Upload 12 files
Browse files- .gitattributes +1 -0
- README.md +202 -3
- adapter_config.json +32 -0
- adapter_model.safetensors +3 -0
- optimizer.pt +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +30 -0
- tokenizer.json +3 -0
- tokenizer.model +3 -0
- tokenizer_config.json +49 -0
- trainer_state.json +721 -0
- training_args.bin +3 -0
.gitattributes
CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
36 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
README.md
CHANGED
@@ -1,5 +1,204 @@
|
|
1 |
---
|
2 |
-
|
3 |
-
|
4 |
-
license_link: https://ai.google.dev/gemma/terms
|
5 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
---
|
2 |
+
library_name: peft
|
3 |
+
base_model: google/gemma-7b
|
|
|
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": "google/gemma-7b",
|
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": 8,
|
13 |
+
"lora_dropout": 0.0,
|
14 |
+
"megatron_config": null,
|
15 |
+
"megatron_core": "megatron.core",
|
16 |
+
"modules_to_save": null,
|
17 |
+
"peft_type": "LORA",
|
18 |
+
"r": 8,
|
19 |
+
"rank_pattern": {},
|
20 |
+
"revision": null,
|
21 |
+
"target_modules": [
|
22 |
+
"up_proj",
|
23 |
+
"k_proj",
|
24 |
+
"down_proj",
|
25 |
+
"q_proj",
|
26 |
+
"gate_proj",
|
27 |
+
"o_proj",
|
28 |
+
"v_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 sha256:739c690ef4eae43186cdf20b6d0b365f9f8aec9ff68e1eb1fc02757f7b36e64b
|
3 |
+
size 100059752
|
optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:35e33d06110cf53a299925654ed15d6eb64b743536c5bffb424426a2eb0ffd5a
|
3 |
+
size 50545780
|
rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a0e32a00d1dc583ddebb6ee0c3b9cb549aa96ce10f763167188e46f4b89e143b
|
3 |
+
size 14244
|
scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3a60c7d771c1fd156acee762fba03c724cb41829a3f71df370ecd1d20b134982
|
3 |
+
size 1064
|
special_tokens_map.json
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<bos>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": {
|
10 |
+
"content": "<eos>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": {
|
17 |
+
"content": "<pad>",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": false,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
},
|
23 |
+
"unk_token": {
|
24 |
+
"content": "<unk>",
|
25 |
+
"lstrip": false,
|
26 |
+
"normalized": false,
|
27 |
+
"rstrip": false,
|
28 |
+
"single_word": false
|
29 |
+
}
|
30 |
+
}
|
tokenizer.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d0d908b4f9326e0998815690e325b6abbd378978553e10627924dd825db7e243
|
3 |
+
size 17477553
|
tokenizer.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:61a7b147390c64585d6c3543dd6fc636906c9af3865a5548f27f31aee1d4c8e2
|
3 |
+
size 4241003
|
tokenizer_config.json
ADDED
@@ -0,0 +1,49 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": true,
|
3 |
+
"add_eos_token": false,
|
4 |
+
"added_tokens_decoder": {
|
5 |
+
"0": {
|
6 |
+
"content": "<pad>",
|
7 |
+
"lstrip": false,
|
8 |
+
"normalized": false,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false,
|
11 |
+
"special": true
|
12 |
+
},
|
13 |
+
"1": {
|
14 |
+
"content": "<eos>",
|
15 |
+
"lstrip": false,
|
16 |
+
"normalized": false,
|
17 |
+
"rstrip": false,
|
18 |
+
"single_word": false,
|
19 |
+
"special": true
|
20 |
+
},
|
21 |
+
"2": {
|
22 |
+
"content": "<bos>",
|
23 |
+
"lstrip": false,
|
24 |
+
"normalized": false,
|
25 |
+
"rstrip": false,
|
26 |
+
"single_word": false,
|
27 |
+
"special": true
|
28 |
+
},
|
29 |
+
"3": {
|
30 |
+
"content": "<unk>",
|
31 |
+
"lstrip": false,
|
32 |
+
"normalized": false,
|
33 |
+
"rstrip": false,
|
34 |
+
"single_word": false,
|
35 |
+
"special": true
|
36 |
+
}
|
37 |
+
},
|
38 |
+
"bos_token": "<bos>",
|
39 |
+
"clean_up_tokenization_spaces": false,
|
40 |
+
"eos_token": "<eos>",
|
41 |
+
"legacy": null,
|
42 |
+
"model_max_length": 1000000000000000019884624838656,
|
43 |
+
"pad_token": "<pad>",
|
44 |
+
"sp_model_kwargs": {},
|
45 |
+
"spaces_between_special_tokens": false,
|
46 |
+
"tokenizer_class": "GemmaTokenizer",
|
47 |
+
"unk_token": "<unk>",
|
48 |
+
"use_default_system_prompt": false
|
49 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,721 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 100.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 100,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 1.0,
|
13 |
+
"grad_norm": 2.4236936569213867,
|
14 |
+
"learning_rate": 0.0001,
|
15 |
+
"loss": 1.1597,
|
16 |
+
"step": 1
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 2.0,
|
20 |
+
"grad_norm": 2.4236936569213867,
|
21 |
+
"learning_rate": 0.0002,
|
22 |
+
"loss": 1.1597,
|
23 |
+
"step": 2
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 3.0,
|
27 |
+
"grad_norm": 1.3299813270568848,
|
28 |
+
"learning_rate": 0.00019795918367346938,
|
29 |
+
"loss": 0.9809,
|
30 |
+
"step": 3
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 4.0,
|
34 |
+
"grad_norm": 1.62615966796875,
|
35 |
+
"learning_rate": 0.0001959183673469388,
|
36 |
+
"loss": 0.7416,
|
37 |
+
"step": 4
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 5.0,
|
41 |
+
"grad_norm": 1.3189771175384521,
|
42 |
+
"learning_rate": 0.00019387755102040816,
|
43 |
+
"loss": 0.5219,
|
44 |
+
"step": 5
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 6.0,
|
48 |
+
"grad_norm": 1.062267780303955,
|
49 |
+
"learning_rate": 0.00019183673469387756,
|
50 |
+
"loss": 0.3376,
|
51 |
+
"step": 6
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 7.0,
|
55 |
+
"grad_norm": 0.7606938481330872,
|
56 |
+
"learning_rate": 0.00018979591836734697,
|
57 |
+
"loss": 0.1999,
|
58 |
+
"step": 7
|
59 |
+
},
|
60 |
+
{
|
61 |
+
"epoch": 8.0,
|
62 |
+
"grad_norm": 0.6657623648643494,
|
63 |
+
"learning_rate": 0.00018775510204081634,
|
64 |
+
"loss": 0.1314,
|
65 |
+
"step": 8
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 9.0,
|
69 |
+
"grad_norm": 0.4108690917491913,
|
70 |
+
"learning_rate": 0.00018571428571428572,
|
71 |
+
"loss": 0.087,
|
72 |
+
"step": 9
|
73 |
+
},
|
74 |
+
{
|
75 |
+
"epoch": 10.0,
|
76 |
+
"grad_norm": 0.25315290689468384,
|
77 |
+
"learning_rate": 0.00018367346938775512,
|
78 |
+
"loss": 0.0777,
|
79 |
+
"step": 10
|
80 |
+
},
|
81 |
+
{
|
82 |
+
"epoch": 11.0,
|
83 |
+
"grad_norm": 4.897407054901123,
|
84 |
+
"learning_rate": 0.0001816326530612245,
|
85 |
+
"loss": 0.087,
|
86 |
+
"step": 11
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 12.0,
|
90 |
+
"grad_norm": 0.3001738488674164,
|
91 |
+
"learning_rate": 0.0001795918367346939,
|
92 |
+
"loss": 0.0707,
|
93 |
+
"step": 12
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 13.0,
|
97 |
+
"grad_norm": 5.1508378982543945,
|
98 |
+
"learning_rate": 0.00017755102040816327,
|
99 |
+
"loss": 0.088,
|
100 |
+
"step": 13
|
101 |
+
},
|
102 |
+
{
|
103 |
+
"epoch": 14.0,
|
104 |
+
"grad_norm": 9.67592716217041,
|
105 |
+
"learning_rate": 0.00017551020408163265,
|
106 |
+
"loss": 0.0799,
|
107 |
+
"step": 14
|
108 |
+
},
|
109 |
+
{
|
110 |
+
"epoch": 15.0,
|
111 |
+
"grad_norm": 2.7876245975494385,
|
112 |
+
"learning_rate": 0.00017346938775510205,
|
113 |
+
"loss": 0.0967,
|
114 |
+
"step": 15
|
115 |
+
},
|
116 |
+
{
|
117 |
+
"epoch": 16.0,
|
118 |
+
"grad_norm": 1.8201392889022827,
|
119 |
+
"learning_rate": 0.00017142857142857143,
|
120 |
+
"loss": 0.0601,
|
121 |
+
"step": 16
|
122 |
+
},
|
123 |
+
{
|
124 |
+
"epoch": 17.0,
|
125 |
+
"grad_norm": 1.6338967084884644,
|
126 |
+
"learning_rate": 0.00016938775510204083,
|
127 |
+
"loss": 0.0512,
|
128 |
+
"step": 17
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 18.0,
|
132 |
+
"grad_norm": 0.4770618975162506,
|
133 |
+
"learning_rate": 0.00016734693877551023,
|
134 |
+
"loss": 0.0373,
|
135 |
+
"step": 18
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 19.0,
|
139 |
+
"grad_norm": 0.458904504776001,
|
140 |
+
"learning_rate": 0.0001653061224489796,
|
141 |
+
"loss": 0.0279,
|
142 |
+
"step": 19
|
143 |
+
},
|
144 |
+
{
|
145 |
+
"epoch": 20.0,
|
146 |
+
"grad_norm": 1.6127618551254272,
|
147 |
+
"learning_rate": 0.00016326530612244898,
|
148 |
+
"loss": 0.023,
|
149 |
+
"step": 20
|
150 |
+
},
|
151 |
+
{
|
152 |
+
"epoch": 21.0,
|
153 |
+
"grad_norm": 1.090635895729065,
|
154 |
+
"learning_rate": 0.00016122448979591838,
|
155 |
+
"loss": 0.0105,
|
156 |
+
"step": 21
|
157 |
+
},
|
158 |
+
{
|
159 |
+
"epoch": 22.0,
|
160 |
+
"grad_norm": 0.08737627416849136,
|
161 |
+
"learning_rate": 0.00015918367346938776,
|
162 |
+
"loss": 0.0061,
|
163 |
+
"step": 22
|
164 |
+
},
|
165 |
+
{
|
166 |
+
"epoch": 23.0,
|
167 |
+
"grad_norm": 0.08030153065919876,
|
168 |
+
"learning_rate": 0.00015714285714285716,
|
169 |
+
"loss": 0.0051,
|
170 |
+
"step": 23
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 24.0,
|
174 |
+
"grad_norm": 0.04834992438554764,
|
175 |
+
"learning_rate": 0.00015510204081632654,
|
176 |
+
"loss": 0.0048,
|
177 |
+
"step": 24
|
178 |
+
},
|
179 |
+
{
|
180 |
+
"epoch": 25.0,
|
181 |
+
"grad_norm": 0.09552427381277084,
|
182 |
+
"learning_rate": 0.0001530612244897959,
|
183 |
+
"loss": 0.0048,
|
184 |
+
"step": 25
|
185 |
+
},
|
186 |
+
{
|
187 |
+
"epoch": 26.0,
|
188 |
+
"grad_norm": 0.0460357591509819,
|
189 |
+
"learning_rate": 0.0001510204081632653,
|
190 |
+
"loss": 0.0046,
|
191 |
+
"step": 26
|
192 |
+
},
|
193 |
+
{
|
194 |
+
"epoch": 27.0,
|
195 |
+
"grad_norm": 0.0992983803153038,
|
196 |
+
"learning_rate": 0.00014897959183673472,
|
197 |
+
"loss": 0.0047,
|
198 |
+
"step": 27
|
199 |
+
},
|
200 |
+
{
|
201 |
+
"epoch": 28.0,
|
202 |
+
"grad_norm": 0.1185307577252388,
|
203 |
+
"learning_rate": 0.0001469387755102041,
|
204 |
+
"loss": 0.0048,
|
205 |
+
"step": 28
|
206 |
+
},
|
207 |
+
{
|
208 |
+
"epoch": 29.0,
|
209 |
+
"grad_norm": 0.14356577396392822,
|
210 |
+
"learning_rate": 0.0001448979591836735,
|
211 |
+
"loss": 0.0049,
|
212 |
+
"step": 29
|
213 |
+
},
|
214 |
+
{
|
215 |
+
"epoch": 30.0,
|
216 |
+
"grad_norm": 0.0876593366265297,
|
217 |
+
"learning_rate": 0.00014285714285714287,
|
218 |
+
"loss": 0.0046,
|
219 |
+
"step": 30
|
220 |
+
},
|
221 |
+
{
|
222 |
+
"epoch": 31.0,
|
223 |
+
"grad_norm": 0.08368655294179916,
|
224 |
+
"learning_rate": 0.00014081632653061224,
|
225 |
+
"loss": 0.0047,
|
226 |
+
"step": 31
|
227 |
+
},
|
228 |
+
{
|
229 |
+
"epoch": 32.0,
|
230 |
+
"grad_norm": 0.042614325881004333,
|
231 |
+
"learning_rate": 0.00013877551020408165,
|
232 |
+
"loss": 0.0045,
|
233 |
+
"step": 32
|
234 |
+
},
|
235 |
+
{
|
236 |
+
"epoch": 33.0,
|
237 |
+
"grad_norm": 0.00863147247582674,
|
238 |
+
"learning_rate": 0.00013673469387755102,
|
239 |
+
"loss": 0.0044,
|
240 |
+
"step": 33
|
241 |
+
},
|
242 |
+
{
|
243 |
+
"epoch": 34.0,
|
244 |
+
"grad_norm": 0.0089035639539361,
|
245 |
+
"learning_rate": 0.0001346938775510204,
|
246 |
+
"loss": 0.0044,
|
247 |
+
"step": 34
|
248 |
+
},
|
249 |
+
{
|
250 |
+
"epoch": 35.0,
|
251 |
+
"grad_norm": 0.03151445463299751,
|
252 |
+
"learning_rate": 0.0001326530612244898,
|
253 |
+
"loss": 0.0044,
|
254 |
+
"step": 35
|
255 |
+
},
|
256 |
+
{
|
257 |
+
"epoch": 36.0,
|
258 |
+
"grad_norm": 0.0310219656676054,
|
259 |
+
"learning_rate": 0.00013061224489795917,
|
260 |
+
"loss": 0.0044,
|
261 |
+
"step": 36
|
262 |
+
},
|
263 |
+
{
|
264 |
+
"epoch": 37.0,
|
265 |
+
"grad_norm": 0.030537990853190422,
|
266 |
+
"learning_rate": 0.00012857142857142858,
|
267 |
+
"loss": 0.0044,
|
268 |
+
"step": 37
|
269 |
+
},
|
270 |
+
{
|
271 |
+
"epoch": 38.0,
|
272 |
+
"grad_norm": 0.03915323689579964,
|
273 |
+
"learning_rate": 0.00012653061224489798,
|
274 |
+
"loss": 0.0044,
|
275 |
+
"step": 38
|
276 |
+
},
|
277 |
+
{
|
278 |
+
"epoch": 39.0,
|
279 |
+
"grad_norm": 0.038823168724775314,
|
280 |
+
"learning_rate": 0.00012448979591836735,
|
281 |
+
"loss": 0.0044,
|
282 |
+
"step": 39
|
283 |
+
},
|
284 |
+
{
|
285 |
+
"epoch": 40.0,
|
286 |
+
"grad_norm": 0.005813094321638346,
|
287 |
+
"learning_rate": 0.00012244897959183676,
|
288 |
+
"loss": 0.0044,
|
289 |
+
"step": 40
|
290 |
+
},
|
291 |
+
{
|
292 |
+
"epoch": 41.0,
|
293 |
+
"grad_norm": 0.02931728959083557,
|
294 |
+
"learning_rate": 0.00012040816326530613,
|
295 |
+
"loss": 0.0044,
|
296 |
+
"step": 41
|
297 |
+
},
|
298 |
+
{
|
299 |
+
"epoch": 42.0,
|
300 |
+
"grad_norm": 0.02919776178896427,
|
301 |
+
"learning_rate": 0.00011836734693877552,
|
302 |
+
"loss": 0.0044,
|
303 |
+
"step": 42
|
304 |
+
},
|
305 |
+
{
|
306 |
+
"epoch": 43.0,
|
307 |
+
"grad_norm": 0.005404920782893896,
|
308 |
+
"learning_rate": 0.0001163265306122449,
|
309 |
+
"loss": 0.0044,
|
310 |
+
"step": 43
|
311 |
+
},
|
312 |
+
{
|
313 |
+
"epoch": 44.0,
|
314 |
+
"grad_norm": 0.03844524547457695,
|
315 |
+
"learning_rate": 0.00011428571428571428,
|
316 |
+
"loss": 0.0044,
|
317 |
+
"step": 44
|
318 |
+
},
|
319 |
+
{
|
320 |
+
"epoch": 45.0,
|
321 |
+
"grad_norm": 0.005866413004696369,
|
322 |
+
"learning_rate": 0.00011224489795918367,
|
323 |
+
"loss": 0.0043,
|
324 |
+
"step": 45
|
325 |
+
},
|
326 |
+
{
|
327 |
+
"epoch": 46.0,
|
328 |
+
"grad_norm": 0.028769973665475845,
|
329 |
+
"learning_rate": 0.00011020408163265306,
|
330 |
+
"loss": 0.0044,
|
331 |
+
"step": 46
|
332 |
+
},
|
333 |
+
{
|
334 |
+
"epoch": 47.0,
|
335 |
+
"grad_norm": 0.028779389336705208,
|
336 |
+
"learning_rate": 0.00010816326530612246,
|
337 |
+
"loss": 0.0044,
|
338 |
+
"step": 47
|
339 |
+
},
|
340 |
+
{
|
341 |
+
"epoch": 48.0,
|
342 |
+
"grad_norm": 0.006406720262020826,
|
343 |
+
"learning_rate": 0.00010612244897959185,
|
344 |
+
"loss": 0.0043,
|
345 |
+
"step": 48
|
346 |
+
},
|
347 |
+
{
|
348 |
+
"epoch": 49.0,
|
349 |
+
"grad_norm": 0.03870103508234024,
|
350 |
+
"learning_rate": 0.00010408163265306123,
|
351 |
+
"loss": 0.0044,
|
352 |
+
"step": 49
|
353 |
+
},
|
354 |
+
{
|
355 |
+
"epoch": 50.0,
|
356 |
+
"grad_norm": 0.038732465356588364,
|
357 |
+
"learning_rate": 0.00010204081632653062,
|
358 |
+
"loss": 0.0044,
|
359 |
+
"step": 50
|
360 |
+
},
|
361 |
+
{
|
362 |
+
"epoch": 51.0,
|
363 |
+
"grad_norm": 0.00536749605089426,
|
364 |
+
"learning_rate": 0.0001,
|
365 |
+
"loss": 0.0043,
|
366 |
+
"step": 51
|
367 |
+
},
|
368 |
+
{
|
369 |
+
"epoch": 52.0,
|
370 |
+
"grad_norm": 0.028795704245567322,
|
371 |
+
"learning_rate": 9.79591836734694e-05,
|
372 |
+
"loss": 0.0044,
|
373 |
+
"step": 52
|
374 |
+
},
|
375 |
+
{
|
376 |
+
"epoch": 53.0,
|
377 |
+
"grad_norm": 0.02882838249206543,
|
378 |
+
"learning_rate": 9.591836734693878e-05,
|
379 |
+
"loss": 0.0044,
|
380 |
+
"step": 53
|
381 |
+
},
|
382 |
+
{
|
383 |
+
"epoch": 54.0,
|
384 |
+
"grad_norm": 0.02882484346628189,
|
385 |
+
"learning_rate": 9.387755102040817e-05,
|
386 |
+
"loss": 0.0044,
|
387 |
+
"step": 54
|
388 |
+
},
|
389 |
+
{
|
390 |
+
"epoch": 55.0,
|
391 |
+
"grad_norm": 0.00502988463267684,
|
392 |
+
"learning_rate": 9.183673469387756e-05,
|
393 |
+
"loss": 0.0043,
|
394 |
+
"step": 55
|
395 |
+
},
|
396 |
+
{
|
397 |
+
"epoch": 56.0,
|
398 |
+
"grad_norm": 0.005017813295125961,
|
399 |
+
"learning_rate": 8.979591836734695e-05,
|
400 |
+
"loss": 0.0043,
|
401 |
+
"step": 56
|
402 |
+
},
|
403 |
+
{
|
404 |
+
"epoch": 57.0,
|
405 |
+
"grad_norm": 0.005218982230871916,
|
406 |
+
"learning_rate": 8.775510204081632e-05,
|
407 |
+
"loss": 0.0043,
|
408 |
+
"step": 57
|
409 |
+
},
|
410 |
+
{
|
411 |
+
"epoch": 58.0,
|
412 |
+
"grad_norm": 0.038150474429130554,
|
413 |
+
"learning_rate": 8.571428571428571e-05,
|
414 |
+
"loss": 0.0044,
|
415 |
+
"step": 58
|
416 |
+
},
|
417 |
+
{
|
418 |
+
"epoch": 59.0,
|
419 |
+
"grad_norm": 0.03801121190190315,
|
420 |
+
"learning_rate": 8.367346938775511e-05,
|
421 |
+
"loss": 0.0044,
|
422 |
+
"step": 59
|
423 |
+
},
|
424 |
+
{
|
425 |
+
"epoch": 60.0,
|
426 |
+
"grad_norm": 0.004977047443389893,
|
427 |
+
"learning_rate": 8.163265306122449e-05,
|
428 |
+
"loss": 0.0043,
|
429 |
+
"step": 60
|
430 |
+
},
|
431 |
+
{
|
432 |
+
"epoch": 61.0,
|
433 |
+
"grad_norm": 0.0602005235850811,
|
434 |
+
"learning_rate": 7.959183673469388e-05,
|
435 |
+
"loss": 0.0045,
|
436 |
+
"step": 61
|
437 |
+
},
|
438 |
+
{
|
439 |
+
"epoch": 62.0,
|
440 |
+
"grad_norm": 0.0284713264554739,
|
441 |
+
"learning_rate": 7.755102040816327e-05,
|
442 |
+
"loss": 0.0044,
|
443 |
+
"step": 62
|
444 |
+
},
|
445 |
+
{
|
446 |
+
"epoch": 63.0,
|
447 |
+
"grad_norm": 0.004900462459772825,
|
448 |
+
"learning_rate": 7.551020408163266e-05,
|
449 |
+
"loss": 0.0043,
|
450 |
+
"step": 63
|
451 |
+
},
|
452 |
+
{
|
453 |
+
"epoch": 64.0,
|
454 |
+
"grad_norm": 0.0048695337027311325,
|
455 |
+
"learning_rate": 7.346938775510205e-05,
|
456 |
+
"loss": 0.0043,
|
457 |
+
"step": 64
|
458 |
+
},
|
459 |
+
{
|
460 |
+
"epoch": 65.0,
|
461 |
+
"grad_norm": 0.004841310903429985,
|
462 |
+
"learning_rate": 7.142857142857143e-05,
|
463 |
+
"loss": 0.0043,
|
464 |
+
"step": 65
|
465 |
+
},
|
466 |
+
{
|
467 |
+
"epoch": 66.0,
|
468 |
+
"grad_norm": 0.004835947882384062,
|
469 |
+
"learning_rate": 6.938775510204082e-05,
|
470 |
+
"loss": 0.0043,
|
471 |
+
"step": 66
|
472 |
+
},
|
473 |
+
{
|
474 |
+
"epoch": 67.0,
|
475 |
+
"grad_norm": 0.03715803846716881,
|
476 |
+
"learning_rate": 6.73469387755102e-05,
|
477 |
+
"loss": 0.0044,
|
478 |
+
"step": 67
|
479 |
+
},
|
480 |
+
{
|
481 |
+
"epoch": 68.0,
|
482 |
+
"grad_norm": 0.004820631351321936,
|
483 |
+
"learning_rate": 6.530612244897959e-05,
|
484 |
+
"loss": 0.0043,
|
485 |
+
"step": 68
|
486 |
+
},
|
487 |
+
{
|
488 |
+
"epoch": 69.0,
|
489 |
+
"grad_norm": 0.004830862861126661,
|
490 |
+
"learning_rate": 6.326530612244899e-05,
|
491 |
+
"loss": 0.0043,
|
492 |
+
"step": 69
|
493 |
+
},
|
494 |
+
{
|
495 |
+
"epoch": 70.0,
|
496 |
+
"grad_norm": 0.02773592434823513,
|
497 |
+
"learning_rate": 6.122448979591838e-05,
|
498 |
+
"loss": 0.0044,
|
499 |
+
"step": 70
|
500 |
+
},
|
501 |
+
{
|
502 |
+
"epoch": 71.0,
|
503 |
+
"grad_norm": 0.02766617201268673,
|
504 |
+
"learning_rate": 5.918367346938776e-05,
|
505 |
+
"loss": 0.0044,
|
506 |
+
"step": 71
|
507 |
+
},
|
508 |
+
{
|
509 |
+
"epoch": 72.0,
|
510 |
+
"grad_norm": 0.027592068538069725,
|
511 |
+
"learning_rate": 5.714285714285714e-05,
|
512 |
+
"loss": 0.0044,
|
513 |
+
"step": 72
|
514 |
+
},
|
515 |
+
{
|
516 |
+
"epoch": 73.0,
|
517 |
+
"grad_norm": 0.004762730095535517,
|
518 |
+
"learning_rate": 5.510204081632653e-05,
|
519 |
+
"loss": 0.0043,
|
520 |
+
"step": 73
|
521 |
+
},
|
522 |
+
{
|
523 |
+
"epoch": 74.0,
|
524 |
+
"grad_norm": 0.004771250765770674,
|
525 |
+
"learning_rate": 5.3061224489795926e-05,
|
526 |
+
"loss": 0.0043,
|
527 |
+
"step": 74
|
528 |
+
},
|
529 |
+
{
|
530 |
+
"epoch": 75.0,
|
531 |
+
"grad_norm": 0.004748388193547726,
|
532 |
+
"learning_rate": 5.102040816326531e-05,
|
533 |
+
"loss": 0.0043,
|
534 |
+
"step": 75
|
535 |
+
},
|
536 |
+
{
|
537 |
+
"epoch": 76.0,
|
538 |
+
"grad_norm": 0.03664989769458771,
|
539 |
+
"learning_rate": 4.89795918367347e-05,
|
540 |
+
"loss": 0.0044,
|
541 |
+
"step": 76
|
542 |
+
},
|
543 |
+
{
|
544 |
+
"epoch": 77.0,
|
545 |
+
"grad_norm": 0.004758178256452084,
|
546 |
+
"learning_rate": 4.6938775510204086e-05,
|
547 |
+
"loss": 0.0043,
|
548 |
+
"step": 77
|
549 |
+
},
|
550 |
+
{
|
551 |
+
"epoch": 78.0,
|
552 |
+
"grad_norm": 0.03650437667965889,
|
553 |
+
"learning_rate": 4.4897959183673474e-05,
|
554 |
+
"loss": 0.0044,
|
555 |
+
"step": 78
|
556 |
+
},
|
557 |
+
{
|
558 |
+
"epoch": 79.0,
|
559 |
+
"grad_norm": 0.004723742604255676,
|
560 |
+
"learning_rate": 4.2857142857142856e-05,
|
561 |
+
"loss": 0.0043,
|
562 |
+
"step": 79
|
563 |
+
},
|
564 |
+
{
|
565 |
+
"epoch": 80.0,
|
566 |
+
"grad_norm": 0.027179496362805367,
|
567 |
+
"learning_rate": 4.0816326530612245e-05,
|
568 |
+
"loss": 0.0044,
|
569 |
+
"step": 80
|
570 |
+
},
|
571 |
+
{
|
572 |
+
"epoch": 81.0,
|
573 |
+
"grad_norm": 0.027180835604667664,
|
574 |
+
"learning_rate": 3.8775510204081634e-05,
|
575 |
+
"loss": 0.0044,
|
576 |
+
"step": 81
|
577 |
+
},
|
578 |
+
{
|
579 |
+
"epoch": 82.0,
|
580 |
+
"grad_norm": 0.027134299278259277,
|
581 |
+
"learning_rate": 3.673469387755102e-05,
|
582 |
+
"loss": 0.0044,
|
583 |
+
"step": 82
|
584 |
+
},
|
585 |
+
{
|
586 |
+
"epoch": 83.0,
|
587 |
+
"grad_norm": 0.027070023119449615,
|
588 |
+
"learning_rate": 3.469387755102041e-05,
|
589 |
+
"loss": 0.0044,
|
590 |
+
"step": 83
|
591 |
+
},
|
592 |
+
{
|
593 |
+
"epoch": 84.0,
|
594 |
+
"grad_norm": 0.004842973779886961,
|
595 |
+
"learning_rate": 3.265306122448979e-05,
|
596 |
+
"loss": 0.0043,
|
597 |
+
"step": 84
|
598 |
+
},
|
599 |
+
{
|
600 |
+
"epoch": 85.0,
|
601 |
+
"grad_norm": 0.004742528777569532,
|
602 |
+
"learning_rate": 3.061224489795919e-05,
|
603 |
+
"loss": 0.0043,
|
604 |
+
"step": 85
|
605 |
+
},
|
606 |
+
{
|
607 |
+
"epoch": 86.0,
|
608 |
+
"grad_norm": 0.004724172409623861,
|
609 |
+
"learning_rate": 2.857142857142857e-05,
|
610 |
+
"loss": 0.0043,
|
611 |
+
"step": 86
|
612 |
+
},
|
613 |
+
{
|
614 |
+
"epoch": 87.0,
|
615 |
+
"grad_norm": 0.03628339245915413,
|
616 |
+
"learning_rate": 2.6530612244897963e-05,
|
617 |
+
"loss": 0.0044,
|
618 |
+
"step": 87
|
619 |
+
},
|
620 |
+
{
|
621 |
+
"epoch": 88.0,
|
622 |
+
"grad_norm": 0.036234479397535324,
|
623 |
+
"learning_rate": 2.448979591836735e-05,
|
624 |
+
"loss": 0.0044,
|
625 |
+
"step": 88
|
626 |
+
},
|
627 |
+
{
|
628 |
+
"epoch": 89.0,
|
629 |
+
"grad_norm": 0.004697797354310751,
|
630 |
+
"learning_rate": 2.2448979591836737e-05,
|
631 |
+
"loss": 0.0043,
|
632 |
+
"step": 89
|
633 |
+
},
|
634 |
+
{
|
635 |
+
"epoch": 90.0,
|
636 |
+
"grad_norm": 0.004719586111605167,
|
637 |
+
"learning_rate": 2.0408163265306123e-05,
|
638 |
+
"loss": 0.0043,
|
639 |
+
"step": 90
|
640 |
+
},
|
641 |
+
{
|
642 |
+
"epoch": 91.0,
|
643 |
+
"grad_norm": 0.004701649770140648,
|
644 |
+
"learning_rate": 1.836734693877551e-05,
|
645 |
+
"loss": 0.0043,
|
646 |
+
"step": 91
|
647 |
+
},
|
648 |
+
{
|
649 |
+
"epoch": 92.0,
|
650 |
+
"grad_norm": 0.026852702721953392,
|
651 |
+
"learning_rate": 1.6326530612244897e-05,
|
652 |
+
"loss": 0.0044,
|
653 |
+
"step": 92
|
654 |
+
},
|
655 |
+
{
|
656 |
+
"epoch": 93.0,
|
657 |
+
"grad_norm": 0.02685590460896492,
|
658 |
+
"learning_rate": 1.4285714285714285e-05,
|
659 |
+
"loss": 0.0044,
|
660 |
+
"step": 93
|
661 |
+
},
|
662 |
+
{
|
663 |
+
"epoch": 94.0,
|
664 |
+
"grad_norm": 0.0047478387132287025,
|
665 |
+
"learning_rate": 1.2244897959183674e-05,
|
666 |
+
"loss": 0.0043,
|
667 |
+
"step": 94
|
668 |
+
},
|
669 |
+
{
|
670 |
+
"epoch": 95.0,
|
671 |
+
"grad_norm": 0.026850329712033272,
|
672 |
+
"learning_rate": 1.0204081632653061e-05,
|
673 |
+
"loss": 0.0044,
|
674 |
+
"step": 95
|
675 |
+
},
|
676 |
+
{
|
677 |
+
"epoch": 96.0,
|
678 |
+
"grad_norm": 0.00475778803229332,
|
679 |
+
"learning_rate": 8.163265306122448e-06,
|
680 |
+
"loss": 0.0043,
|
681 |
+
"step": 96
|
682 |
+
},
|
683 |
+
{
|
684 |
+
"epoch": 97.0,
|
685 |
+
"grad_norm": 0.004756512586027384,
|
686 |
+
"learning_rate": 6.122448979591837e-06,
|
687 |
+
"loss": 0.0043,
|
688 |
+
"step": 97
|
689 |
+
},
|
690 |
+
{
|
691 |
+
"epoch": 98.0,
|
692 |
+
"grad_norm": 0.004749584477394819,
|
693 |
+
"learning_rate": 4.081632653061224e-06,
|
694 |
+
"loss": 0.0043,
|
695 |
+
"step": 98
|
696 |
+
},
|
697 |
+
{
|
698 |
+
"epoch": 99.0,
|
699 |
+
"grad_norm": 0.004759279545396566,
|
700 |
+
"learning_rate": 2.040816326530612e-06,
|
701 |
+
"loss": 0.0043,
|
702 |
+
"step": 99
|
703 |
+
},
|
704 |
+
{
|
705 |
+
"epoch": 100.0,
|
706 |
+
"grad_norm": 0.004726547747850418,
|
707 |
+
"learning_rate": 0.0,
|
708 |
+
"loss": 0.0043,
|
709 |
+
"step": 100
|
710 |
+
}
|
711 |
+
],
|
712 |
+
"logging_steps": 1,
|
713 |
+
"max_steps": 100,
|
714 |
+
"num_input_tokens_seen": 0,
|
715 |
+
"num_train_epochs": 100,
|
716 |
+
"save_steps": 500,
|
717 |
+
"total_flos": 760517336064000.0,
|
718 |
+
"train_batch_size": 1,
|
719 |
+
"trial_name": null,
|
720 |
+
"trial_params": null
|
721 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:700afa88f3f25a9108feb30e33c64c29aca41d329b79f230609b2023fa359c16
|
3 |
+
size 4984
|