Upload folder using huggingface_hub
Browse files- .gitattributes +1 -0
- README.md +202 -3
- adapter_config.json +37 -0
- adapter_model.safetensors +3 -0
- optimizer.pt +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +23 -0
- tokenizer.json +3 -0
- tokenizer_config.json +2069 -0
- trainer_state.json +1577 -0
- training_args.bin +3 -0
.gitattributes
CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
36 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
README.md
CHANGED
@@ -1,3 +1,202 @@
|
|
1 |
-
---
|
2 |
-
|
3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
base_model: unsloth/Llama-3.2-3B-Instruct
|
3 |
+
library_name: peft
|
4 |
+
---
|
5 |
+
|
6 |
+
# Model Card for Model ID
|
7 |
+
|
8 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
9 |
+
|
10 |
+
|
11 |
+
|
12 |
+
## Model Details
|
13 |
+
|
14 |
+
### Model Description
|
15 |
+
|
16 |
+
<!-- Provide a longer summary of what this model is. -->
|
17 |
+
|
18 |
+
|
19 |
+
|
20 |
+
- **Developed by:** [More Information Needed]
|
21 |
+
- **Funded by [optional]:** [More Information Needed]
|
22 |
+
- **Shared by [optional]:** [More Information Needed]
|
23 |
+
- **Model type:** [More Information Needed]
|
24 |
+
- **Language(s) (NLP):** [More Information Needed]
|
25 |
+
- **License:** [More Information Needed]
|
26 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
27 |
+
|
28 |
+
### Model Sources [optional]
|
29 |
+
|
30 |
+
<!-- Provide the basic links for the model. -->
|
31 |
+
|
32 |
+
- **Repository:** [More Information Needed]
|
33 |
+
- **Paper [optional]:** [More Information Needed]
|
34 |
+
- **Demo [optional]:** [More Information Needed]
|
35 |
+
|
36 |
+
## Uses
|
37 |
+
|
38 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
39 |
+
|
40 |
+
### Direct Use
|
41 |
+
|
42 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
43 |
+
|
44 |
+
[More Information Needed]
|
45 |
+
|
46 |
+
### Downstream Use [optional]
|
47 |
+
|
48 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
49 |
+
|
50 |
+
[More Information Needed]
|
51 |
+
|
52 |
+
### Out-of-Scope Use
|
53 |
+
|
54 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
55 |
+
|
56 |
+
[More Information Needed]
|
57 |
+
|
58 |
+
## Bias, Risks, and Limitations
|
59 |
+
|
60 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
61 |
+
|
62 |
+
[More Information Needed]
|
63 |
+
|
64 |
+
### Recommendations
|
65 |
+
|
66 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
67 |
+
|
68 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
69 |
+
|
70 |
+
## How to Get Started with the Model
|
71 |
+
|
72 |
+
Use the code below to get started with the model.
|
73 |
+
|
74 |
+
[More Information Needed]
|
75 |
+
|
76 |
+
## Training Details
|
77 |
+
|
78 |
+
### Training Data
|
79 |
+
|
80 |
+
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
81 |
+
|
82 |
+
[More Information Needed]
|
83 |
+
|
84 |
+
### Training Procedure
|
85 |
+
|
86 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
87 |
+
|
88 |
+
#### Preprocessing [optional]
|
89 |
+
|
90 |
+
[More Information Needed]
|
91 |
+
|
92 |
+
|
93 |
+
#### Training Hyperparameters
|
94 |
+
|
95 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
96 |
+
|
97 |
+
#### Speeds, Sizes, Times [optional]
|
98 |
+
|
99 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
100 |
+
|
101 |
+
[More Information Needed]
|
102 |
+
|
103 |
+
## Evaluation
|
104 |
+
|
105 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
106 |
+
|
107 |
+
### Testing Data, Factors & Metrics
|
108 |
+
|
109 |
+
#### Testing Data
|
110 |
+
|
111 |
+
<!-- This should link to a Dataset Card if possible. -->
|
112 |
+
|
113 |
+
[More Information Needed]
|
114 |
+
|
115 |
+
#### Factors
|
116 |
+
|
117 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
118 |
+
|
119 |
+
[More Information Needed]
|
120 |
+
|
121 |
+
#### Metrics
|
122 |
+
|
123 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
124 |
+
|
125 |
+
[More Information Needed]
|
126 |
+
|
127 |
+
### Results
|
128 |
+
|
129 |
+
[More Information Needed]
|
130 |
+
|
131 |
+
#### Summary
|
132 |
+
|
133 |
+
|
134 |
+
|
135 |
+
## Model Examination [optional]
|
136 |
+
|
137 |
+
<!-- Relevant interpretability work for the model goes here -->
|
138 |
+
|
139 |
+
[More Information Needed]
|
140 |
+
|
141 |
+
## Environmental Impact
|
142 |
+
|
143 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
144 |
+
|
145 |
+
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
146 |
+
|
147 |
+
- **Hardware Type:** [More Information Needed]
|
148 |
+
- **Hours used:** [More Information Needed]
|
149 |
+
- **Cloud Provider:** [More Information Needed]
|
150 |
+
- **Compute Region:** [More Information Needed]
|
151 |
+
- **Carbon Emitted:** [More Information Needed]
|
152 |
+
|
153 |
+
## Technical Specifications [optional]
|
154 |
+
|
155 |
+
### Model Architecture and Objective
|
156 |
+
|
157 |
+
[More Information Needed]
|
158 |
+
|
159 |
+
### Compute Infrastructure
|
160 |
+
|
161 |
+
[More Information Needed]
|
162 |
+
|
163 |
+
#### Hardware
|
164 |
+
|
165 |
+
[More Information Needed]
|
166 |
+
|
167 |
+
#### Software
|
168 |
+
|
169 |
+
[More Information Needed]
|
170 |
+
|
171 |
+
## Citation [optional]
|
172 |
+
|
173 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
174 |
+
|
175 |
+
**BibTeX:**
|
176 |
+
|
177 |
+
[More Information Needed]
|
178 |
+
|
179 |
+
**APA:**
|
180 |
+
|
181 |
+
[More Information Needed]
|
182 |
+
|
183 |
+
## Glossary [optional]
|
184 |
+
|
185 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
186 |
+
|
187 |
+
[More Information Needed]
|
188 |
+
|
189 |
+
## More Information [optional]
|
190 |
+
|
191 |
+
[More Information Needed]
|
192 |
+
|
193 |
+
## Model Card Authors [optional]
|
194 |
+
|
195 |
+
[More Information Needed]
|
196 |
+
|
197 |
+
## Model Card Contact
|
198 |
+
|
199 |
+
[More Information Needed]
|
200 |
+
### Framework versions
|
201 |
+
|
202 |
+
- PEFT 0.14.0
|
adapter_config.json
ADDED
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "unsloth/Llama-3.2-3B-Instruct",
|
5 |
+
"bias": "none",
|
6 |
+
"eva_config": null,
|
7 |
+
"exclude_modules": null,
|
8 |
+
"fan_in_fan_out": false,
|
9 |
+
"inference_mode": true,
|
10 |
+
"init_lora_weights": true,
|
11 |
+
"layer_replication": null,
|
12 |
+
"layers_pattern": null,
|
13 |
+
"layers_to_transform": null,
|
14 |
+
"loftq_config": {},
|
15 |
+
"lora_alpha": 16,
|
16 |
+
"lora_bias": false,
|
17 |
+
"lora_dropout": 0.05,
|
18 |
+
"megatron_config": null,
|
19 |
+
"megatron_core": "megatron.core",
|
20 |
+
"modules_to_save": null,
|
21 |
+
"peft_type": "LORA",
|
22 |
+
"r": 16,
|
23 |
+
"rank_pattern": {},
|
24 |
+
"revision": null,
|
25 |
+
"target_modules": [
|
26 |
+
"up_proj",
|
27 |
+
"down_proj",
|
28 |
+
"gate_proj",
|
29 |
+
"k_proj",
|
30 |
+
"q_proj",
|
31 |
+
"o_proj",
|
32 |
+
"v_proj"
|
33 |
+
],
|
34 |
+
"task_type": "CAUSAL_LM",
|
35 |
+
"use_dora": false,
|
36 |
+
"use_rslora": false
|
37 |
+
}
|
adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:57437140e63b34163d094d0c5cd5dee178be3c021910305be9686a0a818f77b7
|
3 |
+
size 97307544
|
optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:693fde74856dbbf606b796166876946ae7fcd021a5859be8fbc34b57a6088b7a
|
3 |
+
size 49846260
|
rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:559a16c3d987f0a76dfa63d6b07bbf64dcd574e671a1a86d0cc9a3aad4629604
|
3 |
+
size 14244
|
scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8c85b63b878904b20604f3988b84fb7c71dfa5ac37569d4500af4cad57b6472b
|
3 |
+
size 1064
|
special_tokens_map.json
ADDED
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<|begin_of_text|>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": {
|
10 |
+
"content": "<|eot_id|>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": {
|
17 |
+
"content": "<|finetune_right_pad_id|>",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": false,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
}
|
23 |
+
}
|
tokenizer.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:89e7f2180ba598b166b631d64b2b2ba1d4fad8977a4c716b907c0eb2903f56a3
|
3 |
+
size 17210019
|
tokenizer_config.json
ADDED
@@ -0,0 +1,2069 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": false,
|
3 |
+
"add_eos_token": false,
|
4 |
+
"added_tokens_decoder": {
|
5 |
+
"128000": {
|
6 |
+
"content": "<|begin_of_text|>",
|
7 |
+
"lstrip": false,
|
8 |
+
"normalized": false,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false,
|
11 |
+
"special": true
|
12 |
+
},
|
13 |
+
"128001": {
|
14 |
+
"content": "<|end_of_text|>",
|
15 |
+
"lstrip": false,
|
16 |
+
"normalized": false,
|
17 |
+
"rstrip": false,
|
18 |
+
"single_word": false,
|
19 |
+
"special": true
|
20 |
+
},
|
21 |
+
"128002": {
|
22 |
+
"content": "<|reserved_special_token_0|>",
|
23 |
+
"lstrip": false,
|
24 |
+
"normalized": false,
|
25 |
+
"rstrip": false,
|
26 |
+
"single_word": false,
|
27 |
+
"special": true
|
28 |
+
},
|
29 |
+
"128003": {
|
30 |
+
"content": "<|reserved_special_token_1|>",
|
31 |
+
"lstrip": false,
|
32 |
+
"normalized": false,
|
33 |
+
"rstrip": false,
|
34 |
+
"single_word": false,
|
35 |
+
"special": true
|
36 |
+
},
|
37 |
+
"128004": {
|
38 |
+
"content": "<|finetune_right_pad_id|>",
|
39 |
+
"lstrip": false,
|
40 |
+
"normalized": false,
|
41 |
+
"rstrip": false,
|
42 |
+
"single_word": false,
|
43 |
+
"special": true
|
44 |
+
},
|
45 |
+
"128005": {
|
46 |
+
"content": "<|reserved_special_token_2|>",
|
47 |
+
"lstrip": false,
|
48 |
+
"normalized": false,
|
49 |
+
"rstrip": false,
|
50 |
+
"single_word": false,
|
51 |
+
"special": true
|
52 |
+
},
|
53 |
+
"128006": {
|
54 |
+
"content": "<|start_header_id|>",
|
55 |
+
"lstrip": false,
|
56 |
+
"normalized": false,
|
57 |
+
"rstrip": false,
|
58 |
+
"single_word": false,
|
59 |
+
"special": true
|
60 |
+
},
|
61 |
+
"128007": {
|
62 |
+
"content": "<|end_header_id|>",
|
63 |
+
"lstrip": false,
|
64 |
+
"normalized": false,
|
65 |
+
"rstrip": false,
|
66 |
+
"single_word": false,
|
67 |
+
"special": true
|
68 |
+
},
|
69 |
+
"128008": {
|
70 |
+
"content": "<|eom_id|>",
|
71 |
+
"lstrip": false,
|
72 |
+
"normalized": false,
|
73 |
+
"rstrip": false,
|
74 |
+
"single_word": false,
|
75 |
+
"special": true
|
76 |
+
},
|
77 |
+
"128009": {
|
78 |
+
"content": "<|eot_id|>",
|
79 |
+
"lstrip": false,
|
80 |
+
"normalized": false,
|
81 |
+
"rstrip": false,
|
82 |
+
"single_word": false,
|
83 |
+
"special": true
|
84 |
+
},
|
85 |
+
"128010": {
|
86 |
+
"content": "<|python_tag|>",
|
87 |
+
"lstrip": false,
|
88 |
+
"normalized": false,
|
89 |
+
"rstrip": false,
|
90 |
+
"single_word": false,
|
91 |
+
"special": true
|
92 |
+
},
|
93 |
+
"128011": {
|
94 |
+
"content": "<|reserved_special_token_3|>",
|
95 |
+
"lstrip": false,
|
96 |
+
"normalized": false,
|
97 |
+
"rstrip": false,
|
98 |
+
"single_word": false,
|
99 |
+
"special": true
|
100 |
+
},
|
101 |
+
"128012": {
|
102 |
+
"content": "<|reserved_special_token_4|>",
|
103 |
+
"lstrip": false,
|
104 |
+
"normalized": false,
|
105 |
+
"rstrip": false,
|
106 |
+
"single_word": false,
|
107 |
+
"special": true
|
108 |
+
},
|
109 |
+
"128013": {
|
110 |
+
"content": "<|reserved_special_token_5|>",
|
111 |
+
"lstrip": false,
|
112 |
+
"normalized": false,
|
113 |
+
"rstrip": false,
|
114 |
+
"single_word": false,
|
115 |
+
"special": true
|
116 |
+
},
|
117 |
+
"128014": {
|
118 |
+
"content": "<|reserved_special_token_6|>",
|
119 |
+
"lstrip": false,
|
120 |
+
"normalized": false,
|
121 |
+
"rstrip": false,
|
122 |
+
"single_word": false,
|
123 |
+
"special": true
|
124 |
+
},
|
125 |
+
"128015": {
|
126 |
+
"content": "<|reserved_special_token_7|>",
|
127 |
+
"lstrip": false,
|
128 |
+
"normalized": false,
|
129 |
+
"rstrip": false,
|
130 |
+
"single_word": false,
|
131 |
+
"special": true
|
132 |
+
},
|
133 |
+
"128016": {
|
134 |
+
"content": "<|reserved_special_token_8|>",
|
135 |
+
"lstrip": false,
|
136 |
+
"normalized": false,
|
137 |
+
"rstrip": false,
|
138 |
+
"single_word": false,
|
139 |
+
"special": true
|
140 |
+
},
|
141 |
+
"128017": {
|
142 |
+
"content": "<|reserved_special_token_9|>",
|
143 |
+
"lstrip": false,
|
144 |
+
"normalized": false,
|
145 |
+
"rstrip": false,
|
146 |
+
"single_word": false,
|
147 |
+
"special": true
|
148 |
+
},
|
149 |
+
"128018": {
|
150 |
+
"content": "<|reserved_special_token_10|>",
|
151 |
+
"lstrip": false,
|
152 |
+
"normalized": false,
|
153 |
+
"rstrip": false,
|
154 |
+
"single_word": false,
|
155 |
+
"special": true
|
156 |
+
},
|
157 |
+
"128019": {
|
158 |
+
"content": "<|reserved_special_token_11|>",
|
159 |
+
"lstrip": false,
|
160 |
+
"normalized": false,
|
161 |
+
"rstrip": false,
|
162 |
+
"single_word": false,
|
163 |
+
"special": true
|
164 |
+
},
|
165 |
+
"128020": {
|
166 |
+
"content": "<|reserved_special_token_12|>",
|
167 |
+
"lstrip": false,
|
168 |
+
"normalized": false,
|
169 |
+
"rstrip": false,
|
170 |
+
"single_word": false,
|
171 |
+
"special": true
|
172 |
+
},
|
173 |
+
"128021": {
|
174 |
+
"content": "<|reserved_special_token_13|>",
|
175 |
+
"lstrip": false,
|
176 |
+
"normalized": false,
|
177 |
+
"rstrip": false,
|
178 |
+
"single_word": false,
|
179 |
+
"special": true
|
180 |
+
},
|
181 |
+
"128022": {
|
182 |
+
"content": "<|reserved_special_token_14|>",
|
183 |
+
"lstrip": false,
|
184 |
+
"normalized": false,
|
185 |
+
"rstrip": false,
|
186 |
+
"single_word": false,
|
187 |
+
"special": true
|
188 |
+
},
|
189 |
+
"128023": {
|
190 |
+
"content": "<|reserved_special_token_15|>",
|
191 |
+
"lstrip": false,
|
192 |
+
"normalized": false,
|
193 |
+
"rstrip": false,
|
194 |
+
"single_word": false,
|
195 |
+
"special": true
|
196 |
+
},
|
197 |
+
"128024": {
|
198 |
+
"content": "<|reserved_special_token_16|>",
|
199 |
+
"lstrip": false,
|
200 |
+
"normalized": false,
|
201 |
+
"rstrip": false,
|
202 |
+
"single_word": false,
|
203 |
+
"special": true
|
204 |
+
},
|
205 |
+
"128025": {
|
206 |
+
"content": "<|reserved_special_token_17|>",
|
207 |
+
"lstrip": false,
|
208 |
+
"normalized": false,
|
209 |
+
"rstrip": false,
|
210 |
+
"single_word": false,
|
211 |
+
"special": true
|
212 |
+
},
|
213 |
+
"128026": {
|
214 |
+
"content": "<|reserved_special_token_18|>",
|
215 |
+
"lstrip": false,
|
216 |
+
"normalized": false,
|
217 |
+
"rstrip": false,
|
218 |
+
"single_word": false,
|
219 |
+
"special": true
|
220 |
+
},
|
221 |
+
"128027": {
|
222 |
+
"content": "<|reserved_special_token_19|>",
|
223 |
+
"lstrip": false,
|
224 |
+
"normalized": false,
|
225 |
+
"rstrip": false,
|
226 |
+
"single_word": false,
|
227 |
+
"special": true
|
228 |
+
},
|
229 |
+
"128028": {
|
230 |
+
"content": "<|reserved_special_token_20|>",
|
231 |
+
"lstrip": false,
|
232 |
+
"normalized": false,
|
233 |
+
"rstrip": false,
|
234 |
+
"single_word": false,
|
235 |
+
"special": true
|
236 |
+
},
|
237 |
+
"128029": {
|
238 |
+
"content": "<|reserved_special_token_21|>",
|
239 |
+
"lstrip": false,
|
240 |
+
"normalized": false,
|
241 |
+
"rstrip": false,
|
242 |
+
"single_word": false,
|
243 |
+
"special": true
|
244 |
+
},
|
245 |
+
"128030": {
|
246 |
+
"content": "<|reserved_special_token_22|>",
|
247 |
+
"lstrip": false,
|
248 |
+
"normalized": false,
|
249 |
+
"rstrip": false,
|
250 |
+
"single_word": false,
|
251 |
+
"special": true
|
252 |
+
},
|
253 |
+
"128031": {
|
254 |
+
"content": "<|reserved_special_token_23|>",
|
255 |
+
"lstrip": false,
|
256 |
+
"normalized": false,
|
257 |
+
"rstrip": false,
|
258 |
+
"single_word": false,
|
259 |
+
"special": true
|
260 |
+
},
|
261 |
+
"128032": {
|
262 |
+
"content": "<|reserved_special_token_24|>",
|
263 |
+
"lstrip": false,
|
264 |
+
"normalized": false,
|
265 |
+
"rstrip": false,
|
266 |
+
"single_word": false,
|
267 |
+
"special": true
|
268 |
+
},
|
269 |
+
"128033": {
|
270 |
+
"content": "<|reserved_special_token_25|>",
|
271 |
+
"lstrip": false,
|
272 |
+
"normalized": false,
|
273 |
+
"rstrip": false,
|
274 |
+
"single_word": false,
|
275 |
+
"special": true
|
276 |
+
},
|
277 |
+
"128034": {
|
278 |
+
"content": "<|reserved_special_token_26|>",
|
279 |
+
"lstrip": false,
|
280 |
+
"normalized": false,
|
281 |
+
"rstrip": false,
|
282 |
+
"single_word": false,
|
283 |
+
"special": true
|
284 |
+
},
|
285 |
+
"128035": {
|
286 |
+
"content": "<|reserved_special_token_27|>",
|
287 |
+
"lstrip": false,
|
288 |
+
"normalized": false,
|
289 |
+
"rstrip": false,
|
290 |
+
"single_word": false,
|
291 |
+
"special": true
|
292 |
+
},
|
293 |
+
"128036": {
|
294 |
+
"content": "<|reserved_special_token_28|>",
|
295 |
+
"lstrip": false,
|
296 |
+
"normalized": false,
|
297 |
+
"rstrip": false,
|
298 |
+
"single_word": false,
|
299 |
+
"special": true
|
300 |
+
},
|
301 |
+
"128037": {
|
302 |
+
"content": "<|reserved_special_token_29|>",
|
303 |
+
"lstrip": false,
|
304 |
+
"normalized": false,
|
305 |
+
"rstrip": false,
|
306 |
+
"single_word": false,
|
307 |
+
"special": true
|
308 |
+
},
|
309 |
+
"128038": {
|
310 |
+
"content": "<|reserved_special_token_30|>",
|
311 |
+
"lstrip": false,
|
312 |
+
"normalized": false,
|
313 |
+
"rstrip": false,
|
314 |
+
"single_word": false,
|
315 |
+
"special": true
|
316 |
+
},
|
317 |
+
"128039": {
|
318 |
+
"content": "<|reserved_special_token_31|>",
|
319 |
+
"lstrip": false,
|
320 |
+
"normalized": false,
|
321 |
+
"rstrip": false,
|
322 |
+
"single_word": false,
|
323 |
+
"special": true
|
324 |
+
},
|
325 |
+
"128040": {
|
326 |
+
"content": "<|reserved_special_token_32|>",
|
327 |
+
"lstrip": false,
|
328 |
+
"normalized": false,
|
329 |
+
"rstrip": false,
|
330 |
+
"single_word": false,
|
331 |
+
"special": true
|
332 |
+
},
|
333 |
+
"128041": {
|
334 |
+
"content": "<|reserved_special_token_33|>",
|
335 |
+
"lstrip": false,
|
336 |
+
"normalized": false,
|
337 |
+
"rstrip": false,
|
338 |
+
"single_word": false,
|
339 |
+
"special": true
|
340 |
+
},
|
341 |
+
"128042": {
|
342 |
+
"content": "<|reserved_special_token_34|>",
|
343 |
+
"lstrip": false,
|
344 |
+
"normalized": false,
|
345 |
+
"rstrip": false,
|
346 |
+
"single_word": false,
|
347 |
+
"special": true
|
348 |
+
},
|
349 |
+
"128043": {
|
350 |
+
"content": "<|reserved_special_token_35|>",
|
351 |
+
"lstrip": false,
|
352 |
+
"normalized": false,
|
353 |
+
"rstrip": false,
|
354 |
+
"single_word": false,
|
355 |
+
"special": true
|
356 |
+
},
|
357 |
+
"128044": {
|
358 |
+
"content": "<|reserved_special_token_36|>",
|
359 |
+
"lstrip": false,
|
360 |
+
"normalized": false,
|
361 |
+
"rstrip": false,
|
362 |
+
"single_word": false,
|
363 |
+
"special": true
|
364 |
+
},
|
365 |
+
"128045": {
|
366 |
+
"content": "<|reserved_special_token_37|>",
|
367 |
+
"lstrip": false,
|
368 |
+
"normalized": false,
|
369 |
+
"rstrip": false,
|
370 |
+
"single_word": false,
|
371 |
+
"special": true
|
372 |
+
},
|
373 |
+
"128046": {
|
374 |
+
"content": "<|reserved_special_token_38|>",
|
375 |
+
"lstrip": false,
|
376 |
+
"normalized": false,
|
377 |
+
"rstrip": false,
|
378 |
+
"single_word": false,
|
379 |
+
"special": true
|
380 |
+
},
|
381 |
+
"128047": {
|
382 |
+
"content": "<|reserved_special_token_39|>",
|
383 |
+
"lstrip": false,
|
384 |
+
"normalized": false,
|
385 |
+
"rstrip": false,
|
386 |
+
"single_word": false,
|
387 |
+
"special": true
|
388 |
+
},
|
389 |
+
"128048": {
|
390 |
+
"content": "<|reserved_special_token_40|>",
|
391 |
+
"lstrip": false,
|
392 |
+
"normalized": false,
|
393 |
+
"rstrip": false,
|
394 |
+
"single_word": false,
|
395 |
+
"special": true
|
396 |
+
},
|
397 |
+
"128049": {
|
398 |
+
"content": "<|reserved_special_token_41|>",
|
399 |
+
"lstrip": false,
|
400 |
+
"normalized": false,
|
401 |
+
"rstrip": false,
|
402 |
+
"single_word": false,
|
403 |
+
"special": true
|
404 |
+
},
|
405 |
+
"128050": {
|
406 |
+
"content": "<|reserved_special_token_42|>",
|
407 |
+
"lstrip": false,
|
408 |
+
"normalized": false,
|
409 |
+
"rstrip": false,
|
410 |
+
"single_word": false,
|
411 |
+
"special": true
|
412 |
+
},
|
413 |
+
"128051": {
|
414 |
+
"content": "<|reserved_special_token_43|>",
|
415 |
+
"lstrip": false,
|
416 |
+
"normalized": false,
|
417 |
+
"rstrip": false,
|
418 |
+
"single_word": false,
|
419 |
+
"special": true
|
420 |
+
},
|
421 |
+
"128052": {
|
422 |
+
"content": "<|reserved_special_token_44|>",
|
423 |
+
"lstrip": false,
|
424 |
+
"normalized": false,
|
425 |
+
"rstrip": false,
|
426 |
+
"single_word": false,
|
427 |
+
"special": true
|
428 |
+
},
|
429 |
+
"128053": {
|
430 |
+
"content": "<|reserved_special_token_45|>",
|
431 |
+
"lstrip": false,
|
432 |
+
"normalized": false,
|
433 |
+
"rstrip": false,
|
434 |
+
"single_word": false,
|
435 |
+
"special": true
|
436 |
+
},
|
437 |
+
"128054": {
|
438 |
+
"content": "<|reserved_special_token_46|>",
|
439 |
+
"lstrip": false,
|
440 |
+
"normalized": false,
|
441 |
+
"rstrip": false,
|
442 |
+
"single_word": false,
|
443 |
+
"special": true
|
444 |
+
},
|
445 |
+
"128055": {
|
446 |
+
"content": "<|reserved_special_token_47|>",
|
447 |
+
"lstrip": false,
|
448 |
+
"normalized": false,
|
449 |
+
"rstrip": false,
|
450 |
+
"single_word": false,
|
451 |
+
"special": true
|
452 |
+
},
|
453 |
+
"128056": {
|
454 |
+
"content": "<|reserved_special_token_48|>",
|
455 |
+
"lstrip": false,
|
456 |
+
"normalized": false,
|
457 |
+
"rstrip": false,
|
458 |
+
"single_word": false,
|
459 |
+
"special": true
|
460 |
+
},
|
461 |
+
"128057": {
|
462 |
+
"content": "<|reserved_special_token_49|>",
|
463 |
+
"lstrip": false,
|
464 |
+
"normalized": false,
|
465 |
+
"rstrip": false,
|
466 |
+
"single_word": false,
|
467 |
+
"special": true
|
468 |
+
},
|
469 |
+
"128058": {
|
470 |
+
"content": "<|reserved_special_token_50|>",
|
471 |
+
"lstrip": false,
|
472 |
+
"normalized": false,
|
473 |
+
"rstrip": false,
|
474 |
+
"single_word": false,
|
475 |
+
"special": true
|
476 |
+
},
|
477 |
+
"128059": {
|
478 |
+
"content": "<|reserved_special_token_51|>",
|
479 |
+
"lstrip": false,
|
480 |
+
"normalized": false,
|
481 |
+
"rstrip": false,
|
482 |
+
"single_word": false,
|
483 |
+
"special": true
|
484 |
+
},
|
485 |
+
"128060": {
|
486 |
+
"content": "<|reserved_special_token_52|>",
|
487 |
+
"lstrip": false,
|
488 |
+
"normalized": false,
|
489 |
+
"rstrip": false,
|
490 |
+
"single_word": false,
|
491 |
+
"special": true
|
492 |
+
},
|
493 |
+
"128061": {
|
494 |
+
"content": "<|reserved_special_token_53|>",
|
495 |
+
"lstrip": false,
|
496 |
+
"normalized": false,
|
497 |
+
"rstrip": false,
|
498 |
+
"single_word": false,
|
499 |
+
"special": true
|
500 |
+
},
|
501 |
+
"128062": {
|
502 |
+
"content": "<|reserved_special_token_54|>",
|
503 |
+
"lstrip": false,
|
504 |
+
"normalized": false,
|
505 |
+
"rstrip": false,
|
506 |
+
"single_word": false,
|
507 |
+
"special": true
|
508 |
+
},
|
509 |
+
"128063": {
|
510 |
+
"content": "<|reserved_special_token_55|>",
|
511 |
+
"lstrip": false,
|
512 |
+
"normalized": false,
|
513 |
+
"rstrip": false,
|
514 |
+
"single_word": false,
|
515 |
+
"special": true
|
516 |
+
},
|
517 |
+
"128064": {
|
518 |
+
"content": "<|reserved_special_token_56|>",
|
519 |
+
"lstrip": false,
|
520 |
+
"normalized": false,
|
521 |
+
"rstrip": false,
|
522 |
+
"single_word": false,
|
523 |
+
"special": true
|
524 |
+
},
|
525 |
+
"128065": {
|
526 |
+
"content": "<|reserved_special_token_57|>",
|
527 |
+
"lstrip": false,
|
528 |
+
"normalized": false,
|
529 |
+
"rstrip": false,
|
530 |
+
"single_word": false,
|
531 |
+
"special": true
|
532 |
+
},
|
533 |
+
"128066": {
|
534 |
+
"content": "<|reserved_special_token_58|>",
|
535 |
+
"lstrip": false,
|
536 |
+
"normalized": false,
|
537 |
+
"rstrip": false,
|
538 |
+
"single_word": false,
|
539 |
+
"special": true
|
540 |
+
},
|
541 |
+
"128067": {
|
542 |
+
"content": "<|reserved_special_token_59|>",
|
543 |
+
"lstrip": false,
|
544 |
+
"normalized": false,
|
545 |
+
"rstrip": false,
|
546 |
+
"single_word": false,
|
547 |
+
"special": true
|
548 |
+
},
|
549 |
+
"128068": {
|
550 |
+
"content": "<|reserved_special_token_60|>",
|
551 |
+
"lstrip": false,
|
552 |
+
"normalized": false,
|
553 |
+
"rstrip": false,
|
554 |
+
"single_word": false,
|
555 |
+
"special": true
|
556 |
+
},
|
557 |
+
"128069": {
|
558 |
+
"content": "<|reserved_special_token_61|>",
|
559 |
+
"lstrip": false,
|
560 |
+
"normalized": false,
|
561 |
+
"rstrip": false,
|
562 |
+
"single_word": false,
|
563 |
+
"special": true
|
564 |
+
},
|
565 |
+
"128070": {
|
566 |
+
"content": "<|reserved_special_token_62|>",
|
567 |
+
"lstrip": false,
|
568 |
+
"normalized": false,
|
569 |
+
"rstrip": false,
|
570 |
+
"single_word": false,
|
571 |
+
"special": true
|
572 |
+
},
|
573 |
+
"128071": {
|
574 |
+
"content": "<|reserved_special_token_63|>",
|
575 |
+
"lstrip": false,
|
576 |
+
"normalized": false,
|
577 |
+
"rstrip": false,
|
578 |
+
"single_word": false,
|
579 |
+
"special": true
|
580 |
+
},
|
581 |
+
"128072": {
|
582 |
+
"content": "<|reserved_special_token_64|>",
|
583 |
+
"lstrip": false,
|
584 |
+
"normalized": false,
|
585 |
+
"rstrip": false,
|
586 |
+
"single_word": false,
|
587 |
+
"special": true
|
588 |
+
},
|
589 |
+
"128073": {
|
590 |
+
"content": "<|reserved_special_token_65|>",
|
591 |
+
"lstrip": false,
|
592 |
+
"normalized": false,
|
593 |
+
"rstrip": false,
|
594 |
+
"single_word": false,
|
595 |
+
"special": true
|
596 |
+
},
|
597 |
+
"128074": {
|
598 |
+
"content": "<|reserved_special_token_66|>",
|
599 |
+
"lstrip": false,
|
600 |
+
"normalized": false,
|
601 |
+
"rstrip": false,
|
602 |
+
"single_word": false,
|
603 |
+
"special": true
|
604 |
+
},
|
605 |
+
"128075": {
|
606 |
+
"content": "<|reserved_special_token_67|>",
|
607 |
+
"lstrip": false,
|
608 |
+
"normalized": false,
|
609 |
+
"rstrip": false,
|
610 |
+
"single_word": false,
|
611 |
+
"special": true
|
612 |
+
},
|
613 |
+
"128076": {
|
614 |
+
"content": "<|reserved_special_token_68|>",
|
615 |
+
"lstrip": false,
|
616 |
+
"normalized": false,
|
617 |
+
"rstrip": false,
|
618 |
+
"single_word": false,
|
619 |
+
"special": true
|
620 |
+
},
|
621 |
+
"128077": {
|
622 |
+
"content": "<|reserved_special_token_69|>",
|
623 |
+
"lstrip": false,
|
624 |
+
"normalized": false,
|
625 |
+
"rstrip": false,
|
626 |
+
"single_word": false,
|
627 |
+
"special": true
|
628 |
+
},
|
629 |
+
"128078": {
|
630 |
+
"content": "<|reserved_special_token_70|>",
|
631 |
+
"lstrip": false,
|
632 |
+
"normalized": false,
|
633 |
+
"rstrip": false,
|
634 |
+
"single_word": false,
|
635 |
+
"special": true
|
636 |
+
},
|
637 |
+
"128079": {
|
638 |
+
"content": "<|reserved_special_token_71|>",
|
639 |
+
"lstrip": false,
|
640 |
+
"normalized": false,
|
641 |
+
"rstrip": false,
|
642 |
+
"single_word": false,
|
643 |
+
"special": true
|
644 |
+
},
|
645 |
+
"128080": {
|
646 |
+
"content": "<|reserved_special_token_72|>",
|
647 |
+
"lstrip": false,
|
648 |
+
"normalized": false,
|
649 |
+
"rstrip": false,
|
650 |
+
"single_word": false,
|
651 |
+
"special": true
|
652 |
+
},
|
653 |
+
"128081": {
|
654 |
+
"content": "<|reserved_special_token_73|>",
|
655 |
+
"lstrip": false,
|
656 |
+
"normalized": false,
|
657 |
+
"rstrip": false,
|
658 |
+
"single_word": false,
|
659 |
+
"special": true
|
660 |
+
},
|
661 |
+
"128082": {
|
662 |
+
"content": "<|reserved_special_token_74|>",
|
663 |
+
"lstrip": false,
|
664 |
+
"normalized": false,
|
665 |
+
"rstrip": false,
|
666 |
+
"single_word": false,
|
667 |
+
"special": true
|
668 |
+
},
|
669 |
+
"128083": {
|
670 |
+
"content": "<|reserved_special_token_75|>",
|
671 |
+
"lstrip": false,
|
672 |
+
"normalized": false,
|
673 |
+
"rstrip": false,
|
674 |
+
"single_word": false,
|
675 |
+
"special": true
|
676 |
+
},
|
677 |
+
"128084": {
|
678 |
+
"content": "<|reserved_special_token_76|>",
|
679 |
+
"lstrip": false,
|
680 |
+
"normalized": false,
|
681 |
+
"rstrip": false,
|
682 |
+
"single_word": false,
|
683 |
+
"special": true
|
684 |
+
},
|
685 |
+
"128085": {
|
686 |
+
"content": "<|reserved_special_token_77|>",
|
687 |
+
"lstrip": false,
|
688 |
+
"normalized": false,
|
689 |
+
"rstrip": false,
|
690 |
+
"single_word": false,
|
691 |
+
"special": true
|
692 |
+
},
|
693 |
+
"128086": {
|
694 |
+
"content": "<|reserved_special_token_78|>",
|
695 |
+
"lstrip": false,
|
696 |
+
"normalized": false,
|
697 |
+
"rstrip": false,
|
698 |
+
"single_word": false,
|
699 |
+
"special": true
|
700 |
+
},
|
701 |
+
"128087": {
|
702 |
+
"content": "<|reserved_special_token_79|>",
|
703 |
+
"lstrip": false,
|
704 |
+
"normalized": false,
|
705 |
+
"rstrip": false,
|
706 |
+
"single_word": false,
|
707 |
+
"special": true
|
708 |
+
},
|
709 |
+
"128088": {
|
710 |
+
"content": "<|reserved_special_token_80|>",
|
711 |
+
"lstrip": false,
|
712 |
+
"normalized": false,
|
713 |
+
"rstrip": false,
|
714 |
+
"single_word": false,
|
715 |
+
"special": true
|
716 |
+
},
|
717 |
+
"128089": {
|
718 |
+
"content": "<|reserved_special_token_81|>",
|
719 |
+
"lstrip": false,
|
720 |
+
"normalized": false,
|
721 |
+
"rstrip": false,
|
722 |
+
"single_word": false,
|
723 |
+
"special": true
|
724 |
+
},
|
725 |
+
"128090": {
|
726 |
+
"content": "<|reserved_special_token_82|>",
|
727 |
+
"lstrip": false,
|
728 |
+
"normalized": false,
|
729 |
+
"rstrip": false,
|
730 |
+
"single_word": false,
|
731 |
+
"special": true
|
732 |
+
},
|
733 |
+
"128091": {
|
734 |
+
"content": "<|reserved_special_token_83|>",
|
735 |
+
"lstrip": false,
|
736 |
+
"normalized": false,
|
737 |
+
"rstrip": false,
|
738 |
+
"single_word": false,
|
739 |
+
"special": true
|
740 |
+
},
|
741 |
+
"128092": {
|
742 |
+
"content": "<|reserved_special_token_84|>",
|
743 |
+
"lstrip": false,
|
744 |
+
"normalized": false,
|
745 |
+
"rstrip": false,
|
746 |
+
"single_word": false,
|
747 |
+
"special": true
|
748 |
+
},
|
749 |
+
"128093": {
|
750 |
+
"content": "<|reserved_special_token_85|>",
|
751 |
+
"lstrip": false,
|
752 |
+
"normalized": false,
|
753 |
+
"rstrip": false,
|
754 |
+
"single_word": false,
|
755 |
+
"special": true
|
756 |
+
},
|
757 |
+
"128094": {
|
758 |
+
"content": "<|reserved_special_token_86|>",
|
759 |
+
"lstrip": false,
|
760 |
+
"normalized": false,
|
761 |
+
"rstrip": false,
|
762 |
+
"single_word": false,
|
763 |
+
"special": true
|
764 |
+
},
|
765 |
+
"128095": {
|
766 |
+
"content": "<|reserved_special_token_87|>",
|
767 |
+
"lstrip": false,
|
768 |
+
"normalized": false,
|
769 |
+
"rstrip": false,
|
770 |
+
"single_word": false,
|
771 |
+
"special": true
|
772 |
+
},
|
773 |
+
"128096": {
|
774 |
+
"content": "<|reserved_special_token_88|>",
|
775 |
+
"lstrip": false,
|
776 |
+
"normalized": false,
|
777 |
+
"rstrip": false,
|
778 |
+
"single_word": false,
|
779 |
+
"special": true
|
780 |
+
},
|
781 |
+
"128097": {
|
782 |
+
"content": "<|reserved_special_token_89|>",
|
783 |
+
"lstrip": false,
|
784 |
+
"normalized": false,
|
785 |
+
"rstrip": false,
|
786 |
+
"single_word": false,
|
787 |
+
"special": true
|
788 |
+
},
|
789 |
+
"128098": {
|
790 |
+
"content": "<|reserved_special_token_90|>",
|
791 |
+
"lstrip": false,
|
792 |
+
"normalized": false,
|
793 |
+
"rstrip": false,
|
794 |
+
"single_word": false,
|
795 |
+
"special": true
|
796 |
+
},
|
797 |
+
"128099": {
|
798 |
+
"content": "<|reserved_special_token_91|>",
|
799 |
+
"lstrip": false,
|
800 |
+
"normalized": false,
|
801 |
+
"rstrip": false,
|
802 |
+
"single_word": false,
|
803 |
+
"special": true
|
804 |
+
},
|
805 |
+
"128100": {
|
806 |
+
"content": "<|reserved_special_token_92|>",
|
807 |
+
"lstrip": false,
|
808 |
+
"normalized": false,
|
809 |
+
"rstrip": false,
|
810 |
+
"single_word": false,
|
811 |
+
"special": true
|
812 |
+
},
|
813 |
+
"128101": {
|
814 |
+
"content": "<|reserved_special_token_93|>",
|
815 |
+
"lstrip": false,
|
816 |
+
"normalized": false,
|
817 |
+
"rstrip": false,
|
818 |
+
"single_word": false,
|
819 |
+
"special": true
|
820 |
+
},
|
821 |
+
"128102": {
|
822 |
+
"content": "<|reserved_special_token_94|>",
|
823 |
+
"lstrip": false,
|
824 |
+
"normalized": false,
|
825 |
+
"rstrip": false,
|
826 |
+
"single_word": false,
|
827 |
+
"special": true
|
828 |
+
},
|
829 |
+
"128103": {
|
830 |
+
"content": "<|reserved_special_token_95|>",
|
831 |
+
"lstrip": false,
|
832 |
+
"normalized": false,
|
833 |
+
"rstrip": false,
|
834 |
+
"single_word": false,
|
835 |
+
"special": true
|
836 |
+
},
|
837 |
+
"128104": {
|
838 |
+
"content": "<|reserved_special_token_96|>",
|
839 |
+
"lstrip": false,
|
840 |
+
"normalized": false,
|
841 |
+
"rstrip": false,
|
842 |
+
"single_word": false,
|
843 |
+
"special": true
|
844 |
+
},
|
845 |
+
"128105": {
|
846 |
+
"content": "<|reserved_special_token_97|>",
|
847 |
+
"lstrip": false,
|
848 |
+
"normalized": false,
|
849 |
+
"rstrip": false,
|
850 |
+
"single_word": false,
|
851 |
+
"special": true
|
852 |
+
},
|
853 |
+
"128106": {
|
854 |
+
"content": "<|reserved_special_token_98|>",
|
855 |
+
"lstrip": false,
|
856 |
+
"normalized": false,
|
857 |
+
"rstrip": false,
|
858 |
+
"single_word": false,
|
859 |
+
"special": true
|
860 |
+
},
|
861 |
+
"128107": {
|
862 |
+
"content": "<|reserved_special_token_99|>",
|
863 |
+
"lstrip": false,
|
864 |
+
"normalized": false,
|
865 |
+
"rstrip": false,
|
866 |
+
"single_word": false,
|
867 |
+
"special": true
|
868 |
+
},
|
869 |
+
"128108": {
|
870 |
+
"content": "<|reserved_special_token_100|>",
|
871 |
+
"lstrip": false,
|
872 |
+
"normalized": false,
|
873 |
+
"rstrip": false,
|
874 |
+
"single_word": false,
|
875 |
+
"special": true
|
876 |
+
},
|
877 |
+
"128109": {
|
878 |
+
"content": "<|reserved_special_token_101|>",
|
879 |
+
"lstrip": false,
|
880 |
+
"normalized": false,
|
881 |
+
"rstrip": false,
|
882 |
+
"single_word": false,
|
883 |
+
"special": true
|
884 |
+
},
|
885 |
+
"128110": {
|
886 |
+
"content": "<|reserved_special_token_102|>",
|
887 |
+
"lstrip": false,
|
888 |
+
"normalized": false,
|
889 |
+
"rstrip": false,
|
890 |
+
"single_word": false,
|
891 |
+
"special": true
|
892 |
+
},
|
893 |
+
"128111": {
|
894 |
+
"content": "<|reserved_special_token_103|>",
|
895 |
+
"lstrip": false,
|
896 |
+
"normalized": false,
|
897 |
+
"rstrip": false,
|
898 |
+
"single_word": false,
|
899 |
+
"special": true
|
900 |
+
},
|
901 |
+
"128112": {
|
902 |
+
"content": "<|reserved_special_token_104|>",
|
903 |
+
"lstrip": false,
|
904 |
+
"normalized": false,
|
905 |
+
"rstrip": false,
|
906 |
+
"single_word": false,
|
907 |
+
"special": true
|
908 |
+
},
|
909 |
+
"128113": {
|
910 |
+
"content": "<|reserved_special_token_105|>",
|
911 |
+
"lstrip": false,
|
912 |
+
"normalized": false,
|
913 |
+
"rstrip": false,
|
914 |
+
"single_word": false,
|
915 |
+
"special": true
|
916 |
+
},
|
917 |
+
"128114": {
|
918 |
+
"content": "<|reserved_special_token_106|>",
|
919 |
+
"lstrip": false,
|
920 |
+
"normalized": false,
|
921 |
+
"rstrip": false,
|
922 |
+
"single_word": false,
|
923 |
+
"special": true
|
924 |
+
},
|
925 |
+
"128115": {
|
926 |
+
"content": "<|reserved_special_token_107|>",
|
927 |
+
"lstrip": false,
|
928 |
+
"normalized": false,
|
929 |
+
"rstrip": false,
|
930 |
+
"single_word": false,
|
931 |
+
"special": true
|
932 |
+
},
|
933 |
+
"128116": {
|
934 |
+
"content": "<|reserved_special_token_108|>",
|
935 |
+
"lstrip": false,
|
936 |
+
"normalized": false,
|
937 |
+
"rstrip": false,
|
938 |
+
"single_word": false,
|
939 |
+
"special": true
|
940 |
+
},
|
941 |
+
"128117": {
|
942 |
+
"content": "<|reserved_special_token_109|>",
|
943 |
+
"lstrip": false,
|
944 |
+
"normalized": false,
|
945 |
+
"rstrip": false,
|
946 |
+
"single_word": false,
|
947 |
+
"special": true
|
948 |
+
},
|
949 |
+
"128118": {
|
950 |
+
"content": "<|reserved_special_token_110|>",
|
951 |
+
"lstrip": false,
|
952 |
+
"normalized": false,
|
953 |
+
"rstrip": false,
|
954 |
+
"single_word": false,
|
955 |
+
"special": true
|
956 |
+
},
|
957 |
+
"128119": {
|
958 |
+
"content": "<|reserved_special_token_111|>",
|
959 |
+
"lstrip": false,
|
960 |
+
"normalized": false,
|
961 |
+
"rstrip": false,
|
962 |
+
"single_word": false,
|
963 |
+
"special": true
|
964 |
+
},
|
965 |
+
"128120": {
|
966 |
+
"content": "<|reserved_special_token_112|>",
|
967 |
+
"lstrip": false,
|
968 |
+
"normalized": false,
|
969 |
+
"rstrip": false,
|
970 |
+
"single_word": false,
|
971 |
+
"special": true
|
972 |
+
},
|
973 |
+
"128121": {
|
974 |
+
"content": "<|reserved_special_token_113|>",
|
975 |
+
"lstrip": false,
|
976 |
+
"normalized": false,
|
977 |
+
"rstrip": false,
|
978 |
+
"single_word": false,
|
979 |
+
"special": true
|
980 |
+
},
|
981 |
+
"128122": {
|
982 |
+
"content": "<|reserved_special_token_114|>",
|
983 |
+
"lstrip": false,
|
984 |
+
"normalized": false,
|
985 |
+
"rstrip": false,
|
986 |
+
"single_word": false,
|
987 |
+
"special": true
|
988 |
+
},
|
989 |
+
"128123": {
|
990 |
+
"content": "<|reserved_special_token_115|>",
|
991 |
+
"lstrip": false,
|
992 |
+
"normalized": false,
|
993 |
+
"rstrip": false,
|
994 |
+
"single_word": false,
|
995 |
+
"special": true
|
996 |
+
},
|
997 |
+
"128124": {
|
998 |
+
"content": "<|reserved_special_token_116|>",
|
999 |
+
"lstrip": false,
|
1000 |
+
"normalized": false,
|
1001 |
+
"rstrip": false,
|
1002 |
+
"single_word": false,
|
1003 |
+
"special": true
|
1004 |
+
},
|
1005 |
+
"128125": {
|
1006 |
+
"content": "<|reserved_special_token_117|>",
|
1007 |
+
"lstrip": false,
|
1008 |
+
"normalized": false,
|
1009 |
+
"rstrip": false,
|
1010 |
+
"single_word": false,
|
1011 |
+
"special": true
|
1012 |
+
},
|
1013 |
+
"128126": {
|
1014 |
+
"content": "<|reserved_special_token_118|>",
|
1015 |
+
"lstrip": false,
|
1016 |
+
"normalized": false,
|
1017 |
+
"rstrip": false,
|
1018 |
+
"single_word": false,
|
1019 |
+
"special": true
|
1020 |
+
},
|
1021 |
+
"128127": {
|
1022 |
+
"content": "<|reserved_special_token_119|>",
|
1023 |
+
"lstrip": false,
|
1024 |
+
"normalized": false,
|
1025 |
+
"rstrip": false,
|
1026 |
+
"single_word": false,
|
1027 |
+
"special": true
|
1028 |
+
},
|
1029 |
+
"128128": {
|
1030 |
+
"content": "<|reserved_special_token_120|>",
|
1031 |
+
"lstrip": false,
|
1032 |
+
"normalized": false,
|
1033 |
+
"rstrip": false,
|
1034 |
+
"single_word": false,
|
1035 |
+
"special": true
|
1036 |
+
},
|
1037 |
+
"128129": {
|
1038 |
+
"content": "<|reserved_special_token_121|>",
|
1039 |
+
"lstrip": false,
|
1040 |
+
"normalized": false,
|
1041 |
+
"rstrip": false,
|
1042 |
+
"single_word": false,
|
1043 |
+
"special": true
|
1044 |
+
},
|
1045 |
+
"128130": {
|
1046 |
+
"content": "<|reserved_special_token_122|>",
|
1047 |
+
"lstrip": false,
|
1048 |
+
"normalized": false,
|
1049 |
+
"rstrip": false,
|
1050 |
+
"single_word": false,
|
1051 |
+
"special": true
|
1052 |
+
},
|
1053 |
+
"128131": {
|
1054 |
+
"content": "<|reserved_special_token_123|>",
|
1055 |
+
"lstrip": false,
|
1056 |
+
"normalized": false,
|
1057 |
+
"rstrip": false,
|
1058 |
+
"single_word": false,
|
1059 |
+
"special": true
|
1060 |
+
},
|
1061 |
+
"128132": {
|
1062 |
+
"content": "<|reserved_special_token_124|>",
|
1063 |
+
"lstrip": false,
|
1064 |
+
"normalized": false,
|
1065 |
+
"rstrip": false,
|
1066 |
+
"single_word": false,
|
1067 |
+
"special": true
|
1068 |
+
},
|
1069 |
+
"128133": {
|
1070 |
+
"content": "<|reserved_special_token_125|>",
|
1071 |
+
"lstrip": false,
|
1072 |
+
"normalized": false,
|
1073 |
+
"rstrip": false,
|
1074 |
+
"single_word": false,
|
1075 |
+
"special": true
|
1076 |
+
},
|
1077 |
+
"128134": {
|
1078 |
+
"content": "<|reserved_special_token_126|>",
|
1079 |
+
"lstrip": false,
|
1080 |
+
"normalized": false,
|
1081 |
+
"rstrip": false,
|
1082 |
+
"single_word": false,
|
1083 |
+
"special": true
|
1084 |
+
},
|
1085 |
+
"128135": {
|
1086 |
+
"content": "<|reserved_special_token_127|>",
|
1087 |
+
"lstrip": false,
|
1088 |
+
"normalized": false,
|
1089 |
+
"rstrip": false,
|
1090 |
+
"single_word": false,
|
1091 |
+
"special": true
|
1092 |
+
},
|
1093 |
+
"128136": {
|
1094 |
+
"content": "<|reserved_special_token_128|>",
|
1095 |
+
"lstrip": false,
|
1096 |
+
"normalized": false,
|
1097 |
+
"rstrip": false,
|
1098 |
+
"single_word": false,
|
1099 |
+
"special": true
|
1100 |
+
},
|
1101 |
+
"128137": {
|
1102 |
+
"content": "<|reserved_special_token_129|>",
|
1103 |
+
"lstrip": false,
|
1104 |
+
"normalized": false,
|
1105 |
+
"rstrip": false,
|
1106 |
+
"single_word": false,
|
1107 |
+
"special": true
|
1108 |
+
},
|
1109 |
+
"128138": {
|
1110 |
+
"content": "<|reserved_special_token_130|>",
|
1111 |
+
"lstrip": false,
|
1112 |
+
"normalized": false,
|
1113 |
+
"rstrip": false,
|
1114 |
+
"single_word": false,
|
1115 |
+
"special": true
|
1116 |
+
},
|
1117 |
+
"128139": {
|
1118 |
+
"content": "<|reserved_special_token_131|>",
|
1119 |
+
"lstrip": false,
|
1120 |
+
"normalized": false,
|
1121 |
+
"rstrip": false,
|
1122 |
+
"single_word": false,
|
1123 |
+
"special": true
|
1124 |
+
},
|
1125 |
+
"128140": {
|
1126 |
+
"content": "<|reserved_special_token_132|>",
|
1127 |
+
"lstrip": false,
|
1128 |
+
"normalized": false,
|
1129 |
+
"rstrip": false,
|
1130 |
+
"single_word": false,
|
1131 |
+
"special": true
|
1132 |
+
},
|
1133 |
+
"128141": {
|
1134 |
+
"content": "<|reserved_special_token_133|>",
|
1135 |
+
"lstrip": false,
|
1136 |
+
"normalized": false,
|
1137 |
+
"rstrip": false,
|
1138 |
+
"single_word": false,
|
1139 |
+
"special": true
|
1140 |
+
},
|
1141 |
+
"128142": {
|
1142 |
+
"content": "<|reserved_special_token_134|>",
|
1143 |
+
"lstrip": false,
|
1144 |
+
"normalized": false,
|
1145 |
+
"rstrip": false,
|
1146 |
+
"single_word": false,
|
1147 |
+
"special": true
|
1148 |
+
},
|
1149 |
+
"128143": {
|
1150 |
+
"content": "<|reserved_special_token_135|>",
|
1151 |
+
"lstrip": false,
|
1152 |
+
"normalized": false,
|
1153 |
+
"rstrip": false,
|
1154 |
+
"single_word": false,
|
1155 |
+
"special": true
|
1156 |
+
},
|
1157 |
+
"128144": {
|
1158 |
+
"content": "<|reserved_special_token_136|>",
|
1159 |
+
"lstrip": false,
|
1160 |
+
"normalized": false,
|
1161 |
+
"rstrip": false,
|
1162 |
+
"single_word": false,
|
1163 |
+
"special": true
|
1164 |
+
},
|
1165 |
+
"128145": {
|
1166 |
+
"content": "<|reserved_special_token_137|>",
|
1167 |
+
"lstrip": false,
|
1168 |
+
"normalized": false,
|
1169 |
+
"rstrip": false,
|
1170 |
+
"single_word": false,
|
1171 |
+
"special": true
|
1172 |
+
},
|
1173 |
+
"128146": {
|
1174 |
+
"content": "<|reserved_special_token_138|>",
|
1175 |
+
"lstrip": false,
|
1176 |
+
"normalized": false,
|
1177 |
+
"rstrip": false,
|
1178 |
+
"single_word": false,
|
1179 |
+
"special": true
|
1180 |
+
},
|
1181 |
+
"128147": {
|
1182 |
+
"content": "<|reserved_special_token_139|>",
|
1183 |
+
"lstrip": false,
|
1184 |
+
"normalized": false,
|
1185 |
+
"rstrip": false,
|
1186 |
+
"single_word": false,
|
1187 |
+
"special": true
|
1188 |
+
},
|
1189 |
+
"128148": {
|
1190 |
+
"content": "<|reserved_special_token_140|>",
|
1191 |
+
"lstrip": false,
|
1192 |
+
"normalized": false,
|
1193 |
+
"rstrip": false,
|
1194 |
+
"single_word": false,
|
1195 |
+
"special": true
|
1196 |
+
},
|
1197 |
+
"128149": {
|
1198 |
+
"content": "<|reserved_special_token_141|>",
|
1199 |
+
"lstrip": false,
|
1200 |
+
"normalized": false,
|
1201 |
+
"rstrip": false,
|
1202 |
+
"single_word": false,
|
1203 |
+
"special": true
|
1204 |
+
},
|
1205 |
+
"128150": {
|
1206 |
+
"content": "<|reserved_special_token_142|>",
|
1207 |
+
"lstrip": false,
|
1208 |
+
"normalized": false,
|
1209 |
+
"rstrip": false,
|
1210 |
+
"single_word": false,
|
1211 |
+
"special": true
|
1212 |
+
},
|
1213 |
+
"128151": {
|
1214 |
+
"content": "<|reserved_special_token_143|>",
|
1215 |
+
"lstrip": false,
|
1216 |
+
"normalized": false,
|
1217 |
+
"rstrip": false,
|
1218 |
+
"single_word": false,
|
1219 |
+
"special": true
|
1220 |
+
},
|
1221 |
+
"128152": {
|
1222 |
+
"content": "<|reserved_special_token_144|>",
|
1223 |
+
"lstrip": false,
|
1224 |
+
"normalized": false,
|
1225 |
+
"rstrip": false,
|
1226 |
+
"single_word": false,
|
1227 |
+
"special": true
|
1228 |
+
},
|
1229 |
+
"128153": {
|
1230 |
+
"content": "<|reserved_special_token_145|>",
|
1231 |
+
"lstrip": false,
|
1232 |
+
"normalized": false,
|
1233 |
+
"rstrip": false,
|
1234 |
+
"single_word": false,
|
1235 |
+
"special": true
|
1236 |
+
},
|
1237 |
+
"128154": {
|
1238 |
+
"content": "<|reserved_special_token_146|>",
|
1239 |
+
"lstrip": false,
|
1240 |
+
"normalized": false,
|
1241 |
+
"rstrip": false,
|
1242 |
+
"single_word": false,
|
1243 |
+
"special": true
|
1244 |
+
},
|
1245 |
+
"128155": {
|
1246 |
+
"content": "<|reserved_special_token_147|>",
|
1247 |
+
"lstrip": false,
|
1248 |
+
"normalized": false,
|
1249 |
+
"rstrip": false,
|
1250 |
+
"single_word": false,
|
1251 |
+
"special": true
|
1252 |
+
},
|
1253 |
+
"128156": {
|
1254 |
+
"content": "<|reserved_special_token_148|>",
|
1255 |
+
"lstrip": false,
|
1256 |
+
"normalized": false,
|
1257 |
+
"rstrip": false,
|
1258 |
+
"single_word": false,
|
1259 |
+
"special": true
|
1260 |
+
},
|
1261 |
+
"128157": {
|
1262 |
+
"content": "<|reserved_special_token_149|>",
|
1263 |
+
"lstrip": false,
|
1264 |
+
"normalized": false,
|
1265 |
+
"rstrip": false,
|
1266 |
+
"single_word": false,
|
1267 |
+
"special": true
|
1268 |
+
},
|
1269 |
+
"128158": {
|
1270 |
+
"content": "<|reserved_special_token_150|>",
|
1271 |
+
"lstrip": false,
|
1272 |
+
"normalized": false,
|
1273 |
+
"rstrip": false,
|
1274 |
+
"single_word": false,
|
1275 |
+
"special": true
|
1276 |
+
},
|
1277 |
+
"128159": {
|
1278 |
+
"content": "<|reserved_special_token_151|>",
|
1279 |
+
"lstrip": false,
|
1280 |
+
"normalized": false,
|
1281 |
+
"rstrip": false,
|
1282 |
+
"single_word": false,
|
1283 |
+
"special": true
|
1284 |
+
},
|
1285 |
+
"128160": {
|
1286 |
+
"content": "<|reserved_special_token_152|>",
|
1287 |
+
"lstrip": false,
|
1288 |
+
"normalized": false,
|
1289 |
+
"rstrip": false,
|
1290 |
+
"single_word": false,
|
1291 |
+
"special": true
|
1292 |
+
},
|
1293 |
+
"128161": {
|
1294 |
+
"content": "<|reserved_special_token_153|>",
|
1295 |
+
"lstrip": false,
|
1296 |
+
"normalized": false,
|
1297 |
+
"rstrip": false,
|
1298 |
+
"single_word": false,
|
1299 |
+
"special": true
|
1300 |
+
},
|
1301 |
+
"128162": {
|
1302 |
+
"content": "<|reserved_special_token_154|>",
|
1303 |
+
"lstrip": false,
|
1304 |
+
"normalized": false,
|
1305 |
+
"rstrip": false,
|
1306 |
+
"single_word": false,
|
1307 |
+
"special": true
|
1308 |
+
},
|
1309 |
+
"128163": {
|
1310 |
+
"content": "<|reserved_special_token_155|>",
|
1311 |
+
"lstrip": false,
|
1312 |
+
"normalized": false,
|
1313 |
+
"rstrip": false,
|
1314 |
+
"single_word": false,
|
1315 |
+
"special": true
|
1316 |
+
},
|
1317 |
+
"128164": {
|
1318 |
+
"content": "<|reserved_special_token_156|>",
|
1319 |
+
"lstrip": false,
|
1320 |
+
"normalized": false,
|
1321 |
+
"rstrip": false,
|
1322 |
+
"single_word": false,
|
1323 |
+
"special": true
|
1324 |
+
},
|
1325 |
+
"128165": {
|
1326 |
+
"content": "<|reserved_special_token_157|>",
|
1327 |
+
"lstrip": false,
|
1328 |
+
"normalized": false,
|
1329 |
+
"rstrip": false,
|
1330 |
+
"single_word": false,
|
1331 |
+
"special": true
|
1332 |
+
},
|
1333 |
+
"128166": {
|
1334 |
+
"content": "<|reserved_special_token_158|>",
|
1335 |
+
"lstrip": false,
|
1336 |
+
"normalized": false,
|
1337 |
+
"rstrip": false,
|
1338 |
+
"single_word": false,
|
1339 |
+
"special": true
|
1340 |
+
},
|
1341 |
+
"128167": {
|
1342 |
+
"content": "<|reserved_special_token_159|>",
|
1343 |
+
"lstrip": false,
|
1344 |
+
"normalized": false,
|
1345 |
+
"rstrip": false,
|
1346 |
+
"single_word": false,
|
1347 |
+
"special": true
|
1348 |
+
},
|
1349 |
+
"128168": {
|
1350 |
+
"content": "<|reserved_special_token_160|>",
|
1351 |
+
"lstrip": false,
|
1352 |
+
"normalized": false,
|
1353 |
+
"rstrip": false,
|
1354 |
+
"single_word": false,
|
1355 |
+
"special": true
|
1356 |
+
},
|
1357 |
+
"128169": {
|
1358 |
+
"content": "<|reserved_special_token_161|>",
|
1359 |
+
"lstrip": false,
|
1360 |
+
"normalized": false,
|
1361 |
+
"rstrip": false,
|
1362 |
+
"single_word": false,
|
1363 |
+
"special": true
|
1364 |
+
},
|
1365 |
+
"128170": {
|
1366 |
+
"content": "<|reserved_special_token_162|>",
|
1367 |
+
"lstrip": false,
|
1368 |
+
"normalized": false,
|
1369 |
+
"rstrip": false,
|
1370 |
+
"single_word": false,
|
1371 |
+
"special": true
|
1372 |
+
},
|
1373 |
+
"128171": {
|
1374 |
+
"content": "<|reserved_special_token_163|>",
|
1375 |
+
"lstrip": false,
|
1376 |
+
"normalized": false,
|
1377 |
+
"rstrip": false,
|
1378 |
+
"single_word": false,
|
1379 |
+
"special": true
|
1380 |
+
},
|
1381 |
+
"128172": {
|
1382 |
+
"content": "<|reserved_special_token_164|>",
|
1383 |
+
"lstrip": false,
|
1384 |
+
"normalized": false,
|
1385 |
+
"rstrip": false,
|
1386 |
+
"single_word": false,
|
1387 |
+
"special": true
|
1388 |
+
},
|
1389 |
+
"128173": {
|
1390 |
+
"content": "<|reserved_special_token_165|>",
|
1391 |
+
"lstrip": false,
|
1392 |
+
"normalized": false,
|
1393 |
+
"rstrip": false,
|
1394 |
+
"single_word": false,
|
1395 |
+
"special": true
|
1396 |
+
},
|
1397 |
+
"128174": {
|
1398 |
+
"content": "<|reserved_special_token_166|>",
|
1399 |
+
"lstrip": false,
|
1400 |
+
"normalized": false,
|
1401 |
+
"rstrip": false,
|
1402 |
+
"single_word": false,
|
1403 |
+
"special": true
|
1404 |
+
},
|
1405 |
+
"128175": {
|
1406 |
+
"content": "<|reserved_special_token_167|>",
|
1407 |
+
"lstrip": false,
|
1408 |
+
"normalized": false,
|
1409 |
+
"rstrip": false,
|
1410 |
+
"single_word": false,
|
1411 |
+
"special": true
|
1412 |
+
},
|
1413 |
+
"128176": {
|
1414 |
+
"content": "<|reserved_special_token_168|>",
|
1415 |
+
"lstrip": false,
|
1416 |
+
"normalized": false,
|
1417 |
+
"rstrip": false,
|
1418 |
+
"single_word": false,
|
1419 |
+
"special": true
|
1420 |
+
},
|
1421 |
+
"128177": {
|
1422 |
+
"content": "<|reserved_special_token_169|>",
|
1423 |
+
"lstrip": false,
|
1424 |
+
"normalized": false,
|
1425 |
+
"rstrip": false,
|
1426 |
+
"single_word": false,
|
1427 |
+
"special": true
|
1428 |
+
},
|
1429 |
+
"128178": {
|
1430 |
+
"content": "<|reserved_special_token_170|>",
|
1431 |
+
"lstrip": false,
|
1432 |
+
"normalized": false,
|
1433 |
+
"rstrip": false,
|
1434 |
+
"single_word": false,
|
1435 |
+
"special": true
|
1436 |
+
},
|
1437 |
+
"128179": {
|
1438 |
+
"content": "<|reserved_special_token_171|>",
|
1439 |
+
"lstrip": false,
|
1440 |
+
"normalized": false,
|
1441 |
+
"rstrip": false,
|
1442 |
+
"single_word": false,
|
1443 |
+
"special": true
|
1444 |
+
},
|
1445 |
+
"128180": {
|
1446 |
+
"content": "<|reserved_special_token_172|>",
|
1447 |
+
"lstrip": false,
|
1448 |
+
"normalized": false,
|
1449 |
+
"rstrip": false,
|
1450 |
+
"single_word": false,
|
1451 |
+
"special": true
|
1452 |
+
},
|
1453 |
+
"128181": {
|
1454 |
+
"content": "<|reserved_special_token_173|>",
|
1455 |
+
"lstrip": false,
|
1456 |
+
"normalized": false,
|
1457 |
+
"rstrip": false,
|
1458 |
+
"single_word": false,
|
1459 |
+
"special": true
|
1460 |
+
},
|
1461 |
+
"128182": {
|
1462 |
+
"content": "<|reserved_special_token_174|>",
|
1463 |
+
"lstrip": false,
|
1464 |
+
"normalized": false,
|
1465 |
+
"rstrip": false,
|
1466 |
+
"single_word": false,
|
1467 |
+
"special": true
|
1468 |
+
},
|
1469 |
+
"128183": {
|
1470 |
+
"content": "<|reserved_special_token_175|>",
|
1471 |
+
"lstrip": false,
|
1472 |
+
"normalized": false,
|
1473 |
+
"rstrip": false,
|
1474 |
+
"single_word": false,
|
1475 |
+
"special": true
|
1476 |
+
},
|
1477 |
+
"128184": {
|
1478 |
+
"content": "<|reserved_special_token_176|>",
|
1479 |
+
"lstrip": false,
|
1480 |
+
"normalized": false,
|
1481 |
+
"rstrip": false,
|
1482 |
+
"single_word": false,
|
1483 |
+
"special": true
|
1484 |
+
},
|
1485 |
+
"128185": {
|
1486 |
+
"content": "<|reserved_special_token_177|>",
|
1487 |
+
"lstrip": false,
|
1488 |
+
"normalized": false,
|
1489 |
+
"rstrip": false,
|
1490 |
+
"single_word": false,
|
1491 |
+
"special": true
|
1492 |
+
},
|
1493 |
+
"128186": {
|
1494 |
+
"content": "<|reserved_special_token_178|>",
|
1495 |
+
"lstrip": false,
|
1496 |
+
"normalized": false,
|
1497 |
+
"rstrip": false,
|
1498 |
+
"single_word": false,
|
1499 |
+
"special": true
|
1500 |
+
},
|
1501 |
+
"128187": {
|
1502 |
+
"content": "<|reserved_special_token_179|>",
|
1503 |
+
"lstrip": false,
|
1504 |
+
"normalized": false,
|
1505 |
+
"rstrip": false,
|
1506 |
+
"single_word": false,
|
1507 |
+
"special": true
|
1508 |
+
},
|
1509 |
+
"128188": {
|
1510 |
+
"content": "<|reserved_special_token_180|>",
|
1511 |
+
"lstrip": false,
|
1512 |
+
"normalized": false,
|
1513 |
+
"rstrip": false,
|
1514 |
+
"single_word": false,
|
1515 |
+
"special": true
|
1516 |
+
},
|
1517 |
+
"128189": {
|
1518 |
+
"content": "<|reserved_special_token_181|>",
|
1519 |
+
"lstrip": false,
|
1520 |
+
"normalized": false,
|
1521 |
+
"rstrip": false,
|
1522 |
+
"single_word": false,
|
1523 |
+
"special": true
|
1524 |
+
},
|
1525 |
+
"128190": {
|
1526 |
+
"content": "<|reserved_special_token_182|>",
|
1527 |
+
"lstrip": false,
|
1528 |
+
"normalized": false,
|
1529 |
+
"rstrip": false,
|
1530 |
+
"single_word": false,
|
1531 |
+
"special": true
|
1532 |
+
},
|
1533 |
+
"128191": {
|
1534 |
+
"content": "<|reserved_special_token_183|>",
|
1535 |
+
"lstrip": false,
|
1536 |
+
"normalized": false,
|
1537 |
+
"rstrip": false,
|
1538 |
+
"single_word": false,
|
1539 |
+
"special": true
|
1540 |
+
},
|
1541 |
+
"128192": {
|
1542 |
+
"content": "<|reserved_special_token_184|>",
|
1543 |
+
"lstrip": false,
|
1544 |
+
"normalized": false,
|
1545 |
+
"rstrip": false,
|
1546 |
+
"single_word": false,
|
1547 |
+
"special": true
|
1548 |
+
},
|
1549 |
+
"128193": {
|
1550 |
+
"content": "<|reserved_special_token_185|>",
|
1551 |
+
"lstrip": false,
|
1552 |
+
"normalized": false,
|
1553 |
+
"rstrip": false,
|
1554 |
+
"single_word": false,
|
1555 |
+
"special": true
|
1556 |
+
},
|
1557 |
+
"128194": {
|
1558 |
+
"content": "<|reserved_special_token_186|>",
|
1559 |
+
"lstrip": false,
|
1560 |
+
"normalized": false,
|
1561 |
+
"rstrip": false,
|
1562 |
+
"single_word": false,
|
1563 |
+
"special": true
|
1564 |
+
},
|
1565 |
+
"128195": {
|
1566 |
+
"content": "<|reserved_special_token_187|>",
|
1567 |
+
"lstrip": false,
|
1568 |
+
"normalized": false,
|
1569 |
+
"rstrip": false,
|
1570 |
+
"single_word": false,
|
1571 |
+
"special": true
|
1572 |
+
},
|
1573 |
+
"128196": {
|
1574 |
+
"content": "<|reserved_special_token_188|>",
|
1575 |
+
"lstrip": false,
|
1576 |
+
"normalized": false,
|
1577 |
+
"rstrip": false,
|
1578 |
+
"single_word": false,
|
1579 |
+
"special": true
|
1580 |
+
},
|
1581 |
+
"128197": {
|
1582 |
+
"content": "<|reserved_special_token_189|>",
|
1583 |
+
"lstrip": false,
|
1584 |
+
"normalized": false,
|
1585 |
+
"rstrip": false,
|
1586 |
+
"single_word": false,
|
1587 |
+
"special": true
|
1588 |
+
},
|
1589 |
+
"128198": {
|
1590 |
+
"content": "<|reserved_special_token_190|>",
|
1591 |
+
"lstrip": false,
|
1592 |
+
"normalized": false,
|
1593 |
+
"rstrip": false,
|
1594 |
+
"single_word": false,
|
1595 |
+
"special": true
|
1596 |
+
},
|
1597 |
+
"128199": {
|
1598 |
+
"content": "<|reserved_special_token_191|>",
|
1599 |
+
"lstrip": false,
|
1600 |
+
"normalized": false,
|
1601 |
+
"rstrip": false,
|
1602 |
+
"single_word": false,
|
1603 |
+
"special": true
|
1604 |
+
},
|
1605 |
+
"128200": {
|
1606 |
+
"content": "<|reserved_special_token_192|>",
|
1607 |
+
"lstrip": false,
|
1608 |
+
"normalized": false,
|
1609 |
+
"rstrip": false,
|
1610 |
+
"single_word": false,
|
1611 |
+
"special": true
|
1612 |
+
},
|
1613 |
+
"128201": {
|
1614 |
+
"content": "<|reserved_special_token_193|>",
|
1615 |
+
"lstrip": false,
|
1616 |
+
"normalized": false,
|
1617 |
+
"rstrip": false,
|
1618 |
+
"single_word": false,
|
1619 |
+
"special": true
|
1620 |
+
},
|
1621 |
+
"128202": {
|
1622 |
+
"content": "<|reserved_special_token_194|>",
|
1623 |
+
"lstrip": false,
|
1624 |
+
"normalized": false,
|
1625 |
+
"rstrip": false,
|
1626 |
+
"single_word": false,
|
1627 |
+
"special": true
|
1628 |
+
},
|
1629 |
+
"128203": {
|
1630 |
+
"content": "<|reserved_special_token_195|>",
|
1631 |
+
"lstrip": false,
|
1632 |
+
"normalized": false,
|
1633 |
+
"rstrip": false,
|
1634 |
+
"single_word": false,
|
1635 |
+
"special": true
|
1636 |
+
},
|
1637 |
+
"128204": {
|
1638 |
+
"content": "<|reserved_special_token_196|>",
|
1639 |
+
"lstrip": false,
|
1640 |
+
"normalized": false,
|
1641 |
+
"rstrip": false,
|
1642 |
+
"single_word": false,
|
1643 |
+
"special": true
|
1644 |
+
},
|
1645 |
+
"128205": {
|
1646 |
+
"content": "<|reserved_special_token_197|>",
|
1647 |
+
"lstrip": false,
|
1648 |
+
"normalized": false,
|
1649 |
+
"rstrip": false,
|
1650 |
+
"single_word": false,
|
1651 |
+
"special": true
|
1652 |
+
},
|
1653 |
+
"128206": {
|
1654 |
+
"content": "<|reserved_special_token_198|>",
|
1655 |
+
"lstrip": false,
|
1656 |
+
"normalized": false,
|
1657 |
+
"rstrip": false,
|
1658 |
+
"single_word": false,
|
1659 |
+
"special": true
|
1660 |
+
},
|
1661 |
+
"128207": {
|
1662 |
+
"content": "<|reserved_special_token_199|>",
|
1663 |
+
"lstrip": false,
|
1664 |
+
"normalized": false,
|
1665 |
+
"rstrip": false,
|
1666 |
+
"single_word": false,
|
1667 |
+
"special": true
|
1668 |
+
},
|
1669 |
+
"128208": {
|
1670 |
+
"content": "<|reserved_special_token_200|>",
|
1671 |
+
"lstrip": false,
|
1672 |
+
"normalized": false,
|
1673 |
+
"rstrip": false,
|
1674 |
+
"single_word": false,
|
1675 |
+
"special": true
|
1676 |
+
},
|
1677 |
+
"128209": {
|
1678 |
+
"content": "<|reserved_special_token_201|>",
|
1679 |
+
"lstrip": false,
|
1680 |
+
"normalized": false,
|
1681 |
+
"rstrip": false,
|
1682 |
+
"single_word": false,
|
1683 |
+
"special": true
|
1684 |
+
},
|
1685 |
+
"128210": {
|
1686 |
+
"content": "<|reserved_special_token_202|>",
|
1687 |
+
"lstrip": false,
|
1688 |
+
"normalized": false,
|
1689 |
+
"rstrip": false,
|
1690 |
+
"single_word": false,
|
1691 |
+
"special": true
|
1692 |
+
},
|
1693 |
+
"128211": {
|
1694 |
+
"content": "<|reserved_special_token_203|>",
|
1695 |
+
"lstrip": false,
|
1696 |
+
"normalized": false,
|
1697 |
+
"rstrip": false,
|
1698 |
+
"single_word": false,
|
1699 |
+
"special": true
|
1700 |
+
},
|
1701 |
+
"128212": {
|
1702 |
+
"content": "<|reserved_special_token_204|>",
|
1703 |
+
"lstrip": false,
|
1704 |
+
"normalized": false,
|
1705 |
+
"rstrip": false,
|
1706 |
+
"single_word": false,
|
1707 |
+
"special": true
|
1708 |
+
},
|
1709 |
+
"128213": {
|
1710 |
+
"content": "<|reserved_special_token_205|>",
|
1711 |
+
"lstrip": false,
|
1712 |
+
"normalized": false,
|
1713 |
+
"rstrip": false,
|
1714 |
+
"single_word": false,
|
1715 |
+
"special": true
|
1716 |
+
},
|
1717 |
+
"128214": {
|
1718 |
+
"content": "<|reserved_special_token_206|>",
|
1719 |
+
"lstrip": false,
|
1720 |
+
"normalized": false,
|
1721 |
+
"rstrip": false,
|
1722 |
+
"single_word": false,
|
1723 |
+
"special": true
|
1724 |
+
},
|
1725 |
+
"128215": {
|
1726 |
+
"content": "<|reserved_special_token_207|>",
|
1727 |
+
"lstrip": false,
|
1728 |
+
"normalized": false,
|
1729 |
+
"rstrip": false,
|
1730 |
+
"single_word": false,
|
1731 |
+
"special": true
|
1732 |
+
},
|
1733 |
+
"128216": {
|
1734 |
+
"content": "<|reserved_special_token_208|>",
|
1735 |
+
"lstrip": false,
|
1736 |
+
"normalized": false,
|
1737 |
+
"rstrip": false,
|
1738 |
+
"single_word": false,
|
1739 |
+
"special": true
|
1740 |
+
},
|
1741 |
+
"128217": {
|
1742 |
+
"content": "<|reserved_special_token_209|>",
|
1743 |
+
"lstrip": false,
|
1744 |
+
"normalized": false,
|
1745 |
+
"rstrip": false,
|
1746 |
+
"single_word": false,
|
1747 |
+
"special": true
|
1748 |
+
},
|
1749 |
+
"128218": {
|
1750 |
+
"content": "<|reserved_special_token_210|>",
|
1751 |
+
"lstrip": false,
|
1752 |
+
"normalized": false,
|
1753 |
+
"rstrip": false,
|
1754 |
+
"single_word": false,
|
1755 |
+
"special": true
|
1756 |
+
},
|
1757 |
+
"128219": {
|
1758 |
+
"content": "<|reserved_special_token_211|>",
|
1759 |
+
"lstrip": false,
|
1760 |
+
"normalized": false,
|
1761 |
+
"rstrip": false,
|
1762 |
+
"single_word": false,
|
1763 |
+
"special": true
|
1764 |
+
},
|
1765 |
+
"128220": {
|
1766 |
+
"content": "<|reserved_special_token_212|>",
|
1767 |
+
"lstrip": false,
|
1768 |
+
"normalized": false,
|
1769 |
+
"rstrip": false,
|
1770 |
+
"single_word": false,
|
1771 |
+
"special": true
|
1772 |
+
},
|
1773 |
+
"128221": {
|
1774 |
+
"content": "<|reserved_special_token_213|>",
|
1775 |
+
"lstrip": false,
|
1776 |
+
"normalized": false,
|
1777 |
+
"rstrip": false,
|
1778 |
+
"single_word": false,
|
1779 |
+
"special": true
|
1780 |
+
},
|
1781 |
+
"128222": {
|
1782 |
+
"content": "<|reserved_special_token_214|>",
|
1783 |
+
"lstrip": false,
|
1784 |
+
"normalized": false,
|
1785 |
+
"rstrip": false,
|
1786 |
+
"single_word": false,
|
1787 |
+
"special": true
|
1788 |
+
},
|
1789 |
+
"128223": {
|
1790 |
+
"content": "<|reserved_special_token_215|>",
|
1791 |
+
"lstrip": false,
|
1792 |
+
"normalized": false,
|
1793 |
+
"rstrip": false,
|
1794 |
+
"single_word": false,
|
1795 |
+
"special": true
|
1796 |
+
},
|
1797 |
+
"128224": {
|
1798 |
+
"content": "<|reserved_special_token_216|>",
|
1799 |
+
"lstrip": false,
|
1800 |
+
"normalized": false,
|
1801 |
+
"rstrip": false,
|
1802 |
+
"single_word": false,
|
1803 |
+
"special": true
|
1804 |
+
},
|
1805 |
+
"128225": {
|
1806 |
+
"content": "<|reserved_special_token_217|>",
|
1807 |
+
"lstrip": false,
|
1808 |
+
"normalized": false,
|
1809 |
+
"rstrip": false,
|
1810 |
+
"single_word": false,
|
1811 |
+
"special": true
|
1812 |
+
},
|
1813 |
+
"128226": {
|
1814 |
+
"content": "<|reserved_special_token_218|>",
|
1815 |
+
"lstrip": false,
|
1816 |
+
"normalized": false,
|
1817 |
+
"rstrip": false,
|
1818 |
+
"single_word": false,
|
1819 |
+
"special": true
|
1820 |
+
},
|
1821 |
+
"128227": {
|
1822 |
+
"content": "<|reserved_special_token_219|>",
|
1823 |
+
"lstrip": false,
|
1824 |
+
"normalized": false,
|
1825 |
+
"rstrip": false,
|
1826 |
+
"single_word": false,
|
1827 |
+
"special": true
|
1828 |
+
},
|
1829 |
+
"128228": {
|
1830 |
+
"content": "<|reserved_special_token_220|>",
|
1831 |
+
"lstrip": false,
|
1832 |
+
"normalized": false,
|
1833 |
+
"rstrip": false,
|
1834 |
+
"single_word": false,
|
1835 |
+
"special": true
|
1836 |
+
},
|
1837 |
+
"128229": {
|
1838 |
+
"content": "<|reserved_special_token_221|>",
|
1839 |
+
"lstrip": false,
|
1840 |
+
"normalized": false,
|
1841 |
+
"rstrip": false,
|
1842 |
+
"single_word": false,
|
1843 |
+
"special": true
|
1844 |
+
},
|
1845 |
+
"128230": {
|
1846 |
+
"content": "<|reserved_special_token_222|>",
|
1847 |
+
"lstrip": false,
|
1848 |
+
"normalized": false,
|
1849 |
+
"rstrip": false,
|
1850 |
+
"single_word": false,
|
1851 |
+
"special": true
|
1852 |
+
},
|
1853 |
+
"128231": {
|
1854 |
+
"content": "<|reserved_special_token_223|>",
|
1855 |
+
"lstrip": false,
|
1856 |
+
"normalized": false,
|
1857 |
+
"rstrip": false,
|
1858 |
+
"single_word": false,
|
1859 |
+
"special": true
|
1860 |
+
},
|
1861 |
+
"128232": {
|
1862 |
+
"content": "<|reserved_special_token_224|>",
|
1863 |
+
"lstrip": false,
|
1864 |
+
"normalized": false,
|
1865 |
+
"rstrip": false,
|
1866 |
+
"single_word": false,
|
1867 |
+
"special": true
|
1868 |
+
},
|
1869 |
+
"128233": {
|
1870 |
+
"content": "<|reserved_special_token_225|>",
|
1871 |
+
"lstrip": false,
|
1872 |
+
"normalized": false,
|
1873 |
+
"rstrip": false,
|
1874 |
+
"single_word": false,
|
1875 |
+
"special": true
|
1876 |
+
},
|
1877 |
+
"128234": {
|
1878 |
+
"content": "<|reserved_special_token_226|>",
|
1879 |
+
"lstrip": false,
|
1880 |
+
"normalized": false,
|
1881 |
+
"rstrip": false,
|
1882 |
+
"single_word": false,
|
1883 |
+
"special": true
|
1884 |
+
},
|
1885 |
+
"128235": {
|
1886 |
+
"content": "<|reserved_special_token_227|>",
|
1887 |
+
"lstrip": false,
|
1888 |
+
"normalized": false,
|
1889 |
+
"rstrip": false,
|
1890 |
+
"single_word": false,
|
1891 |
+
"special": true
|
1892 |
+
},
|
1893 |
+
"128236": {
|
1894 |
+
"content": "<|reserved_special_token_228|>",
|
1895 |
+
"lstrip": false,
|
1896 |
+
"normalized": false,
|
1897 |
+
"rstrip": false,
|
1898 |
+
"single_word": false,
|
1899 |
+
"special": true
|
1900 |
+
},
|
1901 |
+
"128237": {
|
1902 |
+
"content": "<|reserved_special_token_229|>",
|
1903 |
+
"lstrip": false,
|
1904 |
+
"normalized": false,
|
1905 |
+
"rstrip": false,
|
1906 |
+
"single_word": false,
|
1907 |
+
"special": true
|
1908 |
+
},
|
1909 |
+
"128238": {
|
1910 |
+
"content": "<|reserved_special_token_230|>",
|
1911 |
+
"lstrip": false,
|
1912 |
+
"normalized": false,
|
1913 |
+
"rstrip": false,
|
1914 |
+
"single_word": false,
|
1915 |
+
"special": true
|
1916 |
+
},
|
1917 |
+
"128239": {
|
1918 |
+
"content": "<|reserved_special_token_231|>",
|
1919 |
+
"lstrip": false,
|
1920 |
+
"normalized": false,
|
1921 |
+
"rstrip": false,
|
1922 |
+
"single_word": false,
|
1923 |
+
"special": true
|
1924 |
+
},
|
1925 |
+
"128240": {
|
1926 |
+
"content": "<|reserved_special_token_232|>",
|
1927 |
+
"lstrip": false,
|
1928 |
+
"normalized": false,
|
1929 |
+
"rstrip": false,
|
1930 |
+
"single_word": false,
|
1931 |
+
"special": true
|
1932 |
+
},
|
1933 |
+
"128241": {
|
1934 |
+
"content": "<|reserved_special_token_233|>",
|
1935 |
+
"lstrip": false,
|
1936 |
+
"normalized": false,
|
1937 |
+
"rstrip": false,
|
1938 |
+
"single_word": false,
|
1939 |
+
"special": true
|
1940 |
+
},
|
1941 |
+
"128242": {
|
1942 |
+
"content": "<|reserved_special_token_234|>",
|
1943 |
+
"lstrip": false,
|
1944 |
+
"normalized": false,
|
1945 |
+
"rstrip": false,
|
1946 |
+
"single_word": false,
|
1947 |
+
"special": true
|
1948 |
+
},
|
1949 |
+
"128243": {
|
1950 |
+
"content": "<|reserved_special_token_235|>",
|
1951 |
+
"lstrip": false,
|
1952 |
+
"normalized": false,
|
1953 |
+
"rstrip": false,
|
1954 |
+
"single_word": false,
|
1955 |
+
"special": true
|
1956 |
+
},
|
1957 |
+
"128244": {
|
1958 |
+
"content": "<|reserved_special_token_236|>",
|
1959 |
+
"lstrip": false,
|
1960 |
+
"normalized": false,
|
1961 |
+
"rstrip": false,
|
1962 |
+
"single_word": false,
|
1963 |
+
"special": true
|
1964 |
+
},
|
1965 |
+
"128245": {
|
1966 |
+
"content": "<|reserved_special_token_237|>",
|
1967 |
+
"lstrip": false,
|
1968 |
+
"normalized": false,
|
1969 |
+
"rstrip": false,
|
1970 |
+
"single_word": false,
|
1971 |
+
"special": true
|
1972 |
+
},
|
1973 |
+
"128246": {
|
1974 |
+
"content": "<|reserved_special_token_238|>",
|
1975 |
+
"lstrip": false,
|
1976 |
+
"normalized": false,
|
1977 |
+
"rstrip": false,
|
1978 |
+
"single_word": false,
|
1979 |
+
"special": true
|
1980 |
+
},
|
1981 |
+
"128247": {
|
1982 |
+
"content": "<|reserved_special_token_239|>",
|
1983 |
+
"lstrip": false,
|
1984 |
+
"normalized": false,
|
1985 |
+
"rstrip": false,
|
1986 |
+
"single_word": false,
|
1987 |
+
"special": true
|
1988 |
+
},
|
1989 |
+
"128248": {
|
1990 |
+
"content": "<|reserved_special_token_240|>",
|
1991 |
+
"lstrip": false,
|
1992 |
+
"normalized": false,
|
1993 |
+
"rstrip": false,
|
1994 |
+
"single_word": false,
|
1995 |
+
"special": true
|
1996 |
+
},
|
1997 |
+
"128249": {
|
1998 |
+
"content": "<|reserved_special_token_241|>",
|
1999 |
+
"lstrip": false,
|
2000 |
+
"normalized": false,
|
2001 |
+
"rstrip": false,
|
2002 |
+
"single_word": false,
|
2003 |
+
"special": true
|
2004 |
+
},
|
2005 |
+
"128250": {
|
2006 |
+
"content": "<|reserved_special_token_242|>",
|
2007 |
+
"lstrip": false,
|
2008 |
+
"normalized": false,
|
2009 |
+
"rstrip": false,
|
2010 |
+
"single_word": false,
|
2011 |
+
"special": true
|
2012 |
+
},
|
2013 |
+
"128251": {
|
2014 |
+
"content": "<|reserved_special_token_243|>",
|
2015 |
+
"lstrip": false,
|
2016 |
+
"normalized": false,
|
2017 |
+
"rstrip": false,
|
2018 |
+
"single_word": false,
|
2019 |
+
"special": true
|
2020 |
+
},
|
2021 |
+
"128252": {
|
2022 |
+
"content": "<|reserved_special_token_244|>",
|
2023 |
+
"lstrip": false,
|
2024 |
+
"normalized": false,
|
2025 |
+
"rstrip": false,
|
2026 |
+
"single_word": false,
|
2027 |
+
"special": true
|
2028 |
+
},
|
2029 |
+
"128253": {
|
2030 |
+
"content": "<|reserved_special_token_245|>",
|
2031 |
+
"lstrip": false,
|
2032 |
+
"normalized": false,
|
2033 |
+
"rstrip": false,
|
2034 |
+
"single_word": false,
|
2035 |
+
"special": true
|
2036 |
+
},
|
2037 |
+
"128254": {
|
2038 |
+
"content": "<|reserved_special_token_246|>",
|
2039 |
+
"lstrip": false,
|
2040 |
+
"normalized": false,
|
2041 |
+
"rstrip": false,
|
2042 |
+
"single_word": false,
|
2043 |
+
"special": true
|
2044 |
+
},
|
2045 |
+
"128255": {
|
2046 |
+
"content": "<|reserved_special_token_247|>",
|
2047 |
+
"lstrip": false,
|
2048 |
+
"normalized": false,
|
2049 |
+
"rstrip": false,
|
2050 |
+
"single_word": false,
|
2051 |
+
"special": true
|
2052 |
+
}
|
2053 |
+
},
|
2054 |
+
"bos_token": "<|begin_of_text|>",
|
2055 |
+
"chat_template": "{{- bos_token }}\n{%- if custom_tools is defined %}\n {%- set tools = custom_tools %}\n{%- endif %}\n{%- if not tools_in_user_message is defined %}\n {%- set tools_in_user_message = true %}\n{%- endif %}\n{%- if not date_string is defined %}\n {%- if strftime_now is defined %}\n {%- set date_string = strftime_now(\"%d %b %Y\") %}\n {%- else %}\n {%- set date_string = \"26 Jul 2024\" %}\n {%- endif %}\n{%- endif %}\n{%- if not tools is defined %}\n {%- set tools = none %}\n{%- endif %}\n\n{#- This block extracts the system message, so we can slot it into the right place. #}\n{%- if messages[0]['role'] == 'system' %}\n {%- set system_message = messages[0]['content']|trim %}\n {%- set messages = messages[1:] %}\n{%- else %}\n {%- set system_message = \"\" %}\n{%- endif %}\n\n{#- System message #}\n{{- \"<|start_header_id|>system<|end_header_id|>\\n\\n\" }}\n{%- if tools is not none %}\n {{- \"Environment: ipython\\n\" }}\n{%- endif %}\n{{- \"Cutting Knowledge Date: December 2023\\n\" }}\n{{- \"Today Date: \" + date_string + \"\\n\\n\" }}\n{%- if tools is not none and not tools_in_user_message %}\n {{- \"You have access to the following functions. To call a function, please respond with JSON for a function call.\" }}\n {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n {{- \"Do not use variables.\\n\\n\" }}\n {%- for t in tools %}\n {{- t | tojson(indent=4) }}\n {{- \"\\n\\n\" }}\n {%- endfor %}\n{%- endif %}\n{{- system_message }}\n{{- \"<|eot_id|>\" }}\n\n{#- Custom tools are passed in a user message with some extra guidance #}\n{%- if tools_in_user_message and not tools is none %}\n {#- Extract the first user message so we can plug it in here #}\n {%- if messages | length != 0 %}\n {%- set first_user_message = messages[0]['content']|trim %}\n {%- set messages = messages[1:] %}\n {%- else %}\n {{- raise_exception(\"Cannot put tools in the first user message when there's no first user message!\") }}\n{%- endif %}\n {{- '<|start_header_id|>user<|end_header_id|>\\n\\n' -}}\n {{- \"Given the following functions, please respond with a JSON for a function call \" }}\n {{- \"with its proper arguments that best answers the given prompt.\\n\\n\" }}\n {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n {{- \"Do not use variables.\\n\\n\" }}\n {%- for t in tools %}\n {{- t | tojson(indent=4) }}\n {{- \"\\n\\n\" }}\n {%- endfor %}\n {{- first_user_message + \"<|eot_id|>\"}}\n{%- endif %}\n\n{%- for message in messages %}\n {%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %}\n {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\\n\\n'+ message['content'] | trim + '<|eot_id|>' }}\n {%- elif 'tool_calls' in message %}\n {%- if not message.tool_calls|length == 1 %}\n {{- raise_exception(\"This model only supports single tool-calls at once!\") }}\n {%- endif %}\n {%- set tool_call = message.tool_calls[0].function %}\n {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' -}}\n {{- '{\"name\": \"' + tool_call.name + '\", ' }}\n {{- '\"parameters\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- \"}\" }}\n {{- \"<|eot_id|>\" }}\n {%- elif message.role == \"tool\" or message.role == \"ipython\" %}\n {{- \"<|start_header_id|>ipython<|end_header_id|>\\n\\n\" }}\n {%- if message.content is mapping or message.content is iterable %}\n {{- message.content | tojson }}\n {%- else %}\n {{- message.content }}\n {%- endif %}\n {{- \"<|eot_id|>\" }}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' }}\n{%- endif %}\n",
|
2056 |
+
"clean_up_tokenization_spaces": true,
|
2057 |
+
"eos_token": "<|eot_id|>",
|
2058 |
+
"extra_special_tokens": {},
|
2059 |
+
"max_sequence_length": 3072,
|
2060 |
+
"model_input_names": [
|
2061 |
+
"input_ids",
|
2062 |
+
"attention_mask"
|
2063 |
+
],
|
2064 |
+
"model_max_length": 3072,
|
2065 |
+
"pad_token": "<|finetune_right_pad_id|>",
|
2066 |
+
"padding_side": "right",
|
2067 |
+
"tokenizer_class": "PreTrainedTokenizerFast",
|
2068 |
+
"unk_token": null
|
2069 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,1577 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 1.7067729234695435,
|
3 |
+
"best_model_checkpoint": "4bit_repro_03022025/host18_seed_42_full_det_fp16_no_flash_attn_fix_pad_llama-3.2-instruct-l16-cot-wt_feb7-4ep-lr3e04-ws20-bs8-ga4-fp16-16022025/checkpoint-110",
|
4 |
+
"epoch": 3.9357798165137616,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 216,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.01834862385321101,
|
13 |
+
"grad_norm": 0.8146735429763794,
|
14 |
+
"learning_rate": 1.4999999999999999e-05,
|
15 |
+
"loss": 3.458,
|
16 |
+
"step": 1
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.03669724770642202,
|
20 |
+
"grad_norm": 0.8460527658462524,
|
21 |
+
"learning_rate": 2.9999999999999997e-05,
|
22 |
+
"loss": 3.318,
|
23 |
+
"step": 2
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.05504587155963303,
|
27 |
+
"grad_norm": 1.0199122428894043,
|
28 |
+
"learning_rate": 4.4999999999999996e-05,
|
29 |
+
"loss": 3.4251,
|
30 |
+
"step": 3
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 0.07339449541284404,
|
34 |
+
"grad_norm": 0.738707959651947,
|
35 |
+
"learning_rate": 5.9999999999999995e-05,
|
36 |
+
"loss": 3.3918,
|
37 |
+
"step": 4
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 0.09174311926605505,
|
41 |
+
"grad_norm": 0.9168875217437744,
|
42 |
+
"learning_rate": 7.5e-05,
|
43 |
+
"loss": 3.2804,
|
44 |
+
"step": 5
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.11009174311926606,
|
48 |
+
"grad_norm": 0.7749077081680298,
|
49 |
+
"learning_rate": 8.999999999999999e-05,
|
50 |
+
"loss": 3.1672,
|
51 |
+
"step": 6
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.12844036697247707,
|
55 |
+
"grad_norm": 0.8257707953453064,
|
56 |
+
"learning_rate": 0.00010499999999999999,
|
57 |
+
"loss": 3.1118,
|
58 |
+
"step": 7
|
59 |
+
},
|
60 |
+
{
|
61 |
+
"epoch": 0.14678899082568808,
|
62 |
+
"grad_norm": 0.7854360342025757,
|
63 |
+
"learning_rate": 0.00011999999999999999,
|
64 |
+
"loss": 3.1685,
|
65 |
+
"step": 8
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 0.1651376146788991,
|
69 |
+
"grad_norm": 0.9187895059585571,
|
70 |
+
"learning_rate": 0.000135,
|
71 |
+
"loss": 2.821,
|
72 |
+
"step": 9
|
73 |
+
},
|
74 |
+
{
|
75 |
+
"epoch": 0.1834862385321101,
|
76 |
+
"grad_norm": 0.70020991563797,
|
77 |
+
"learning_rate": 0.00015,
|
78 |
+
"loss": 2.7924,
|
79 |
+
"step": 10
|
80 |
+
},
|
81 |
+
{
|
82 |
+
"epoch": 0.2018348623853211,
|
83 |
+
"grad_norm": 0.513304591178894,
|
84 |
+
"learning_rate": 0.000165,
|
85 |
+
"loss": 2.8753,
|
86 |
+
"step": 11
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 0.22018348623853212,
|
90 |
+
"grad_norm": 0.49817588925361633,
|
91 |
+
"learning_rate": 0.00017999999999999998,
|
92 |
+
"loss": 2.6701,
|
93 |
+
"step": 12
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 0.23853211009174313,
|
97 |
+
"grad_norm": 0.4605925977230072,
|
98 |
+
"learning_rate": 0.000195,
|
99 |
+
"loss": 2.7468,
|
100 |
+
"step": 13
|
101 |
+
},
|
102 |
+
{
|
103 |
+
"epoch": 0.25688073394495414,
|
104 |
+
"grad_norm": 0.5559924244880676,
|
105 |
+
"learning_rate": 0.00020999999999999998,
|
106 |
+
"loss": 2.532,
|
107 |
+
"step": 14
|
108 |
+
},
|
109 |
+
{
|
110 |
+
"epoch": 0.27522935779816515,
|
111 |
+
"grad_norm": 0.5250511765480042,
|
112 |
+
"learning_rate": 0.000225,
|
113 |
+
"loss": 2.8411,
|
114 |
+
"step": 15
|
115 |
+
},
|
116 |
+
{
|
117 |
+
"epoch": 0.29357798165137616,
|
118 |
+
"grad_norm": 0.5654911398887634,
|
119 |
+
"learning_rate": 0.00023999999999999998,
|
120 |
+
"loss": 2.5375,
|
121 |
+
"step": 16
|
122 |
+
},
|
123 |
+
{
|
124 |
+
"epoch": 0.3119266055045872,
|
125 |
+
"grad_norm": 0.6329001188278198,
|
126 |
+
"learning_rate": 0.00025499999999999996,
|
127 |
+
"loss": 2.431,
|
128 |
+
"step": 17
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 0.3302752293577982,
|
132 |
+
"grad_norm": 0.6397466063499451,
|
133 |
+
"learning_rate": 0.00027,
|
134 |
+
"loss": 2.4786,
|
135 |
+
"step": 18
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 0.3486238532110092,
|
139 |
+
"grad_norm": 0.5889459252357483,
|
140 |
+
"learning_rate": 0.000285,
|
141 |
+
"loss": 2.6437,
|
142 |
+
"step": 19
|
143 |
+
},
|
144 |
+
{
|
145 |
+
"epoch": 0.3669724770642202,
|
146 |
+
"grad_norm": 0.5488238334655762,
|
147 |
+
"learning_rate": 0.0003,
|
148 |
+
"loss": 2.539,
|
149 |
+
"step": 20
|
150 |
+
},
|
151 |
+
{
|
152 |
+
"epoch": 0.3853211009174312,
|
153 |
+
"grad_norm": 0.5296560525894165,
|
154 |
+
"learning_rate": 0.00029846938775510205,
|
155 |
+
"loss": 2.3395,
|
156 |
+
"step": 21
|
157 |
+
},
|
158 |
+
{
|
159 |
+
"epoch": 0.4036697247706422,
|
160 |
+
"grad_norm": 0.4363678991794586,
|
161 |
+
"learning_rate": 0.0002969387755102041,
|
162 |
+
"loss": 2.2912,
|
163 |
+
"step": 22
|
164 |
+
},
|
165 |
+
{
|
166 |
+
"epoch": 0.42201834862385323,
|
167 |
+
"grad_norm": 0.4143035411834717,
|
168 |
+
"learning_rate": 0.0002954081632653061,
|
169 |
+
"loss": 2.3358,
|
170 |
+
"step": 23
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 0.44036697247706424,
|
174 |
+
"grad_norm": 0.4551326632499695,
|
175 |
+
"learning_rate": 0.0002938775510204081,
|
176 |
+
"loss": 2.2228,
|
177 |
+
"step": 24
|
178 |
+
},
|
179 |
+
{
|
180 |
+
"epoch": 0.45871559633027525,
|
181 |
+
"grad_norm": 0.39562949538230896,
|
182 |
+
"learning_rate": 0.0002923469387755102,
|
183 |
+
"loss": 2.0389,
|
184 |
+
"step": 25
|
185 |
+
},
|
186 |
+
{
|
187 |
+
"epoch": 0.47706422018348627,
|
188 |
+
"grad_norm": 0.35010403394699097,
|
189 |
+
"learning_rate": 0.00029081632653061223,
|
190 |
+
"loss": 2.3651,
|
191 |
+
"step": 26
|
192 |
+
},
|
193 |
+
{
|
194 |
+
"epoch": 0.4954128440366973,
|
195 |
+
"grad_norm": 0.3502652943134308,
|
196 |
+
"learning_rate": 0.00028928571428571425,
|
197 |
+
"loss": 1.8895,
|
198 |
+
"step": 27
|
199 |
+
},
|
200 |
+
{
|
201 |
+
"epoch": 0.5137614678899083,
|
202 |
+
"grad_norm": 0.3823269307613373,
|
203 |
+
"learning_rate": 0.0002877551020408163,
|
204 |
+
"loss": 2.3629,
|
205 |
+
"step": 28
|
206 |
+
},
|
207 |
+
{
|
208 |
+
"epoch": 0.5321100917431193,
|
209 |
+
"grad_norm": 0.3375133275985718,
|
210 |
+
"learning_rate": 0.00028622448979591836,
|
211 |
+
"loss": 2.1808,
|
212 |
+
"step": 29
|
213 |
+
},
|
214 |
+
{
|
215 |
+
"epoch": 0.5504587155963303,
|
216 |
+
"grad_norm": 0.3216778635978699,
|
217 |
+
"learning_rate": 0.0002846938775510204,
|
218 |
+
"loss": 2.2516,
|
219 |
+
"step": 30
|
220 |
+
},
|
221 |
+
{
|
222 |
+
"epoch": 0.5688073394495413,
|
223 |
+
"grad_norm": 0.30818313360214233,
|
224 |
+
"learning_rate": 0.0002831632653061224,
|
225 |
+
"loss": 2.1212,
|
226 |
+
"step": 31
|
227 |
+
},
|
228 |
+
{
|
229 |
+
"epoch": 0.5871559633027523,
|
230 |
+
"grad_norm": 0.32901531457901,
|
231 |
+
"learning_rate": 0.0002816326530612245,
|
232 |
+
"loss": 1.9435,
|
233 |
+
"step": 32
|
234 |
+
},
|
235 |
+
{
|
236 |
+
"epoch": 0.6055045871559633,
|
237 |
+
"grad_norm": 0.3240410387516022,
|
238 |
+
"learning_rate": 0.0002801020408163265,
|
239 |
+
"loss": 1.8977,
|
240 |
+
"step": 33
|
241 |
+
},
|
242 |
+
{
|
243 |
+
"epoch": 0.6238532110091743,
|
244 |
+
"grad_norm": 0.31374916434288025,
|
245 |
+
"learning_rate": 0.00027857142857142854,
|
246 |
+
"loss": 2.2115,
|
247 |
+
"step": 34
|
248 |
+
},
|
249 |
+
{
|
250 |
+
"epoch": 0.6422018348623854,
|
251 |
+
"grad_norm": 0.31450748443603516,
|
252 |
+
"learning_rate": 0.00027704081632653056,
|
253 |
+
"loss": 2.0926,
|
254 |
+
"step": 35
|
255 |
+
},
|
256 |
+
{
|
257 |
+
"epoch": 0.6605504587155964,
|
258 |
+
"grad_norm": 0.30289527773857117,
|
259 |
+
"learning_rate": 0.00027551020408163264,
|
260 |
+
"loss": 2.1462,
|
261 |
+
"step": 36
|
262 |
+
},
|
263 |
+
{
|
264 |
+
"epoch": 0.6788990825688074,
|
265 |
+
"grad_norm": 0.3504111170768738,
|
266 |
+
"learning_rate": 0.00027397959183673466,
|
267 |
+
"loss": 2.2673,
|
268 |
+
"step": 37
|
269 |
+
},
|
270 |
+
{
|
271 |
+
"epoch": 0.6972477064220184,
|
272 |
+
"grad_norm": 0.3244895040988922,
|
273 |
+
"learning_rate": 0.0002724489795918367,
|
274 |
+
"loss": 2.1864,
|
275 |
+
"step": 38
|
276 |
+
},
|
277 |
+
{
|
278 |
+
"epoch": 0.7155963302752294,
|
279 |
+
"grad_norm": 0.3336032032966614,
|
280 |
+
"learning_rate": 0.0002709183673469387,
|
281 |
+
"loss": 1.8489,
|
282 |
+
"step": 39
|
283 |
+
},
|
284 |
+
{
|
285 |
+
"epoch": 0.7339449541284404,
|
286 |
+
"grad_norm": 0.3516104519367218,
|
287 |
+
"learning_rate": 0.0002693877551020408,
|
288 |
+
"loss": 2.3057,
|
289 |
+
"step": 40
|
290 |
+
},
|
291 |
+
{
|
292 |
+
"epoch": 0.7522935779816514,
|
293 |
+
"grad_norm": 0.30326011776924133,
|
294 |
+
"learning_rate": 0.00026785714285714287,
|
295 |
+
"loss": 1.9602,
|
296 |
+
"step": 41
|
297 |
+
},
|
298 |
+
{
|
299 |
+
"epoch": 0.7706422018348624,
|
300 |
+
"grad_norm": 0.34224340319633484,
|
301 |
+
"learning_rate": 0.0002663265306122449,
|
302 |
+
"loss": 1.994,
|
303 |
+
"step": 42
|
304 |
+
},
|
305 |
+
{
|
306 |
+
"epoch": 0.7889908256880734,
|
307 |
+
"grad_norm": 0.33715730905532837,
|
308 |
+
"learning_rate": 0.0002647959183673469,
|
309 |
+
"loss": 1.9931,
|
310 |
+
"step": 43
|
311 |
+
},
|
312 |
+
{
|
313 |
+
"epoch": 0.8073394495412844,
|
314 |
+
"grad_norm": 0.3272618353366852,
|
315 |
+
"learning_rate": 0.00026326530612244894,
|
316 |
+
"loss": 2.1401,
|
317 |
+
"step": 44
|
318 |
+
},
|
319 |
+
{
|
320 |
+
"epoch": 0.8256880733944955,
|
321 |
+
"grad_norm": 0.3652991056442261,
|
322 |
+
"learning_rate": 0.000261734693877551,
|
323 |
+
"loss": 1.625,
|
324 |
+
"step": 45
|
325 |
+
},
|
326 |
+
{
|
327 |
+
"epoch": 0.8440366972477065,
|
328 |
+
"grad_norm": 0.3317834138870239,
|
329 |
+
"learning_rate": 0.00026020408163265305,
|
330 |
+
"loss": 2.0808,
|
331 |
+
"step": 46
|
332 |
+
},
|
333 |
+
{
|
334 |
+
"epoch": 0.8623853211009175,
|
335 |
+
"grad_norm": 0.36255204677581787,
|
336 |
+
"learning_rate": 0.00025867346938775507,
|
337 |
+
"loss": 1.7574,
|
338 |
+
"step": 47
|
339 |
+
},
|
340 |
+
{
|
341 |
+
"epoch": 0.8807339449541285,
|
342 |
+
"grad_norm": 0.35033008456230164,
|
343 |
+
"learning_rate": 0.0002571428571428571,
|
344 |
+
"loss": 1.9578,
|
345 |
+
"step": 48
|
346 |
+
},
|
347 |
+
{
|
348 |
+
"epoch": 0.8990825688073395,
|
349 |
+
"grad_norm": 0.3665790855884552,
|
350 |
+
"learning_rate": 0.0002556122448979592,
|
351 |
+
"loss": 1.9175,
|
352 |
+
"step": 49
|
353 |
+
},
|
354 |
+
{
|
355 |
+
"epoch": 0.9174311926605505,
|
356 |
+
"grad_norm": 0.3547409772872925,
|
357 |
+
"learning_rate": 0.0002540816326530612,
|
358 |
+
"loss": 1.8527,
|
359 |
+
"step": 50
|
360 |
+
},
|
361 |
+
{
|
362 |
+
"epoch": 0.9357798165137615,
|
363 |
+
"grad_norm": 0.37087056040763855,
|
364 |
+
"learning_rate": 0.0002525510204081632,
|
365 |
+
"loss": 1.7837,
|
366 |
+
"step": 51
|
367 |
+
},
|
368 |
+
{
|
369 |
+
"epoch": 0.9541284403669725,
|
370 |
+
"grad_norm": 0.40799495577812195,
|
371 |
+
"learning_rate": 0.0002510204081632653,
|
372 |
+
"loss": 1.5264,
|
373 |
+
"step": 52
|
374 |
+
},
|
375 |
+
{
|
376 |
+
"epoch": 0.9724770642201835,
|
377 |
+
"grad_norm": 0.3731648027896881,
|
378 |
+
"learning_rate": 0.00024948979591836733,
|
379 |
+
"loss": 1.8249,
|
380 |
+
"step": 53
|
381 |
+
},
|
382 |
+
{
|
383 |
+
"epoch": 0.9908256880733946,
|
384 |
+
"grad_norm": 0.3571811616420746,
|
385 |
+
"learning_rate": 0.00024795918367346935,
|
386 |
+
"loss": 1.7617,
|
387 |
+
"step": 54
|
388 |
+
},
|
389 |
+
{
|
390 |
+
"epoch": 1.0,
|
391 |
+
"grad_norm": 0.5152439475059509,
|
392 |
+
"learning_rate": 0.0002464285714285714,
|
393 |
+
"loss": 1.8187,
|
394 |
+
"step": 55
|
395 |
+
},
|
396 |
+
{
|
397 |
+
"epoch": 1.0,
|
398 |
+
"eval_loss": 1.8342303037643433,
|
399 |
+
"eval_runtime": 40.5217,
|
400 |
+
"eval_samples_per_second": 8.193,
|
401 |
+
"eval_steps_per_second": 4.097,
|
402 |
+
"step": 55
|
403 |
+
},
|
404 |
+
{
|
405 |
+
"epoch": 1.018348623853211,
|
406 |
+
"grad_norm": 0.38449227809906006,
|
407 |
+
"learning_rate": 0.00024489795918367346,
|
408 |
+
"loss": 1.7036,
|
409 |
+
"step": 56
|
410 |
+
},
|
411 |
+
{
|
412 |
+
"epoch": 1.036697247706422,
|
413 |
+
"grad_norm": 0.3873405158519745,
|
414 |
+
"learning_rate": 0.00024336734693877548,
|
415 |
+
"loss": 1.9332,
|
416 |
+
"step": 57
|
417 |
+
},
|
418 |
+
{
|
419 |
+
"epoch": 1.0550458715596331,
|
420 |
+
"grad_norm": 0.4064755439758301,
|
421 |
+
"learning_rate": 0.00024183673469387753,
|
422 |
+
"loss": 1.7656,
|
423 |
+
"step": 58
|
424 |
+
},
|
425 |
+
{
|
426 |
+
"epoch": 1.073394495412844,
|
427 |
+
"grad_norm": 0.39023351669311523,
|
428 |
+
"learning_rate": 0.00024030612244897956,
|
429 |
+
"loss": 1.8004,
|
430 |
+
"step": 59
|
431 |
+
},
|
432 |
+
{
|
433 |
+
"epoch": 1.091743119266055,
|
434 |
+
"grad_norm": 0.40451326966285706,
|
435 |
+
"learning_rate": 0.0002387755102040816,
|
436 |
+
"loss": 1.674,
|
437 |
+
"step": 60
|
438 |
+
},
|
439 |
+
{
|
440 |
+
"epoch": 1.110091743119266,
|
441 |
+
"grad_norm": 0.3661345839500427,
|
442 |
+
"learning_rate": 0.00023724489795918366,
|
443 |
+
"loss": 1.9113,
|
444 |
+
"step": 61
|
445 |
+
},
|
446 |
+
{
|
447 |
+
"epoch": 1.1284403669724772,
|
448 |
+
"grad_norm": 0.4025841951370239,
|
449 |
+
"learning_rate": 0.00023571428571428569,
|
450 |
+
"loss": 1.8991,
|
451 |
+
"step": 62
|
452 |
+
},
|
453 |
+
{
|
454 |
+
"epoch": 1.146788990825688,
|
455 |
+
"grad_norm": 0.41999149322509766,
|
456 |
+
"learning_rate": 0.00023418367346938774,
|
457 |
+
"loss": 1.7361,
|
458 |
+
"step": 63
|
459 |
+
},
|
460 |
+
{
|
461 |
+
"epoch": 1.165137614678899,
|
462 |
+
"grad_norm": 0.39743533730506897,
|
463 |
+
"learning_rate": 0.00023265306122448976,
|
464 |
+
"loss": 1.5829,
|
465 |
+
"step": 64
|
466 |
+
},
|
467 |
+
{
|
468 |
+
"epoch": 1.18348623853211,
|
469 |
+
"grad_norm": 0.42366546392440796,
|
470 |
+
"learning_rate": 0.00023112244897959181,
|
471 |
+
"loss": 1.7228,
|
472 |
+
"step": 65
|
473 |
+
},
|
474 |
+
{
|
475 |
+
"epoch": 1.2018348623853212,
|
476 |
+
"grad_norm": 0.37864112854003906,
|
477 |
+
"learning_rate": 0.00022959183673469384,
|
478 |
+
"loss": 1.636,
|
479 |
+
"step": 66
|
480 |
+
},
|
481 |
+
{
|
482 |
+
"epoch": 1.2201834862385321,
|
483 |
+
"grad_norm": 0.392802357673645,
|
484 |
+
"learning_rate": 0.0002280612244897959,
|
485 |
+
"loss": 1.5435,
|
486 |
+
"step": 67
|
487 |
+
},
|
488 |
+
{
|
489 |
+
"epoch": 1.238532110091743,
|
490 |
+
"grad_norm": 0.4146474301815033,
|
491 |
+
"learning_rate": 0.00022653061224489791,
|
492 |
+
"loss": 1.7305,
|
493 |
+
"step": 68
|
494 |
+
},
|
495 |
+
{
|
496 |
+
"epoch": 1.2568807339449541,
|
497 |
+
"grad_norm": 0.401034951210022,
|
498 |
+
"learning_rate": 0.000225,
|
499 |
+
"loss": 1.6097,
|
500 |
+
"step": 69
|
501 |
+
},
|
502 |
+
{
|
503 |
+
"epoch": 1.2752293577981653,
|
504 |
+
"grad_norm": 0.4014700949192047,
|
505 |
+
"learning_rate": 0.00022346938775510205,
|
506 |
+
"loss": 1.8824,
|
507 |
+
"step": 70
|
508 |
+
},
|
509 |
+
{
|
510 |
+
"epoch": 1.2935779816513762,
|
511 |
+
"grad_norm": 0.4407334327697754,
|
512 |
+
"learning_rate": 0.00022193877551020407,
|
513 |
+
"loss": 1.6208,
|
514 |
+
"step": 71
|
515 |
+
},
|
516 |
+
{
|
517 |
+
"epoch": 1.311926605504587,
|
518 |
+
"grad_norm": 0.3951621353626251,
|
519 |
+
"learning_rate": 0.00022040816326530612,
|
520 |
+
"loss": 1.7436,
|
521 |
+
"step": 72
|
522 |
+
},
|
523 |
+
{
|
524 |
+
"epoch": 1.3302752293577982,
|
525 |
+
"grad_norm": 0.40659868717193604,
|
526 |
+
"learning_rate": 0.00021887755102040815,
|
527 |
+
"loss": 1.7545,
|
528 |
+
"step": 73
|
529 |
+
},
|
530 |
+
{
|
531 |
+
"epoch": 1.3486238532110093,
|
532 |
+
"grad_norm": 0.40831202268600464,
|
533 |
+
"learning_rate": 0.0002173469387755102,
|
534 |
+
"loss": 1.8652,
|
535 |
+
"step": 74
|
536 |
+
},
|
537 |
+
{
|
538 |
+
"epoch": 1.3669724770642202,
|
539 |
+
"grad_norm": 0.44127607345581055,
|
540 |
+
"learning_rate": 0.00021581632653061222,
|
541 |
+
"loss": 1.5706,
|
542 |
+
"step": 75
|
543 |
+
},
|
544 |
+
{
|
545 |
+
"epoch": 1.385321100917431,
|
546 |
+
"grad_norm": 0.413889616727829,
|
547 |
+
"learning_rate": 0.00021428571428571427,
|
548 |
+
"loss": 1.5272,
|
549 |
+
"step": 76
|
550 |
+
},
|
551 |
+
{
|
552 |
+
"epoch": 1.4036697247706422,
|
553 |
+
"grad_norm": 0.4785701036453247,
|
554 |
+
"learning_rate": 0.0002127551020408163,
|
555 |
+
"loss": 1.572,
|
556 |
+
"step": 77
|
557 |
+
},
|
558 |
+
{
|
559 |
+
"epoch": 1.4220183486238533,
|
560 |
+
"grad_norm": 0.45182228088378906,
|
561 |
+
"learning_rate": 0.00021122448979591835,
|
562 |
+
"loss": 1.5978,
|
563 |
+
"step": 78
|
564 |
+
},
|
565 |
+
{
|
566 |
+
"epoch": 1.4403669724770642,
|
567 |
+
"grad_norm": 0.4382292628288269,
|
568 |
+
"learning_rate": 0.0002096938775510204,
|
569 |
+
"loss": 1.6424,
|
570 |
+
"step": 79
|
571 |
+
},
|
572 |
+
{
|
573 |
+
"epoch": 1.4587155963302751,
|
574 |
+
"grad_norm": 0.529373288154602,
|
575 |
+
"learning_rate": 0.00020816326530612243,
|
576 |
+
"loss": 1.5756,
|
577 |
+
"step": 80
|
578 |
+
},
|
579 |
+
{
|
580 |
+
"epoch": 1.4770642201834863,
|
581 |
+
"grad_norm": 0.4828866720199585,
|
582 |
+
"learning_rate": 0.00020663265306122448,
|
583 |
+
"loss": 1.6252,
|
584 |
+
"step": 81
|
585 |
+
},
|
586 |
+
{
|
587 |
+
"epoch": 1.4954128440366974,
|
588 |
+
"grad_norm": 0.455864816904068,
|
589 |
+
"learning_rate": 0.0002051020408163265,
|
590 |
+
"loss": 1.6719,
|
591 |
+
"step": 82
|
592 |
+
},
|
593 |
+
{
|
594 |
+
"epoch": 1.5137614678899083,
|
595 |
+
"grad_norm": 0.43042704463005066,
|
596 |
+
"learning_rate": 0.00020357142857142856,
|
597 |
+
"loss": 1.4768,
|
598 |
+
"step": 83
|
599 |
+
},
|
600 |
+
{
|
601 |
+
"epoch": 1.5321100917431192,
|
602 |
+
"grad_norm": 0.43703892827033997,
|
603 |
+
"learning_rate": 0.00020204081632653058,
|
604 |
+
"loss": 1.4823,
|
605 |
+
"step": 84
|
606 |
+
},
|
607 |
+
{
|
608 |
+
"epoch": 1.5504587155963303,
|
609 |
+
"grad_norm": 0.6060220003128052,
|
610 |
+
"learning_rate": 0.00020051020408163263,
|
611 |
+
"loss": 1.7325,
|
612 |
+
"step": 85
|
613 |
+
},
|
614 |
+
{
|
615 |
+
"epoch": 1.5688073394495414,
|
616 |
+
"grad_norm": 0.4146731495857239,
|
617 |
+
"learning_rate": 0.00019897959183673466,
|
618 |
+
"loss": 1.5784,
|
619 |
+
"step": 86
|
620 |
+
},
|
621 |
+
{
|
622 |
+
"epoch": 1.5871559633027523,
|
623 |
+
"grad_norm": 0.48514559864997864,
|
624 |
+
"learning_rate": 0.0001974489795918367,
|
625 |
+
"loss": 1.7322,
|
626 |
+
"step": 87
|
627 |
+
},
|
628 |
+
{
|
629 |
+
"epoch": 1.6055045871559632,
|
630 |
+
"grad_norm": 0.4649484157562256,
|
631 |
+
"learning_rate": 0.00019591836734693873,
|
632 |
+
"loss": 1.4178,
|
633 |
+
"step": 88
|
634 |
+
},
|
635 |
+
{
|
636 |
+
"epoch": 1.6238532110091743,
|
637 |
+
"grad_norm": 0.48133671283721924,
|
638 |
+
"learning_rate": 0.0001943877551020408,
|
639 |
+
"loss": 1.5013,
|
640 |
+
"step": 89
|
641 |
+
},
|
642 |
+
{
|
643 |
+
"epoch": 1.6422018348623855,
|
644 |
+
"grad_norm": 0.4548419415950775,
|
645 |
+
"learning_rate": 0.00019285714285714286,
|
646 |
+
"loss": 1.5874,
|
647 |
+
"step": 90
|
648 |
+
},
|
649 |
+
{
|
650 |
+
"epoch": 1.6605504587155964,
|
651 |
+
"grad_norm": 0.5536527633666992,
|
652 |
+
"learning_rate": 0.0001913265306122449,
|
653 |
+
"loss": 1.4934,
|
654 |
+
"step": 91
|
655 |
+
},
|
656 |
+
{
|
657 |
+
"epoch": 1.6788990825688073,
|
658 |
+
"grad_norm": 0.5949488878250122,
|
659 |
+
"learning_rate": 0.00018979591836734694,
|
660 |
+
"loss": 1.5306,
|
661 |
+
"step": 92
|
662 |
+
},
|
663 |
+
{
|
664 |
+
"epoch": 1.6972477064220184,
|
665 |
+
"grad_norm": 0.5679605603218079,
|
666 |
+
"learning_rate": 0.00018826530612244896,
|
667 |
+
"loss": 1.5162,
|
668 |
+
"step": 93
|
669 |
+
},
|
670 |
+
{
|
671 |
+
"epoch": 1.7155963302752295,
|
672 |
+
"grad_norm": 0.5724030137062073,
|
673 |
+
"learning_rate": 0.00018673469387755102,
|
674 |
+
"loss": 1.4972,
|
675 |
+
"step": 94
|
676 |
+
},
|
677 |
+
{
|
678 |
+
"epoch": 1.7339449541284404,
|
679 |
+
"grad_norm": 0.5926903486251831,
|
680 |
+
"learning_rate": 0.00018520408163265304,
|
681 |
+
"loss": 1.512,
|
682 |
+
"step": 95
|
683 |
+
},
|
684 |
+
{
|
685 |
+
"epoch": 1.7522935779816513,
|
686 |
+
"grad_norm": 0.49787193536758423,
|
687 |
+
"learning_rate": 0.0001836734693877551,
|
688 |
+
"loss": 1.5754,
|
689 |
+
"step": 96
|
690 |
+
},
|
691 |
+
{
|
692 |
+
"epoch": 1.7706422018348624,
|
693 |
+
"grad_norm": 0.521364152431488,
|
694 |
+
"learning_rate": 0.00018214285714285712,
|
695 |
+
"loss": 1.5558,
|
696 |
+
"step": 97
|
697 |
+
},
|
698 |
+
{
|
699 |
+
"epoch": 1.7889908256880735,
|
700 |
+
"grad_norm": 0.5252606868743896,
|
701 |
+
"learning_rate": 0.00018061224489795917,
|
702 |
+
"loss": 1.5562,
|
703 |
+
"step": 98
|
704 |
+
},
|
705 |
+
{
|
706 |
+
"epoch": 1.8073394495412844,
|
707 |
+
"grad_norm": 0.520020604133606,
|
708 |
+
"learning_rate": 0.00017908163265306122,
|
709 |
+
"loss": 1.5431,
|
710 |
+
"step": 99
|
711 |
+
},
|
712 |
+
{
|
713 |
+
"epoch": 1.8256880733944953,
|
714 |
+
"grad_norm": 0.5684699416160583,
|
715 |
+
"learning_rate": 0.00017755102040816325,
|
716 |
+
"loss": 1.4776,
|
717 |
+
"step": 100
|
718 |
+
},
|
719 |
+
{
|
720 |
+
"epoch": 1.8440366972477065,
|
721 |
+
"grad_norm": 0.49918070435523987,
|
722 |
+
"learning_rate": 0.0001760204081632653,
|
723 |
+
"loss": 1.5665,
|
724 |
+
"step": 101
|
725 |
+
},
|
726 |
+
{
|
727 |
+
"epoch": 1.8623853211009176,
|
728 |
+
"grad_norm": 0.5219622850418091,
|
729 |
+
"learning_rate": 0.00017448979591836732,
|
730 |
+
"loss": 1.4726,
|
731 |
+
"step": 102
|
732 |
+
},
|
733 |
+
{
|
734 |
+
"epoch": 1.8807339449541285,
|
735 |
+
"grad_norm": 0.49506455659866333,
|
736 |
+
"learning_rate": 0.00017295918367346937,
|
737 |
+
"loss": 1.5677,
|
738 |
+
"step": 103
|
739 |
+
},
|
740 |
+
{
|
741 |
+
"epoch": 1.8990825688073394,
|
742 |
+
"grad_norm": 0.48011767864227295,
|
743 |
+
"learning_rate": 0.0001714285714285714,
|
744 |
+
"loss": 1.4628,
|
745 |
+
"step": 104
|
746 |
+
},
|
747 |
+
{
|
748 |
+
"epoch": 1.9174311926605505,
|
749 |
+
"grad_norm": 0.49670523405075073,
|
750 |
+
"learning_rate": 0.00016989795918367345,
|
751 |
+
"loss": 1.343,
|
752 |
+
"step": 105
|
753 |
+
},
|
754 |
+
{
|
755 |
+
"epoch": 1.9357798165137616,
|
756 |
+
"grad_norm": 0.5730084180831909,
|
757 |
+
"learning_rate": 0.00016836734693877547,
|
758 |
+
"loss": 1.5211,
|
759 |
+
"step": 106
|
760 |
+
},
|
761 |
+
{
|
762 |
+
"epoch": 1.9541284403669725,
|
763 |
+
"grad_norm": 0.5185048580169678,
|
764 |
+
"learning_rate": 0.00016683673469387753,
|
765 |
+
"loss": 1.4416,
|
766 |
+
"step": 107
|
767 |
+
},
|
768 |
+
{
|
769 |
+
"epoch": 1.9724770642201834,
|
770 |
+
"grad_norm": 0.5075457692146301,
|
771 |
+
"learning_rate": 0.00016530612244897955,
|
772 |
+
"loss": 1.3877,
|
773 |
+
"step": 108
|
774 |
+
},
|
775 |
+
{
|
776 |
+
"epoch": 1.9908256880733946,
|
777 |
+
"grad_norm": 0.5157256126403809,
|
778 |
+
"learning_rate": 0.00016377551020408163,
|
779 |
+
"loss": 1.4932,
|
780 |
+
"step": 109
|
781 |
+
},
|
782 |
+
{
|
783 |
+
"epoch": 2.0,
|
784 |
+
"grad_norm": 0.8046102523803711,
|
785 |
+
"learning_rate": 0.00016224489795918368,
|
786 |
+
"loss": 1.3092,
|
787 |
+
"step": 110
|
788 |
+
},
|
789 |
+
{
|
790 |
+
"epoch": 2.0,
|
791 |
+
"eval_loss": 1.7067729234695435,
|
792 |
+
"eval_runtime": 40.3292,
|
793 |
+
"eval_samples_per_second": 8.232,
|
794 |
+
"eval_steps_per_second": 4.116,
|
795 |
+
"step": 110
|
796 |
+
},
|
797 |
+
{
|
798 |
+
"epoch": 2.018348623853211,
|
799 |
+
"grad_norm": 0.5372384786605835,
|
800 |
+
"learning_rate": 0.0001607142857142857,
|
801 |
+
"loss": 1.4086,
|
802 |
+
"step": 111
|
803 |
+
},
|
804 |
+
{
|
805 |
+
"epoch": 2.036697247706422,
|
806 |
+
"grad_norm": 0.5499650239944458,
|
807 |
+
"learning_rate": 0.00015918367346938776,
|
808 |
+
"loss": 1.4309,
|
809 |
+
"step": 112
|
810 |
+
},
|
811 |
+
{
|
812 |
+
"epoch": 2.055045871559633,
|
813 |
+
"grad_norm": 0.5393022298812866,
|
814 |
+
"learning_rate": 0.00015765306122448978,
|
815 |
+
"loss": 1.3377,
|
816 |
+
"step": 113
|
817 |
+
},
|
818 |
+
{
|
819 |
+
"epoch": 2.073394495412844,
|
820 |
+
"grad_norm": 0.4644460678100586,
|
821 |
+
"learning_rate": 0.00015612244897959183,
|
822 |
+
"loss": 1.3486,
|
823 |
+
"step": 114
|
824 |
+
},
|
825 |
+
{
|
826 |
+
"epoch": 2.091743119266055,
|
827 |
+
"grad_norm": 0.5637883543968201,
|
828 |
+
"learning_rate": 0.00015459183673469386,
|
829 |
+
"loss": 1.3423,
|
830 |
+
"step": 115
|
831 |
+
},
|
832 |
+
{
|
833 |
+
"epoch": 2.1100917431192663,
|
834 |
+
"grad_norm": 0.5196585655212402,
|
835 |
+
"learning_rate": 0.0001530612244897959,
|
836 |
+
"loss": 1.1701,
|
837 |
+
"step": 116
|
838 |
+
},
|
839 |
+
{
|
840 |
+
"epoch": 2.128440366972477,
|
841 |
+
"grad_norm": 0.5293002724647522,
|
842 |
+
"learning_rate": 0.00015153061224489794,
|
843 |
+
"loss": 1.3339,
|
844 |
+
"step": 117
|
845 |
+
},
|
846 |
+
{
|
847 |
+
"epoch": 2.146788990825688,
|
848 |
+
"grad_norm": 0.5287687182426453,
|
849 |
+
"learning_rate": 0.00015,
|
850 |
+
"loss": 1.2385,
|
851 |
+
"step": 118
|
852 |
+
},
|
853 |
+
{
|
854 |
+
"epoch": 2.165137614678899,
|
855 |
+
"grad_norm": 0.5759944319725037,
|
856 |
+
"learning_rate": 0.00014846938775510204,
|
857 |
+
"loss": 1.3614,
|
858 |
+
"step": 119
|
859 |
+
},
|
860 |
+
{
|
861 |
+
"epoch": 2.18348623853211,
|
862 |
+
"grad_norm": 0.6487063765525818,
|
863 |
+
"learning_rate": 0.00014693877551020406,
|
864 |
+
"loss": 1.392,
|
865 |
+
"step": 120
|
866 |
+
},
|
867 |
+
{
|
868 |
+
"epoch": 2.2018348623853212,
|
869 |
+
"grad_norm": 0.5643731355667114,
|
870 |
+
"learning_rate": 0.00014540816326530611,
|
871 |
+
"loss": 1.3722,
|
872 |
+
"step": 121
|
873 |
+
},
|
874 |
+
{
|
875 |
+
"epoch": 2.220183486238532,
|
876 |
+
"grad_norm": 0.6352585554122925,
|
877 |
+
"learning_rate": 0.00014387755102040814,
|
878 |
+
"loss": 1.4423,
|
879 |
+
"step": 122
|
880 |
+
},
|
881 |
+
{
|
882 |
+
"epoch": 2.238532110091743,
|
883 |
+
"grad_norm": 0.5605873465538025,
|
884 |
+
"learning_rate": 0.0001423469387755102,
|
885 |
+
"loss": 1.3284,
|
886 |
+
"step": 123
|
887 |
+
},
|
888 |
+
{
|
889 |
+
"epoch": 2.2568807339449544,
|
890 |
+
"grad_norm": 0.49541911482810974,
|
891 |
+
"learning_rate": 0.00014081632653061224,
|
892 |
+
"loss": 1.324,
|
893 |
+
"step": 124
|
894 |
+
},
|
895 |
+
{
|
896 |
+
"epoch": 2.2752293577981653,
|
897 |
+
"grad_norm": 0.5412710905075073,
|
898 |
+
"learning_rate": 0.00013928571428571427,
|
899 |
+
"loss": 1.2605,
|
900 |
+
"step": 125
|
901 |
+
},
|
902 |
+
{
|
903 |
+
"epoch": 2.293577981651376,
|
904 |
+
"grad_norm": 0.575342059135437,
|
905 |
+
"learning_rate": 0.00013775510204081632,
|
906 |
+
"loss": 1.2615,
|
907 |
+
"step": 126
|
908 |
+
},
|
909 |
+
{
|
910 |
+
"epoch": 2.311926605504587,
|
911 |
+
"grad_norm": 0.6061179637908936,
|
912 |
+
"learning_rate": 0.00013622448979591834,
|
913 |
+
"loss": 1.3793,
|
914 |
+
"step": 127
|
915 |
+
},
|
916 |
+
{
|
917 |
+
"epoch": 2.330275229357798,
|
918 |
+
"grad_norm": 0.5834862589836121,
|
919 |
+
"learning_rate": 0.0001346938775510204,
|
920 |
+
"loss": 1.3506,
|
921 |
+
"step": 128
|
922 |
+
},
|
923 |
+
{
|
924 |
+
"epoch": 2.3486238532110093,
|
925 |
+
"grad_norm": 0.5381261110305786,
|
926 |
+
"learning_rate": 0.00013316326530612245,
|
927 |
+
"loss": 1.224,
|
928 |
+
"step": 129
|
929 |
+
},
|
930 |
+
{
|
931 |
+
"epoch": 2.36697247706422,
|
932 |
+
"grad_norm": 0.7020912170410156,
|
933 |
+
"learning_rate": 0.00013163265306122447,
|
934 |
+
"loss": 1.3398,
|
935 |
+
"step": 130
|
936 |
+
},
|
937 |
+
{
|
938 |
+
"epoch": 2.385321100917431,
|
939 |
+
"grad_norm": 0.5954611897468567,
|
940 |
+
"learning_rate": 0.00013010204081632652,
|
941 |
+
"loss": 1.2508,
|
942 |
+
"step": 131
|
943 |
+
},
|
944 |
+
{
|
945 |
+
"epoch": 2.4036697247706424,
|
946 |
+
"grad_norm": 0.5576110482215881,
|
947 |
+
"learning_rate": 0.00012857142857142855,
|
948 |
+
"loss": 1.266,
|
949 |
+
"step": 132
|
950 |
+
},
|
951 |
+
{
|
952 |
+
"epoch": 2.4220183486238533,
|
953 |
+
"grad_norm": 0.5651321411132812,
|
954 |
+
"learning_rate": 0.0001270408163265306,
|
955 |
+
"loss": 1.1969,
|
956 |
+
"step": 133
|
957 |
+
},
|
958 |
+
{
|
959 |
+
"epoch": 2.4403669724770642,
|
960 |
+
"grad_norm": 0.6407105326652527,
|
961 |
+
"learning_rate": 0.00012551020408163265,
|
962 |
+
"loss": 1.2142,
|
963 |
+
"step": 134
|
964 |
+
},
|
965 |
+
{
|
966 |
+
"epoch": 2.458715596330275,
|
967 |
+
"grad_norm": 0.6058876514434814,
|
968 |
+
"learning_rate": 0.00012397959183673468,
|
969 |
+
"loss": 1.2383,
|
970 |
+
"step": 135
|
971 |
+
},
|
972 |
+
{
|
973 |
+
"epoch": 2.477064220183486,
|
974 |
+
"grad_norm": 0.5757945775985718,
|
975 |
+
"learning_rate": 0.00012244897959183673,
|
976 |
+
"loss": 1.286,
|
977 |
+
"step": 136
|
978 |
+
},
|
979 |
+
{
|
980 |
+
"epoch": 2.4954128440366974,
|
981 |
+
"grad_norm": 0.5286776423454285,
|
982 |
+
"learning_rate": 0.00012091836734693877,
|
983 |
+
"loss": 1.364,
|
984 |
+
"step": 137
|
985 |
+
},
|
986 |
+
{
|
987 |
+
"epoch": 2.5137614678899083,
|
988 |
+
"grad_norm": 0.5179428458213806,
|
989 |
+
"learning_rate": 0.0001193877551020408,
|
990 |
+
"loss": 1.1119,
|
991 |
+
"step": 138
|
992 |
+
},
|
993 |
+
{
|
994 |
+
"epoch": 2.532110091743119,
|
995 |
+
"grad_norm": 0.6148931384086609,
|
996 |
+
"learning_rate": 0.00011785714285714284,
|
997 |
+
"loss": 1.2517,
|
998 |
+
"step": 139
|
999 |
+
},
|
1000 |
+
{
|
1001 |
+
"epoch": 2.5504587155963305,
|
1002 |
+
"grad_norm": 0.5199230313301086,
|
1003 |
+
"learning_rate": 0.00011632653061224488,
|
1004 |
+
"loss": 1.2244,
|
1005 |
+
"step": 140
|
1006 |
+
},
|
1007 |
+
{
|
1008 |
+
"epoch": 2.5688073394495414,
|
1009 |
+
"grad_norm": 0.8426241278648376,
|
1010 |
+
"learning_rate": 0.00011479591836734692,
|
1011 |
+
"loss": 1.2683,
|
1012 |
+
"step": 141
|
1013 |
+
},
|
1014 |
+
{
|
1015 |
+
"epoch": 2.5871559633027523,
|
1016 |
+
"grad_norm": 0.5697855949401855,
|
1017 |
+
"learning_rate": 0.00011326530612244896,
|
1018 |
+
"loss": 1.1894,
|
1019 |
+
"step": 142
|
1020 |
+
},
|
1021 |
+
{
|
1022 |
+
"epoch": 2.6055045871559632,
|
1023 |
+
"grad_norm": 0.6371927261352539,
|
1024 |
+
"learning_rate": 0.00011173469387755102,
|
1025 |
+
"loss": 1.1667,
|
1026 |
+
"step": 143
|
1027 |
+
},
|
1028 |
+
{
|
1029 |
+
"epoch": 2.623853211009174,
|
1030 |
+
"grad_norm": 0.5687111616134644,
|
1031 |
+
"learning_rate": 0.00011020408163265306,
|
1032 |
+
"loss": 1.2333,
|
1033 |
+
"step": 144
|
1034 |
+
},
|
1035 |
+
{
|
1036 |
+
"epoch": 2.6422018348623855,
|
1037 |
+
"grad_norm": 0.7226176261901855,
|
1038 |
+
"learning_rate": 0.0001086734693877551,
|
1039 |
+
"loss": 1.1316,
|
1040 |
+
"step": 145
|
1041 |
+
},
|
1042 |
+
{
|
1043 |
+
"epoch": 2.6605504587155964,
|
1044 |
+
"grad_norm": 0.5449386239051819,
|
1045 |
+
"learning_rate": 0.00010714285714285714,
|
1046 |
+
"loss": 1.3315,
|
1047 |
+
"step": 146
|
1048 |
+
},
|
1049 |
+
{
|
1050 |
+
"epoch": 2.6788990825688073,
|
1051 |
+
"grad_norm": 0.5627453327178955,
|
1052 |
+
"learning_rate": 0.00010561224489795918,
|
1053 |
+
"loss": 1.1903,
|
1054 |
+
"step": 147
|
1055 |
+
},
|
1056 |
+
{
|
1057 |
+
"epoch": 2.6972477064220186,
|
1058 |
+
"grad_norm": 0.6717932820320129,
|
1059 |
+
"learning_rate": 0.00010408163265306121,
|
1060 |
+
"loss": 1.1551,
|
1061 |
+
"step": 148
|
1062 |
+
},
|
1063 |
+
{
|
1064 |
+
"epoch": 2.7155963302752295,
|
1065 |
+
"grad_norm": 0.6216678619384766,
|
1066 |
+
"learning_rate": 0.00010255102040816325,
|
1067 |
+
"loss": 1.3409,
|
1068 |
+
"step": 149
|
1069 |
+
},
|
1070 |
+
{
|
1071 |
+
"epoch": 2.7339449541284404,
|
1072 |
+
"grad_norm": 0.565977156162262,
|
1073 |
+
"learning_rate": 0.00010102040816326529,
|
1074 |
+
"loss": 1.2799,
|
1075 |
+
"step": 150
|
1076 |
+
},
|
1077 |
+
{
|
1078 |
+
"epoch": 2.7522935779816513,
|
1079 |
+
"grad_norm": 0.6974563598632812,
|
1080 |
+
"learning_rate": 9.948979591836733e-05,
|
1081 |
+
"loss": 1.2034,
|
1082 |
+
"step": 151
|
1083 |
+
},
|
1084 |
+
{
|
1085 |
+
"epoch": 2.770642201834862,
|
1086 |
+
"grad_norm": 0.5820234417915344,
|
1087 |
+
"learning_rate": 9.795918367346937e-05,
|
1088 |
+
"loss": 1.1747,
|
1089 |
+
"step": 152
|
1090 |
+
},
|
1091 |
+
{
|
1092 |
+
"epoch": 2.7889908256880735,
|
1093 |
+
"grad_norm": 0.5635000467300415,
|
1094 |
+
"learning_rate": 9.642857142857143e-05,
|
1095 |
+
"loss": 1.2143,
|
1096 |
+
"step": 153
|
1097 |
+
},
|
1098 |
+
{
|
1099 |
+
"epoch": 2.8073394495412844,
|
1100 |
+
"grad_norm": 0.6183028817176819,
|
1101 |
+
"learning_rate": 9.489795918367347e-05,
|
1102 |
+
"loss": 1.0934,
|
1103 |
+
"step": 154
|
1104 |
+
},
|
1105 |
+
{
|
1106 |
+
"epoch": 2.8256880733944953,
|
1107 |
+
"grad_norm": 0.5435863733291626,
|
1108 |
+
"learning_rate": 9.336734693877551e-05,
|
1109 |
+
"loss": 1.254,
|
1110 |
+
"step": 155
|
1111 |
+
},
|
1112 |
+
{
|
1113 |
+
"epoch": 2.8440366972477067,
|
1114 |
+
"grad_norm": 0.6071304678916931,
|
1115 |
+
"learning_rate": 9.183673469387755e-05,
|
1116 |
+
"loss": 1.0866,
|
1117 |
+
"step": 156
|
1118 |
+
},
|
1119 |
+
{
|
1120 |
+
"epoch": 2.8623853211009176,
|
1121 |
+
"grad_norm": 0.6845288276672363,
|
1122 |
+
"learning_rate": 9.030612244897958e-05,
|
1123 |
+
"loss": 1.0657,
|
1124 |
+
"step": 157
|
1125 |
+
},
|
1126 |
+
{
|
1127 |
+
"epoch": 2.8807339449541285,
|
1128 |
+
"grad_norm": 0.7707186341285706,
|
1129 |
+
"learning_rate": 8.877551020408162e-05,
|
1130 |
+
"loss": 1.1873,
|
1131 |
+
"step": 158
|
1132 |
+
},
|
1133 |
+
{
|
1134 |
+
"epoch": 2.8990825688073394,
|
1135 |
+
"grad_norm": 0.6403721570968628,
|
1136 |
+
"learning_rate": 8.724489795918366e-05,
|
1137 |
+
"loss": 1.2217,
|
1138 |
+
"step": 159
|
1139 |
+
},
|
1140 |
+
{
|
1141 |
+
"epoch": 2.9174311926605503,
|
1142 |
+
"grad_norm": 0.6184455752372742,
|
1143 |
+
"learning_rate": 8.57142857142857e-05,
|
1144 |
+
"loss": 1.2699,
|
1145 |
+
"step": 160
|
1146 |
+
},
|
1147 |
+
{
|
1148 |
+
"epoch": 2.9357798165137616,
|
1149 |
+
"grad_norm": 0.6127010583877563,
|
1150 |
+
"learning_rate": 8.418367346938774e-05,
|
1151 |
+
"loss": 1.1339,
|
1152 |
+
"step": 161
|
1153 |
+
},
|
1154 |
+
{
|
1155 |
+
"epoch": 2.9541284403669725,
|
1156 |
+
"grad_norm": 0.5781142711639404,
|
1157 |
+
"learning_rate": 8.265306122448978e-05,
|
1158 |
+
"loss": 1.0983,
|
1159 |
+
"step": 162
|
1160 |
+
},
|
1161 |
+
{
|
1162 |
+
"epoch": 2.9724770642201834,
|
1163 |
+
"grad_norm": 0.6162577271461487,
|
1164 |
+
"learning_rate": 8.112244897959184e-05,
|
1165 |
+
"loss": 1.225,
|
1166 |
+
"step": 163
|
1167 |
+
},
|
1168 |
+
{
|
1169 |
+
"epoch": 2.9908256880733948,
|
1170 |
+
"grad_norm": 0.5873180031776428,
|
1171 |
+
"learning_rate": 7.959183673469388e-05,
|
1172 |
+
"loss": 1.1027,
|
1173 |
+
"step": 164
|
1174 |
+
},
|
1175 |
+
{
|
1176 |
+
"epoch": 3.0,
|
1177 |
+
"grad_norm": 0.9156239032745361,
|
1178 |
+
"learning_rate": 7.806122448979592e-05,
|
1179 |
+
"loss": 1.2634,
|
1180 |
+
"step": 165
|
1181 |
+
},
|
1182 |
+
{
|
1183 |
+
"epoch": 3.0,
|
1184 |
+
"eval_loss": 1.765793800354004,
|
1185 |
+
"eval_runtime": 40.2043,
|
1186 |
+
"eval_samples_per_second": 8.258,
|
1187 |
+
"eval_steps_per_second": 4.129,
|
1188 |
+
"step": 165
|
1189 |
+
},
|
1190 |
+
{
|
1191 |
+
"epoch": 3.018348623853211,
|
1192 |
+
"grad_norm": 2.7086777687072754,
|
1193 |
+
"learning_rate": 7.653061224489796e-05,
|
1194 |
+
"loss": 0.9086,
|
1195 |
+
"step": 166
|
1196 |
+
},
|
1197 |
+
{
|
1198 |
+
"epoch": 3.036697247706422,
|
1199 |
+
"grad_norm": 0.798815131187439,
|
1200 |
+
"learning_rate": 7.5e-05,
|
1201 |
+
"loss": 0.9862,
|
1202 |
+
"step": 167
|
1203 |
+
},
|
1204 |
+
{
|
1205 |
+
"epoch": 3.055045871559633,
|
1206 |
+
"grad_norm": 0.6483126878738403,
|
1207 |
+
"learning_rate": 7.346938775510203e-05,
|
1208 |
+
"loss": 1.0914,
|
1209 |
+
"step": 168
|
1210 |
+
},
|
1211 |
+
{
|
1212 |
+
"epoch": 3.073394495412844,
|
1213 |
+
"grad_norm": 0.9064918160438538,
|
1214 |
+
"learning_rate": 7.193877551020407e-05,
|
1215 |
+
"loss": 0.9983,
|
1216 |
+
"step": 169
|
1217 |
+
},
|
1218 |
+
{
|
1219 |
+
"epoch": 3.091743119266055,
|
1220 |
+
"grad_norm": 0.5859102010726929,
|
1221 |
+
"learning_rate": 7.040816326530612e-05,
|
1222 |
+
"loss": 1.2501,
|
1223 |
+
"step": 170
|
1224 |
+
},
|
1225 |
+
{
|
1226 |
+
"epoch": 3.1100917431192663,
|
1227 |
+
"grad_norm": 1.0210392475128174,
|
1228 |
+
"learning_rate": 6.887755102040816e-05,
|
1229 |
+
"loss": 0.9503,
|
1230 |
+
"step": 171
|
1231 |
+
},
|
1232 |
+
{
|
1233 |
+
"epoch": 3.128440366972477,
|
1234 |
+
"grad_norm": 0.5909506678581238,
|
1235 |
+
"learning_rate": 6.73469387755102e-05,
|
1236 |
+
"loss": 1.1646,
|
1237 |
+
"step": 172
|
1238 |
+
},
|
1239 |
+
{
|
1240 |
+
"epoch": 3.146788990825688,
|
1241 |
+
"grad_norm": 0.8601213693618774,
|
1242 |
+
"learning_rate": 6.581632653061224e-05,
|
1243 |
+
"loss": 1.089,
|
1244 |
+
"step": 173
|
1245 |
+
},
|
1246 |
+
{
|
1247 |
+
"epoch": 3.165137614678899,
|
1248 |
+
"grad_norm": 1.5392725467681885,
|
1249 |
+
"learning_rate": 6.428571428571427e-05,
|
1250 |
+
"loss": 1.1588,
|
1251 |
+
"step": 174
|
1252 |
+
},
|
1253 |
+
{
|
1254 |
+
"epoch": 3.18348623853211,
|
1255 |
+
"grad_norm": 0.6926484107971191,
|
1256 |
+
"learning_rate": 6.275510204081633e-05,
|
1257 |
+
"loss": 1.0608,
|
1258 |
+
"step": 175
|
1259 |
+
},
|
1260 |
+
{
|
1261 |
+
"epoch": 3.2018348623853212,
|
1262 |
+
"grad_norm": 0.6359078288078308,
|
1263 |
+
"learning_rate": 6.122448979591836e-05,
|
1264 |
+
"loss": 1.2014,
|
1265 |
+
"step": 176
|
1266 |
+
},
|
1267 |
+
{
|
1268 |
+
"epoch": 3.220183486238532,
|
1269 |
+
"grad_norm": 0.7411192655563354,
|
1270 |
+
"learning_rate": 5.96938775510204e-05,
|
1271 |
+
"loss": 1.0524,
|
1272 |
+
"step": 177
|
1273 |
+
},
|
1274 |
+
{
|
1275 |
+
"epoch": 3.238532110091743,
|
1276 |
+
"grad_norm": 0.7913389801979065,
|
1277 |
+
"learning_rate": 5.816326530612244e-05,
|
1278 |
+
"loss": 0.9702,
|
1279 |
+
"step": 178
|
1280 |
+
},
|
1281 |
+
{
|
1282 |
+
"epoch": 3.2568807339449544,
|
1283 |
+
"grad_norm": 0.5389623045921326,
|
1284 |
+
"learning_rate": 5.663265306122448e-05,
|
1285 |
+
"loss": 1.0675,
|
1286 |
+
"step": 179
|
1287 |
+
},
|
1288 |
+
{
|
1289 |
+
"epoch": 3.2752293577981653,
|
1290 |
+
"grad_norm": 0.4771580398082733,
|
1291 |
+
"learning_rate": 5.510204081632653e-05,
|
1292 |
+
"loss": 1.0254,
|
1293 |
+
"step": 180
|
1294 |
+
},
|
1295 |
+
{
|
1296 |
+
"epoch": 3.293577981651376,
|
1297 |
+
"grad_norm": 0.7268071174621582,
|
1298 |
+
"learning_rate": 5.357142857142857e-05,
|
1299 |
+
"loss": 1.0475,
|
1300 |
+
"step": 181
|
1301 |
+
},
|
1302 |
+
{
|
1303 |
+
"epoch": 3.311926605504587,
|
1304 |
+
"grad_norm": 0.6685888767242432,
|
1305 |
+
"learning_rate": 5.204081632653061e-05,
|
1306 |
+
"loss": 0.9658,
|
1307 |
+
"step": 182
|
1308 |
+
},
|
1309 |
+
{
|
1310 |
+
"epoch": 3.330275229357798,
|
1311 |
+
"grad_norm": 0.5965012907981873,
|
1312 |
+
"learning_rate": 5.0510204081632645e-05,
|
1313 |
+
"loss": 1.0657,
|
1314 |
+
"step": 183
|
1315 |
+
},
|
1316 |
+
{
|
1317 |
+
"epoch": 3.3486238532110093,
|
1318 |
+
"grad_norm": 0.5370911955833435,
|
1319 |
+
"learning_rate": 4.897959183673468e-05,
|
1320 |
+
"loss": 1.0277,
|
1321 |
+
"step": 184
|
1322 |
+
},
|
1323 |
+
{
|
1324 |
+
"epoch": 3.36697247706422,
|
1325 |
+
"grad_norm": 0.646511971950531,
|
1326 |
+
"learning_rate": 4.7448979591836735e-05,
|
1327 |
+
"loss": 1.1439,
|
1328 |
+
"step": 185
|
1329 |
+
},
|
1330 |
+
{
|
1331 |
+
"epoch": 3.385321100917431,
|
1332 |
+
"grad_norm": 0.5768170356750488,
|
1333 |
+
"learning_rate": 4.591836734693877e-05,
|
1334 |
+
"loss": 1.253,
|
1335 |
+
"step": 186
|
1336 |
+
},
|
1337 |
+
{
|
1338 |
+
"epoch": 3.4036697247706424,
|
1339 |
+
"grad_norm": 0.6067250370979309,
|
1340 |
+
"learning_rate": 4.438775510204081e-05,
|
1341 |
+
"loss": 0.9355,
|
1342 |
+
"step": 187
|
1343 |
+
},
|
1344 |
+
{
|
1345 |
+
"epoch": 3.4220183486238533,
|
1346 |
+
"grad_norm": 0.8360852003097534,
|
1347 |
+
"learning_rate": 4.285714285714285e-05,
|
1348 |
+
"loss": 1.0526,
|
1349 |
+
"step": 188
|
1350 |
+
},
|
1351 |
+
{
|
1352 |
+
"epoch": 3.4403669724770642,
|
1353 |
+
"grad_norm": 0.59422767162323,
|
1354 |
+
"learning_rate": 4.132653061224489e-05,
|
1355 |
+
"loss": 1.1794,
|
1356 |
+
"step": 189
|
1357 |
+
},
|
1358 |
+
{
|
1359 |
+
"epoch": 3.458715596330275,
|
1360 |
+
"grad_norm": 0.5541112422943115,
|
1361 |
+
"learning_rate": 3.979591836734694e-05,
|
1362 |
+
"loss": 0.9477,
|
1363 |
+
"step": 190
|
1364 |
+
},
|
1365 |
+
{
|
1366 |
+
"epoch": 3.477064220183486,
|
1367 |
+
"grad_norm": 0.587552547454834,
|
1368 |
+
"learning_rate": 3.826530612244898e-05,
|
1369 |
+
"loss": 1.0714,
|
1370 |
+
"step": 191
|
1371 |
+
},
|
1372 |
+
{
|
1373 |
+
"epoch": 3.4954128440366974,
|
1374 |
+
"grad_norm": 0.5143390893936157,
|
1375 |
+
"learning_rate": 3.6734693877551016e-05,
|
1376 |
+
"loss": 1.0379,
|
1377 |
+
"step": 192
|
1378 |
+
},
|
1379 |
+
{
|
1380 |
+
"epoch": 3.5137614678899083,
|
1381 |
+
"grad_norm": 0.6476455330848694,
|
1382 |
+
"learning_rate": 3.520408163265306e-05,
|
1383 |
+
"loss": 0.9505,
|
1384 |
+
"step": 193
|
1385 |
+
},
|
1386 |
+
{
|
1387 |
+
"epoch": 3.532110091743119,
|
1388 |
+
"grad_norm": 0.5314425230026245,
|
1389 |
+
"learning_rate": 3.36734693877551e-05,
|
1390 |
+
"loss": 1.0504,
|
1391 |
+
"step": 194
|
1392 |
+
},
|
1393 |
+
{
|
1394 |
+
"epoch": 3.5504587155963305,
|
1395 |
+
"grad_norm": 0.6685779094696045,
|
1396 |
+
"learning_rate": 3.214285714285714e-05,
|
1397 |
+
"loss": 1.083,
|
1398 |
+
"step": 195
|
1399 |
+
},
|
1400 |
+
{
|
1401 |
+
"epoch": 3.5688073394495414,
|
1402 |
+
"grad_norm": 0.5587136149406433,
|
1403 |
+
"learning_rate": 3.061224489795918e-05,
|
1404 |
+
"loss": 0.9242,
|
1405 |
+
"step": 196
|
1406 |
+
},
|
1407 |
+
{
|
1408 |
+
"epoch": 3.5871559633027523,
|
1409 |
+
"grad_norm": 0.5730684995651245,
|
1410 |
+
"learning_rate": 2.908163265306122e-05,
|
1411 |
+
"loss": 1.0271,
|
1412 |
+
"step": 197
|
1413 |
+
},
|
1414 |
+
{
|
1415 |
+
"epoch": 3.6055045871559632,
|
1416 |
+
"grad_norm": 0.5254084467887878,
|
1417 |
+
"learning_rate": 2.7551020408163265e-05,
|
1418 |
+
"loss": 1.0828,
|
1419 |
+
"step": 198
|
1420 |
+
},
|
1421 |
+
{
|
1422 |
+
"epoch": 3.623853211009174,
|
1423 |
+
"grad_norm": 0.5611628890037537,
|
1424 |
+
"learning_rate": 2.6020408163265303e-05,
|
1425 |
+
"loss": 1.1933,
|
1426 |
+
"step": 199
|
1427 |
+
},
|
1428 |
+
{
|
1429 |
+
"epoch": 3.6422018348623855,
|
1430 |
+
"grad_norm": 0.541988730430603,
|
1431 |
+
"learning_rate": 2.448979591836734e-05,
|
1432 |
+
"loss": 0.9135,
|
1433 |
+
"step": 200
|
1434 |
+
},
|
1435 |
+
{
|
1436 |
+
"epoch": 3.6605504587155964,
|
1437 |
+
"grad_norm": 0.5615597367286682,
|
1438 |
+
"learning_rate": 2.2959183673469387e-05,
|
1439 |
+
"loss": 0.9679,
|
1440 |
+
"step": 201
|
1441 |
+
},
|
1442 |
+
{
|
1443 |
+
"epoch": 3.6788990825688073,
|
1444 |
+
"grad_norm": 0.664253830909729,
|
1445 |
+
"learning_rate": 2.1428571428571425e-05,
|
1446 |
+
"loss": 0.9984,
|
1447 |
+
"step": 202
|
1448 |
+
},
|
1449 |
+
{
|
1450 |
+
"epoch": 3.6972477064220186,
|
1451 |
+
"grad_norm": 0.5762522220611572,
|
1452 |
+
"learning_rate": 1.989795918367347e-05,
|
1453 |
+
"loss": 1.0341,
|
1454 |
+
"step": 203
|
1455 |
+
},
|
1456 |
+
{
|
1457 |
+
"epoch": 3.7155963302752295,
|
1458 |
+
"grad_norm": 0.544408917427063,
|
1459 |
+
"learning_rate": 1.8367346938775508e-05,
|
1460 |
+
"loss": 1.2647,
|
1461 |
+
"step": 204
|
1462 |
+
},
|
1463 |
+
{
|
1464 |
+
"epoch": 3.7339449541284404,
|
1465 |
+
"grad_norm": 0.5570142865180969,
|
1466 |
+
"learning_rate": 1.683673469387755e-05,
|
1467 |
+
"loss": 0.8697,
|
1468 |
+
"step": 205
|
1469 |
+
},
|
1470 |
+
{
|
1471 |
+
"epoch": 3.7522935779816513,
|
1472 |
+
"grad_norm": 0.5823831558227539,
|
1473 |
+
"learning_rate": 1.530612244897959e-05,
|
1474 |
+
"loss": 1.0817,
|
1475 |
+
"step": 206
|
1476 |
+
},
|
1477 |
+
{
|
1478 |
+
"epoch": 3.770642201834862,
|
1479 |
+
"grad_norm": 0.672044038772583,
|
1480 |
+
"learning_rate": 1.3775510204081633e-05,
|
1481 |
+
"loss": 1.029,
|
1482 |
+
"step": 207
|
1483 |
+
},
|
1484 |
+
{
|
1485 |
+
"epoch": 3.7889908256880735,
|
1486 |
+
"grad_norm": 0.6006896495819092,
|
1487 |
+
"learning_rate": 1.224489795918367e-05,
|
1488 |
+
"loss": 1.1158,
|
1489 |
+
"step": 208
|
1490 |
+
},
|
1491 |
+
{
|
1492 |
+
"epoch": 3.8073394495412844,
|
1493 |
+
"grad_norm": 0.546748697757721,
|
1494 |
+
"learning_rate": 1.0714285714285712e-05,
|
1495 |
+
"loss": 0.8507,
|
1496 |
+
"step": 209
|
1497 |
+
},
|
1498 |
+
{
|
1499 |
+
"epoch": 3.8256880733944953,
|
1500 |
+
"grad_norm": 0.6468778252601624,
|
1501 |
+
"learning_rate": 9.183673469387754e-06,
|
1502 |
+
"loss": 1.0383,
|
1503 |
+
"step": 210
|
1504 |
+
},
|
1505 |
+
{
|
1506 |
+
"epoch": 3.8440366972477067,
|
1507 |
+
"grad_norm": 0.510528564453125,
|
1508 |
+
"learning_rate": 7.653061224489796e-06,
|
1509 |
+
"loss": 0.8932,
|
1510 |
+
"step": 211
|
1511 |
+
},
|
1512 |
+
{
|
1513 |
+
"epoch": 3.8623853211009176,
|
1514 |
+
"grad_norm": 0.5235452055931091,
|
1515 |
+
"learning_rate": 6.122448979591835e-06,
|
1516 |
+
"loss": 0.9912,
|
1517 |
+
"step": 212
|
1518 |
+
},
|
1519 |
+
{
|
1520 |
+
"epoch": 3.8807339449541285,
|
1521 |
+
"grad_norm": 0.589995801448822,
|
1522 |
+
"learning_rate": 4.591836734693877e-06,
|
1523 |
+
"loss": 0.9821,
|
1524 |
+
"step": 213
|
1525 |
+
},
|
1526 |
+
{
|
1527 |
+
"epoch": 3.8990825688073394,
|
1528 |
+
"grad_norm": 0.5095317959785461,
|
1529 |
+
"learning_rate": 3.0612244897959177e-06,
|
1530 |
+
"loss": 0.9985,
|
1531 |
+
"step": 214
|
1532 |
+
},
|
1533 |
+
{
|
1534 |
+
"epoch": 3.9174311926605503,
|
1535 |
+
"grad_norm": 0.6477232575416565,
|
1536 |
+
"learning_rate": 1.5306122448979589e-06,
|
1537 |
+
"loss": 0.9372,
|
1538 |
+
"step": 215
|
1539 |
+
},
|
1540 |
+
{
|
1541 |
+
"epoch": 3.9357798165137616,
|
1542 |
+
"grad_norm": 0.5697444677352905,
|
1543 |
+
"learning_rate": 0.0,
|
1544 |
+
"loss": 1.0124,
|
1545 |
+
"step": 216
|
1546 |
+
},
|
1547 |
+
{
|
1548 |
+
"epoch": 3.9357798165137616,
|
1549 |
+
"eval_loss": 1.7458010911941528,
|
1550 |
+
"eval_runtime": 39.9333,
|
1551 |
+
"eval_samples_per_second": 8.314,
|
1552 |
+
"eval_steps_per_second": 4.157,
|
1553 |
+
"step": 216
|
1554 |
+
}
|
1555 |
+
],
|
1556 |
+
"logging_steps": 1,
|
1557 |
+
"max_steps": 216,
|
1558 |
+
"num_input_tokens_seen": 0,
|
1559 |
+
"num_train_epochs": 4,
|
1560 |
+
"save_steps": 500,
|
1561 |
+
"stateful_callbacks": {
|
1562 |
+
"TrainerControl": {
|
1563 |
+
"args": {
|
1564 |
+
"should_epoch_stop": false,
|
1565 |
+
"should_evaluate": false,
|
1566 |
+
"should_log": false,
|
1567 |
+
"should_save": true,
|
1568 |
+
"should_training_stop": true
|
1569 |
+
},
|
1570 |
+
"attributes": {}
|
1571 |
+
}
|
1572 |
+
},
|
1573 |
+
"total_flos": 1.809327135010898e+17,
|
1574 |
+
"train_batch_size": 8,
|
1575 |
+
"trial_name": null,
|
1576 |
+
"trial_params": null
|
1577 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:791f7ab8e0f3d100b9d62edbaee55f969d72876283112f01c97333a9fad0c7a1
|
3 |
+
size 5816
|