
"rstrip": false,
|
26 |
+
"single_word": false,
|
27 |
+
"special": false
|
28 |
+
},
|
29 |
+
"50259": {
|
30 |
+
"content": " ",
|
31 |
+
"lstrip": false,
|
32 |
+
"normalized": true,
|
33 |
+
"rstrip": false,
|
34 |
+
"single_word": false,
|
35 |
+
"special": false
|
36 |
+
},
|
37 |
+
"50260": {
|
38 |
+
"content": " ",
|
39 |
+
"lstrip": false,
|
40 |
+
"normalized": true,
|
41 |
+
"rstrip": false,
|
42 |
+
"single_word": false,
|
43 |
+
"special": false
|
44 |
+
},
|
45 |
+
"50261": {
|
46 |
+
"content": " ",
|
47 |
+
"lstrip": false,
|
48 |
+
"normalized": true,
|
49 |
+
"rstrip": false,
|
50 |
+
"single_word": false,
|
51 |
+
"special": false
|
52 |
+
},
|
53 |
+
"50262": {
|
54 |
+
"content": " ",
|
55 |
+
"lstrip": false,
|
56 |
+
"normalized": true,
|
57 |
+
"rstrip": false,
|
58 |
+
"single_word": false,
|
59 |
+
"special": false
|
60 |
+
},
|
61 |
+
"50263": {
|
62 |
+
"content": " ",
|
63 |
+
"lstrip": false,
|
64 |
+
"normalized": true,
|
65 |
+
"rstrip": false,
|
66 |
+
"single_word": false,
|
67 |
+
"special": false
|
68 |
+
},
|
69 |
+
"50264": {
|
70 |
+
"content": " ",
|
71 |
+
"lstrip": false,
|
72 |
+
"normalized": true,
|
73 |
+
"rstrip": false,
|
74 |
+
"single_word": false,
|
75 |
+
"special": false
|
76 |
+
},
|
77 |
+
"50265": {
|
78 |
+
"content": " ",
|
79 |
+
"lstrip": false,
|
80 |
+
"normalized": true,
|
81 |
+
"rstrip": false,
|
82 |
+
"single_word": false,
|
83 |
+
"special": false
|
84 |
+
},
|
85 |
+
"50266": {
|
86 |
+
"content": " ",
|
87 |
+
"lstrip": false,
|
88 |
+
"normalized": true,
|
89 |
+
"rstrip": false,
|
90 |
+
"single_word": false,
|
91 |
+
"special": false
|
92 |
+
},
|
93 |
+
"50267": {
|
94 |
+
"content": " ",
|
95 |
+
"lstrip": false,
|
96 |
+
"normalized": true,
|
97 |
+
"rstrip": false,
|
98 |
+
"single_word": false,
|
99 |
+
"special": false
|
100 |
+
},
|
101 |
+
"50268": {
|
102 |
+
"content": " ",
|
103 |
+
"lstrip": false,
|
104 |
+
"normalized": true,
|
105 |
+
"rstrip": false,
|
106 |
+
"single_word": false,
|
107 |
+
"special": false
|
108 |
+
},
|
109 |
+
"50269": {
|
110 |
+
"content": " ",
|
111 |
+
"lstrip": false,
|
112 |
+
"normalized": true,
|
113 |
+
"rstrip": false,
|
114 |
+
"single_word": false,
|
115 |
+
"special": false
|
116 |
+
},
|
117 |
+
"50270": {
|
118 |
+
"content": " ",
|
119 |
+
"lstrip": false,
|
120 |
+
"normalized": true,
|
121 |
+
"rstrip": false,
|
122 |
+
"single_word": false,
|
123 |
+
"special": false
|
124 |
+
},
|
125 |
+
"50271": {
|
126 |
+
"content": " ",
|
127 |
+
"lstrip": false,
|
128 |
+
"normalized": true,
|
129 |
+
"rstrip": false,
|
130 |
+
"single_word": false,
|
131 |
+
"special": false
|
132 |
+
},
|
133 |
+
"50272": {
|
134 |
+
"content": " ",
|
135 |
+
"lstrip": false,
|
136 |
+
"normalized": true,
|
137 |
+
"rstrip": false,
|
138 |
+
"single_word": false,
|
139 |
+
"special": false
|
140 |
+
},
|
141 |
+
"50273": {
|
142 |
+
"content": " ",
|
143 |
+
"lstrip": false,
|
144 |
+
"normalized": true,
|
145 |
+
"rstrip": false,
|
146 |
+
"single_word": false,
|
147 |
+
"special": false
|
148 |
+
},
|
149 |
+
"50274": {
|
150 |
+
"content": " ",
|
151 |
+
"lstrip": false,
|
152 |
+
"normalized": true,
|
153 |
+
"rstrip": false,
|
154 |
+
"single_word": false,
|
155 |
+
"special": false
|
156 |
+
},
|
157 |
+
"50275": {
|
158 |
+
"content": " ",
|
159 |
+
"lstrip": false,
|
160 |
+
"normalized": true,
|
161 |
+
"rstrip": false,
|
162 |
+
"single_word": false,
|
163 |
+
"special": false
|
164 |
+
},
|
165 |
+
"50276": {
|
166 |
+
"content": " ",
|
167 |
+
"lstrip": false,
|
168 |
+
"normalized": true,
|
169 |
+
"rstrip": false,
|
170 |
+
"single_word": false,
|
171 |
+
"special": false
|
172 |
+
},
|
173 |
+
"50277": {
|
174 |
+
"content": " ",
|
175 |
+
"lstrip": false,
|
176 |
+
"normalized": true,
|
177 |
+
"rstrip": false,
|
178 |
+
"single_word": false,
|
179 |
+
"special": false
|
180 |
+
},
|
181 |
+
"50278": {
|
182 |
+
"content": " ",
|
183 |
+
"lstrip": false,
|
184 |
+
"normalized": true,
|
185 |
+
"rstrip": false,
|
186 |
+
"single_word": false,
|
187 |
+
"special": false
|
188 |
+
},
|
189 |
+
"50279": {
|
190 |
+
"content": " ",
|
191 |
+
"lstrip": false,
|
192 |
+
"normalized": true,
|
193 |
+
"rstrip": false,
|
194 |
+
"single_word": false,
|
195 |
+
"special": false
|
196 |
+
},
|
197 |
+
"50280": {
|
198 |
+
"content": " ",
|
199 |
+
"lstrip": false,
|
200 |
+
"normalized": true,
|
201 |
+
"rstrip": false,
|
202 |
+
"single_word": false,
|
203 |
+
"special": false
|
204 |
+
},
|
205 |
+
"50281": {
|
206 |
+
"content": " ",
|
207 |
+
"lstrip": false,
|
208 |
+
"normalized": true,
|
209 |
+
"rstrip": false,
|
210 |
+
"single_word": false,
|
211 |
+
"special": false
|
212 |
+
},
|
213 |
+
"50282": {
|
214 |
+
"content": " ",
|
215 |
+
"lstrip": false,
|
216 |
+
"normalized": true,
|
217 |
+
"rstrip": false,
|
218 |
+
"single_word": false,
|
219 |
+
"special": false
|
220 |
+
},
|
221 |
+
"50283": {
|
222 |
+
"content": " ",
|
223 |
+
"lstrip": false,
|
224 |
+
"normalized": true,
|
225 |
+
"rstrip": false,
|
226 |
+
"single_word": false,
|
227 |
+
"special": false
|
228 |
+
},
|
229 |
+
"50284": {
|
230 |
+
"content": " ",
|
231 |
+
"lstrip": false,
|
232 |
+
"normalized": true,
|
233 |
+
"rstrip": false,
|
234 |
+
"single_word": false,
|
235 |
+
"special": false
|
236 |
+
},
|
237 |
+
"50285": {
|
238 |
+
"content": " ",
|
239 |
+
"lstrip": false,
|
240 |
+
"normalized": true,
|
241 |
+
"rstrip": false,
|
242 |
+
"single_word": false,
|
243 |
+
"special": false
|
244 |
+
},
|
245 |
+
"50286": {
|
246 |
+
"content": " ",
|
247 |
+
"lstrip": false,
|
248 |
+
"normalized": true,
|
249 |
+
"rstrip": false,
|
250 |
+
"single_word": false,
|
251 |
+
"special": false
|
252 |
+
},
|
253 |
+
"50287": {
|
254 |
+
"content": "\t\t\t\t\t\t\t\t\t",
|
255 |
+
"lstrip": false,
|
256 |
+
"normalized": true,
|
257 |
+
"rstrip": false,
|
258 |
+
"single_word": false,
|
259 |
+
"special": false
|
260 |
+
},
|
261 |
+
"50288": {
|
262 |
+
"content": "\t\t\t\t\t\t\t\t",
|
263 |
+
"lstrip": false,
|
264 |
+
"normalized": true,
|
265 |
+
"rstrip": false,
|
266 |
+
"single_word": false,
|
267 |
+
"special": false
|
268 |
+
},
|
269 |
+
"50289": {
|
270 |
+
"content": "\t\t\t\t\t\t\t",
|
271 |
+
"lstrip": false,
|
272 |
+
"normalized": true,
|
273 |
+
"rstrip": false,
|
274 |
+
"single_word": false,
|
275 |
+
"special": false
|
276 |
+
},
|
277 |
+
"50290": {
|
278 |
+
"content": "\t\t\t\t\t\t",
|
279 |
+
"lstrip": false,
|
280 |
+
"normalized": true,
|
281 |
+
"rstrip": false,
|
282 |
+
"single_word": false,
|
283 |
+
"special": false
|
284 |
+
},
|
285 |
+
"50291": {
|
286 |
+
"content": "\t\t\t\t\t",
|
287 |
+
"lstrip": false,
|
288 |
+
"normalized": true,
|
289 |
+
"rstrip": false,
|
290 |
+
"single_word": false,
|
291 |
+
"special": false
|
292 |
+
},
|
293 |
+
"50292": {
|
294 |
+
"content": "\t\t\t\t",
|
295 |
+
"lstrip": false,
|
296 |
+
"normalized": true,
|
297 |
+
"rstrip": false,
|
298 |
+
"single_word": false,
|
299 |
+
"special": false
|
300 |
+
},
|
301 |
+
"50293": {
|
302 |
+
"content": "\t\t\t",
|
303 |
+
"lstrip": false,
|
304 |
+
"normalized": true,
|
305 |
+
"rstrip": false,
|
306 |
+
"single_word": false,
|
307 |
+
"special": false
|
308 |
+
},
|
309 |
+
"50294": {
|
310 |
+
"content": "\t\t",
|
311 |
+
"lstrip": false,
|
312 |
+
"normalized": true,
|
313 |
+
"rstrip": false,
|
314 |
+
"single_word": false,
|
315 |
+
"special": false
|
316 |
+
}
|
317 |
+
},
|
318 |
+
"bos_token": "<|endoftext|>",
|
319 |
+
"clean_up_tokenization_spaces": true,
|
320 |
+
"eos_token": "<|endoftext|>",
|
321 |
+
"max_length": 1024,
|
322 |
+
"model_max_length": 2048,
|
323 |
+
"pad_token": "<|endoftext|>",
|
324 |
+
"tokenizer_class": "CodeGenTokenizer",
|
325 |
+
"unk_token": "<|endoftext|>"
|
326 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,553 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 10.997134670487107,
|
5 |
+
"eval_steps": 50,
|
6 |
+
"global_step": 1919,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.14,
|
13 |
+
"grad_norm": 0.1376492828130722,
|
14 |
+
"learning_rate": 2.5e-05,
|
15 |
+
"loss": 0.9919,
|
16 |
+
"step": 25
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.29,
|
20 |
+
"grad_norm": 0.14622816443443298,
|
21 |
+
"learning_rate": 5e-05,
|
22 |
+
"loss": 0.8765,
|
23 |
+
"step": 50
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.43,
|
27 |
+
"grad_norm": 0.1424524486064911,
|
28 |
+
"learning_rate": 7.500000000000001e-05,
|
29 |
+
"loss": 0.6284,
|
30 |
+
"step": 75
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 0.57,
|
34 |
+
"grad_norm": 0.09082940965890884,
|
35 |
+
"learning_rate": 0.0001,
|
36 |
+
"loss": 0.4119,
|
37 |
+
"step": 100
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 0.72,
|
41 |
+
"grad_norm": 0.11173515766859055,
|
42 |
+
"learning_rate": 9.92603550295858e-05,
|
43 |
+
"loss": 0.3504,
|
44 |
+
"step": 125
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.86,
|
48 |
+
"grad_norm": 0.09382566064596176,
|
49 |
+
"learning_rate": 9.85207100591716e-05,
|
50 |
+
"loss": 0.3142,
|
51 |
+
"step": 150
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 1.0,
|
55 |
+
"grad_norm": 0.11800573766231537,
|
56 |
+
"learning_rate": 9.77810650887574e-05,
|
57 |
+
"loss": 0.299,
|
58 |
+
"step": 175
|
59 |
+
},
|
60 |
+
{
|
61 |
+
"epoch": 1.15,
|
62 |
+
"grad_norm": 0.1385473757982254,
|
63 |
+
"learning_rate": 9.70414201183432e-05,
|
64 |
+
"loss": 0.2783,
|
65 |
+
"step": 200
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 1.29,
|
69 |
+
"grad_norm": 0.1731497198343277,
|
70 |
+
"learning_rate": 9.6301775147929e-05,
|
71 |
+
"loss": 0.2583,
|
72 |
+
"step": 225
|
73 |
+
},
|
74 |
+
{
|
75 |
+
"epoch": 1.43,
|
76 |
+
"grad_norm": 0.16235513985157013,
|
77 |
+
"learning_rate": 9.55621301775148e-05,
|
78 |
+
"loss": 0.2408,
|
79 |
+
"step": 250
|
80 |
+
},
|
81 |
+
{
|
82 |
+
"epoch": 1.58,
|
83 |
+
"grad_norm": 0.2389882653951645,
|
84 |
+
"learning_rate": 9.48224852071006e-05,
|
85 |
+
"loss": 0.2279,
|
86 |
+
"step": 275
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 1.72,
|
90 |
+
"grad_norm": 0.2514766454696655,
|
91 |
+
"learning_rate": 9.408284023668639e-05,
|
92 |
+
"loss": 0.2109,
|
93 |
+
"step": 300
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 1.86,
|
97 |
+
"grad_norm": 0.3435331881046295,
|
98 |
+
"learning_rate": 9.33431952662722e-05,
|
99 |
+
"loss": 0.2009,
|
100 |
+
"step": 325
|
101 |
+
},
|
102 |
+
{
|
103 |
+
"epoch": 2.01,
|
104 |
+
"grad_norm": 0.2297317236661911,
|
105 |
+
"learning_rate": 9.260355029585799e-05,
|
106 |
+
"loss": 0.1904,
|
107 |
+
"step": 350
|
108 |
+
},
|
109 |
+
{
|
110 |
+
"epoch": 2.15,
|
111 |
+
"grad_norm": 0.23601436614990234,
|
112 |
+
"learning_rate": 9.186390532544379e-05,
|
113 |
+
"loss": 0.1728,
|
114 |
+
"step": 375
|
115 |
+
},
|
116 |
+
{
|
117 |
+
"epoch": 2.29,
|
118 |
+
"grad_norm": 0.26974865794181824,
|
119 |
+
"learning_rate": 9.112426035502959e-05,
|
120 |
+
"loss": 0.1658,
|
121 |
+
"step": 400
|
122 |
+
},
|
123 |
+
{
|
124 |
+
"epoch": 2.44,
|
125 |
+
"grad_norm": 0.3188651502132416,
|
126 |
+
"learning_rate": 9.038461538461538e-05,
|
127 |
+
"loss": 0.1619,
|
128 |
+
"step": 425
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 2.58,
|
132 |
+
"grad_norm": 0.40681496262550354,
|
133 |
+
"learning_rate": 8.96449704142012e-05,
|
134 |
+
"loss": 0.1496,
|
135 |
+
"step": 450
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 2.72,
|
139 |
+
"grad_norm": 0.32123222947120667,
|
140 |
+
"learning_rate": 8.8905325443787e-05,
|
141 |
+
"loss": 0.1498,
|
142 |
+
"step": 475
|
143 |
+
},
|
144 |
+
{
|
145 |
+
"epoch": 2.87,
|
146 |
+
"grad_norm": 0.2911372482776642,
|
147 |
+
"learning_rate": 8.816568047337278e-05,
|
148 |
+
"loss": 0.1378,
|
149 |
+
"step": 500
|
150 |
+
},
|
151 |
+
{
|
152 |
+
"epoch": 3.01,
|
153 |
+
"grad_norm": 0.28380608558654785,
|
154 |
+
"learning_rate": 8.742603550295858e-05,
|
155 |
+
"loss": 0.1355,
|
156 |
+
"step": 525
|
157 |
+
},
|
158 |
+
{
|
159 |
+
"epoch": 3.15,
|
160 |
+
"grad_norm": 0.3216865062713623,
|
161 |
+
"learning_rate": 8.668639053254438e-05,
|
162 |
+
"loss": 0.1302,
|
163 |
+
"step": 550
|
164 |
+
},
|
165 |
+
{
|
166 |
+
"epoch": 3.3,
|
167 |
+
"grad_norm": 0.29950952529907227,
|
168 |
+
"learning_rate": 8.594674556213019e-05,
|
169 |
+
"loss": 0.1209,
|
170 |
+
"step": 575
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 3.44,
|
174 |
+
"grad_norm": 0.2643551826477051,
|
175 |
+
"learning_rate": 8.520710059171599e-05,
|
176 |
+
"loss": 0.1222,
|
177 |
+
"step": 600
|
178 |
+
},
|
179 |
+
{
|
180 |
+
"epoch": 3.58,
|
181 |
+
"grad_norm": 0.31945034861564636,
|
182 |
+
"learning_rate": 8.446745562130178e-05,
|
183 |
+
"loss": 0.1172,
|
184 |
+
"step": 625
|
185 |
+
},
|
186 |
+
{
|
187 |
+
"epoch": 3.72,
|
188 |
+
"grad_norm": 0.28063860535621643,
|
189 |
+
"learning_rate": 8.372781065088757e-05,
|
190 |
+
"loss": 0.1162,
|
191 |
+
"step": 650
|
192 |
+
},
|
193 |
+
{
|
194 |
+
"epoch": 3.87,
|
195 |
+
"grad_norm": 0.30673155188560486,
|
196 |
+
"learning_rate": 8.298816568047337e-05,
|
197 |
+
"loss": 0.1127,
|
198 |
+
"step": 675
|
199 |
+
},
|
200 |
+
{
|
201 |
+
"epoch": 4.01,
|
202 |
+
"grad_norm": 0.26293325424194336,
|
203 |
+
"learning_rate": 8.224852071005918e-05,
|
204 |
+
"loss": 0.1078,
|
205 |
+
"step": 700
|
206 |
+
},
|
207 |
+
{
|
208 |
+
"epoch": 4.15,
|
209 |
+
"grad_norm": 0.3006896674633026,
|
210 |
+
"learning_rate": 8.150887573964498e-05,
|
211 |
+
"loss": 0.1039,
|
212 |
+
"step": 725
|
213 |
+
},
|
214 |
+
{
|
215 |
+
"epoch": 4.3,
|
216 |
+
"grad_norm": 0.22531060874462128,
|
217 |
+
"learning_rate": 8.076923076923078e-05,
|
218 |
+
"loss": 0.1026,
|
219 |
+
"step": 750
|
220 |
+
},
|
221 |
+
{
|
222 |
+
"epoch": 4.44,
|
223 |
+
"grad_norm": 0.27850422263145447,
|
224 |
+
"learning_rate": 8.002958579881658e-05,
|
225 |
+
"loss": 0.1038,
|
226 |
+
"step": 775
|
227 |
+
},
|
228 |
+
{
|
229 |
+
"epoch": 4.58,
|
230 |
+
"grad_norm": 0.24622277915477753,
|
231 |
+
"learning_rate": 7.928994082840237e-05,
|
232 |
+
"loss": 0.1004,
|
233 |
+
"step": 800
|
234 |
+
},
|
235 |
+
{
|
236 |
+
"epoch": 4.73,
|
237 |
+
"grad_norm": 0.2631712555885315,
|
238 |
+
"learning_rate": 7.855029585798817e-05,
|
239 |
+
"loss": 0.0944,
|
240 |
+
"step": 825
|
241 |
+
},
|
242 |
+
{
|
243 |
+
"epoch": 4.87,
|
244 |
+
"grad_norm": 0.2231552004814148,
|
245 |
+
"learning_rate": 7.781065088757397e-05,
|
246 |
+
"loss": 0.0937,
|
247 |
+
"step": 850
|
248 |
+
},
|
249 |
+
{
|
250 |
+
"epoch": 5.01,
|
251 |
+
"grad_norm": 0.2672629952430725,
|
252 |
+
"learning_rate": 7.707100591715977e-05,
|
253 |
+
"loss": 0.0908,
|
254 |
+
"step": 875
|
255 |
+
},
|
256 |
+
{
|
257 |
+
"epoch": 5.16,
|
258 |
+
"grad_norm": 0.32010477781295776,
|
259 |
+
"learning_rate": 7.633136094674557e-05,
|
260 |
+
"loss": 0.0949,
|
261 |
+
"step": 900
|
262 |
+
},
|
263 |
+
{
|
264 |
+
"epoch": 5.3,
|
265 |
+
"grad_norm": 0.20605669915676117,
|
266 |
+
"learning_rate": 7.559171597633137e-05,
|
267 |
+
"loss": 0.0883,
|
268 |
+
"step": 925
|
269 |
+
},
|
270 |
+
{
|
271 |
+
"epoch": 5.44,
|
272 |
+
"grad_norm": 0.2745099663734436,
|
273 |
+
"learning_rate": 7.485207100591716e-05,
|
274 |
+
"loss": 0.0881,
|
275 |
+
"step": 950
|
276 |
+
},
|
277 |
+
{
|
278 |
+
"epoch": 5.59,
|
279 |
+
"grad_norm": 0.22129909694194794,
|
280 |
+
"learning_rate": 7.411242603550296e-05,
|
281 |
+
"loss": 0.0861,
|
282 |
+
"step": 975
|
283 |
+
},
|
284 |
+
{
|
285 |
+
"epoch": 5.73,
|
286 |
+
"grad_norm": 0.19070565700531006,
|
287 |
+
"learning_rate": 7.337278106508876e-05,
|
288 |
+
"loss": 0.0874,
|
289 |
+
"step": 1000
|
290 |
+
},
|
291 |
+
{
|
292 |
+
"epoch": 5.87,
|
293 |
+
"grad_norm": 0.27825799584388733,
|
294 |
+
"learning_rate": 7.263313609467456e-05,
|
295 |
+
"loss": 0.0846,
|
296 |
+
"step": 1025
|
297 |
+
},
|
298 |
+
{
|
299 |
+
"epoch": 6.02,
|
300 |
+
"grad_norm": 0.28191158175468445,
|
301 |
+
"learning_rate": 7.189349112426036e-05,
|
302 |
+
"loss": 0.0859,
|
303 |
+
"step": 1050
|
304 |
+
},
|
305 |
+
{
|
306 |
+
"epoch": 6.16,
|
307 |
+
"grad_norm": 0.2130414992570877,
|
308 |
+
"learning_rate": 7.115384615384616e-05,
|
309 |
+
"loss": 0.0843,
|
310 |
+
"step": 1075
|
311 |
+
},
|
312 |
+
{
|
313 |
+
"epoch": 6.3,
|
314 |
+
"grad_norm": 0.2572125494480133,
|
315 |
+
"learning_rate": 7.041420118343195e-05,
|
316 |
+
"loss": 0.0829,
|
317 |
+
"step": 1100
|
318 |
+
},
|
319 |
+
{
|
320 |
+
"epoch": 6.45,
|
321 |
+
"grad_norm": 0.2799431383609772,
|
322 |
+
"learning_rate": 6.967455621301775e-05,
|
323 |
+
"loss": 0.0794,
|
324 |
+
"step": 1125
|
325 |
+
},
|
326 |
+
{
|
327 |
+
"epoch": 6.59,
|
328 |
+
"grad_norm": 0.22224412858486176,
|
329 |
+
"learning_rate": 6.893491124260355e-05,
|
330 |
+
"loss": 0.0807,
|
331 |
+
"step": 1150
|
332 |
+
},
|
333 |
+
{
|
334 |
+
"epoch": 6.73,
|
335 |
+
"grad_norm": 0.19804546236991882,
|
336 |
+
"learning_rate": 6.819526627218935e-05,
|
337 |
+
"loss": 0.077,
|
338 |
+
"step": 1175
|
339 |
+
},
|
340 |
+
{
|
341 |
+
"epoch": 6.88,
|
342 |
+
"grad_norm": 0.2524961233139038,
|
343 |
+
"learning_rate": 6.745562130177515e-05,
|
344 |
+
"loss": 0.0802,
|
345 |
+
"step": 1200
|
346 |
+
},
|
347 |
+
{
|
348 |
+
"epoch": 7.02,
|
349 |
+
"grad_norm": 0.18262654542922974,
|
350 |
+
"learning_rate": 6.671597633136095e-05,
|
351 |
+
"loss": 0.0757,
|
352 |
+
"step": 1225
|
353 |
+
},
|
354 |
+
{
|
355 |
+
"epoch": 7.16,
|
356 |
+
"grad_norm": 0.1993337720632553,
|
357 |
+
"learning_rate": 6.597633136094676e-05,
|
358 |
+
"loss": 0.0766,
|
359 |
+
"step": 1250
|
360 |
+
},
|
361 |
+
{
|
362 |
+
"epoch": 7.31,
|
363 |
+
"grad_norm": 0.19785763323307037,
|
364 |
+
"learning_rate": 6.523668639053254e-05,
|
365 |
+
"loss": 0.0751,
|
366 |
+
"step": 1275
|
367 |
+
},
|
368 |
+
{
|
369 |
+
"epoch": 7.45,
|
370 |
+
"grad_norm": 0.19745734333992004,
|
371 |
+
"learning_rate": 6.449704142011834e-05,
|
372 |
+
"loss": 0.0768,
|
373 |
+
"step": 1300
|
374 |
+
},
|
375 |
+
{
|
376 |
+
"epoch": 7.59,
|
377 |
+
"grad_norm": 0.17973637580871582,
|
378 |
+
"learning_rate": 6.375739644970414e-05,
|
379 |
+
"loss": 0.0738,
|
380 |
+
"step": 1325
|
381 |
+
},
|
382 |
+
{
|
383 |
+
"epoch": 7.74,
|
384 |
+
"grad_norm": 0.1808304488658905,
|
385 |
+
"learning_rate": 6.301775147928994e-05,
|
386 |
+
"loss": 0.0757,
|
387 |
+
"step": 1350
|
388 |
+
},
|
389 |
+
{
|
390 |
+
"epoch": 7.88,
|
391 |
+
"grad_norm": 0.19356884062290192,
|
392 |
+
"learning_rate": 6.227810650887575e-05,
|
393 |
+
"loss": 0.0738,
|
394 |
+
"step": 1375
|
395 |
+
},
|
396 |
+
{
|
397 |
+
"epoch": 8.02,
|
398 |
+
"grad_norm": 0.19427159428596497,
|
399 |
+
"learning_rate": 6.153846153846155e-05,
|
400 |
+
"loss": 0.0748,
|
401 |
+
"step": 1400
|
402 |
+
},
|
403 |
+
{
|
404 |
+
"epoch": 8.17,
|
405 |
+
"grad_norm": 0.16624993085861206,
|
406 |
+
"learning_rate": 6.079881656804735e-05,
|
407 |
+
"loss": 0.0737,
|
408 |
+
"step": 1425
|
409 |
+
},
|
410 |
+
{
|
411 |
+
"epoch": 8.31,
|
412 |
+
"grad_norm": 0.2472502738237381,
|
413 |
+
"learning_rate": 6.005917159763313e-05,
|
414 |
+
"loss": 0.0726,
|
415 |
+
"step": 1450
|
416 |
+
},
|
417 |
+
{
|
418 |
+
"epoch": 8.45,
|
419 |
+
"grad_norm": 0.20945917069911957,
|
420 |
+
"learning_rate": 5.931952662721894e-05,
|
421 |
+
"loss": 0.0703,
|
422 |
+
"step": 1475
|
423 |
+
},
|
424 |
+
{
|
425 |
+
"epoch": 8.6,
|
426 |
+
"grad_norm": 0.21044062077999115,
|
427 |
+
"learning_rate": 5.8579881656804736e-05,
|
428 |
+
"loss": 0.0705,
|
429 |
+
"step": 1500
|
430 |
+
},
|
431 |
+
{
|
432 |
+
"epoch": 8.74,
|
433 |
+
"grad_norm": 0.1783844232559204,
|
434 |
+
"learning_rate": 5.7840236686390534e-05,
|
435 |
+
"loss": 0.0711,
|
436 |
+
"step": 1525
|
437 |
+
},
|
438 |
+
{
|
439 |
+
"epoch": 8.88,
|
440 |
+
"grad_norm": 0.1689521223306656,
|
441 |
+
"learning_rate": 5.710059171597634e-05,
|
442 |
+
"loss": 0.0738,
|
443 |
+
"step": 1550
|
444 |
+
},
|
445 |
+
{
|
446 |
+
"epoch": 9.03,
|
447 |
+
"grad_norm": 0.1530502885580063,
|
448 |
+
"learning_rate": 5.636094674556214e-05,
|
449 |
+
"loss": 0.0684,
|
450 |
+
"step": 1575
|
451 |
+
},
|
452 |
+
{
|
453 |
+
"epoch": 9.17,
|
454 |
+
"grad_norm": 0.1769784688949585,
|
455 |
+
"learning_rate": 5.562130177514793e-05,
|
456 |
+
"loss": 0.0699,
|
457 |
+
"step": 1600
|
458 |
+
},
|
459 |
+
{
|
460 |
+
"epoch": 9.31,
|
461 |
+
"grad_norm": 0.19619758427143097,
|
462 |
+
"learning_rate": 5.488165680473373e-05,
|
463 |
+
"loss": 0.0681,
|
464 |
+
"step": 1625
|
465 |
+
},
|
466 |
+
{
|
467 |
+
"epoch": 9.46,
|
468 |
+
"grad_norm": 0.19810470938682556,
|
469 |
+
"learning_rate": 5.4142011834319526e-05,
|
470 |
+
"loss": 0.071,
|
471 |
+
"step": 1650
|
472 |
+
},
|
473 |
+
{
|
474 |
+
"epoch": 9.6,
|
475 |
+
"grad_norm": 0.183139830827713,
|
476 |
+
"learning_rate": 5.340236686390533e-05,
|
477 |
+
"loss": 0.0675,
|
478 |
+
"step": 1675
|
479 |
+
},
|
480 |
+
{
|
481 |
+
"epoch": 9.74,
|
482 |
+
"grad_norm": 0.22580993175506592,
|
483 |
+
"learning_rate": 5.266272189349113e-05,
|
484 |
+
"loss": 0.068,
|
485 |
+
"step": 1700
|
486 |
+
},
|
487 |
+
{
|
488 |
+
"epoch": 9.89,
|
489 |
+
"grad_norm": 0.1878005862236023,
|
490 |
+
"learning_rate": 5.192307692307693e-05,
|
491 |
+
"loss": 0.0682,
|
492 |
+
"step": 1725
|
493 |
+
},
|
494 |
+
{
|
495 |
+
"epoch": 10.03,
|
496 |
+
"grad_norm": 0.17333678901195526,
|
497 |
+
"learning_rate": 5.118343195266272e-05,
|
498 |
+
"loss": 0.0683,
|
499 |
+
"step": 1750
|
500 |
+
},
|
501 |
+
{
|
502 |
+
"epoch": 10.17,
|
503 |
+
"grad_norm": 0.16736529767513275,
|
504 |
+
"learning_rate": 5.044378698224852e-05,
|
505 |
+
"loss": 0.0639,
|
506 |
+
"step": 1775
|
507 |
+
},
|
508 |
+
{
|
509 |
+
"epoch": 10.32,
|
510 |
+
"grad_norm": 0.15685293078422546,
|
511 |
+
"learning_rate": 4.970414201183432e-05,
|
512 |
+
"loss": 0.0682,
|
513 |
+
"step": 1800
|
514 |
+
},
|
515 |
+
{
|
516 |
+
"epoch": 10.46,
|
517 |
+
"grad_norm": 0.16026218235492706,
|
518 |
+
"learning_rate": 4.896449704142012e-05,
|
519 |
+
"loss": 0.0657,
|
520 |
+
"step": 1825
|
521 |
+
},
|
522 |
+
{
|
523 |
+
"epoch": 10.6,
|
524 |
+
"grad_norm": 0.17992612719535828,
|
525 |
+
"learning_rate": 4.822485207100592e-05,
|
526 |
+
"loss": 0.0648,
|
527 |
+
"step": 1850
|
528 |
+
},
|
529 |
+
{
|
530 |
+
"epoch": 10.74,
|
531 |
+
"grad_norm": 0.17420756816864014,
|
532 |
+
"learning_rate": 4.748520710059172e-05,
|
533 |
+
"loss": 0.0664,
|
534 |
+
"step": 1875
|
535 |
+
},
|
536 |
+
{
|
537 |
+
"epoch": 10.89,
|
538 |
+
"grad_norm": 0.14792782068252563,
|
539 |
+
"learning_rate": 4.674556213017752e-05,
|
540 |
+
"loss": 0.0668,
|
541 |
+
"step": 1900
|
542 |
+
}
|
543 |
+
],
|
544 |
+
"logging_steps": 25,
|
545 |
+
"max_steps": 3480,
|
546 |
+
"num_input_tokens_seen": 0,
|
547 |
+
"num_train_epochs": 20,
|
548 |
+
"save_steps": 100,
|
549 |
+
"total_flos": 1.371816806339666e+18,
|
550 |
+
"train_batch_size": 4,
|
551 |
+
"trial_name": null,
|
552 |
+
"trial_params": null
|
553 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bee6c4ac1bb5eee5c3ca89170029e67c25eed7c51ae10f0c764857ccec3d4ce9
|
3 |
+
size 4984
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|