Add checkpoint-4992
Browse files- .gitattributes +1 -0
- README.md +202 -0
- adapter_config.json +37 -0
- adapter_model.safetensors +3 -0
- added_tokens.json +24 -0
- merges.txt +0 -0
- optimizer.pt +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +31 -0
- tokenizer.json +3 -0
- tokenizer_config.json +209 -0
- trainer_state.json +3534 -0
- training_args.bin +3 -0
- vocab.json +0 -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
ADDED
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
base_model: Qwen/Qwen2.5-7B-Instruct
|
3 |
+
library_name: peft
|
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 0.14.0
|
adapter_config.json
ADDED
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "Qwen/Qwen2.5-7B-Instruct",
|
5 |
+
"bias": "none",
|
6 |
+
"eva_config": null,
|
7 |
+
"exclude_modules": null,
|
8 |
+
"fan_in_fan_out": false,
|
9 |
+
"inference_mode": true,
|
10 |
+
"init_lora_weights": true,
|
11 |
+
"layer_replication": null,
|
12 |
+
"layers_pattern": null,
|
13 |
+
"layers_to_transform": null,
|
14 |
+
"loftq_config": {},
|
15 |
+
"lora_alpha": 128,
|
16 |
+
"lora_bias": false,
|
17 |
+
"lora_dropout": 0,
|
18 |
+
"megatron_config": null,
|
19 |
+
"megatron_core": "megatron.core",
|
20 |
+
"modules_to_save": null,
|
21 |
+
"peft_type": "LORA",
|
22 |
+
"r": 32,
|
23 |
+
"rank_pattern": {},
|
24 |
+
"revision": null,
|
25 |
+
"target_modules": [
|
26 |
+
"down_proj",
|
27 |
+
"k_proj",
|
28 |
+
"gate_proj",
|
29 |
+
"up_proj",
|
30 |
+
"o_proj",
|
31 |
+
"q_proj",
|
32 |
+
"v_proj"
|
33 |
+
],
|
34 |
+
"task_type": "CAUSAL_LM",
|
35 |
+
"use_dora": false,
|
36 |
+
"use_rslora": false
|
37 |
+
}
|
adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:230b39b066ea45e7876ded0009fe17a1bac25106b0d9de6d850422b30187c23d
|
3 |
+
size 323014168
|
added_tokens.json
ADDED
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"</tool_call>": 151658,
|
3 |
+
"<tool_call>": 151657,
|
4 |
+
"<|box_end|>": 151649,
|
5 |
+
"<|box_start|>": 151648,
|
6 |
+
"<|endoftext|>": 151643,
|
7 |
+
"<|file_sep|>": 151664,
|
8 |
+
"<|fim_middle|>": 151660,
|
9 |
+
"<|fim_pad|>": 151662,
|
10 |
+
"<|fim_prefix|>": 151659,
|
11 |
+
"<|fim_suffix|>": 151661,
|
12 |
+
"<|im_end|>": 151645,
|
13 |
+
"<|im_start|>": 151644,
|
14 |
+
"<|image_pad|>": 151655,
|
15 |
+
"<|object_ref_end|>": 151647,
|
16 |
+
"<|object_ref_start|>": 151646,
|
17 |
+
"<|quad_end|>": 151651,
|
18 |
+
"<|quad_start|>": 151650,
|
19 |
+
"<|repo_name|>": 151663,
|
20 |
+
"<|video_pad|>": 151656,
|
21 |
+
"<|vision_end|>": 151653,
|
22 |
+
"<|vision_pad|>": 151654,
|
23 |
+
"<|vision_start|>": 151652
|
24 |
+
}
|
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:b9d393c4922ebce2252cbabde985e73bc4be0480543929a6fe3f280f239274a6
|
3 |
+
size 646253418
|
rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3d7ecf15e83ac4d18e0d90f8a44821af2f304313a6ae05eeb21767226a79c463
|
3 |
+
size 14244
|
scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ccfbf1d4519279d8a43fa386541f90b04b01234a7aad50160487aa37a1971872
|
3 |
+
size 1064
|
special_tokens_map.json
ADDED
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"<|im_start|>",
|
4 |
+
"<|im_end|>",
|
5 |
+
"<|object_ref_start|>",
|
6 |
+
"<|object_ref_end|>",
|
7 |
+
"<|box_start|>",
|
8 |
+
"<|box_end|>",
|
9 |
+
"<|quad_start|>",
|
10 |
+
"<|quad_end|>",
|
11 |
+
"<|vision_start|>",
|
12 |
+
"<|vision_end|>",
|
13 |
+
"<|vision_pad|>",
|
14 |
+
"<|image_pad|>",
|
15 |
+
"<|video_pad|>"
|
16 |
+
],
|
17 |
+
"eos_token": {
|
18 |
+
"content": "<|im_end|>",
|
19 |
+
"lstrip": false,
|
20 |
+
"normalized": false,
|
21 |
+
"rstrip": false,
|
22 |
+
"single_word": false
|
23 |
+
},
|
24 |
+
"pad_token": {
|
25 |
+
"content": "<|endoftext|>",
|
26 |
+
"lstrip": false,
|
27 |
+
"normalized": false,
|
28 |
+
"rstrip": false,
|
29 |
+
"single_word": false
|
30 |
+
}
|
31 |
+
}
|
tokenizer.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
|
3 |
+
size 11421896
|
tokenizer_config.json
ADDED
@@ -0,0 +1,209 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": false,
|
3 |
+
"add_prefix_space": false,
|
4 |
+
"added_tokens_decoder": {
|
5 |
+
"151643": {
|
6 |
+
"content": "<|endoftext|>",
|
7 |
+
"lstrip": false,
|
8 |
+
"normalized": false,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false,
|
11 |
+
"special": true
|
12 |
+
},
|
13 |
+
"151644": {
|
14 |
+
"content": "<|im_start|>",
|
15 |
+
"lstrip": false,
|
16 |
+
"normalized": false,
|
17 |
+
"rstrip": false,
|
18 |
+
"single_word": false,
|
19 |
+
"special": true
|
20 |
+
},
|
21 |
+
"151645": {
|
22 |
+
"content": "<|im_end|>",
|
23 |
+
"lstrip": false,
|
24 |
+
"normalized": false,
|
25 |
+
"rstrip": false,
|
26 |
+
"single_word": false,
|
27 |
+
"special": true
|
28 |
+
},
|
29 |
+
"151646": {
|
30 |
+
"content": "<|object_ref_start|>",
|
31 |
+
"lstrip": false,
|
32 |
+
"normalized": false,
|
33 |
+
"rstrip": false,
|
34 |
+
"single_word": false,
|
35 |
+
"special": true
|
36 |
+
},
|
37 |
+
"151647": {
|
38 |
+
"content": "<|object_ref_end|>",
|
39 |
+
"lstrip": false,
|
40 |
+
"normalized": false,
|
41 |
+
"rstrip": false,
|
42 |
+
"single_word": false,
|
43 |
+
"special": true
|
44 |
+
},
|
45 |
+
"151648": {
|
46 |
+
"content": "<|box_start|>",
|
47 |
+
"lstrip": false,
|
48 |
+
"normalized": false,
|
49 |
+
"rstrip": false,
|
50 |
+
"single_word": false,
|
51 |
+
"special": true
|
52 |
+
},
|
53 |
+
"151649": {
|
54 |
+
"content": "<|box_end|>",
|
55 |
+
"lstrip": false,
|
56 |
+
"normalized": false,
|
57 |
+
"rstrip": false,
|
58 |
+
"single_word": false,
|
59 |
+
"special": true
|
60 |
+
},
|
61 |
+
"151650": {
|
62 |
+
"content": "<|quad_start|>",
|
63 |
+
"lstrip": false,
|
64 |
+
"normalized": false,
|
65 |
+
"rstrip": false,
|
66 |
+
"single_word": false,
|
67 |
+
"special": true
|
68 |
+
},
|
69 |
+
"151651": {
|
70 |
+
"content": "<|quad_end|>",
|
71 |
+
"lstrip": false,
|
72 |
+
"normalized": false,
|
73 |
+
"rstrip": false,
|
74 |
+
"single_word": false,
|
75 |
+
"special": true
|
76 |
+
},
|
77 |
+
"151652": {
|
78 |
+
"content": "<|vision_start|>",
|
79 |
+
"lstrip": false,
|
80 |
+
"normalized": false,
|
81 |
+
"rstrip": false,
|
82 |
+
"single_word": false,
|
83 |
+
"special": true
|
84 |
+
},
|
85 |
+
"151653": {
|
86 |
+
"content": "<|vision_end|>",
|
87 |
+
"lstrip": false,
|
88 |
+
"normalized": false,
|
89 |
+
"rstrip": false,
|
90 |
+
"single_word": false,
|
91 |
+
"special": true
|
92 |
+
},
|
93 |
+
"151654": {
|
94 |
+
"content": "<|vision_pad|>",
|
95 |
+
"lstrip": false,
|
96 |
+
"normalized": false,
|
97 |
+
"rstrip": false,
|
98 |
+
"single_word": false,
|
99 |
+
"special": true
|
100 |
+
},
|
101 |
+
"151655": {
|
102 |
+
"content": "<|image_pad|>",
|
103 |
+
"lstrip": false,
|
104 |
+
"normalized": false,
|
105 |
+
"rstrip": false,
|
106 |
+
"single_word": false,
|
107 |
+
"special": true
|
108 |
+
},
|
109 |
+
"151656": {
|
110 |
+
"content": "<|video_pad|>",
|
111 |
+
"lstrip": false,
|
112 |
+
"normalized": false,
|
113 |
+
"rstrip": false,
|
114 |
+
"single_word": false,
|
115 |
+
"special": true
|
116 |
+
},
|
117 |
+
"151657": {
|
118 |
+
"content": "<tool_call>",
|
119 |
+
"lstrip": false,
|
120 |
+
"normalized": false,
|
121 |
+
"rstrip": false,
|
122 |
+
"single_word": false,
|
123 |
+
"special": false
|
124 |
+
},
|
125 |
+
"151658": {
|
126 |
+
"content": "</tool_call>",
|
127 |
+
"lstrip": false,
|
128 |
+
"normalized": false,
|
129 |
+
"rstrip": false,
|
130 |
+
"single_word": false,
|
131 |
+
"special": false
|
132 |
+
},
|
133 |
+
"151659": {
|
134 |
+
"content": "<|fim_prefix|>",
|
135 |
+
"lstrip": false,
|
136 |
+
"normalized": false,
|
137 |
+
"rstrip": false,
|
138 |
+
"single_word": false,
|
139 |
+
"special": false
|
140 |
+
},
|
141 |
+
"151660": {
|
142 |
+
"content": "<|fim_middle|>",
|
143 |
+
"lstrip": false,
|
144 |
+
"normalized": false,
|
145 |
+
"rstrip": false,
|
146 |
+
"single_word": false,
|
147 |
+
"special": false
|
148 |
+
},
|
149 |
+
"151661": {
|
150 |
+
"content": "<|fim_suffix|>",
|
151 |
+
"lstrip": false,
|
152 |
+
"normalized": false,
|
153 |
+
"rstrip": false,
|
154 |
+
"single_word": false,
|
155 |
+
"special": false
|
156 |
+
},
|
157 |
+
"151662": {
|
158 |
+
"content": "<|fim_pad|>",
|
159 |
+
"lstrip": false,
|
160 |
+
"normalized": false,
|
161 |
+
"rstrip": false,
|
162 |
+
"single_word": false,
|
163 |
+
"special": false
|
164 |
+
},
|
165 |
+
"151663": {
|
166 |
+
"content": "<|repo_name|>",
|
167 |
+
"lstrip": false,
|
168 |
+
"normalized": false,
|
169 |
+
"rstrip": false,
|
170 |
+
"single_word": false,
|
171 |
+
"special": false
|
172 |
+
},
|
173 |
+
"151664": {
|
174 |
+
"content": "<|file_sep|>",
|
175 |
+
"lstrip": false,
|
176 |
+
"normalized": false,
|
177 |
+
"rstrip": false,
|
178 |
+
"single_word": false,
|
179 |
+
"special": false
|
180 |
+
}
|
181 |
+
},
|
182 |
+
"additional_special_tokens": [
|
183 |
+
"<|im_start|>",
|
184 |
+
"<|im_end|>",
|
185 |
+
"<|object_ref_start|>",
|
186 |
+
"<|object_ref_end|>",
|
187 |
+
"<|box_start|>",
|
188 |
+
"<|box_end|>",
|
189 |
+
"<|quad_start|>",
|
190 |
+
"<|quad_end|>",
|
191 |
+
"<|vision_start|>",
|
192 |
+
"<|vision_end|>",
|
193 |
+
"<|vision_pad|>",
|
194 |
+
"<|image_pad|>",
|
195 |
+
"<|video_pad|>"
|
196 |
+
],
|
197 |
+
"bos_token": null,
|
198 |
+
"chat_template": "{% if 'role' in messages[0] %}{% for message in messages %}\n{% if message['role'] == 'system' %}\n<|im_start|>system\n{{ message['message'] }}<|im_end|>\n{% elif message['role'] == 'user' %}\n<|im_start|>user\n{{ message['message'] }}<|im_end|>\n{% elif message['role'] == 'assistant' %}\n<|im_start|>assistant\n{{ message['message'] }}<|im_end|>\n{% endif %}\n{% endfor %}\n{% if add_generation_prompt %}\n<|im_start|>assistant\n{% endif %}{% else %}{% for message in messages %}\n{% if message['role'] == 'system' %}\n<|im_start|>system\n{{ message['message'] }}<|im_end|>\n{% elif message['role'] == 'user' %}\n<|im_start|>user\n{{ message['message'] }}<|im_end|>\n{% elif message['role'] == 'assistant' %}\n<|im_start|>assistant\n{{ message['message'] }}<|im_end|>\n{% endif %}\n{% endfor %}\n{% if add_generation_prompt %}\n<|im_start|>assistant\n{% endif %}{% endif %}",
|
199 |
+
"clean_up_tokenization_spaces": false,
|
200 |
+
"eos_token": "<|im_end|>",
|
201 |
+
"errors": "replace",
|
202 |
+
"extra_special_tokens": {},
|
203 |
+
"model_max_length": 32768,
|
204 |
+
"pad_token": "<|endoftext|>",
|
205 |
+
"padding_side": "right",
|
206 |
+
"split_special_tokens": false,
|
207 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
208 |
+
"unk_token": null
|
209 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,3534 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 2.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 4992,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.004006410256410256,
|
13 |
+
"grad_norm": 1.243200421333313,
|
14 |
+
"learning_rate": 6.666666666666667e-06,
|
15 |
+
"loss": 0.5025,
|
16 |
+
"step": 10
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.008012820512820512,
|
20 |
+
"grad_norm": 0.40575382113456726,
|
21 |
+
"learning_rate": 1.3333333333333333e-05,
|
22 |
+
"loss": 0.3957,
|
23 |
+
"step": 20
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.01201923076923077,
|
27 |
+
"grad_norm": 0.2619800269603729,
|
28 |
+
"learning_rate": 2e-05,
|
29 |
+
"loss": 0.3277,
|
30 |
+
"step": 30
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 0.016025641025641024,
|
34 |
+
"grad_norm": 0.2629871964454651,
|
35 |
+
"learning_rate": 2.6666666666666667e-05,
|
36 |
+
"loss": 0.319,
|
37 |
+
"step": 40
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 0.020032051282051284,
|
41 |
+
"grad_norm": 0.2376326471567154,
|
42 |
+
"learning_rate": 3.3333333333333335e-05,
|
43 |
+
"loss": 0.2829,
|
44 |
+
"step": 50
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.02403846153846154,
|
48 |
+
"grad_norm": 0.25014540553092957,
|
49 |
+
"learning_rate": 4e-05,
|
50 |
+
"loss": 0.2777,
|
51 |
+
"step": 60
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.028044871794871796,
|
55 |
+
"grad_norm": 0.30097439885139465,
|
56 |
+
"learning_rate": 4.666666666666667e-05,
|
57 |
+
"loss": 0.2688,
|
58 |
+
"step": 70
|
59 |
+
},
|
60 |
+
{
|
61 |
+
"epoch": 0.03205128205128205,
|
62 |
+
"grad_norm": 0.29906877875328064,
|
63 |
+
"learning_rate": 5.333333333333333e-05,
|
64 |
+
"loss": 0.272,
|
65 |
+
"step": 80
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 0.036057692307692304,
|
69 |
+
"grad_norm": 0.31522494554519653,
|
70 |
+
"learning_rate": 6e-05,
|
71 |
+
"loss": 0.2573,
|
72 |
+
"step": 90
|
73 |
+
},
|
74 |
+
{
|
75 |
+
"epoch": 0.04006410256410257,
|
76 |
+
"grad_norm": 0.31278184056282043,
|
77 |
+
"learning_rate": 6.666666666666667e-05,
|
78 |
+
"loss": 0.2548,
|
79 |
+
"step": 100
|
80 |
+
},
|
81 |
+
{
|
82 |
+
"epoch": 0.044070512820512824,
|
83 |
+
"grad_norm": 0.31608548760414124,
|
84 |
+
"learning_rate": 7.333333333333333e-05,
|
85 |
+
"loss": 0.2496,
|
86 |
+
"step": 110
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 0.04807692307692308,
|
90 |
+
"grad_norm": 0.29328644275665283,
|
91 |
+
"learning_rate": 8e-05,
|
92 |
+
"loss": 0.2475,
|
93 |
+
"step": 120
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 0.052083333333333336,
|
97 |
+
"grad_norm": 0.33972907066345215,
|
98 |
+
"learning_rate": 8.666666666666667e-05,
|
99 |
+
"loss": 0.2512,
|
100 |
+
"step": 130
|
101 |
+
},
|
102 |
+
{
|
103 |
+
"epoch": 0.05608974358974359,
|
104 |
+
"grad_norm": 0.32710641622543335,
|
105 |
+
"learning_rate": 9.333333333333334e-05,
|
106 |
+
"loss": 0.2382,
|
107 |
+
"step": 140
|
108 |
+
},
|
109 |
+
{
|
110 |
+
"epoch": 0.06009615384615385,
|
111 |
+
"grad_norm": 0.2911882996559143,
|
112 |
+
"learning_rate": 0.0001,
|
113 |
+
"loss": 0.2373,
|
114 |
+
"step": 150
|
115 |
+
},
|
116 |
+
{
|
117 |
+
"epoch": 0.0641025641025641,
|
118 |
+
"grad_norm": 0.29396378993988037,
|
119 |
+
"learning_rate": 9.999894758104792e-05,
|
120 |
+
"loss": 0.2433,
|
121 |
+
"step": 160
|
122 |
+
},
|
123 |
+
{
|
124 |
+
"epoch": 0.06810897435897435,
|
125 |
+
"grad_norm": 0.33355265855789185,
|
126 |
+
"learning_rate": 9.999579036849509e-05,
|
127 |
+
"loss": 0.2435,
|
128 |
+
"step": 170
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 0.07211538461538461,
|
132 |
+
"grad_norm": 0.29101336002349854,
|
133 |
+
"learning_rate": 9.999052849524992e-05,
|
134 |
+
"loss": 0.2376,
|
135 |
+
"step": 180
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 0.07612179487179487,
|
139 |
+
"grad_norm": 0.27655455470085144,
|
140 |
+
"learning_rate": 9.998316218282024e-05,
|
141 |
+
"loss": 0.2365,
|
142 |
+
"step": 190
|
143 |
+
},
|
144 |
+
{
|
145 |
+
"epoch": 0.08012820512820513,
|
146 |
+
"grad_norm": 0.2681509554386139,
|
147 |
+
"learning_rate": 9.997369174130391e-05,
|
148 |
+
"loss": 0.2425,
|
149 |
+
"step": 200
|
150 |
+
},
|
151 |
+
{
|
152 |
+
"epoch": 0.08413461538461539,
|
153 |
+
"grad_norm": 0.26265430450439453,
|
154 |
+
"learning_rate": 9.996211756937579e-05,
|
155 |
+
"loss": 0.2389,
|
156 |
+
"step": 210
|
157 |
+
},
|
158 |
+
{
|
159 |
+
"epoch": 0.08814102564102565,
|
160 |
+
"grad_norm": 0.2830798625946045,
|
161 |
+
"learning_rate": 9.994844015427102e-05,
|
162 |
+
"loss": 0.2304,
|
163 |
+
"step": 220
|
164 |
+
},
|
165 |
+
{
|
166 |
+
"epoch": 0.0921474358974359,
|
167 |
+
"grad_norm": 0.2548621892929077,
|
168 |
+
"learning_rate": 9.993266007176445e-05,
|
169 |
+
"loss": 0.2308,
|
170 |
+
"step": 230
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 0.09615384615384616,
|
174 |
+
"grad_norm": 0.27960866689682007,
|
175 |
+
"learning_rate": 9.991477798614638e-05,
|
176 |
+
"loss": 0.2277,
|
177 |
+
"step": 240
|
178 |
+
},
|
179 |
+
{
|
180 |
+
"epoch": 0.10016025641025642,
|
181 |
+
"grad_norm": 0.2278411090373993,
|
182 |
+
"learning_rate": 9.989479465019462e-05,
|
183 |
+
"loss": 0.2314,
|
184 |
+
"step": 250
|
185 |
+
},
|
186 |
+
{
|
187 |
+
"epoch": 0.10416666666666667,
|
188 |
+
"grad_norm": 0.2582249045372009,
|
189 |
+
"learning_rate": 9.987271090514288e-05,
|
190 |
+
"loss": 0.2355,
|
191 |
+
"step": 260
|
192 |
+
},
|
193 |
+
{
|
194 |
+
"epoch": 0.10817307692307693,
|
195 |
+
"grad_norm": 0.28811654448509216,
|
196 |
+
"learning_rate": 9.984852768064516e-05,
|
197 |
+
"loss": 0.2285,
|
198 |
+
"step": 270
|
199 |
+
},
|
200 |
+
{
|
201 |
+
"epoch": 0.11217948717948718,
|
202 |
+
"grad_norm": 0.241895392537117,
|
203 |
+
"learning_rate": 9.982224599473689e-05,
|
204 |
+
"loss": 0.2344,
|
205 |
+
"step": 280
|
206 |
+
},
|
207 |
+
{
|
208 |
+
"epoch": 0.11618589743589744,
|
209 |
+
"grad_norm": 0.2796310484409332,
|
210 |
+
"learning_rate": 9.97938669537918e-05,
|
211 |
+
"loss": 0.2246,
|
212 |
+
"step": 290
|
213 |
+
},
|
214 |
+
{
|
215 |
+
"epoch": 0.1201923076923077,
|
216 |
+
"grad_norm": 0.24658632278442383,
|
217 |
+
"learning_rate": 9.976339175247551e-05,
|
218 |
+
"loss": 0.2187,
|
219 |
+
"step": 300
|
220 |
+
},
|
221 |
+
{
|
222 |
+
"epoch": 0.12419871794871795,
|
223 |
+
"grad_norm": 0.23214490711688995,
|
224 |
+
"learning_rate": 9.973082167369521e-05,
|
225 |
+
"loss": 0.225,
|
226 |
+
"step": 310
|
227 |
+
},
|
228 |
+
{
|
229 |
+
"epoch": 0.1282051282051282,
|
230 |
+
"grad_norm": 0.25273966789245605,
|
231 |
+
"learning_rate": 9.969615808854562e-05,
|
232 |
+
"loss": 0.2291,
|
233 |
+
"step": 320
|
234 |
+
},
|
235 |
+
{
|
236 |
+
"epoch": 0.13221153846153846,
|
237 |
+
"grad_norm": 0.25187525153160095,
|
238 |
+
"learning_rate": 9.965940245625131e-05,
|
239 |
+
"loss": 0.2227,
|
240 |
+
"step": 330
|
241 |
+
},
|
242 |
+
{
|
243 |
+
"epoch": 0.1362179487179487,
|
244 |
+
"grad_norm": 0.296224445104599,
|
245 |
+
"learning_rate": 9.962055632410523e-05,
|
246 |
+
"loss": 0.2185,
|
247 |
+
"step": 340
|
248 |
+
},
|
249 |
+
{
|
250 |
+
"epoch": 0.14022435897435898,
|
251 |
+
"grad_norm": 0.2560974955558777,
|
252 |
+
"learning_rate": 9.95796213274036e-05,
|
253 |
+
"loss": 0.2251,
|
254 |
+
"step": 350
|
255 |
+
},
|
256 |
+
{
|
257 |
+
"epoch": 0.14423076923076922,
|
258 |
+
"grad_norm": 0.24337032437324524,
|
259 |
+
"learning_rate": 9.95365991893771e-05,
|
260 |
+
"loss": 0.2212,
|
261 |
+
"step": 360
|
262 |
+
},
|
263 |
+
{
|
264 |
+
"epoch": 0.1482371794871795,
|
265 |
+
"grad_norm": 0.2607037127017975,
|
266 |
+
"learning_rate": 9.949149172111825e-05,
|
267 |
+
"loss": 0.2229,
|
268 |
+
"step": 370
|
269 |
+
},
|
270 |
+
{
|
271 |
+
"epoch": 0.15224358974358973,
|
272 |
+
"grad_norm": 0.2829968333244324,
|
273 |
+
"learning_rate": 9.944430082150522e-05,
|
274 |
+
"loss": 0.2276,
|
275 |
+
"step": 380
|
276 |
+
},
|
277 |
+
{
|
278 |
+
"epoch": 0.15625,
|
279 |
+
"grad_norm": 0.24074934422969818,
|
280 |
+
"learning_rate": 9.93950284771219e-05,
|
281 |
+
"loss": 0.2241,
|
282 |
+
"step": 390
|
283 |
+
},
|
284 |
+
{
|
285 |
+
"epoch": 0.16025641025641027,
|
286 |
+
"grad_norm": 0.27647778391838074,
|
287 |
+
"learning_rate": 9.934367676217427e-05,
|
288 |
+
"loss": 0.2071,
|
289 |
+
"step": 400
|
290 |
+
},
|
291 |
+
{
|
292 |
+
"epoch": 0.1642628205128205,
|
293 |
+
"grad_norm": 0.2719784677028656,
|
294 |
+
"learning_rate": 9.929024783840302e-05,
|
295 |
+
"loss": 0.2217,
|
296 |
+
"step": 410
|
297 |
+
},
|
298 |
+
{
|
299 |
+
"epoch": 0.16826923076923078,
|
300 |
+
"grad_norm": 0.23359382152557373,
|
301 |
+
"learning_rate": 9.923474395499265e-05,
|
302 |
+
"loss": 0.2222,
|
303 |
+
"step": 420
|
304 |
+
},
|
305 |
+
{
|
306 |
+
"epoch": 0.17227564102564102,
|
307 |
+
"grad_norm": 0.27376872301101685,
|
308 |
+
"learning_rate": 9.917716744847673e-05,
|
309 |
+
"loss": 0.222,
|
310 |
+
"step": 430
|
311 |
+
},
|
312 |
+
{
|
313 |
+
"epoch": 0.1762820512820513,
|
314 |
+
"grad_norm": 0.2602153718471527,
|
315 |
+
"learning_rate": 9.911752074263949e-05,
|
316 |
+
"loss": 0.2232,
|
317 |
+
"step": 440
|
318 |
+
},
|
319 |
+
{
|
320 |
+
"epoch": 0.18028846153846154,
|
321 |
+
"grad_norm": 0.29065001010894775,
|
322 |
+
"learning_rate": 9.905580634841388e-05,
|
323 |
+
"loss": 0.2212,
|
324 |
+
"step": 450
|
325 |
+
},
|
326 |
+
{
|
327 |
+
"epoch": 0.1842948717948718,
|
328 |
+
"grad_norm": 0.24715092778205872,
|
329 |
+
"learning_rate": 9.899202686377584e-05,
|
330 |
+
"loss": 0.2246,
|
331 |
+
"step": 460
|
332 |
+
},
|
333 |
+
{
|
334 |
+
"epoch": 0.18830128205128205,
|
335 |
+
"grad_norm": 0.2442002296447754,
|
336 |
+
"learning_rate": 9.89261849736349e-05,
|
337 |
+
"loss": 0.2171,
|
338 |
+
"step": 470
|
339 |
+
},
|
340 |
+
{
|
341 |
+
"epoch": 0.19230769230769232,
|
342 |
+
"grad_norm": 0.22722263634204865,
|
343 |
+
"learning_rate": 9.88582834497212e-05,
|
344 |
+
"loss": 0.2176,
|
345 |
+
"step": 480
|
346 |
+
},
|
347 |
+
{
|
348 |
+
"epoch": 0.19631410256410256,
|
349 |
+
"grad_norm": 0.22697150707244873,
|
350 |
+
"learning_rate": 9.878832515046871e-05,
|
351 |
+
"loss": 0.2179,
|
352 |
+
"step": 490
|
353 |
+
},
|
354 |
+
{
|
355 |
+
"epoch": 0.20032051282051283,
|
356 |
+
"grad_norm": 0.23478808999061584,
|
357 |
+
"learning_rate": 9.87163130208951e-05,
|
358 |
+
"loss": 0.2114,
|
359 |
+
"step": 500
|
360 |
+
},
|
361 |
+
{
|
362 |
+
"epoch": 0.20432692307692307,
|
363 |
+
"grad_norm": 0.26591965556144714,
|
364 |
+
"learning_rate": 9.864225009247751e-05,
|
365 |
+
"loss": 0.2165,
|
366 |
+
"step": 510
|
367 |
+
},
|
368 |
+
{
|
369 |
+
"epoch": 0.20833333333333334,
|
370 |
+
"grad_norm": 0.23949167132377625,
|
371 |
+
"learning_rate": 9.856613948302518e-05,
|
372 |
+
"loss": 0.2118,
|
373 |
+
"step": 520
|
374 |
+
},
|
375 |
+
{
|
376 |
+
"epoch": 0.21233974358974358,
|
377 |
+
"grad_norm": 0.22695676982402802,
|
378 |
+
"learning_rate": 9.848798439654797e-05,
|
379 |
+
"loss": 0.2256,
|
380 |
+
"step": 530
|
381 |
+
},
|
382 |
+
{
|
383 |
+
"epoch": 0.21634615384615385,
|
384 |
+
"grad_norm": 0.2355981171131134,
|
385 |
+
"learning_rate": 9.840778812312165e-05,
|
386 |
+
"loss": 0.2123,
|
387 |
+
"step": 540
|
388 |
+
},
|
389 |
+
{
|
390 |
+
"epoch": 0.2203525641025641,
|
391 |
+
"grad_norm": 0.2660483419895172,
|
392 |
+
"learning_rate": 9.832555403874937e-05,
|
393 |
+
"loss": 0.2207,
|
394 |
+
"step": 550
|
395 |
+
},
|
396 |
+
{
|
397 |
+
"epoch": 0.22435897435897437,
|
398 |
+
"grad_norm": 0.2517046630382538,
|
399 |
+
"learning_rate": 9.824128560521948e-05,
|
400 |
+
"loss": 0.2144,
|
401 |
+
"step": 560
|
402 |
+
},
|
403 |
+
{
|
404 |
+
"epoch": 0.2283653846153846,
|
405 |
+
"grad_norm": 0.23771142959594727,
|
406 |
+
"learning_rate": 9.815498636995983e-05,
|
407 |
+
"loss": 0.2061,
|
408 |
+
"step": 570
|
409 |
+
},
|
410 |
+
{
|
411 |
+
"epoch": 0.23237179487179488,
|
412 |
+
"grad_norm": 0.23048646748065948,
|
413 |
+
"learning_rate": 9.806665996588844e-05,
|
414 |
+
"loss": 0.2151,
|
415 |
+
"step": 580
|
416 |
+
},
|
417 |
+
{
|
418 |
+
"epoch": 0.23637820512820512,
|
419 |
+
"grad_norm": 0.26294463872909546,
|
420 |
+
"learning_rate": 9.79763101112606e-05,
|
421 |
+
"loss": 0.2129,
|
422 |
+
"step": 590
|
423 |
+
},
|
424 |
+
{
|
425 |
+
"epoch": 0.2403846153846154,
|
426 |
+
"grad_norm": 0.2391149401664734,
|
427 |
+
"learning_rate": 9.788394060951229e-05,
|
428 |
+
"loss": 0.2134,
|
429 |
+
"step": 600
|
430 |
+
},
|
431 |
+
{
|
432 |
+
"epoch": 0.24439102564102563,
|
433 |
+
"grad_norm": 0.21405121684074402,
|
434 |
+
"learning_rate": 9.778955534910003e-05,
|
435 |
+
"loss": 0.2204,
|
436 |
+
"step": 610
|
437 |
+
},
|
438 |
+
{
|
439 |
+
"epoch": 0.2483974358974359,
|
440 |
+
"grad_norm": 0.21098735928535461,
|
441 |
+
"learning_rate": 9.769315830333735e-05,
|
442 |
+
"loss": 0.212,
|
443 |
+
"step": 620
|
444 |
+
},
|
445 |
+
{
|
446 |
+
"epoch": 0.25240384615384615,
|
447 |
+
"grad_norm": 0.24548964202404022,
|
448 |
+
"learning_rate": 9.759475353022734e-05,
|
449 |
+
"loss": 0.2091,
|
450 |
+
"step": 630
|
451 |
+
},
|
452 |
+
{
|
453 |
+
"epoch": 0.2564102564102564,
|
454 |
+
"grad_norm": 0.23211954534053802,
|
455 |
+
"learning_rate": 9.749434517229191e-05,
|
456 |
+
"loss": 0.2074,
|
457 |
+
"step": 640
|
458 |
+
},
|
459 |
+
{
|
460 |
+
"epoch": 0.2604166666666667,
|
461 |
+
"grad_norm": 0.24367853999137878,
|
462 |
+
"learning_rate": 9.739193745639745e-05,
|
463 |
+
"loss": 0.2,
|
464 |
+
"step": 650
|
465 |
+
},
|
466 |
+
{
|
467 |
+
"epoch": 0.2644230769230769,
|
468 |
+
"grad_norm": 0.22633159160614014,
|
469 |
+
"learning_rate": 9.728753469357677e-05,
|
470 |
+
"loss": 0.2144,
|
471 |
+
"step": 660
|
472 |
+
},
|
473 |
+
{
|
474 |
+
"epoch": 0.26842948717948717,
|
475 |
+
"grad_norm": 0.23814593255519867,
|
476 |
+
"learning_rate": 9.718114127884774e-05,
|
477 |
+
"loss": 0.2105,
|
478 |
+
"step": 670
|
479 |
+
},
|
480 |
+
{
|
481 |
+
"epoch": 0.2724358974358974,
|
482 |
+
"grad_norm": 0.23060369491577148,
|
483 |
+
"learning_rate": 9.70727616910282e-05,
|
484 |
+
"loss": 0.2095,
|
485 |
+
"step": 680
|
486 |
+
},
|
487 |
+
{
|
488 |
+
"epoch": 0.2764423076923077,
|
489 |
+
"grad_norm": 0.24806129932403564,
|
490 |
+
"learning_rate": 9.696240049254743e-05,
|
491 |
+
"loss": 0.2023,
|
492 |
+
"step": 690
|
493 |
+
},
|
494 |
+
{
|
495 |
+
"epoch": 0.28044871794871795,
|
496 |
+
"grad_norm": 0.2317938357591629,
|
497 |
+
"learning_rate": 9.685006232925413e-05,
|
498 |
+
"loss": 0.2069,
|
499 |
+
"step": 700
|
500 |
+
},
|
501 |
+
{
|
502 |
+
"epoch": 0.2844551282051282,
|
503 |
+
"grad_norm": 0.2503266930580139,
|
504 |
+
"learning_rate": 9.673575193022073e-05,
|
505 |
+
"loss": 0.2131,
|
506 |
+
"step": 710
|
507 |
+
},
|
508 |
+
{
|
509 |
+
"epoch": 0.28846153846153844,
|
510 |
+
"grad_norm": 0.24147148430347443,
|
511 |
+
"learning_rate": 9.661947410754449e-05,
|
512 |
+
"loss": 0.2024,
|
513 |
+
"step": 720
|
514 |
+
},
|
515 |
+
{
|
516 |
+
"epoch": 0.29246794871794873,
|
517 |
+
"grad_norm": 0.2683294117450714,
|
518 |
+
"learning_rate": 9.650123375614477e-05,
|
519 |
+
"loss": 0.2088,
|
520 |
+
"step": 730
|
521 |
+
},
|
522 |
+
{
|
523 |
+
"epoch": 0.296474358974359,
|
524 |
+
"grad_norm": 0.23034317791461945,
|
525 |
+
"learning_rate": 9.638103585355705e-05,
|
526 |
+
"loss": 0.2103,
|
527 |
+
"step": 740
|
528 |
+
},
|
529 |
+
{
|
530 |
+
"epoch": 0.3004807692307692,
|
531 |
+
"grad_norm": 0.23943544924259186,
|
532 |
+
"learning_rate": 9.625888545972332e-05,
|
533 |
+
"loss": 0.211,
|
534 |
+
"step": 750
|
535 |
+
},
|
536 |
+
{
|
537 |
+
"epoch": 0.30448717948717946,
|
538 |
+
"grad_norm": 0.24953238666057587,
|
539 |
+
"learning_rate": 9.613478771677921e-05,
|
540 |
+
"loss": 0.217,
|
541 |
+
"step": 760
|
542 |
+
},
|
543 |
+
{
|
544 |
+
"epoch": 0.30849358974358976,
|
545 |
+
"grad_norm": 0.25620102882385254,
|
546 |
+
"learning_rate": 9.600874784883736e-05,
|
547 |
+
"loss": 0.208,
|
548 |
+
"step": 770
|
549 |
+
},
|
550 |
+
{
|
551 |
+
"epoch": 0.3125,
|
552 |
+
"grad_norm": 0.22348496317863464,
|
553 |
+
"learning_rate": 9.588077116176756e-05,
|
554 |
+
"loss": 0.2048,
|
555 |
+
"step": 780
|
556 |
+
},
|
557 |
+
{
|
558 |
+
"epoch": 0.31650641025641024,
|
559 |
+
"grad_norm": 0.21532465517520905,
|
560 |
+
"learning_rate": 9.575086304297351e-05,
|
561 |
+
"loss": 0.1997,
|
562 |
+
"step": 790
|
563 |
+
},
|
564 |
+
{
|
565 |
+
"epoch": 0.32051282051282054,
|
566 |
+
"grad_norm": 0.23346661031246185,
|
567 |
+
"learning_rate": 9.561902896116583e-05,
|
568 |
+
"loss": 0.2085,
|
569 |
+
"step": 800
|
570 |
+
},
|
571 |
+
{
|
572 |
+
"epoch": 0.3245192307692308,
|
573 |
+
"grad_norm": 0.23158910870552063,
|
574 |
+
"learning_rate": 9.548527446613198e-05,
|
575 |
+
"loss": 0.2005,
|
576 |
+
"step": 810
|
577 |
+
},
|
578 |
+
{
|
579 |
+
"epoch": 0.328525641025641,
|
580 |
+
"grad_norm": 0.2302473783493042,
|
581 |
+
"learning_rate": 9.534960518850257e-05,
|
582 |
+
"loss": 0.1993,
|
583 |
+
"step": 820
|
584 |
+
},
|
585 |
+
{
|
586 |
+
"epoch": 0.33253205128205127,
|
587 |
+
"grad_norm": 0.21067394316196442,
|
588 |
+
"learning_rate": 9.521202683951436e-05,
|
589 |
+
"loss": 0.1902,
|
590 |
+
"step": 830
|
591 |
+
},
|
592 |
+
{
|
593 |
+
"epoch": 0.33653846153846156,
|
594 |
+
"grad_norm": 0.22453920543193817,
|
595 |
+
"learning_rate": 9.507254521076982e-05,
|
596 |
+
"loss": 0.1907,
|
597 |
+
"step": 840
|
598 |
+
},
|
599 |
+
{
|
600 |
+
"epoch": 0.3405448717948718,
|
601 |
+
"grad_norm": 0.23678337037563324,
|
602 |
+
"learning_rate": 9.493116617399334e-05,
|
603 |
+
"loss": 0.2007,
|
604 |
+
"step": 850
|
605 |
+
},
|
606 |
+
{
|
607 |
+
"epoch": 0.34455128205128205,
|
608 |
+
"grad_norm": 0.2377959042787552,
|
609 |
+
"learning_rate": 9.478789568078403e-05,
|
610 |
+
"loss": 0.2077,
|
611 |
+
"step": 860
|
612 |
+
},
|
613 |
+
{
|
614 |
+
"epoch": 0.3485576923076923,
|
615 |
+
"grad_norm": 0.23520340025424957,
|
616 |
+
"learning_rate": 9.464273976236517e-05,
|
617 |
+
"loss": 0.2079,
|
618 |
+
"step": 870
|
619 |
+
},
|
620 |
+
{
|
621 |
+
"epoch": 0.3525641025641026,
|
622 |
+
"grad_norm": 0.21978124976158142,
|
623 |
+
"learning_rate": 9.449570452933038e-05,
|
624 |
+
"loss": 0.2076,
|
625 |
+
"step": 880
|
626 |
+
},
|
627 |
+
{
|
628 |
+
"epoch": 0.35657051282051283,
|
629 |
+
"grad_norm": 0.21525253355503082,
|
630 |
+
"learning_rate": 9.434679617138625e-05,
|
631 |
+
"loss": 0.207,
|
632 |
+
"step": 890
|
633 |
+
},
|
634 |
+
{
|
635 |
+
"epoch": 0.3605769230769231,
|
636 |
+
"grad_norm": 0.23039253056049347,
|
637 |
+
"learning_rate": 9.419602095709193e-05,
|
638 |
+
"loss": 0.1985,
|
639 |
+
"step": 900
|
640 |
+
},
|
641 |
+
{
|
642 |
+
"epoch": 0.3645833333333333,
|
643 |
+
"grad_norm": 0.2329927235841751,
|
644 |
+
"learning_rate": 9.40433852335951e-05,
|
645 |
+
"loss": 0.2136,
|
646 |
+
"step": 910
|
647 |
+
},
|
648 |
+
{
|
649 |
+
"epoch": 0.3685897435897436,
|
650 |
+
"grad_norm": 0.24603788554668427,
|
651 |
+
"learning_rate": 9.388889542636495e-05,
|
652 |
+
"loss": 0.2106,
|
653 |
+
"step": 920
|
654 |
+
},
|
655 |
+
{
|
656 |
+
"epoch": 0.37259615384615385,
|
657 |
+
"grad_norm": 0.2563282549381256,
|
658 |
+
"learning_rate": 9.373255803892149e-05,
|
659 |
+
"loss": 0.2052,
|
660 |
+
"step": 930
|
661 |
+
},
|
662 |
+
{
|
663 |
+
"epoch": 0.3766025641025641,
|
664 |
+
"grad_norm": 0.2391922026872635,
|
665 |
+
"learning_rate": 9.357437965256188e-05,
|
666 |
+
"loss": 0.1965,
|
667 |
+
"step": 940
|
668 |
+
},
|
669 |
+
{
|
670 |
+
"epoch": 0.38060897435897434,
|
671 |
+
"grad_norm": 0.22608546912670135,
|
672 |
+
"learning_rate": 9.341436692608341e-05,
|
673 |
+
"loss": 0.1995,
|
674 |
+
"step": 950
|
675 |
+
},
|
676 |
+
{
|
677 |
+
"epoch": 0.38461538461538464,
|
678 |
+
"grad_norm": 0.2254156768321991,
|
679 |
+
"learning_rate": 9.325252659550309e-05,
|
680 |
+
"loss": 0.2023,
|
681 |
+
"step": 960
|
682 |
+
},
|
683 |
+
{
|
684 |
+
"epoch": 0.3886217948717949,
|
685 |
+
"grad_norm": 0.2172781527042389,
|
686 |
+
"learning_rate": 9.30888654737742e-05,
|
687 |
+
"loss": 0.1935,
|
688 |
+
"step": 970
|
689 |
+
},
|
690 |
+
{
|
691 |
+
"epoch": 0.3926282051282051,
|
692 |
+
"grad_norm": 0.24400238692760468,
|
693 |
+
"learning_rate": 9.292339045049938e-05,
|
694 |
+
"loss": 0.2046,
|
695 |
+
"step": 980
|
696 |
+
},
|
697 |
+
{
|
698 |
+
"epoch": 0.39663461538461536,
|
699 |
+
"grad_norm": 0.23503102362155914,
|
700 |
+
"learning_rate": 9.275610849164064e-05,
|
701 |
+
"loss": 0.1896,
|
702 |
+
"step": 990
|
703 |
+
},
|
704 |
+
{
|
705 |
+
"epoch": 0.40064102564102566,
|
706 |
+
"grad_norm": 0.23404181003570557,
|
707 |
+
"learning_rate": 9.258702663922614e-05,
|
708 |
+
"loss": 0.2034,
|
709 |
+
"step": 1000
|
710 |
+
},
|
711 |
+
{
|
712 |
+
"epoch": 0.4046474358974359,
|
713 |
+
"grad_norm": 0.24212764203548431,
|
714 |
+
"learning_rate": 9.241615201105372e-05,
|
715 |
+
"loss": 0.2027,
|
716 |
+
"step": 1010
|
717 |
+
},
|
718 |
+
{
|
719 |
+
"epoch": 0.40865384615384615,
|
720 |
+
"grad_norm": 0.2275129109621048,
|
721 |
+
"learning_rate": 9.224349180039124e-05,
|
722 |
+
"loss": 0.195,
|
723 |
+
"step": 1020
|
724 |
+
},
|
725 |
+
{
|
726 |
+
"epoch": 0.4126602564102564,
|
727 |
+
"grad_norm": 0.2557786703109741,
|
728 |
+
"learning_rate": 9.206905327567386e-05,
|
729 |
+
"loss": 0.2029,
|
730 |
+
"step": 1030
|
731 |
+
},
|
732 |
+
{
|
733 |
+
"epoch": 0.4166666666666667,
|
734 |
+
"grad_norm": 0.23480971157550812,
|
735 |
+
"learning_rate": 9.189284378019794e-05,
|
736 |
+
"loss": 0.1896,
|
737 |
+
"step": 1040
|
738 |
+
},
|
739 |
+
{
|
740 |
+
"epoch": 0.4206730769230769,
|
741 |
+
"grad_norm": 0.20550891757011414,
|
742 |
+
"learning_rate": 9.171487073181198e-05,
|
743 |
+
"loss": 0.2012,
|
744 |
+
"step": 1050
|
745 |
+
},
|
746 |
+
{
|
747 |
+
"epoch": 0.42467948717948717,
|
748 |
+
"grad_norm": 0.23816007375717163,
|
749 |
+
"learning_rate": 9.153514162260432e-05,
|
750 |
+
"loss": 0.2038,
|
751 |
+
"step": 1060
|
752 |
+
},
|
753 |
+
{
|
754 |
+
"epoch": 0.4286858974358974,
|
755 |
+
"grad_norm": 0.22253037989139557,
|
756 |
+
"learning_rate": 9.135366401858783e-05,
|
757 |
+
"loss": 0.2038,
|
758 |
+
"step": 1070
|
759 |
+
},
|
760 |
+
{
|
761 |
+
"epoch": 0.4326923076923077,
|
762 |
+
"grad_norm": 0.2550757825374603,
|
763 |
+
"learning_rate": 9.117044555938128e-05,
|
764 |
+
"loss": 0.192,
|
765 |
+
"step": 1080
|
766 |
+
},
|
767 |
+
{
|
768 |
+
"epoch": 0.43669871794871795,
|
769 |
+
"grad_norm": 0.24329575896263123,
|
770 |
+
"learning_rate": 9.098549395788784e-05,
|
771 |
+
"loss": 0.2033,
|
772 |
+
"step": 1090
|
773 |
+
},
|
774 |
+
{
|
775 |
+
"epoch": 0.4407051282051282,
|
776 |
+
"grad_norm": 0.23914198577404022,
|
777 |
+
"learning_rate": 9.079881699997033e-05,
|
778 |
+
"loss": 0.203,
|
779 |
+
"step": 1100
|
780 |
+
},
|
781 |
+
{
|
782 |
+
"epoch": 0.44471153846153844,
|
783 |
+
"grad_norm": 0.22172652184963226,
|
784 |
+
"learning_rate": 9.061042254412346e-05,
|
785 |
+
"loss": 0.1974,
|
786 |
+
"step": 1110
|
787 |
+
},
|
788 |
+
{
|
789 |
+
"epoch": 0.44871794871794873,
|
790 |
+
"grad_norm": 0.24050387740135193,
|
791 |
+
"learning_rate": 9.042031852114311e-05,
|
792 |
+
"loss": 0.2068,
|
793 |
+
"step": 1120
|
794 |
+
},
|
795 |
+
{
|
796 |
+
"epoch": 0.452724358974359,
|
797 |
+
"grad_norm": 0.25631067156791687,
|
798 |
+
"learning_rate": 9.022851293379231e-05,
|
799 |
+
"loss": 0.1932,
|
800 |
+
"step": 1130
|
801 |
+
},
|
802 |
+
{
|
803 |
+
"epoch": 0.4567307692307692,
|
804 |
+
"grad_norm": 0.24415907263755798,
|
805 |
+
"learning_rate": 9.003501385646449e-05,
|
806 |
+
"loss": 0.195,
|
807 |
+
"step": 1140
|
808 |
+
},
|
809 |
+
{
|
810 |
+
"epoch": 0.46073717948717946,
|
811 |
+
"grad_norm": 0.2140500694513321,
|
812 |
+
"learning_rate": 8.983982943484349e-05,
|
813 |
+
"loss": 0.197,
|
814 |
+
"step": 1150
|
815 |
+
},
|
816 |
+
{
|
817 |
+
"epoch": 0.46474358974358976,
|
818 |
+
"grad_norm": 0.2267265021800995,
|
819 |
+
"learning_rate": 8.964296788556067e-05,
|
820 |
+
"loss": 0.1956,
|
821 |
+
"step": 1160
|
822 |
+
},
|
823 |
+
{
|
824 |
+
"epoch": 0.46875,
|
825 |
+
"grad_norm": 0.2181784212589264,
|
826 |
+
"learning_rate": 8.944443749584907e-05,
|
827 |
+
"loss": 0.2025,
|
828 |
+
"step": 1170
|
829 |
+
},
|
830 |
+
{
|
831 |
+
"epoch": 0.47275641025641024,
|
832 |
+
"grad_norm": 0.22020593285560608,
|
833 |
+
"learning_rate": 8.924424662319448e-05,
|
834 |
+
"loss": 0.1965,
|
835 |
+
"step": 1180
|
836 |
+
},
|
837 |
+
{
|
838 |
+
"epoch": 0.47676282051282054,
|
839 |
+
"grad_norm": 0.21737538278102875,
|
840 |
+
"learning_rate": 8.904240369498362e-05,
|
841 |
+
"loss": 0.1989,
|
842 |
+
"step": 1190
|
843 |
+
},
|
844 |
+
{
|
845 |
+
"epoch": 0.4807692307692308,
|
846 |
+
"grad_norm": 0.21464964747428894,
|
847 |
+
"learning_rate": 8.883891720814942e-05,
|
848 |
+
"loss": 0.1845,
|
849 |
+
"step": 1200
|
850 |
+
},
|
851 |
+
{
|
852 |
+
"epoch": 0.484775641025641,
|
853 |
+
"grad_norm": 0.26550692319869995,
|
854 |
+
"learning_rate": 8.863379572881329e-05,
|
855 |
+
"loss": 0.1888,
|
856 |
+
"step": 1210
|
857 |
+
},
|
858 |
+
{
|
859 |
+
"epoch": 0.48878205128205127,
|
860 |
+
"grad_norm": 0.24705030024051666,
|
861 |
+
"learning_rate": 8.84270478919245e-05,
|
862 |
+
"loss": 0.1912,
|
863 |
+
"step": 1220
|
864 |
+
},
|
865 |
+
{
|
866 |
+
"epoch": 0.49278846153846156,
|
867 |
+
"grad_norm": 0.22611679136753082,
|
868 |
+
"learning_rate": 8.821868240089676e-05,
|
869 |
+
"loss": 0.1998,
|
870 |
+
"step": 1230
|
871 |
+
},
|
872 |
+
{
|
873 |
+
"epoch": 0.4967948717948718,
|
874 |
+
"grad_norm": 0.21941202878952026,
|
875 |
+
"learning_rate": 8.800870802724175e-05,
|
876 |
+
"loss": 0.1981,
|
877 |
+
"step": 1240
|
878 |
+
},
|
879 |
+
{
|
880 |
+
"epoch": 0.500801282051282,
|
881 |
+
"grad_norm": 0.22026574611663818,
|
882 |
+
"learning_rate": 8.779713361019982e-05,
|
883 |
+
"loss": 0.1915,
|
884 |
+
"step": 1250
|
885 |
+
},
|
886 |
+
{
|
887 |
+
"epoch": 0.5048076923076923,
|
888 |
+
"grad_norm": 0.2143823504447937,
|
889 |
+
"learning_rate": 8.758396805636806e-05,
|
890 |
+
"loss": 0.1952,
|
891 |
+
"step": 1260
|
892 |
+
},
|
893 |
+
{
|
894 |
+
"epoch": 0.5088141025641025,
|
895 |
+
"grad_norm": 0.22727568447589874,
|
896 |
+
"learning_rate": 8.736922033932522e-05,
|
897 |
+
"loss": 0.1942,
|
898 |
+
"step": 1270
|
899 |
+
},
|
900 |
+
{
|
901 |
+
"epoch": 0.5128205128205128,
|
902 |
+
"grad_norm": 0.226875901222229,
|
903 |
+
"learning_rate": 8.715289949925401e-05,
|
904 |
+
"loss": 0.1945,
|
905 |
+
"step": 1280
|
906 |
+
},
|
907 |
+
{
|
908 |
+
"epoch": 0.5168269230769231,
|
909 |
+
"grad_norm": 0.1967984139919281,
|
910 |
+
"learning_rate": 8.693501464256046e-05,
|
911 |
+
"loss": 0.1888,
|
912 |
+
"step": 1290
|
913 |
+
},
|
914 |
+
{
|
915 |
+
"epoch": 0.5208333333333334,
|
916 |
+
"grad_norm": 0.2363027185201645,
|
917 |
+
"learning_rate": 8.67155749414907e-05,
|
918 |
+
"loss": 0.1925,
|
919 |
+
"step": 1300
|
920 |
+
},
|
921 |
+
{
|
922 |
+
"epoch": 0.5248397435897436,
|
923 |
+
"grad_norm": 0.23106949031352997,
|
924 |
+
"learning_rate": 8.649458963374473e-05,
|
925 |
+
"loss": 0.1927,
|
926 |
+
"step": 1310
|
927 |
+
},
|
928 |
+
{
|
929 |
+
"epoch": 0.5288461538461539,
|
930 |
+
"grad_norm": 0.20555250346660614,
|
931 |
+
"learning_rate": 8.62720680220876e-05,
|
932 |
+
"loss": 0.2296,
|
933 |
+
"step": 1320
|
934 |
+
},
|
935 |
+
{
|
936 |
+
"epoch": 0.5328525641025641,
|
937 |
+
"grad_norm": 0.21878638863563538,
|
938 |
+
"learning_rate": 8.604801947395777e-05,
|
939 |
+
"loss": 0.1993,
|
940 |
+
"step": 1330
|
941 |
+
},
|
942 |
+
{
|
943 |
+
"epoch": 0.5368589743589743,
|
944 |
+
"grad_norm": 0.22356002032756805,
|
945 |
+
"learning_rate": 8.582245342107273e-05,
|
946 |
+
"loss": 0.1911,
|
947 |
+
"step": 1340
|
948 |
+
},
|
949 |
+
{
|
950 |
+
"epoch": 0.5408653846153846,
|
951 |
+
"grad_norm": 0.23506873846054077,
|
952 |
+
"learning_rate": 8.55953793590321e-05,
|
953 |
+
"loss": 0.1879,
|
954 |
+
"step": 1350
|
955 |
+
},
|
956 |
+
{
|
957 |
+
"epoch": 0.5448717948717948,
|
958 |
+
"grad_norm": 0.23467378318309784,
|
959 |
+
"learning_rate": 8.53668068469177e-05,
|
960 |
+
"loss": 0.1949,
|
961 |
+
"step": 1360
|
962 |
+
},
|
963 |
+
{
|
964 |
+
"epoch": 0.5488782051282052,
|
965 |
+
"grad_norm": 0.24210813641548157,
|
966 |
+
"learning_rate": 8.513674550689128e-05,
|
967 |
+
"loss": 0.1842,
|
968 |
+
"step": 1370
|
969 |
+
},
|
970 |
+
{
|
971 |
+
"epoch": 0.5528846153846154,
|
972 |
+
"grad_norm": 0.2602980434894562,
|
973 |
+
"learning_rate": 8.49052050237894e-05,
|
974 |
+
"loss": 0.192,
|
975 |
+
"step": 1380
|
976 |
+
},
|
977 |
+
{
|
978 |
+
"epoch": 0.5568910256410257,
|
979 |
+
"grad_norm": 0.23115062713623047,
|
980 |
+
"learning_rate": 8.467219514471581e-05,
|
981 |
+
"loss": 0.2008,
|
982 |
+
"step": 1390
|
983 |
+
},
|
984 |
+
{
|
985 |
+
"epoch": 0.5608974358974359,
|
986 |
+
"grad_norm": 0.23633736371994019,
|
987 |
+
"learning_rate": 8.443772567863097e-05,
|
988 |
+
"loss": 0.1893,
|
989 |
+
"step": 1400
|
990 |
+
},
|
991 |
+
{
|
992 |
+
"epoch": 0.5649038461538461,
|
993 |
+
"grad_norm": 0.21265539526939392,
|
994 |
+
"learning_rate": 8.420180649593929e-05,
|
995 |
+
"loss": 0.2016,
|
996 |
+
"step": 1410
|
997 |
+
},
|
998 |
+
{
|
999 |
+
"epoch": 0.5689102564102564,
|
1000 |
+
"grad_norm": 0.21362069249153137,
|
1001 |
+
"learning_rate": 8.396444752807357e-05,
|
1002 |
+
"loss": 0.1861,
|
1003 |
+
"step": 1420
|
1004 |
+
},
|
1005 |
+
{
|
1006 |
+
"epoch": 0.5729166666666666,
|
1007 |
+
"grad_norm": 0.2480146735906601,
|
1008 |
+
"learning_rate": 8.37256587670768e-05,
|
1009 |
+
"loss": 0.1948,
|
1010 |
+
"step": 1430
|
1011 |
+
},
|
1012 |
+
{
|
1013 |
+
"epoch": 0.5769230769230769,
|
1014 |
+
"grad_norm": 0.24672983586788177,
|
1015 |
+
"learning_rate": 8.348545026518171e-05,
|
1016 |
+
"loss": 0.193,
|
1017 |
+
"step": 1440
|
1018 |
+
},
|
1019 |
+
{
|
1020 |
+
"epoch": 0.5809294871794872,
|
1021 |
+
"grad_norm": 0.23038969933986664,
|
1022 |
+
"learning_rate": 8.32438321343875e-05,
|
1023 |
+
"loss": 0.1865,
|
1024 |
+
"step": 1450
|
1025 |
+
},
|
1026 |
+
{
|
1027 |
+
"epoch": 0.5849358974358975,
|
1028 |
+
"grad_norm": 0.23314690589904785,
|
1029 |
+
"learning_rate": 8.300081454603415e-05,
|
1030 |
+
"loss": 0.1863,
|
1031 |
+
"step": 1460
|
1032 |
+
},
|
1033 |
+
{
|
1034 |
+
"epoch": 0.5889423076923077,
|
1035 |
+
"grad_norm": 0.2449977695941925,
|
1036 |
+
"learning_rate": 8.27564077303743e-05,
|
1037 |
+
"loss": 0.199,
|
1038 |
+
"step": 1470
|
1039 |
+
},
|
1040 |
+
{
|
1041 |
+
"epoch": 0.592948717948718,
|
1042 |
+
"grad_norm": 0.22973774373531342,
|
1043 |
+
"learning_rate": 8.251062197614257e-05,
|
1044 |
+
"loss": 0.1818,
|
1045 |
+
"step": 1480
|
1046 |
+
},
|
1047 |
+
{
|
1048 |
+
"epoch": 0.5969551282051282,
|
1049 |
+
"grad_norm": 0.2545977830886841,
|
1050 |
+
"learning_rate": 8.226346763012234e-05,
|
1051 |
+
"loss": 0.1963,
|
1052 |
+
"step": 1490
|
1053 |
+
},
|
1054 |
+
{
|
1055 |
+
"epoch": 0.6009615384615384,
|
1056 |
+
"grad_norm": 0.23034323751926422,
|
1057 |
+
"learning_rate": 8.201495509671037e-05,
|
1058 |
+
"loss": 0.1791,
|
1059 |
+
"step": 1500
|
1060 |
+
},
|
1061 |
+
{
|
1062 |
+
"epoch": 0.6049679487179487,
|
1063 |
+
"grad_norm": 0.22426968812942505,
|
1064 |
+
"learning_rate": 8.176509483747862e-05,
|
1065 |
+
"loss": 0.1941,
|
1066 |
+
"step": 1510
|
1067 |
+
},
|
1068 |
+
{
|
1069 |
+
"epoch": 0.6089743589743589,
|
1070 |
+
"grad_norm": 0.2258072942495346,
|
1071 |
+
"learning_rate": 8.151389737073403e-05,
|
1072 |
+
"loss": 0.195,
|
1073 |
+
"step": 1520
|
1074 |
+
},
|
1075 |
+
{
|
1076 |
+
"epoch": 0.6129807692307693,
|
1077 |
+
"grad_norm": 0.22930273413658142,
|
1078 |
+
"learning_rate": 8.126137327107554e-05,
|
1079 |
+
"loss": 0.191,
|
1080 |
+
"step": 1530
|
1081 |
+
},
|
1082 |
+
{
|
1083 |
+
"epoch": 0.6169871794871795,
|
1084 |
+
"grad_norm": 0.239192396402359,
|
1085 |
+
"learning_rate": 8.100753316894913e-05,
|
1086 |
+
"loss": 0.2073,
|
1087 |
+
"step": 1540
|
1088 |
+
},
|
1089 |
+
{
|
1090 |
+
"epoch": 0.6209935897435898,
|
1091 |
+
"grad_norm": 0.21774733066558838,
|
1092 |
+
"learning_rate": 8.075238775020011e-05,
|
1093 |
+
"loss": 0.1875,
|
1094 |
+
"step": 1550
|
1095 |
+
},
|
1096 |
+
{
|
1097 |
+
"epoch": 0.625,
|
1098 |
+
"grad_norm": 0.21093542873859406,
|
1099 |
+
"learning_rate": 8.04959477556235e-05,
|
1100 |
+
"loss": 0.1942,
|
1101 |
+
"step": 1560
|
1102 |
+
},
|
1103 |
+
{
|
1104 |
+
"epoch": 0.6290064102564102,
|
1105 |
+
"grad_norm": 0.21208257973194122,
|
1106 |
+
"learning_rate": 8.023822398051168e-05,
|
1107 |
+
"loss": 0.1928,
|
1108 |
+
"step": 1570
|
1109 |
+
},
|
1110 |
+
{
|
1111 |
+
"epoch": 0.6330128205128205,
|
1112 |
+
"grad_norm": 0.20604068040847778,
|
1113 |
+
"learning_rate": 7.997922727420011e-05,
|
1114 |
+
"loss": 0.1891,
|
1115 |
+
"step": 1580
|
1116 |
+
},
|
1117 |
+
{
|
1118 |
+
"epoch": 0.6370192307692307,
|
1119 |
+
"grad_norm": 0.209623783826828,
|
1120 |
+
"learning_rate": 7.971896853961042e-05,
|
1121 |
+
"loss": 0.1962,
|
1122 |
+
"step": 1590
|
1123 |
+
},
|
1124 |
+
{
|
1125 |
+
"epoch": 0.6410256410256411,
|
1126 |
+
"grad_norm": 0.22957240045070648,
|
1127 |
+
"learning_rate": 7.945745873279164e-05,
|
1128 |
+
"loss": 0.1908,
|
1129 |
+
"step": 1600
|
1130 |
+
},
|
1131 |
+
{
|
1132 |
+
"epoch": 0.6450320512820513,
|
1133 |
+
"grad_norm": 0.2278134673833847,
|
1134 |
+
"learning_rate": 7.919470886245886e-05,
|
1135 |
+
"loss": 0.186,
|
1136 |
+
"step": 1610
|
1137 |
+
},
|
1138 |
+
{
|
1139 |
+
"epoch": 0.6490384615384616,
|
1140 |
+
"grad_norm": 0.2224593311548233,
|
1141 |
+
"learning_rate": 7.893072998952975e-05,
|
1142 |
+
"loss": 0.1837,
|
1143 |
+
"step": 1620
|
1144 |
+
},
|
1145 |
+
{
|
1146 |
+
"epoch": 0.6530448717948718,
|
1147 |
+
"grad_norm": 0.2841613292694092,
|
1148 |
+
"learning_rate": 7.866553322665911e-05,
|
1149 |
+
"loss": 0.1961,
|
1150 |
+
"step": 1630
|
1151 |
+
},
|
1152 |
+
{
|
1153 |
+
"epoch": 0.657051282051282,
|
1154 |
+
"grad_norm": 0.2239413857460022,
|
1155 |
+
"learning_rate": 7.839912973777088e-05,
|
1156 |
+
"loss": 0.1864,
|
1157 |
+
"step": 1640
|
1158 |
+
},
|
1159 |
+
{
|
1160 |
+
"epoch": 0.6610576923076923,
|
1161 |
+
"grad_norm": 0.24558769166469574,
|
1162 |
+
"learning_rate": 7.813153073758832e-05,
|
1163 |
+
"loss": 0.1902,
|
1164 |
+
"step": 1650
|
1165 |
+
},
|
1166 |
+
{
|
1167 |
+
"epoch": 0.6650641025641025,
|
1168 |
+
"grad_norm": 0.22548821568489075,
|
1169 |
+
"learning_rate": 7.786274749116178e-05,
|
1170 |
+
"loss": 0.1927,
|
1171 |
+
"step": 1660
|
1172 |
+
},
|
1173 |
+
{
|
1174 |
+
"epoch": 0.6690705128205128,
|
1175 |
+
"grad_norm": 0.24735094606876373,
|
1176 |
+
"learning_rate": 7.759279131339454e-05,
|
1177 |
+
"loss": 0.1822,
|
1178 |
+
"step": 1670
|
1179 |
+
},
|
1180 |
+
{
|
1181 |
+
"epoch": 0.6730769230769231,
|
1182 |
+
"grad_norm": 0.23317532241344452,
|
1183 |
+
"learning_rate": 7.732167356856655e-05,
|
1184 |
+
"loss": 0.1928,
|
1185 |
+
"step": 1680
|
1186 |
+
},
|
1187 |
+
{
|
1188 |
+
"epoch": 0.6770833333333334,
|
1189 |
+
"grad_norm": 0.23926283419132233,
|
1190 |
+
"learning_rate": 7.704940566985592e-05,
|
1191 |
+
"loss": 0.1875,
|
1192 |
+
"step": 1690
|
1193 |
+
},
|
1194 |
+
{
|
1195 |
+
"epoch": 0.6810897435897436,
|
1196 |
+
"grad_norm": 0.18621069192886353,
|
1197 |
+
"learning_rate": 7.677599907885851e-05,
|
1198 |
+
"loss": 0.1967,
|
1199 |
+
"step": 1700
|
1200 |
+
},
|
1201 |
+
{
|
1202 |
+
"epoch": 0.6850961538461539,
|
1203 |
+
"grad_norm": 0.2330184280872345,
|
1204 |
+
"learning_rate": 7.650146530510542e-05,
|
1205 |
+
"loss": 0.188,
|
1206 |
+
"step": 1710
|
1207 |
+
},
|
1208 |
+
{
|
1209 |
+
"epoch": 0.6891025641025641,
|
1210 |
+
"grad_norm": 0.2638700008392334,
|
1211 |
+
"learning_rate": 7.622581590557853e-05,
|
1212 |
+
"loss": 0.1815,
|
1213 |
+
"step": 1720
|
1214 |
+
},
|
1215 |
+
{
|
1216 |
+
"epoch": 0.6931089743589743,
|
1217 |
+
"grad_norm": 0.22845664620399475,
|
1218 |
+
"learning_rate": 7.594906248422392e-05,
|
1219 |
+
"loss": 0.1838,
|
1220 |
+
"step": 1730
|
1221 |
+
},
|
1222 |
+
{
|
1223 |
+
"epoch": 0.6971153846153846,
|
1224 |
+
"grad_norm": 0.20396199822425842,
|
1225 |
+
"learning_rate": 7.567121669146343e-05,
|
1226 |
+
"loss": 0.181,
|
1227 |
+
"step": 1740
|
1228 |
+
},
|
1229 |
+
{
|
1230 |
+
"epoch": 0.7011217948717948,
|
1231 |
+
"grad_norm": 0.24452732503414154,
|
1232 |
+
"learning_rate": 7.539229022370417e-05,
|
1233 |
+
"loss": 0.1869,
|
1234 |
+
"step": 1750
|
1235 |
+
},
|
1236 |
+
{
|
1237 |
+
"epoch": 0.7051282051282052,
|
1238 |
+
"grad_norm": 0.21035702526569366,
|
1239 |
+
"learning_rate": 7.511229482284619e-05,
|
1240 |
+
"loss": 0.1912,
|
1241 |
+
"step": 1760
|
1242 |
+
},
|
1243 |
+
{
|
1244 |
+
"epoch": 0.7091346153846154,
|
1245 |
+
"grad_norm": 0.25418221950531006,
|
1246 |
+
"learning_rate": 7.483124227578811e-05,
|
1247 |
+
"loss": 0.1842,
|
1248 |
+
"step": 1770
|
1249 |
+
},
|
1250 |
+
{
|
1251 |
+
"epoch": 0.7131410256410257,
|
1252 |
+
"grad_norm": 0.20252016186714172,
|
1253 |
+
"learning_rate": 7.454914441393104e-05,
|
1254 |
+
"loss": 0.1799,
|
1255 |
+
"step": 1780
|
1256 |
+
},
|
1257 |
+
{
|
1258 |
+
"epoch": 0.7171474358974359,
|
1259 |
+
"grad_norm": 0.22078120708465576,
|
1260 |
+
"learning_rate": 7.426601311268043e-05,
|
1261 |
+
"loss": 0.1864,
|
1262 |
+
"step": 1790
|
1263 |
+
},
|
1264 |
+
{
|
1265 |
+
"epoch": 0.7211538461538461,
|
1266 |
+
"grad_norm": 0.22004160284996033,
|
1267 |
+
"learning_rate": 7.398186029094617e-05,
|
1268 |
+
"loss": 0.1868,
|
1269 |
+
"step": 1800
|
1270 |
+
},
|
1271 |
+
{
|
1272 |
+
"epoch": 0.7251602564102564,
|
1273 |
+
"grad_norm": 0.23584477603435516,
|
1274 |
+
"learning_rate": 7.369669791064084e-05,
|
1275 |
+
"loss": 0.1972,
|
1276 |
+
"step": 1810
|
1277 |
+
},
|
1278 |
+
{
|
1279 |
+
"epoch": 0.7291666666666666,
|
1280 |
+
"grad_norm": 0.23261332511901855,
|
1281 |
+
"learning_rate": 7.341053797617621e-05,
|
1282 |
+
"loss": 0.188,
|
1283 |
+
"step": 1820
|
1284 |
+
},
|
1285 |
+
{
|
1286 |
+
"epoch": 0.7331730769230769,
|
1287 |
+
"grad_norm": 0.23437419533729553,
|
1288 |
+
"learning_rate": 7.312339253395778e-05,
|
1289 |
+
"loss": 0.1912,
|
1290 |
+
"step": 1830
|
1291 |
+
},
|
1292 |
+
{
|
1293 |
+
"epoch": 0.7371794871794872,
|
1294 |
+
"grad_norm": 0.22874341905117035,
|
1295 |
+
"learning_rate": 7.283527367187778e-05,
|
1296 |
+
"loss": 0.1826,
|
1297 |
+
"step": 1840
|
1298 |
+
},
|
1299 |
+
{
|
1300 |
+
"epoch": 0.7411858974358975,
|
1301 |
+
"grad_norm": 0.21897387504577637,
|
1302 |
+
"learning_rate": 7.254619351880625e-05,
|
1303 |
+
"loss": 0.1765,
|
1304 |
+
"step": 1850
|
1305 |
+
},
|
1306 |
+
{
|
1307 |
+
"epoch": 0.7451923076923077,
|
1308 |
+
"grad_norm": 0.24442484974861145,
|
1309 |
+
"learning_rate": 7.225616424408045e-05,
|
1310 |
+
"loss": 0.1903,
|
1311 |
+
"step": 1860
|
1312 |
+
},
|
1313 |
+
{
|
1314 |
+
"epoch": 0.749198717948718,
|
1315 |
+
"grad_norm": 0.22574163973331451,
|
1316 |
+
"learning_rate": 7.19651980569926e-05,
|
1317 |
+
"loss": 0.1861,
|
1318 |
+
"step": 1870
|
1319 |
+
},
|
1320 |
+
{
|
1321 |
+
"epoch": 0.7532051282051282,
|
1322 |
+
"grad_norm": 0.2647426724433899,
|
1323 |
+
"learning_rate": 7.167330720627591e-05,
|
1324 |
+
"loss": 0.1838,
|
1325 |
+
"step": 1880
|
1326 |
+
},
|
1327 |
+
{
|
1328 |
+
"epoch": 0.7572115384615384,
|
1329 |
+
"grad_norm": 0.19669461250305176,
|
1330 |
+
"learning_rate": 7.138050397958888e-05,
|
1331 |
+
"loss": 0.178,
|
1332 |
+
"step": 1890
|
1333 |
+
},
|
1334 |
+
{
|
1335 |
+
"epoch": 0.7612179487179487,
|
1336 |
+
"grad_norm": 0.22219333052635193,
|
1337 |
+
"learning_rate": 7.108680070299813e-05,
|
1338 |
+
"loss": 0.1813,
|
1339 |
+
"step": 1900
|
1340 |
+
},
|
1341 |
+
{
|
1342 |
+
"epoch": 0.7652243589743589,
|
1343 |
+
"grad_norm": 0.24694056808948517,
|
1344 |
+
"learning_rate": 7.079220974045941e-05,
|
1345 |
+
"loss": 0.186,
|
1346 |
+
"step": 1910
|
1347 |
+
},
|
1348 |
+
{
|
1349 |
+
"epoch": 0.7692307692307693,
|
1350 |
+
"grad_norm": 0.2198621928691864,
|
1351 |
+
"learning_rate": 7.049674349329724e-05,
|
1352 |
+
"loss": 0.1883,
|
1353 |
+
"step": 1920
|
1354 |
+
},
|
1355 |
+
{
|
1356 |
+
"epoch": 0.7732371794871795,
|
1357 |
+
"grad_norm": 0.22908103466033936,
|
1358 |
+
"learning_rate": 7.020041439968274e-05,
|
1359 |
+
"loss": 0.1925,
|
1360 |
+
"step": 1930
|
1361 |
+
},
|
1362 |
+
{
|
1363 |
+
"epoch": 0.7772435897435898,
|
1364 |
+
"grad_norm": 0.2108490765094757,
|
1365 |
+
"learning_rate": 6.990323493411006e-05,
|
1366 |
+
"loss": 0.1832,
|
1367 |
+
"step": 1940
|
1368 |
+
},
|
1369 |
+
{
|
1370 |
+
"epoch": 0.78125,
|
1371 |
+
"grad_norm": 0.23686829209327698,
|
1372 |
+
"learning_rate": 6.960521760687129e-05,
|
1373 |
+
"loss": 0.1814,
|
1374 |
+
"step": 1950
|
1375 |
+
},
|
1376 |
+
{
|
1377 |
+
"epoch": 0.7852564102564102,
|
1378 |
+
"grad_norm": 0.21755458414554596,
|
1379 |
+
"learning_rate": 6.930637496352975e-05,
|
1380 |
+
"loss": 0.1869,
|
1381 |
+
"step": 1960
|
1382 |
+
},
|
1383 |
+
{
|
1384 |
+
"epoch": 0.7892628205128205,
|
1385 |
+
"grad_norm": 0.19528847932815552,
|
1386 |
+
"learning_rate": 6.90067195843919e-05,
|
1387 |
+
"loss": 0.181,
|
1388 |
+
"step": 1970
|
1389 |
+
},
|
1390 |
+
{
|
1391 |
+
"epoch": 0.7932692307692307,
|
1392 |
+
"grad_norm": 0.2116439789533615,
|
1393 |
+
"learning_rate": 6.870626408397775e-05,
|
1394 |
+
"loss": 0.1878,
|
1395 |
+
"step": 1980
|
1396 |
+
},
|
1397 |
+
{
|
1398 |
+
"epoch": 0.7972756410256411,
|
1399 |
+
"grad_norm": 0.21799945831298828,
|
1400 |
+
"learning_rate": 6.840502111048981e-05,
|
1401 |
+
"loss": 0.1774,
|
1402 |
+
"step": 1990
|
1403 |
+
},
|
1404 |
+
{
|
1405 |
+
"epoch": 0.8012820512820513,
|
1406 |
+
"grad_norm": 0.21898455917835236,
|
1407 |
+
"learning_rate": 6.810300334528069e-05,
|
1408 |
+
"loss": 0.1873,
|
1409 |
+
"step": 2000
|
1410 |
+
},
|
1411 |
+
{
|
1412 |
+
"epoch": 0.8052884615384616,
|
1413 |
+
"grad_norm": 0.23046636581420898,
|
1414 |
+
"learning_rate": 6.780022350231912e-05,
|
1415 |
+
"loss": 0.1817,
|
1416 |
+
"step": 2010
|
1417 |
+
},
|
1418 |
+
{
|
1419 |
+
"epoch": 0.8092948717948718,
|
1420 |
+
"grad_norm": 0.2145206779241562,
|
1421 |
+
"learning_rate": 6.749669432765496e-05,
|
1422 |
+
"loss": 0.1818,
|
1423 |
+
"step": 2020
|
1424 |
+
},
|
1425 |
+
{
|
1426 |
+
"epoch": 0.813301282051282,
|
1427 |
+
"grad_norm": 0.21499067544937134,
|
1428 |
+
"learning_rate": 6.719242859888244e-05,
|
1429 |
+
"loss": 0.1819,
|
1430 |
+
"step": 2030
|
1431 |
+
},
|
1432 |
+
{
|
1433 |
+
"epoch": 0.8173076923076923,
|
1434 |
+
"grad_norm": 0.23782077431678772,
|
1435 |
+
"learning_rate": 6.688743912460229e-05,
|
1436 |
+
"loss": 0.1813,
|
1437 |
+
"step": 2040
|
1438 |
+
},
|
1439 |
+
{
|
1440 |
+
"epoch": 0.8213141025641025,
|
1441 |
+
"grad_norm": 0.2248157560825348,
|
1442 |
+
"learning_rate": 6.65817387438827e-05,
|
1443 |
+
"loss": 0.1879,
|
1444 |
+
"step": 2050
|
1445 |
+
},
|
1446 |
+
{
|
1447 |
+
"epoch": 0.8253205128205128,
|
1448 |
+
"grad_norm": 0.25905272364616394,
|
1449 |
+
"learning_rate": 6.627534032571859e-05,
|
1450 |
+
"loss": 0.1895,
|
1451 |
+
"step": 2060
|
1452 |
+
},
|
1453 |
+
{
|
1454 |
+
"epoch": 0.8293269230769231,
|
1455 |
+
"grad_norm": 0.21141692996025085,
|
1456 |
+
"learning_rate": 6.596825676849006e-05,
|
1457 |
+
"loss": 0.1812,
|
1458 |
+
"step": 2070
|
1459 |
+
},
|
1460 |
+
{
|
1461 |
+
"epoch": 0.8333333333333334,
|
1462 |
+
"grad_norm": 0.2148115485906601,
|
1463 |
+
"learning_rate": 6.566050099941934e-05,
|
1464 |
+
"loss": 0.1766,
|
1465 |
+
"step": 2080
|
1466 |
+
},
|
1467 |
+
{
|
1468 |
+
"epoch": 0.8373397435897436,
|
1469 |
+
"grad_norm": 0.24514557421207428,
|
1470 |
+
"learning_rate": 6.535208597402658e-05,
|
1471 |
+
"loss": 0.1805,
|
1472 |
+
"step": 2090
|
1473 |
+
},
|
1474 |
+
{
|
1475 |
+
"epoch": 0.8413461538461539,
|
1476 |
+
"grad_norm": 0.20855912566184998,
|
1477 |
+
"learning_rate": 6.50430246755845e-05,
|
1478 |
+
"loss": 0.1908,
|
1479 |
+
"step": 2100
|
1480 |
+
},
|
1481 |
+
{
|
1482 |
+
"epoch": 0.8453525641025641,
|
1483 |
+
"grad_norm": 0.21720488369464874,
|
1484 |
+
"learning_rate": 6.47333301145718e-05,
|
1485 |
+
"loss": 0.2313,
|
1486 |
+
"step": 2110
|
1487 |
+
},
|
1488 |
+
{
|
1489 |
+
"epoch": 0.8493589743589743,
|
1490 |
+
"grad_norm": 0.22862492501735687,
|
1491 |
+
"learning_rate": 6.442301532812552e-05,
|
1492 |
+
"loss": 0.1867,
|
1493 |
+
"step": 2120
|
1494 |
+
},
|
1495 |
+
{
|
1496 |
+
"epoch": 0.8533653846153846,
|
1497 |
+
"grad_norm": 0.23019257187843323,
|
1498 |
+
"learning_rate": 6.411209337949214e-05,
|
1499 |
+
"loss": 0.1857,
|
1500 |
+
"step": 2130
|
1501 |
+
},
|
1502 |
+
{
|
1503 |
+
"epoch": 0.8573717948717948,
|
1504 |
+
"grad_norm": 0.21849659085273743,
|
1505 |
+
"learning_rate": 6.380057735747768e-05,
|
1506 |
+
"loss": 0.1795,
|
1507 |
+
"step": 2140
|
1508 |
+
},
|
1509 |
+
{
|
1510 |
+
"epoch": 0.8613782051282052,
|
1511 |
+
"grad_norm": 0.22794140875339508,
|
1512 |
+
"learning_rate": 6.348848037589683e-05,
|
1513 |
+
"loss": 0.1796,
|
1514 |
+
"step": 2150
|
1515 |
+
},
|
1516 |
+
{
|
1517 |
+
"epoch": 0.8653846153846154,
|
1518 |
+
"grad_norm": 0.22126458585262299,
|
1519 |
+
"learning_rate": 6.317581557302066e-05,
|
1520 |
+
"loss": 0.1854,
|
1521 |
+
"step": 2160
|
1522 |
+
},
|
1523 |
+
{
|
1524 |
+
"epoch": 0.8693910256410257,
|
1525 |
+
"grad_norm": 0.24870412051677704,
|
1526 |
+
"learning_rate": 6.286259611102377e-05,
|
1527 |
+
"loss": 0.1771,
|
1528 |
+
"step": 2170
|
1529 |
+
},
|
1530 |
+
{
|
1531 |
+
"epoch": 0.8733974358974359,
|
1532 |
+
"grad_norm": 0.226875439286232,
|
1533 |
+
"learning_rate": 6.254883517543006e-05,
|
1534 |
+
"loss": 0.1769,
|
1535 |
+
"step": 2180
|
1536 |
+
},
|
1537 |
+
{
|
1538 |
+
"epoch": 0.8774038461538461,
|
1539 |
+
"grad_norm": 0.2393677532672882,
|
1540 |
+
"learning_rate": 6.223454597455776e-05,
|
1541 |
+
"loss": 0.1878,
|
1542 |
+
"step": 2190
|
1543 |
+
},
|
1544 |
+
{
|
1545 |
+
"epoch": 0.8814102564102564,
|
1546 |
+
"grad_norm": 0.23450277745723724,
|
1547 |
+
"learning_rate": 6.191974173896329e-05,
|
1548 |
+
"loss": 0.1795,
|
1549 |
+
"step": 2200
|
1550 |
+
},
|
1551 |
+
{
|
1552 |
+
"epoch": 0.8854166666666666,
|
1553 |
+
"grad_norm": 0.23429277539253235,
|
1554 |
+
"learning_rate": 6.160443572088444e-05,
|
1555 |
+
"loss": 0.1809,
|
1556 |
+
"step": 2210
|
1557 |
+
},
|
1558 |
+
{
|
1559 |
+
"epoch": 0.8894230769230769,
|
1560 |
+
"grad_norm": 0.2641499638557434,
|
1561 |
+
"learning_rate": 6.128864119368234e-05,
|
1562 |
+
"loss": 0.1908,
|
1563 |
+
"step": 2220
|
1564 |
+
},
|
1565 |
+
{
|
1566 |
+
"epoch": 0.8934294871794872,
|
1567 |
+
"grad_norm": 0.25299501419067383,
|
1568 |
+
"learning_rate": 6.0972371451282817e-05,
|
1569 |
+
"loss": 0.1935,
|
1570 |
+
"step": 2230
|
1571 |
+
},
|
1572 |
+
{
|
1573 |
+
"epoch": 0.8974358974358975,
|
1574 |
+
"grad_norm": 0.21204617619514465,
|
1575 |
+
"learning_rate": 6.0655639807616705e-05,
|
1576 |
+
"loss": 0.1871,
|
1577 |
+
"step": 2240
|
1578 |
+
},
|
1579 |
+
{
|
1580 |
+
"epoch": 0.9014423076923077,
|
1581 |
+
"grad_norm": 0.20044928789138794,
|
1582 |
+
"learning_rate": 6.0338459596059395e-05,
|
1583 |
+
"loss": 0.185,
|
1584 |
+
"step": 2250
|
1585 |
+
},
|
1586 |
+
{
|
1587 |
+
"epoch": 0.905448717948718,
|
1588 |
+
"grad_norm": 0.22311033308506012,
|
1589 |
+
"learning_rate": 6.0020844168869496e-05,
|
1590 |
+
"loss": 0.1809,
|
1591 |
+
"step": 2260
|
1592 |
+
},
|
1593 |
+
{
|
1594 |
+
"epoch": 0.9094551282051282,
|
1595 |
+
"grad_norm": 0.2073046863079071,
|
1596 |
+
"learning_rate": 5.970280689662685e-05,
|
1597 |
+
"loss": 0.1822,
|
1598 |
+
"step": 2270
|
1599 |
+
},
|
1600 |
+
{
|
1601 |
+
"epoch": 0.9134615384615384,
|
1602 |
+
"grad_norm": 0.23054327070713043,
|
1603 |
+
"learning_rate": 5.938436116766954e-05,
|
1604 |
+
"loss": 0.1862,
|
1605 |
+
"step": 2280
|
1606 |
+
},
|
1607 |
+
{
|
1608 |
+
"epoch": 0.9174679487179487,
|
1609 |
+
"grad_norm": 0.2098427712917328,
|
1610 |
+
"learning_rate": 5.9065520387530394e-05,
|
1611 |
+
"loss": 0.1766,
|
1612 |
+
"step": 2290
|
1613 |
+
},
|
1614 |
+
{
|
1615 |
+
"epoch": 0.9214743589743589,
|
1616 |
+
"grad_norm": 0.2541731595993042,
|
1617 |
+
"learning_rate": 5.874629797837259e-05,
|
1618 |
+
"loss": 0.1779,
|
1619 |
+
"step": 2300
|
1620 |
+
},
|
1621 |
+
{
|
1622 |
+
"epoch": 0.9254807692307693,
|
1623 |
+
"grad_norm": 0.22261784970760345,
|
1624 |
+
"learning_rate": 5.8426707378424675e-05,
|
1625 |
+
"loss": 0.1885,
|
1626 |
+
"step": 2310
|
1627 |
+
},
|
1628 |
+
{
|
1629 |
+
"epoch": 0.9294871794871795,
|
1630 |
+
"grad_norm": 0.23702876269817352,
|
1631 |
+
"learning_rate": 5.8106762041414795e-05,
|
1632 |
+
"loss": 0.1808,
|
1633 |
+
"step": 2320
|
1634 |
+
},
|
1635 |
+
{
|
1636 |
+
"epoch": 0.9334935897435898,
|
1637 |
+
"grad_norm": 0.22513940930366516,
|
1638 |
+
"learning_rate": 5.778647543600443e-05,
|
1639 |
+
"loss": 0.1861,
|
1640 |
+
"step": 2330
|
1641 |
+
},
|
1642 |
+
{
|
1643 |
+
"epoch": 0.9375,
|
1644 |
+
"grad_norm": 0.2372877299785614,
|
1645 |
+
"learning_rate": 5.7465861045221295e-05,
|
1646 |
+
"loss": 0.1831,
|
1647 |
+
"step": 2340
|
1648 |
+
},
|
1649 |
+
{
|
1650 |
+
"epoch": 0.9415064102564102,
|
1651 |
+
"grad_norm": 0.2384011596441269,
|
1652 |
+
"learning_rate": 5.714493236589187e-05,
|
1653 |
+
"loss": 0.1835,
|
1654 |
+
"step": 2350
|
1655 |
+
},
|
1656 |
+
{
|
1657 |
+
"epoch": 0.9455128205128205,
|
1658 |
+
"grad_norm": 0.22022205591201782,
|
1659 |
+
"learning_rate": 5.6823702908073104e-05,
|
1660 |
+
"loss": 0.1836,
|
1661 |
+
"step": 2360
|
1662 |
+
},
|
1663 |
+
{
|
1664 |
+
"epoch": 0.9495192307692307,
|
1665 |
+
"grad_norm": 0.2236844301223755,
|
1666 |
+
"learning_rate": 5.6502186194483783e-05,
|
1667 |
+
"loss": 0.1797,
|
1668 |
+
"step": 2370
|
1669 |
+
},
|
1670 |
+
{
|
1671 |
+
"epoch": 0.9535256410256411,
|
1672 |
+
"grad_norm": 0.24858827888965607,
|
1673 |
+
"learning_rate": 5.6180395759935234e-05,
|
1674 |
+
"loss": 0.1947,
|
1675 |
+
"step": 2380
|
1676 |
+
},
|
1677 |
+
{
|
1678 |
+
"epoch": 0.9575320512820513,
|
1679 |
+
"grad_norm": 0.19967874884605408,
|
1680 |
+
"learning_rate": 5.5858345150761514e-05,
|
1681 |
+
"loss": 0.1831,
|
1682 |
+
"step": 2390
|
1683 |
+
},
|
1684 |
+
{
|
1685 |
+
"epoch": 0.9615384615384616,
|
1686 |
+
"grad_norm": 0.25792399048805237,
|
1687 |
+
"learning_rate": 5.553604792424922e-05,
|
1688 |
+
"loss": 0.1875,
|
1689 |
+
"step": 2400
|
1690 |
+
},
|
1691 |
+
{
|
1692 |
+
"epoch": 0.9655448717948718,
|
1693 |
+
"grad_norm": 0.22758032381534576,
|
1694 |
+
"learning_rate": 5.521351764806671e-05,
|
1695 |
+
"loss": 0.1851,
|
1696 |
+
"step": 2410
|
1697 |
+
},
|
1698 |
+
{
|
1699 |
+
"epoch": 0.969551282051282,
|
1700 |
+
"grad_norm": 0.20984916388988495,
|
1701 |
+
"learning_rate": 5.4890767899693015e-05,
|
1702 |
+
"loss": 0.1811,
|
1703 |
+
"step": 2420
|
1704 |
+
},
|
1705 |
+
{
|
1706 |
+
"epoch": 0.9735576923076923,
|
1707 |
+
"grad_norm": 0.2236003577709198,
|
1708 |
+
"learning_rate": 5.4567812265846206e-05,
|
1709 |
+
"loss": 0.1824,
|
1710 |
+
"step": 2430
|
1711 |
+
},
|
1712 |
+
{
|
1713 |
+
"epoch": 0.9775641025641025,
|
1714 |
+
"grad_norm": 0.2495725303888321,
|
1715 |
+
"learning_rate": 5.424466434191146e-05,
|
1716 |
+
"loss": 0.1838,
|
1717 |
+
"step": 2440
|
1718 |
+
},
|
1719 |
+
{
|
1720 |
+
"epoch": 0.9815705128205128,
|
1721 |
+
"grad_norm": 0.21274955570697784,
|
1722 |
+
"learning_rate": 5.392133773136877e-05,
|
1723 |
+
"loss": 0.1818,
|
1724 |
+
"step": 2450
|
1725 |
+
},
|
1726 |
+
{
|
1727 |
+
"epoch": 0.9855769230769231,
|
1728 |
+
"grad_norm": 0.24202273786067963,
|
1729 |
+
"learning_rate": 5.359784604522023e-05,
|
1730 |
+
"loss": 0.1821,
|
1731 |
+
"step": 2460
|
1732 |
+
},
|
1733 |
+
{
|
1734 |
+
"epoch": 0.9895833333333334,
|
1735 |
+
"grad_norm": 0.21269406378269196,
|
1736 |
+
"learning_rate": 5.3274202901417115e-05,
|
1737 |
+
"loss": 0.1853,
|
1738 |
+
"step": 2470
|
1739 |
+
},
|
1740 |
+
{
|
1741 |
+
"epoch": 0.9935897435897436,
|
1742 |
+
"grad_norm": 0.2370026856660843,
|
1743 |
+
"learning_rate": 5.2950421924286544e-05,
|
1744 |
+
"loss": 0.167,
|
1745 |
+
"step": 2480
|
1746 |
+
},
|
1747 |
+
{
|
1748 |
+
"epoch": 0.9975961538461539,
|
1749 |
+
"grad_norm": 0.1984049528837204,
|
1750 |
+
"learning_rate": 5.262651674395799e-05,
|
1751 |
+
"loss": 0.1715,
|
1752 |
+
"step": 2490
|
1753 |
+
},
|
1754 |
+
{
|
1755 |
+
"epoch": 1.0,
|
1756 |
+
"eval_loss": 0.18003696203231812,
|
1757 |
+
"eval_runtime": 312.955,
|
1758 |
+
"eval_samples_per_second": 26.863,
|
1759 |
+
"eval_steps_per_second": 3.358,
|
1760 |
+
"step": 2496
|
1761 |
+
},
|
1762 |
+
{
|
1763 |
+
"epoch": 1.001602564102564,
|
1764 |
+
"grad_norm": 0.2148449867963791,
|
1765 |
+
"learning_rate": 5.230250099578945e-05,
|
1766 |
+
"loss": 0.1671,
|
1767 |
+
"step": 2500
|
1768 |
+
},
|
1769 |
+
{
|
1770 |
+
"epoch": 1.0056089743589745,
|
1771 |
+
"grad_norm": 0.23484507203102112,
|
1772 |
+
"learning_rate": 5.197838831979351e-05,
|
1773 |
+
"loss": 0.1478,
|
1774 |
+
"step": 2510
|
1775 |
+
},
|
1776 |
+
{
|
1777 |
+
"epoch": 1.0096153846153846,
|
1778 |
+
"grad_norm": 0.23629869520664215,
|
1779 |
+
"learning_rate": 5.165419236006308e-05,
|
1780 |
+
"loss": 0.1466,
|
1781 |
+
"step": 2520
|
1782 |
+
},
|
1783 |
+
{
|
1784 |
+
"epoch": 1.013621794871795,
|
1785 |
+
"grad_norm": 0.2193659245967865,
|
1786 |
+
"learning_rate": 5.132992676419703e-05,
|
1787 |
+
"loss": 0.1487,
|
1788 |
+
"step": 2530
|
1789 |
+
},
|
1790 |
+
{
|
1791 |
+
"epoch": 1.017628205128205,
|
1792 |
+
"grad_norm": 0.23937292397022247,
|
1793 |
+
"learning_rate": 5.100560518272573e-05,
|
1794 |
+
"loss": 0.1453,
|
1795 |
+
"step": 2540
|
1796 |
+
},
|
1797 |
+
{
|
1798 |
+
"epoch": 1.0216346153846154,
|
1799 |
+
"grad_norm": 0.22235561907291412,
|
1800 |
+
"learning_rate": 5.068124126853633e-05,
|
1801 |
+
"loss": 0.1497,
|
1802 |
+
"step": 2550
|
1803 |
+
},
|
1804 |
+
{
|
1805 |
+
"epoch": 1.0256410256410255,
|
1806 |
+
"grad_norm": 0.22830457985401154,
|
1807 |
+
"learning_rate": 5.035684867629803e-05,
|
1808 |
+
"loss": 0.1532,
|
1809 |
+
"step": 2560
|
1810 |
+
},
|
1811 |
+
{
|
1812 |
+
"epoch": 1.029647435897436,
|
1813 |
+
"grad_norm": 0.23195677995681763,
|
1814 |
+
"learning_rate": 5.003244106188735e-05,
|
1815 |
+
"loss": 0.1531,
|
1816 |
+
"step": 2570
|
1817 |
+
},
|
1818 |
+
{
|
1819 |
+
"epoch": 1.0336538461538463,
|
1820 |
+
"grad_norm": 0.24194592237472534,
|
1821 |
+
"learning_rate": 4.9708032081813144e-05,
|
1822 |
+
"loss": 0.1543,
|
1823 |
+
"step": 2580
|
1824 |
+
},
|
1825 |
+
{
|
1826 |
+
"epoch": 1.0376602564102564,
|
1827 |
+
"grad_norm": 0.24159836769104004,
|
1828 |
+
"learning_rate": 4.938363539264175e-05,
|
1829 |
+
"loss": 0.1569,
|
1830 |
+
"step": 2590
|
1831 |
+
},
|
1832 |
+
{
|
1833 |
+
"epoch": 1.0416666666666667,
|
1834 |
+
"grad_norm": 0.24700869619846344,
|
1835 |
+
"learning_rate": 4.90592646504221e-05,
|
1836 |
+
"loss": 0.1502,
|
1837 |
+
"step": 2600
|
1838 |
+
},
|
1839 |
+
{
|
1840 |
+
"epoch": 1.0456730769230769,
|
1841 |
+
"grad_norm": 0.24695070087909698,
|
1842 |
+
"learning_rate": 4.8734933510110905e-05,
|
1843 |
+
"loss": 0.1555,
|
1844 |
+
"step": 2610
|
1845 |
+
},
|
1846 |
+
{
|
1847 |
+
"epoch": 1.0496794871794872,
|
1848 |
+
"grad_norm": 0.21207590401172638,
|
1849 |
+
"learning_rate": 4.841065562499769e-05,
|
1850 |
+
"loss": 0.1495,
|
1851 |
+
"step": 2620
|
1852 |
+
},
|
1853 |
+
{
|
1854 |
+
"epoch": 1.0536858974358974,
|
1855 |
+
"grad_norm": 0.22604689002037048,
|
1856 |
+
"learning_rate": 4.8086444646130144e-05,
|
1857 |
+
"loss": 0.1505,
|
1858 |
+
"step": 2630
|
1859 |
+
},
|
1860 |
+
{
|
1861 |
+
"epoch": 1.0576923076923077,
|
1862 |
+
"grad_norm": 0.23026780784130096,
|
1863 |
+
"learning_rate": 4.7762314221739416e-05,
|
1864 |
+
"loss": 0.1414,
|
1865 |
+
"step": 2640
|
1866 |
+
},
|
1867 |
+
{
|
1868 |
+
"epoch": 1.061698717948718,
|
1869 |
+
"grad_norm": 0.2474188357591629,
|
1870 |
+
"learning_rate": 4.7438277996665546e-05,
|
1871 |
+
"loss": 0.1563,
|
1872 |
+
"step": 2650
|
1873 |
+
},
|
1874 |
+
{
|
1875 |
+
"epoch": 1.0657051282051282,
|
1876 |
+
"grad_norm": 0.2669748067855835,
|
1877 |
+
"learning_rate": 4.7114349611783124e-05,
|
1878 |
+
"loss": 0.1446,
|
1879 |
+
"step": 2660
|
1880 |
+
},
|
1881 |
+
{
|
1882 |
+
"epoch": 1.0697115384615385,
|
1883 |
+
"grad_norm": 0.2164994478225708,
|
1884 |
+
"learning_rate": 4.679054270342703e-05,
|
1885 |
+
"loss": 0.1557,
|
1886 |
+
"step": 2670
|
1887 |
+
},
|
1888 |
+
{
|
1889 |
+
"epoch": 1.0737179487179487,
|
1890 |
+
"grad_norm": 0.2127254158258438,
|
1891 |
+
"learning_rate": 4.646687090281832e-05,
|
1892 |
+
"loss": 0.1489,
|
1893 |
+
"step": 2680
|
1894 |
+
},
|
1895 |
+
{
|
1896 |
+
"epoch": 1.077724358974359,
|
1897 |
+
"grad_norm": 0.25909334421157837,
|
1898 |
+
"learning_rate": 4.614334783549049e-05,
|
1899 |
+
"loss": 0.1517,
|
1900 |
+
"step": 2690
|
1901 |
+
},
|
1902 |
+
{
|
1903 |
+
"epoch": 1.0817307692307692,
|
1904 |
+
"grad_norm": 0.20796196162700653,
|
1905 |
+
"learning_rate": 4.581998712071583e-05,
|
1906 |
+
"loss": 0.1459,
|
1907 |
+
"step": 2700
|
1908 |
+
},
|
1909 |
+
{
|
1910 |
+
"epoch": 1.0857371794871795,
|
1911 |
+
"grad_norm": 0.21044594049453735,
|
1912 |
+
"learning_rate": 4.549680237093215e-05,
|
1913 |
+
"loss": 0.1508,
|
1914 |
+
"step": 2710
|
1915 |
+
},
|
1916 |
+
{
|
1917 |
+
"epoch": 1.0897435897435896,
|
1918 |
+
"grad_norm": 0.22035610675811768,
|
1919 |
+
"learning_rate": 4.517380719116966e-05,
|
1920 |
+
"loss": 0.1518,
|
1921 |
+
"step": 2720
|
1922 |
+
},
|
1923 |
+
{
|
1924 |
+
"epoch": 1.09375,
|
1925 |
+
"grad_norm": 0.2175433337688446,
|
1926 |
+
"learning_rate": 4.485101517847831e-05,
|
1927 |
+
"loss": 0.1532,
|
1928 |
+
"step": 2730
|
1929 |
+
},
|
1930 |
+
{
|
1931 |
+
"epoch": 1.0977564102564104,
|
1932 |
+
"grad_norm": 0.23213978111743927,
|
1933 |
+
"learning_rate": 4.452843992135536e-05,
|
1934 |
+
"loss": 0.1503,
|
1935 |
+
"step": 2740
|
1936 |
+
},
|
1937 |
+
{
|
1938 |
+
"epoch": 1.1017628205128205,
|
1939 |
+
"grad_norm": 0.22997038066387177,
|
1940 |
+
"learning_rate": 4.420609499917337e-05,
|
1941 |
+
"loss": 0.1532,
|
1942 |
+
"step": 2750
|
1943 |
+
},
|
1944 |
+
{
|
1945 |
+
"epoch": 1.1057692307692308,
|
1946 |
+
"grad_norm": 0.24814608693122864,
|
1947 |
+
"learning_rate": 4.3883993981608576e-05,
|
1948 |
+
"loss": 0.1541,
|
1949 |
+
"step": 2760
|
1950 |
+
},
|
1951 |
+
{
|
1952 |
+
"epoch": 1.109775641025641,
|
1953 |
+
"grad_norm": 0.24005189538002014,
|
1954 |
+
"learning_rate": 4.3562150428069565e-05,
|
1955 |
+
"loss": 0.1493,
|
1956 |
+
"step": 2770
|
1957 |
+
},
|
1958 |
+
{
|
1959 |
+
"epoch": 1.1137820512820513,
|
1960 |
+
"grad_norm": 0.24364899098873138,
|
1961 |
+
"learning_rate": 4.3240577887126565e-05,
|
1962 |
+
"loss": 0.1507,
|
1963 |
+
"step": 2780
|
1964 |
+
},
|
1965 |
+
{
|
1966 |
+
"epoch": 1.1177884615384615,
|
1967 |
+
"grad_norm": 0.25002944469451904,
|
1968 |
+
"learning_rate": 4.291928989594101e-05,
|
1969 |
+
"loss": 0.1493,
|
1970 |
+
"step": 2790
|
1971 |
+
},
|
1972 |
+
{
|
1973 |
+
"epoch": 1.1217948717948718,
|
1974 |
+
"grad_norm": 0.24269698560237885,
|
1975 |
+
"learning_rate": 4.2598299979695795e-05,
|
1976 |
+
"loss": 0.146,
|
1977 |
+
"step": 2800
|
1978 |
+
},
|
1979 |
+
{
|
1980 |
+
"epoch": 1.125801282051282,
|
1981 |
+
"grad_norm": 0.2566970884799957,
|
1982 |
+
"learning_rate": 4.2277621651025736e-05,
|
1983 |
+
"loss": 0.1498,
|
1984 |
+
"step": 2810
|
1985 |
+
},
|
1986 |
+
{
|
1987 |
+
"epoch": 1.1298076923076923,
|
1988 |
+
"grad_norm": 0.24423649907112122,
|
1989 |
+
"learning_rate": 4.195726840944886e-05,
|
1990 |
+
"loss": 0.1562,
|
1991 |
+
"step": 2820
|
1992 |
+
},
|
1993 |
+
{
|
1994 |
+
"epoch": 1.1338141025641026,
|
1995 |
+
"grad_norm": 0.2457042932510376,
|
1996 |
+
"learning_rate": 4.1637253740798075e-05,
|
1997 |
+
"loss": 0.1532,
|
1998 |
+
"step": 2830
|
1999 |
+
},
|
2000 |
+
{
|
2001 |
+
"epoch": 1.1378205128205128,
|
2002 |
+
"grad_norm": 0.2585982382297516,
|
2003 |
+
"learning_rate": 4.131759111665349e-05,
|
2004 |
+
"loss": 0.1487,
|
2005 |
+
"step": 2840
|
2006 |
+
},
|
2007 |
+
{
|
2008 |
+
"epoch": 1.1418269230769231,
|
2009 |
+
"grad_norm": 0.2370419055223465,
|
2010 |
+
"learning_rate": 4.0998293993775237e-05,
|
2011 |
+
"loss": 0.1442,
|
2012 |
+
"step": 2850
|
2013 |
+
},
|
2014 |
+
{
|
2015 |
+
"epoch": 1.1458333333333333,
|
2016 |
+
"grad_norm": 0.25113531947135925,
|
2017 |
+
"learning_rate": 4.067937581353708e-05,
|
2018 |
+
"loss": 0.1459,
|
2019 |
+
"step": 2860
|
2020 |
+
},
|
2021 |
+
{
|
2022 |
+
"epoch": 1.1498397435897436,
|
2023 |
+
"grad_norm": 0.22391347587108612,
|
2024 |
+
"learning_rate": 4.036085000136046e-05,
|
2025 |
+
"loss": 0.149,
|
2026 |
+
"step": 2870
|
2027 |
+
},
|
2028 |
+
{
|
2029 |
+
"epoch": 1.1538461538461537,
|
2030 |
+
"grad_norm": 0.2450188249349594,
|
2031 |
+
"learning_rate": 4.004272996614948e-05,
|
2032 |
+
"loss": 0.1402,
|
2033 |
+
"step": 2880
|
2034 |
+
},
|
2035 |
+
{
|
2036 |
+
"epoch": 1.157852564102564,
|
2037 |
+
"grad_norm": 0.2271914780139923,
|
2038 |
+
"learning_rate": 3.972502909972629e-05,
|
2039 |
+
"loss": 0.1488,
|
2040 |
+
"step": 2890
|
2041 |
+
},
|
2042 |
+
{
|
2043 |
+
"epoch": 1.1618589743589745,
|
2044 |
+
"grad_norm": 0.2330724447965622,
|
2045 |
+
"learning_rate": 3.940776077626739e-05,
|
2046 |
+
"loss": 0.1517,
|
2047 |
+
"step": 2900
|
2048 |
+
},
|
2049 |
+
{
|
2050 |
+
"epoch": 1.1658653846153846,
|
2051 |
+
"grad_norm": 0.23422060906887054,
|
2052 |
+
"learning_rate": 3.909093835174066e-05,
|
2053 |
+
"loss": 0.1475,
|
2054 |
+
"step": 2910
|
2055 |
+
},
|
2056 |
+
{
|
2057 |
+
"epoch": 1.169871794871795,
|
2058 |
+
"grad_norm": 0.2604200541973114,
|
2059 |
+
"learning_rate": 3.8774575163343065e-05,
|
2060 |
+
"loss": 0.1531,
|
2061 |
+
"step": 2920
|
2062 |
+
},
|
2063 |
+
{
|
2064 |
+
"epoch": 1.173878205128205,
|
2065 |
+
"grad_norm": 0.23886078596115112,
|
2066 |
+
"learning_rate": 3.8458684528939185e-05,
|
2067 |
+
"loss": 0.142,
|
2068 |
+
"step": 2930
|
2069 |
+
},
|
2070 |
+
{
|
2071 |
+
"epoch": 1.1778846153846154,
|
2072 |
+
"grad_norm": 0.24594782292842865,
|
2073 |
+
"learning_rate": 3.814327974650067e-05,
|
2074 |
+
"loss": 0.1477,
|
2075 |
+
"step": 2940
|
2076 |
+
},
|
2077 |
+
{
|
2078 |
+
"epoch": 1.1818910256410255,
|
2079 |
+
"grad_norm": 0.247484028339386,
|
2080 |
+
"learning_rate": 3.7828374093546306e-05,
|
2081 |
+
"loss": 0.1516,
|
2082 |
+
"step": 2950
|
2083 |
+
},
|
2084 |
+
{
|
2085 |
+
"epoch": 1.185897435897436,
|
2086 |
+
"grad_norm": 0.22961559891700745,
|
2087 |
+
"learning_rate": 3.751398082658322e-05,
|
2088 |
+
"loss": 0.1508,
|
2089 |
+
"step": 2960
|
2090 |
+
},
|
2091 |
+
{
|
2092 |
+
"epoch": 1.1899038461538463,
|
2093 |
+
"grad_norm": 0.2492343634366989,
|
2094 |
+
"learning_rate": 3.720011318054871e-05,
|
2095 |
+
"loss": 0.1412,
|
2096 |
+
"step": 2970
|
2097 |
+
},
|
2098 |
+
{
|
2099 |
+
"epoch": 1.1939102564102564,
|
2100 |
+
"grad_norm": 0.24057136476039886,
|
2101 |
+
"learning_rate": 3.688678436825313e-05,
|
2102 |
+
"loss": 0.1476,
|
2103 |
+
"step": 2980
|
2104 |
+
},
|
2105 |
+
{
|
2106 |
+
"epoch": 1.1979166666666667,
|
2107 |
+
"grad_norm": 0.2430902123451233,
|
2108 |
+
"learning_rate": 3.657400757982366e-05,
|
2109 |
+
"loss": 0.1506,
|
2110 |
+
"step": 2990
|
2111 |
+
},
|
2112 |
+
{
|
2113 |
+
"epoch": 1.2019230769230769,
|
2114 |
+
"grad_norm": 0.23617245256900787,
|
2115 |
+
"learning_rate": 3.626179598214917e-05,
|
2116 |
+
"loss": 0.1454,
|
2117 |
+
"step": 3000
|
2118 |
+
},
|
2119 |
+
{
|
2120 |
+
"epoch": 1.2059294871794872,
|
2121 |
+
"grad_norm": 0.26724281907081604,
|
2122 |
+
"learning_rate": 3.595016271832572e-05,
|
2123 |
+
"loss": 0.1435,
|
2124 |
+
"step": 3010
|
2125 |
+
},
|
2126 |
+
{
|
2127 |
+
"epoch": 1.2099358974358974,
|
2128 |
+
"grad_norm": 0.24820230901241302,
|
2129 |
+
"learning_rate": 3.5639120907103416e-05,
|
2130 |
+
"loss": 0.1435,
|
2131 |
+
"step": 3020
|
2132 |
+
},
|
2133 |
+
{
|
2134 |
+
"epoch": 1.2139423076923077,
|
2135 |
+
"grad_norm": 0.2463800460100174,
|
2136 |
+
"learning_rate": 3.532868364233416e-05,
|
2137 |
+
"loss": 0.1529,
|
2138 |
+
"step": 3030
|
2139 |
+
},
|
2140 |
+
{
|
2141 |
+
"epoch": 1.217948717948718,
|
2142 |
+
"grad_norm": 0.25976675748825073,
|
2143 |
+
"learning_rate": 3.501886399242038e-05,
|
2144 |
+
"loss": 0.15,
|
2145 |
+
"step": 3040
|
2146 |
+
},
|
2147 |
+
{
|
2148 |
+
"epoch": 1.2219551282051282,
|
2149 |
+
"grad_norm": 0.22920717298984528,
|
2150 |
+
"learning_rate": 3.470967499976492e-05,
|
2151 |
+
"loss": 0.1449,
|
2152 |
+
"step": 3050
|
2153 |
+
},
|
2154 |
+
{
|
2155 |
+
"epoch": 1.2259615384615385,
|
2156 |
+
"grad_norm": 0.2552580237388611,
|
2157 |
+
"learning_rate": 3.440112968022201e-05,
|
2158 |
+
"loss": 0.1453,
|
2159 |
+
"step": 3060
|
2160 |
+
},
|
2161 |
+
{
|
2162 |
+
"epoch": 1.2299679487179487,
|
2163 |
+
"grad_norm": 0.22986732423305511,
|
2164 |
+
"learning_rate": 3.409324102254932e-05,
|
2165 |
+
"loss": 0.1434,
|
2166 |
+
"step": 3070
|
2167 |
+
},
|
2168 |
+
{
|
2169 |
+
"epoch": 1.233974358974359,
|
2170 |
+
"grad_norm": 0.2583804130554199,
|
2171 |
+
"learning_rate": 3.37860219878612e-05,
|
2172 |
+
"loss": 0.1532,
|
2173 |
+
"step": 3080
|
2174 |
+
},
|
2175 |
+
{
|
2176 |
+
"epoch": 1.2379807692307692,
|
2177 |
+
"grad_norm": 0.24155107140541077,
|
2178 |
+
"learning_rate": 3.347948550908303e-05,
|
2179 |
+
"loss": 0.1482,
|
2180 |
+
"step": 3090
|
2181 |
+
},
|
2182 |
+
{
|
2183 |
+
"epoch": 1.2419871794871795,
|
2184 |
+
"grad_norm": 0.25099289417266846,
|
2185 |
+
"learning_rate": 3.31736444904068e-05,
|
2186 |
+
"loss": 0.1494,
|
2187 |
+
"step": 3100
|
2188 |
+
},
|
2189 |
+
{
|
2190 |
+
"epoch": 1.2459935897435896,
|
2191 |
+
"grad_norm": 0.26350319385528564,
|
2192 |
+
"learning_rate": 3.286851180674788e-05,
|
2193 |
+
"loss": 0.1441,
|
2194 |
+
"step": 3110
|
2195 |
+
},
|
2196 |
+
{
|
2197 |
+
"epoch": 1.25,
|
2198 |
+
"grad_norm": 0.23903068900108337,
|
2199 |
+
"learning_rate": 3.2564100303203035e-05,
|
2200 |
+
"loss": 0.1455,
|
2201 |
+
"step": 3120
|
2202 |
+
},
|
2203 |
+
{
|
2204 |
+
"epoch": 1.2540064102564101,
|
2205 |
+
"grad_norm": 0.25470852851867676,
|
2206 |
+
"learning_rate": 3.22604227945097e-05,
|
2207 |
+
"loss": 0.149,
|
2208 |
+
"step": 3130
|
2209 |
+
},
|
2210 |
+
{
|
2211 |
+
"epoch": 1.2580128205128205,
|
2212 |
+
"grad_norm": 0.25256025791168213,
|
2213 |
+
"learning_rate": 3.195749206450649e-05,
|
2214 |
+
"loss": 0.1484,
|
2215 |
+
"step": 3140
|
2216 |
+
},
|
2217 |
+
{
|
2218 |
+
"epoch": 1.2620192307692308,
|
2219 |
+
"grad_norm": 0.2604450583457947,
|
2220 |
+
"learning_rate": 3.165532086559504e-05,
|
2221 |
+
"loss": 0.1438,
|
2222 |
+
"step": 3150
|
2223 |
+
},
|
2224 |
+
{
|
2225 |
+
"epoch": 1.266025641025641,
|
2226 |
+
"grad_norm": 0.2456076741218567,
|
2227 |
+
"learning_rate": 3.135392191820324e-05,
|
2228 |
+
"loss": 0.1475,
|
2229 |
+
"step": 3160
|
2230 |
+
},
|
2231 |
+
{
|
2232 |
+
"epoch": 1.2700320512820513,
|
2233 |
+
"grad_norm": 0.23290812969207764,
|
2234 |
+
"learning_rate": 3.1053307910249654e-05,
|
2235 |
+
"loss": 0.1473,
|
2236 |
+
"step": 3170
|
2237 |
+
},
|
2238 |
+
{
|
2239 |
+
"epoch": 1.2740384615384617,
|
2240 |
+
"grad_norm": 0.2368566393852234,
|
2241 |
+
"learning_rate": 3.0753491496609445e-05,
|
2242 |
+
"loss": 0.1468,
|
2243 |
+
"step": 3180
|
2244 |
+
},
|
2245 |
+
{
|
2246 |
+
"epoch": 1.2780448717948718,
|
2247 |
+
"grad_norm": 0.242570161819458,
|
2248 |
+
"learning_rate": 3.045448529858165e-05,
|
2249 |
+
"loss": 0.1489,
|
2250 |
+
"step": 3190
|
2251 |
+
},
|
2252 |
+
{
|
2253 |
+
"epoch": 1.282051282051282,
|
2254 |
+
"grad_norm": 0.23196978867053986,
|
2255 |
+
"learning_rate": 3.0156301903357864e-05,
|
2256 |
+
"loss": 0.1479,
|
2257 |
+
"step": 3200
|
2258 |
+
},
|
2259 |
+
{
|
2260 |
+
"epoch": 1.2860576923076923,
|
2261 |
+
"grad_norm": 0.2525078356266022,
|
2262 |
+
"learning_rate": 2.9858953863492334e-05,
|
2263 |
+
"loss": 0.1508,
|
2264 |
+
"step": 3210
|
2265 |
+
},
|
2266 |
+
{
|
2267 |
+
"epoch": 1.2900641025641026,
|
2268 |
+
"grad_norm": 0.23984560370445251,
|
2269 |
+
"learning_rate": 2.956245369637356e-05,
|
2270 |
+
"loss": 0.1428,
|
2271 |
+
"step": 3220
|
2272 |
+
},
|
2273 |
+
{
|
2274 |
+
"epoch": 1.2940705128205128,
|
2275 |
+
"grad_norm": 0.2553931176662445,
|
2276 |
+
"learning_rate": 2.9266813883697342e-05,
|
2277 |
+
"loss": 0.1542,
|
2278 |
+
"step": 3230
|
2279 |
+
},
|
2280 |
+
{
|
2281 |
+
"epoch": 1.2980769230769231,
|
2282 |
+
"grad_norm": 0.2719983458518982,
|
2283 |
+
"learning_rate": 2.897204687094136e-05,
|
2284 |
+
"loss": 0.1533,
|
2285 |
+
"step": 3240
|
2286 |
+
},
|
2287 |
+
{
|
2288 |
+
"epoch": 1.3020833333333333,
|
2289 |
+
"grad_norm": 0.26820674538612366,
|
2290 |
+
"learning_rate": 2.8678165066841257e-05,
|
2291 |
+
"loss": 0.144,
|
2292 |
+
"step": 3250
|
2293 |
+
},
|
2294 |
+
{
|
2295 |
+
"epoch": 1.3060897435897436,
|
2296 |
+
"grad_norm": 0.22624927759170532,
|
2297 |
+
"learning_rate": 2.8385180842868207e-05,
|
2298 |
+
"loss": 0.1453,
|
2299 |
+
"step": 3260
|
2300 |
+
},
|
2301 |
+
{
|
2302 |
+
"epoch": 1.3100961538461537,
|
2303 |
+
"grad_norm": 0.2596217095851898,
|
2304 |
+
"learning_rate": 2.8093106532708253e-05,
|
2305 |
+
"loss": 0.1365,
|
2306 |
+
"step": 3270
|
2307 |
+
},
|
2308 |
+
{
|
2309 |
+
"epoch": 1.314102564102564,
|
2310 |
+
"grad_norm": 0.24350501596927643,
|
2311 |
+
"learning_rate": 2.780195443174293e-05,
|
2312 |
+
"loss": 0.1458,
|
2313 |
+
"step": 3280
|
2314 |
+
},
|
2315 |
+
{
|
2316 |
+
"epoch": 1.3181089743589745,
|
2317 |
+
"grad_norm": 0.2782920300960541,
|
2318 |
+
"learning_rate": 2.7511736796531838e-05,
|
2319 |
+
"loss": 0.1437,
|
2320 |
+
"step": 3290
|
2321 |
+
},
|
2322 |
+
{
|
2323 |
+
"epoch": 1.3221153846153846,
|
2324 |
+
"grad_norm": 0.2512044310569763,
|
2325 |
+
"learning_rate": 2.722246584429652e-05,
|
2326 |
+
"loss": 0.1473,
|
2327 |
+
"step": 3300
|
2328 |
+
},
|
2329 |
+
{
|
2330 |
+
"epoch": 1.326121794871795,
|
2331 |
+
"grad_norm": 0.24395060539245605,
|
2332 |
+
"learning_rate": 2.6934153752406287e-05,
|
2333 |
+
"loss": 0.1437,
|
2334 |
+
"step": 3310
|
2335 |
+
},
|
2336 |
+
{
|
2337 |
+
"epoch": 1.330128205128205,
|
2338 |
+
"grad_norm": 0.24087293446063995,
|
2339 |
+
"learning_rate": 2.6646812657865557e-05,
|
2340 |
+
"loss": 0.1465,
|
2341 |
+
"step": 3320
|
2342 |
+
},
|
2343 |
+
{
|
2344 |
+
"epoch": 1.3341346153846154,
|
2345 |
+
"grad_norm": 0.23852036893367767,
|
2346 |
+
"learning_rate": 2.636045465680282e-05,
|
2347 |
+
"loss": 0.1386,
|
2348 |
+
"step": 3330
|
2349 |
+
},
|
2350 |
+
{
|
2351 |
+
"epoch": 1.3381410256410255,
|
2352 |
+
"grad_norm": 0.2611803114414215,
|
2353 |
+
"learning_rate": 2.6075091803961616e-05,
|
2354 |
+
"loss": 0.1436,
|
2355 |
+
"step": 3340
|
2356 |
+
},
|
2357 |
+
{
|
2358 |
+
"epoch": 1.342147435897436,
|
2359 |
+
"grad_norm": 0.2321190983057022,
|
2360 |
+
"learning_rate": 2.5790736112192894e-05,
|
2361 |
+
"loss": 0.1507,
|
2362 |
+
"step": 3350
|
2363 |
+
},
|
2364 |
+
{
|
2365 |
+
"epoch": 1.3461538461538463,
|
2366 |
+
"grad_norm": 0.2473578155040741,
|
2367 |
+
"learning_rate": 2.550739955194944e-05,
|
2368 |
+
"loss": 0.1422,
|
2369 |
+
"step": 3360
|
2370 |
+
},
|
2371 |
+
{
|
2372 |
+
"epoch": 1.3501602564102564,
|
2373 |
+
"grad_norm": 0.2508649528026581,
|
2374 |
+
"learning_rate": 2.5225094050781872e-05,
|
2375 |
+
"loss": 0.1432,
|
2376 |
+
"step": 3370
|
2377 |
+
},
|
2378 |
+
{
|
2379 |
+
"epoch": 1.3541666666666667,
|
2380 |
+
"grad_norm": 0.2570420205593109,
|
2381 |
+
"learning_rate": 2.4943831492836588e-05,
|
2382 |
+
"loss": 0.1531,
|
2383 |
+
"step": 3380
|
2384 |
+
},
|
2385 |
+
{
|
2386 |
+
"epoch": 1.3581730769230769,
|
2387 |
+
"grad_norm": 0.24803844094276428,
|
2388 |
+
"learning_rate": 2.4663623718355444e-05,
|
2389 |
+
"loss": 0.2464,
|
2390 |
+
"step": 3390
|
2391 |
+
},
|
2392 |
+
{
|
2393 |
+
"epoch": 1.3621794871794872,
|
2394 |
+
"grad_norm": 0.23173387348651886,
|
2395 |
+
"learning_rate": 2.438448252317736e-05,
|
2396 |
+
"loss": 0.1485,
|
2397 |
+
"step": 3400
|
2398 |
+
},
|
2399 |
+
{
|
2400 |
+
"epoch": 1.3661858974358974,
|
2401 |
+
"grad_norm": 0.23720696568489075,
|
2402 |
+
"learning_rate": 2.410641965824166e-05,
|
2403 |
+
"loss": 0.1428,
|
2404 |
+
"step": 3410
|
2405 |
+
},
|
2406 |
+
{
|
2407 |
+
"epoch": 1.3701923076923077,
|
2408 |
+
"grad_norm": 0.2676253318786621,
|
2409 |
+
"learning_rate": 2.3829446829093537e-05,
|
2410 |
+
"loss": 0.1471,
|
2411 |
+
"step": 3420
|
2412 |
+
},
|
2413 |
+
{
|
2414 |
+
"epoch": 1.374198717948718,
|
2415 |
+
"grad_norm": 0.2445019632577896,
|
2416 |
+
"learning_rate": 2.355357569539114e-05,
|
2417 |
+
"loss": 0.1392,
|
2418 |
+
"step": 3430
|
2419 |
+
},
|
2420 |
+
{
|
2421 |
+
"epoch": 1.3782051282051282,
|
2422 |
+
"grad_norm": 0.22741925716400146,
|
2423 |
+
"learning_rate": 2.3278817870414866e-05,
|
2424 |
+
"loss": 0.15,
|
2425 |
+
"step": 3440
|
2426 |
+
},
|
2427 |
+
{
|
2428 |
+
"epoch": 1.3822115384615383,
|
2429 |
+
"grad_norm": 0.24508029222488403,
|
2430 |
+
"learning_rate": 2.300518492057842e-05,
|
2431 |
+
"loss": 0.1492,
|
2432 |
+
"step": 3450
|
2433 |
+
},
|
2434 |
+
{
|
2435 |
+
"epoch": 1.3862179487179487,
|
2436 |
+
"grad_norm": 0.25865378975868225,
|
2437 |
+
"learning_rate": 2.2732688364941862e-05,
|
2438 |
+
"loss": 0.1494,
|
2439 |
+
"step": 3460
|
2440 |
+
},
|
2441 |
+
{
|
2442 |
+
"epoch": 1.390224358974359,
|
2443 |
+
"grad_norm": 0.2557166814804077,
|
2444 |
+
"learning_rate": 2.2461339674726806e-05,
|
2445 |
+
"loss": 0.1486,
|
2446 |
+
"step": 3470
|
2447 |
+
},
|
2448 |
+
{
|
2449 |
+
"epoch": 1.3942307692307692,
|
2450 |
+
"grad_norm": 0.25431498885154724,
|
2451 |
+
"learning_rate": 2.219115027283339e-05,
|
2452 |
+
"loss": 0.1443,
|
2453 |
+
"step": 3480
|
2454 |
+
},
|
2455 |
+
{
|
2456 |
+
"epoch": 1.3982371794871795,
|
2457 |
+
"grad_norm": 0.2517376244068146,
|
2458 |
+
"learning_rate": 2.192213153335953e-05,
|
2459 |
+
"loss": 0.1434,
|
2460 |
+
"step": 3490
|
2461 |
+
},
|
2462 |
+
{
|
2463 |
+
"epoch": 1.4022435897435899,
|
2464 |
+
"grad_norm": 0.24723024666309357,
|
2465 |
+
"learning_rate": 2.165429478112199e-05,
|
2466 |
+
"loss": 0.1405,
|
2467 |
+
"step": 3500
|
2468 |
+
},
|
2469 |
+
{
|
2470 |
+
"epoch": 1.40625,
|
2471 |
+
"grad_norm": 0.24276477098464966,
|
2472 |
+
"learning_rate": 2.138765129117977e-05,
|
2473 |
+
"loss": 0.1483,
|
2474 |
+
"step": 3510
|
2475 |
+
},
|
2476 |
+
{
|
2477 |
+
"epoch": 1.4102564102564101,
|
2478 |
+
"grad_norm": 0.23349566757678986,
|
2479 |
+
"learning_rate": 2.1122212288359335e-05,
|
2480 |
+
"loss": 0.1508,
|
2481 |
+
"step": 3520
|
2482 |
+
},
|
2483 |
+
{
|
2484 |
+
"epoch": 1.4142628205128205,
|
2485 |
+
"grad_norm": 0.2291381061077118,
|
2486 |
+
"learning_rate": 2.085798894678217e-05,
|
2487 |
+
"loss": 0.1502,
|
2488 |
+
"step": 3530
|
2489 |
+
},
|
2490 |
+
{
|
2491 |
+
"epoch": 1.4182692307692308,
|
2492 |
+
"grad_norm": 0.2317928522825241,
|
2493 |
+
"learning_rate": 2.0594992389394395e-05,
|
2494 |
+
"loss": 0.1408,
|
2495 |
+
"step": 3540
|
2496 |
+
},
|
2497 |
+
{
|
2498 |
+
"epoch": 1.422275641025641,
|
2499 |
+
"grad_norm": 0.2636735141277313,
|
2500 |
+
"learning_rate": 2.0333233687498433e-05,
|
2501 |
+
"loss": 0.1418,
|
2502 |
+
"step": 3550
|
2503 |
+
},
|
2504 |
+
{
|
2505 |
+
"epoch": 1.4262820512820513,
|
2506 |
+
"grad_norm": 0.2535155415534973,
|
2507 |
+
"learning_rate": 2.0072723860287056e-05,
|
2508 |
+
"loss": 0.1484,
|
2509 |
+
"step": 3560
|
2510 |
+
},
|
2511 |
+
{
|
2512 |
+
"epoch": 1.4302884615384617,
|
2513 |
+
"grad_norm": 0.2632095217704773,
|
2514 |
+
"learning_rate": 1.9813473874379395e-05,
|
2515 |
+
"loss": 0.147,
|
2516 |
+
"step": 3570
|
2517 |
+
},
|
2518 |
+
{
|
2519 |
+
"epoch": 1.4342948717948718,
|
2520 |
+
"grad_norm": 0.25649628043174744,
|
2521 |
+
"learning_rate": 1.9555494643359457e-05,
|
2522 |
+
"loss": 0.1464,
|
2523 |
+
"step": 3580
|
2524 |
+
},
|
2525 |
+
{
|
2526 |
+
"epoch": 1.438301282051282,
|
2527 |
+
"grad_norm": 0.2731545865535736,
|
2528 |
+
"learning_rate": 1.9298797027316474e-05,
|
2529 |
+
"loss": 0.1516,
|
2530 |
+
"step": 3590
|
2531 |
+
},
|
2532 |
+
{
|
2533 |
+
"epoch": 1.4423076923076923,
|
2534 |
+
"grad_norm": 0.22635942697525024,
|
2535 |
+
"learning_rate": 1.9043391832387914e-05,
|
2536 |
+
"loss": 0.1405,
|
2537 |
+
"step": 3600
|
2538 |
+
},
|
2539 |
+
{
|
2540 |
+
"epoch": 1.4463141025641026,
|
2541 |
+
"grad_norm": 0.24070985615253448,
|
2542 |
+
"learning_rate": 1.878928981030445e-05,
|
2543 |
+
"loss": 0.1427,
|
2544 |
+
"step": 3610
|
2545 |
+
},
|
2546 |
+
{
|
2547 |
+
"epoch": 1.4503205128205128,
|
2548 |
+
"grad_norm": 0.29021933674812317,
|
2549 |
+
"learning_rate": 1.853650165793747e-05,
|
2550 |
+
"loss": 0.1435,
|
2551 |
+
"step": 3620
|
2552 |
+
},
|
2553 |
+
{
|
2554 |
+
"epoch": 1.4543269230769231,
|
2555 |
+
"grad_norm": 0.2542175352573395,
|
2556 |
+
"learning_rate": 1.8285038016848636e-05,
|
2557 |
+
"loss": 0.1531,
|
2558 |
+
"step": 3630
|
2559 |
+
},
|
2560 |
+
{
|
2561 |
+
"epoch": 1.4583333333333333,
|
2562 |
+
"grad_norm": 0.24497313797473907,
|
2563 |
+
"learning_rate": 1.803490947284204e-05,
|
2564 |
+
"loss": 0.1451,
|
2565 |
+
"step": 3640
|
2566 |
+
},
|
2567 |
+
{
|
2568 |
+
"epoch": 1.4623397435897436,
|
2569 |
+
"grad_norm": 0.24667443335056305,
|
2570 |
+
"learning_rate": 1.7786126555518485e-05,
|
2571 |
+
"loss": 0.1417,
|
2572 |
+
"step": 3650
|
2573 |
+
},
|
2574 |
+
{
|
2575 |
+
"epoch": 1.4663461538461537,
|
2576 |
+
"grad_norm": 0.2563740015029907,
|
2577 |
+
"learning_rate": 1.7538699737832236e-05,
|
2578 |
+
"loss": 0.1524,
|
2579 |
+
"step": 3660
|
2580 |
+
},
|
2581 |
+
{
|
2582 |
+
"epoch": 1.470352564102564,
|
2583 |
+
"grad_norm": 0.2556226849555969,
|
2584 |
+
"learning_rate": 1.7292639435650222e-05,
|
2585 |
+
"loss": 0.141,
|
2586 |
+
"step": 3670
|
2587 |
+
},
|
2588 |
+
{
|
2589 |
+
"epoch": 1.4743589743589745,
|
2590 |
+
"grad_norm": 0.23436102271080017,
|
2591 |
+
"learning_rate": 1.704795600731341e-05,
|
2592 |
+
"loss": 0.1477,
|
2593 |
+
"step": 3680
|
2594 |
+
},
|
2595 |
+
{
|
2596 |
+
"epoch": 1.4783653846153846,
|
2597 |
+
"grad_norm": 0.2800445556640625,
|
2598 |
+
"learning_rate": 1.6804659753200924e-05,
|
2599 |
+
"loss": 0.1429,
|
2600 |
+
"step": 3690
|
2601 |
+
},
|
2602 |
+
{
|
2603 |
+
"epoch": 1.482371794871795,
|
2604 |
+
"grad_norm": 0.28161168098449707,
|
2605 |
+
"learning_rate": 1.6562760915296295e-05,
|
2606 |
+
"loss": 0.1423,
|
2607 |
+
"step": 3700
|
2608 |
+
},
|
2609 |
+
{
|
2610 |
+
"epoch": 1.486378205128205,
|
2611 |
+
"grad_norm": 0.2788082957267761,
|
2612 |
+
"learning_rate": 1.63222696767564e-05,
|
2613 |
+
"loss": 0.1465,
|
2614 |
+
"step": 3710
|
2615 |
+
},
|
2616 |
+
{
|
2617 |
+
"epoch": 1.4903846153846154,
|
2618 |
+
"grad_norm": 0.2512800097465515,
|
2619 |
+
"learning_rate": 1.608319616148271e-05,
|
2620 |
+
"loss": 0.1354,
|
2621 |
+
"step": 3720
|
2622 |
+
},
|
2623 |
+
{
|
2624 |
+
"epoch": 1.4943910256410255,
|
2625 |
+
"grad_norm": 0.24340157210826874,
|
2626 |
+
"learning_rate": 1.5845550433695173e-05,
|
2627 |
+
"loss": 0.1461,
|
2628 |
+
"step": 3730
|
2629 |
+
},
|
2630 |
+
{
|
2631 |
+
"epoch": 1.498397435897436,
|
2632 |
+
"grad_norm": 0.25012919306755066,
|
2633 |
+
"learning_rate": 1.560934249750851e-05,
|
2634 |
+
"loss": 0.1493,
|
2635 |
+
"step": 3740
|
2636 |
+
},
|
2637 |
+
{
|
2638 |
+
"epoch": 1.5024038461538463,
|
2639 |
+
"grad_norm": 0.242750346660614,
|
2640 |
+
"learning_rate": 1.5374582296511053e-05,
|
2641 |
+
"loss": 0.1411,
|
2642 |
+
"step": 3750
|
2643 |
+
},
|
2644 |
+
{
|
2645 |
+
"epoch": 1.5064102564102564,
|
2646 |
+
"grad_norm": 0.23980247974395752,
|
2647 |
+
"learning_rate": 1.5141279713346208e-05,
|
2648 |
+
"loss": 0.1441,
|
2649 |
+
"step": 3760
|
2650 |
+
},
|
2651 |
+
{
|
2652 |
+
"epoch": 1.5104166666666665,
|
2653 |
+
"grad_norm": 0.2511241137981415,
|
2654 |
+
"learning_rate": 1.4909444569296333e-05,
|
2655 |
+
"loss": 0.1447,
|
2656 |
+
"step": 3770
|
2657 |
+
},
|
2658 |
+
{
|
2659 |
+
"epoch": 1.5144230769230769,
|
2660 |
+
"grad_norm": 0.24846923351287842,
|
2661 |
+
"learning_rate": 1.4679086623869464e-05,
|
2662 |
+
"loss": 0.1441,
|
2663 |
+
"step": 3780
|
2664 |
+
},
|
2665 |
+
{
|
2666 |
+
"epoch": 1.5184294871794872,
|
2667 |
+
"grad_norm": 0.24027830362319946,
|
2668 |
+
"learning_rate": 1.4450215574388265e-05,
|
2669 |
+
"loss": 0.1402,
|
2670 |
+
"step": 3790
|
2671 |
+
},
|
2672 |
+
{
|
2673 |
+
"epoch": 1.5224358974358974,
|
2674 |
+
"grad_norm": 0.2580472528934479,
|
2675 |
+
"learning_rate": 1.4222841055581964e-05,
|
2676 |
+
"loss": 0.1377,
|
2677 |
+
"step": 3800
|
2678 |
+
},
|
2679 |
+
{
|
2680 |
+
"epoch": 1.5264423076923077,
|
2681 |
+
"grad_norm": 0.23837298154830933,
|
2682 |
+
"learning_rate": 1.3996972639180644e-05,
|
2683 |
+
"loss": 0.142,
|
2684 |
+
"step": 3810
|
2685 |
+
},
|
2686 |
+
{
|
2687 |
+
"epoch": 1.530448717948718,
|
2688 |
+
"grad_norm": 0.22810089588165283,
|
2689 |
+
"learning_rate": 1.3772619833512412e-05,
|
2690 |
+
"loss": 0.1456,
|
2691 |
+
"step": 3820
|
2692 |
+
},
|
2693 |
+
{
|
2694 |
+
"epoch": 1.5344551282051282,
|
2695 |
+
"grad_norm": 0.22962678968906403,
|
2696 |
+
"learning_rate": 1.3549792083103036e-05,
|
2697 |
+
"loss": 0.1374,
|
2698 |
+
"step": 3830
|
2699 |
+
},
|
2700 |
+
{
|
2701 |
+
"epoch": 1.5384615384615383,
|
2702 |
+
"grad_norm": 0.2668929398059845,
|
2703 |
+
"learning_rate": 1.332849876827842e-05,
|
2704 |
+
"loss": 0.1499,
|
2705 |
+
"step": 3840
|
2706 |
+
},
|
2707 |
+
{
|
2708 |
+
"epoch": 1.5424679487179487,
|
2709 |
+
"grad_norm": 0.24207815527915955,
|
2710 |
+
"learning_rate": 1.3108749204769733e-05,
|
2711 |
+
"loss": 0.1369,
|
2712 |
+
"step": 3850
|
2713 |
+
},
|
2714 |
+
{
|
2715 |
+
"epoch": 1.546474358974359,
|
2716 |
+
"grad_norm": 0.2575761377811432,
|
2717 |
+
"learning_rate": 1.2890552643321146e-05,
|
2718 |
+
"loss": 0.1504,
|
2719 |
+
"step": 3860
|
2720 |
+
},
|
2721 |
+
{
|
2722 |
+
"epoch": 1.5504807692307692,
|
2723 |
+
"grad_norm": 0.23695258796215057,
|
2724 |
+
"learning_rate": 1.2673918269300556e-05,
|
2725 |
+
"loss": 0.1422,
|
2726 |
+
"step": 3870
|
2727 |
+
},
|
2728 |
+
{
|
2729 |
+
"epoch": 1.5544871794871795,
|
2730 |
+
"grad_norm": 0.2854330837726593,
|
2731 |
+
"learning_rate": 1.2458855202312775e-05,
|
2732 |
+
"loss": 0.1506,
|
2733 |
+
"step": 3880
|
2734 |
+
},
|
2735 |
+
{
|
2736 |
+
"epoch": 1.5584935897435899,
|
2737 |
+
"grad_norm": 0.2639913260936737,
|
2738 |
+
"learning_rate": 1.2245372495815726e-05,
|
2739 |
+
"loss": 0.1386,
|
2740 |
+
"step": 3890
|
2741 |
+
},
|
2742 |
+
{
|
2743 |
+
"epoch": 1.5625,
|
2744 |
+
"grad_norm": 0.26962000131607056,
|
2745 |
+
"learning_rate": 1.203347913673924e-05,
|
2746 |
+
"loss": 0.1469,
|
2747 |
+
"step": 3900
|
2748 |
+
},
|
2749 |
+
{
|
2750 |
+
"epoch": 1.5665064102564101,
|
2751 |
+
"grad_norm": 0.2668505907058716,
|
2752 |
+
"learning_rate": 1.1823184045106817e-05,
|
2753 |
+
"loss": 0.1381,
|
2754 |
+
"step": 3910
|
2755 |
+
},
|
2756 |
+
{
|
2757 |
+
"epoch": 1.5705128205128205,
|
2758 |
+
"grad_norm": 0.24999478459358215,
|
2759 |
+
"learning_rate": 1.1614496073660026e-05,
|
2760 |
+
"loss": 0.1488,
|
2761 |
+
"step": 3920
|
2762 |
+
},
|
2763 |
+
{
|
2764 |
+
"epoch": 1.5745192307692308,
|
2765 |
+
"grad_norm": 0.2618054151535034,
|
2766 |
+
"learning_rate": 1.1407424007485929e-05,
|
2767 |
+
"loss": 0.1365,
|
2768 |
+
"step": 3930
|
2769 |
+
},
|
2770 |
+
{
|
2771 |
+
"epoch": 1.578525641025641,
|
2772 |
+
"grad_norm": 0.25881797075271606,
|
2773 |
+
"learning_rate": 1.120197656364722e-05,
|
2774 |
+
"loss": 0.1424,
|
2775 |
+
"step": 3940
|
2776 |
+
},
|
2777 |
+
{
|
2778 |
+
"epoch": 1.5825320512820513,
|
2779 |
+
"grad_norm": 0.23021487891674042,
|
2780 |
+
"learning_rate": 1.0998162390815208e-05,
|
2781 |
+
"loss": 0.1344,
|
2782 |
+
"step": 3950
|
2783 |
+
},
|
2784 |
+
{
|
2785 |
+
"epoch": 1.5865384615384617,
|
2786 |
+
"grad_norm": 0.24012772738933563,
|
2787 |
+
"learning_rate": 1.0795990068905843e-05,
|
2788 |
+
"loss": 0.1511,
|
2789 |
+
"step": 3960
|
2790 |
+
},
|
2791 |
+
{
|
2792 |
+
"epoch": 1.5905448717948718,
|
2793 |
+
"grad_norm": 0.251249760389328,
|
2794 |
+
"learning_rate": 1.0595468108718449e-05,
|
2795 |
+
"loss": 0.1433,
|
2796 |
+
"step": 3970
|
2797 |
+
},
|
2798 |
+
{
|
2799 |
+
"epoch": 1.594551282051282,
|
2800 |
+
"grad_norm": 0.2358747273683548,
|
2801 |
+
"learning_rate": 1.0396604951577483e-05,
|
2802 |
+
"loss": 0.147,
|
2803 |
+
"step": 3980
|
2804 |
+
},
|
2805 |
+
{
|
2806 |
+
"epoch": 1.5985576923076923,
|
2807 |
+
"grad_norm": 0.25139543414115906,
|
2808 |
+
"learning_rate": 1.0199408968977136e-05,
|
2809 |
+
"loss": 0.1478,
|
2810 |
+
"step": 3990
|
2811 |
+
},
|
2812 |
+
{
|
2813 |
+
"epoch": 1.6025641025641026,
|
2814 |
+
"grad_norm": 0.25917524099349976,
|
2815 |
+
"learning_rate": 1.0003888462229011e-05,
|
2816 |
+
"loss": 0.1467,
|
2817 |
+
"step": 4000
|
2818 |
+
},
|
2819 |
+
{
|
2820 |
+
"epoch": 1.6065705128205128,
|
2821 |
+
"grad_norm": 0.2669861316680908,
|
2822 |
+
"learning_rate": 9.810051662112557e-06,
|
2823 |
+
"loss": 0.1348,
|
2824 |
+
"step": 4010
|
2825 |
+
},
|
2826 |
+
{
|
2827 |
+
"epoch": 1.6105769230769231,
|
2828 |
+
"grad_norm": 0.27329695224761963,
|
2829 |
+
"learning_rate": 9.61790672852868e-06,
|
2830 |
+
"loss": 0.1384,
|
2831 |
+
"step": 4020
|
2832 |
+
},
|
2833 |
+
{
|
2834 |
+
"epoch": 1.6145833333333335,
|
2835 |
+
"grad_norm": 0.2671654522418976,
|
2836 |
+
"learning_rate": 9.427461750156142e-06,
|
2837 |
+
"loss": 0.1431,
|
2838 |
+
"step": 4030
|
2839 |
+
},
|
2840 |
+
{
|
2841 |
+
"epoch": 1.6185897435897436,
|
2842 |
+
"grad_norm": 0.25406405329704285,
|
2843 |
+
"learning_rate": 9.238724744111138e-06,
|
2844 |
+
"loss": 0.1444,
|
2845 |
+
"step": 4040
|
2846 |
+
},
|
2847 |
+
{
|
2848 |
+
"epoch": 1.6225961538461537,
|
2849 |
+
"grad_norm": 0.25970324873924255,
|
2850 |
+
"learning_rate": 9.05170365560976e-06,
|
2851 |
+
"loss": 0.1396,
|
2852 |
+
"step": 4050
|
2853 |
+
},
|
2854 |
+
{
|
2855 |
+
"epoch": 1.626602564102564,
|
2856 |
+
"grad_norm": 0.2700863480567932,
|
2857 |
+
"learning_rate": 8.86640635763351e-06,
|
2858 |
+
"loss": 0.1484,
|
2859 |
+
"step": 4060
|
2860 |
+
},
|
2861 |
+
{
|
2862 |
+
"epoch": 1.6306089743589745,
|
2863 |
+
"grad_norm": 0.24397385120391846,
|
2864 |
+
"learning_rate": 8.68284065059794e-06,
|
2865 |
+
"loss": 0.1407,
|
2866 |
+
"step": 4070
|
2867 |
+
},
|
2868 |
+
{
|
2869 |
+
"epoch": 1.6346153846153846,
|
2870 |
+
"grad_norm": 0.2537296414375305,
|
2871 |
+
"learning_rate": 8.501014262024176e-06,
|
2872 |
+
"loss": 0.1468,
|
2873 |
+
"step": 4080
|
2874 |
+
},
|
2875 |
+
{
|
2876 |
+
"epoch": 1.6386217948717947,
|
2877 |
+
"grad_norm": 0.2614051103591919,
|
2878 |
+
"learning_rate": 8.320934846213746e-06,
|
2879 |
+
"loss": 0.1368,
|
2880 |
+
"step": 4090
|
2881 |
+
},
|
2882 |
+
{
|
2883 |
+
"epoch": 1.6426282051282053,
|
2884 |
+
"grad_norm": 0.2941496670246124,
|
2885 |
+
"learning_rate": 8.142609983926225e-06,
|
2886 |
+
"loss": 0.1434,
|
2887 |
+
"step": 4100
|
2888 |
+
},
|
2889 |
+
{
|
2890 |
+
"epoch": 1.6466346153846154,
|
2891 |
+
"grad_norm": 0.2491438090801239,
|
2892 |
+
"learning_rate": 7.966047182060226e-06,
|
2893 |
+
"loss": 0.1433,
|
2894 |
+
"step": 4110
|
2895 |
+
},
|
2896 |
+
{
|
2897 |
+
"epoch": 1.6506410256410255,
|
2898 |
+
"grad_norm": 0.267880916595459,
|
2899 |
+
"learning_rate": 7.791253873337278e-06,
|
2900 |
+
"loss": 0.1437,
|
2901 |
+
"step": 4120
|
2902 |
+
},
|
2903 |
+
{
|
2904 |
+
"epoch": 1.654647435897436,
|
2905 |
+
"grad_norm": 0.25333133339881897,
|
2906 |
+
"learning_rate": 7.618237415989032e-06,
|
2907 |
+
"loss": 0.1433,
|
2908 |
+
"step": 4130
|
2909 |
+
},
|
2910 |
+
{
|
2911 |
+
"epoch": 1.6586538461538463,
|
2912 |
+
"grad_norm": 0.25538668036460876,
|
2913 |
+
"learning_rate": 7.44700509344744e-06,
|
2914 |
+
"loss": 0.139,
|
2915 |
+
"step": 4140
|
2916 |
+
},
|
2917 |
+
{
|
2918 |
+
"epoch": 1.6626602564102564,
|
2919 |
+
"grad_norm": 0.25621935725212097,
|
2920 |
+
"learning_rate": 7.277564114038149e-06,
|
2921 |
+
"loss": 0.1347,
|
2922 |
+
"step": 4150
|
2923 |
+
},
|
2924 |
+
{
|
2925 |
+
"epoch": 1.6666666666666665,
|
2926 |
+
"grad_norm": 0.2569233775138855,
|
2927 |
+
"learning_rate": 7.109921610677078e-06,
|
2928 |
+
"loss": 0.1408,
|
2929 |
+
"step": 4160
|
2930 |
+
},
|
2931 |
+
{
|
2932 |
+
"epoch": 1.6706730769230769,
|
2933 |
+
"grad_norm": 0.23728112876415253,
|
2934 |
+
"learning_rate": 6.9440846405701424e-06,
|
2935 |
+
"loss": 0.1352,
|
2936 |
+
"step": 4170
|
2937 |
+
},
|
2938 |
+
{
|
2939 |
+
"epoch": 1.6746794871794872,
|
2940 |
+
"grad_norm": 0.23264577984809875,
|
2941 |
+
"learning_rate": 6.780060184916159e-06,
|
2942 |
+
"loss": 0.1463,
|
2943 |
+
"step": 4180
|
2944 |
+
},
|
2945 |
+
{
|
2946 |
+
"epoch": 1.6786858974358974,
|
2947 |
+
"grad_norm": 0.24841400980949402,
|
2948 |
+
"learning_rate": 6.6178551486129445e-06,
|
2949 |
+
"loss": 0.1438,
|
2950 |
+
"step": 4190
|
2951 |
+
},
|
2952 |
+
{
|
2953 |
+
"epoch": 1.6826923076923077,
|
2954 |
+
"grad_norm": 0.2776187062263489,
|
2955 |
+
"learning_rate": 6.4574763599666856e-06,
|
2956 |
+
"loss": 0.1438,
|
2957 |
+
"step": 4200
|
2958 |
+
},
|
2959 |
+
{
|
2960 |
+
"epoch": 1.686698717948718,
|
2961 |
+
"grad_norm": 0.2587837874889374,
|
2962 |
+
"learning_rate": 6.2989305704044325e-06,
|
2963 |
+
"loss": 0.1367,
|
2964 |
+
"step": 4210
|
2965 |
+
},
|
2966 |
+
{
|
2967 |
+
"epoch": 1.6907051282051282,
|
2968 |
+
"grad_norm": 0.2615884244441986,
|
2969 |
+
"learning_rate": 6.142224454189954e-06,
|
2970 |
+
"loss": 0.1726,
|
2971 |
+
"step": 4220
|
2972 |
+
},
|
2973 |
+
{
|
2974 |
+
"epoch": 1.6947115384615383,
|
2975 |
+
"grad_norm": 0.25619083642959595,
|
2976 |
+
"learning_rate": 5.987364608142693e-06,
|
2977 |
+
"loss": 0.151,
|
2978 |
+
"step": 4230
|
2979 |
+
},
|
2980 |
+
{
|
2981 |
+
"epoch": 1.6987179487179487,
|
2982 |
+
"grad_norm": 0.28548672795295715,
|
2983 |
+
"learning_rate": 5.834357551360132e-06,
|
2984 |
+
"loss": 0.1421,
|
2985 |
+
"step": 4240
|
2986 |
+
},
|
2987 |
+
{
|
2988 |
+
"epoch": 1.702724358974359,
|
2989 |
+
"grad_norm": 0.26761943101882935,
|
2990 |
+
"learning_rate": 5.683209724943345e-06,
|
2991 |
+
"loss": 0.1383,
|
2992 |
+
"step": 4250
|
2993 |
+
},
|
2994 |
+
{
|
2995 |
+
"epoch": 1.7067307692307692,
|
2996 |
+
"grad_norm": 0.2561447322368622,
|
2997 |
+
"learning_rate": 5.533927491725787e-06,
|
2998 |
+
"loss": 0.1421,
|
2999 |
+
"step": 4260
|
3000 |
+
},
|
3001 |
+
{
|
3002 |
+
"epoch": 1.7107371794871795,
|
3003 |
+
"grad_norm": 0.2707176208496094,
|
3004 |
+
"learning_rate": 5.3865171360055425e-06,
|
3005 |
+
"loss": 0.1519,
|
3006 |
+
"step": 4270
|
3007 |
+
},
|
3008 |
+
{
|
3009 |
+
"epoch": 1.7147435897435899,
|
3010 |
+
"grad_norm": 0.264593243598938,
|
3011 |
+
"learning_rate": 5.240984863280668e-06,
|
3012 |
+
"loss": 0.1464,
|
3013 |
+
"step": 4280
|
3014 |
+
},
|
3015 |
+
{
|
3016 |
+
"epoch": 1.71875,
|
3017 |
+
"grad_norm": 0.2739621102809906,
|
3018 |
+
"learning_rate": 5.097336799988067e-06,
|
3019 |
+
"loss": 0.1392,
|
3020 |
+
"step": 4290
|
3021 |
+
},
|
3022 |
+
{
|
3023 |
+
"epoch": 1.7227564102564101,
|
3024 |
+
"grad_norm": 0.23156005144119263,
|
3025 |
+
"learning_rate": 4.955578993245485e-06,
|
3026 |
+
"loss": 0.1377,
|
3027 |
+
"step": 4300
|
3028 |
+
},
|
3029 |
+
{
|
3030 |
+
"epoch": 1.7267628205128205,
|
3031 |
+
"grad_norm": 0.24819669127464294,
|
3032 |
+
"learning_rate": 4.815717410597043e-06,
|
3033 |
+
"loss": 0.138,
|
3034 |
+
"step": 4310
|
3035 |
+
},
|
3036 |
+
{
|
3037 |
+
"epoch": 1.7307692307692308,
|
3038 |
+
"grad_norm": 0.25722768902778625,
|
3039 |
+
"learning_rate": 4.6777579397619285e-06,
|
3040 |
+
"loss": 0.1434,
|
3041 |
+
"step": 4320
|
3042 |
+
},
|
3043 |
+
{
|
3044 |
+
"epoch": 1.734775641025641,
|
3045 |
+
"grad_norm": 0.22565537691116333,
|
3046 |
+
"learning_rate": 4.541706388386624e-06,
|
3047 |
+
"loss": 0.1409,
|
3048 |
+
"step": 4330
|
3049 |
+
},
|
3050 |
+
{
|
3051 |
+
"epoch": 1.7387820512820513,
|
3052 |
+
"grad_norm": 0.2539729177951813,
|
3053 |
+
"learning_rate": 4.4075684838003784e-06,
|
3054 |
+
"loss": 0.1447,
|
3055 |
+
"step": 4340
|
3056 |
+
},
|
3057 |
+
{
|
3058 |
+
"epoch": 1.7427884615384617,
|
3059 |
+
"grad_norm": 0.2426980435848236,
|
3060 |
+
"learning_rate": 4.275349872774098e-06,
|
3061 |
+
"loss": 0.1422,
|
3062 |
+
"step": 4350
|
3063 |
+
},
|
3064 |
+
{
|
3065 |
+
"epoch": 1.7467948717948718,
|
3066 |
+
"grad_norm": 0.26267197728157043,
|
3067 |
+
"learning_rate": 4.14505612128267e-06,
|
3068 |
+
"loss": 0.1381,
|
3069 |
+
"step": 4360
|
3070 |
+
},
|
3071 |
+
{
|
3072 |
+
"epoch": 1.750801282051282,
|
3073 |
+
"grad_norm": 0.23471184074878693,
|
3074 |
+
"learning_rate": 4.016692714270631e-06,
|
3075 |
+
"loss": 0.1367,
|
3076 |
+
"step": 4370
|
3077 |
+
},
|
3078 |
+
{
|
3079 |
+
"epoch": 1.7548076923076923,
|
3080 |
+
"grad_norm": 0.2703573703765869,
|
3081 |
+
"learning_rate": 3.890265055421283e-06,
|
3082 |
+
"loss": 0.144,
|
3083 |
+
"step": 4380
|
3084 |
+
},
|
3085 |
+
{
|
3086 |
+
"epoch": 1.7588141025641026,
|
3087 |
+
"grad_norm": 0.23946279287338257,
|
3088 |
+
"learning_rate": 3.7657784669291816e-06,
|
3089 |
+
"loss": 0.1397,
|
3090 |
+
"step": 4390
|
3091 |
+
},
|
3092 |
+
{
|
3093 |
+
"epoch": 1.7628205128205128,
|
3094 |
+
"grad_norm": 0.23393961787223816,
|
3095 |
+
"learning_rate": 3.643238189276138e-06,
|
3096 |
+
"loss": 0.1329,
|
3097 |
+
"step": 4400
|
3098 |
+
},
|
3099 |
+
{
|
3100 |
+
"epoch": 1.7668269230769231,
|
3101 |
+
"grad_norm": 0.24087683856487274,
|
3102 |
+
"learning_rate": 3.522649381010562e-06,
|
3103 |
+
"loss": 0.1367,
|
3104 |
+
"step": 4410
|
3105 |
+
},
|
3106 |
+
{
|
3107 |
+
"epoch": 1.7708333333333335,
|
3108 |
+
"grad_norm": 0.2636178135871887,
|
3109 |
+
"learning_rate": 3.4040171185303616e-06,
|
3110 |
+
"loss": 0.1415,
|
3111 |
+
"step": 4420
|
3112 |
+
},
|
3113 |
+
{
|
3114 |
+
"epoch": 1.7748397435897436,
|
3115 |
+
"grad_norm": 0.2364189773797989,
|
3116 |
+
"learning_rate": 3.2873463958691673e-06,
|
3117 |
+
"loss": 0.1445,
|
3118 |
+
"step": 4430
|
3119 |
+
},
|
3120 |
+
{
|
3121 |
+
"epoch": 1.7788461538461537,
|
3122 |
+
"grad_norm": 0.26020485162734985,
|
3123 |
+
"learning_rate": 3.1726421244861917e-06,
|
3124 |
+
"loss": 0.1388,
|
3125 |
+
"step": 4440
|
3126 |
+
},
|
3127 |
+
{
|
3128 |
+
"epoch": 1.782852564102564,
|
3129 |
+
"grad_norm": 0.25162965059280396,
|
3130 |
+
"learning_rate": 3.0599091330593797e-06,
|
3131 |
+
"loss": 0.1427,
|
3132 |
+
"step": 4450
|
3133 |
+
},
|
3134 |
+
{
|
3135 |
+
"epoch": 1.7868589743589745,
|
3136 |
+
"grad_norm": 0.24311134219169617,
|
3137 |
+
"learning_rate": 2.949152167282204e-06,
|
3138 |
+
"loss": 0.1313,
|
3139 |
+
"step": 4460
|
3140 |
+
},
|
3141 |
+
{
|
3142 |
+
"epoch": 1.7908653846153846,
|
3143 |
+
"grad_norm": 0.249532088637352,
|
3144 |
+
"learning_rate": 2.840375889663871e-06,
|
3145 |
+
"loss": 0.1486,
|
3146 |
+
"step": 4470
|
3147 |
+
},
|
3148 |
+
{
|
3149 |
+
"epoch": 1.7948717948717947,
|
3150 |
+
"grad_norm": 0.2393971085548401,
|
3151 |
+
"learning_rate": 2.733584879333001e-06,
|
3152 |
+
"loss": 0.1467,
|
3153 |
+
"step": 4480
|
3154 |
+
},
|
3155 |
+
{
|
3156 |
+
"epoch": 1.7988782051282053,
|
3157 |
+
"grad_norm": 0.25224366784095764,
|
3158 |
+
"learning_rate": 2.62878363184495e-06,
|
3159 |
+
"loss": 0.1446,
|
3160 |
+
"step": 4490
|
3161 |
+
},
|
3162 |
+
{
|
3163 |
+
"epoch": 1.8028846153846154,
|
3164 |
+
"grad_norm": 0.2636267840862274,
|
3165 |
+
"learning_rate": 2.5259765589924544e-06,
|
3166 |
+
"loss": 0.1487,
|
3167 |
+
"step": 4500
|
3168 |
+
},
|
3169 |
+
{
|
3170 |
+
"epoch": 1.8068910256410255,
|
3171 |
+
"grad_norm": 0.25640687346458435,
|
3172 |
+
"learning_rate": 2.425167988620014e-06,
|
3173 |
+
"loss": 0.1358,
|
3174 |
+
"step": 4510
|
3175 |
+
},
|
3176 |
+
{
|
3177 |
+
"epoch": 1.810897435897436,
|
3178 |
+
"grad_norm": 0.24088767170906067,
|
3179 |
+
"learning_rate": 2.3263621644416034e-06,
|
3180 |
+
"loss": 0.1404,
|
3181 |
+
"step": 4520
|
3182 |
+
},
|
3183 |
+
{
|
3184 |
+
"epoch": 1.8149038461538463,
|
3185 |
+
"grad_norm": 0.2403586059808731,
|
3186 |
+
"learning_rate": 2.2295632458621095e-06,
|
3187 |
+
"loss": 0.1412,
|
3188 |
+
"step": 4530
|
3189 |
+
},
|
3190 |
+
{
|
3191 |
+
"epoch": 1.8189102564102564,
|
3192 |
+
"grad_norm": 0.23450630903244019,
|
3193 |
+
"learning_rate": 2.1347753078022005e-06,
|
3194 |
+
"loss": 0.1447,
|
3195 |
+
"step": 4540
|
3196 |
+
},
|
3197 |
+
{
|
3198 |
+
"epoch": 1.8229166666666665,
|
3199 |
+
"grad_norm": 0.2330087125301361,
|
3200 |
+
"learning_rate": 2.0420023405267665e-06,
|
3201 |
+
"loss": 0.1438,
|
3202 |
+
"step": 4550
|
3203 |
+
},
|
3204 |
+
{
|
3205 |
+
"epoch": 1.8269230769230769,
|
3206 |
+
"grad_norm": 0.208469420671463,
|
3207 |
+
"learning_rate": 1.9512482494769613e-06,
|
3208 |
+
"loss": 0.1363,
|
3209 |
+
"step": 4560
|
3210 |
+
},
|
3211 |
+
{
|
3212 |
+
"epoch": 1.8309294871794872,
|
3213 |
+
"grad_norm": 0.24098703265190125,
|
3214 |
+
"learning_rate": 1.8625168551058114e-06,
|
3215 |
+
"loss": 0.145,
|
3216 |
+
"step": 4570
|
3217 |
+
},
|
3218 |
+
{
|
3219 |
+
"epoch": 1.8349358974358974,
|
3220 |
+
"grad_norm": 0.24833528697490692,
|
3221 |
+
"learning_rate": 1.7758118927173606e-06,
|
3222 |
+
"loss": 0.1417,
|
3223 |
+
"step": 4580
|
3224 |
+
},
|
3225 |
+
{
|
3226 |
+
"epoch": 1.8389423076923077,
|
3227 |
+
"grad_norm": 0.2671266496181488,
|
3228 |
+
"learning_rate": 1.6911370123094239e-06,
|
3229 |
+
"loss": 0.141,
|
3230 |
+
"step": 4590
|
3231 |
+
},
|
3232 |
+
{
|
3233 |
+
"epoch": 1.842948717948718,
|
3234 |
+
"grad_norm": 0.25512388348579407,
|
3235 |
+
"learning_rate": 1.6084957784199662e-06,
|
3236 |
+
"loss": 0.1357,
|
3237 |
+
"step": 4600
|
3238 |
+
},
|
3239 |
+
{
|
3240 |
+
"epoch": 1.8469551282051282,
|
3241 |
+
"grad_norm": 0.2621639668941498,
|
3242 |
+
"learning_rate": 1.5278916699770163e-06,
|
3243 |
+
"loss": 0.1446,
|
3244 |
+
"step": 4610
|
3245 |
+
},
|
3246 |
+
{
|
3247 |
+
"epoch": 1.8509615384615383,
|
3248 |
+
"grad_norm": 0.2648192048072815,
|
3249 |
+
"learning_rate": 1.4493280801522347e-06,
|
3250 |
+
"loss": 0.1391,
|
3251 |
+
"step": 4620
|
3252 |
+
},
|
3253 |
+
{
|
3254 |
+
"epoch": 1.8549679487179487,
|
3255 |
+
"grad_norm": 0.26396840810775757,
|
3256 |
+
"learning_rate": 1.3728083162180382e-06,
|
3257 |
+
"loss": 0.1409,
|
3258 |
+
"step": 4630
|
3259 |
+
},
|
3260 |
+
{
|
3261 |
+
"epoch": 1.858974358974359,
|
3262 |
+
"grad_norm": 0.24495120346546173,
|
3263 |
+
"learning_rate": 1.2983355994084401e-06,
|
3264 |
+
"loss": 0.1388,
|
3265 |
+
"step": 4640
|
3266 |
+
},
|
3267 |
+
{
|
3268 |
+
"epoch": 1.8629807692307692,
|
3269 |
+
"grad_norm": 0.26375770568847656,
|
3270 |
+
"learning_rate": 1.2259130647833627e-06,
|
3271 |
+
"loss": 0.1376,
|
3272 |
+
"step": 4650
|
3273 |
+
},
|
3274 |
+
{
|
3275 |
+
"epoch": 1.8669871794871795,
|
3276 |
+
"grad_norm": 0.25506845116615295,
|
3277 |
+
"learning_rate": 1.155543761096739e-06,
|
3278 |
+
"loss": 0.1432,
|
3279 |
+
"step": 4660
|
3280 |
+
},
|
3281 |
+
{
|
3282 |
+
"epoch": 1.8709935897435899,
|
3283 |
+
"grad_norm": 0.2563297152519226,
|
3284 |
+
"learning_rate": 1.0872306506681251e-06,
|
3285 |
+
"loss": 0.143,
|
3286 |
+
"step": 4670
|
3287 |
+
},
|
3288 |
+
{
|
3289 |
+
"epoch": 1.875,
|
3290 |
+
"grad_norm": 0.23788757622241974,
|
3291 |
+
"learning_rate": 1.0209766092579897e-06,
|
3292 |
+
"loss": 0.1387,
|
3293 |
+
"step": 4680
|
3294 |
+
},
|
3295 |
+
{
|
3296 |
+
"epoch": 1.8790064102564101,
|
3297 |
+
"grad_norm": 0.2355082929134369,
|
3298 |
+
"learning_rate": 9.56784425946705e-07,
|
3299 |
+
"loss": 0.1403,
|
3300 |
+
"step": 4690
|
3301 |
+
},
|
3302 |
+
{
|
3303 |
+
"epoch": 1.8830128205128205,
|
3304 |
+
"grad_norm": 0.26146796345710754,
|
3305 |
+
"learning_rate": 8.946568030170688e-07,
|
3306 |
+
"loss": 0.1413,
|
3307 |
+
"step": 4700
|
3308 |
+
},
|
3309 |
+
{
|
3310 |
+
"epoch": 1.8870192307692308,
|
3311 |
+
"grad_norm": 0.2697630822658539,
|
3312 |
+
"learning_rate": 8.345963558406e-07,
|
3313 |
+
"loss": 0.147,
|
3314 |
+
"step": 4710
|
3315 |
+
},
|
3316 |
+
{
|
3317 |
+
"epoch": 1.891025641025641,
|
3318 |
+
"grad_norm": 0.26238909363746643,
|
3319 |
+
"learning_rate": 7.766056127674115e-07,
|
3320 |
+
"loss": 0.1458,
|
3321 |
+
"step": 4720
|
3322 |
+
},
|
3323 |
+
{
|
3324 |
+
"epoch": 1.8950320512820513,
|
3325 |
+
"grad_norm": 0.2590833902359009,
|
3326 |
+
"learning_rate": 7.20687015019783e-07,
|
3327 |
+
"loss": 0.1396,
|
3328 |
+
"step": 4730
|
3329 |
+
},
|
3330 |
+
{
|
3331 |
+
"epoch": 1.8990384615384617,
|
3332 |
+
"grad_norm": 0.2681121230125427,
|
3333 |
+
"learning_rate": 6.668429165893997e-07,
|
3334 |
+
"loss": 0.1356,
|
3335 |
+
"step": 4740
|
3336 |
+
},
|
3337 |
+
{
|
3338 |
+
"epoch": 1.9030448717948718,
|
3339 |
+
"grad_norm": 0.2643556296825409,
|
3340 |
+
"learning_rate": 6.150755841382527e-07,
|
3341 |
+
"loss": 0.1429,
|
3342 |
+
"step": 4750
|
3343 |
+
},
|
3344 |
+
{
|
3345 |
+
"epoch": 1.907051282051282,
|
3346 |
+
"grad_norm": 0.2717660963535309,
|
3347 |
+
"learning_rate": 5.653871969032054e-07,
|
3348 |
+
"loss": 0.1409,
|
3349 |
+
"step": 4760
|
3350 |
+
},
|
3351 |
+
{
|
3352 |
+
"epoch": 1.9110576923076923,
|
3353 |
+
"grad_norm": 0.24568721652030945,
|
3354 |
+
"learning_rate": 5.177798466042716e-07,
|
3355 |
+
"loss": 0.1444,
|
3356 |
+
"step": 4770
|
3357 |
+
},
|
3358 |
+
{
|
3359 |
+
"epoch": 1.9150641025641026,
|
3360 |
+
"grad_norm": 0.23634164035320282,
|
3361 |
+
"learning_rate": 4.722555373565751e-07,
|
3362 |
+
"loss": 0.1472,
|
3363 |
+
"step": 4780
|
3364 |
+
},
|
3365 |
+
{
|
3366 |
+
"epoch": 1.9190705128205128,
|
3367 |
+
"grad_norm": 0.23092865943908691,
|
3368 |
+
"learning_rate": 4.288161855859285e-07,
|
3369 |
+
"loss": 0.141,
|
3370 |
+
"step": 4790
|
3371 |
+
},
|
3372 |
+
{
|
3373 |
+
"epoch": 1.9230769230769231,
|
3374 |
+
"grad_norm": 0.26985424757003784,
|
3375 |
+
"learning_rate": 3.874636199482307e-07,
|
3376 |
+
"loss": 0.1446,
|
3377 |
+
"step": 4800
|
3378 |
+
},
|
3379 |
+
{
|
3380 |
+
"epoch": 1.9270833333333335,
|
3381 |
+
"grad_norm": 0.2507458031177521,
|
3382 |
+
"learning_rate": 3.481995812524286e-07,
|
3383 |
+
"loss": 0.1398,
|
3384 |
+
"step": 4810
|
3385 |
+
},
|
3386 |
+
{
|
3387 |
+
"epoch": 1.9310897435897436,
|
3388 |
+
"grad_norm": 0.24660862982273102,
|
3389 |
+
"learning_rate": 3.110257223872592e-07,
|
3390 |
+
"loss": 0.1421,
|
3391 |
+
"step": 4820
|
3392 |
+
},
|
3393 |
+
{
|
3394 |
+
"epoch": 1.9350961538461537,
|
3395 |
+
"grad_norm": 0.24846522510051727,
|
3396 |
+
"learning_rate": 2.7594360825166644e-07,
|
3397 |
+
"loss": 0.1439,
|
3398 |
+
"step": 4830
|
3399 |
+
},
|
3400 |
+
{
|
3401 |
+
"epoch": 1.939102564102564,
|
3402 |
+
"grad_norm": 0.25589925050735474,
|
3403 |
+
"learning_rate": 2.4295471568892005e-07,
|
3404 |
+
"loss": 0.136,
|
3405 |
+
"step": 4840
|
3406 |
+
},
|
3407 |
+
{
|
3408 |
+
"epoch": 1.9431089743589745,
|
3409 |
+
"grad_norm": 0.23860958218574524,
|
3410 |
+
"learning_rate": 2.1206043342445469e-07,
|
3411 |
+
"loss": 0.1446,
|
3412 |
+
"step": 4850
|
3413 |
+
},
|
3414 |
+
{
|
3415 |
+
"epoch": 1.9471153846153846,
|
3416 |
+
"grad_norm": 0.2679506540298462,
|
3417 |
+
"learning_rate": 1.8326206200739436e-07,
|
3418 |
+
"loss": 0.1399,
|
3419 |
+
"step": 4860
|
3420 |
+
},
|
3421 |
+
{
|
3422 |
+
"epoch": 1.9511217948717947,
|
3423 |
+
"grad_norm": 0.2246963083744049,
|
3424 |
+
"learning_rate": 1.5656081375581277e-07,
|
3425 |
+
"loss": 0.1435,
|
3426 |
+
"step": 4870
|
3427 |
+
},
|
3428 |
+
{
|
3429 |
+
"epoch": 1.9551282051282053,
|
3430 |
+
"grad_norm": 0.23173221945762634,
|
3431 |
+
"learning_rate": 1.3195781270570196e-07,
|
3432 |
+
"loss": 0.1438,
|
3433 |
+
"step": 4880
|
3434 |
+
},
|
3435 |
+
{
|
3436 |
+
"epoch": 1.9591346153846154,
|
3437 |
+
"grad_norm": 0.24970708787441254,
|
3438 |
+
"learning_rate": 1.0945409456364352e-07,
|
3439 |
+
"loss": 0.1429,
|
3440 |
+
"step": 4890
|
3441 |
+
},
|
3442 |
+
{
|
3443 |
+
"epoch": 1.9631410256410255,
|
3444 |
+
"grad_norm": 0.23272265493869781,
|
3445 |
+
"learning_rate": 8.90506066632102e-08,
|
3446 |
+
"loss": 0.14,
|
3447 |
+
"step": 4900
|
3448 |
+
},
|
3449 |
+
{
|
3450 |
+
"epoch": 1.967147435897436,
|
3451 |
+
"grad_norm": 0.25013232231140137,
|
3452 |
+
"learning_rate": 7.074820792510317e-08,
|
3453 |
+
"loss": 0.143,
|
3454 |
+
"step": 4910
|
3455 |
+
},
|
3456 |
+
{
|
3457 |
+
"epoch": 1.9711538461538463,
|
3458 |
+
"grad_norm": 0.2563280165195465,
|
3459 |
+
"learning_rate": 5.454766882097007e-08,
|
3460 |
+
"loss": 0.149,
|
3461 |
+
"step": 4920
|
3462 |
+
},
|
3463 |
+
{
|
3464 |
+
"epoch": 1.9751602564102564,
|
3465 |
+
"grad_norm": 0.25120726227760315,
|
3466 |
+
"learning_rate": 4.0449671340991866e-08,
|
3467 |
+
"loss": 0.1454,
|
3468 |
+
"step": 4930
|
3469 |
+
},
|
3470 |
+
{
|
3471 |
+
"epoch": 1.9791666666666665,
|
3472 |
+
"grad_norm": 0.2662029564380646,
|
3473 |
+
"learning_rate": 2.8454808965155954e-08,
|
3474 |
+
"loss": 0.1461,
|
3475 |
+
"step": 4940
|
3476 |
+
},
|
3477 |
+
{
|
3478 |
+
"epoch": 1.9831730769230769,
|
3479 |
+
"grad_norm": 0.24329765141010284,
|
3480 |
+
"learning_rate": 1.8563586638281615e-08,
|
3481 |
+
"loss": 0.1352,
|
3482 |
+
"step": 4950
|
3483 |
+
},
|
3484 |
+
{
|
3485 |
+
"epoch": 1.9871794871794872,
|
3486 |
+
"grad_norm": 0.24964918196201324,
|
3487 |
+
"learning_rate": 1.0776420748753734e-08,
|
3488 |
+
"loss": 0.1378,
|
3489 |
+
"step": 4960
|
3490 |
+
},
|
3491 |
+
{
|
3492 |
+
"epoch": 1.9911858974358974,
|
3493 |
+
"grad_norm": 0.24900883436203003,
|
3494 |
+
"learning_rate": 5.093639111025672e-09,
|
3495 |
+
"loss": 0.1451,
|
3496 |
+
"step": 4970
|
3497 |
+
},
|
3498 |
+
{
|
3499 |
+
"epoch": 1.9951923076923077,
|
3500 |
+
"grad_norm": 0.24761377274990082,
|
3501 |
+
"learning_rate": 1.5154809517747837e-09,
|
3502 |
+
"loss": 0.1333,
|
3503 |
+
"step": 4980
|
3504 |
+
},
|
3505 |
+
{
|
3506 |
+
"epoch": 1.999198717948718,
|
3507 |
+
"grad_norm": 0.2465759515762329,
|
3508 |
+
"learning_rate": 4.2096899854904284e-11,
|
3509 |
+
"loss": 0.1421,
|
3510 |
+
"step": 4990
|
3511 |
+
}
|
3512 |
+
],
|
3513 |
+
"logging_steps": 10,
|
3514 |
+
"max_steps": 4992,
|
3515 |
+
"num_input_tokens_seen": 0,
|
3516 |
+
"num_train_epochs": 2,
|
3517 |
+
"save_steps": 500,
|
3518 |
+
"stateful_callbacks": {
|
3519 |
+
"TrainerControl": {
|
3520 |
+
"args": {
|
3521 |
+
"should_epoch_stop": false,
|
3522 |
+
"should_evaluate": false,
|
3523 |
+
"should_log": false,
|
3524 |
+
"should_save": true,
|
3525 |
+
"should_training_stop": true
|
3526 |
+
},
|
3527 |
+
"attributes": {}
|
3528 |
+
}
|
3529 |
+
},
|
3530 |
+
"total_flos": 1.3554923454948815e+19,
|
3531 |
+
"train_batch_size": 64,
|
3532 |
+
"trial_name": null,
|
3533 |
+
"trial_params": null
|
3534 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6f9fb04aeb4879803b9e2e38cbebba39f4d71178946783943c8e19dbdb7f6f42
|
3 |
+
size 5624
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|