Upload LoRA adapter checkpoint
Browse files- .gitattributes +1 -0
- README.md +202 -0
- adapter_config.json +31 -0
- adapter_model.safetensors +3 -0
- optimizer.pt +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +17 -0
- tokenizer.json +3 -0
- tokenizer_config.json +2068 -0
- trainer_state.json +1959 -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
ADDED
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 0.15.1
|
adapter_config.json
ADDED
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
"corda_config": null,
|
7 |
+
"eva_config": null,
|
8 |
+
"exclude_modules": null,
|
9 |
+
"fan_in_fan_out": false,
|
10 |
+
"inference_mode": true,
|
11 |
+
"init_lora_weights": true,
|
12 |
+
"layer_replication": null,
|
13 |
+
"layers_pattern": null,
|
14 |
+
"layers_to_transform": null,
|
15 |
+
"loftq_config": {},
|
16 |
+
"lora_alpha": 32,
|
17 |
+
"lora_bias": false,
|
18 |
+
"lora_dropout": 0,
|
19 |
+
"megatron_config": null,
|
20 |
+
"megatron_core": "megatron.core",
|
21 |
+
"modules_to_save": null,
|
22 |
+
"peft_type": "LORA",
|
23 |
+
"r": 16,
|
24 |
+
"rank_pattern": {},
|
25 |
+
"revision": null,
|
26 |
+
"target_modules": "(?:.*?(?:language|text).*?(?:self_attn|attention|attn|mlp|feed_forward|ffn|dense).*?(?:q_proj|k_proj|v_proj|o_proj|gate_proj|up_proj|down_proj).*?)|(?:\\bmodel\\.layers\\.[\\d]{1,}\\.(?:self_attn|attention|attn|mlp|feed_forward|ffn|dense)\\.(?:(?:q_proj|k_proj|v_proj|o_proj|gate_proj|up_proj|down_proj)))",
|
27 |
+
"task_type": "CAUSAL_LM",
|
28 |
+
"trainable_token_indices": null,
|
29 |
+
"use_dora": false,
|
30 |
+
"use_rslora": false
|
31 |
+
}
|
adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:06c45878dd3118a5446ffe1a21b9bb7b52e4cd4c1c80102d4ab4c2c4297adb6c
|
3 |
+
size 167832240
|
optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cf14a6a964efdc124b8ef039718b3e36134dbbf7a243b86126d8488226a588c5
|
3 |
+
size 85723732
|
rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2b66e3cc7c452b707ddac5caf0aa17618afb9bc1a0333600a22c4afb353f3165
|
3 |
+
size 14244
|
scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9a8da7a94370983a4fc56eb0e0701c5642e71315756408eddadcbd4e4d200300
|
3 |
+
size 1064
|
special_tokens_map.json
ADDED
@@ -0,0 +1,17 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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": "<|end▁of▁sentence|>"
|
17 |
+
}
|
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": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set ns = namespace(is_first=false, is_tool=false, is_output_first=true, system_prompt='') %}{%- for message in messages %}{%- if message['role'] == 'system' %}{% set ns.system_prompt = message['content'] %}{%- endif %}{%- endfor %}{{bos_token}}{{ns.system_prompt}}{%- for message in messages %}{%- if message['role'] == 'user' %}{%- set ns.is_tool = false -%}{{'<|User|>' + message['content']}}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is none %}{%- set ns.is_tool = false -%}{%- for tool in message['tool_calls']%}{%- if not ns.is_first %}{{'<|Assistant|><|tool▁calls▁begin|><|tool▁call▁begin|>' + tool['type'] + '<|tool▁sep|>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<|tool▁call▁end|>'}}{%- set ns.is_first = true -%}{%- else %}{{'\\n' + '<|tool▁call▁begin|>' + tool['type'] + '<|tool▁sep|>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<|tool▁call▁end|>'}}{{'<|tool▁calls▁end|><|end▁of▁sentence|>'}}{%- endif %}{%- endfor %}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is not none %}{%- if ns.is_tool %}{{'<|tool▁outputs▁end|>' + message['content'] + '<|end▁of▁sentence|>'}}{%- set ns.is_tool = false -%}{%- else %}{% set content = message['content'] %}{% if '</think>' in content %}{% set content = content.split('</think>')[-1] %}{% endif %}{{'<|Assistant|>' + content + '<|end▁of▁sentence|>'}}{%- endif %}{%- endif %}{%- if message['role'] == 'tool' %}{%- set ns.is_tool = true -%}{%- if ns.is_output_first %}{{'<|tool▁outputs▁begin|><|tool▁output▁begin|>' + message['content'] + '<|tool▁output▁end|>'}}{%- set ns.is_output_first = false %}{%- else %}{{'\\n<|tool▁output▁begin|>' + message['content'] + '<|tool▁output▁end|>'}}{%- endif %}{%- endif %}{%- endfor -%}{% if ns.is_tool %}{{'<|tool▁outputs▁end|>'}}{% endif %}{% if add_generation_prompt and not ns.is_tool %}{{'<|Assistant|><think>\\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": "<|end▁of▁sentence|>",
|
2063 |
+
"padding_side": "right",
|
2064 |
+
"sp_model_kwargs": {},
|
2065 |
+
"tokenizer_class": "LlamaTokenizerFast",
|
2066 |
+
"unk_token": null,
|
2067 |
+
"use_default_system_prompt": false
|
2068 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,1959 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_global_step": null,
|
3 |
+
"best_metric": null,
|
4 |
+
"best_model_checkpoint": null,
|
5 |
+
"epoch": 1.9824561403508771,
|
6 |
+
"eval_steps": 500,
|
7 |
+
"global_step": 550,
|
8 |
+
"is_hyper_param_search": false,
|
9 |
+
"is_local_process_zero": true,
|
10 |
+
"is_world_process_zero": true,
|
11 |
+
"log_history": [
|
12 |
+
{
|
13 |
+
"epoch": 0.007197480881691408,
|
14 |
+
"grad_norm": 0.15582965314388275,
|
15 |
+
"learning_rate": 2.3809523809523808e-06,
|
16 |
+
"loss": 0.4336,
|
17 |
+
"step": 2
|
18 |
+
},
|
19 |
+
{
|
20 |
+
"epoch": 0.014394961763382817,
|
21 |
+
"grad_norm": 0.18861062824726105,
|
22 |
+
"learning_rate": 7.142857142857143e-06,
|
23 |
+
"loss": 0.444,
|
24 |
+
"step": 4
|
25 |
+
},
|
26 |
+
{
|
27 |
+
"epoch": 0.021592442645074223,
|
28 |
+
"grad_norm": 0.2031652182340622,
|
29 |
+
"learning_rate": 1.1904761904761905e-05,
|
30 |
+
"loss": 0.4497,
|
31 |
+
"step": 6
|
32 |
+
},
|
33 |
+
{
|
34 |
+
"epoch": 0.028789923526765633,
|
35 |
+
"grad_norm": 0.1832951456308365,
|
36 |
+
"learning_rate": 1.6666666666666667e-05,
|
37 |
+
"loss": 0.4637,
|
38 |
+
"step": 8
|
39 |
+
},
|
40 |
+
{
|
41 |
+
"epoch": 0.03598740440845704,
|
42 |
+
"grad_norm": 0.12462884187698364,
|
43 |
+
"learning_rate": 2.1428571428571428e-05,
|
44 |
+
"loss": 0.4348,
|
45 |
+
"step": 10
|
46 |
+
},
|
47 |
+
{
|
48 |
+
"epoch": 0.043184885290148446,
|
49 |
+
"grad_norm": 0.14522534608840942,
|
50 |
+
"learning_rate": 2.6190476190476192e-05,
|
51 |
+
"loss": 0.4358,
|
52 |
+
"step": 12
|
53 |
+
},
|
54 |
+
{
|
55 |
+
"epoch": 0.05038236617183985,
|
56 |
+
"grad_norm": 0.14399775862693787,
|
57 |
+
"learning_rate": 3.095238095238095e-05,
|
58 |
+
"loss": 0.5393,
|
59 |
+
"step": 14
|
60 |
+
},
|
61 |
+
{
|
62 |
+
"epoch": 0.057579847053531266,
|
63 |
+
"grad_norm": 0.1419936716556549,
|
64 |
+
"learning_rate": 3.571428571428572e-05,
|
65 |
+
"loss": 0.4061,
|
66 |
+
"step": 16
|
67 |
+
},
|
68 |
+
{
|
69 |
+
"epoch": 0.06477732793522267,
|
70 |
+
"grad_norm": 0.172491654753685,
|
71 |
+
"learning_rate": 4.047619047619048e-05,
|
72 |
+
"loss": 0.4315,
|
73 |
+
"step": 18
|
74 |
+
},
|
75 |
+
{
|
76 |
+
"epoch": 0.07197480881691408,
|
77 |
+
"grad_norm": 0.10637587308883667,
|
78 |
+
"learning_rate": 4.523809523809524e-05,
|
79 |
+
"loss": 0.5996,
|
80 |
+
"step": 20
|
81 |
+
},
|
82 |
+
{
|
83 |
+
"epoch": 0.07917228969860549,
|
84 |
+
"grad_norm": 0.20852264761924744,
|
85 |
+
"learning_rate": 5e-05,
|
86 |
+
"loss": 0.5786,
|
87 |
+
"step": 22
|
88 |
+
},
|
89 |
+
{
|
90 |
+
"epoch": 0.08636977058029689,
|
91 |
+
"grad_norm": 0.13951802253723145,
|
92 |
+
"learning_rate": 5.4761904761904766e-05,
|
93 |
+
"loss": 0.371,
|
94 |
+
"step": 24
|
95 |
+
},
|
96 |
+
{
|
97 |
+
"epoch": 0.0935672514619883,
|
98 |
+
"grad_norm": 0.14239338040351868,
|
99 |
+
"learning_rate": 5.9523809523809524e-05,
|
100 |
+
"loss": 0.381,
|
101 |
+
"step": 26
|
102 |
+
},
|
103 |
+
{
|
104 |
+
"epoch": 0.1007647323436797,
|
105 |
+
"grad_norm": 0.13879814743995667,
|
106 |
+
"learning_rate": 6.428571428571429e-05,
|
107 |
+
"loss": 0.3763,
|
108 |
+
"step": 28
|
109 |
+
},
|
110 |
+
{
|
111 |
+
"epoch": 0.10796221322537113,
|
112 |
+
"grad_norm": 0.08805831521749496,
|
113 |
+
"learning_rate": 6.904761904761905e-05,
|
114 |
+
"loss": 0.3619,
|
115 |
+
"step": 30
|
116 |
+
},
|
117 |
+
{
|
118 |
+
"epoch": 0.11515969410706253,
|
119 |
+
"grad_norm": 0.1161579117178917,
|
120 |
+
"learning_rate": 7.380952380952382e-05,
|
121 |
+
"loss": 0.3793,
|
122 |
+
"step": 32
|
123 |
+
},
|
124 |
+
{
|
125 |
+
"epoch": 0.12235717498875394,
|
126 |
+
"grad_norm": 0.09849085658788681,
|
127 |
+
"learning_rate": 7.857142857142858e-05,
|
128 |
+
"loss": 0.3728,
|
129 |
+
"step": 34
|
130 |
+
},
|
131 |
+
{
|
132 |
+
"epoch": 0.12955465587044535,
|
133 |
+
"grad_norm": 0.10439599305391312,
|
134 |
+
"learning_rate": 8.333333333333334e-05,
|
135 |
+
"loss": 0.3764,
|
136 |
+
"step": 36
|
137 |
+
},
|
138 |
+
{
|
139 |
+
"epoch": 0.13675213675213677,
|
140 |
+
"grad_norm": 0.10647670179605484,
|
141 |
+
"learning_rate": 8.80952380952381e-05,
|
142 |
+
"loss": 0.3663,
|
143 |
+
"step": 38
|
144 |
+
},
|
145 |
+
{
|
146 |
+
"epoch": 0.14394961763382816,
|
147 |
+
"grad_norm": 0.10219459235668182,
|
148 |
+
"learning_rate": 9.285714285714286e-05,
|
149 |
+
"loss": 0.4261,
|
150 |
+
"step": 40
|
151 |
+
},
|
152 |
+
{
|
153 |
+
"epoch": 0.15114709851551958,
|
154 |
+
"grad_norm": 0.10852818191051483,
|
155 |
+
"learning_rate": 9.761904761904762e-05,
|
156 |
+
"loss": 0.3476,
|
157 |
+
"step": 42
|
158 |
+
},
|
159 |
+
{
|
160 |
+
"epoch": 0.15834457939721097,
|
161 |
+
"grad_norm": 0.1352754682302475,
|
162 |
+
"learning_rate": 0.00010238095238095237,
|
163 |
+
"loss": 0.3655,
|
164 |
+
"step": 44
|
165 |
+
},
|
166 |
+
{
|
167 |
+
"epoch": 0.1655420602789024,
|
168 |
+
"grad_norm": 0.0873698815703392,
|
169 |
+
"learning_rate": 0.00010714285714285715,
|
170 |
+
"loss": 0.3598,
|
171 |
+
"step": 46
|
172 |
+
},
|
173 |
+
{
|
174 |
+
"epoch": 0.17273954116059378,
|
175 |
+
"grad_norm": 0.0955437570810318,
|
176 |
+
"learning_rate": 0.00011190476190476191,
|
177 |
+
"loss": 0.3548,
|
178 |
+
"step": 48
|
179 |
+
},
|
180 |
+
{
|
181 |
+
"epoch": 0.1799370220422852,
|
182 |
+
"grad_norm": 0.08287126570940018,
|
183 |
+
"learning_rate": 0.00011666666666666668,
|
184 |
+
"loss": 0.3675,
|
185 |
+
"step": 50
|
186 |
+
},
|
187 |
+
{
|
188 |
+
"epoch": 0.1871345029239766,
|
189 |
+
"grad_norm": 0.1574493646621704,
|
190 |
+
"learning_rate": 0.00012142857142857143,
|
191 |
+
"loss": 0.4667,
|
192 |
+
"step": 52
|
193 |
+
},
|
194 |
+
{
|
195 |
+
"epoch": 0.19433198380566802,
|
196 |
+
"grad_norm": 0.09171266108751297,
|
197 |
+
"learning_rate": 0.0001261904761904762,
|
198 |
+
"loss": 0.3979,
|
199 |
+
"step": 54
|
200 |
+
},
|
201 |
+
{
|
202 |
+
"epoch": 0.2015294646873594,
|
203 |
+
"grad_norm": 0.11109217256307602,
|
204 |
+
"learning_rate": 0.00013095238095238096,
|
205 |
+
"loss": 0.361,
|
206 |
+
"step": 56
|
207 |
+
},
|
208 |
+
{
|
209 |
+
"epoch": 0.20872694556905083,
|
210 |
+
"grad_norm": 0.09685403108596802,
|
211 |
+
"learning_rate": 0.00013571428571428572,
|
212 |
+
"loss": 0.3332,
|
213 |
+
"step": 58
|
214 |
+
},
|
215 |
+
{
|
216 |
+
"epoch": 0.21592442645074225,
|
217 |
+
"grad_norm": 0.11084886640310287,
|
218 |
+
"learning_rate": 0.00014047619047619049,
|
219 |
+
"loss": 0.3452,
|
220 |
+
"step": 60
|
221 |
+
},
|
222 |
+
{
|
223 |
+
"epoch": 0.22312190733243364,
|
224 |
+
"grad_norm": 0.08224218338727951,
|
225 |
+
"learning_rate": 0.00014523809523809525,
|
226 |
+
"loss": 0.3546,
|
227 |
+
"step": 62
|
228 |
+
},
|
229 |
+
{
|
230 |
+
"epoch": 0.23031938821412506,
|
231 |
+
"grad_norm": 0.0776989609003067,
|
232 |
+
"learning_rate": 0.00015000000000000001,
|
233 |
+
"loss": 0.359,
|
234 |
+
"step": 64
|
235 |
+
},
|
236 |
+
{
|
237 |
+
"epoch": 0.23751686909581646,
|
238 |
+
"grad_norm": 0.09840333461761475,
|
239 |
+
"learning_rate": 0.00015476190476190478,
|
240 |
+
"loss": 0.3468,
|
241 |
+
"step": 66
|
242 |
+
},
|
243 |
+
{
|
244 |
+
"epoch": 0.24471434997750788,
|
245 |
+
"grad_norm": 0.09042467176914215,
|
246 |
+
"learning_rate": 0.00015952380952380954,
|
247 |
+
"loss": 0.3495,
|
248 |
+
"step": 68
|
249 |
+
},
|
250 |
+
{
|
251 |
+
"epoch": 0.25191183085919927,
|
252 |
+
"grad_norm": 0.09852752834558487,
|
253 |
+
"learning_rate": 0.00016428571428571428,
|
254 |
+
"loss": 0.353,
|
255 |
+
"step": 70
|
256 |
+
},
|
257 |
+
{
|
258 |
+
"epoch": 0.2591093117408907,
|
259 |
+
"grad_norm": 0.08400912582874298,
|
260 |
+
"learning_rate": 0.00016904761904761904,
|
261 |
+
"loss": 0.3611,
|
262 |
+
"step": 72
|
263 |
+
},
|
264 |
+
{
|
265 |
+
"epoch": 0.2663067926225821,
|
266 |
+
"grad_norm": 0.07677467167377472,
|
267 |
+
"learning_rate": 0.00017380952380952383,
|
268 |
+
"loss": 0.3525,
|
269 |
+
"step": 74
|
270 |
+
},
|
271 |
+
{
|
272 |
+
"epoch": 0.27350427350427353,
|
273 |
+
"grad_norm": 0.07701747119426727,
|
274 |
+
"learning_rate": 0.0001785714285714286,
|
275 |
+
"loss": 0.3388,
|
276 |
+
"step": 76
|
277 |
+
},
|
278 |
+
{
|
279 |
+
"epoch": 0.2807017543859649,
|
280 |
+
"grad_norm": 0.09317085146903992,
|
281 |
+
"learning_rate": 0.00018333333333333334,
|
282 |
+
"loss": 0.3346,
|
283 |
+
"step": 78
|
284 |
+
},
|
285 |
+
{
|
286 |
+
"epoch": 0.2878992352676563,
|
287 |
+
"grad_norm": 0.08855720609426498,
|
288 |
+
"learning_rate": 0.0001880952380952381,
|
289 |
+
"loss": 0.3156,
|
290 |
+
"step": 80
|
291 |
+
},
|
292 |
+
{
|
293 |
+
"epoch": 0.29509671614934774,
|
294 |
+
"grad_norm": 0.0836637020111084,
|
295 |
+
"learning_rate": 0.00019285714285714286,
|
296 |
+
"loss": 0.3103,
|
297 |
+
"step": 82
|
298 |
+
},
|
299 |
+
{
|
300 |
+
"epoch": 0.30229419703103916,
|
301 |
+
"grad_norm": 0.09901738166809082,
|
302 |
+
"learning_rate": 0.00019761904761904763,
|
303 |
+
"loss": 0.3561,
|
304 |
+
"step": 84
|
305 |
+
},
|
306 |
+
{
|
307 |
+
"epoch": 0.3094916779127305,
|
308 |
+
"grad_norm": 0.09006400406360626,
|
309 |
+
"learning_rate": 0.0001997322623828648,
|
310 |
+
"loss": 0.3486,
|
311 |
+
"step": 86
|
312 |
+
},
|
313 |
+
{
|
314 |
+
"epoch": 0.31668915879442194,
|
315 |
+
"grad_norm": 0.08155179023742676,
|
316 |
+
"learning_rate": 0.0001991967871485944,
|
317 |
+
"loss": 0.3468,
|
318 |
+
"step": 88
|
319 |
+
},
|
320 |
+
{
|
321 |
+
"epoch": 0.32388663967611336,
|
322 |
+
"grad_norm": 0.08293768018484116,
|
323 |
+
"learning_rate": 0.00019866131191432397,
|
324 |
+
"loss": 0.3287,
|
325 |
+
"step": 90
|
326 |
+
},
|
327 |
+
{
|
328 |
+
"epoch": 0.3310841205578048,
|
329 |
+
"grad_norm": 0.09627004712820053,
|
330 |
+
"learning_rate": 0.00019812583668005356,
|
331 |
+
"loss": 0.3504,
|
332 |
+
"step": 92
|
333 |
+
},
|
334 |
+
{
|
335 |
+
"epoch": 0.33828160143949615,
|
336 |
+
"grad_norm": 0.09711097180843353,
|
337 |
+
"learning_rate": 0.00019759036144578314,
|
338 |
+
"loss": 0.3465,
|
339 |
+
"step": 94
|
340 |
+
},
|
341 |
+
{
|
342 |
+
"epoch": 0.34547908232118757,
|
343 |
+
"grad_norm": 0.07109538465738297,
|
344 |
+
"learning_rate": 0.00019705488621151273,
|
345 |
+
"loss": 0.3366,
|
346 |
+
"step": 96
|
347 |
+
},
|
348 |
+
{
|
349 |
+
"epoch": 0.352676563202879,
|
350 |
+
"grad_norm": 0.09591926634311676,
|
351 |
+
"learning_rate": 0.00019651941097724232,
|
352 |
+
"loss": 0.4935,
|
353 |
+
"step": 98
|
354 |
+
},
|
355 |
+
{
|
356 |
+
"epoch": 0.3598740440845704,
|
357 |
+
"grad_norm": 0.07593443989753723,
|
358 |
+
"learning_rate": 0.0001959839357429719,
|
359 |
+
"loss": 0.328,
|
360 |
+
"step": 100
|
361 |
+
},
|
362 |
+
{
|
363 |
+
"epoch": 0.36707152496626183,
|
364 |
+
"grad_norm": 0.08672759681940079,
|
365 |
+
"learning_rate": 0.0001954484605087015,
|
366 |
+
"loss": 0.3442,
|
367 |
+
"step": 102
|
368 |
+
},
|
369 |
+
{
|
370 |
+
"epoch": 0.3742690058479532,
|
371 |
+
"grad_norm": 0.08630123734474182,
|
372 |
+
"learning_rate": 0.00019491298527443107,
|
373 |
+
"loss": 0.3316,
|
374 |
+
"step": 104
|
375 |
+
},
|
376 |
+
{
|
377 |
+
"epoch": 0.3814664867296446,
|
378 |
+
"grad_norm": 0.08149603754281998,
|
379 |
+
"learning_rate": 0.00019437751004016066,
|
380 |
+
"loss": 0.3264,
|
381 |
+
"step": 106
|
382 |
+
},
|
383 |
+
{
|
384 |
+
"epoch": 0.38866396761133604,
|
385 |
+
"grad_norm": 0.08842544257640839,
|
386 |
+
"learning_rate": 0.00019384203480589022,
|
387 |
+
"loss": 0.3147,
|
388 |
+
"step": 108
|
389 |
+
},
|
390 |
+
{
|
391 |
+
"epoch": 0.39586144849302746,
|
392 |
+
"grad_norm": 0.07070264220237732,
|
393 |
+
"learning_rate": 0.00019330655957161983,
|
394 |
+
"loss": 0.3315,
|
395 |
+
"step": 110
|
396 |
+
},
|
397 |
+
{
|
398 |
+
"epoch": 0.4030589293747188,
|
399 |
+
"grad_norm": 0.07985159754753113,
|
400 |
+
"learning_rate": 0.00019277108433734942,
|
401 |
+
"loss": 0.3197,
|
402 |
+
"step": 112
|
403 |
+
},
|
404 |
+
{
|
405 |
+
"epoch": 0.41025641025641024,
|
406 |
+
"grad_norm": 0.09197162836790085,
|
407 |
+
"learning_rate": 0.00019223560910307897,
|
408 |
+
"loss": 0.3336,
|
409 |
+
"step": 114
|
410 |
+
},
|
411 |
+
{
|
412 |
+
"epoch": 0.41745389113810166,
|
413 |
+
"grad_norm": 0.08832088857889175,
|
414 |
+
"learning_rate": 0.0001917001338688086,
|
415 |
+
"loss": 0.352,
|
416 |
+
"step": 116
|
417 |
+
},
|
418 |
+
{
|
419 |
+
"epoch": 0.4246513720197931,
|
420 |
+
"grad_norm": 0.08948203176259995,
|
421 |
+
"learning_rate": 0.00019116465863453817,
|
422 |
+
"loss": 0.3297,
|
423 |
+
"step": 118
|
424 |
+
},
|
425 |
+
{
|
426 |
+
"epoch": 0.4318488529014845,
|
427 |
+
"grad_norm": 0.07525552809238434,
|
428 |
+
"learning_rate": 0.00019062918340026773,
|
429 |
+
"loss": 0.3175,
|
430 |
+
"step": 120
|
431 |
+
},
|
432 |
+
{
|
433 |
+
"epoch": 0.43904633378317587,
|
434 |
+
"grad_norm": 0.07528162747621536,
|
435 |
+
"learning_rate": 0.00019009370816599734,
|
436 |
+
"loss": 0.3371,
|
437 |
+
"step": 122
|
438 |
+
},
|
439 |
+
{
|
440 |
+
"epoch": 0.4462438146648673,
|
441 |
+
"grad_norm": 0.08338086307048798,
|
442 |
+
"learning_rate": 0.00018955823293172693,
|
443 |
+
"loss": 0.3413,
|
444 |
+
"step": 124
|
445 |
+
},
|
446 |
+
{
|
447 |
+
"epoch": 0.4534412955465587,
|
448 |
+
"grad_norm": 0.08500686287879944,
|
449 |
+
"learning_rate": 0.0001890227576974565,
|
450 |
+
"loss": 0.3473,
|
451 |
+
"step": 126
|
452 |
+
},
|
453 |
+
{
|
454 |
+
"epoch": 0.46063877642825013,
|
455 |
+
"grad_norm": 0.07290051877498627,
|
456 |
+
"learning_rate": 0.00018848728246318607,
|
457 |
+
"loss": 0.3271,
|
458 |
+
"step": 128
|
459 |
+
},
|
460 |
+
{
|
461 |
+
"epoch": 0.4678362573099415,
|
462 |
+
"grad_norm": 0.0794425904750824,
|
463 |
+
"learning_rate": 0.00018795180722891569,
|
464 |
+
"loss": 0.3291,
|
465 |
+
"step": 130
|
466 |
+
},
|
467 |
+
{
|
468 |
+
"epoch": 0.4750337381916329,
|
469 |
+
"grad_norm": 0.08603560924530029,
|
470 |
+
"learning_rate": 0.00018741633199464524,
|
471 |
+
"loss": 0.3237,
|
472 |
+
"step": 132
|
473 |
+
},
|
474 |
+
{
|
475 |
+
"epoch": 0.48223121907332434,
|
476 |
+
"grad_norm": 0.08800648152828217,
|
477 |
+
"learning_rate": 0.00018688085676037483,
|
478 |
+
"loss": 0.3264,
|
479 |
+
"step": 134
|
480 |
+
},
|
481 |
+
{
|
482 |
+
"epoch": 0.48942869995501576,
|
483 |
+
"grad_norm": 0.07836563140153885,
|
484 |
+
"learning_rate": 0.00018634538152610444,
|
485 |
+
"loss": 0.3267,
|
486 |
+
"step": 136
|
487 |
+
},
|
488 |
+
{
|
489 |
+
"epoch": 0.4966261808367072,
|
490 |
+
"grad_norm": 0.07838405668735504,
|
491 |
+
"learning_rate": 0.000185809906291834,
|
492 |
+
"loss": 0.3288,
|
493 |
+
"step": 138
|
494 |
+
},
|
495 |
+
{
|
496 |
+
"epoch": 0.5038236617183985,
|
497 |
+
"grad_norm": 0.08208189904689789,
|
498 |
+
"learning_rate": 0.0001852744310575636,
|
499 |
+
"loss": 0.3563,
|
500 |
+
"step": 140
|
501 |
+
},
|
502 |
+
{
|
503 |
+
"epoch": 0.51102114260009,
|
504 |
+
"grad_norm": 0.08661529421806335,
|
505 |
+
"learning_rate": 0.0001847389558232932,
|
506 |
+
"loss": 0.3271,
|
507 |
+
"step": 142
|
508 |
+
},
|
509 |
+
{
|
510 |
+
"epoch": 0.5182186234817814,
|
511 |
+
"grad_norm": 0.0783449113368988,
|
512 |
+
"learning_rate": 0.00018420348058902276,
|
513 |
+
"loss": 0.3342,
|
514 |
+
"step": 144
|
515 |
+
},
|
516 |
+
{
|
517 |
+
"epoch": 0.5254161043634727,
|
518 |
+
"grad_norm": 0.07989764213562012,
|
519 |
+
"learning_rate": 0.00018366800535475234,
|
520 |
+
"loss": 0.328,
|
521 |
+
"step": 146
|
522 |
+
},
|
523 |
+
{
|
524 |
+
"epoch": 0.5326135852451642,
|
525 |
+
"grad_norm": 0.06965967267751694,
|
526 |
+
"learning_rate": 0.00018313253012048193,
|
527 |
+
"loss": 0.3185,
|
528 |
+
"step": 148
|
529 |
+
},
|
530 |
+
{
|
531 |
+
"epoch": 0.5398110661268556,
|
532 |
+
"grad_norm": 0.07600811868906021,
|
533 |
+
"learning_rate": 0.00018259705488621152,
|
534 |
+
"loss": 0.3309,
|
535 |
+
"step": 150
|
536 |
+
},
|
537 |
+
{
|
538 |
+
"epoch": 0.5470085470085471,
|
539 |
+
"grad_norm": 0.07425697892904282,
|
540 |
+
"learning_rate": 0.0001820615796519411,
|
541 |
+
"loss": 0.3161,
|
542 |
+
"step": 152
|
543 |
+
},
|
544 |
+
{
|
545 |
+
"epoch": 0.5542060278902384,
|
546 |
+
"grad_norm": 0.08030654489994049,
|
547 |
+
"learning_rate": 0.0001815261044176707,
|
548 |
+
"loss": 0.3309,
|
549 |
+
"step": 154
|
550 |
+
},
|
551 |
+
{
|
552 |
+
"epoch": 0.5614035087719298,
|
553 |
+
"grad_norm": 0.09007160365581512,
|
554 |
+
"learning_rate": 0.00018099062918340027,
|
555 |
+
"loss": 0.3272,
|
556 |
+
"step": 156
|
557 |
+
},
|
558 |
+
{
|
559 |
+
"epoch": 0.5686009896536213,
|
560 |
+
"grad_norm": 0.08113101124763489,
|
561 |
+
"learning_rate": 0.00018045515394912986,
|
562 |
+
"loss": 0.3321,
|
563 |
+
"step": 158
|
564 |
+
},
|
565 |
+
{
|
566 |
+
"epoch": 0.5757984705353126,
|
567 |
+
"grad_norm": 0.08860523998737335,
|
568 |
+
"learning_rate": 0.00017991967871485944,
|
569 |
+
"loss": 0.3187,
|
570 |
+
"step": 160
|
571 |
+
},
|
572 |
+
{
|
573 |
+
"epoch": 0.582995951417004,
|
574 |
+
"grad_norm": 0.08832719177007675,
|
575 |
+
"learning_rate": 0.00017938420348058903,
|
576 |
+
"loss": 0.3521,
|
577 |
+
"step": 162
|
578 |
+
},
|
579 |
+
{
|
580 |
+
"epoch": 0.5901934322986955,
|
581 |
+
"grad_norm": 0.07766098529100418,
|
582 |
+
"learning_rate": 0.00017884872824631862,
|
583 |
+
"loss": 0.3436,
|
584 |
+
"step": 164
|
585 |
+
},
|
586 |
+
{
|
587 |
+
"epoch": 0.5973909131803868,
|
588 |
+
"grad_norm": 0.07725965231657028,
|
589 |
+
"learning_rate": 0.0001783132530120482,
|
590 |
+
"loss": 0.3073,
|
591 |
+
"step": 166
|
592 |
+
},
|
593 |
+
{
|
594 |
+
"epoch": 0.6045883940620783,
|
595 |
+
"grad_norm": 0.07833445817232132,
|
596 |
+
"learning_rate": 0.00017777777777777779,
|
597 |
+
"loss": 0.3114,
|
598 |
+
"step": 168
|
599 |
+
},
|
600 |
+
{
|
601 |
+
"epoch": 0.6117858749437697,
|
602 |
+
"grad_norm": 0.07358026504516602,
|
603 |
+
"learning_rate": 0.00017724230254350737,
|
604 |
+
"loss": 0.3352,
|
605 |
+
"step": 170
|
606 |
+
},
|
607 |
+
{
|
608 |
+
"epoch": 0.618983355825461,
|
609 |
+
"grad_norm": 0.07532913982868195,
|
610 |
+
"learning_rate": 0.00017670682730923696,
|
611 |
+
"loss": 0.3178,
|
612 |
+
"step": 172
|
613 |
+
},
|
614 |
+
{
|
615 |
+
"epoch": 0.6261808367071525,
|
616 |
+
"grad_norm": 0.07211969792842865,
|
617 |
+
"learning_rate": 0.00017617135207496654,
|
618 |
+
"loss": 0.3374,
|
619 |
+
"step": 174
|
620 |
+
},
|
621 |
+
{
|
622 |
+
"epoch": 0.6333783175888439,
|
623 |
+
"grad_norm": 0.08238798379898071,
|
624 |
+
"learning_rate": 0.00017563587684069613,
|
625 |
+
"loss": 0.3354,
|
626 |
+
"step": 176
|
627 |
+
},
|
628 |
+
{
|
629 |
+
"epoch": 0.6405757984705354,
|
630 |
+
"grad_norm": 0.07084181904792786,
|
631 |
+
"learning_rate": 0.00017510040160642571,
|
632 |
+
"loss": 0.3344,
|
633 |
+
"step": 178
|
634 |
+
},
|
635 |
+
{
|
636 |
+
"epoch": 0.6477732793522267,
|
637 |
+
"grad_norm": 0.08737006038427353,
|
638 |
+
"learning_rate": 0.0001745649263721553,
|
639 |
+
"loss": 0.3163,
|
640 |
+
"step": 180
|
641 |
+
},
|
642 |
+
{
|
643 |
+
"epoch": 0.6549707602339181,
|
644 |
+
"grad_norm": 0.08218367397785187,
|
645 |
+
"learning_rate": 0.00017402945113788489,
|
646 |
+
"loss": 0.3204,
|
647 |
+
"step": 182
|
648 |
+
},
|
649 |
+
{
|
650 |
+
"epoch": 0.6621682411156096,
|
651 |
+
"grad_norm": 0.08106492459774017,
|
652 |
+
"learning_rate": 0.00017349397590361447,
|
653 |
+
"loss": 0.327,
|
654 |
+
"step": 184
|
655 |
+
},
|
656 |
+
{
|
657 |
+
"epoch": 0.6693657219973009,
|
658 |
+
"grad_norm": 0.08296571671962738,
|
659 |
+
"learning_rate": 0.00017295850066934406,
|
660 |
+
"loss": 0.3344,
|
661 |
+
"step": 186
|
662 |
+
},
|
663 |
+
{
|
664 |
+
"epoch": 0.6765632028789923,
|
665 |
+
"grad_norm": 0.07554973661899567,
|
666 |
+
"learning_rate": 0.00017242302543507362,
|
667 |
+
"loss": 0.3222,
|
668 |
+
"step": 188
|
669 |
+
},
|
670 |
+
{
|
671 |
+
"epoch": 0.6837606837606838,
|
672 |
+
"grad_norm": 0.07743542641401291,
|
673 |
+
"learning_rate": 0.00017188755020080323,
|
674 |
+
"loss": 0.339,
|
675 |
+
"step": 190
|
676 |
+
},
|
677 |
+
{
|
678 |
+
"epoch": 0.6909581646423751,
|
679 |
+
"grad_norm": 0.0864499881863594,
|
680 |
+
"learning_rate": 0.00017135207496653281,
|
681 |
+
"loss": 0.3444,
|
682 |
+
"step": 192
|
683 |
+
},
|
684 |
+
{
|
685 |
+
"epoch": 0.6981556455240666,
|
686 |
+
"grad_norm": 0.08249206095933914,
|
687 |
+
"learning_rate": 0.00017081659973226237,
|
688 |
+
"loss": 0.3159,
|
689 |
+
"step": 194
|
690 |
+
},
|
691 |
+
{
|
692 |
+
"epoch": 0.705353126405758,
|
693 |
+
"grad_norm": 0.06611233204603195,
|
694 |
+
"learning_rate": 0.00017028112449799199,
|
695 |
+
"loss": 0.3209,
|
696 |
+
"step": 196
|
697 |
+
},
|
698 |
+
{
|
699 |
+
"epoch": 0.7125506072874493,
|
700 |
+
"grad_norm": 0.06984489411115646,
|
701 |
+
"learning_rate": 0.00016974564926372157,
|
702 |
+
"loss": 0.3273,
|
703 |
+
"step": 198
|
704 |
+
},
|
705 |
+
{
|
706 |
+
"epoch": 0.7197480881691408,
|
707 |
+
"grad_norm": 0.09003317356109619,
|
708 |
+
"learning_rate": 0.00016921017402945113,
|
709 |
+
"loss": 0.3432,
|
710 |
+
"step": 200
|
711 |
+
},
|
712 |
+
{
|
713 |
+
"epoch": 0.7269455690508322,
|
714 |
+
"grad_norm": 0.0860399454832077,
|
715 |
+
"learning_rate": 0.00016867469879518074,
|
716 |
+
"loss": 0.3391,
|
717 |
+
"step": 202
|
718 |
+
},
|
719 |
+
{
|
720 |
+
"epoch": 0.7341430499325237,
|
721 |
+
"grad_norm": 0.08255202323198318,
|
722 |
+
"learning_rate": 0.00016813922356091033,
|
723 |
+
"loss": 0.3424,
|
724 |
+
"step": 204
|
725 |
+
},
|
726 |
+
{
|
727 |
+
"epoch": 0.741340530814215,
|
728 |
+
"grad_norm": 0.07150615751743317,
|
729 |
+
"learning_rate": 0.00016760374832663989,
|
730 |
+
"loss": 0.3045,
|
731 |
+
"step": 206
|
732 |
+
},
|
733 |
+
{
|
734 |
+
"epoch": 0.7485380116959064,
|
735 |
+
"grad_norm": 0.08122894167900085,
|
736 |
+
"learning_rate": 0.00016706827309236947,
|
737 |
+
"loss": 0.3096,
|
738 |
+
"step": 208
|
739 |
+
},
|
740 |
+
{
|
741 |
+
"epoch": 0.7557354925775979,
|
742 |
+
"grad_norm": 0.0879962295293808,
|
743 |
+
"learning_rate": 0.00016653279785809908,
|
744 |
+
"loss": 0.3681,
|
745 |
+
"step": 210
|
746 |
+
},
|
747 |
+
{
|
748 |
+
"epoch": 0.7629329734592892,
|
749 |
+
"grad_norm": 0.09908217191696167,
|
750 |
+
"learning_rate": 0.00016599732262382864,
|
751 |
+
"loss": 0.315,
|
752 |
+
"step": 212
|
753 |
+
},
|
754 |
+
{
|
755 |
+
"epoch": 0.7701304543409807,
|
756 |
+
"grad_norm": 0.08676367998123169,
|
757 |
+
"learning_rate": 0.00016546184738955823,
|
758 |
+
"loss": 0.3265,
|
759 |
+
"step": 214
|
760 |
+
},
|
761 |
+
{
|
762 |
+
"epoch": 0.7773279352226721,
|
763 |
+
"grad_norm": 0.09469082951545715,
|
764 |
+
"learning_rate": 0.00016492637215528784,
|
765 |
+
"loss": 0.3133,
|
766 |
+
"step": 216
|
767 |
+
},
|
768 |
+
{
|
769 |
+
"epoch": 0.7845254161043634,
|
770 |
+
"grad_norm": 0.08231190592050552,
|
771 |
+
"learning_rate": 0.0001643908969210174,
|
772 |
+
"loss": 0.3309,
|
773 |
+
"step": 218
|
774 |
+
},
|
775 |
+
{
|
776 |
+
"epoch": 0.7917228969860549,
|
777 |
+
"grad_norm": 0.06851623952388763,
|
778 |
+
"learning_rate": 0.00016385542168674699,
|
779 |
+
"loss": 0.4886,
|
780 |
+
"step": 220
|
781 |
+
},
|
782 |
+
{
|
783 |
+
"epoch": 0.7989203778677463,
|
784 |
+
"grad_norm": 0.07207497954368591,
|
785 |
+
"learning_rate": 0.0001633199464524766,
|
786 |
+
"loss": 0.3192,
|
787 |
+
"step": 222
|
788 |
+
},
|
789 |
+
{
|
790 |
+
"epoch": 0.8061178587494376,
|
791 |
+
"grad_norm": 0.08718705177307129,
|
792 |
+
"learning_rate": 0.00016278447121820616,
|
793 |
+
"loss": 0.3386,
|
794 |
+
"step": 224
|
795 |
+
},
|
796 |
+
{
|
797 |
+
"epoch": 0.8133153396311291,
|
798 |
+
"grad_norm": 0.07431904226541519,
|
799 |
+
"learning_rate": 0.00016224899598393574,
|
800 |
+
"loss": 0.3248,
|
801 |
+
"step": 226
|
802 |
+
},
|
803 |
+
{
|
804 |
+
"epoch": 0.8205128205128205,
|
805 |
+
"grad_norm": 0.09158064424991608,
|
806 |
+
"learning_rate": 0.00016171352074966533,
|
807 |
+
"loss": 0.3031,
|
808 |
+
"step": 228
|
809 |
+
},
|
810 |
+
{
|
811 |
+
"epoch": 0.827710301394512,
|
812 |
+
"grad_norm": 0.0761372447013855,
|
813 |
+
"learning_rate": 0.00016117804551539491,
|
814 |
+
"loss": 0.3075,
|
815 |
+
"step": 230
|
816 |
+
},
|
817 |
+
{
|
818 |
+
"epoch": 0.8349077822762033,
|
819 |
+
"grad_norm": 0.08416109532117844,
|
820 |
+
"learning_rate": 0.0001606425702811245,
|
821 |
+
"loss": 0.3141,
|
822 |
+
"step": 232
|
823 |
+
},
|
824 |
+
{
|
825 |
+
"epoch": 0.8421052631578947,
|
826 |
+
"grad_norm": 0.08785945177078247,
|
827 |
+
"learning_rate": 0.00016010709504685409,
|
828 |
+
"loss": 0.3386,
|
829 |
+
"step": 234
|
830 |
+
},
|
831 |
+
{
|
832 |
+
"epoch": 0.8493027440395862,
|
833 |
+
"grad_norm": 0.06951107829809189,
|
834 |
+
"learning_rate": 0.00015957161981258367,
|
835 |
+
"loss": 0.321,
|
836 |
+
"step": 236
|
837 |
+
},
|
838 |
+
{
|
839 |
+
"epoch": 0.8565002249212775,
|
840 |
+
"grad_norm": 0.07590968906879425,
|
841 |
+
"learning_rate": 0.00015903614457831326,
|
842 |
+
"loss": 0.3252,
|
843 |
+
"step": 238
|
844 |
+
},
|
845 |
+
{
|
846 |
+
"epoch": 0.863697705802969,
|
847 |
+
"grad_norm": 0.07252885401248932,
|
848 |
+
"learning_rate": 0.00015850066934404284,
|
849 |
+
"loss": 0.3212,
|
850 |
+
"step": 240
|
851 |
+
},
|
852 |
+
{
|
853 |
+
"epoch": 0.8708951866846604,
|
854 |
+
"grad_norm": 0.08582789450883865,
|
855 |
+
"learning_rate": 0.00015796519410977243,
|
856 |
+
"loss": 0.3304,
|
857 |
+
"step": 242
|
858 |
+
},
|
859 |
+
{
|
860 |
+
"epoch": 0.8780926675663517,
|
861 |
+
"grad_norm": 0.07337023317813873,
|
862 |
+
"learning_rate": 0.000157429718875502,
|
863 |
+
"loss": 0.3503,
|
864 |
+
"step": 244
|
865 |
+
},
|
866 |
+
{
|
867 |
+
"epoch": 0.8852901484480432,
|
868 |
+
"grad_norm": 0.08561820536851883,
|
869 |
+
"learning_rate": 0.0001568942436412316,
|
870 |
+
"loss": 0.6188,
|
871 |
+
"step": 246
|
872 |
+
},
|
873 |
+
{
|
874 |
+
"epoch": 0.8924876293297346,
|
875 |
+
"grad_norm": 0.09793461859226227,
|
876 |
+
"learning_rate": 0.00015635876840696118,
|
877 |
+
"loss": 0.3325,
|
878 |
+
"step": 248
|
879 |
+
},
|
880 |
+
{
|
881 |
+
"epoch": 0.899685110211426,
|
882 |
+
"grad_norm": 0.07272443920373917,
|
883 |
+
"learning_rate": 0.00015582329317269077,
|
884 |
+
"loss": 0.3389,
|
885 |
+
"step": 250
|
886 |
+
},
|
887 |
+
{
|
888 |
+
"epoch": 0.9068825910931174,
|
889 |
+
"grad_norm": 0.08381237089633942,
|
890 |
+
"learning_rate": 0.00015528781793842036,
|
891 |
+
"loss": 0.3229,
|
892 |
+
"step": 252
|
893 |
+
},
|
894 |
+
{
|
895 |
+
"epoch": 0.9140800719748088,
|
896 |
+
"grad_norm": 0.08167573809623718,
|
897 |
+
"learning_rate": 0.00015475234270414994,
|
898 |
+
"loss": 0.326,
|
899 |
+
"step": 254
|
900 |
+
},
|
901 |
+
{
|
902 |
+
"epoch": 0.9212775528565003,
|
903 |
+
"grad_norm": 0.09698246419429779,
|
904 |
+
"learning_rate": 0.00015421686746987953,
|
905 |
+
"loss": 0.3344,
|
906 |
+
"step": 256
|
907 |
+
},
|
908 |
+
{
|
909 |
+
"epoch": 0.9284750337381916,
|
910 |
+
"grad_norm": 0.08641395717859268,
|
911 |
+
"learning_rate": 0.0001536813922356091,
|
912 |
+
"loss": 0.3244,
|
913 |
+
"step": 258
|
914 |
+
},
|
915 |
+
{
|
916 |
+
"epoch": 0.935672514619883,
|
917 |
+
"grad_norm": 0.085604727268219,
|
918 |
+
"learning_rate": 0.0001531459170013387,
|
919 |
+
"loss": 0.3251,
|
920 |
+
"step": 260
|
921 |
+
},
|
922 |
+
{
|
923 |
+
"epoch": 0.9428699955015745,
|
924 |
+
"grad_norm": 0.08560743182897568,
|
925 |
+
"learning_rate": 0.00015261044176706828,
|
926 |
+
"loss": 0.2974,
|
927 |
+
"step": 262
|
928 |
+
},
|
929 |
+
{
|
930 |
+
"epoch": 0.9500674763832658,
|
931 |
+
"grad_norm": 0.07273954898118973,
|
932 |
+
"learning_rate": 0.00015207496653279787,
|
933 |
+
"loss": 0.3284,
|
934 |
+
"step": 264
|
935 |
+
},
|
936 |
+
{
|
937 |
+
"epoch": 0.9572649572649573,
|
938 |
+
"grad_norm": 0.06591767072677612,
|
939 |
+
"learning_rate": 0.00015153949129852746,
|
940 |
+
"loss": 0.3293,
|
941 |
+
"step": 266
|
942 |
+
},
|
943 |
+
{
|
944 |
+
"epoch": 0.9644624381466487,
|
945 |
+
"grad_norm": 0.08961295336484909,
|
946 |
+
"learning_rate": 0.00015100401606425701,
|
947 |
+
"loss": 0.3524,
|
948 |
+
"step": 268
|
949 |
+
},
|
950 |
+
{
|
951 |
+
"epoch": 0.97165991902834,
|
952 |
+
"grad_norm": 0.08635508269071579,
|
953 |
+
"learning_rate": 0.00015046854082998663,
|
954 |
+
"loss": 0.3274,
|
955 |
+
"step": 270
|
956 |
+
},
|
957 |
+
{
|
958 |
+
"epoch": 0.9788573999100315,
|
959 |
+
"grad_norm": 0.08155159652233124,
|
960 |
+
"learning_rate": 0.0001499330655957162,
|
961 |
+
"loss": 0.3327,
|
962 |
+
"step": 272
|
963 |
+
},
|
964 |
+
{
|
965 |
+
"epoch": 0.9860548807917229,
|
966 |
+
"grad_norm": 0.10817470401525497,
|
967 |
+
"learning_rate": 0.00014939759036144577,
|
968 |
+
"loss": 0.303,
|
969 |
+
"step": 274
|
970 |
+
},
|
971 |
+
{
|
972 |
+
"epoch": 0.9932523616734144,
|
973 |
+
"grad_norm": 0.09444508701562881,
|
974 |
+
"learning_rate": 0.00014886211512717538,
|
975 |
+
"loss": 0.3276,
|
976 |
+
"step": 276
|
977 |
+
},
|
978 |
+
{
|
979 |
+
"epoch": 1.0035987404408457,
|
980 |
+
"grad_norm": 0.13199453055858612,
|
981 |
+
"learning_rate": 0.00014832663989290497,
|
982 |
+
"loss": 0.4554,
|
983 |
+
"step": 278
|
984 |
+
},
|
985 |
+
{
|
986 |
+
"epoch": 1.0107962213225372,
|
987 |
+
"grad_norm": 0.08432269096374512,
|
988 |
+
"learning_rate": 0.00014779116465863453,
|
989 |
+
"loss": 0.2906,
|
990 |
+
"step": 280
|
991 |
+
},
|
992 |
+
{
|
993 |
+
"epoch": 1.0179937022042285,
|
994 |
+
"grad_norm": 0.07900276780128479,
|
995 |
+
"learning_rate": 0.00014725568942436414,
|
996 |
+
"loss": 0.2902,
|
997 |
+
"step": 282
|
998 |
+
},
|
999 |
+
{
|
1000 |
+
"epoch": 1.02519118308592,
|
1001 |
+
"grad_norm": 0.09046148508787155,
|
1002 |
+
"learning_rate": 0.00014672021419009373,
|
1003 |
+
"loss": 0.282,
|
1004 |
+
"step": 284
|
1005 |
+
},
|
1006 |
+
{
|
1007 |
+
"epoch": 1.0323886639676114,
|
1008 |
+
"grad_norm": 0.0738753154873848,
|
1009 |
+
"learning_rate": 0.00014618473895582328,
|
1010 |
+
"loss": 0.2867,
|
1011 |
+
"step": 286
|
1012 |
+
},
|
1013 |
+
{
|
1014 |
+
"epoch": 1.0395861448493027,
|
1015 |
+
"grad_norm": 0.07705972343683243,
|
1016 |
+
"learning_rate": 0.00014564926372155287,
|
1017 |
+
"loss": 0.3072,
|
1018 |
+
"step": 288
|
1019 |
+
},
|
1020 |
+
{
|
1021 |
+
"epoch": 1.0467836257309941,
|
1022 |
+
"grad_norm": 0.10410559922456741,
|
1023 |
+
"learning_rate": 0.00014511378848728248,
|
1024 |
+
"loss": 0.293,
|
1025 |
+
"step": 290
|
1026 |
+
},
|
1027 |
+
{
|
1028 |
+
"epoch": 1.0539811066126856,
|
1029 |
+
"grad_norm": 0.08596571534872055,
|
1030 |
+
"learning_rate": 0.00014457831325301204,
|
1031 |
+
"loss": 0.2816,
|
1032 |
+
"step": 292
|
1033 |
+
},
|
1034 |
+
{
|
1035 |
+
"epoch": 1.0611785874943769,
|
1036 |
+
"grad_norm": 0.08276987075805664,
|
1037 |
+
"learning_rate": 0.00014404283801874163,
|
1038 |
+
"loss": 0.2921,
|
1039 |
+
"step": 294
|
1040 |
+
},
|
1041 |
+
{
|
1042 |
+
"epoch": 1.0683760683760684,
|
1043 |
+
"grad_norm": 0.07834933698177338,
|
1044 |
+
"learning_rate": 0.00014350736278447124,
|
1045 |
+
"loss": 0.2815,
|
1046 |
+
"step": 296
|
1047 |
+
},
|
1048 |
+
{
|
1049 |
+
"epoch": 1.0755735492577598,
|
1050 |
+
"grad_norm": 0.08302914351224899,
|
1051 |
+
"learning_rate": 0.0001429718875502008,
|
1052 |
+
"loss": 0.2897,
|
1053 |
+
"step": 298
|
1054 |
+
},
|
1055 |
+
{
|
1056 |
+
"epoch": 1.082771030139451,
|
1057 |
+
"grad_norm": 0.08388438820838928,
|
1058 |
+
"learning_rate": 0.00014243641231593038,
|
1059 |
+
"loss": 0.2756,
|
1060 |
+
"step": 300
|
1061 |
+
},
|
1062 |
+
{
|
1063 |
+
"epoch": 1.0899685110211426,
|
1064 |
+
"grad_norm": 0.08975379914045334,
|
1065 |
+
"learning_rate": 0.00014190093708166,
|
1066 |
+
"loss": 0.3026,
|
1067 |
+
"step": 302
|
1068 |
+
},
|
1069 |
+
{
|
1070 |
+
"epoch": 1.097165991902834,
|
1071 |
+
"grad_norm": 0.09952361136674881,
|
1072 |
+
"learning_rate": 0.00014136546184738956,
|
1073 |
+
"loss": 0.2906,
|
1074 |
+
"step": 304
|
1075 |
+
},
|
1076 |
+
{
|
1077 |
+
"epoch": 1.1043634727845255,
|
1078 |
+
"grad_norm": 0.0946754440665245,
|
1079 |
+
"learning_rate": 0.00014082998661311914,
|
1080 |
+
"loss": 0.2795,
|
1081 |
+
"step": 306
|
1082 |
+
},
|
1083 |
+
{
|
1084 |
+
"epoch": 1.1115609536662168,
|
1085 |
+
"grad_norm": 0.10857745260000229,
|
1086 |
+
"learning_rate": 0.00014029451137884873,
|
1087 |
+
"loss": 0.3088,
|
1088 |
+
"step": 308
|
1089 |
+
},
|
1090 |
+
{
|
1091 |
+
"epoch": 1.1187584345479082,
|
1092 |
+
"grad_norm": 0.08599863946437836,
|
1093 |
+
"learning_rate": 0.00013975903614457834,
|
1094 |
+
"loss": 0.2841,
|
1095 |
+
"step": 310
|
1096 |
+
},
|
1097 |
+
{
|
1098 |
+
"epoch": 1.1259559154295997,
|
1099 |
+
"grad_norm": 2.8567867279052734,
|
1100 |
+
"learning_rate": 0.0001392235609103079,
|
1101 |
+
"loss": 0.6751,
|
1102 |
+
"step": 312
|
1103 |
+
},
|
1104 |
+
{
|
1105 |
+
"epoch": 1.133153396311291,
|
1106 |
+
"grad_norm": 0.09657253324985504,
|
1107 |
+
"learning_rate": 0.00013868808567603748,
|
1108 |
+
"loss": 0.3061,
|
1109 |
+
"step": 314
|
1110 |
+
},
|
1111 |
+
{
|
1112 |
+
"epoch": 1.1403508771929824,
|
1113 |
+
"grad_norm": 0.10296836495399475,
|
1114 |
+
"learning_rate": 0.0001381526104417671,
|
1115 |
+
"loss": 0.2934,
|
1116 |
+
"step": 316
|
1117 |
+
},
|
1118 |
+
{
|
1119 |
+
"epoch": 1.147548358074674,
|
1120 |
+
"grad_norm": 0.10470768064260483,
|
1121 |
+
"learning_rate": 0.00013761713520749665,
|
1122 |
+
"loss": 0.31,
|
1123 |
+
"step": 318
|
1124 |
+
},
|
1125 |
+
{
|
1126 |
+
"epoch": 1.1547458389563652,
|
1127 |
+
"grad_norm": 0.08361463993787766,
|
1128 |
+
"learning_rate": 0.00013708165997322624,
|
1129 |
+
"loss": 0.3066,
|
1130 |
+
"step": 320
|
1131 |
+
},
|
1132 |
+
{
|
1133 |
+
"epoch": 1.1619433198380567,
|
1134 |
+
"grad_norm": 0.09037966281175613,
|
1135 |
+
"learning_rate": 0.00013654618473895585,
|
1136 |
+
"loss": 0.2839,
|
1137 |
+
"step": 322
|
1138 |
+
},
|
1139 |
+
{
|
1140 |
+
"epoch": 1.1691408007197481,
|
1141 |
+
"grad_norm": 0.09697765856981277,
|
1142 |
+
"learning_rate": 0.0001360107095046854,
|
1143 |
+
"loss": 0.2901,
|
1144 |
+
"step": 324
|
1145 |
+
},
|
1146 |
+
{
|
1147 |
+
"epoch": 1.1763382816014394,
|
1148 |
+
"grad_norm": 0.10401667654514313,
|
1149 |
+
"learning_rate": 0.000135475234270415,
|
1150 |
+
"loss": 0.2968,
|
1151 |
+
"step": 326
|
1152 |
+
},
|
1153 |
+
{
|
1154 |
+
"epoch": 1.1835357624831309,
|
1155 |
+
"grad_norm": 0.08152046799659729,
|
1156 |
+
"learning_rate": 0.00013493975903614458,
|
1157 |
+
"loss": 0.2984,
|
1158 |
+
"step": 328
|
1159 |
+
},
|
1160 |
+
{
|
1161 |
+
"epoch": 1.1907332433648223,
|
1162 |
+
"grad_norm": 0.096259206533432,
|
1163 |
+
"learning_rate": 0.00013440428380187417,
|
1164 |
+
"loss": 0.311,
|
1165 |
+
"step": 330
|
1166 |
+
},
|
1167 |
+
{
|
1168 |
+
"epoch": 1.1979307242465138,
|
1169 |
+
"grad_norm": 0.10856079310178757,
|
1170 |
+
"learning_rate": 0.00013386880856760375,
|
1171 |
+
"loss": 0.308,
|
1172 |
+
"step": 332
|
1173 |
+
},
|
1174 |
+
{
|
1175 |
+
"epoch": 1.205128205128205,
|
1176 |
+
"grad_norm": 0.08968297392129898,
|
1177 |
+
"learning_rate": 0.00013333333333333334,
|
1178 |
+
"loss": 0.2946,
|
1179 |
+
"step": 334
|
1180 |
+
},
|
1181 |
+
{
|
1182 |
+
"epoch": 1.2123256860098965,
|
1183 |
+
"grad_norm": 0.09199783951044083,
|
1184 |
+
"learning_rate": 0.00013279785809906293,
|
1185 |
+
"loss": 0.3172,
|
1186 |
+
"step": 336
|
1187 |
+
},
|
1188 |
+
{
|
1189 |
+
"epoch": 1.219523166891588,
|
1190 |
+
"grad_norm": 0.08464746922254562,
|
1191 |
+
"learning_rate": 0.0001322623828647925,
|
1192 |
+
"loss": 0.2717,
|
1193 |
+
"step": 338
|
1194 |
+
},
|
1195 |
+
{
|
1196 |
+
"epoch": 1.2267206477732793,
|
1197 |
+
"grad_norm": 0.10605645179748535,
|
1198 |
+
"learning_rate": 0.0001317269076305221,
|
1199 |
+
"loss": 0.3192,
|
1200 |
+
"step": 340
|
1201 |
+
},
|
1202 |
+
{
|
1203 |
+
"epoch": 1.2339181286549707,
|
1204 |
+
"grad_norm": 0.10637731105089188,
|
1205 |
+
"learning_rate": 0.00013119143239625168,
|
1206 |
+
"loss": 0.3004,
|
1207 |
+
"step": 342
|
1208 |
+
},
|
1209 |
+
{
|
1210 |
+
"epoch": 1.2411156095366622,
|
1211 |
+
"grad_norm": 0.10228827595710754,
|
1212 |
+
"learning_rate": 0.00013065595716198127,
|
1213 |
+
"loss": 0.2856,
|
1214 |
+
"step": 344
|
1215 |
+
},
|
1216 |
+
{
|
1217 |
+
"epoch": 1.2483130904183537,
|
1218 |
+
"grad_norm": 0.10706611722707748,
|
1219 |
+
"learning_rate": 0.00013012048192771085,
|
1220 |
+
"loss": 0.3062,
|
1221 |
+
"step": 346
|
1222 |
+
},
|
1223 |
+
{
|
1224 |
+
"epoch": 1.255510571300045,
|
1225 |
+
"grad_norm": 0.07844937592744827,
|
1226 |
+
"learning_rate": 0.0001295850066934404,
|
1227 |
+
"loss": 0.266,
|
1228 |
+
"step": 348
|
1229 |
+
},
|
1230 |
+
{
|
1231 |
+
"epoch": 1.2627080521817364,
|
1232 |
+
"grad_norm": 0.1091390922665596,
|
1233 |
+
"learning_rate": 0.00012904953145917002,
|
1234 |
+
"loss": 0.3,
|
1235 |
+
"step": 350
|
1236 |
+
},
|
1237 |
+
{
|
1238 |
+
"epoch": 1.2699055330634277,
|
1239 |
+
"grad_norm": 0.0894734114408493,
|
1240 |
+
"learning_rate": 0.0001285140562248996,
|
1241 |
+
"loss": 0.3039,
|
1242 |
+
"step": 352
|
1243 |
+
},
|
1244 |
+
{
|
1245 |
+
"epoch": 1.2771030139451192,
|
1246 |
+
"grad_norm": 0.08384036272764206,
|
1247 |
+
"learning_rate": 0.00012797858099062917,
|
1248 |
+
"loss": 0.3066,
|
1249 |
+
"step": 354
|
1250 |
+
},
|
1251 |
+
{
|
1252 |
+
"epoch": 1.2843004948268106,
|
1253 |
+
"grad_norm": 0.09407312422990799,
|
1254 |
+
"learning_rate": 0.00012744310575635878,
|
1255 |
+
"loss": 0.2751,
|
1256 |
+
"step": 356
|
1257 |
+
},
|
1258 |
+
{
|
1259 |
+
"epoch": 1.291497975708502,
|
1260 |
+
"grad_norm": 0.1107960194349289,
|
1261 |
+
"learning_rate": 0.00012690763052208837,
|
1262 |
+
"loss": 0.3054,
|
1263 |
+
"step": 358
|
1264 |
+
},
|
1265 |
+
{
|
1266 |
+
"epoch": 1.2986954565901934,
|
1267 |
+
"grad_norm": 0.10553433001041412,
|
1268 |
+
"learning_rate": 0.00012637215528781793,
|
1269 |
+
"loss": 0.3039,
|
1270 |
+
"step": 360
|
1271 |
+
},
|
1272 |
+
{
|
1273 |
+
"epoch": 1.3058929374718848,
|
1274 |
+
"grad_norm": 0.09584353119134903,
|
1275 |
+
"learning_rate": 0.00012583668005354754,
|
1276 |
+
"loss": 0.3016,
|
1277 |
+
"step": 362
|
1278 |
+
},
|
1279 |
+
{
|
1280 |
+
"epoch": 1.3130904183535763,
|
1281 |
+
"grad_norm": 0.08024152368307114,
|
1282 |
+
"learning_rate": 0.00012530120481927712,
|
1283 |
+
"loss": 0.2915,
|
1284 |
+
"step": 364
|
1285 |
+
},
|
1286 |
+
{
|
1287 |
+
"epoch": 1.3202878992352676,
|
1288 |
+
"grad_norm": 0.07824230939149857,
|
1289 |
+
"learning_rate": 0.0001247657295850067,
|
1290 |
+
"loss": 0.2938,
|
1291 |
+
"step": 366
|
1292 |
+
},
|
1293 |
+
{
|
1294 |
+
"epoch": 1.327485380116959,
|
1295 |
+
"grad_norm": 0.10034101456403732,
|
1296 |
+
"learning_rate": 0.00012423025435073627,
|
1297 |
+
"loss": 0.2987,
|
1298 |
+
"step": 368
|
1299 |
+
},
|
1300 |
+
{
|
1301 |
+
"epoch": 1.3346828609986505,
|
1302 |
+
"grad_norm": 0.10064958781003952,
|
1303 |
+
"learning_rate": 0.00012369477911646588,
|
1304 |
+
"loss": 0.303,
|
1305 |
+
"step": 370
|
1306 |
+
},
|
1307 |
+
{
|
1308 |
+
"epoch": 1.341880341880342,
|
1309 |
+
"grad_norm": 0.10911820828914642,
|
1310 |
+
"learning_rate": 0.00012315930388219547,
|
1311 |
+
"loss": 0.2891,
|
1312 |
+
"step": 372
|
1313 |
+
},
|
1314 |
+
{
|
1315 |
+
"epoch": 1.3490778227620333,
|
1316 |
+
"grad_norm": 0.09767185896635056,
|
1317 |
+
"learning_rate": 0.00012262382864792503,
|
1318 |
+
"loss": 0.311,
|
1319 |
+
"step": 374
|
1320 |
+
},
|
1321 |
+
{
|
1322 |
+
"epoch": 1.3562753036437247,
|
1323 |
+
"grad_norm": 0.09713630378246307,
|
1324 |
+
"learning_rate": 0.00012208835341365464,
|
1325 |
+
"loss": 0.3032,
|
1326 |
+
"step": 376
|
1327 |
+
},
|
1328 |
+
{
|
1329 |
+
"epoch": 1.363472784525416,
|
1330 |
+
"grad_norm": 0.10266932100057602,
|
1331 |
+
"learning_rate": 0.00012155287817938421,
|
1332 |
+
"loss": 0.2892,
|
1333 |
+
"step": 378
|
1334 |
+
},
|
1335 |
+
{
|
1336 |
+
"epoch": 1.3706702654071075,
|
1337 |
+
"grad_norm": 0.09847443550825119,
|
1338 |
+
"learning_rate": 0.0001210174029451138,
|
1339 |
+
"loss": 0.276,
|
1340 |
+
"step": 380
|
1341 |
+
},
|
1342 |
+
{
|
1343 |
+
"epoch": 1.377867746288799,
|
1344 |
+
"grad_norm": 0.09444069117307663,
|
1345 |
+
"learning_rate": 0.0001204819277108434,
|
1346 |
+
"loss": 0.2947,
|
1347 |
+
"step": 382
|
1348 |
+
},
|
1349 |
+
{
|
1350 |
+
"epoch": 1.3850652271704904,
|
1351 |
+
"grad_norm": 0.0944535955786705,
|
1352 |
+
"learning_rate": 0.00011994645247657297,
|
1353 |
+
"loss": 0.3079,
|
1354 |
+
"step": 384
|
1355 |
+
},
|
1356 |
+
{
|
1357 |
+
"epoch": 1.3922627080521817,
|
1358 |
+
"grad_norm": 0.093000128865242,
|
1359 |
+
"learning_rate": 0.00011941097724230255,
|
1360 |
+
"loss": 0.2724,
|
1361 |
+
"step": 386
|
1362 |
+
},
|
1363 |
+
{
|
1364 |
+
"epoch": 1.3994601889338731,
|
1365 |
+
"grad_norm": 0.09892039000988007,
|
1366 |
+
"learning_rate": 0.00011887550200803212,
|
1367 |
+
"loss": 0.2952,
|
1368 |
+
"step": 388
|
1369 |
+
},
|
1370 |
+
{
|
1371 |
+
"epoch": 1.4066576698155646,
|
1372 |
+
"grad_norm": 0.08851997554302216,
|
1373 |
+
"learning_rate": 0.00011834002677376172,
|
1374 |
+
"loss": 0.3031,
|
1375 |
+
"step": 390
|
1376 |
+
},
|
1377 |
+
{
|
1378 |
+
"epoch": 1.4138551506972559,
|
1379 |
+
"grad_norm": 0.08816903084516525,
|
1380 |
+
"learning_rate": 0.00011780455153949131,
|
1381 |
+
"loss": 0.2865,
|
1382 |
+
"step": 392
|
1383 |
+
},
|
1384 |
+
{
|
1385 |
+
"epoch": 1.4210526315789473,
|
1386 |
+
"grad_norm": 0.09311983734369278,
|
1387 |
+
"learning_rate": 0.00011726907630522088,
|
1388 |
+
"loss": 0.2935,
|
1389 |
+
"step": 394
|
1390 |
+
},
|
1391 |
+
{
|
1392 |
+
"epoch": 1.4282501124606388,
|
1393 |
+
"grad_norm": 0.09623560309410095,
|
1394 |
+
"learning_rate": 0.00011673360107095048,
|
1395 |
+
"loss": 0.3098,
|
1396 |
+
"step": 396
|
1397 |
+
},
|
1398 |
+
{
|
1399 |
+
"epoch": 1.4354475933423303,
|
1400 |
+
"grad_norm": 0.09442677348852158,
|
1401 |
+
"learning_rate": 0.00011619812583668007,
|
1402 |
+
"loss": 0.387,
|
1403 |
+
"step": 398
|
1404 |
+
},
|
1405 |
+
{
|
1406 |
+
"epoch": 1.4426450742240216,
|
1407 |
+
"grad_norm": 0.10945068299770355,
|
1408 |
+
"learning_rate": 0.00011566265060240964,
|
1409 |
+
"loss": 0.2979,
|
1410 |
+
"step": 400
|
1411 |
+
},
|
1412 |
+
{
|
1413 |
+
"epoch": 1.449842555105713,
|
1414 |
+
"grad_norm": 0.10483969748020172,
|
1415 |
+
"learning_rate": 0.00011512717536813924,
|
1416 |
+
"loss": 0.2908,
|
1417 |
+
"step": 402
|
1418 |
+
},
|
1419 |
+
{
|
1420 |
+
"epoch": 1.4570400359874043,
|
1421 |
+
"grad_norm": 0.10481242835521698,
|
1422 |
+
"learning_rate": 0.00011459170013386882,
|
1423 |
+
"loss": 0.3097,
|
1424 |
+
"step": 404
|
1425 |
+
},
|
1426 |
+
{
|
1427 |
+
"epoch": 1.4642375168690958,
|
1428 |
+
"grad_norm": 0.1191711500287056,
|
1429 |
+
"learning_rate": 0.0001140562248995984,
|
1430 |
+
"loss": 0.2912,
|
1431 |
+
"step": 406
|
1432 |
+
},
|
1433 |
+
{
|
1434 |
+
"epoch": 1.4714349977507872,
|
1435 |
+
"grad_norm": 0.09692753851413727,
|
1436 |
+
"learning_rate": 0.00011352074966532798,
|
1437 |
+
"loss": 0.3035,
|
1438 |
+
"step": 408
|
1439 |
+
},
|
1440 |
+
{
|
1441 |
+
"epoch": 1.4786324786324787,
|
1442 |
+
"grad_norm": 0.0871867686510086,
|
1443 |
+
"learning_rate": 0.00011298527443105758,
|
1444 |
+
"loss": 0.291,
|
1445 |
+
"step": 410
|
1446 |
+
},
|
1447 |
+
{
|
1448 |
+
"epoch": 1.48582995951417,
|
1449 |
+
"grad_norm": 0.10090082138776779,
|
1450 |
+
"learning_rate": 0.00011244979919678715,
|
1451 |
+
"loss": 0.2915,
|
1452 |
+
"step": 412
|
1453 |
+
},
|
1454 |
+
{
|
1455 |
+
"epoch": 1.4930274403958614,
|
1456 |
+
"grad_norm": 0.1211143434047699,
|
1457 |
+
"learning_rate": 0.00011191432396251674,
|
1458 |
+
"loss": 0.3121,
|
1459 |
+
"step": 414
|
1460 |
+
},
|
1461 |
+
{
|
1462 |
+
"epoch": 1.5002249212775527,
|
1463 |
+
"grad_norm": 0.09828200936317444,
|
1464 |
+
"learning_rate": 0.00011137884872824634,
|
1465 |
+
"loss": 0.3061,
|
1466 |
+
"step": 416
|
1467 |
+
},
|
1468 |
+
{
|
1469 |
+
"epoch": 1.5074224021592442,
|
1470 |
+
"grad_norm": 0.08047261089086533,
|
1471 |
+
"learning_rate": 0.00011084337349397591,
|
1472 |
+
"loss": 0.2757,
|
1473 |
+
"step": 418
|
1474 |
+
},
|
1475 |
+
{
|
1476 |
+
"epoch": 1.5146198830409356,
|
1477 |
+
"grad_norm": 0.10605444014072418,
|
1478 |
+
"learning_rate": 0.0001103078982597055,
|
1479 |
+
"loss": 0.2875,
|
1480 |
+
"step": 420
|
1481 |
+
},
|
1482 |
+
{
|
1483 |
+
"epoch": 1.5218173639226271,
|
1484 |
+
"grad_norm": 0.11116360872983932,
|
1485 |
+
"learning_rate": 0.0001097724230254351,
|
1486 |
+
"loss": 0.2841,
|
1487 |
+
"step": 422
|
1488 |
+
},
|
1489 |
+
{
|
1490 |
+
"epoch": 1.5290148448043186,
|
1491 |
+
"grad_norm": 0.11266501247882843,
|
1492 |
+
"learning_rate": 0.00010923694779116467,
|
1493 |
+
"loss": 0.2838,
|
1494 |
+
"step": 424
|
1495 |
+
},
|
1496 |
+
{
|
1497 |
+
"epoch": 1.5362123256860098,
|
1498 |
+
"grad_norm": 0.1050829365849495,
|
1499 |
+
"learning_rate": 0.00010870147255689425,
|
1500 |
+
"loss": 0.319,
|
1501 |
+
"step": 426
|
1502 |
+
},
|
1503 |
+
{
|
1504 |
+
"epoch": 1.5434098065677013,
|
1505 |
+
"grad_norm": 0.10433949530124664,
|
1506 |
+
"learning_rate": 0.00010816599732262382,
|
1507 |
+
"loss": 0.3035,
|
1508 |
+
"step": 428
|
1509 |
+
},
|
1510 |
+
{
|
1511 |
+
"epoch": 1.5506072874493926,
|
1512 |
+
"grad_norm": 0.087762251496315,
|
1513 |
+
"learning_rate": 0.00010763052208835342,
|
1514 |
+
"loss": 0.2726,
|
1515 |
+
"step": 430
|
1516 |
+
},
|
1517 |
+
{
|
1518 |
+
"epoch": 1.557804768331084,
|
1519 |
+
"grad_norm": 0.11899640411138535,
|
1520 |
+
"learning_rate": 0.00010709504685408301,
|
1521 |
+
"loss": 0.2943,
|
1522 |
+
"step": 432
|
1523 |
+
},
|
1524 |
+
{
|
1525 |
+
"epoch": 1.5650022492127755,
|
1526 |
+
"grad_norm": 0.11921849101781845,
|
1527 |
+
"learning_rate": 0.00010655957161981258,
|
1528 |
+
"loss": 0.2998,
|
1529 |
+
"step": 434
|
1530 |
+
},
|
1531 |
+
{
|
1532 |
+
"epoch": 1.572199730094467,
|
1533 |
+
"grad_norm": 0.08324792236089706,
|
1534 |
+
"learning_rate": 0.00010602409638554218,
|
1535 |
+
"loss": 0.2844,
|
1536 |
+
"step": 436
|
1537 |
+
},
|
1538 |
+
{
|
1539 |
+
"epoch": 1.5793972109761585,
|
1540 |
+
"grad_norm": 0.09534008800983429,
|
1541 |
+
"learning_rate": 0.00010548862115127177,
|
1542 |
+
"loss": 0.2875,
|
1543 |
+
"step": 438
|
1544 |
+
},
|
1545 |
+
{
|
1546 |
+
"epoch": 1.5865946918578497,
|
1547 |
+
"grad_norm": 0.09821389615535736,
|
1548 |
+
"learning_rate": 0.00010495314591700134,
|
1549 |
+
"loss": 0.2831,
|
1550 |
+
"step": 440
|
1551 |
+
},
|
1552 |
+
{
|
1553 |
+
"epoch": 1.5937921727395412,
|
1554 |
+
"grad_norm": 0.09222885221242905,
|
1555 |
+
"learning_rate": 0.00010441767068273094,
|
1556 |
+
"loss": 0.2732,
|
1557 |
+
"step": 442
|
1558 |
+
},
|
1559 |
+
{
|
1560 |
+
"epoch": 1.6009896536212325,
|
1561 |
+
"grad_norm": 0.09654019773006439,
|
1562 |
+
"learning_rate": 0.00010388219544846052,
|
1563 |
+
"loss": 0.2825,
|
1564 |
+
"step": 444
|
1565 |
+
},
|
1566 |
+
{
|
1567 |
+
"epoch": 1.608187134502924,
|
1568 |
+
"grad_norm": 0.1169133186340332,
|
1569 |
+
"learning_rate": 0.0001033467202141901,
|
1570 |
+
"loss": 0.2694,
|
1571 |
+
"step": 446
|
1572 |
+
},
|
1573 |
+
{
|
1574 |
+
"epoch": 1.6153846153846154,
|
1575 |
+
"grad_norm": 0.08105048537254333,
|
1576 |
+
"learning_rate": 0.00010281124497991968,
|
1577 |
+
"loss": 0.2932,
|
1578 |
+
"step": 448
|
1579 |
+
},
|
1580 |
+
{
|
1581 |
+
"epoch": 1.622582096266307,
|
1582 |
+
"grad_norm": 0.09561537951231003,
|
1583 |
+
"learning_rate": 0.00010227576974564928,
|
1584 |
+
"loss": 0.2931,
|
1585 |
+
"step": 450
|
1586 |
+
},
|
1587 |
+
{
|
1588 |
+
"epoch": 1.6297795771479981,
|
1589 |
+
"grad_norm": 0.0990828201174736,
|
1590 |
+
"learning_rate": 0.00010174029451137885,
|
1591 |
+
"loss": 0.297,
|
1592 |
+
"step": 452
|
1593 |
+
},
|
1594 |
+
{
|
1595 |
+
"epoch": 1.6369770580296896,
|
1596 |
+
"grad_norm": 0.09118147939443588,
|
1597 |
+
"learning_rate": 0.00010120481927710844,
|
1598 |
+
"loss": 0.3117,
|
1599 |
+
"step": 454
|
1600 |
+
},
|
1601 |
+
{
|
1602 |
+
"epoch": 1.6441745389113809,
|
1603 |
+
"grad_norm": 0.08818702399730682,
|
1604 |
+
"learning_rate": 0.00010066934404283804,
|
1605 |
+
"loss": 0.3027,
|
1606 |
+
"step": 456
|
1607 |
+
},
|
1608 |
+
{
|
1609 |
+
"epoch": 1.6513720197930724,
|
1610 |
+
"grad_norm": 0.10290935635566711,
|
1611 |
+
"learning_rate": 0.00010013386880856761,
|
1612 |
+
"loss": 0.297,
|
1613 |
+
"step": 458
|
1614 |
+
},
|
1615 |
+
{
|
1616 |
+
"epoch": 1.6585695006747638,
|
1617 |
+
"grad_norm": 0.11350158601999283,
|
1618 |
+
"learning_rate": 9.95983935742972e-05,
|
1619 |
+
"loss": 0.3067,
|
1620 |
+
"step": 460
|
1621 |
+
},
|
1622 |
+
{
|
1623 |
+
"epoch": 1.6657669815564553,
|
1624 |
+
"grad_norm": 0.09453711658716202,
|
1625 |
+
"learning_rate": 9.906291834002678e-05,
|
1626 |
+
"loss": 0.3018,
|
1627 |
+
"step": 462
|
1628 |
+
},
|
1629 |
+
{
|
1630 |
+
"epoch": 1.6729644624381468,
|
1631 |
+
"grad_norm": 0.0882163718342781,
|
1632 |
+
"learning_rate": 9.852744310575637e-05,
|
1633 |
+
"loss": 0.3109,
|
1634 |
+
"step": 464
|
1635 |
+
},
|
1636 |
+
{
|
1637 |
+
"epoch": 1.680161943319838,
|
1638 |
+
"grad_norm": 0.09760285168886185,
|
1639 |
+
"learning_rate": 9.799196787148595e-05,
|
1640 |
+
"loss": 0.2827,
|
1641 |
+
"step": 466
|
1642 |
+
},
|
1643 |
+
{
|
1644 |
+
"epoch": 1.6873594242015295,
|
1645 |
+
"grad_norm": 0.08591054379940033,
|
1646 |
+
"learning_rate": 9.745649263721554e-05,
|
1647 |
+
"loss": 0.2717,
|
1648 |
+
"step": 468
|
1649 |
+
},
|
1650 |
+
{
|
1651 |
+
"epoch": 1.6945569050832208,
|
1652 |
+
"grad_norm": 0.08686313778162003,
|
1653 |
+
"learning_rate": 9.692101740294511e-05,
|
1654 |
+
"loss": 0.4576,
|
1655 |
+
"step": 470
|
1656 |
+
},
|
1657 |
+
{
|
1658 |
+
"epoch": 1.7017543859649122,
|
1659 |
+
"grad_norm": 0.1008240357041359,
|
1660 |
+
"learning_rate": 9.638554216867471e-05,
|
1661 |
+
"loss": 0.3075,
|
1662 |
+
"step": 472
|
1663 |
+
},
|
1664 |
+
{
|
1665 |
+
"epoch": 1.7089518668466037,
|
1666 |
+
"grad_norm": 0.11971218138933182,
|
1667 |
+
"learning_rate": 9.58500669344043e-05,
|
1668 |
+
"loss": 0.2992,
|
1669 |
+
"step": 474
|
1670 |
+
},
|
1671 |
+
{
|
1672 |
+
"epoch": 1.7161493477282952,
|
1673 |
+
"grad_norm": 0.09750854223966599,
|
1674 |
+
"learning_rate": 9.531459170013387e-05,
|
1675 |
+
"loss": 0.2908,
|
1676 |
+
"step": 476
|
1677 |
+
},
|
1678 |
+
{
|
1679 |
+
"epoch": 1.7233468286099867,
|
1680 |
+
"grad_norm": 0.09968557953834534,
|
1681 |
+
"learning_rate": 9.477911646586346e-05,
|
1682 |
+
"loss": 0.2964,
|
1683 |
+
"step": 478
|
1684 |
+
},
|
1685 |
+
{
|
1686 |
+
"epoch": 1.730544309491678,
|
1687 |
+
"grad_norm": 0.10224322974681854,
|
1688 |
+
"learning_rate": 9.424364123159304e-05,
|
1689 |
+
"loss": 0.2906,
|
1690 |
+
"step": 480
|
1691 |
+
},
|
1692 |
+
{
|
1693 |
+
"epoch": 1.7377417903733692,
|
1694 |
+
"grad_norm": 0.16597296297550201,
|
1695 |
+
"learning_rate": 9.370816599732262e-05,
|
1696 |
+
"loss": 0.3444,
|
1697 |
+
"step": 482
|
1698 |
+
},
|
1699 |
+
{
|
1700 |
+
"epoch": 1.7449392712550607,
|
1701 |
+
"grad_norm": 0.09388897567987442,
|
1702 |
+
"learning_rate": 9.317269076305222e-05,
|
1703 |
+
"loss": 0.3055,
|
1704 |
+
"step": 484
|
1705 |
+
},
|
1706 |
+
{
|
1707 |
+
"epoch": 1.7521367521367521,
|
1708 |
+
"grad_norm": 0.10003037750720978,
|
1709 |
+
"learning_rate": 9.26372155287818e-05,
|
1710 |
+
"loss": 0.2911,
|
1711 |
+
"step": 486
|
1712 |
+
},
|
1713 |
+
{
|
1714 |
+
"epoch": 1.7593342330184436,
|
1715 |
+
"grad_norm": 0.08807525038719177,
|
1716 |
+
"learning_rate": 9.210174029451138e-05,
|
1717 |
+
"loss": 0.3146,
|
1718 |
+
"step": 488
|
1719 |
+
},
|
1720 |
+
{
|
1721 |
+
"epoch": 1.766531713900135,
|
1722 |
+
"grad_norm": 0.10171247273683548,
|
1723 |
+
"learning_rate": 9.156626506024096e-05,
|
1724 |
+
"loss": 0.3314,
|
1725 |
+
"step": 490
|
1726 |
+
},
|
1727 |
+
{
|
1728 |
+
"epoch": 1.7737291947818263,
|
1729 |
+
"grad_norm": 0.10340695828199387,
|
1730 |
+
"learning_rate": 9.103078982597055e-05,
|
1731 |
+
"loss": 0.3033,
|
1732 |
+
"step": 492
|
1733 |
+
},
|
1734 |
+
{
|
1735 |
+
"epoch": 1.7809266756635178,
|
1736 |
+
"grad_norm": 0.09169702231884003,
|
1737 |
+
"learning_rate": 9.049531459170014e-05,
|
1738 |
+
"loss": 0.4022,
|
1739 |
+
"step": 494
|
1740 |
+
},
|
1741 |
+
{
|
1742 |
+
"epoch": 1.788124156545209,
|
1743 |
+
"grad_norm": 0.11728455126285553,
|
1744 |
+
"learning_rate": 8.995983935742972e-05,
|
1745 |
+
"loss": 0.2889,
|
1746 |
+
"step": 496
|
1747 |
+
},
|
1748 |
+
{
|
1749 |
+
"epoch": 1.7953216374269005,
|
1750 |
+
"grad_norm": 0.11627179384231567,
|
1751 |
+
"learning_rate": 8.942436412315931e-05,
|
1752 |
+
"loss": 0.2731,
|
1753 |
+
"step": 498
|
1754 |
+
},
|
1755 |
+
{
|
1756 |
+
"epoch": 1.802519118308592,
|
1757 |
+
"grad_norm": 0.10158301889896393,
|
1758 |
+
"learning_rate": 8.888888888888889e-05,
|
1759 |
+
"loss": 0.3039,
|
1760 |
+
"step": 500
|
1761 |
+
},
|
1762 |
+
{
|
1763 |
+
"epoch": 1.8097165991902835,
|
1764 |
+
"grad_norm": 0.08781228959560394,
|
1765 |
+
"learning_rate": 8.835341365461848e-05,
|
1766 |
+
"loss": 0.3067,
|
1767 |
+
"step": 502
|
1768 |
+
},
|
1769 |
+
{
|
1770 |
+
"epoch": 1.816914080071975,
|
1771 |
+
"grad_norm": 0.10025554150342941,
|
1772 |
+
"learning_rate": 8.781793842034806e-05,
|
1773 |
+
"loss": 0.2814,
|
1774 |
+
"step": 504
|
1775 |
+
},
|
1776 |
+
{
|
1777 |
+
"epoch": 1.8241115609536662,
|
1778 |
+
"grad_norm": 0.10106230527162552,
|
1779 |
+
"learning_rate": 8.728246318607765e-05,
|
1780 |
+
"loss": 0.3023,
|
1781 |
+
"step": 506
|
1782 |
+
},
|
1783 |
+
{
|
1784 |
+
"epoch": 1.8313090418353575,
|
1785 |
+
"grad_norm": 0.10547325015068054,
|
1786 |
+
"learning_rate": 8.674698795180724e-05,
|
1787 |
+
"loss": 0.3053,
|
1788 |
+
"step": 508
|
1789 |
+
},
|
1790 |
+
{
|
1791 |
+
"epoch": 1.838506522717049,
|
1792 |
+
"grad_norm": 0.10827834159135818,
|
1793 |
+
"learning_rate": 8.621151271753681e-05,
|
1794 |
+
"loss": 0.2935,
|
1795 |
+
"step": 510
|
1796 |
+
},
|
1797 |
+
{
|
1798 |
+
"epoch": 1.8457040035987404,
|
1799 |
+
"grad_norm": 0.1048627495765686,
|
1800 |
+
"learning_rate": 8.567603748326641e-05,
|
1801 |
+
"loss": 0.3064,
|
1802 |
+
"step": 512
|
1803 |
+
},
|
1804 |
+
{
|
1805 |
+
"epoch": 1.852901484480432,
|
1806 |
+
"grad_norm": 0.09031334519386292,
|
1807 |
+
"learning_rate": 8.514056224899599e-05,
|
1808 |
+
"loss": 0.284,
|
1809 |
+
"step": 514
|
1810 |
+
},
|
1811 |
+
{
|
1812 |
+
"epoch": 1.8600989653621234,
|
1813 |
+
"grad_norm": 0.09391462057828903,
|
1814 |
+
"learning_rate": 8.460508701472556e-05,
|
1815 |
+
"loss": 0.2983,
|
1816 |
+
"step": 516
|
1817 |
+
},
|
1818 |
+
{
|
1819 |
+
"epoch": 1.8672964462438146,
|
1820 |
+
"grad_norm": 0.14464600384235382,
|
1821 |
+
"learning_rate": 8.406961178045516e-05,
|
1822 |
+
"loss": 0.4371,
|
1823 |
+
"step": 518
|
1824 |
+
},
|
1825 |
+
{
|
1826 |
+
"epoch": 1.874493927125506,
|
1827 |
+
"grad_norm": 0.10378314554691315,
|
1828 |
+
"learning_rate": 8.353413654618474e-05,
|
1829 |
+
"loss": 0.4844,
|
1830 |
+
"step": 520
|
1831 |
+
},
|
1832 |
+
{
|
1833 |
+
"epoch": 1.8816914080071974,
|
1834 |
+
"grad_norm": 0.10564987361431122,
|
1835 |
+
"learning_rate": 8.299866131191432e-05,
|
1836 |
+
"loss": 0.2709,
|
1837 |
+
"step": 522
|
1838 |
+
},
|
1839 |
+
{
|
1840 |
+
"epoch": 1.8888888888888888,
|
1841 |
+
"grad_norm": 0.10246952623128891,
|
1842 |
+
"learning_rate": 8.246318607764392e-05,
|
1843 |
+
"loss": 0.2894,
|
1844 |
+
"step": 524
|
1845 |
+
},
|
1846 |
+
{
|
1847 |
+
"epoch": 1.8960863697705803,
|
1848 |
+
"grad_norm": 0.11684907227754593,
|
1849 |
+
"learning_rate": 8.192771084337349e-05,
|
1850 |
+
"loss": 0.3246,
|
1851 |
+
"step": 526
|
1852 |
+
},
|
1853 |
+
{
|
1854 |
+
"epoch": 1.9032838506522718,
|
1855 |
+
"grad_norm": 0.10560288280248642,
|
1856 |
+
"learning_rate": 8.139223560910308e-05,
|
1857 |
+
"loss": 0.2955,
|
1858 |
+
"step": 528
|
1859 |
+
},
|
1860 |
+
{
|
1861 |
+
"epoch": 1.9104813315339633,
|
1862 |
+
"grad_norm": 0.09018637984991074,
|
1863 |
+
"learning_rate": 8.085676037483266e-05,
|
1864 |
+
"loss": 0.2954,
|
1865 |
+
"step": 530
|
1866 |
+
},
|
1867 |
+
{
|
1868 |
+
"epoch": 1.9176788124156545,
|
1869 |
+
"grad_norm": 0.10339517891407013,
|
1870 |
+
"learning_rate": 8.032128514056225e-05,
|
1871 |
+
"loss": 0.282,
|
1872 |
+
"step": 532
|
1873 |
+
},
|
1874 |
+
{
|
1875 |
+
"epoch": 1.9248762932973458,
|
1876 |
+
"grad_norm": 0.08229915797710419,
|
1877 |
+
"learning_rate": 7.978580990629184e-05,
|
1878 |
+
"loss": 0.431,
|
1879 |
+
"step": 534
|
1880 |
+
},
|
1881 |
+
{
|
1882 |
+
"epoch": 1.9320737741790373,
|
1883 |
+
"grad_norm": 0.10314471274614334,
|
1884 |
+
"learning_rate": 7.925033467202142e-05,
|
1885 |
+
"loss": 0.2981,
|
1886 |
+
"step": 536
|
1887 |
+
},
|
1888 |
+
{
|
1889 |
+
"epoch": 1.9392712550607287,
|
1890 |
+
"grad_norm": 0.11645660549402237,
|
1891 |
+
"learning_rate": 7.8714859437751e-05,
|
1892 |
+
"loss": 0.283,
|
1893 |
+
"step": 538
|
1894 |
+
},
|
1895 |
+
{
|
1896 |
+
"epoch": 1.9464687359424202,
|
1897 |
+
"grad_norm": 0.10056841373443604,
|
1898 |
+
"learning_rate": 7.817938420348059e-05,
|
1899 |
+
"loss": 0.3047,
|
1900 |
+
"step": 540
|
1901 |
+
},
|
1902 |
+
{
|
1903 |
+
"epoch": 1.9536662168241117,
|
1904 |
+
"grad_norm": 0.10680730640888214,
|
1905 |
+
"learning_rate": 7.764390896921018e-05,
|
1906 |
+
"loss": 0.2887,
|
1907 |
+
"step": 542
|
1908 |
+
},
|
1909 |
+
{
|
1910 |
+
"epoch": 1.960863697705803,
|
1911 |
+
"grad_norm": 0.09448685497045517,
|
1912 |
+
"learning_rate": 7.710843373493976e-05,
|
1913 |
+
"loss": 0.2765,
|
1914 |
+
"step": 544
|
1915 |
+
},
|
1916 |
+
{
|
1917 |
+
"epoch": 1.9680611785874944,
|
1918 |
+
"grad_norm": 0.08228401094675064,
|
1919 |
+
"learning_rate": 7.657295850066935e-05,
|
1920 |
+
"loss": 0.2827,
|
1921 |
+
"step": 546
|
1922 |
+
},
|
1923 |
+
{
|
1924 |
+
"epoch": 1.9752586594691857,
|
1925 |
+
"grad_norm": 0.11218800395727158,
|
1926 |
+
"learning_rate": 7.603748326639893e-05,
|
1927 |
+
"loss": 0.4554,
|
1928 |
+
"step": 548
|
1929 |
+
},
|
1930 |
+
{
|
1931 |
+
"epoch": 1.9824561403508771,
|
1932 |
+
"grad_norm": 0.09007290750741959,
|
1933 |
+
"learning_rate": 7.550200803212851e-05,
|
1934 |
+
"loss": 0.2914,
|
1935 |
+
"step": 550
|
1936 |
+
}
|
1937 |
+
],
|
1938 |
+
"logging_steps": 2,
|
1939 |
+
"max_steps": 831,
|
1940 |
+
"num_input_tokens_seen": 0,
|
1941 |
+
"num_train_epochs": 3,
|
1942 |
+
"save_steps": 50,
|
1943 |
+
"stateful_callbacks": {
|
1944 |
+
"TrainerControl": {
|
1945 |
+
"args": {
|
1946 |
+
"should_epoch_stop": false,
|
1947 |
+
"should_evaluate": false,
|
1948 |
+
"should_log": false,
|
1949 |
+
"should_save": true,
|
1950 |
+
"should_training_stop": false
|
1951 |
+
},
|
1952 |
+
"attributes": {}
|
1953 |
+
}
|
1954 |
+
},
|
1955 |
+
"total_flos": 2.189887705353388e+18,
|
1956 |
+
"train_batch_size": 2,
|
1957 |
+
"trial_name": null,
|
1958 |
+
"trial_params": null
|
1959 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:69b1fb78f005623b725bcca16f73ee4234a6374386a5ab45665bc2dcc6b81c3a
|
3 |
+
size 5624
|