upload 11 files
Browse files- .gitattributes +1 -0
- README.md +202 -3
- adapter_config.json +34 -0
- adapter_model.safetensors +3 -0
- optimizer.pt +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +23 -0
- tokenizer.json +3 -0
- tokenizer_config.json +2068 -0
- trainer_state.json +2049 -0
- training_args.bin +3 -0
.gitattributes
CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
36 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
README.md
CHANGED
@@ -1,3 +1,202 @@
|
|
1 |
-
---
|
2 |
-
|
3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
base_model: unsloth/DeepSeek-R1-Distill-Llama-8B-unsloth-bnb-4bit
|
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 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "unsloth/DeepSeek-R1-Distill-Llama-8B-unsloth-bnb-4bit",
|
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": 16,
|
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": 4,
|
23 |
+
"rank_pattern": {},
|
24 |
+
"revision": null,
|
25 |
+
"target_modules": [
|
26 |
+
"o_proj",
|
27 |
+
"k_proj",
|
28 |
+
"q_proj",
|
29 |
+
"v_proj"
|
30 |
+
],
|
31 |
+
"task_type": "CAUSAL_LM",
|
32 |
+
"use_dora": false,
|
33 |
+
"use_rslora": false
|
34 |
+
}
|
adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:91b67c56efb502ebf032b56ba437b54ebc421bd46cbd880ce640ba514e37b95c
|
3 |
+
size 13665336
|
optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5e8482eae2a485a0ff93eaaf8ef2a98a5bc94ab55124527ca13218988f63c08d
|
3 |
+
size 7115284
|
rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d4c917636c7a58af68a29056522a757e9f9b99005b776641aa157c536967817d
|
3 |
+
size 14244
|
scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bb6ec96c80ae2a50b0dd328ba09a32ddbdcad248c7b74338d86580693ca3886f
|
3 |
+
size 1064
|
special_tokens_map.json
ADDED
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<|begin▁of▁sentence|>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": {
|
10 |
+
"content": "<|end▁of▁sentence|>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": {
|
17 |
+
"content": "<|finetune_right_pad_id|>",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": false,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
}
|
23 |
+
}
|
tokenizer.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d91915040cfac999d8c55f4b5bc6e67367c065e3a7a4e4b9438ce1f256addd86
|
3 |
+
size 17209530
|
tokenizer_config.json
ADDED
@@ -0,0 +1,2068 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": true,
|
3 |
+
"add_eos_token": false,
|
4 |
+
"add_prefix_space": null,
|
5 |
+
"added_tokens_decoder": {
|
6 |
+
"128000": {
|
7 |
+
"content": "<|begin▁of▁sentence|>",
|
8 |
+
"lstrip": false,
|
9 |
+
"normalized": false,
|
10 |
+
"rstrip": false,
|
11 |
+
"single_word": false,
|
12 |
+
"special": true
|
13 |
+
},
|
14 |
+
"128001": {
|
15 |
+
"content": "<|end▁of▁sentence|>",
|
16 |
+
"lstrip": false,
|
17 |
+
"normalized": false,
|
18 |
+
"rstrip": false,
|
19 |
+
"single_word": false,
|
20 |
+
"special": true
|
21 |
+
},
|
22 |
+
"128002": {
|
23 |
+
"content": "<|reserved_special_token_0|>",
|
24 |
+
"lstrip": false,
|
25 |
+
"normalized": false,
|
26 |
+
"rstrip": false,
|
27 |
+
"single_word": false,
|
28 |
+
"special": true
|
29 |
+
},
|
30 |
+
"128003": {
|
31 |
+
"content": "<|reserved_special_token_1|>",
|
32 |
+
"lstrip": false,
|
33 |
+
"normalized": false,
|
34 |
+
"rstrip": false,
|
35 |
+
"single_word": false,
|
36 |
+
"special": true
|
37 |
+
},
|
38 |
+
"128004": {
|
39 |
+
"content": "<|finetune_right_pad_id|>",
|
40 |
+
"lstrip": false,
|
41 |
+
"normalized": false,
|
42 |
+
"rstrip": false,
|
43 |
+
"single_word": false,
|
44 |
+
"special": true
|
45 |
+
},
|
46 |
+
"128005": {
|
47 |
+
"content": "<|reserved_special_token_2|>",
|
48 |
+
"lstrip": false,
|
49 |
+
"normalized": false,
|
50 |
+
"rstrip": false,
|
51 |
+
"single_word": false,
|
52 |
+
"special": true
|
53 |
+
},
|
54 |
+
"128006": {
|
55 |
+
"content": "<|start_header_id|>",
|
56 |
+
"lstrip": false,
|
57 |
+
"normalized": false,
|
58 |
+
"rstrip": false,
|
59 |
+
"single_word": false,
|
60 |
+
"special": true
|
61 |
+
},
|
62 |
+
"128007": {
|
63 |
+
"content": "<|end_header_id|>",
|
64 |
+
"lstrip": false,
|
65 |
+
"normalized": false,
|
66 |
+
"rstrip": false,
|
67 |
+
"single_word": false,
|
68 |
+
"special": true
|
69 |
+
},
|
70 |
+
"128008": {
|
71 |
+
"content": "<|eom_id|>",
|
72 |
+
"lstrip": false,
|
73 |
+
"normalized": false,
|
74 |
+
"rstrip": false,
|
75 |
+
"single_word": false,
|
76 |
+
"special": true
|
77 |
+
},
|
78 |
+
"128009": {
|
79 |
+
"content": "<|eot_id|>",
|
80 |
+
"lstrip": false,
|
81 |
+
"normalized": false,
|
82 |
+
"rstrip": false,
|
83 |
+
"single_word": false,
|
84 |
+
"special": true
|
85 |
+
},
|
86 |
+
"128010": {
|
87 |
+
"content": "<|python_tag|>",
|
88 |
+
"lstrip": false,
|
89 |
+
"normalized": false,
|
90 |
+
"rstrip": false,
|
91 |
+
"single_word": false,
|
92 |
+
"special": true
|
93 |
+
},
|
94 |
+
"128011": {
|
95 |
+
"content": "<|User|>",
|
96 |
+
"lstrip": false,
|
97 |
+
"normalized": false,
|
98 |
+
"rstrip": false,
|
99 |
+
"single_word": false,
|
100 |
+
"special": false
|
101 |
+
},
|
102 |
+
"128012": {
|
103 |
+
"content": "<|Assistant|>",
|
104 |
+
"lstrip": false,
|
105 |
+
"normalized": false,
|
106 |
+
"rstrip": false,
|
107 |
+
"single_word": false,
|
108 |
+
"special": false
|
109 |
+
},
|
110 |
+
"128013": {
|
111 |
+
"content": "<think>",
|
112 |
+
"lstrip": false,
|
113 |
+
"normalized": false,
|
114 |
+
"rstrip": false,
|
115 |
+
"single_word": false,
|
116 |
+
"special": false
|
117 |
+
},
|
118 |
+
"128014": {
|
119 |
+
"content": "</think>",
|
120 |
+
"lstrip": false,
|
121 |
+
"normalized": false,
|
122 |
+
"rstrip": false,
|
123 |
+
"single_word": false,
|
124 |
+
"special": false
|
125 |
+
},
|
126 |
+
"128015": {
|
127 |
+
"content": "<|▁pad▁|>",
|
128 |
+
"lstrip": false,
|
129 |
+
"normalized": false,
|
130 |
+
"rstrip": false,
|
131 |
+
"single_word": false,
|
132 |
+
"special": true
|
133 |
+
},
|
134 |
+
"128016": {
|
135 |
+
"content": "<|reserved_special_token_8|>",
|
136 |
+
"lstrip": false,
|
137 |
+
"normalized": false,
|
138 |
+
"rstrip": false,
|
139 |
+
"single_word": false,
|
140 |
+
"special": true
|
141 |
+
},
|
142 |
+
"128017": {
|
143 |
+
"content": "<|reserved_special_token_9|>",
|
144 |
+
"lstrip": false,
|
145 |
+
"normalized": false,
|
146 |
+
"rstrip": false,
|
147 |
+
"single_word": false,
|
148 |
+
"special": true
|
149 |
+
},
|
150 |
+
"128018": {
|
151 |
+
"content": "<|reserved_special_token_10|>",
|
152 |
+
"lstrip": false,
|
153 |
+
"normalized": false,
|
154 |
+
"rstrip": false,
|
155 |
+
"single_word": false,
|
156 |
+
"special": true
|
157 |
+
},
|
158 |
+
"128019": {
|
159 |
+
"content": "<|reserved_special_token_11|>",
|
160 |
+
"lstrip": false,
|
161 |
+
"normalized": false,
|
162 |
+
"rstrip": false,
|
163 |
+
"single_word": false,
|
164 |
+
"special": true
|
165 |
+
},
|
166 |
+
"128020": {
|
167 |
+
"content": "<|reserved_special_token_12|>",
|
168 |
+
"lstrip": false,
|
169 |
+
"normalized": false,
|
170 |
+
"rstrip": false,
|
171 |
+
"single_word": false,
|
172 |
+
"special": true
|
173 |
+
},
|
174 |
+
"128021": {
|
175 |
+
"content": "<|reserved_special_token_13|>",
|
176 |
+
"lstrip": false,
|
177 |
+
"normalized": false,
|
178 |
+
"rstrip": false,
|
179 |
+
"single_word": false,
|
180 |
+
"special": true
|
181 |
+
},
|
182 |
+
"128022": {
|
183 |
+
"content": "<|reserved_special_token_14|>",
|
184 |
+
"lstrip": false,
|
185 |
+
"normalized": false,
|
186 |
+
"rstrip": false,
|
187 |
+
"single_word": false,
|
188 |
+
"special": true
|
189 |
+
},
|
190 |
+
"128023": {
|
191 |
+
"content": "<|reserved_special_token_15|>",
|
192 |
+
"lstrip": false,
|
193 |
+
"normalized": false,
|
194 |
+
"rstrip": false,
|
195 |
+
"single_word": false,
|
196 |
+
"special": true
|
197 |
+
},
|
198 |
+
"128024": {
|
199 |
+
"content": "<|reserved_special_token_16|>",
|
200 |
+
"lstrip": false,
|
201 |
+
"normalized": false,
|
202 |
+
"rstrip": false,
|
203 |
+
"single_word": false,
|
204 |
+
"special": true
|
205 |
+
},
|
206 |
+
"128025": {
|
207 |
+
"content": "<|reserved_special_token_17|>",
|
208 |
+
"lstrip": false,
|
209 |
+
"normalized": false,
|
210 |
+
"rstrip": false,
|
211 |
+
"single_word": false,
|
212 |
+
"special": true
|
213 |
+
},
|
214 |
+
"128026": {
|
215 |
+
"content": "<|reserved_special_token_18|>",
|
216 |
+
"lstrip": false,
|
217 |
+
"normalized": false,
|
218 |
+
"rstrip": false,
|
219 |
+
"single_word": false,
|
220 |
+
"special": true
|
221 |
+
},
|
222 |
+
"128027": {
|
223 |
+
"content": "<|reserved_special_token_19|>",
|
224 |
+
"lstrip": false,
|
225 |
+
"normalized": false,
|
226 |
+
"rstrip": false,
|
227 |
+
"single_word": false,
|
228 |
+
"special": true
|
229 |
+
},
|
230 |
+
"128028": {
|
231 |
+
"content": "<|reserved_special_token_20|>",
|
232 |
+
"lstrip": false,
|
233 |
+
"normalized": false,
|
234 |
+
"rstrip": false,
|
235 |
+
"single_word": false,
|
236 |
+
"special": true
|
237 |
+
},
|
238 |
+
"128029": {
|
239 |
+
"content": "<|reserved_special_token_21|>",
|
240 |
+
"lstrip": false,
|
241 |
+
"normalized": false,
|
242 |
+
"rstrip": false,
|
243 |
+
"single_word": false,
|
244 |
+
"special": true
|
245 |
+
},
|
246 |
+
"128030": {
|
247 |
+
"content": "<|reserved_special_token_22|>",
|
248 |
+
"lstrip": false,
|
249 |
+
"normalized": false,
|
250 |
+
"rstrip": false,
|
251 |
+
"single_word": false,
|
252 |
+
"special": true
|
253 |
+
},
|
254 |
+
"128031": {
|
255 |
+
"content": "<|reserved_special_token_23|>",
|
256 |
+
"lstrip": false,
|
257 |
+
"normalized": false,
|
258 |
+
"rstrip": false,
|
259 |
+
"single_word": false,
|
260 |
+
"special": true
|
261 |
+
},
|
262 |
+
"128032": {
|
263 |
+
"content": "<|reserved_special_token_24|>",
|
264 |
+
"lstrip": false,
|
265 |
+
"normalized": false,
|
266 |
+
"rstrip": false,
|
267 |
+
"single_word": false,
|
268 |
+
"special": true
|
269 |
+
},
|
270 |
+
"128033": {
|
271 |
+
"content": "<|reserved_special_token_25|>",
|
272 |
+
"lstrip": false,
|
273 |
+
"normalized": false,
|
274 |
+
"rstrip": false,
|
275 |
+
"single_word": false,
|
276 |
+
"special": true
|
277 |
+
},
|
278 |
+
"128034": {
|
279 |
+
"content": "<|reserved_special_token_26|>",
|
280 |
+
"lstrip": false,
|
281 |
+
"normalized": false,
|
282 |
+
"rstrip": false,
|
283 |
+
"single_word": false,
|
284 |
+
"special": true
|
285 |
+
},
|
286 |
+
"128035": {
|
287 |
+
"content": "<|reserved_special_token_27|>",
|
288 |
+
"lstrip": false,
|
289 |
+
"normalized": false,
|
290 |
+
"rstrip": false,
|
291 |
+
"single_word": false,
|
292 |
+
"special": true
|
293 |
+
},
|
294 |
+
"128036": {
|
295 |
+
"content": "<|reserved_special_token_28|>",
|
296 |
+
"lstrip": false,
|
297 |
+
"normalized": false,
|
298 |
+
"rstrip": false,
|
299 |
+
"single_word": false,
|
300 |
+
"special": true
|
301 |
+
},
|
302 |
+
"128037": {
|
303 |
+
"content": "<|reserved_special_token_29|>",
|
304 |
+
"lstrip": false,
|
305 |
+
"normalized": false,
|
306 |
+
"rstrip": false,
|
307 |
+
"single_word": false,
|
308 |
+
"special": true
|
309 |
+
},
|
310 |
+
"128038": {
|
311 |
+
"content": "<|reserved_special_token_30|>",
|
312 |
+
"lstrip": false,
|
313 |
+
"normalized": false,
|
314 |
+
"rstrip": false,
|
315 |
+
"single_word": false,
|
316 |
+
"special": true
|
317 |
+
},
|
318 |
+
"128039": {
|
319 |
+
"content": "<|reserved_special_token_31|>",
|
320 |
+
"lstrip": false,
|
321 |
+
"normalized": false,
|
322 |
+
"rstrip": false,
|
323 |
+
"single_word": false,
|
324 |
+
"special": true
|
325 |
+
},
|
326 |
+
"128040": {
|
327 |
+
"content": "<|reserved_special_token_32|>",
|
328 |
+
"lstrip": false,
|
329 |
+
"normalized": false,
|
330 |
+
"rstrip": false,
|
331 |
+
"single_word": false,
|
332 |
+
"special": true
|
333 |
+
},
|
334 |
+
"128041": {
|
335 |
+
"content": "<|reserved_special_token_33|>",
|
336 |
+
"lstrip": false,
|
337 |
+
"normalized": false,
|
338 |
+
"rstrip": false,
|
339 |
+
"single_word": false,
|
340 |
+
"special": true
|
341 |
+
},
|
342 |
+
"128042": {
|
343 |
+
"content": "<|reserved_special_token_34|>",
|
344 |
+
"lstrip": false,
|
345 |
+
"normalized": false,
|
346 |
+
"rstrip": false,
|
347 |
+
"single_word": false,
|
348 |
+
"special": true
|
349 |
+
},
|
350 |
+
"128043": {
|
351 |
+
"content": "<|reserved_special_token_35|>",
|
352 |
+
"lstrip": false,
|
353 |
+
"normalized": false,
|
354 |
+
"rstrip": false,
|
355 |
+
"single_word": false,
|
356 |
+
"special": true
|
357 |
+
},
|
358 |
+
"128044": {
|
359 |
+
"content": "<|reserved_special_token_36|>",
|
360 |
+
"lstrip": false,
|
361 |
+
"normalized": false,
|
362 |
+
"rstrip": false,
|
363 |
+
"single_word": false,
|
364 |
+
"special": true
|
365 |
+
},
|
366 |
+
"128045": {
|
367 |
+
"content": "<|reserved_special_token_37|>",
|
368 |
+
"lstrip": false,
|
369 |
+
"normalized": false,
|
370 |
+
"rstrip": false,
|
371 |
+
"single_word": false,
|
372 |
+
"special": true
|
373 |
+
},
|
374 |
+
"128046": {
|
375 |
+
"content": "<|reserved_special_token_38|>",
|
376 |
+
"lstrip": false,
|
377 |
+
"normalized": false,
|
378 |
+
"rstrip": false,
|
379 |
+
"single_word": false,
|
380 |
+
"special": true
|
381 |
+
},
|
382 |
+
"128047": {
|
383 |
+
"content": "<|reserved_special_token_39|>",
|
384 |
+
"lstrip": false,
|
385 |
+
"normalized": false,
|
386 |
+
"rstrip": false,
|
387 |
+
"single_word": false,
|
388 |
+
"special": true
|
389 |
+
},
|
390 |
+
"128048": {
|
391 |
+
"content": "<|reserved_special_token_40|>",
|
392 |
+
"lstrip": false,
|
393 |
+
"normalized": false,
|
394 |
+
"rstrip": false,
|
395 |
+
"single_word": false,
|
396 |
+
"special": true
|
397 |
+
},
|
398 |
+
"128049": {
|
399 |
+
"content": "<|reserved_special_token_41|>",
|
400 |
+
"lstrip": false,
|
401 |
+
"normalized": false,
|
402 |
+
"rstrip": false,
|
403 |
+
"single_word": false,
|
404 |
+
"special": true
|
405 |
+
},
|
406 |
+
"128050": {
|
407 |
+
"content": "<|reserved_special_token_42|>",
|
408 |
+
"lstrip": false,
|
409 |
+
"normalized": false,
|
410 |
+
"rstrip": false,
|
411 |
+
"single_word": false,
|
412 |
+
"special": true
|
413 |
+
},
|
414 |
+
"128051": {
|
415 |
+
"content": "<|reserved_special_token_43|>",
|
416 |
+
"lstrip": false,
|
417 |
+
"normalized": false,
|
418 |
+
"rstrip": false,
|
419 |
+
"single_word": false,
|
420 |
+
"special": true
|
421 |
+
},
|
422 |
+
"128052": {
|
423 |
+
"content": "<|reserved_special_token_44|>",
|
424 |
+
"lstrip": false,
|
425 |
+
"normalized": false,
|
426 |
+
"rstrip": false,
|
427 |
+
"single_word": false,
|
428 |
+
"special": true
|
429 |
+
},
|
430 |
+
"128053": {
|
431 |
+
"content": "<|reserved_special_token_45|>",
|
432 |
+
"lstrip": false,
|
433 |
+
"normalized": false,
|
434 |
+
"rstrip": false,
|
435 |
+
"single_word": false,
|
436 |
+
"special": true
|
437 |
+
},
|
438 |
+
"128054": {
|
439 |
+
"content": "<|reserved_special_token_46|>",
|
440 |
+
"lstrip": false,
|
441 |
+
"normalized": false,
|
442 |
+
"rstrip": false,
|
443 |
+
"single_word": false,
|
444 |
+
"special": true
|
445 |
+
},
|
446 |
+
"128055": {
|
447 |
+
"content": "<|reserved_special_token_47|>",
|
448 |
+
"lstrip": false,
|
449 |
+
"normalized": false,
|
450 |
+
"rstrip": false,
|
451 |
+
"single_word": false,
|
452 |
+
"special": true
|
453 |
+
},
|
454 |
+
"128056": {
|
455 |
+
"content": "<|reserved_special_token_48|>",
|
456 |
+
"lstrip": false,
|
457 |
+
"normalized": false,
|
458 |
+
"rstrip": false,
|
459 |
+
"single_word": false,
|
460 |
+
"special": true
|
461 |
+
},
|
462 |
+
"128057": {
|
463 |
+
"content": "<|reserved_special_token_49|>",
|
464 |
+
"lstrip": false,
|
465 |
+
"normalized": false,
|
466 |
+
"rstrip": false,
|
467 |
+
"single_word": false,
|
468 |
+
"special": true
|
469 |
+
},
|
470 |
+
"128058": {
|
471 |
+
"content": "<|reserved_special_token_50|>",
|
472 |
+
"lstrip": false,
|
473 |
+
"normalized": false,
|
474 |
+
"rstrip": false,
|
475 |
+
"single_word": false,
|
476 |
+
"special": true
|
477 |
+
},
|
478 |
+
"128059": {
|
479 |
+
"content": "<|reserved_special_token_51|>",
|
480 |
+
"lstrip": false,
|
481 |
+
"normalized": false,
|
482 |
+
"rstrip": false,
|
483 |
+
"single_word": false,
|
484 |
+
"special": true
|
485 |
+
},
|
486 |
+
"128060": {
|
487 |
+
"content": "<|reserved_special_token_52|>",
|
488 |
+
"lstrip": false,
|
489 |
+
"normalized": false,
|
490 |
+
"rstrip": false,
|
491 |
+
"single_word": false,
|
492 |
+
"special": true
|
493 |
+
},
|
494 |
+
"128061": {
|
495 |
+
"content": "<|reserved_special_token_53|>",
|
496 |
+
"lstrip": false,
|
497 |
+
"normalized": false,
|
498 |
+
"rstrip": false,
|
499 |
+
"single_word": false,
|
500 |
+
"special": true
|
501 |
+
},
|
502 |
+
"128062": {
|
503 |
+
"content": "<|reserved_special_token_54|>",
|
504 |
+
"lstrip": false,
|
505 |
+
"normalized": false,
|
506 |
+
"rstrip": false,
|
507 |
+
"single_word": false,
|
508 |
+
"special": true
|
509 |
+
},
|
510 |
+
"128063": {
|
511 |
+
"content": "<|reserved_special_token_55|>",
|
512 |
+
"lstrip": false,
|
513 |
+
"normalized": false,
|
514 |
+
"rstrip": false,
|
515 |
+
"single_word": false,
|
516 |
+
"special": true
|
517 |
+
},
|
518 |
+
"128064": {
|
519 |
+
"content": "<|reserved_special_token_56|>",
|
520 |
+
"lstrip": false,
|
521 |
+
"normalized": false,
|
522 |
+
"rstrip": false,
|
523 |
+
"single_word": false,
|
524 |
+
"special": true
|
525 |
+
},
|
526 |
+
"128065": {
|
527 |
+
"content": "<|reserved_special_token_57|>",
|
528 |
+
"lstrip": false,
|
529 |
+
"normalized": false,
|
530 |
+
"rstrip": false,
|
531 |
+
"single_word": false,
|
532 |
+
"special": true
|
533 |
+
},
|
534 |
+
"128066": {
|
535 |
+
"content": "<|reserved_special_token_58|>",
|
536 |
+
"lstrip": false,
|
537 |
+
"normalized": false,
|
538 |
+
"rstrip": false,
|
539 |
+
"single_word": false,
|
540 |
+
"special": true
|
541 |
+
},
|
542 |
+
"128067": {
|
543 |
+
"content": "<|reserved_special_token_59|>",
|
544 |
+
"lstrip": false,
|
545 |
+
"normalized": false,
|
546 |
+
"rstrip": false,
|
547 |
+
"single_word": false,
|
548 |
+
"special": true
|
549 |
+
},
|
550 |
+
"128068": {
|
551 |
+
"content": "<|reserved_special_token_60|>",
|
552 |
+
"lstrip": false,
|
553 |
+
"normalized": false,
|
554 |
+
"rstrip": false,
|
555 |
+
"single_word": false,
|
556 |
+
"special": true
|
557 |
+
},
|
558 |
+
"128069": {
|
559 |
+
"content": "<|reserved_special_token_61|>",
|
560 |
+
"lstrip": false,
|
561 |
+
"normalized": false,
|
562 |
+
"rstrip": false,
|
563 |
+
"single_word": false,
|
564 |
+
"special": true
|
565 |
+
},
|
566 |
+
"128070": {
|
567 |
+
"content": "<|reserved_special_token_62|>",
|
568 |
+
"lstrip": false,
|
569 |
+
"normalized": false,
|
570 |
+
"rstrip": false,
|
571 |
+
"single_word": false,
|
572 |
+
"special": true
|
573 |
+
},
|
574 |
+
"128071": {
|
575 |
+
"content": "<|reserved_special_token_63|>",
|
576 |
+
"lstrip": false,
|
577 |
+
"normalized": false,
|
578 |
+
"rstrip": false,
|
579 |
+
"single_word": false,
|
580 |
+
"special": true
|
581 |
+
},
|
582 |
+
"128072": {
|
583 |
+
"content": "<|reserved_special_token_64|>",
|
584 |
+
"lstrip": false,
|
585 |
+
"normalized": false,
|
586 |
+
"rstrip": false,
|
587 |
+
"single_word": false,
|
588 |
+
"special": true
|
589 |
+
},
|
590 |
+
"128073": {
|
591 |
+
"content": "<|reserved_special_token_65|>",
|
592 |
+
"lstrip": false,
|
593 |
+
"normalized": false,
|
594 |
+
"rstrip": false,
|
595 |
+
"single_word": false,
|
596 |
+
"special": true
|
597 |
+
},
|
598 |
+
"128074": {
|
599 |
+
"content": "<|reserved_special_token_66|>",
|
600 |
+
"lstrip": false,
|
601 |
+
"normalized": false,
|
602 |
+
"rstrip": false,
|
603 |
+
"single_word": false,
|
604 |
+
"special": true
|
605 |
+
},
|
606 |
+
"128075": {
|
607 |
+
"content": "<|reserved_special_token_67|>",
|
608 |
+
"lstrip": false,
|
609 |
+
"normalized": false,
|
610 |
+
"rstrip": false,
|
611 |
+
"single_word": false,
|
612 |
+
"special": true
|
613 |
+
},
|
614 |
+
"128076": {
|
615 |
+
"content": "<|reserved_special_token_68|>",
|
616 |
+
"lstrip": false,
|
617 |
+
"normalized": false,
|
618 |
+
"rstrip": false,
|
619 |
+
"single_word": false,
|
620 |
+
"special": true
|
621 |
+
},
|
622 |
+
"128077": {
|
623 |
+
"content": "<|reserved_special_token_69|>",
|
624 |
+
"lstrip": false,
|
625 |
+
"normalized": false,
|
626 |
+
"rstrip": false,
|
627 |
+
"single_word": false,
|
628 |
+
"special": true
|
629 |
+
},
|
630 |
+
"128078": {
|
631 |
+
"content": "<|reserved_special_token_70|>",
|
632 |
+
"lstrip": false,
|
633 |
+
"normalized": false,
|
634 |
+
"rstrip": false,
|
635 |
+
"single_word": false,
|
636 |
+
"special": true
|
637 |
+
},
|
638 |
+
"128079": {
|
639 |
+
"content": "<|reserved_special_token_71|>",
|
640 |
+
"lstrip": false,
|
641 |
+
"normalized": false,
|
642 |
+
"rstrip": false,
|
643 |
+
"single_word": false,
|
644 |
+
"special": true
|
645 |
+
},
|
646 |
+
"128080": {
|
647 |
+
"content": "<|reserved_special_token_72|>",
|
648 |
+
"lstrip": false,
|
649 |
+
"normalized": false,
|
650 |
+
"rstrip": false,
|
651 |
+
"single_word": false,
|
652 |
+
"special": true
|
653 |
+
},
|
654 |
+
"128081": {
|
655 |
+
"content": "<|reserved_special_token_73|>",
|
656 |
+
"lstrip": false,
|
657 |
+
"normalized": false,
|
658 |
+
"rstrip": false,
|
659 |
+
"single_word": false,
|
660 |
+
"special": true
|
661 |
+
},
|
662 |
+
"128082": {
|
663 |
+
"content": "<|reserved_special_token_74|>",
|
664 |
+
"lstrip": false,
|
665 |
+
"normalized": false,
|
666 |
+
"rstrip": false,
|
667 |
+
"single_word": false,
|
668 |
+
"special": true
|
669 |
+
},
|
670 |
+
"128083": {
|
671 |
+
"content": "<|reserved_special_token_75|>",
|
672 |
+
"lstrip": false,
|
673 |
+
"normalized": false,
|
674 |
+
"rstrip": false,
|
675 |
+
"single_word": false,
|
676 |
+
"special": true
|
677 |
+
},
|
678 |
+
"128084": {
|
679 |
+
"content": "<|reserved_special_token_76|>",
|
680 |
+
"lstrip": false,
|
681 |
+
"normalized": false,
|
682 |
+
"rstrip": false,
|
683 |
+
"single_word": false,
|
684 |
+
"special": true
|
685 |
+
},
|
686 |
+
"128085": {
|
687 |
+
"content": "<|reserved_special_token_77|>",
|
688 |
+
"lstrip": false,
|
689 |
+
"normalized": false,
|
690 |
+
"rstrip": false,
|
691 |
+
"single_word": false,
|
692 |
+
"special": true
|
693 |
+
},
|
694 |
+
"128086": {
|
695 |
+
"content": "<|reserved_special_token_78|>",
|
696 |
+
"lstrip": false,
|
697 |
+
"normalized": false,
|
698 |
+
"rstrip": false,
|
699 |
+
"single_word": false,
|
700 |
+
"special": true
|
701 |
+
},
|
702 |
+
"128087": {
|
703 |
+
"content": "<|reserved_special_token_79|>",
|
704 |
+
"lstrip": false,
|
705 |
+
"normalized": false,
|
706 |
+
"rstrip": false,
|
707 |
+
"single_word": false,
|
708 |
+
"special": true
|
709 |
+
},
|
710 |
+
"128088": {
|
711 |
+
"content": "<|reserved_special_token_80|>",
|
712 |
+
"lstrip": false,
|
713 |
+
"normalized": false,
|
714 |
+
"rstrip": false,
|
715 |
+
"single_word": false,
|
716 |
+
"special": true
|
717 |
+
},
|
718 |
+
"128089": {
|
719 |
+
"content": "<|reserved_special_token_81|>",
|
720 |
+
"lstrip": false,
|
721 |
+
"normalized": false,
|
722 |
+
"rstrip": false,
|
723 |
+
"single_word": false,
|
724 |
+
"special": true
|
725 |
+
},
|
726 |
+
"128090": {
|
727 |
+
"content": "<|reserved_special_token_82|>",
|
728 |
+
"lstrip": false,
|
729 |
+
"normalized": false,
|
730 |
+
"rstrip": false,
|
731 |
+
"single_word": false,
|
732 |
+
"special": true
|
733 |
+
},
|
734 |
+
"128091": {
|
735 |
+
"content": "<|reserved_special_token_83|>",
|
736 |
+
"lstrip": false,
|
737 |
+
"normalized": false,
|
738 |
+
"rstrip": false,
|
739 |
+
"single_word": false,
|
740 |
+
"special": true
|
741 |
+
},
|
742 |
+
"128092": {
|
743 |
+
"content": "<|reserved_special_token_84|>",
|
744 |
+
"lstrip": false,
|
745 |
+
"normalized": false,
|
746 |
+
"rstrip": false,
|
747 |
+
"single_word": false,
|
748 |
+
"special": true
|
749 |
+
},
|
750 |
+
"128093": {
|
751 |
+
"content": "<|reserved_special_token_85|>",
|
752 |
+
"lstrip": false,
|
753 |
+
"normalized": false,
|
754 |
+
"rstrip": false,
|
755 |
+
"single_word": false,
|
756 |
+
"special": true
|
757 |
+
},
|
758 |
+
"128094": {
|
759 |
+
"content": "<|reserved_special_token_86|>",
|
760 |
+
"lstrip": false,
|
761 |
+
"normalized": false,
|
762 |
+
"rstrip": false,
|
763 |
+
"single_word": false,
|
764 |
+
"special": true
|
765 |
+
},
|
766 |
+
"128095": {
|
767 |
+
"content": "<|reserved_special_token_87|>",
|
768 |
+
"lstrip": false,
|
769 |
+
"normalized": false,
|
770 |
+
"rstrip": false,
|
771 |
+
"single_word": false,
|
772 |
+
"special": true
|
773 |
+
},
|
774 |
+
"128096": {
|
775 |
+
"content": "<|reserved_special_token_88|>",
|
776 |
+
"lstrip": false,
|
777 |
+
"normalized": false,
|
778 |
+
"rstrip": false,
|
779 |
+
"single_word": false,
|
780 |
+
"special": true
|
781 |
+
},
|
782 |
+
"128097": {
|
783 |
+
"content": "<|reserved_special_token_89|>",
|
784 |
+
"lstrip": false,
|
785 |
+
"normalized": false,
|
786 |
+
"rstrip": false,
|
787 |
+
"single_word": false,
|
788 |
+
"special": true
|
789 |
+
},
|
790 |
+
"128098": {
|
791 |
+
"content": "<|reserved_special_token_90|>",
|
792 |
+
"lstrip": false,
|
793 |
+
"normalized": false,
|
794 |
+
"rstrip": false,
|
795 |
+
"single_word": false,
|
796 |
+
"special": true
|
797 |
+
},
|
798 |
+
"128099": {
|
799 |
+
"content": "<|reserved_special_token_91|>",
|
800 |
+
"lstrip": false,
|
801 |
+
"normalized": false,
|
802 |
+
"rstrip": false,
|
803 |
+
"single_word": false,
|
804 |
+
"special": true
|
805 |
+
},
|
806 |
+
"128100": {
|
807 |
+
"content": "<|reserved_special_token_92|>",
|
808 |
+
"lstrip": false,
|
809 |
+
"normalized": false,
|
810 |
+
"rstrip": false,
|
811 |
+
"single_word": false,
|
812 |
+
"special": true
|
813 |
+
},
|
814 |
+
"128101": {
|
815 |
+
"content": "<|reserved_special_token_93|>",
|
816 |
+
"lstrip": false,
|
817 |
+
"normalized": false,
|
818 |
+
"rstrip": false,
|
819 |
+
"single_word": false,
|
820 |
+
"special": true
|
821 |
+
},
|
822 |
+
"128102": {
|
823 |
+
"content": "<|reserved_special_token_94|>",
|
824 |
+
"lstrip": false,
|
825 |
+
"normalized": false,
|
826 |
+
"rstrip": false,
|
827 |
+
"single_word": false,
|
828 |
+
"special": true
|
829 |
+
},
|
830 |
+
"128103": {
|
831 |
+
"content": "<|reserved_special_token_95|>",
|
832 |
+
"lstrip": false,
|
833 |
+
"normalized": false,
|
834 |
+
"rstrip": false,
|
835 |
+
"single_word": false,
|
836 |
+
"special": true
|
837 |
+
},
|
838 |
+
"128104": {
|
839 |
+
"content": "<|reserved_special_token_96|>",
|
840 |
+
"lstrip": false,
|
841 |
+
"normalized": false,
|
842 |
+
"rstrip": false,
|
843 |
+
"single_word": false,
|
844 |
+
"special": true
|
845 |
+
},
|
846 |
+
"128105": {
|
847 |
+
"content": "<|reserved_special_token_97|>",
|
848 |
+
"lstrip": false,
|
849 |
+
"normalized": false,
|
850 |
+
"rstrip": false,
|
851 |
+
"single_word": false,
|
852 |
+
"special": true
|
853 |
+
},
|
854 |
+
"128106": {
|
855 |
+
"content": "<|reserved_special_token_98|>",
|
856 |
+
"lstrip": false,
|
857 |
+
"normalized": false,
|
858 |
+
"rstrip": false,
|
859 |
+
"single_word": false,
|
860 |
+
"special": true
|
861 |
+
},
|
862 |
+
"128107": {
|
863 |
+
"content": "<|reserved_special_token_99|>",
|
864 |
+
"lstrip": false,
|
865 |
+
"normalized": false,
|
866 |
+
"rstrip": false,
|
867 |
+
"single_word": false,
|
868 |
+
"special": true
|
869 |
+
},
|
870 |
+
"128108": {
|
871 |
+
"content": "<|reserved_special_token_100|>",
|
872 |
+
"lstrip": false,
|
873 |
+
"normalized": false,
|
874 |
+
"rstrip": false,
|
875 |
+
"single_word": false,
|
876 |
+
"special": true
|
877 |
+
},
|
878 |
+
"128109": {
|
879 |
+
"content": "<|reserved_special_token_101|>",
|
880 |
+
"lstrip": false,
|
881 |
+
"normalized": false,
|
882 |
+
"rstrip": false,
|
883 |
+
"single_word": false,
|
884 |
+
"special": true
|
885 |
+
},
|
886 |
+
"128110": {
|
887 |
+
"content": "<|reserved_special_token_102|>",
|
888 |
+
"lstrip": false,
|
889 |
+
"normalized": false,
|
890 |
+
"rstrip": false,
|
891 |
+
"single_word": false,
|
892 |
+
"special": true
|
893 |
+
},
|
894 |
+
"128111": {
|
895 |
+
"content": "<|reserved_special_token_103|>",
|
896 |
+
"lstrip": false,
|
897 |
+
"normalized": false,
|
898 |
+
"rstrip": false,
|
899 |
+
"single_word": false,
|
900 |
+
"special": true
|
901 |
+
},
|
902 |
+
"128112": {
|
903 |
+
"content": "<|reserved_special_token_104|>",
|
904 |
+
"lstrip": false,
|
905 |
+
"normalized": false,
|
906 |
+
"rstrip": false,
|
907 |
+
"single_word": false,
|
908 |
+
"special": true
|
909 |
+
},
|
910 |
+
"128113": {
|
911 |
+
"content": "<|reserved_special_token_105|>",
|
912 |
+
"lstrip": false,
|
913 |
+
"normalized": false,
|
914 |
+
"rstrip": false,
|
915 |
+
"single_word": false,
|
916 |
+
"special": true
|
917 |
+
},
|
918 |
+
"128114": {
|
919 |
+
"content": "<|reserved_special_token_106|>",
|
920 |
+
"lstrip": false,
|
921 |
+
"normalized": false,
|
922 |
+
"rstrip": false,
|
923 |
+
"single_word": false,
|
924 |
+
"special": true
|
925 |
+
},
|
926 |
+
"128115": {
|
927 |
+
"content": "<|reserved_special_token_107|>",
|
928 |
+
"lstrip": false,
|
929 |
+
"normalized": false,
|
930 |
+
"rstrip": false,
|
931 |
+
"single_word": false,
|
932 |
+
"special": true
|
933 |
+
},
|
934 |
+
"128116": {
|
935 |
+
"content": "<|reserved_special_token_108|>",
|
936 |
+
"lstrip": false,
|
937 |
+
"normalized": false,
|
938 |
+
"rstrip": false,
|
939 |
+
"single_word": false,
|
940 |
+
"special": true
|
941 |
+
},
|
942 |
+
"128117": {
|
943 |
+
"content": "<|reserved_special_token_109|>",
|
944 |
+
"lstrip": false,
|
945 |
+
"normalized": false,
|
946 |
+
"rstrip": false,
|
947 |
+
"single_word": false,
|
948 |
+
"special": true
|
949 |
+
},
|
950 |
+
"128118": {
|
951 |
+
"content": "<|reserved_special_token_110|>",
|
952 |
+
"lstrip": false,
|
953 |
+
"normalized": false,
|
954 |
+
"rstrip": false,
|
955 |
+
"single_word": false,
|
956 |
+
"special": true
|
957 |
+
},
|
958 |
+
"128119": {
|
959 |
+
"content": "<|reserved_special_token_111|>",
|
960 |
+
"lstrip": false,
|
961 |
+
"normalized": false,
|
962 |
+
"rstrip": false,
|
963 |
+
"single_word": false,
|
964 |
+
"special": true
|
965 |
+
},
|
966 |
+
"128120": {
|
967 |
+
"content": "<|reserved_special_token_112|>",
|
968 |
+
"lstrip": false,
|
969 |
+
"normalized": false,
|
970 |
+
"rstrip": false,
|
971 |
+
"single_word": false,
|
972 |
+
"special": true
|
973 |
+
},
|
974 |
+
"128121": {
|
975 |
+
"content": "<|reserved_special_token_113|>",
|
976 |
+
"lstrip": false,
|
977 |
+
"normalized": false,
|
978 |
+
"rstrip": false,
|
979 |
+
"single_word": false,
|
980 |
+
"special": true
|
981 |
+
},
|
982 |
+
"128122": {
|
983 |
+
"content": "<|reserved_special_token_114|>",
|
984 |
+
"lstrip": false,
|
985 |
+
"normalized": false,
|
986 |
+
"rstrip": false,
|
987 |
+
"single_word": false,
|
988 |
+
"special": true
|
989 |
+
},
|
990 |
+
"128123": {
|
991 |
+
"content": "<|reserved_special_token_115|>",
|
992 |
+
"lstrip": false,
|
993 |
+
"normalized": false,
|
994 |
+
"rstrip": false,
|
995 |
+
"single_word": false,
|
996 |
+
"special": true
|
997 |
+
},
|
998 |
+
"128124": {
|
999 |
+
"content": "<|reserved_special_token_116|>",
|
1000 |
+
"lstrip": false,
|
1001 |
+
"normalized": false,
|
1002 |
+
"rstrip": false,
|
1003 |
+
"single_word": false,
|
1004 |
+
"special": true
|
1005 |
+
},
|
1006 |
+
"128125": {
|
1007 |
+
"content": "<|reserved_special_token_117|>",
|
1008 |
+
"lstrip": false,
|
1009 |
+
"normalized": false,
|
1010 |
+
"rstrip": false,
|
1011 |
+
"single_word": false,
|
1012 |
+
"special": true
|
1013 |
+
},
|
1014 |
+
"128126": {
|
1015 |
+
"content": "<|reserved_special_token_118|>",
|
1016 |
+
"lstrip": false,
|
1017 |
+
"normalized": false,
|
1018 |
+
"rstrip": false,
|
1019 |
+
"single_word": false,
|
1020 |
+
"special": true
|
1021 |
+
},
|
1022 |
+
"128127": {
|
1023 |
+
"content": "<|reserved_special_token_119|>",
|
1024 |
+
"lstrip": false,
|
1025 |
+
"normalized": false,
|
1026 |
+
"rstrip": false,
|
1027 |
+
"single_word": false,
|
1028 |
+
"special": true
|
1029 |
+
},
|
1030 |
+
"128128": {
|
1031 |
+
"content": "<|reserved_special_token_120|>",
|
1032 |
+
"lstrip": false,
|
1033 |
+
"normalized": false,
|
1034 |
+
"rstrip": false,
|
1035 |
+
"single_word": false,
|
1036 |
+
"special": true
|
1037 |
+
},
|
1038 |
+
"128129": {
|
1039 |
+
"content": "<|reserved_special_token_121|>",
|
1040 |
+
"lstrip": false,
|
1041 |
+
"normalized": false,
|
1042 |
+
"rstrip": false,
|
1043 |
+
"single_word": false,
|
1044 |
+
"special": true
|
1045 |
+
},
|
1046 |
+
"128130": {
|
1047 |
+
"content": "<|reserved_special_token_122|>",
|
1048 |
+
"lstrip": false,
|
1049 |
+
"normalized": false,
|
1050 |
+
"rstrip": false,
|
1051 |
+
"single_word": false,
|
1052 |
+
"special": true
|
1053 |
+
},
|
1054 |
+
"128131": {
|
1055 |
+
"content": "<|reserved_special_token_123|>",
|
1056 |
+
"lstrip": false,
|
1057 |
+
"normalized": false,
|
1058 |
+
"rstrip": false,
|
1059 |
+
"single_word": false,
|
1060 |
+
"special": true
|
1061 |
+
},
|
1062 |
+
"128132": {
|
1063 |
+
"content": "<|reserved_special_token_124|>",
|
1064 |
+
"lstrip": false,
|
1065 |
+
"normalized": false,
|
1066 |
+
"rstrip": false,
|
1067 |
+
"single_word": false,
|
1068 |
+
"special": true
|
1069 |
+
},
|
1070 |
+
"128133": {
|
1071 |
+
"content": "<|reserved_special_token_125|>",
|
1072 |
+
"lstrip": false,
|
1073 |
+
"normalized": false,
|
1074 |
+
"rstrip": false,
|
1075 |
+
"single_word": false,
|
1076 |
+
"special": true
|
1077 |
+
},
|
1078 |
+
"128134": {
|
1079 |
+
"content": "<|reserved_special_token_126|>",
|
1080 |
+
"lstrip": false,
|
1081 |
+
"normalized": false,
|
1082 |
+
"rstrip": false,
|
1083 |
+
"single_word": false,
|
1084 |
+
"special": true
|
1085 |
+
},
|
1086 |
+
"128135": {
|
1087 |
+
"content": "<|reserved_special_token_127|>",
|
1088 |
+
"lstrip": false,
|
1089 |
+
"normalized": false,
|
1090 |
+
"rstrip": false,
|
1091 |
+
"single_word": false,
|
1092 |
+
"special": true
|
1093 |
+
},
|
1094 |
+
"128136": {
|
1095 |
+
"content": "<|reserved_special_token_128|>",
|
1096 |
+
"lstrip": false,
|
1097 |
+
"normalized": false,
|
1098 |
+
"rstrip": false,
|
1099 |
+
"single_word": false,
|
1100 |
+
"special": true
|
1101 |
+
},
|
1102 |
+
"128137": {
|
1103 |
+
"content": "<|reserved_special_token_129|>",
|
1104 |
+
"lstrip": false,
|
1105 |
+
"normalized": false,
|
1106 |
+
"rstrip": false,
|
1107 |
+
"single_word": false,
|
1108 |
+
"special": true
|
1109 |
+
},
|
1110 |
+
"128138": {
|
1111 |
+
"content": "<|reserved_special_token_130|>",
|
1112 |
+
"lstrip": false,
|
1113 |
+
"normalized": false,
|
1114 |
+
"rstrip": false,
|
1115 |
+
"single_word": false,
|
1116 |
+
"special": true
|
1117 |
+
},
|
1118 |
+
"128139": {
|
1119 |
+
"content": "<|reserved_special_token_131|>",
|
1120 |
+
"lstrip": false,
|
1121 |
+
"normalized": false,
|
1122 |
+
"rstrip": false,
|
1123 |
+
"single_word": false,
|
1124 |
+
"special": true
|
1125 |
+
},
|
1126 |
+
"128140": {
|
1127 |
+
"content": "<|reserved_special_token_132|>",
|
1128 |
+
"lstrip": false,
|
1129 |
+
"normalized": false,
|
1130 |
+
"rstrip": false,
|
1131 |
+
"single_word": false,
|
1132 |
+
"special": true
|
1133 |
+
},
|
1134 |
+
"128141": {
|
1135 |
+
"content": "<|reserved_special_token_133|>",
|
1136 |
+
"lstrip": false,
|
1137 |
+
"normalized": false,
|
1138 |
+
"rstrip": false,
|
1139 |
+
"single_word": false,
|
1140 |
+
"special": true
|
1141 |
+
},
|
1142 |
+
"128142": {
|
1143 |
+
"content": "<|reserved_special_token_134|>",
|
1144 |
+
"lstrip": false,
|
1145 |
+
"normalized": false,
|
1146 |
+
"rstrip": false,
|
1147 |
+
"single_word": false,
|
1148 |
+
"special": true
|
1149 |
+
},
|
1150 |
+
"128143": {
|
1151 |
+
"content": "<|reserved_special_token_135|>",
|
1152 |
+
"lstrip": false,
|
1153 |
+
"normalized": false,
|
1154 |
+
"rstrip": false,
|
1155 |
+
"single_word": false,
|
1156 |
+
"special": true
|
1157 |
+
},
|
1158 |
+
"128144": {
|
1159 |
+
"content": "<|reserved_special_token_136|>",
|
1160 |
+
"lstrip": false,
|
1161 |
+
"normalized": false,
|
1162 |
+
"rstrip": false,
|
1163 |
+
"single_word": false,
|
1164 |
+
"special": true
|
1165 |
+
},
|
1166 |
+
"128145": {
|
1167 |
+
"content": "<|reserved_special_token_137|>",
|
1168 |
+
"lstrip": false,
|
1169 |
+
"normalized": false,
|
1170 |
+
"rstrip": false,
|
1171 |
+
"single_word": false,
|
1172 |
+
"special": true
|
1173 |
+
},
|
1174 |
+
"128146": {
|
1175 |
+
"content": "<|reserved_special_token_138|>",
|
1176 |
+
"lstrip": false,
|
1177 |
+
"normalized": false,
|
1178 |
+
"rstrip": false,
|
1179 |
+
"single_word": false,
|
1180 |
+
"special": true
|
1181 |
+
},
|
1182 |
+
"128147": {
|
1183 |
+
"content": "<|reserved_special_token_139|>",
|
1184 |
+
"lstrip": false,
|
1185 |
+
"normalized": false,
|
1186 |
+
"rstrip": false,
|
1187 |
+
"single_word": false,
|
1188 |
+
"special": true
|
1189 |
+
},
|
1190 |
+
"128148": {
|
1191 |
+
"content": "<|reserved_special_token_140|>",
|
1192 |
+
"lstrip": false,
|
1193 |
+
"normalized": false,
|
1194 |
+
"rstrip": false,
|
1195 |
+
"single_word": false,
|
1196 |
+
"special": true
|
1197 |
+
},
|
1198 |
+
"128149": {
|
1199 |
+
"content": "<|reserved_special_token_141|>",
|
1200 |
+
"lstrip": false,
|
1201 |
+
"normalized": false,
|
1202 |
+
"rstrip": false,
|
1203 |
+
"single_word": false,
|
1204 |
+
"special": true
|
1205 |
+
},
|
1206 |
+
"128150": {
|
1207 |
+
"content": "<|reserved_special_token_142|>",
|
1208 |
+
"lstrip": false,
|
1209 |
+
"normalized": false,
|
1210 |
+
"rstrip": false,
|
1211 |
+
"single_word": false,
|
1212 |
+
"special": true
|
1213 |
+
},
|
1214 |
+
"128151": {
|
1215 |
+
"content": "<|reserved_special_token_143|>",
|
1216 |
+
"lstrip": false,
|
1217 |
+
"normalized": false,
|
1218 |
+
"rstrip": false,
|
1219 |
+
"single_word": false,
|
1220 |
+
"special": true
|
1221 |
+
},
|
1222 |
+
"128152": {
|
1223 |
+
"content": "<|reserved_special_token_144|>",
|
1224 |
+
"lstrip": false,
|
1225 |
+
"normalized": false,
|
1226 |
+
"rstrip": false,
|
1227 |
+
"single_word": false,
|
1228 |
+
"special": true
|
1229 |
+
},
|
1230 |
+
"128153": {
|
1231 |
+
"content": "<|reserved_special_token_145|>",
|
1232 |
+
"lstrip": false,
|
1233 |
+
"normalized": false,
|
1234 |
+
"rstrip": false,
|
1235 |
+
"single_word": false,
|
1236 |
+
"special": true
|
1237 |
+
},
|
1238 |
+
"128154": {
|
1239 |
+
"content": "<|reserved_special_token_146|>",
|
1240 |
+
"lstrip": false,
|
1241 |
+
"normalized": false,
|
1242 |
+
"rstrip": false,
|
1243 |
+
"single_word": false,
|
1244 |
+
"special": true
|
1245 |
+
},
|
1246 |
+
"128155": {
|
1247 |
+
"content": "<|reserved_special_token_147|>",
|
1248 |
+
"lstrip": false,
|
1249 |
+
"normalized": false,
|
1250 |
+
"rstrip": false,
|
1251 |
+
"single_word": false,
|
1252 |
+
"special": true
|
1253 |
+
},
|
1254 |
+
"128156": {
|
1255 |
+
"content": "<|reserved_special_token_148|>",
|
1256 |
+
"lstrip": false,
|
1257 |
+
"normalized": false,
|
1258 |
+
"rstrip": false,
|
1259 |
+
"single_word": false,
|
1260 |
+
"special": true
|
1261 |
+
},
|
1262 |
+
"128157": {
|
1263 |
+
"content": "<|reserved_special_token_149|>",
|
1264 |
+
"lstrip": false,
|
1265 |
+
"normalized": false,
|
1266 |
+
"rstrip": false,
|
1267 |
+
"single_word": false,
|
1268 |
+
"special": true
|
1269 |
+
},
|
1270 |
+
"128158": {
|
1271 |
+
"content": "<|reserved_special_token_150|>",
|
1272 |
+
"lstrip": false,
|
1273 |
+
"normalized": false,
|
1274 |
+
"rstrip": false,
|
1275 |
+
"single_word": false,
|
1276 |
+
"special": true
|
1277 |
+
},
|
1278 |
+
"128159": {
|
1279 |
+
"content": "<|reserved_special_token_151|>",
|
1280 |
+
"lstrip": false,
|
1281 |
+
"normalized": false,
|
1282 |
+
"rstrip": false,
|
1283 |
+
"single_word": false,
|
1284 |
+
"special": true
|
1285 |
+
},
|
1286 |
+
"128160": {
|
1287 |
+
"content": "<|reserved_special_token_152|>",
|
1288 |
+
"lstrip": false,
|
1289 |
+
"normalized": false,
|
1290 |
+
"rstrip": false,
|
1291 |
+
"single_word": false,
|
1292 |
+
"special": true
|
1293 |
+
},
|
1294 |
+
"128161": {
|
1295 |
+
"content": "<|reserved_special_token_153|>",
|
1296 |
+
"lstrip": false,
|
1297 |
+
"normalized": false,
|
1298 |
+
"rstrip": false,
|
1299 |
+
"single_word": false,
|
1300 |
+
"special": true
|
1301 |
+
},
|
1302 |
+
"128162": {
|
1303 |
+
"content": "<|reserved_special_token_154|>",
|
1304 |
+
"lstrip": false,
|
1305 |
+
"normalized": false,
|
1306 |
+
"rstrip": false,
|
1307 |
+
"single_word": false,
|
1308 |
+
"special": true
|
1309 |
+
},
|
1310 |
+
"128163": {
|
1311 |
+
"content": "<|reserved_special_token_155|>",
|
1312 |
+
"lstrip": false,
|
1313 |
+
"normalized": false,
|
1314 |
+
"rstrip": false,
|
1315 |
+
"single_word": false,
|
1316 |
+
"special": true
|
1317 |
+
},
|
1318 |
+
"128164": {
|
1319 |
+
"content": "<|reserved_special_token_156|>",
|
1320 |
+
"lstrip": false,
|
1321 |
+
"normalized": false,
|
1322 |
+
"rstrip": false,
|
1323 |
+
"single_word": false,
|
1324 |
+
"special": true
|
1325 |
+
},
|
1326 |
+
"128165": {
|
1327 |
+
"content": "<|reserved_special_token_157|>",
|
1328 |
+
"lstrip": false,
|
1329 |
+
"normalized": false,
|
1330 |
+
"rstrip": false,
|
1331 |
+
"single_word": false,
|
1332 |
+
"special": true
|
1333 |
+
},
|
1334 |
+
"128166": {
|
1335 |
+
"content": "<|reserved_special_token_158|>",
|
1336 |
+
"lstrip": false,
|
1337 |
+
"normalized": false,
|
1338 |
+
"rstrip": false,
|
1339 |
+
"single_word": false,
|
1340 |
+
"special": true
|
1341 |
+
},
|
1342 |
+
"128167": {
|
1343 |
+
"content": "<|reserved_special_token_159|>",
|
1344 |
+
"lstrip": false,
|
1345 |
+
"normalized": false,
|
1346 |
+
"rstrip": false,
|
1347 |
+
"single_word": false,
|
1348 |
+
"special": true
|
1349 |
+
},
|
1350 |
+
"128168": {
|
1351 |
+
"content": "<|reserved_special_token_160|>",
|
1352 |
+
"lstrip": false,
|
1353 |
+
"normalized": false,
|
1354 |
+
"rstrip": false,
|
1355 |
+
"single_word": false,
|
1356 |
+
"special": true
|
1357 |
+
},
|
1358 |
+
"128169": {
|
1359 |
+
"content": "<|reserved_special_token_161|>",
|
1360 |
+
"lstrip": false,
|
1361 |
+
"normalized": false,
|
1362 |
+
"rstrip": false,
|
1363 |
+
"single_word": false,
|
1364 |
+
"special": true
|
1365 |
+
},
|
1366 |
+
"128170": {
|
1367 |
+
"content": "<|reserved_special_token_162|>",
|
1368 |
+
"lstrip": false,
|
1369 |
+
"normalized": false,
|
1370 |
+
"rstrip": false,
|
1371 |
+
"single_word": false,
|
1372 |
+
"special": true
|
1373 |
+
},
|
1374 |
+
"128171": {
|
1375 |
+
"content": "<|reserved_special_token_163|>",
|
1376 |
+
"lstrip": false,
|
1377 |
+
"normalized": false,
|
1378 |
+
"rstrip": false,
|
1379 |
+
"single_word": false,
|
1380 |
+
"special": true
|
1381 |
+
},
|
1382 |
+
"128172": {
|
1383 |
+
"content": "<|reserved_special_token_164|>",
|
1384 |
+
"lstrip": false,
|
1385 |
+
"normalized": false,
|
1386 |
+
"rstrip": false,
|
1387 |
+
"single_word": false,
|
1388 |
+
"special": true
|
1389 |
+
},
|
1390 |
+
"128173": {
|
1391 |
+
"content": "<|reserved_special_token_165|>",
|
1392 |
+
"lstrip": false,
|
1393 |
+
"normalized": false,
|
1394 |
+
"rstrip": false,
|
1395 |
+
"single_word": false,
|
1396 |
+
"special": true
|
1397 |
+
},
|
1398 |
+
"128174": {
|
1399 |
+
"content": "<|reserved_special_token_166|>",
|
1400 |
+
"lstrip": false,
|
1401 |
+
"normalized": false,
|
1402 |
+
"rstrip": false,
|
1403 |
+
"single_word": false,
|
1404 |
+
"special": true
|
1405 |
+
},
|
1406 |
+
"128175": {
|
1407 |
+
"content": "<|reserved_special_token_167|>",
|
1408 |
+
"lstrip": false,
|
1409 |
+
"normalized": false,
|
1410 |
+
"rstrip": false,
|
1411 |
+
"single_word": false,
|
1412 |
+
"special": true
|
1413 |
+
},
|
1414 |
+
"128176": {
|
1415 |
+
"content": "<|reserved_special_token_168|>",
|
1416 |
+
"lstrip": false,
|
1417 |
+
"normalized": false,
|
1418 |
+
"rstrip": false,
|
1419 |
+
"single_word": false,
|
1420 |
+
"special": true
|
1421 |
+
},
|
1422 |
+
"128177": {
|
1423 |
+
"content": "<|reserved_special_token_169|>",
|
1424 |
+
"lstrip": false,
|
1425 |
+
"normalized": false,
|
1426 |
+
"rstrip": false,
|
1427 |
+
"single_word": false,
|
1428 |
+
"special": true
|
1429 |
+
},
|
1430 |
+
"128178": {
|
1431 |
+
"content": "<|reserved_special_token_170|>",
|
1432 |
+
"lstrip": false,
|
1433 |
+
"normalized": false,
|
1434 |
+
"rstrip": false,
|
1435 |
+
"single_word": false,
|
1436 |
+
"special": true
|
1437 |
+
},
|
1438 |
+
"128179": {
|
1439 |
+
"content": "<|reserved_special_token_171|>",
|
1440 |
+
"lstrip": false,
|
1441 |
+
"normalized": false,
|
1442 |
+
"rstrip": false,
|
1443 |
+
"single_word": false,
|
1444 |
+
"special": true
|
1445 |
+
},
|
1446 |
+
"128180": {
|
1447 |
+
"content": "<|reserved_special_token_172|>",
|
1448 |
+
"lstrip": false,
|
1449 |
+
"normalized": false,
|
1450 |
+
"rstrip": false,
|
1451 |
+
"single_word": false,
|
1452 |
+
"special": true
|
1453 |
+
},
|
1454 |
+
"128181": {
|
1455 |
+
"content": "<|reserved_special_token_173|>",
|
1456 |
+
"lstrip": false,
|
1457 |
+
"normalized": false,
|
1458 |
+
"rstrip": false,
|
1459 |
+
"single_word": false,
|
1460 |
+
"special": true
|
1461 |
+
},
|
1462 |
+
"128182": {
|
1463 |
+
"content": "<|reserved_special_token_174|>",
|
1464 |
+
"lstrip": false,
|
1465 |
+
"normalized": false,
|
1466 |
+
"rstrip": false,
|
1467 |
+
"single_word": false,
|
1468 |
+
"special": true
|
1469 |
+
},
|
1470 |
+
"128183": {
|
1471 |
+
"content": "<|reserved_special_token_175|>",
|
1472 |
+
"lstrip": false,
|
1473 |
+
"normalized": false,
|
1474 |
+
"rstrip": false,
|
1475 |
+
"single_word": false,
|
1476 |
+
"special": true
|
1477 |
+
},
|
1478 |
+
"128184": {
|
1479 |
+
"content": "<|reserved_special_token_176|>",
|
1480 |
+
"lstrip": false,
|
1481 |
+
"normalized": false,
|
1482 |
+
"rstrip": false,
|
1483 |
+
"single_word": false,
|
1484 |
+
"special": true
|
1485 |
+
},
|
1486 |
+
"128185": {
|
1487 |
+
"content": "<|reserved_special_token_177|>",
|
1488 |
+
"lstrip": false,
|
1489 |
+
"normalized": false,
|
1490 |
+
"rstrip": false,
|
1491 |
+
"single_word": false,
|
1492 |
+
"special": true
|
1493 |
+
},
|
1494 |
+
"128186": {
|
1495 |
+
"content": "<|reserved_special_token_178|>",
|
1496 |
+
"lstrip": false,
|
1497 |
+
"normalized": false,
|
1498 |
+
"rstrip": false,
|
1499 |
+
"single_word": false,
|
1500 |
+
"special": true
|
1501 |
+
},
|
1502 |
+
"128187": {
|
1503 |
+
"content": "<|reserved_special_token_179|>",
|
1504 |
+
"lstrip": false,
|
1505 |
+
"normalized": false,
|
1506 |
+
"rstrip": false,
|
1507 |
+
"single_word": false,
|
1508 |
+
"special": true
|
1509 |
+
},
|
1510 |
+
"128188": {
|
1511 |
+
"content": "<|reserved_special_token_180|>",
|
1512 |
+
"lstrip": false,
|
1513 |
+
"normalized": false,
|
1514 |
+
"rstrip": false,
|
1515 |
+
"single_word": false,
|
1516 |
+
"special": true
|
1517 |
+
},
|
1518 |
+
"128189": {
|
1519 |
+
"content": "<|reserved_special_token_181|>",
|
1520 |
+
"lstrip": false,
|
1521 |
+
"normalized": false,
|
1522 |
+
"rstrip": false,
|
1523 |
+
"single_word": false,
|
1524 |
+
"special": true
|
1525 |
+
},
|
1526 |
+
"128190": {
|
1527 |
+
"content": "<|reserved_special_token_182|>",
|
1528 |
+
"lstrip": false,
|
1529 |
+
"normalized": false,
|
1530 |
+
"rstrip": false,
|
1531 |
+
"single_word": false,
|
1532 |
+
"special": true
|
1533 |
+
},
|
1534 |
+
"128191": {
|
1535 |
+
"content": "<|reserved_special_token_183|>",
|
1536 |
+
"lstrip": false,
|
1537 |
+
"normalized": false,
|
1538 |
+
"rstrip": false,
|
1539 |
+
"single_word": false,
|
1540 |
+
"special": true
|
1541 |
+
},
|
1542 |
+
"128192": {
|
1543 |
+
"content": "<|reserved_special_token_184|>",
|
1544 |
+
"lstrip": false,
|
1545 |
+
"normalized": false,
|
1546 |
+
"rstrip": false,
|
1547 |
+
"single_word": false,
|
1548 |
+
"special": true
|
1549 |
+
},
|
1550 |
+
"128193": {
|
1551 |
+
"content": "<|reserved_special_token_185|>",
|
1552 |
+
"lstrip": false,
|
1553 |
+
"normalized": false,
|
1554 |
+
"rstrip": false,
|
1555 |
+
"single_word": false,
|
1556 |
+
"special": true
|
1557 |
+
},
|
1558 |
+
"128194": {
|
1559 |
+
"content": "<|reserved_special_token_186|>",
|
1560 |
+
"lstrip": false,
|
1561 |
+
"normalized": false,
|
1562 |
+
"rstrip": false,
|
1563 |
+
"single_word": false,
|
1564 |
+
"special": true
|
1565 |
+
},
|
1566 |
+
"128195": {
|
1567 |
+
"content": "<|reserved_special_token_187|>",
|
1568 |
+
"lstrip": false,
|
1569 |
+
"normalized": false,
|
1570 |
+
"rstrip": false,
|
1571 |
+
"single_word": false,
|
1572 |
+
"special": true
|
1573 |
+
},
|
1574 |
+
"128196": {
|
1575 |
+
"content": "<|reserved_special_token_188|>",
|
1576 |
+
"lstrip": false,
|
1577 |
+
"normalized": false,
|
1578 |
+
"rstrip": false,
|
1579 |
+
"single_word": false,
|
1580 |
+
"special": true
|
1581 |
+
},
|
1582 |
+
"128197": {
|
1583 |
+
"content": "<|reserved_special_token_189|>",
|
1584 |
+
"lstrip": false,
|
1585 |
+
"normalized": false,
|
1586 |
+
"rstrip": false,
|
1587 |
+
"single_word": false,
|
1588 |
+
"special": true
|
1589 |
+
},
|
1590 |
+
"128198": {
|
1591 |
+
"content": "<|reserved_special_token_190|>",
|
1592 |
+
"lstrip": false,
|
1593 |
+
"normalized": false,
|
1594 |
+
"rstrip": false,
|
1595 |
+
"single_word": false,
|
1596 |
+
"special": true
|
1597 |
+
},
|
1598 |
+
"128199": {
|
1599 |
+
"content": "<|reserved_special_token_191|>",
|
1600 |
+
"lstrip": false,
|
1601 |
+
"normalized": false,
|
1602 |
+
"rstrip": false,
|
1603 |
+
"single_word": false,
|
1604 |
+
"special": true
|
1605 |
+
},
|
1606 |
+
"128200": {
|
1607 |
+
"content": "<|reserved_special_token_192|>",
|
1608 |
+
"lstrip": false,
|
1609 |
+
"normalized": false,
|
1610 |
+
"rstrip": false,
|
1611 |
+
"single_word": false,
|
1612 |
+
"special": true
|
1613 |
+
},
|
1614 |
+
"128201": {
|
1615 |
+
"content": "<|reserved_special_token_193|>",
|
1616 |
+
"lstrip": false,
|
1617 |
+
"normalized": false,
|
1618 |
+
"rstrip": false,
|
1619 |
+
"single_word": false,
|
1620 |
+
"special": true
|
1621 |
+
},
|
1622 |
+
"128202": {
|
1623 |
+
"content": "<|reserved_special_token_194|>",
|
1624 |
+
"lstrip": false,
|
1625 |
+
"normalized": false,
|
1626 |
+
"rstrip": false,
|
1627 |
+
"single_word": false,
|
1628 |
+
"special": true
|
1629 |
+
},
|
1630 |
+
"128203": {
|
1631 |
+
"content": "<|reserved_special_token_195|>",
|
1632 |
+
"lstrip": false,
|
1633 |
+
"normalized": false,
|
1634 |
+
"rstrip": false,
|
1635 |
+
"single_word": false,
|
1636 |
+
"special": true
|
1637 |
+
},
|
1638 |
+
"128204": {
|
1639 |
+
"content": "<|reserved_special_token_196|>",
|
1640 |
+
"lstrip": false,
|
1641 |
+
"normalized": false,
|
1642 |
+
"rstrip": false,
|
1643 |
+
"single_word": false,
|
1644 |
+
"special": true
|
1645 |
+
},
|
1646 |
+
"128205": {
|
1647 |
+
"content": "<|reserved_special_token_197|>",
|
1648 |
+
"lstrip": false,
|
1649 |
+
"normalized": false,
|
1650 |
+
"rstrip": false,
|
1651 |
+
"single_word": false,
|
1652 |
+
"special": true
|
1653 |
+
},
|
1654 |
+
"128206": {
|
1655 |
+
"content": "<|reserved_special_token_198|>",
|
1656 |
+
"lstrip": false,
|
1657 |
+
"normalized": false,
|
1658 |
+
"rstrip": false,
|
1659 |
+
"single_word": false,
|
1660 |
+
"special": true
|
1661 |
+
},
|
1662 |
+
"128207": {
|
1663 |
+
"content": "<|reserved_special_token_199|>",
|
1664 |
+
"lstrip": false,
|
1665 |
+
"normalized": false,
|
1666 |
+
"rstrip": false,
|
1667 |
+
"single_word": false,
|
1668 |
+
"special": true
|
1669 |
+
},
|
1670 |
+
"128208": {
|
1671 |
+
"content": "<|reserved_special_token_200|>",
|
1672 |
+
"lstrip": false,
|
1673 |
+
"normalized": false,
|
1674 |
+
"rstrip": false,
|
1675 |
+
"single_word": false,
|
1676 |
+
"special": true
|
1677 |
+
},
|
1678 |
+
"128209": {
|
1679 |
+
"content": "<|reserved_special_token_201|>",
|
1680 |
+
"lstrip": false,
|
1681 |
+
"normalized": false,
|
1682 |
+
"rstrip": false,
|
1683 |
+
"single_word": false,
|
1684 |
+
"special": true
|
1685 |
+
},
|
1686 |
+
"128210": {
|
1687 |
+
"content": "<|reserved_special_token_202|>",
|
1688 |
+
"lstrip": false,
|
1689 |
+
"normalized": false,
|
1690 |
+
"rstrip": false,
|
1691 |
+
"single_word": false,
|
1692 |
+
"special": true
|
1693 |
+
},
|
1694 |
+
"128211": {
|
1695 |
+
"content": "<|reserved_special_token_203|>",
|
1696 |
+
"lstrip": false,
|
1697 |
+
"normalized": false,
|
1698 |
+
"rstrip": false,
|
1699 |
+
"single_word": false,
|
1700 |
+
"special": true
|
1701 |
+
},
|
1702 |
+
"128212": {
|
1703 |
+
"content": "<|reserved_special_token_204|>",
|
1704 |
+
"lstrip": false,
|
1705 |
+
"normalized": false,
|
1706 |
+
"rstrip": false,
|
1707 |
+
"single_word": false,
|
1708 |
+
"special": true
|
1709 |
+
},
|
1710 |
+
"128213": {
|
1711 |
+
"content": "<|reserved_special_token_205|>",
|
1712 |
+
"lstrip": false,
|
1713 |
+
"normalized": false,
|
1714 |
+
"rstrip": false,
|
1715 |
+
"single_word": false,
|
1716 |
+
"special": true
|
1717 |
+
},
|
1718 |
+
"128214": {
|
1719 |
+
"content": "<|reserved_special_token_206|>",
|
1720 |
+
"lstrip": false,
|
1721 |
+
"normalized": false,
|
1722 |
+
"rstrip": false,
|
1723 |
+
"single_word": false,
|
1724 |
+
"special": true
|
1725 |
+
},
|
1726 |
+
"128215": {
|
1727 |
+
"content": "<|reserved_special_token_207|>",
|
1728 |
+
"lstrip": false,
|
1729 |
+
"normalized": false,
|
1730 |
+
"rstrip": false,
|
1731 |
+
"single_word": false,
|
1732 |
+
"special": true
|
1733 |
+
},
|
1734 |
+
"128216": {
|
1735 |
+
"content": "<|reserved_special_token_208|>",
|
1736 |
+
"lstrip": false,
|
1737 |
+
"normalized": false,
|
1738 |
+
"rstrip": false,
|
1739 |
+
"single_word": false,
|
1740 |
+
"special": true
|
1741 |
+
},
|
1742 |
+
"128217": {
|
1743 |
+
"content": "<|reserved_special_token_209|>",
|
1744 |
+
"lstrip": false,
|
1745 |
+
"normalized": false,
|
1746 |
+
"rstrip": false,
|
1747 |
+
"single_word": false,
|
1748 |
+
"special": true
|
1749 |
+
},
|
1750 |
+
"128218": {
|
1751 |
+
"content": "<|reserved_special_token_210|>",
|
1752 |
+
"lstrip": false,
|
1753 |
+
"normalized": false,
|
1754 |
+
"rstrip": false,
|
1755 |
+
"single_word": false,
|
1756 |
+
"special": true
|
1757 |
+
},
|
1758 |
+
"128219": {
|
1759 |
+
"content": "<|reserved_special_token_211|>",
|
1760 |
+
"lstrip": false,
|
1761 |
+
"normalized": false,
|
1762 |
+
"rstrip": false,
|
1763 |
+
"single_word": false,
|
1764 |
+
"special": true
|
1765 |
+
},
|
1766 |
+
"128220": {
|
1767 |
+
"content": "<|reserved_special_token_212|>",
|
1768 |
+
"lstrip": false,
|
1769 |
+
"normalized": false,
|
1770 |
+
"rstrip": false,
|
1771 |
+
"single_word": false,
|
1772 |
+
"special": true
|
1773 |
+
},
|
1774 |
+
"128221": {
|
1775 |
+
"content": "<|reserved_special_token_213|>",
|
1776 |
+
"lstrip": false,
|
1777 |
+
"normalized": false,
|
1778 |
+
"rstrip": false,
|
1779 |
+
"single_word": false,
|
1780 |
+
"special": true
|
1781 |
+
},
|
1782 |
+
"128222": {
|
1783 |
+
"content": "<|reserved_special_token_214|>",
|
1784 |
+
"lstrip": false,
|
1785 |
+
"normalized": false,
|
1786 |
+
"rstrip": false,
|
1787 |
+
"single_word": false,
|
1788 |
+
"special": true
|
1789 |
+
},
|
1790 |
+
"128223": {
|
1791 |
+
"content": "<|reserved_special_token_215|>",
|
1792 |
+
"lstrip": false,
|
1793 |
+
"normalized": false,
|
1794 |
+
"rstrip": false,
|
1795 |
+
"single_word": false,
|
1796 |
+
"special": true
|
1797 |
+
},
|
1798 |
+
"128224": {
|
1799 |
+
"content": "<|reserved_special_token_216|>",
|
1800 |
+
"lstrip": false,
|
1801 |
+
"normalized": false,
|
1802 |
+
"rstrip": false,
|
1803 |
+
"single_word": false,
|
1804 |
+
"special": true
|
1805 |
+
},
|
1806 |
+
"128225": {
|
1807 |
+
"content": "<|reserved_special_token_217|>",
|
1808 |
+
"lstrip": false,
|
1809 |
+
"normalized": false,
|
1810 |
+
"rstrip": false,
|
1811 |
+
"single_word": false,
|
1812 |
+
"special": true
|
1813 |
+
},
|
1814 |
+
"128226": {
|
1815 |
+
"content": "<|reserved_special_token_218|>",
|
1816 |
+
"lstrip": false,
|
1817 |
+
"normalized": false,
|
1818 |
+
"rstrip": false,
|
1819 |
+
"single_word": false,
|
1820 |
+
"special": true
|
1821 |
+
},
|
1822 |
+
"128227": {
|
1823 |
+
"content": "<|reserved_special_token_219|>",
|
1824 |
+
"lstrip": false,
|
1825 |
+
"normalized": false,
|
1826 |
+
"rstrip": false,
|
1827 |
+
"single_word": false,
|
1828 |
+
"special": true
|
1829 |
+
},
|
1830 |
+
"128228": {
|
1831 |
+
"content": "<|reserved_special_token_220|>",
|
1832 |
+
"lstrip": false,
|
1833 |
+
"normalized": false,
|
1834 |
+
"rstrip": false,
|
1835 |
+
"single_word": false,
|
1836 |
+
"special": true
|
1837 |
+
},
|
1838 |
+
"128229": {
|
1839 |
+
"content": "<|reserved_special_token_221|>",
|
1840 |
+
"lstrip": false,
|
1841 |
+
"normalized": false,
|
1842 |
+
"rstrip": false,
|
1843 |
+
"single_word": false,
|
1844 |
+
"special": true
|
1845 |
+
},
|
1846 |
+
"128230": {
|
1847 |
+
"content": "<|reserved_special_token_222|>",
|
1848 |
+
"lstrip": false,
|
1849 |
+
"normalized": false,
|
1850 |
+
"rstrip": false,
|
1851 |
+
"single_word": false,
|
1852 |
+
"special": true
|
1853 |
+
},
|
1854 |
+
"128231": {
|
1855 |
+
"content": "<|reserved_special_token_223|>",
|
1856 |
+
"lstrip": false,
|
1857 |
+
"normalized": false,
|
1858 |
+
"rstrip": false,
|
1859 |
+
"single_word": false,
|
1860 |
+
"special": true
|
1861 |
+
},
|
1862 |
+
"128232": {
|
1863 |
+
"content": "<|reserved_special_token_224|>",
|
1864 |
+
"lstrip": false,
|
1865 |
+
"normalized": false,
|
1866 |
+
"rstrip": false,
|
1867 |
+
"single_word": false,
|
1868 |
+
"special": true
|
1869 |
+
},
|
1870 |
+
"128233": {
|
1871 |
+
"content": "<|reserved_special_token_225|>",
|
1872 |
+
"lstrip": false,
|
1873 |
+
"normalized": false,
|
1874 |
+
"rstrip": false,
|
1875 |
+
"single_word": false,
|
1876 |
+
"special": true
|
1877 |
+
},
|
1878 |
+
"128234": {
|
1879 |
+
"content": "<|reserved_special_token_226|>",
|
1880 |
+
"lstrip": false,
|
1881 |
+
"normalized": false,
|
1882 |
+
"rstrip": false,
|
1883 |
+
"single_word": false,
|
1884 |
+
"special": true
|
1885 |
+
},
|
1886 |
+
"128235": {
|
1887 |
+
"content": "<|reserved_special_token_227|>",
|
1888 |
+
"lstrip": false,
|
1889 |
+
"normalized": false,
|
1890 |
+
"rstrip": false,
|
1891 |
+
"single_word": false,
|
1892 |
+
"special": true
|
1893 |
+
},
|
1894 |
+
"128236": {
|
1895 |
+
"content": "<|reserved_special_token_228|>",
|
1896 |
+
"lstrip": false,
|
1897 |
+
"normalized": false,
|
1898 |
+
"rstrip": false,
|
1899 |
+
"single_word": false,
|
1900 |
+
"special": true
|
1901 |
+
},
|
1902 |
+
"128237": {
|
1903 |
+
"content": "<|reserved_special_token_229|>",
|
1904 |
+
"lstrip": false,
|
1905 |
+
"normalized": false,
|
1906 |
+
"rstrip": false,
|
1907 |
+
"single_word": false,
|
1908 |
+
"special": true
|
1909 |
+
},
|
1910 |
+
"128238": {
|
1911 |
+
"content": "<|reserved_special_token_230|>",
|
1912 |
+
"lstrip": false,
|
1913 |
+
"normalized": false,
|
1914 |
+
"rstrip": false,
|
1915 |
+
"single_word": false,
|
1916 |
+
"special": true
|
1917 |
+
},
|
1918 |
+
"128239": {
|
1919 |
+
"content": "<|reserved_special_token_231|>",
|
1920 |
+
"lstrip": false,
|
1921 |
+
"normalized": false,
|
1922 |
+
"rstrip": false,
|
1923 |
+
"single_word": false,
|
1924 |
+
"special": true
|
1925 |
+
},
|
1926 |
+
"128240": {
|
1927 |
+
"content": "<|reserved_special_token_232|>",
|
1928 |
+
"lstrip": false,
|
1929 |
+
"normalized": false,
|
1930 |
+
"rstrip": false,
|
1931 |
+
"single_word": false,
|
1932 |
+
"special": true
|
1933 |
+
},
|
1934 |
+
"128241": {
|
1935 |
+
"content": "<|reserved_special_token_233|>",
|
1936 |
+
"lstrip": false,
|
1937 |
+
"normalized": false,
|
1938 |
+
"rstrip": false,
|
1939 |
+
"single_word": false,
|
1940 |
+
"special": true
|
1941 |
+
},
|
1942 |
+
"128242": {
|
1943 |
+
"content": "<|reserved_special_token_234|>",
|
1944 |
+
"lstrip": false,
|
1945 |
+
"normalized": false,
|
1946 |
+
"rstrip": false,
|
1947 |
+
"single_word": false,
|
1948 |
+
"special": true
|
1949 |
+
},
|
1950 |
+
"128243": {
|
1951 |
+
"content": "<|reserved_special_token_235|>",
|
1952 |
+
"lstrip": false,
|
1953 |
+
"normalized": false,
|
1954 |
+
"rstrip": false,
|
1955 |
+
"single_word": false,
|
1956 |
+
"special": true
|
1957 |
+
},
|
1958 |
+
"128244": {
|
1959 |
+
"content": "<|reserved_special_token_236|>",
|
1960 |
+
"lstrip": false,
|
1961 |
+
"normalized": false,
|
1962 |
+
"rstrip": false,
|
1963 |
+
"single_word": false,
|
1964 |
+
"special": true
|
1965 |
+
},
|
1966 |
+
"128245": {
|
1967 |
+
"content": "<|reserved_special_token_237|>",
|
1968 |
+
"lstrip": false,
|
1969 |
+
"normalized": false,
|
1970 |
+
"rstrip": false,
|
1971 |
+
"single_word": false,
|
1972 |
+
"special": true
|
1973 |
+
},
|
1974 |
+
"128246": {
|
1975 |
+
"content": "<|reserved_special_token_238|>",
|
1976 |
+
"lstrip": false,
|
1977 |
+
"normalized": false,
|
1978 |
+
"rstrip": false,
|
1979 |
+
"single_word": false,
|
1980 |
+
"special": true
|
1981 |
+
},
|
1982 |
+
"128247": {
|
1983 |
+
"content": "<|reserved_special_token_239|>",
|
1984 |
+
"lstrip": false,
|
1985 |
+
"normalized": false,
|
1986 |
+
"rstrip": false,
|
1987 |
+
"single_word": false,
|
1988 |
+
"special": true
|
1989 |
+
},
|
1990 |
+
"128248": {
|
1991 |
+
"content": "<|reserved_special_token_240|>",
|
1992 |
+
"lstrip": false,
|
1993 |
+
"normalized": false,
|
1994 |
+
"rstrip": false,
|
1995 |
+
"single_word": false,
|
1996 |
+
"special": true
|
1997 |
+
},
|
1998 |
+
"128249": {
|
1999 |
+
"content": "<|reserved_special_token_241|>",
|
2000 |
+
"lstrip": false,
|
2001 |
+
"normalized": false,
|
2002 |
+
"rstrip": false,
|
2003 |
+
"single_word": false,
|
2004 |
+
"special": true
|
2005 |
+
},
|
2006 |
+
"128250": {
|
2007 |
+
"content": "<|reserved_special_token_242|>",
|
2008 |
+
"lstrip": false,
|
2009 |
+
"normalized": false,
|
2010 |
+
"rstrip": false,
|
2011 |
+
"single_word": false,
|
2012 |
+
"special": true
|
2013 |
+
},
|
2014 |
+
"128251": {
|
2015 |
+
"content": "<|reserved_special_token_243|>",
|
2016 |
+
"lstrip": false,
|
2017 |
+
"normalized": false,
|
2018 |
+
"rstrip": false,
|
2019 |
+
"single_word": false,
|
2020 |
+
"special": true
|
2021 |
+
},
|
2022 |
+
"128252": {
|
2023 |
+
"content": "<|reserved_special_token_244|>",
|
2024 |
+
"lstrip": false,
|
2025 |
+
"normalized": false,
|
2026 |
+
"rstrip": false,
|
2027 |
+
"single_word": false,
|
2028 |
+
"special": true
|
2029 |
+
},
|
2030 |
+
"128253": {
|
2031 |
+
"content": "<|reserved_special_token_245|>",
|
2032 |
+
"lstrip": false,
|
2033 |
+
"normalized": false,
|
2034 |
+
"rstrip": false,
|
2035 |
+
"single_word": false,
|
2036 |
+
"special": true
|
2037 |
+
},
|
2038 |
+
"128254": {
|
2039 |
+
"content": "<|reserved_special_token_246|>",
|
2040 |
+
"lstrip": false,
|
2041 |
+
"normalized": false,
|
2042 |
+
"rstrip": false,
|
2043 |
+
"single_word": false,
|
2044 |
+
"special": true
|
2045 |
+
},
|
2046 |
+
"128255": {
|
2047 |
+
"content": "<|reserved_special_token_247|>",
|
2048 |
+
"lstrip": false,
|
2049 |
+
"normalized": false,
|
2050 |
+
"rstrip": false,
|
2051 |
+
"single_word": false,
|
2052 |
+
"special": true
|
2053 |
+
}
|
2054 |
+
},
|
2055 |
+
"bos_token": "<|begin▁of▁sentence|>",
|
2056 |
+
"chat_template": "{{ bos_token }}{{ 'Below are some instructions that describe some tasks. Write responses in Arabic language only that appropriately complete each request.' }}{% for message in messages %}{% if message['role'] == 'user' %}{{ '\n\n### Instruction:\n' + message['content'] }}{% elif message['role'] == 'assistant' %}{{ '\n\n### Response:\n' + message['content'] + '<|end▁of▁sentence|>' }}{% else %}{{ raise_exception('Only user and assistant roles are supported!') }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '\n\n### Response:\n' }}{% endif %}",
|
2057 |
+
"clean_up_tokenization_spaces": false,
|
2058 |
+
"eos_token": "<|end▁of▁sentence|>",
|
2059 |
+
"extra_special_tokens": {},
|
2060 |
+
"legacy": true,
|
2061 |
+
"model_max_length": 131072,
|
2062 |
+
"pad_token": "<|finetune_right_pad_id|>",
|
2063 |
+
"padding_side": "right",
|
2064 |
+
"sp_model_kwargs": {},
|
2065 |
+
"tokenizer_class": "LlamaTokenizer",
|
2066 |
+
"unk_token": null,
|
2067 |
+
"use_default_system_prompt": false
|
2068 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,2049 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 1.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 288,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.003472222222222222,
|
13 |
+
"grad_norm": 0.6381791234016418,
|
14 |
+
"learning_rate": 4e-05,
|
15 |
+
"loss": 1.664,
|
16 |
+
"step": 1
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.006944444444444444,
|
20 |
+
"grad_norm": 0.6412252187728882,
|
21 |
+
"learning_rate": 8e-05,
|
22 |
+
"loss": 1.6095,
|
23 |
+
"step": 2
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.010416666666666666,
|
27 |
+
"grad_norm": 0.6355312466621399,
|
28 |
+
"learning_rate": 0.00012,
|
29 |
+
"loss": 1.6431,
|
30 |
+
"step": 3
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 0.013888888888888888,
|
34 |
+
"grad_norm": 0.7827576994895935,
|
35 |
+
"learning_rate": 0.00016,
|
36 |
+
"loss": 1.7554,
|
37 |
+
"step": 4
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 0.017361111111111112,
|
41 |
+
"grad_norm": 0.7365180850028992,
|
42 |
+
"learning_rate": 0.0002,
|
43 |
+
"loss": 1.6866,
|
44 |
+
"step": 5
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.020833333333333332,
|
48 |
+
"grad_norm": 0.7607629299163818,
|
49 |
+
"learning_rate": 0.00019929328621908128,
|
50 |
+
"loss": 1.5447,
|
51 |
+
"step": 6
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.024305555555555556,
|
55 |
+
"grad_norm": 0.7718775272369385,
|
56 |
+
"learning_rate": 0.00019858657243816254,
|
57 |
+
"loss": 1.5777,
|
58 |
+
"step": 7
|
59 |
+
},
|
60 |
+
{
|
61 |
+
"epoch": 0.027777777777777776,
|
62 |
+
"grad_norm": 0.7301136255264282,
|
63 |
+
"learning_rate": 0.00019787985865724384,
|
64 |
+
"loss": 1.3402,
|
65 |
+
"step": 8
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 0.03125,
|
69 |
+
"grad_norm": 0.6953989863395691,
|
70 |
+
"learning_rate": 0.0001971731448763251,
|
71 |
+
"loss": 1.4443,
|
72 |
+
"step": 9
|
73 |
+
},
|
74 |
+
{
|
75 |
+
"epoch": 0.034722222222222224,
|
76 |
+
"grad_norm": 0.605755090713501,
|
77 |
+
"learning_rate": 0.00019646643109540637,
|
78 |
+
"loss": 1.3609,
|
79 |
+
"step": 10
|
80 |
+
},
|
81 |
+
{
|
82 |
+
"epoch": 0.03819444444444445,
|
83 |
+
"grad_norm": 0.5867183804512024,
|
84 |
+
"learning_rate": 0.00019575971731448764,
|
85 |
+
"loss": 1.2765,
|
86 |
+
"step": 11
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 0.041666666666666664,
|
90 |
+
"grad_norm": 0.5973581075668335,
|
91 |
+
"learning_rate": 0.00019505300353356894,
|
92 |
+
"loss": 1.2585,
|
93 |
+
"step": 12
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 0.04513888888888889,
|
97 |
+
"grad_norm": 0.7357228398323059,
|
98 |
+
"learning_rate": 0.0001943462897526502,
|
99 |
+
"loss": 1.2199,
|
100 |
+
"step": 13
|
101 |
+
},
|
102 |
+
{
|
103 |
+
"epoch": 0.04861111111111111,
|
104 |
+
"grad_norm": 0.7804207801818848,
|
105 |
+
"learning_rate": 0.00019363957597173144,
|
106 |
+
"loss": 1.1996,
|
107 |
+
"step": 14
|
108 |
+
},
|
109 |
+
{
|
110 |
+
"epoch": 0.052083333333333336,
|
111 |
+
"grad_norm": 0.813244640827179,
|
112 |
+
"learning_rate": 0.0001929328621908127,
|
113 |
+
"loss": 1.1735,
|
114 |
+
"step": 15
|
115 |
+
},
|
116 |
+
{
|
117 |
+
"epoch": 0.05555555555555555,
|
118 |
+
"grad_norm": 0.7277530431747437,
|
119 |
+
"learning_rate": 0.00019222614840989398,
|
120 |
+
"loss": 1.1094,
|
121 |
+
"step": 16
|
122 |
+
},
|
123 |
+
{
|
124 |
+
"epoch": 0.059027777777777776,
|
125 |
+
"grad_norm": 0.6414357423782349,
|
126 |
+
"learning_rate": 0.00019151943462897527,
|
127 |
+
"loss": 1.1786,
|
128 |
+
"step": 17
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 0.0625,
|
132 |
+
"grad_norm": 0.5542577505111694,
|
133 |
+
"learning_rate": 0.00019081272084805654,
|
134 |
+
"loss": 0.9343,
|
135 |
+
"step": 18
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 0.06597222222222222,
|
139 |
+
"grad_norm": 0.5263577699661255,
|
140 |
+
"learning_rate": 0.0001901060070671378,
|
141 |
+
"loss": 1.0607,
|
142 |
+
"step": 19
|
143 |
+
},
|
144 |
+
{
|
145 |
+
"epoch": 0.06944444444444445,
|
146 |
+
"grad_norm": 0.49260228872299194,
|
147 |
+
"learning_rate": 0.00018939929328621908,
|
148 |
+
"loss": 0.9934,
|
149 |
+
"step": 20
|
150 |
+
},
|
151 |
+
{
|
152 |
+
"epoch": 0.07291666666666667,
|
153 |
+
"grad_norm": 0.5072307586669922,
|
154 |
+
"learning_rate": 0.00018869257950530037,
|
155 |
+
"loss": 1.0165,
|
156 |
+
"step": 21
|
157 |
+
},
|
158 |
+
{
|
159 |
+
"epoch": 0.0763888888888889,
|
160 |
+
"grad_norm": 0.5154305696487427,
|
161 |
+
"learning_rate": 0.00018798586572438164,
|
162 |
+
"loss": 1.0159,
|
163 |
+
"step": 22
|
164 |
+
},
|
165 |
+
{
|
166 |
+
"epoch": 0.0798611111111111,
|
167 |
+
"grad_norm": 0.5033209919929504,
|
168 |
+
"learning_rate": 0.0001872791519434629,
|
169 |
+
"loss": 1.0102,
|
170 |
+
"step": 23
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 0.08333333333333333,
|
174 |
+
"grad_norm": 0.5032006502151489,
|
175 |
+
"learning_rate": 0.00018657243816254417,
|
176 |
+
"loss": 1.0215,
|
177 |
+
"step": 24
|
178 |
+
},
|
179 |
+
{
|
180 |
+
"epoch": 0.08680555555555555,
|
181 |
+
"grad_norm": 0.4746347665786743,
|
182 |
+
"learning_rate": 0.00018586572438162547,
|
183 |
+
"loss": 0.867,
|
184 |
+
"step": 25
|
185 |
+
},
|
186 |
+
{
|
187 |
+
"epoch": 0.09027777777777778,
|
188 |
+
"grad_norm": 0.4780479967594147,
|
189 |
+
"learning_rate": 0.00018515901060070673,
|
190 |
+
"loss": 0.951,
|
191 |
+
"step": 26
|
192 |
+
},
|
193 |
+
{
|
194 |
+
"epoch": 0.09375,
|
195 |
+
"grad_norm": 0.45668691396713257,
|
196 |
+
"learning_rate": 0.000184452296819788,
|
197 |
+
"loss": 0.9464,
|
198 |
+
"step": 27
|
199 |
+
},
|
200 |
+
{
|
201 |
+
"epoch": 0.09722222222222222,
|
202 |
+
"grad_norm": 0.43334755301475525,
|
203 |
+
"learning_rate": 0.00018374558303886927,
|
204 |
+
"loss": 0.8768,
|
205 |
+
"step": 28
|
206 |
+
},
|
207 |
+
{
|
208 |
+
"epoch": 0.10069444444444445,
|
209 |
+
"grad_norm": 0.4458893835544586,
|
210 |
+
"learning_rate": 0.00018303886925795054,
|
211 |
+
"loss": 0.8553,
|
212 |
+
"step": 29
|
213 |
+
},
|
214 |
+
{
|
215 |
+
"epoch": 0.10416666666666667,
|
216 |
+
"grad_norm": 0.4605867564678192,
|
217 |
+
"learning_rate": 0.00018233215547703183,
|
218 |
+
"loss": 0.948,
|
219 |
+
"step": 30
|
220 |
+
},
|
221 |
+
{
|
222 |
+
"epoch": 0.1076388888888889,
|
223 |
+
"grad_norm": 0.44694918394088745,
|
224 |
+
"learning_rate": 0.0001816254416961131,
|
225 |
+
"loss": 0.8755,
|
226 |
+
"step": 31
|
227 |
+
},
|
228 |
+
{
|
229 |
+
"epoch": 0.1111111111111111,
|
230 |
+
"grad_norm": 0.45669859647750854,
|
231 |
+
"learning_rate": 0.00018091872791519434,
|
232 |
+
"loss": 0.8554,
|
233 |
+
"step": 32
|
234 |
+
},
|
235 |
+
{
|
236 |
+
"epoch": 0.11458333333333333,
|
237 |
+
"grad_norm": 0.4380110502243042,
|
238 |
+
"learning_rate": 0.0001802120141342756,
|
239 |
+
"loss": 0.8699,
|
240 |
+
"step": 33
|
241 |
+
},
|
242 |
+
{
|
243 |
+
"epoch": 0.11805555555555555,
|
244 |
+
"grad_norm": 0.4494687020778656,
|
245 |
+
"learning_rate": 0.0001795053003533569,
|
246 |
+
"loss": 0.8463,
|
247 |
+
"step": 34
|
248 |
+
},
|
249 |
+
{
|
250 |
+
"epoch": 0.12152777777777778,
|
251 |
+
"grad_norm": 0.4385037422180176,
|
252 |
+
"learning_rate": 0.00017879858657243817,
|
253 |
+
"loss": 0.7964,
|
254 |
+
"step": 35
|
255 |
+
},
|
256 |
+
{
|
257 |
+
"epoch": 0.125,
|
258 |
+
"grad_norm": 0.42709654569625854,
|
259 |
+
"learning_rate": 0.00017809187279151944,
|
260 |
+
"loss": 0.8675,
|
261 |
+
"step": 36
|
262 |
+
},
|
263 |
+
{
|
264 |
+
"epoch": 0.1284722222222222,
|
265 |
+
"grad_norm": 0.462563157081604,
|
266 |
+
"learning_rate": 0.0001773851590106007,
|
267 |
+
"loss": 0.9125,
|
268 |
+
"step": 37
|
269 |
+
},
|
270 |
+
{
|
271 |
+
"epoch": 0.13194444444444445,
|
272 |
+
"grad_norm": 0.4372367560863495,
|
273 |
+
"learning_rate": 0.00017667844522968197,
|
274 |
+
"loss": 0.8352,
|
275 |
+
"step": 38
|
276 |
+
},
|
277 |
+
{
|
278 |
+
"epoch": 0.13541666666666666,
|
279 |
+
"grad_norm": 0.4251866340637207,
|
280 |
+
"learning_rate": 0.00017597173144876327,
|
281 |
+
"loss": 0.8695,
|
282 |
+
"step": 39
|
283 |
+
},
|
284 |
+
{
|
285 |
+
"epoch": 0.1388888888888889,
|
286 |
+
"grad_norm": 0.43755847215652466,
|
287 |
+
"learning_rate": 0.00017526501766784453,
|
288 |
+
"loss": 0.8544,
|
289 |
+
"step": 40
|
290 |
+
},
|
291 |
+
{
|
292 |
+
"epoch": 0.1423611111111111,
|
293 |
+
"grad_norm": 0.44858112931251526,
|
294 |
+
"learning_rate": 0.0001745583038869258,
|
295 |
+
"loss": 0.835,
|
296 |
+
"step": 41
|
297 |
+
},
|
298 |
+
{
|
299 |
+
"epoch": 0.14583333333333334,
|
300 |
+
"grad_norm": 0.4447510838508606,
|
301 |
+
"learning_rate": 0.00017385159010600707,
|
302 |
+
"loss": 0.8537,
|
303 |
+
"step": 42
|
304 |
+
},
|
305 |
+
{
|
306 |
+
"epoch": 0.14930555555555555,
|
307 |
+
"grad_norm": 0.42954930663108826,
|
308 |
+
"learning_rate": 0.00017314487632508836,
|
309 |
+
"loss": 0.7603,
|
310 |
+
"step": 43
|
311 |
+
},
|
312 |
+
{
|
313 |
+
"epoch": 0.1527777777777778,
|
314 |
+
"grad_norm": 0.4357329308986664,
|
315 |
+
"learning_rate": 0.00017243816254416963,
|
316 |
+
"loss": 0.7315,
|
317 |
+
"step": 44
|
318 |
+
},
|
319 |
+
{
|
320 |
+
"epoch": 0.15625,
|
321 |
+
"grad_norm": 0.4562698304653168,
|
322 |
+
"learning_rate": 0.0001717314487632509,
|
323 |
+
"loss": 0.9103,
|
324 |
+
"step": 45
|
325 |
+
},
|
326 |
+
{
|
327 |
+
"epoch": 0.1597222222222222,
|
328 |
+
"grad_norm": 0.46614545583724976,
|
329 |
+
"learning_rate": 0.00017102473498233216,
|
330 |
+
"loss": 0.832,
|
331 |
+
"step": 46
|
332 |
+
},
|
333 |
+
{
|
334 |
+
"epoch": 0.16319444444444445,
|
335 |
+
"grad_norm": 0.42011672258377075,
|
336 |
+
"learning_rate": 0.00017031802120141343,
|
337 |
+
"loss": 0.7172,
|
338 |
+
"step": 47
|
339 |
+
},
|
340 |
+
{
|
341 |
+
"epoch": 0.16666666666666666,
|
342 |
+
"grad_norm": 0.40585461258888245,
|
343 |
+
"learning_rate": 0.00016961130742049473,
|
344 |
+
"loss": 0.7087,
|
345 |
+
"step": 48
|
346 |
+
},
|
347 |
+
{
|
348 |
+
"epoch": 0.1701388888888889,
|
349 |
+
"grad_norm": 0.4490915834903717,
|
350 |
+
"learning_rate": 0.000168904593639576,
|
351 |
+
"loss": 0.7956,
|
352 |
+
"step": 49
|
353 |
+
},
|
354 |
+
{
|
355 |
+
"epoch": 0.1736111111111111,
|
356 |
+
"grad_norm": 0.4251860976219177,
|
357 |
+
"learning_rate": 0.00016819787985865723,
|
358 |
+
"loss": 0.7763,
|
359 |
+
"step": 50
|
360 |
+
},
|
361 |
+
{
|
362 |
+
"epoch": 0.17708333333333334,
|
363 |
+
"grad_norm": 0.4503968060016632,
|
364 |
+
"learning_rate": 0.0001674911660777385,
|
365 |
+
"loss": 0.833,
|
366 |
+
"step": 51
|
367 |
+
},
|
368 |
+
{
|
369 |
+
"epoch": 0.18055555555555555,
|
370 |
+
"grad_norm": 0.452923059463501,
|
371 |
+
"learning_rate": 0.0001667844522968198,
|
372 |
+
"loss": 0.729,
|
373 |
+
"step": 52
|
374 |
+
},
|
375 |
+
{
|
376 |
+
"epoch": 0.1840277777777778,
|
377 |
+
"grad_norm": 0.45421820878982544,
|
378 |
+
"learning_rate": 0.00016607773851590106,
|
379 |
+
"loss": 0.8678,
|
380 |
+
"step": 53
|
381 |
+
},
|
382 |
+
{
|
383 |
+
"epoch": 0.1875,
|
384 |
+
"grad_norm": 0.47255003452301025,
|
385 |
+
"learning_rate": 0.00016537102473498233,
|
386 |
+
"loss": 0.7856,
|
387 |
+
"step": 54
|
388 |
+
},
|
389 |
+
{
|
390 |
+
"epoch": 0.1909722222222222,
|
391 |
+
"grad_norm": 0.49460238218307495,
|
392 |
+
"learning_rate": 0.0001646643109540636,
|
393 |
+
"loss": 0.8103,
|
394 |
+
"step": 55
|
395 |
+
},
|
396 |
+
{
|
397 |
+
"epoch": 0.19444444444444445,
|
398 |
+
"grad_norm": 0.47668716311454773,
|
399 |
+
"learning_rate": 0.0001639575971731449,
|
400 |
+
"loss": 0.6687,
|
401 |
+
"step": 56
|
402 |
+
},
|
403 |
+
{
|
404 |
+
"epoch": 0.19791666666666666,
|
405 |
+
"grad_norm": 0.4631917178630829,
|
406 |
+
"learning_rate": 0.00016325088339222616,
|
407 |
+
"loss": 0.7362,
|
408 |
+
"step": 57
|
409 |
+
},
|
410 |
+
{
|
411 |
+
"epoch": 0.2013888888888889,
|
412 |
+
"grad_norm": 0.4908764064311981,
|
413 |
+
"learning_rate": 0.00016254416961130743,
|
414 |
+
"loss": 0.7734,
|
415 |
+
"step": 58
|
416 |
+
},
|
417 |
+
{
|
418 |
+
"epoch": 0.2048611111111111,
|
419 |
+
"grad_norm": 0.47517484426498413,
|
420 |
+
"learning_rate": 0.0001618374558303887,
|
421 |
+
"loss": 0.8048,
|
422 |
+
"step": 59
|
423 |
+
},
|
424 |
+
{
|
425 |
+
"epoch": 0.20833333333333334,
|
426 |
+
"grad_norm": 0.4693131744861603,
|
427 |
+
"learning_rate": 0.00016113074204946996,
|
428 |
+
"loss": 0.8148,
|
429 |
+
"step": 60
|
430 |
+
},
|
431 |
+
{
|
432 |
+
"epoch": 0.21180555555555555,
|
433 |
+
"grad_norm": 0.48101750016212463,
|
434 |
+
"learning_rate": 0.00016042402826855126,
|
435 |
+
"loss": 0.7089,
|
436 |
+
"step": 61
|
437 |
+
},
|
438 |
+
{
|
439 |
+
"epoch": 0.2152777777777778,
|
440 |
+
"grad_norm": 0.45942020416259766,
|
441 |
+
"learning_rate": 0.00015971731448763253,
|
442 |
+
"loss": 0.7649,
|
443 |
+
"step": 62
|
444 |
+
},
|
445 |
+
{
|
446 |
+
"epoch": 0.21875,
|
447 |
+
"grad_norm": 0.46566373109817505,
|
448 |
+
"learning_rate": 0.0001590106007067138,
|
449 |
+
"loss": 0.7081,
|
450 |
+
"step": 63
|
451 |
+
},
|
452 |
+
{
|
453 |
+
"epoch": 0.2222222222222222,
|
454 |
+
"grad_norm": 0.4782656133174896,
|
455 |
+
"learning_rate": 0.00015830388692579506,
|
456 |
+
"loss": 0.6578,
|
457 |
+
"step": 64
|
458 |
+
},
|
459 |
+
{
|
460 |
+
"epoch": 0.22569444444444445,
|
461 |
+
"grad_norm": 0.4600412845611572,
|
462 |
+
"learning_rate": 0.00015759717314487635,
|
463 |
+
"loss": 0.6907,
|
464 |
+
"step": 65
|
465 |
+
},
|
466 |
+
{
|
467 |
+
"epoch": 0.22916666666666666,
|
468 |
+
"grad_norm": 0.47648143768310547,
|
469 |
+
"learning_rate": 0.00015689045936395762,
|
470 |
+
"loss": 0.7159,
|
471 |
+
"step": 66
|
472 |
+
},
|
473 |
+
{
|
474 |
+
"epoch": 0.2326388888888889,
|
475 |
+
"grad_norm": 0.4845995008945465,
|
476 |
+
"learning_rate": 0.00015618374558303886,
|
477 |
+
"loss": 0.6186,
|
478 |
+
"step": 67
|
479 |
+
},
|
480 |
+
{
|
481 |
+
"epoch": 0.2361111111111111,
|
482 |
+
"grad_norm": 0.5142258405685425,
|
483 |
+
"learning_rate": 0.00015547703180212013,
|
484 |
+
"loss": 0.7643,
|
485 |
+
"step": 68
|
486 |
+
},
|
487 |
+
{
|
488 |
+
"epoch": 0.23958333333333334,
|
489 |
+
"grad_norm": 0.5000512599945068,
|
490 |
+
"learning_rate": 0.0001547703180212014,
|
491 |
+
"loss": 0.734,
|
492 |
+
"step": 69
|
493 |
+
},
|
494 |
+
{
|
495 |
+
"epoch": 0.24305555555555555,
|
496 |
+
"grad_norm": 0.473004549741745,
|
497 |
+
"learning_rate": 0.0001540636042402827,
|
498 |
+
"loss": 0.689,
|
499 |
+
"step": 70
|
500 |
+
},
|
501 |
+
{
|
502 |
+
"epoch": 0.2465277777777778,
|
503 |
+
"grad_norm": 0.49982285499572754,
|
504 |
+
"learning_rate": 0.00015335689045936396,
|
505 |
+
"loss": 0.7162,
|
506 |
+
"step": 71
|
507 |
+
},
|
508 |
+
{
|
509 |
+
"epoch": 0.25,
|
510 |
+
"grad_norm": 0.48723116517066956,
|
511 |
+
"learning_rate": 0.00015265017667844523,
|
512 |
+
"loss": 0.605,
|
513 |
+
"step": 72
|
514 |
+
},
|
515 |
+
{
|
516 |
+
"epoch": 0.2534722222222222,
|
517 |
+
"grad_norm": 0.4668457508087158,
|
518 |
+
"learning_rate": 0.0001519434628975265,
|
519 |
+
"loss": 0.7956,
|
520 |
+
"step": 73
|
521 |
+
},
|
522 |
+
{
|
523 |
+
"epoch": 0.2569444444444444,
|
524 |
+
"grad_norm": 0.5139826536178589,
|
525 |
+
"learning_rate": 0.0001512367491166078,
|
526 |
+
"loss": 0.6877,
|
527 |
+
"step": 74
|
528 |
+
},
|
529 |
+
{
|
530 |
+
"epoch": 0.2604166666666667,
|
531 |
+
"grad_norm": 0.48903441429138184,
|
532 |
+
"learning_rate": 0.00015053003533568906,
|
533 |
+
"loss": 0.7341,
|
534 |
+
"step": 75
|
535 |
+
},
|
536 |
+
{
|
537 |
+
"epoch": 0.2638888888888889,
|
538 |
+
"grad_norm": 0.4892962872982025,
|
539 |
+
"learning_rate": 0.00014982332155477032,
|
540 |
+
"loss": 0.6833,
|
541 |
+
"step": 76
|
542 |
+
},
|
543 |
+
{
|
544 |
+
"epoch": 0.2673611111111111,
|
545 |
+
"grad_norm": 0.510981023311615,
|
546 |
+
"learning_rate": 0.0001491166077738516,
|
547 |
+
"loss": 0.6567,
|
548 |
+
"step": 77
|
549 |
+
},
|
550 |
+
{
|
551 |
+
"epoch": 0.2708333333333333,
|
552 |
+
"grad_norm": 0.48602378368377686,
|
553 |
+
"learning_rate": 0.00014840989399293289,
|
554 |
+
"loss": 0.6592,
|
555 |
+
"step": 78
|
556 |
+
},
|
557 |
+
{
|
558 |
+
"epoch": 0.2743055555555556,
|
559 |
+
"grad_norm": 0.5149515271186829,
|
560 |
+
"learning_rate": 0.00014770318021201415,
|
561 |
+
"loss": 0.7435,
|
562 |
+
"step": 79
|
563 |
+
},
|
564 |
+
{
|
565 |
+
"epoch": 0.2777777777777778,
|
566 |
+
"grad_norm": 0.4999159872531891,
|
567 |
+
"learning_rate": 0.00014699646643109542,
|
568 |
+
"loss": 0.7397,
|
569 |
+
"step": 80
|
570 |
+
},
|
571 |
+
{
|
572 |
+
"epoch": 0.28125,
|
573 |
+
"grad_norm": 0.5036943554878235,
|
574 |
+
"learning_rate": 0.0001462897526501767,
|
575 |
+
"loss": 0.6791,
|
576 |
+
"step": 81
|
577 |
+
},
|
578 |
+
{
|
579 |
+
"epoch": 0.2847222222222222,
|
580 |
+
"grad_norm": 0.4811699688434601,
|
581 |
+
"learning_rate": 0.00014558303886925796,
|
582 |
+
"loss": 0.6376,
|
583 |
+
"step": 82
|
584 |
+
},
|
585 |
+
{
|
586 |
+
"epoch": 0.2881944444444444,
|
587 |
+
"grad_norm": 0.5215135812759399,
|
588 |
+
"learning_rate": 0.00014487632508833925,
|
589 |
+
"loss": 0.6547,
|
590 |
+
"step": 83
|
591 |
+
},
|
592 |
+
{
|
593 |
+
"epoch": 0.2916666666666667,
|
594 |
+
"grad_norm": 0.5180763006210327,
|
595 |
+
"learning_rate": 0.00014416961130742052,
|
596 |
+
"loss": 0.6667,
|
597 |
+
"step": 84
|
598 |
+
},
|
599 |
+
{
|
600 |
+
"epoch": 0.2951388888888889,
|
601 |
+
"grad_norm": 0.5010943412780762,
|
602 |
+
"learning_rate": 0.00014346289752650176,
|
603 |
+
"loss": 0.6496,
|
604 |
+
"step": 85
|
605 |
+
},
|
606 |
+
{
|
607 |
+
"epoch": 0.2986111111111111,
|
608 |
+
"grad_norm": 0.47832784056663513,
|
609 |
+
"learning_rate": 0.00014275618374558303,
|
610 |
+
"loss": 0.6516,
|
611 |
+
"step": 86
|
612 |
+
},
|
613 |
+
{
|
614 |
+
"epoch": 0.3020833333333333,
|
615 |
+
"grad_norm": 0.5183102488517761,
|
616 |
+
"learning_rate": 0.00014204946996466432,
|
617 |
+
"loss": 0.6822,
|
618 |
+
"step": 87
|
619 |
+
},
|
620 |
+
{
|
621 |
+
"epoch": 0.3055555555555556,
|
622 |
+
"grad_norm": 0.5250104069709778,
|
623 |
+
"learning_rate": 0.0001413427561837456,
|
624 |
+
"loss": 0.6837,
|
625 |
+
"step": 88
|
626 |
+
},
|
627 |
+
{
|
628 |
+
"epoch": 0.3090277777777778,
|
629 |
+
"grad_norm": 0.4821203052997589,
|
630 |
+
"learning_rate": 0.00014063604240282686,
|
631 |
+
"loss": 0.6734,
|
632 |
+
"step": 89
|
633 |
+
},
|
634 |
+
{
|
635 |
+
"epoch": 0.3125,
|
636 |
+
"grad_norm": 0.5341935157775879,
|
637 |
+
"learning_rate": 0.00013992932862190812,
|
638 |
+
"loss": 0.7098,
|
639 |
+
"step": 90
|
640 |
+
},
|
641 |
+
{
|
642 |
+
"epoch": 0.3159722222222222,
|
643 |
+
"grad_norm": 0.5351920127868652,
|
644 |
+
"learning_rate": 0.0001392226148409894,
|
645 |
+
"loss": 0.6806,
|
646 |
+
"step": 91
|
647 |
+
},
|
648 |
+
{
|
649 |
+
"epoch": 0.3194444444444444,
|
650 |
+
"grad_norm": 0.5185657143592834,
|
651 |
+
"learning_rate": 0.00013851590106007068,
|
652 |
+
"loss": 0.6212,
|
653 |
+
"step": 92
|
654 |
+
},
|
655 |
+
{
|
656 |
+
"epoch": 0.3229166666666667,
|
657 |
+
"grad_norm": 0.4946865439414978,
|
658 |
+
"learning_rate": 0.00013780918727915195,
|
659 |
+
"loss": 0.7244,
|
660 |
+
"step": 93
|
661 |
+
},
|
662 |
+
{
|
663 |
+
"epoch": 0.3263888888888889,
|
664 |
+
"grad_norm": 0.51689213514328,
|
665 |
+
"learning_rate": 0.00013710247349823322,
|
666 |
+
"loss": 0.532,
|
667 |
+
"step": 94
|
668 |
+
},
|
669 |
+
{
|
670 |
+
"epoch": 0.3298611111111111,
|
671 |
+
"grad_norm": 0.5387365221977234,
|
672 |
+
"learning_rate": 0.0001363957597173145,
|
673 |
+
"loss": 0.6225,
|
674 |
+
"step": 95
|
675 |
+
},
|
676 |
+
{
|
677 |
+
"epoch": 0.3333333333333333,
|
678 |
+
"grad_norm": 0.5210251212120056,
|
679 |
+
"learning_rate": 0.00013568904593639578,
|
680 |
+
"loss": 0.6565,
|
681 |
+
"step": 96
|
682 |
+
},
|
683 |
+
{
|
684 |
+
"epoch": 0.3368055555555556,
|
685 |
+
"grad_norm": 0.5470120310783386,
|
686 |
+
"learning_rate": 0.00013498233215547705,
|
687 |
+
"loss": 0.6181,
|
688 |
+
"step": 97
|
689 |
+
},
|
690 |
+
{
|
691 |
+
"epoch": 0.3402777777777778,
|
692 |
+
"grad_norm": 0.5134613513946533,
|
693 |
+
"learning_rate": 0.00013427561837455832,
|
694 |
+
"loss": 0.5943,
|
695 |
+
"step": 98
|
696 |
+
},
|
697 |
+
{
|
698 |
+
"epoch": 0.34375,
|
699 |
+
"grad_norm": 0.5114628076553345,
|
700 |
+
"learning_rate": 0.00013356890459363958,
|
701 |
+
"loss": 0.7112,
|
702 |
+
"step": 99
|
703 |
+
},
|
704 |
+
{
|
705 |
+
"epoch": 0.3472222222222222,
|
706 |
+
"grad_norm": 0.5393586158752441,
|
707 |
+
"learning_rate": 0.00013286219081272085,
|
708 |
+
"loss": 0.6513,
|
709 |
+
"step": 100
|
710 |
+
},
|
711 |
+
{
|
712 |
+
"epoch": 0.3506944444444444,
|
713 |
+
"grad_norm": 0.5121696591377258,
|
714 |
+
"learning_rate": 0.00013215547703180215,
|
715 |
+
"loss": 0.6112,
|
716 |
+
"step": 101
|
717 |
+
},
|
718 |
+
{
|
719 |
+
"epoch": 0.3541666666666667,
|
720 |
+
"grad_norm": 0.5529887676239014,
|
721 |
+
"learning_rate": 0.0001314487632508834,
|
722 |
+
"loss": 0.704,
|
723 |
+
"step": 102
|
724 |
+
},
|
725 |
+
{
|
726 |
+
"epoch": 0.3576388888888889,
|
727 |
+
"grad_norm": 0.5504875779151917,
|
728 |
+
"learning_rate": 0.00013074204946996465,
|
729 |
+
"loss": 0.6367,
|
730 |
+
"step": 103
|
731 |
+
},
|
732 |
+
{
|
733 |
+
"epoch": 0.3611111111111111,
|
734 |
+
"grad_norm": 0.5555490255355835,
|
735 |
+
"learning_rate": 0.00013003533568904592,
|
736 |
+
"loss": 0.6988,
|
737 |
+
"step": 104
|
738 |
+
},
|
739 |
+
{
|
740 |
+
"epoch": 0.3645833333333333,
|
741 |
+
"grad_norm": 0.5071545839309692,
|
742 |
+
"learning_rate": 0.00012932862190812722,
|
743 |
+
"loss": 0.6598,
|
744 |
+
"step": 105
|
745 |
+
},
|
746 |
+
{
|
747 |
+
"epoch": 0.3680555555555556,
|
748 |
+
"grad_norm": 0.5332069396972656,
|
749 |
+
"learning_rate": 0.00012862190812720848,
|
750 |
+
"loss": 0.65,
|
751 |
+
"step": 106
|
752 |
+
},
|
753 |
+
{
|
754 |
+
"epoch": 0.3715277777777778,
|
755 |
+
"grad_norm": 0.5629200339317322,
|
756 |
+
"learning_rate": 0.00012791519434628975,
|
757 |
+
"loss": 0.699,
|
758 |
+
"step": 107
|
759 |
+
},
|
760 |
+
{
|
761 |
+
"epoch": 0.375,
|
762 |
+
"grad_norm": 0.5515280961990356,
|
763 |
+
"learning_rate": 0.00012720848056537102,
|
764 |
+
"loss": 0.6418,
|
765 |
+
"step": 108
|
766 |
+
},
|
767 |
+
{
|
768 |
+
"epoch": 0.3784722222222222,
|
769 |
+
"grad_norm": 0.527538001537323,
|
770 |
+
"learning_rate": 0.0001265017667844523,
|
771 |
+
"loss": 0.7302,
|
772 |
+
"step": 109
|
773 |
+
},
|
774 |
+
{
|
775 |
+
"epoch": 0.3819444444444444,
|
776 |
+
"grad_norm": 0.5716756582260132,
|
777 |
+
"learning_rate": 0.00012579505300353358,
|
778 |
+
"loss": 0.7443,
|
779 |
+
"step": 110
|
780 |
+
},
|
781 |
+
{
|
782 |
+
"epoch": 0.3854166666666667,
|
783 |
+
"grad_norm": 0.5540614724159241,
|
784 |
+
"learning_rate": 0.00012508833922261485,
|
785 |
+
"loss": 0.6564,
|
786 |
+
"step": 111
|
787 |
+
},
|
788 |
+
{
|
789 |
+
"epoch": 0.3888888888888889,
|
790 |
+
"grad_norm": 0.5193327069282532,
|
791 |
+
"learning_rate": 0.00012438162544169612,
|
792 |
+
"loss": 0.6783,
|
793 |
+
"step": 112
|
794 |
+
},
|
795 |
+
{
|
796 |
+
"epoch": 0.3923611111111111,
|
797 |
+
"grad_norm": 0.5474222302436829,
|
798 |
+
"learning_rate": 0.00012367491166077738,
|
799 |
+
"loss": 0.6519,
|
800 |
+
"step": 113
|
801 |
+
},
|
802 |
+
{
|
803 |
+
"epoch": 0.3958333333333333,
|
804 |
+
"grad_norm": 0.5058162808418274,
|
805 |
+
"learning_rate": 0.00012296819787985868,
|
806 |
+
"loss": 0.5785,
|
807 |
+
"step": 114
|
808 |
+
},
|
809 |
+
{
|
810 |
+
"epoch": 0.3993055555555556,
|
811 |
+
"grad_norm": 0.5280646085739136,
|
812 |
+
"learning_rate": 0.00012226148409893994,
|
813 |
+
"loss": 0.6308,
|
814 |
+
"step": 115
|
815 |
+
},
|
816 |
+
{
|
817 |
+
"epoch": 0.4027777777777778,
|
818 |
+
"grad_norm": 0.536086916923523,
|
819 |
+
"learning_rate": 0.0001215547703180212,
|
820 |
+
"loss": 0.5696,
|
821 |
+
"step": 116
|
822 |
+
},
|
823 |
+
{
|
824 |
+
"epoch": 0.40625,
|
825 |
+
"grad_norm": 0.5223795771598816,
|
826 |
+
"learning_rate": 0.00012084805653710247,
|
827 |
+
"loss": 0.5861,
|
828 |
+
"step": 117
|
829 |
+
},
|
830 |
+
{
|
831 |
+
"epoch": 0.4097222222222222,
|
832 |
+
"grad_norm": 0.5218377113342285,
|
833 |
+
"learning_rate": 0.00012014134275618376,
|
834 |
+
"loss": 0.6151,
|
835 |
+
"step": 118
|
836 |
+
},
|
837 |
+
{
|
838 |
+
"epoch": 0.4131944444444444,
|
839 |
+
"grad_norm": 0.5461903214454651,
|
840 |
+
"learning_rate": 0.00011943462897526503,
|
841 |
+
"loss": 0.585,
|
842 |
+
"step": 119
|
843 |
+
},
|
844 |
+
{
|
845 |
+
"epoch": 0.4166666666666667,
|
846 |
+
"grad_norm": 0.5451020002365112,
|
847 |
+
"learning_rate": 0.0001187279151943463,
|
848 |
+
"loss": 0.6571,
|
849 |
+
"step": 120
|
850 |
+
},
|
851 |
+
{
|
852 |
+
"epoch": 0.4201388888888889,
|
853 |
+
"grad_norm": 0.5320534706115723,
|
854 |
+
"learning_rate": 0.00011802120141342756,
|
855 |
+
"loss": 0.6191,
|
856 |
+
"step": 121
|
857 |
+
},
|
858 |
+
{
|
859 |
+
"epoch": 0.4236111111111111,
|
860 |
+
"grad_norm": 0.5509814023971558,
|
861 |
+
"learning_rate": 0.00011731448763250883,
|
862 |
+
"loss": 0.542,
|
863 |
+
"step": 122
|
864 |
+
},
|
865 |
+
{
|
866 |
+
"epoch": 0.4270833333333333,
|
867 |
+
"grad_norm": 0.5494756102561951,
|
868 |
+
"learning_rate": 0.00011660777385159012,
|
869 |
+
"loss": 0.7145,
|
870 |
+
"step": 123
|
871 |
+
},
|
872 |
+
{
|
873 |
+
"epoch": 0.4305555555555556,
|
874 |
+
"grad_norm": 0.5778016448020935,
|
875 |
+
"learning_rate": 0.00011590106007067139,
|
876 |
+
"loss": 0.6787,
|
877 |
+
"step": 124
|
878 |
+
},
|
879 |
+
{
|
880 |
+
"epoch": 0.4340277777777778,
|
881 |
+
"grad_norm": 0.5546441674232483,
|
882 |
+
"learning_rate": 0.00011519434628975265,
|
883 |
+
"loss": 0.5897,
|
884 |
+
"step": 125
|
885 |
+
},
|
886 |
+
{
|
887 |
+
"epoch": 0.4375,
|
888 |
+
"grad_norm": 0.5590822100639343,
|
889 |
+
"learning_rate": 0.00011448763250883391,
|
890 |
+
"loss": 0.6331,
|
891 |
+
"step": 126
|
892 |
+
},
|
893 |
+
{
|
894 |
+
"epoch": 0.4409722222222222,
|
895 |
+
"grad_norm": 0.5571174025535583,
|
896 |
+
"learning_rate": 0.00011378091872791521,
|
897 |
+
"loss": 0.6624,
|
898 |
+
"step": 127
|
899 |
+
},
|
900 |
+
{
|
901 |
+
"epoch": 0.4444444444444444,
|
902 |
+
"grad_norm": 0.579007625579834,
|
903 |
+
"learning_rate": 0.00011307420494699648,
|
904 |
+
"loss": 0.6377,
|
905 |
+
"step": 128
|
906 |
+
},
|
907 |
+
{
|
908 |
+
"epoch": 0.4479166666666667,
|
909 |
+
"grad_norm": 0.5956988334655762,
|
910 |
+
"learning_rate": 0.00011236749116607774,
|
911 |
+
"loss": 0.6828,
|
912 |
+
"step": 129
|
913 |
+
},
|
914 |
+
{
|
915 |
+
"epoch": 0.4513888888888889,
|
916 |
+
"grad_norm": 0.5952633023262024,
|
917 |
+
"learning_rate": 0.00011166077738515901,
|
918 |
+
"loss": 0.5603,
|
919 |
+
"step": 130
|
920 |
+
},
|
921 |
+
{
|
922 |
+
"epoch": 0.4548611111111111,
|
923 |
+
"grad_norm": 0.561600387096405,
|
924 |
+
"learning_rate": 0.00011095406360424028,
|
925 |
+
"loss": 0.6311,
|
926 |
+
"step": 131
|
927 |
+
},
|
928 |
+
{
|
929 |
+
"epoch": 0.4583333333333333,
|
930 |
+
"grad_norm": 0.5515158772468567,
|
931 |
+
"learning_rate": 0.00011024734982332157,
|
932 |
+
"loss": 0.7293,
|
933 |
+
"step": 132
|
934 |
+
},
|
935 |
+
{
|
936 |
+
"epoch": 0.4618055555555556,
|
937 |
+
"grad_norm": 0.5889860987663269,
|
938 |
+
"learning_rate": 0.00010954063604240284,
|
939 |
+
"loss": 0.6693,
|
940 |
+
"step": 133
|
941 |
+
},
|
942 |
+
{
|
943 |
+
"epoch": 0.4652777777777778,
|
944 |
+
"grad_norm": 0.5815720558166504,
|
945 |
+
"learning_rate": 0.0001088339222614841,
|
946 |
+
"loss": 0.6881,
|
947 |
+
"step": 134
|
948 |
+
},
|
949 |
+
{
|
950 |
+
"epoch": 0.46875,
|
951 |
+
"grad_norm": 0.6205659508705139,
|
952 |
+
"learning_rate": 0.00010812720848056536,
|
953 |
+
"loss": 0.6732,
|
954 |
+
"step": 135
|
955 |
+
},
|
956 |
+
{
|
957 |
+
"epoch": 0.4722222222222222,
|
958 |
+
"grad_norm": 0.5689711570739746,
|
959 |
+
"learning_rate": 0.00010742049469964666,
|
960 |
+
"loss": 0.6206,
|
961 |
+
"step": 136
|
962 |
+
},
|
963 |
+
{
|
964 |
+
"epoch": 0.4756944444444444,
|
965 |
+
"grad_norm": 0.5453592538833618,
|
966 |
+
"learning_rate": 0.00010671378091872792,
|
967 |
+
"loss": 0.6257,
|
968 |
+
"step": 137
|
969 |
+
},
|
970 |
+
{
|
971 |
+
"epoch": 0.4791666666666667,
|
972 |
+
"grad_norm": 0.5330798625946045,
|
973 |
+
"learning_rate": 0.00010600706713780919,
|
974 |
+
"loss": 0.4674,
|
975 |
+
"step": 138
|
976 |
+
},
|
977 |
+
{
|
978 |
+
"epoch": 0.4826388888888889,
|
979 |
+
"grad_norm": 0.5798875093460083,
|
980 |
+
"learning_rate": 0.00010530035335689046,
|
981 |
+
"loss": 0.6017,
|
982 |
+
"step": 139
|
983 |
+
},
|
984 |
+
{
|
985 |
+
"epoch": 0.4861111111111111,
|
986 |
+
"grad_norm": 0.5574885010719299,
|
987 |
+
"learning_rate": 0.00010459363957597175,
|
988 |
+
"loss": 0.6087,
|
989 |
+
"step": 140
|
990 |
+
},
|
991 |
+
{
|
992 |
+
"epoch": 0.4895833333333333,
|
993 |
+
"grad_norm": 0.5381941199302673,
|
994 |
+
"learning_rate": 0.00010388692579505302,
|
995 |
+
"loss": 0.6543,
|
996 |
+
"step": 141
|
997 |
+
},
|
998 |
+
{
|
999 |
+
"epoch": 0.4930555555555556,
|
1000 |
+
"grad_norm": 0.5750802755355835,
|
1001 |
+
"learning_rate": 0.00010318021201413429,
|
1002 |
+
"loss": 0.6662,
|
1003 |
+
"step": 142
|
1004 |
+
},
|
1005 |
+
{
|
1006 |
+
"epoch": 0.4965277777777778,
|
1007 |
+
"grad_norm": 0.6241365671157837,
|
1008 |
+
"learning_rate": 0.00010247349823321554,
|
1009 |
+
"loss": 0.5976,
|
1010 |
+
"step": 143
|
1011 |
+
},
|
1012 |
+
{
|
1013 |
+
"epoch": 0.5,
|
1014 |
+
"grad_norm": 0.5461493134498596,
|
1015 |
+
"learning_rate": 0.00010176678445229681,
|
1016 |
+
"loss": 0.6796,
|
1017 |
+
"step": 144
|
1018 |
+
},
|
1019 |
+
{
|
1020 |
+
"epoch": 0.5034722222222222,
|
1021 |
+
"grad_norm": 0.5892328023910522,
|
1022 |
+
"learning_rate": 0.0001010600706713781,
|
1023 |
+
"loss": 0.6166,
|
1024 |
+
"step": 145
|
1025 |
+
},
|
1026 |
+
{
|
1027 |
+
"epoch": 0.5069444444444444,
|
1028 |
+
"grad_norm": 0.5670603513717651,
|
1029 |
+
"learning_rate": 0.00010035335689045937,
|
1030 |
+
"loss": 0.651,
|
1031 |
+
"step": 146
|
1032 |
+
},
|
1033 |
+
{
|
1034 |
+
"epoch": 0.5104166666666666,
|
1035 |
+
"grad_norm": 0.5573473572731018,
|
1036 |
+
"learning_rate": 9.964664310954064e-05,
|
1037 |
+
"loss": 0.6268,
|
1038 |
+
"step": 147
|
1039 |
+
},
|
1040 |
+
{
|
1041 |
+
"epoch": 0.5138888888888888,
|
1042 |
+
"grad_norm": 0.5641173720359802,
|
1043 |
+
"learning_rate": 9.893992932862192e-05,
|
1044 |
+
"loss": 0.6515,
|
1045 |
+
"step": 148
|
1046 |
+
},
|
1047 |
+
{
|
1048 |
+
"epoch": 0.5173611111111112,
|
1049 |
+
"grad_norm": 0.5903286337852478,
|
1050 |
+
"learning_rate": 9.823321554770319e-05,
|
1051 |
+
"loss": 0.6705,
|
1052 |
+
"step": 149
|
1053 |
+
},
|
1054 |
+
{
|
1055 |
+
"epoch": 0.5208333333333334,
|
1056 |
+
"grad_norm": 0.5907771587371826,
|
1057 |
+
"learning_rate": 9.752650176678447e-05,
|
1058 |
+
"loss": 0.6184,
|
1059 |
+
"step": 150
|
1060 |
+
},
|
1061 |
+
{
|
1062 |
+
"epoch": 0.5243055555555556,
|
1063 |
+
"grad_norm": 0.5515082478523254,
|
1064 |
+
"learning_rate": 9.681978798586572e-05,
|
1065 |
+
"loss": 0.661,
|
1066 |
+
"step": 151
|
1067 |
+
},
|
1068 |
+
{
|
1069 |
+
"epoch": 0.5277777777777778,
|
1070 |
+
"grad_norm": 0.5268746614456177,
|
1071 |
+
"learning_rate": 9.611307420494699e-05,
|
1072 |
+
"loss": 0.6082,
|
1073 |
+
"step": 152
|
1074 |
+
},
|
1075 |
+
{
|
1076 |
+
"epoch": 0.53125,
|
1077 |
+
"grad_norm": 0.5877247452735901,
|
1078 |
+
"learning_rate": 9.540636042402827e-05,
|
1079 |
+
"loss": 0.5856,
|
1080 |
+
"step": 153
|
1081 |
+
},
|
1082 |
+
{
|
1083 |
+
"epoch": 0.5347222222222222,
|
1084 |
+
"grad_norm": 0.5402259826660156,
|
1085 |
+
"learning_rate": 9.469964664310954e-05,
|
1086 |
+
"loss": 0.574,
|
1087 |
+
"step": 154
|
1088 |
+
},
|
1089 |
+
{
|
1090 |
+
"epoch": 0.5381944444444444,
|
1091 |
+
"grad_norm": 0.5235267281532288,
|
1092 |
+
"learning_rate": 9.399293286219082e-05,
|
1093 |
+
"loss": 0.5598,
|
1094 |
+
"step": 155
|
1095 |
+
},
|
1096 |
+
{
|
1097 |
+
"epoch": 0.5416666666666666,
|
1098 |
+
"grad_norm": 0.5417196750640869,
|
1099 |
+
"learning_rate": 9.328621908127209e-05,
|
1100 |
+
"loss": 0.6447,
|
1101 |
+
"step": 156
|
1102 |
+
},
|
1103 |
+
{
|
1104 |
+
"epoch": 0.5451388888888888,
|
1105 |
+
"grad_norm": 0.6259889006614685,
|
1106 |
+
"learning_rate": 9.257950530035337e-05,
|
1107 |
+
"loss": 0.6227,
|
1108 |
+
"step": 157
|
1109 |
+
},
|
1110 |
+
{
|
1111 |
+
"epoch": 0.5486111111111112,
|
1112 |
+
"grad_norm": 0.567189633846283,
|
1113 |
+
"learning_rate": 9.187279151943463e-05,
|
1114 |
+
"loss": 0.5788,
|
1115 |
+
"step": 158
|
1116 |
+
},
|
1117 |
+
{
|
1118 |
+
"epoch": 0.5520833333333334,
|
1119 |
+
"grad_norm": 0.5860530138015747,
|
1120 |
+
"learning_rate": 9.116607773851592e-05,
|
1121 |
+
"loss": 0.5026,
|
1122 |
+
"step": 159
|
1123 |
+
},
|
1124 |
+
{
|
1125 |
+
"epoch": 0.5555555555555556,
|
1126 |
+
"grad_norm": 0.5970867872238159,
|
1127 |
+
"learning_rate": 9.045936395759717e-05,
|
1128 |
+
"loss": 0.65,
|
1129 |
+
"step": 160
|
1130 |
+
},
|
1131 |
+
{
|
1132 |
+
"epoch": 0.5590277777777778,
|
1133 |
+
"grad_norm": 0.5621108412742615,
|
1134 |
+
"learning_rate": 8.975265017667845e-05,
|
1135 |
+
"loss": 0.6118,
|
1136 |
+
"step": 161
|
1137 |
+
},
|
1138 |
+
{
|
1139 |
+
"epoch": 0.5625,
|
1140 |
+
"grad_norm": 0.5695009827613831,
|
1141 |
+
"learning_rate": 8.904593639575972e-05,
|
1142 |
+
"loss": 0.5119,
|
1143 |
+
"step": 162
|
1144 |
+
},
|
1145 |
+
{
|
1146 |
+
"epoch": 0.5659722222222222,
|
1147 |
+
"grad_norm": 0.5741239786148071,
|
1148 |
+
"learning_rate": 8.833922261484099e-05,
|
1149 |
+
"loss": 0.5273,
|
1150 |
+
"step": 163
|
1151 |
+
},
|
1152 |
+
{
|
1153 |
+
"epoch": 0.5694444444444444,
|
1154 |
+
"grad_norm": 0.5961455702781677,
|
1155 |
+
"learning_rate": 8.763250883392227e-05,
|
1156 |
+
"loss": 0.6197,
|
1157 |
+
"step": 164
|
1158 |
+
},
|
1159 |
+
{
|
1160 |
+
"epoch": 0.5729166666666666,
|
1161 |
+
"grad_norm": 0.5358597636222839,
|
1162 |
+
"learning_rate": 8.692579505300353e-05,
|
1163 |
+
"loss": 0.5629,
|
1164 |
+
"step": 165
|
1165 |
+
},
|
1166 |
+
{
|
1167 |
+
"epoch": 0.5763888888888888,
|
1168 |
+
"grad_norm": 0.5704313516616821,
|
1169 |
+
"learning_rate": 8.621908127208482e-05,
|
1170 |
+
"loss": 0.5838,
|
1171 |
+
"step": 166
|
1172 |
+
},
|
1173 |
+
{
|
1174 |
+
"epoch": 0.5798611111111112,
|
1175 |
+
"grad_norm": 0.6421118378639221,
|
1176 |
+
"learning_rate": 8.551236749116608e-05,
|
1177 |
+
"loss": 0.5964,
|
1178 |
+
"step": 167
|
1179 |
+
},
|
1180 |
+
{
|
1181 |
+
"epoch": 0.5833333333333334,
|
1182 |
+
"grad_norm": 0.5588890314102173,
|
1183 |
+
"learning_rate": 8.480565371024736e-05,
|
1184 |
+
"loss": 0.4957,
|
1185 |
+
"step": 168
|
1186 |
+
},
|
1187 |
+
{
|
1188 |
+
"epoch": 0.5868055555555556,
|
1189 |
+
"grad_norm": 0.5954290628433228,
|
1190 |
+
"learning_rate": 8.409893992932862e-05,
|
1191 |
+
"loss": 0.6364,
|
1192 |
+
"step": 169
|
1193 |
+
},
|
1194 |
+
{
|
1195 |
+
"epoch": 0.5902777777777778,
|
1196 |
+
"grad_norm": 0.5738086700439453,
|
1197 |
+
"learning_rate": 8.33922261484099e-05,
|
1198 |
+
"loss": 0.5661,
|
1199 |
+
"step": 170
|
1200 |
+
},
|
1201 |
+
{
|
1202 |
+
"epoch": 0.59375,
|
1203 |
+
"grad_norm": 0.6033700704574585,
|
1204 |
+
"learning_rate": 8.268551236749117e-05,
|
1205 |
+
"loss": 0.6128,
|
1206 |
+
"step": 171
|
1207 |
+
},
|
1208 |
+
{
|
1209 |
+
"epoch": 0.5972222222222222,
|
1210 |
+
"grad_norm": 0.6137632727622986,
|
1211 |
+
"learning_rate": 8.197879858657245e-05,
|
1212 |
+
"loss": 0.6271,
|
1213 |
+
"step": 172
|
1214 |
+
},
|
1215 |
+
{
|
1216 |
+
"epoch": 0.6006944444444444,
|
1217 |
+
"grad_norm": 0.5929612517356873,
|
1218 |
+
"learning_rate": 8.127208480565371e-05,
|
1219 |
+
"loss": 0.6328,
|
1220 |
+
"step": 173
|
1221 |
+
},
|
1222 |
+
{
|
1223 |
+
"epoch": 0.6041666666666666,
|
1224 |
+
"grad_norm": 0.5914517641067505,
|
1225 |
+
"learning_rate": 8.056537102473498e-05,
|
1226 |
+
"loss": 0.6406,
|
1227 |
+
"step": 174
|
1228 |
+
},
|
1229 |
+
{
|
1230 |
+
"epoch": 0.6076388888888888,
|
1231 |
+
"grad_norm": 0.5911087989807129,
|
1232 |
+
"learning_rate": 7.985865724381626e-05,
|
1233 |
+
"loss": 0.5432,
|
1234 |
+
"step": 175
|
1235 |
+
},
|
1236 |
+
{
|
1237 |
+
"epoch": 0.6111111111111112,
|
1238 |
+
"grad_norm": 0.6051996350288391,
|
1239 |
+
"learning_rate": 7.915194346289753e-05,
|
1240 |
+
"loss": 0.576,
|
1241 |
+
"step": 176
|
1242 |
+
},
|
1243 |
+
{
|
1244 |
+
"epoch": 0.6145833333333334,
|
1245 |
+
"grad_norm": 0.5913227200508118,
|
1246 |
+
"learning_rate": 7.844522968197881e-05,
|
1247 |
+
"loss": 0.6012,
|
1248 |
+
"step": 177
|
1249 |
+
},
|
1250 |
+
{
|
1251 |
+
"epoch": 0.6180555555555556,
|
1252 |
+
"grad_norm": 0.5444892048835754,
|
1253 |
+
"learning_rate": 7.773851590106007e-05,
|
1254 |
+
"loss": 0.5324,
|
1255 |
+
"step": 178
|
1256 |
+
},
|
1257 |
+
{
|
1258 |
+
"epoch": 0.6215277777777778,
|
1259 |
+
"grad_norm": 0.5951313972473145,
|
1260 |
+
"learning_rate": 7.703180212014135e-05,
|
1261 |
+
"loss": 0.6932,
|
1262 |
+
"step": 179
|
1263 |
+
},
|
1264 |
+
{
|
1265 |
+
"epoch": 0.625,
|
1266 |
+
"grad_norm": 0.5791239142417908,
|
1267 |
+
"learning_rate": 7.632508833922261e-05,
|
1268 |
+
"loss": 0.6144,
|
1269 |
+
"step": 180
|
1270 |
+
},
|
1271 |
+
{
|
1272 |
+
"epoch": 0.6284722222222222,
|
1273 |
+
"grad_norm": 0.5847236514091492,
|
1274 |
+
"learning_rate": 7.56183745583039e-05,
|
1275 |
+
"loss": 0.5894,
|
1276 |
+
"step": 181
|
1277 |
+
},
|
1278 |
+
{
|
1279 |
+
"epoch": 0.6319444444444444,
|
1280 |
+
"grad_norm": 0.6364589929580688,
|
1281 |
+
"learning_rate": 7.491166077738516e-05,
|
1282 |
+
"loss": 0.5187,
|
1283 |
+
"step": 182
|
1284 |
+
},
|
1285 |
+
{
|
1286 |
+
"epoch": 0.6354166666666666,
|
1287 |
+
"grad_norm": 0.572428822517395,
|
1288 |
+
"learning_rate": 7.420494699646644e-05,
|
1289 |
+
"loss": 0.5653,
|
1290 |
+
"step": 183
|
1291 |
+
},
|
1292 |
+
{
|
1293 |
+
"epoch": 0.6388888888888888,
|
1294 |
+
"grad_norm": 0.5649181008338928,
|
1295 |
+
"learning_rate": 7.349823321554771e-05,
|
1296 |
+
"loss": 0.5586,
|
1297 |
+
"step": 184
|
1298 |
+
},
|
1299 |
+
{
|
1300 |
+
"epoch": 0.6423611111111112,
|
1301 |
+
"grad_norm": 0.5847340226173401,
|
1302 |
+
"learning_rate": 7.279151943462898e-05,
|
1303 |
+
"loss": 0.6389,
|
1304 |
+
"step": 185
|
1305 |
+
},
|
1306 |
+
{
|
1307 |
+
"epoch": 0.6458333333333334,
|
1308 |
+
"grad_norm": 0.5655092597007751,
|
1309 |
+
"learning_rate": 7.208480565371026e-05,
|
1310 |
+
"loss": 0.5809,
|
1311 |
+
"step": 186
|
1312 |
+
},
|
1313 |
+
{
|
1314 |
+
"epoch": 0.6493055555555556,
|
1315 |
+
"grad_norm": 0.5791696310043335,
|
1316 |
+
"learning_rate": 7.137809187279151e-05,
|
1317 |
+
"loss": 0.6295,
|
1318 |
+
"step": 187
|
1319 |
+
},
|
1320 |
+
{
|
1321 |
+
"epoch": 0.6527777777777778,
|
1322 |
+
"grad_norm": 0.6031994223594666,
|
1323 |
+
"learning_rate": 7.06713780918728e-05,
|
1324 |
+
"loss": 0.5962,
|
1325 |
+
"step": 188
|
1326 |
+
},
|
1327 |
+
{
|
1328 |
+
"epoch": 0.65625,
|
1329 |
+
"grad_norm": 0.6025336980819702,
|
1330 |
+
"learning_rate": 6.996466431095406e-05,
|
1331 |
+
"loss": 0.6424,
|
1332 |
+
"step": 189
|
1333 |
+
},
|
1334 |
+
{
|
1335 |
+
"epoch": 0.6597222222222222,
|
1336 |
+
"grad_norm": 0.6521866917610168,
|
1337 |
+
"learning_rate": 6.925795053003534e-05,
|
1338 |
+
"loss": 0.5857,
|
1339 |
+
"step": 190
|
1340 |
+
},
|
1341 |
+
{
|
1342 |
+
"epoch": 0.6631944444444444,
|
1343 |
+
"grad_norm": 0.5835008025169373,
|
1344 |
+
"learning_rate": 6.855123674911661e-05,
|
1345 |
+
"loss": 0.5807,
|
1346 |
+
"step": 191
|
1347 |
+
},
|
1348 |
+
{
|
1349 |
+
"epoch": 0.6666666666666666,
|
1350 |
+
"grad_norm": 0.5866998434066772,
|
1351 |
+
"learning_rate": 6.784452296819789e-05,
|
1352 |
+
"loss": 0.5653,
|
1353 |
+
"step": 192
|
1354 |
+
},
|
1355 |
+
{
|
1356 |
+
"epoch": 0.6701388888888888,
|
1357 |
+
"grad_norm": 0.5725639462471008,
|
1358 |
+
"learning_rate": 6.713780918727916e-05,
|
1359 |
+
"loss": 0.4654,
|
1360 |
+
"step": 193
|
1361 |
+
},
|
1362 |
+
{
|
1363 |
+
"epoch": 0.6736111111111112,
|
1364 |
+
"grad_norm": 0.6040775775909424,
|
1365 |
+
"learning_rate": 6.643109540636043e-05,
|
1366 |
+
"loss": 0.6563,
|
1367 |
+
"step": 194
|
1368 |
+
},
|
1369 |
+
{
|
1370 |
+
"epoch": 0.6770833333333334,
|
1371 |
+
"grad_norm": 0.6573815941810608,
|
1372 |
+
"learning_rate": 6.57243816254417e-05,
|
1373 |
+
"loss": 0.5836,
|
1374 |
+
"step": 195
|
1375 |
+
},
|
1376 |
+
{
|
1377 |
+
"epoch": 0.6805555555555556,
|
1378 |
+
"grad_norm": 0.5753028392791748,
|
1379 |
+
"learning_rate": 6.501766784452296e-05,
|
1380 |
+
"loss": 0.6142,
|
1381 |
+
"step": 196
|
1382 |
+
},
|
1383 |
+
{
|
1384 |
+
"epoch": 0.6840277777777778,
|
1385 |
+
"grad_norm": 0.6084535717964172,
|
1386 |
+
"learning_rate": 6.431095406360424e-05,
|
1387 |
+
"loss": 0.5592,
|
1388 |
+
"step": 197
|
1389 |
+
},
|
1390 |
+
{
|
1391 |
+
"epoch": 0.6875,
|
1392 |
+
"grad_norm": 0.6668769717216492,
|
1393 |
+
"learning_rate": 6.360424028268551e-05,
|
1394 |
+
"loss": 0.563,
|
1395 |
+
"step": 198
|
1396 |
+
},
|
1397 |
+
{
|
1398 |
+
"epoch": 0.6909722222222222,
|
1399 |
+
"grad_norm": 0.620083212852478,
|
1400 |
+
"learning_rate": 6.289752650176679e-05,
|
1401 |
+
"loss": 0.4906,
|
1402 |
+
"step": 199
|
1403 |
+
},
|
1404 |
+
{
|
1405 |
+
"epoch": 0.6944444444444444,
|
1406 |
+
"grad_norm": 0.6372251510620117,
|
1407 |
+
"learning_rate": 6.219081272084806e-05,
|
1408 |
+
"loss": 0.5754,
|
1409 |
+
"step": 200
|
1410 |
+
},
|
1411 |
+
{
|
1412 |
+
"epoch": 0.6979166666666666,
|
1413 |
+
"grad_norm": 0.602571964263916,
|
1414 |
+
"learning_rate": 6.148409893992934e-05,
|
1415 |
+
"loss": 0.5631,
|
1416 |
+
"step": 201
|
1417 |
+
},
|
1418 |
+
{
|
1419 |
+
"epoch": 0.7013888888888888,
|
1420 |
+
"grad_norm": 0.610701322555542,
|
1421 |
+
"learning_rate": 6.07773851590106e-05,
|
1422 |
+
"loss": 0.6417,
|
1423 |
+
"step": 202
|
1424 |
+
},
|
1425 |
+
{
|
1426 |
+
"epoch": 0.7048611111111112,
|
1427 |
+
"grad_norm": 0.6244217753410339,
|
1428 |
+
"learning_rate": 6.007067137809188e-05,
|
1429 |
+
"loss": 0.6194,
|
1430 |
+
"step": 203
|
1431 |
+
},
|
1432 |
+
{
|
1433 |
+
"epoch": 0.7083333333333334,
|
1434 |
+
"grad_norm": 0.6154200434684753,
|
1435 |
+
"learning_rate": 5.936395759717315e-05,
|
1436 |
+
"loss": 0.5724,
|
1437 |
+
"step": 204
|
1438 |
+
},
|
1439 |
+
{
|
1440 |
+
"epoch": 0.7118055555555556,
|
1441 |
+
"grad_norm": 0.5975745916366577,
|
1442 |
+
"learning_rate": 5.8657243816254415e-05,
|
1443 |
+
"loss": 0.6117,
|
1444 |
+
"step": 205
|
1445 |
+
},
|
1446 |
+
{
|
1447 |
+
"epoch": 0.7152777777777778,
|
1448 |
+
"grad_norm": 0.6204216480255127,
|
1449 |
+
"learning_rate": 5.7950530035335696e-05,
|
1450 |
+
"loss": 0.6153,
|
1451 |
+
"step": 206
|
1452 |
+
},
|
1453 |
+
{
|
1454 |
+
"epoch": 0.71875,
|
1455 |
+
"grad_norm": 0.5886074900627136,
|
1456 |
+
"learning_rate": 5.724381625441696e-05,
|
1457 |
+
"loss": 0.4968,
|
1458 |
+
"step": 207
|
1459 |
+
},
|
1460 |
+
{
|
1461 |
+
"epoch": 0.7222222222222222,
|
1462 |
+
"grad_norm": 0.5940162539482117,
|
1463 |
+
"learning_rate": 5.653710247349824e-05,
|
1464 |
+
"loss": 0.6544,
|
1465 |
+
"step": 208
|
1466 |
+
},
|
1467 |
+
{
|
1468 |
+
"epoch": 0.7256944444444444,
|
1469 |
+
"grad_norm": 0.596792459487915,
|
1470 |
+
"learning_rate": 5.5830388692579505e-05,
|
1471 |
+
"loss": 0.5685,
|
1472 |
+
"step": 209
|
1473 |
+
},
|
1474 |
+
{
|
1475 |
+
"epoch": 0.7291666666666666,
|
1476 |
+
"grad_norm": 0.5985198020935059,
|
1477 |
+
"learning_rate": 5.5123674911660786e-05,
|
1478 |
+
"loss": 0.5795,
|
1479 |
+
"step": 210
|
1480 |
+
},
|
1481 |
+
{
|
1482 |
+
"epoch": 0.7326388888888888,
|
1483 |
+
"grad_norm": 0.5998839735984802,
|
1484 |
+
"learning_rate": 5.441696113074205e-05,
|
1485 |
+
"loss": 0.5229,
|
1486 |
+
"step": 211
|
1487 |
+
},
|
1488 |
+
{
|
1489 |
+
"epoch": 0.7361111111111112,
|
1490 |
+
"grad_norm": 0.5900275707244873,
|
1491 |
+
"learning_rate": 5.371024734982333e-05,
|
1492 |
+
"loss": 0.5882,
|
1493 |
+
"step": 212
|
1494 |
+
},
|
1495 |
+
{
|
1496 |
+
"epoch": 0.7395833333333334,
|
1497 |
+
"grad_norm": 0.5826575756072998,
|
1498 |
+
"learning_rate": 5.3003533568904595e-05,
|
1499 |
+
"loss": 0.4709,
|
1500 |
+
"step": 213
|
1501 |
+
},
|
1502 |
+
{
|
1503 |
+
"epoch": 0.7430555555555556,
|
1504 |
+
"grad_norm": 0.5909337997436523,
|
1505 |
+
"learning_rate": 5.2296819787985876e-05,
|
1506 |
+
"loss": 0.5528,
|
1507 |
+
"step": 214
|
1508 |
+
},
|
1509 |
+
{
|
1510 |
+
"epoch": 0.7465277777777778,
|
1511 |
+
"grad_norm": 0.5588683485984802,
|
1512 |
+
"learning_rate": 5.1590106007067144e-05,
|
1513 |
+
"loss": 0.5373,
|
1514 |
+
"step": 215
|
1515 |
+
},
|
1516 |
+
{
|
1517 |
+
"epoch": 0.75,
|
1518 |
+
"grad_norm": 0.5555421710014343,
|
1519 |
+
"learning_rate": 5.0883392226148405e-05,
|
1520 |
+
"loss": 0.5779,
|
1521 |
+
"step": 216
|
1522 |
+
},
|
1523 |
+
{
|
1524 |
+
"epoch": 0.7534722222222222,
|
1525 |
+
"grad_norm": 0.5925477743148804,
|
1526 |
+
"learning_rate": 5.0176678445229686e-05,
|
1527 |
+
"loss": 0.5896,
|
1528 |
+
"step": 217
|
1529 |
+
},
|
1530 |
+
{
|
1531 |
+
"epoch": 0.7569444444444444,
|
1532 |
+
"grad_norm": 0.6183862090110779,
|
1533 |
+
"learning_rate": 4.946996466431096e-05,
|
1534 |
+
"loss": 0.6245,
|
1535 |
+
"step": 218
|
1536 |
+
},
|
1537 |
+
{
|
1538 |
+
"epoch": 0.7604166666666666,
|
1539 |
+
"grad_norm": 0.5807591080665588,
|
1540 |
+
"learning_rate": 4.8763250883392234e-05,
|
1541 |
+
"loss": 0.5509,
|
1542 |
+
"step": 219
|
1543 |
+
},
|
1544 |
+
{
|
1545 |
+
"epoch": 0.7638888888888888,
|
1546 |
+
"grad_norm": 0.5723608136177063,
|
1547 |
+
"learning_rate": 4.8056537102473495e-05,
|
1548 |
+
"loss": 0.5927,
|
1549 |
+
"step": 220
|
1550 |
+
},
|
1551 |
+
{
|
1552 |
+
"epoch": 0.7673611111111112,
|
1553 |
+
"grad_norm": 0.5748648643493652,
|
1554 |
+
"learning_rate": 4.734982332155477e-05,
|
1555 |
+
"loss": 0.5009,
|
1556 |
+
"step": 221
|
1557 |
+
},
|
1558 |
+
{
|
1559 |
+
"epoch": 0.7708333333333334,
|
1560 |
+
"grad_norm": 0.5595970749855042,
|
1561 |
+
"learning_rate": 4.664310954063604e-05,
|
1562 |
+
"loss": 0.5225,
|
1563 |
+
"step": 222
|
1564 |
+
},
|
1565 |
+
{
|
1566 |
+
"epoch": 0.7743055555555556,
|
1567 |
+
"grad_norm": 0.5699341893196106,
|
1568 |
+
"learning_rate": 4.593639575971732e-05,
|
1569 |
+
"loss": 0.5945,
|
1570 |
+
"step": 223
|
1571 |
+
},
|
1572 |
+
{
|
1573 |
+
"epoch": 0.7777777777777778,
|
1574 |
+
"grad_norm": 0.5965125560760498,
|
1575 |
+
"learning_rate": 4.5229681978798585e-05,
|
1576 |
+
"loss": 0.6039,
|
1577 |
+
"step": 224
|
1578 |
+
},
|
1579 |
+
{
|
1580 |
+
"epoch": 0.78125,
|
1581 |
+
"grad_norm": 0.601673424243927,
|
1582 |
+
"learning_rate": 4.452296819787986e-05,
|
1583 |
+
"loss": 0.6116,
|
1584 |
+
"step": 225
|
1585 |
+
},
|
1586 |
+
{
|
1587 |
+
"epoch": 0.7847222222222222,
|
1588 |
+
"grad_norm": 0.6311600804328918,
|
1589 |
+
"learning_rate": 4.381625441696113e-05,
|
1590 |
+
"loss": 0.6356,
|
1591 |
+
"step": 226
|
1592 |
+
},
|
1593 |
+
{
|
1594 |
+
"epoch": 0.7881944444444444,
|
1595 |
+
"grad_norm": 0.6146146059036255,
|
1596 |
+
"learning_rate": 4.310954063604241e-05,
|
1597 |
+
"loss": 0.5925,
|
1598 |
+
"step": 227
|
1599 |
+
},
|
1600 |
+
{
|
1601 |
+
"epoch": 0.7916666666666666,
|
1602 |
+
"grad_norm": 0.5608177781105042,
|
1603 |
+
"learning_rate": 4.240282685512368e-05,
|
1604 |
+
"loss": 0.4546,
|
1605 |
+
"step": 228
|
1606 |
+
},
|
1607 |
+
{
|
1608 |
+
"epoch": 0.7951388888888888,
|
1609 |
+
"grad_norm": 0.6077985167503357,
|
1610 |
+
"learning_rate": 4.169611307420495e-05,
|
1611 |
+
"loss": 0.6111,
|
1612 |
+
"step": 229
|
1613 |
+
},
|
1614 |
+
{
|
1615 |
+
"epoch": 0.7986111111111112,
|
1616 |
+
"grad_norm": 0.5868244171142578,
|
1617 |
+
"learning_rate": 4.0989399293286223e-05,
|
1618 |
+
"loss": 0.5945,
|
1619 |
+
"step": 230
|
1620 |
+
},
|
1621 |
+
{
|
1622 |
+
"epoch": 0.8020833333333334,
|
1623 |
+
"grad_norm": 0.587386965751648,
|
1624 |
+
"learning_rate": 4.028268551236749e-05,
|
1625 |
+
"loss": 0.5294,
|
1626 |
+
"step": 231
|
1627 |
+
},
|
1628 |
+
{
|
1629 |
+
"epoch": 0.8055555555555556,
|
1630 |
+
"grad_norm": 0.5953108668327332,
|
1631 |
+
"learning_rate": 3.9575971731448765e-05,
|
1632 |
+
"loss": 0.5621,
|
1633 |
+
"step": 232
|
1634 |
+
},
|
1635 |
+
{
|
1636 |
+
"epoch": 0.8090277777777778,
|
1637 |
+
"grad_norm": 0.6050392985343933,
|
1638 |
+
"learning_rate": 3.886925795053003e-05,
|
1639 |
+
"loss": 0.5374,
|
1640 |
+
"step": 233
|
1641 |
+
},
|
1642 |
+
{
|
1643 |
+
"epoch": 0.8125,
|
1644 |
+
"grad_norm": 0.6083176732063293,
|
1645 |
+
"learning_rate": 3.816254416961131e-05,
|
1646 |
+
"loss": 0.5843,
|
1647 |
+
"step": 234
|
1648 |
+
},
|
1649 |
+
{
|
1650 |
+
"epoch": 0.8159722222222222,
|
1651 |
+
"grad_norm": 0.5946184992790222,
|
1652 |
+
"learning_rate": 3.745583038869258e-05,
|
1653 |
+
"loss": 0.5049,
|
1654 |
+
"step": 235
|
1655 |
+
},
|
1656 |
+
{
|
1657 |
+
"epoch": 0.8194444444444444,
|
1658 |
+
"grad_norm": 0.5910969972610474,
|
1659 |
+
"learning_rate": 3.6749116607773855e-05,
|
1660 |
+
"loss": 0.5749,
|
1661 |
+
"step": 236
|
1662 |
+
},
|
1663 |
+
{
|
1664 |
+
"epoch": 0.8229166666666666,
|
1665 |
+
"grad_norm": 0.5982712507247925,
|
1666 |
+
"learning_rate": 3.604240282685513e-05,
|
1667 |
+
"loss": 0.5882,
|
1668 |
+
"step": 237
|
1669 |
+
},
|
1670 |
+
{
|
1671 |
+
"epoch": 0.8263888888888888,
|
1672 |
+
"grad_norm": 0.6084917783737183,
|
1673 |
+
"learning_rate": 3.53356890459364e-05,
|
1674 |
+
"loss": 0.5169,
|
1675 |
+
"step": 238
|
1676 |
+
},
|
1677 |
+
{
|
1678 |
+
"epoch": 0.8298611111111112,
|
1679 |
+
"grad_norm": 0.6236574649810791,
|
1680 |
+
"learning_rate": 3.462897526501767e-05,
|
1681 |
+
"loss": 0.6085,
|
1682 |
+
"step": 239
|
1683 |
+
},
|
1684 |
+
{
|
1685 |
+
"epoch": 0.8333333333333334,
|
1686 |
+
"grad_norm": 0.592654824256897,
|
1687 |
+
"learning_rate": 3.3922261484098945e-05,
|
1688 |
+
"loss": 0.5525,
|
1689 |
+
"step": 240
|
1690 |
+
},
|
1691 |
+
{
|
1692 |
+
"epoch": 0.8368055555555556,
|
1693 |
+
"grad_norm": 0.6017850041389465,
|
1694 |
+
"learning_rate": 3.321554770318021e-05,
|
1695 |
+
"loss": 0.636,
|
1696 |
+
"step": 241
|
1697 |
+
},
|
1698 |
+
{
|
1699 |
+
"epoch": 0.8402777777777778,
|
1700 |
+
"grad_norm": 0.5793926119804382,
|
1701 |
+
"learning_rate": 3.250883392226148e-05,
|
1702 |
+
"loss": 0.6003,
|
1703 |
+
"step": 242
|
1704 |
+
},
|
1705 |
+
{
|
1706 |
+
"epoch": 0.84375,
|
1707 |
+
"grad_norm": 0.5898053050041199,
|
1708 |
+
"learning_rate": 3.1802120141342755e-05,
|
1709 |
+
"loss": 0.6925,
|
1710 |
+
"step": 243
|
1711 |
+
},
|
1712 |
+
{
|
1713 |
+
"epoch": 0.8472222222222222,
|
1714 |
+
"grad_norm": 0.6041194796562195,
|
1715 |
+
"learning_rate": 3.109540636042403e-05,
|
1716 |
+
"loss": 0.5509,
|
1717 |
+
"step": 244
|
1718 |
+
},
|
1719 |
+
{
|
1720 |
+
"epoch": 0.8506944444444444,
|
1721 |
+
"grad_norm": 0.5889320373535156,
|
1722 |
+
"learning_rate": 3.03886925795053e-05,
|
1723 |
+
"loss": 0.5377,
|
1724 |
+
"step": 245
|
1725 |
+
},
|
1726 |
+
{
|
1727 |
+
"epoch": 0.8541666666666666,
|
1728 |
+
"grad_norm": 0.65882408618927,
|
1729 |
+
"learning_rate": 2.9681978798586574e-05,
|
1730 |
+
"loss": 0.6909,
|
1731 |
+
"step": 246
|
1732 |
+
},
|
1733 |
+
{
|
1734 |
+
"epoch": 0.8576388888888888,
|
1735 |
+
"grad_norm": 0.5652550458908081,
|
1736 |
+
"learning_rate": 2.8975265017667848e-05,
|
1737 |
+
"loss": 0.6553,
|
1738 |
+
"step": 247
|
1739 |
+
},
|
1740 |
+
{
|
1741 |
+
"epoch": 0.8611111111111112,
|
1742 |
+
"grad_norm": 0.6159343123435974,
|
1743 |
+
"learning_rate": 2.826855123674912e-05,
|
1744 |
+
"loss": 0.4816,
|
1745 |
+
"step": 248
|
1746 |
+
},
|
1747 |
+
{
|
1748 |
+
"epoch": 0.8645833333333334,
|
1749 |
+
"grad_norm": 0.5917626023292542,
|
1750 |
+
"learning_rate": 2.7561837455830393e-05,
|
1751 |
+
"loss": 0.6042,
|
1752 |
+
"step": 249
|
1753 |
+
},
|
1754 |
+
{
|
1755 |
+
"epoch": 0.8680555555555556,
|
1756 |
+
"grad_norm": 0.5773218870162964,
|
1757 |
+
"learning_rate": 2.6855123674911664e-05,
|
1758 |
+
"loss": 0.5723,
|
1759 |
+
"step": 250
|
1760 |
+
},
|
1761 |
+
{
|
1762 |
+
"epoch": 0.8715277777777778,
|
1763 |
+
"grad_norm": 0.5936452150344849,
|
1764 |
+
"learning_rate": 2.6148409893992938e-05,
|
1765 |
+
"loss": 0.6071,
|
1766 |
+
"step": 251
|
1767 |
+
},
|
1768 |
+
{
|
1769 |
+
"epoch": 0.875,
|
1770 |
+
"grad_norm": 0.6094207763671875,
|
1771 |
+
"learning_rate": 2.5441696113074202e-05,
|
1772 |
+
"loss": 0.5406,
|
1773 |
+
"step": 252
|
1774 |
+
},
|
1775 |
+
{
|
1776 |
+
"epoch": 0.8784722222222222,
|
1777 |
+
"grad_norm": 0.6131781935691833,
|
1778 |
+
"learning_rate": 2.473498233215548e-05,
|
1779 |
+
"loss": 0.562,
|
1780 |
+
"step": 253
|
1781 |
+
},
|
1782 |
+
{
|
1783 |
+
"epoch": 0.8819444444444444,
|
1784 |
+
"grad_norm": 0.5903745889663696,
|
1785 |
+
"learning_rate": 2.4028268551236747e-05,
|
1786 |
+
"loss": 0.5841,
|
1787 |
+
"step": 254
|
1788 |
+
},
|
1789 |
+
{
|
1790 |
+
"epoch": 0.8854166666666666,
|
1791 |
+
"grad_norm": 0.5778252482414246,
|
1792 |
+
"learning_rate": 2.332155477031802e-05,
|
1793 |
+
"loss": 0.6071,
|
1794 |
+
"step": 255
|
1795 |
+
},
|
1796 |
+
{
|
1797 |
+
"epoch": 0.8888888888888888,
|
1798 |
+
"grad_norm": 0.6057181358337402,
|
1799 |
+
"learning_rate": 2.2614840989399292e-05,
|
1800 |
+
"loss": 0.5794,
|
1801 |
+
"step": 256
|
1802 |
+
},
|
1803 |
+
{
|
1804 |
+
"epoch": 0.8923611111111112,
|
1805 |
+
"grad_norm": 0.5691949129104614,
|
1806 |
+
"learning_rate": 2.1908127208480567e-05,
|
1807 |
+
"loss": 0.5634,
|
1808 |
+
"step": 257
|
1809 |
+
},
|
1810 |
+
{
|
1811 |
+
"epoch": 0.8958333333333334,
|
1812 |
+
"grad_norm": 0.6154379844665527,
|
1813 |
+
"learning_rate": 2.120141342756184e-05,
|
1814 |
+
"loss": 0.5389,
|
1815 |
+
"step": 258
|
1816 |
+
},
|
1817 |
+
{
|
1818 |
+
"epoch": 0.8993055555555556,
|
1819 |
+
"grad_norm": 0.5671730637550354,
|
1820 |
+
"learning_rate": 2.0494699646643112e-05,
|
1821 |
+
"loss": 0.6045,
|
1822 |
+
"step": 259
|
1823 |
+
},
|
1824 |
+
{
|
1825 |
+
"epoch": 0.9027777777777778,
|
1826 |
+
"grad_norm": 0.6344681978225708,
|
1827 |
+
"learning_rate": 1.9787985865724383e-05,
|
1828 |
+
"loss": 0.4922,
|
1829 |
+
"step": 260
|
1830 |
+
},
|
1831 |
+
{
|
1832 |
+
"epoch": 0.90625,
|
1833 |
+
"grad_norm": 0.584071934223175,
|
1834 |
+
"learning_rate": 1.9081272084805653e-05,
|
1835 |
+
"loss": 0.5283,
|
1836 |
+
"step": 261
|
1837 |
+
},
|
1838 |
+
{
|
1839 |
+
"epoch": 0.9097222222222222,
|
1840 |
+
"grad_norm": 0.5744527578353882,
|
1841 |
+
"learning_rate": 1.8374558303886928e-05,
|
1842 |
+
"loss": 0.51,
|
1843 |
+
"step": 262
|
1844 |
+
},
|
1845 |
+
{
|
1846 |
+
"epoch": 0.9131944444444444,
|
1847 |
+
"grad_norm": 0.5983773469924927,
|
1848 |
+
"learning_rate": 1.76678445229682e-05,
|
1849 |
+
"loss": 0.619,
|
1850 |
+
"step": 263
|
1851 |
+
},
|
1852 |
+
{
|
1853 |
+
"epoch": 0.9166666666666666,
|
1854 |
+
"grad_norm": 0.5973845720291138,
|
1855 |
+
"learning_rate": 1.6961130742049473e-05,
|
1856 |
+
"loss": 0.5131,
|
1857 |
+
"step": 264
|
1858 |
+
},
|
1859 |
+
{
|
1860 |
+
"epoch": 0.9201388888888888,
|
1861 |
+
"grad_norm": 0.6193533539772034,
|
1862 |
+
"learning_rate": 1.625441696113074e-05,
|
1863 |
+
"loss": 0.577,
|
1864 |
+
"step": 265
|
1865 |
+
},
|
1866 |
+
{
|
1867 |
+
"epoch": 0.9236111111111112,
|
1868 |
+
"grad_norm": 0.6047850251197815,
|
1869 |
+
"learning_rate": 1.5547703180212014e-05,
|
1870 |
+
"loss": 0.6277,
|
1871 |
+
"step": 266
|
1872 |
+
},
|
1873 |
+
{
|
1874 |
+
"epoch": 0.9270833333333334,
|
1875 |
+
"grad_norm": 0.6007250547409058,
|
1876 |
+
"learning_rate": 1.4840989399293287e-05,
|
1877 |
+
"loss": 0.6026,
|
1878 |
+
"step": 267
|
1879 |
+
},
|
1880 |
+
{
|
1881 |
+
"epoch": 0.9305555555555556,
|
1882 |
+
"grad_norm": 0.5738986730575562,
|
1883 |
+
"learning_rate": 1.413427561837456e-05,
|
1884 |
+
"loss": 0.5842,
|
1885 |
+
"step": 268
|
1886 |
+
},
|
1887 |
+
{
|
1888 |
+
"epoch": 0.9340277777777778,
|
1889 |
+
"grad_norm": 0.5671294927597046,
|
1890 |
+
"learning_rate": 1.3427561837455832e-05,
|
1891 |
+
"loss": 0.4875,
|
1892 |
+
"step": 269
|
1893 |
+
},
|
1894 |
+
{
|
1895 |
+
"epoch": 0.9375,
|
1896 |
+
"grad_norm": 0.5837607383728027,
|
1897 |
+
"learning_rate": 1.2720848056537101e-05,
|
1898 |
+
"loss": 0.6032,
|
1899 |
+
"step": 270
|
1900 |
+
},
|
1901 |
+
{
|
1902 |
+
"epoch": 0.9409722222222222,
|
1903 |
+
"grad_norm": 0.6210164427757263,
|
1904 |
+
"learning_rate": 1.2014134275618374e-05,
|
1905 |
+
"loss": 0.6143,
|
1906 |
+
"step": 271
|
1907 |
+
},
|
1908 |
+
{
|
1909 |
+
"epoch": 0.9444444444444444,
|
1910 |
+
"grad_norm": 0.5613874197006226,
|
1911 |
+
"learning_rate": 1.1307420494699646e-05,
|
1912 |
+
"loss": 0.5193,
|
1913 |
+
"step": 272
|
1914 |
+
},
|
1915 |
+
{
|
1916 |
+
"epoch": 0.9479166666666666,
|
1917 |
+
"grad_norm": 0.5788601636886597,
|
1918 |
+
"learning_rate": 1.060070671378092e-05,
|
1919 |
+
"loss": 0.5993,
|
1920 |
+
"step": 273
|
1921 |
+
},
|
1922 |
+
{
|
1923 |
+
"epoch": 0.9513888888888888,
|
1924 |
+
"grad_norm": 0.5956071615219116,
|
1925 |
+
"learning_rate": 9.893992932862191e-06,
|
1926 |
+
"loss": 0.6244,
|
1927 |
+
"step": 274
|
1928 |
+
},
|
1929 |
+
{
|
1930 |
+
"epoch": 0.9548611111111112,
|
1931 |
+
"grad_norm": 0.5741413235664368,
|
1932 |
+
"learning_rate": 9.187279151943464e-06,
|
1933 |
+
"loss": 0.5912,
|
1934 |
+
"step": 275
|
1935 |
+
},
|
1936 |
+
{
|
1937 |
+
"epoch": 0.9583333333333334,
|
1938 |
+
"grad_norm": 0.5746176242828369,
|
1939 |
+
"learning_rate": 8.480565371024736e-06,
|
1940 |
+
"loss": 0.4959,
|
1941 |
+
"step": 276
|
1942 |
+
},
|
1943 |
+
{
|
1944 |
+
"epoch": 0.9618055555555556,
|
1945 |
+
"grad_norm": 0.6048396825790405,
|
1946 |
+
"learning_rate": 7.773851590106007e-06,
|
1947 |
+
"loss": 0.5358,
|
1948 |
+
"step": 277
|
1949 |
+
},
|
1950 |
+
{
|
1951 |
+
"epoch": 0.9652777777777778,
|
1952 |
+
"grad_norm": 0.5789562463760376,
|
1953 |
+
"learning_rate": 7.06713780918728e-06,
|
1954 |
+
"loss": 0.526,
|
1955 |
+
"step": 278
|
1956 |
+
},
|
1957 |
+
{
|
1958 |
+
"epoch": 0.96875,
|
1959 |
+
"grad_norm": 0.623224139213562,
|
1960 |
+
"learning_rate": 6.3604240282685506e-06,
|
1961 |
+
"loss": 0.6296,
|
1962 |
+
"step": 279
|
1963 |
+
},
|
1964 |
+
{
|
1965 |
+
"epoch": 0.9722222222222222,
|
1966 |
+
"grad_norm": 0.5628058910369873,
|
1967 |
+
"learning_rate": 5.653710247349823e-06,
|
1968 |
+
"loss": 0.519,
|
1969 |
+
"step": 280
|
1970 |
+
},
|
1971 |
+
{
|
1972 |
+
"epoch": 0.9756944444444444,
|
1973 |
+
"grad_norm": 0.574334442615509,
|
1974 |
+
"learning_rate": 4.946996466431096e-06,
|
1975 |
+
"loss": 0.5241,
|
1976 |
+
"step": 281
|
1977 |
+
},
|
1978 |
+
{
|
1979 |
+
"epoch": 0.9791666666666666,
|
1980 |
+
"grad_norm": 0.6212002038955688,
|
1981 |
+
"learning_rate": 4.240282685512368e-06,
|
1982 |
+
"loss": 0.6307,
|
1983 |
+
"step": 282
|
1984 |
+
},
|
1985 |
+
{
|
1986 |
+
"epoch": 0.9826388888888888,
|
1987 |
+
"grad_norm": 0.6209303140640259,
|
1988 |
+
"learning_rate": 3.53356890459364e-06,
|
1989 |
+
"loss": 0.5419,
|
1990 |
+
"step": 283
|
1991 |
+
},
|
1992 |
+
{
|
1993 |
+
"epoch": 0.9861111111111112,
|
1994 |
+
"grad_norm": 0.6056732535362244,
|
1995 |
+
"learning_rate": 2.8268551236749116e-06,
|
1996 |
+
"loss": 0.6091,
|
1997 |
+
"step": 284
|
1998 |
+
},
|
1999 |
+
{
|
2000 |
+
"epoch": 0.9895833333333334,
|
2001 |
+
"grad_norm": 0.632924497127533,
|
2002 |
+
"learning_rate": 2.120141342756184e-06,
|
2003 |
+
"loss": 0.6159,
|
2004 |
+
"step": 285
|
2005 |
+
},
|
2006 |
+
{
|
2007 |
+
"epoch": 0.9930555555555556,
|
2008 |
+
"grad_norm": 0.6058059334754944,
|
2009 |
+
"learning_rate": 1.4134275618374558e-06,
|
2010 |
+
"loss": 0.5805,
|
2011 |
+
"step": 286
|
2012 |
+
},
|
2013 |
+
{
|
2014 |
+
"epoch": 0.9965277777777778,
|
2015 |
+
"grad_norm": 0.6084165573120117,
|
2016 |
+
"learning_rate": 7.067137809187279e-07,
|
2017 |
+
"loss": 0.6208,
|
2018 |
+
"step": 287
|
2019 |
+
},
|
2020 |
+
{
|
2021 |
+
"epoch": 1.0,
|
2022 |
+
"grad_norm": 0.6049368977546692,
|
2023 |
+
"learning_rate": 0.0,
|
2024 |
+
"loss": 0.4819,
|
2025 |
+
"step": 288
|
2026 |
+
}
|
2027 |
+
],
|
2028 |
+
"logging_steps": 1,
|
2029 |
+
"max_steps": 288,
|
2030 |
+
"num_input_tokens_seen": 0,
|
2031 |
+
"num_train_epochs": 1,
|
2032 |
+
"save_steps": 500,
|
2033 |
+
"stateful_callbacks": {
|
2034 |
+
"TrainerControl": {
|
2035 |
+
"args": {
|
2036 |
+
"should_epoch_stop": false,
|
2037 |
+
"should_evaluate": false,
|
2038 |
+
"should_log": false,
|
2039 |
+
"should_save": true,
|
2040 |
+
"should_training_stop": true
|
2041 |
+
},
|
2042 |
+
"attributes": {}
|
2043 |
+
}
|
2044 |
+
},
|
2045 |
+
"total_flos": 5.5964978416533504e+17,
|
2046 |
+
"train_batch_size": 32,
|
2047 |
+
"trial_name": null,
|
2048 |
+
"trial_params": null
|
2049 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f8952c039e74c402add94711d6444921ca6295627b6b5b755bd1cf444ceb058b
|
3 |
+
size 5560
|