Upload my awesome model
Browse files- README.md +202 -0
- adapter_config.json +34 -0
- adapter_model.safetensors +3 -0
- optimizer.pt +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +17 -0
- tokenizer.json +0 -0
- tokenizer_config.json +2064 -0
- trainer_state.json +1265 -0
- training_args.bin +3 -0
README.md
ADDED
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
base_model: unsloth/llama-3-8b-Instruct-bnb-4bit
|
3 |
+
library_name: peft
|
4 |
+
---
|
5 |
+
|
6 |
+
# Model Card for Model ID
|
7 |
+
|
8 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
9 |
+
|
10 |
+
|
11 |
+
|
12 |
+
## Model Details
|
13 |
+
|
14 |
+
### Model Description
|
15 |
+
|
16 |
+
<!-- Provide a longer summary of what this model is. -->
|
17 |
+
|
18 |
+
|
19 |
+
|
20 |
+
- **Developed by:** [More Information Needed]
|
21 |
+
- **Funded by [optional]:** [More Information Needed]
|
22 |
+
- **Shared by [optional]:** [More Information Needed]
|
23 |
+
- **Model type:** [More Information Needed]
|
24 |
+
- **Language(s) (NLP):** [More Information Needed]
|
25 |
+
- **License:** [More Information Needed]
|
26 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
27 |
+
|
28 |
+
### Model Sources [optional]
|
29 |
+
|
30 |
+
<!-- Provide the basic links for the model. -->
|
31 |
+
|
32 |
+
- **Repository:** [More Information Needed]
|
33 |
+
- **Paper [optional]:** [More Information Needed]
|
34 |
+
- **Demo [optional]:** [More Information Needed]
|
35 |
+
|
36 |
+
## Uses
|
37 |
+
|
38 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
39 |
+
|
40 |
+
### Direct Use
|
41 |
+
|
42 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
43 |
+
|
44 |
+
[More Information Needed]
|
45 |
+
|
46 |
+
### Downstream Use [optional]
|
47 |
+
|
48 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
49 |
+
|
50 |
+
[More Information Needed]
|
51 |
+
|
52 |
+
### Out-of-Scope Use
|
53 |
+
|
54 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
55 |
+
|
56 |
+
[More Information Needed]
|
57 |
+
|
58 |
+
## Bias, Risks, and Limitations
|
59 |
+
|
60 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
61 |
+
|
62 |
+
[More Information Needed]
|
63 |
+
|
64 |
+
### Recommendations
|
65 |
+
|
66 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
67 |
+
|
68 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
69 |
+
|
70 |
+
## How to Get Started with the Model
|
71 |
+
|
72 |
+
Use the code below to get started with the model.
|
73 |
+
|
74 |
+
[More Information Needed]
|
75 |
+
|
76 |
+
## Training Details
|
77 |
+
|
78 |
+
### Training Data
|
79 |
+
|
80 |
+
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
81 |
+
|
82 |
+
[More Information Needed]
|
83 |
+
|
84 |
+
### Training Procedure
|
85 |
+
|
86 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
87 |
+
|
88 |
+
#### Preprocessing [optional]
|
89 |
+
|
90 |
+
[More Information Needed]
|
91 |
+
|
92 |
+
|
93 |
+
#### Training Hyperparameters
|
94 |
+
|
95 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
96 |
+
|
97 |
+
#### Speeds, Sizes, Times [optional]
|
98 |
+
|
99 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
100 |
+
|
101 |
+
[More Information Needed]
|
102 |
+
|
103 |
+
## Evaluation
|
104 |
+
|
105 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
106 |
+
|
107 |
+
### Testing Data, Factors & Metrics
|
108 |
+
|
109 |
+
#### Testing Data
|
110 |
+
|
111 |
+
<!-- This should link to a Dataset Card if possible. -->
|
112 |
+
|
113 |
+
[More Information Needed]
|
114 |
+
|
115 |
+
#### Factors
|
116 |
+
|
117 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
118 |
+
|
119 |
+
[More Information Needed]
|
120 |
+
|
121 |
+
#### Metrics
|
122 |
+
|
123 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
124 |
+
|
125 |
+
[More Information Needed]
|
126 |
+
|
127 |
+
### Results
|
128 |
+
|
129 |
+
[More Information Needed]
|
130 |
+
|
131 |
+
#### Summary
|
132 |
+
|
133 |
+
|
134 |
+
|
135 |
+
## Model Examination [optional]
|
136 |
+
|
137 |
+
<!-- Relevant interpretability work for the model goes here -->
|
138 |
+
|
139 |
+
[More Information Needed]
|
140 |
+
|
141 |
+
## Environmental Impact
|
142 |
+
|
143 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
144 |
+
|
145 |
+
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
146 |
+
|
147 |
+
- **Hardware Type:** [More Information Needed]
|
148 |
+
- **Hours used:** [More Information Needed]
|
149 |
+
- **Cloud Provider:** [More Information Needed]
|
150 |
+
- **Compute Region:** [More Information Needed]
|
151 |
+
- **Carbon Emitted:** [More Information Needed]
|
152 |
+
|
153 |
+
## Technical Specifications [optional]
|
154 |
+
|
155 |
+
### Model Architecture and Objective
|
156 |
+
|
157 |
+
[More Information Needed]
|
158 |
+
|
159 |
+
### Compute Infrastructure
|
160 |
+
|
161 |
+
[More Information Needed]
|
162 |
+
|
163 |
+
#### Hardware
|
164 |
+
|
165 |
+
[More Information Needed]
|
166 |
+
|
167 |
+
#### Software
|
168 |
+
|
169 |
+
[More Information Needed]
|
170 |
+
|
171 |
+
## Citation [optional]
|
172 |
+
|
173 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
174 |
+
|
175 |
+
**BibTeX:**
|
176 |
+
|
177 |
+
[More Information Needed]
|
178 |
+
|
179 |
+
**APA:**
|
180 |
+
|
181 |
+
[More Information Needed]
|
182 |
+
|
183 |
+
## Glossary [optional]
|
184 |
+
|
185 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
186 |
+
|
187 |
+
[More Information Needed]
|
188 |
+
|
189 |
+
## More Information [optional]
|
190 |
+
|
191 |
+
[More Information Needed]
|
192 |
+
|
193 |
+
## Model Card Authors [optional]
|
194 |
+
|
195 |
+
[More Information Needed]
|
196 |
+
|
197 |
+
## Model Card Contact
|
198 |
+
|
199 |
+
[More Information Needed]
|
200 |
+
### Framework versions
|
201 |
+
|
202 |
+
- PEFT 0.11.1
|
adapter_config.json
ADDED
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "unsloth/llama-3-8b-Instruct-bnb-4bit",
|
5 |
+
"bias": "none",
|
6 |
+
"fan_in_fan_out": false,
|
7 |
+
"inference_mode": true,
|
8 |
+
"init_lora_weights": true,
|
9 |
+
"layer_replication": null,
|
10 |
+
"layers_pattern": null,
|
11 |
+
"layers_to_transform": null,
|
12 |
+
"loftq_config": {},
|
13 |
+
"lora_alpha": 128,
|
14 |
+
"lora_dropout": 0.1,
|
15 |
+
"megatron_config": null,
|
16 |
+
"megatron_core": "megatron.core",
|
17 |
+
"modules_to_save": null,
|
18 |
+
"peft_type": "LORA",
|
19 |
+
"r": 64,
|
20 |
+
"rank_pattern": {},
|
21 |
+
"revision": null,
|
22 |
+
"target_modules": [
|
23 |
+
"v_proj",
|
24 |
+
"down_proj",
|
25 |
+
"o_proj",
|
26 |
+
"k_proj",
|
27 |
+
"q_proj",
|
28 |
+
"up_proj",
|
29 |
+
"gate_proj"
|
30 |
+
],
|
31 |
+
"task_type": "CAUSAL_LM",
|
32 |
+
"use_dora": false,
|
33 |
+
"use_rslora": false
|
34 |
+
}
|
adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cc0bd71af8946fe1de23b1485677baca4e80bd57d68e759958d4dc690597f9db
|
3 |
+
size 671149168
|
optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:272ae0d8e3388245f82ee1e3954abd9060ef493c81f735fd481434757bc19e5c
|
3 |
+
size 1342453434
|
rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:eb694f5c0b0f5ec90552b8f96eb0f2361db6b86001f4f9e10684c6d56bb44ca8
|
3 |
+
size 14244
|
scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b42480fcfabc025f115e539461a5c927f7ef6a99c44956674ad4918499131ad8
|
3 |
+
size 1064
|
special_tokens_map.json
ADDED
@@ -0,0 +1,17 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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": "<|eot_id|>"
|
17 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,2064 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"128000": {
|
4 |
+
"content": "<|begin_of_text|>",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false,
|
9 |
+
"special": true
|
10 |
+
},
|
11 |
+
"128001": {
|
12 |
+
"content": "<|end_of_text|>",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"128002": {
|
20 |
+
"content": "<|reserved_special_token_0|>",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
+
"128003": {
|
28 |
+
"content": "<|reserved_special_token_1|>",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
},
|
35 |
+
"128004": {
|
36 |
+
"content": "<|reserved_special_token_2|>",
|
37 |
+
"lstrip": false,
|
38 |
+
"normalized": false,
|
39 |
+
"rstrip": false,
|
40 |
+
"single_word": false,
|
41 |
+
"special": true
|
42 |
+
},
|
43 |
+
"128005": {
|
44 |
+
"content": "<|reserved_special_token_3|>",
|
45 |
+
"lstrip": false,
|
46 |
+
"normalized": false,
|
47 |
+
"rstrip": false,
|
48 |
+
"single_word": false,
|
49 |
+
"special": true
|
50 |
+
},
|
51 |
+
"128006": {
|
52 |
+
"content": "<|start_header_id|>",
|
53 |
+
"lstrip": false,
|
54 |
+
"normalized": false,
|
55 |
+
"rstrip": false,
|
56 |
+
"single_word": false,
|
57 |
+
"special": true
|
58 |
+
},
|
59 |
+
"128007": {
|
60 |
+
"content": "<|end_header_id|>",
|
61 |
+
"lstrip": false,
|
62 |
+
"normalized": false,
|
63 |
+
"rstrip": false,
|
64 |
+
"single_word": false,
|
65 |
+
"special": true
|
66 |
+
},
|
67 |
+
"128008": {
|
68 |
+
"content": "<|reserved_special_token_4|>",
|
69 |
+
"lstrip": false,
|
70 |
+
"normalized": false,
|
71 |
+
"rstrip": false,
|
72 |
+
"single_word": false,
|
73 |
+
"special": true
|
74 |
+
},
|
75 |
+
"128009": {
|
76 |
+
"content": "<|eot_id|>",
|
77 |
+
"lstrip": false,
|
78 |
+
"normalized": false,
|
79 |
+
"rstrip": false,
|
80 |
+
"single_word": false,
|
81 |
+
"special": true
|
82 |
+
},
|
83 |
+
"128010": {
|
84 |
+
"content": "<|reserved_special_token_5|>",
|
85 |
+
"lstrip": false,
|
86 |
+
"normalized": false,
|
87 |
+
"rstrip": false,
|
88 |
+
"single_word": false,
|
89 |
+
"special": true
|
90 |
+
},
|
91 |
+
"128011": {
|
92 |
+
"content": "<|reserved_special_token_6|>",
|
93 |
+
"lstrip": false,
|
94 |
+
"normalized": false,
|
95 |
+
"rstrip": false,
|
96 |
+
"single_word": false,
|
97 |
+
"special": true
|
98 |
+
},
|
99 |
+
"128012": {
|
100 |
+
"content": "<|reserved_special_token_7|>",
|
101 |
+
"lstrip": false,
|
102 |
+
"normalized": false,
|
103 |
+
"rstrip": false,
|
104 |
+
"single_word": false,
|
105 |
+
"special": true
|
106 |
+
},
|
107 |
+
"128013": {
|
108 |
+
"content": "<|reserved_special_token_8|>",
|
109 |
+
"lstrip": false,
|
110 |
+
"normalized": false,
|
111 |
+
"rstrip": false,
|
112 |
+
"single_word": false,
|
113 |
+
"special": true
|
114 |
+
},
|
115 |
+
"128014": {
|
116 |
+
"content": "<|reserved_special_token_9|>",
|
117 |
+
"lstrip": false,
|
118 |
+
"normalized": false,
|
119 |
+
"rstrip": false,
|
120 |
+
"single_word": false,
|
121 |
+
"special": true
|
122 |
+
},
|
123 |
+
"128015": {
|
124 |
+
"content": "<|reserved_special_token_10|>",
|
125 |
+
"lstrip": false,
|
126 |
+
"normalized": false,
|
127 |
+
"rstrip": false,
|
128 |
+
"single_word": false,
|
129 |
+
"special": true
|
130 |
+
},
|
131 |
+
"128016": {
|
132 |
+
"content": "<|reserved_special_token_11|>",
|
133 |
+
"lstrip": false,
|
134 |
+
"normalized": false,
|
135 |
+
"rstrip": false,
|
136 |
+
"single_word": false,
|
137 |
+
"special": true
|
138 |
+
},
|
139 |
+
"128017": {
|
140 |
+
"content": "<|reserved_special_token_12|>",
|
141 |
+
"lstrip": false,
|
142 |
+
"normalized": false,
|
143 |
+
"rstrip": false,
|
144 |
+
"single_word": false,
|
145 |
+
"special": true
|
146 |
+
},
|
147 |
+
"128018": {
|
148 |
+
"content": "<|reserved_special_token_13|>",
|
149 |
+
"lstrip": false,
|
150 |
+
"normalized": false,
|
151 |
+
"rstrip": false,
|
152 |
+
"single_word": false,
|
153 |
+
"special": true
|
154 |
+
},
|
155 |
+
"128019": {
|
156 |
+
"content": "<|reserved_special_token_14|>",
|
157 |
+
"lstrip": false,
|
158 |
+
"normalized": false,
|
159 |
+
"rstrip": false,
|
160 |
+
"single_word": false,
|
161 |
+
"special": true
|
162 |
+
},
|
163 |
+
"128020": {
|
164 |
+
"content": "<|reserved_special_token_15|>",
|
165 |
+
"lstrip": false,
|
166 |
+
"normalized": false,
|
167 |
+
"rstrip": false,
|
168 |
+
"single_word": false,
|
169 |
+
"special": true
|
170 |
+
},
|
171 |
+
"128021": {
|
172 |
+
"content": "<|reserved_special_token_16|>",
|
173 |
+
"lstrip": false,
|
174 |
+
"normalized": false,
|
175 |
+
"rstrip": false,
|
176 |
+
"single_word": false,
|
177 |
+
"special": true
|
178 |
+
},
|
179 |
+
"128022": {
|
180 |
+
"content": "<|reserved_special_token_17|>",
|
181 |
+
"lstrip": false,
|
182 |
+
"normalized": false,
|
183 |
+
"rstrip": false,
|
184 |
+
"single_word": false,
|
185 |
+
"special": true
|
186 |
+
},
|
187 |
+
"128023": {
|
188 |
+
"content": "<|reserved_special_token_18|>",
|
189 |
+
"lstrip": false,
|
190 |
+
"normalized": false,
|
191 |
+
"rstrip": false,
|
192 |
+
"single_word": false,
|
193 |
+
"special": true
|
194 |
+
},
|
195 |
+
"128024": {
|
196 |
+
"content": "<|reserved_special_token_19|>",
|
197 |
+
"lstrip": false,
|
198 |
+
"normalized": false,
|
199 |
+
"rstrip": false,
|
200 |
+
"single_word": false,
|
201 |
+
"special": true
|
202 |
+
},
|
203 |
+
"128025": {
|
204 |
+
"content": "<|reserved_special_token_20|>",
|
205 |
+
"lstrip": false,
|
206 |
+
"normalized": false,
|
207 |
+
"rstrip": false,
|
208 |
+
"single_word": false,
|
209 |
+
"special": true
|
210 |
+
},
|
211 |
+
"128026": {
|
212 |
+
"content": "<|reserved_special_token_21|>",
|
213 |
+
"lstrip": false,
|
214 |
+
"normalized": false,
|
215 |
+
"rstrip": false,
|
216 |
+
"single_word": false,
|
217 |
+
"special": true
|
218 |
+
},
|
219 |
+
"128027": {
|
220 |
+
"content": "<|reserved_special_token_22|>",
|
221 |
+
"lstrip": false,
|
222 |
+
"normalized": false,
|
223 |
+
"rstrip": false,
|
224 |
+
"single_word": false,
|
225 |
+
"special": true
|
226 |
+
},
|
227 |
+
"128028": {
|
228 |
+
"content": "<|reserved_special_token_23|>",
|
229 |
+
"lstrip": false,
|
230 |
+
"normalized": false,
|
231 |
+
"rstrip": false,
|
232 |
+
"single_word": false,
|
233 |
+
"special": true
|
234 |
+
},
|
235 |
+
"128029": {
|
236 |
+
"content": "<|reserved_special_token_24|>",
|
237 |
+
"lstrip": false,
|
238 |
+
"normalized": false,
|
239 |
+
"rstrip": false,
|
240 |
+
"single_word": false,
|
241 |
+
"special": true
|
242 |
+
},
|
243 |
+
"128030": {
|
244 |
+
"content": "<|reserved_special_token_25|>",
|
245 |
+
"lstrip": false,
|
246 |
+
"normalized": false,
|
247 |
+
"rstrip": false,
|
248 |
+
"single_word": false,
|
249 |
+
"special": true
|
250 |
+
},
|
251 |
+
"128031": {
|
252 |
+
"content": "<|reserved_special_token_26|>",
|
253 |
+
"lstrip": false,
|
254 |
+
"normalized": false,
|
255 |
+
"rstrip": false,
|
256 |
+
"single_word": false,
|
257 |
+
"special": true
|
258 |
+
},
|
259 |
+
"128032": {
|
260 |
+
"content": "<|reserved_special_token_27|>",
|
261 |
+
"lstrip": false,
|
262 |
+
"normalized": false,
|
263 |
+
"rstrip": false,
|
264 |
+
"single_word": false,
|
265 |
+
"special": true
|
266 |
+
},
|
267 |
+
"128033": {
|
268 |
+
"content": "<|reserved_special_token_28|>",
|
269 |
+
"lstrip": false,
|
270 |
+
"normalized": false,
|
271 |
+
"rstrip": false,
|
272 |
+
"single_word": false,
|
273 |
+
"special": true
|
274 |
+
},
|
275 |
+
"128034": {
|
276 |
+
"content": "<|reserved_special_token_29|>",
|
277 |
+
"lstrip": false,
|
278 |
+
"normalized": false,
|
279 |
+
"rstrip": false,
|
280 |
+
"single_word": false,
|
281 |
+
"special": true
|
282 |
+
},
|
283 |
+
"128035": {
|
284 |
+
"content": "<|reserved_special_token_30|>",
|
285 |
+
"lstrip": false,
|
286 |
+
"normalized": false,
|
287 |
+
"rstrip": false,
|
288 |
+
"single_word": false,
|
289 |
+
"special": true
|
290 |
+
},
|
291 |
+
"128036": {
|
292 |
+
"content": "<|reserved_special_token_31|>",
|
293 |
+
"lstrip": false,
|
294 |
+
"normalized": false,
|
295 |
+
"rstrip": false,
|
296 |
+
"single_word": false,
|
297 |
+
"special": true
|
298 |
+
},
|
299 |
+
"128037": {
|
300 |
+
"content": "<|reserved_special_token_32|>",
|
301 |
+
"lstrip": false,
|
302 |
+
"normalized": false,
|
303 |
+
"rstrip": false,
|
304 |
+
"single_word": false,
|
305 |
+
"special": true
|
306 |
+
},
|
307 |
+
"128038": {
|
308 |
+
"content": "<|reserved_special_token_33|>",
|
309 |
+
"lstrip": false,
|
310 |
+
"normalized": false,
|
311 |
+
"rstrip": false,
|
312 |
+
"single_word": false,
|
313 |
+
"special": true
|
314 |
+
},
|
315 |
+
"128039": {
|
316 |
+
"content": "<|reserved_special_token_34|>",
|
317 |
+
"lstrip": false,
|
318 |
+
"normalized": false,
|
319 |
+
"rstrip": false,
|
320 |
+
"single_word": false,
|
321 |
+
"special": true
|
322 |
+
},
|
323 |
+
"128040": {
|
324 |
+
"content": "<|reserved_special_token_35|>",
|
325 |
+
"lstrip": false,
|
326 |
+
"normalized": false,
|
327 |
+
"rstrip": false,
|
328 |
+
"single_word": false,
|
329 |
+
"special": true
|
330 |
+
},
|
331 |
+
"128041": {
|
332 |
+
"content": "<|reserved_special_token_36|>",
|
333 |
+
"lstrip": false,
|
334 |
+
"normalized": false,
|
335 |
+
"rstrip": false,
|
336 |
+
"single_word": false,
|
337 |
+
"special": true
|
338 |
+
},
|
339 |
+
"128042": {
|
340 |
+
"content": "<|reserved_special_token_37|>",
|
341 |
+
"lstrip": false,
|
342 |
+
"normalized": false,
|
343 |
+
"rstrip": false,
|
344 |
+
"single_word": false,
|
345 |
+
"special": true
|
346 |
+
},
|
347 |
+
"128043": {
|
348 |
+
"content": "<|reserved_special_token_38|>",
|
349 |
+
"lstrip": false,
|
350 |
+
"normalized": false,
|
351 |
+
"rstrip": false,
|
352 |
+
"single_word": false,
|
353 |
+
"special": true
|
354 |
+
},
|
355 |
+
"128044": {
|
356 |
+
"content": "<|reserved_special_token_39|>",
|
357 |
+
"lstrip": false,
|
358 |
+
"normalized": false,
|
359 |
+
"rstrip": false,
|
360 |
+
"single_word": false,
|
361 |
+
"special": true
|
362 |
+
},
|
363 |
+
"128045": {
|
364 |
+
"content": "<|reserved_special_token_40|>",
|
365 |
+
"lstrip": false,
|
366 |
+
"normalized": false,
|
367 |
+
"rstrip": false,
|
368 |
+
"single_word": false,
|
369 |
+
"special": true
|
370 |
+
},
|
371 |
+
"128046": {
|
372 |
+
"content": "<|reserved_special_token_41|>",
|
373 |
+
"lstrip": false,
|
374 |
+
"normalized": false,
|
375 |
+
"rstrip": false,
|
376 |
+
"single_word": false,
|
377 |
+
"special": true
|
378 |
+
},
|
379 |
+
"128047": {
|
380 |
+
"content": "<|reserved_special_token_42|>",
|
381 |
+
"lstrip": false,
|
382 |
+
"normalized": false,
|
383 |
+
"rstrip": false,
|
384 |
+
"single_word": false,
|
385 |
+
"special": true
|
386 |
+
},
|
387 |
+
"128048": {
|
388 |
+
"content": "<|reserved_special_token_43|>",
|
389 |
+
"lstrip": false,
|
390 |
+
"normalized": false,
|
391 |
+
"rstrip": false,
|
392 |
+
"single_word": false,
|
393 |
+
"special": true
|
394 |
+
},
|
395 |
+
"128049": {
|
396 |
+
"content": "<|reserved_special_token_44|>",
|
397 |
+
"lstrip": false,
|
398 |
+
"normalized": false,
|
399 |
+
"rstrip": false,
|
400 |
+
"single_word": false,
|
401 |
+
"special": true
|
402 |
+
},
|
403 |
+
"128050": {
|
404 |
+
"content": "<|reserved_special_token_45|>",
|
405 |
+
"lstrip": false,
|
406 |
+
"normalized": false,
|
407 |
+
"rstrip": false,
|
408 |
+
"single_word": false,
|
409 |
+
"special": true
|
410 |
+
},
|
411 |
+
"128051": {
|
412 |
+
"content": "<|reserved_special_token_46|>",
|
413 |
+
"lstrip": false,
|
414 |
+
"normalized": false,
|
415 |
+
"rstrip": false,
|
416 |
+
"single_word": false,
|
417 |
+
"special": true
|
418 |
+
},
|
419 |
+
"128052": {
|
420 |
+
"content": "<|reserved_special_token_47|>",
|
421 |
+
"lstrip": false,
|
422 |
+
"normalized": false,
|
423 |
+
"rstrip": false,
|
424 |
+
"single_word": false,
|
425 |
+
"special": true
|
426 |
+
},
|
427 |
+
"128053": {
|
428 |
+
"content": "<|reserved_special_token_48|>",
|
429 |
+
"lstrip": false,
|
430 |
+
"normalized": false,
|
431 |
+
"rstrip": false,
|
432 |
+
"single_word": false,
|
433 |
+
"special": true
|
434 |
+
},
|
435 |
+
"128054": {
|
436 |
+
"content": "<|reserved_special_token_49|>",
|
437 |
+
"lstrip": false,
|
438 |
+
"normalized": false,
|
439 |
+
"rstrip": false,
|
440 |
+
"single_word": false,
|
441 |
+
"special": true
|
442 |
+
},
|
443 |
+
"128055": {
|
444 |
+
"content": "<|reserved_special_token_50|>",
|
445 |
+
"lstrip": false,
|
446 |
+
"normalized": false,
|
447 |
+
"rstrip": false,
|
448 |
+
"single_word": false,
|
449 |
+
"special": true
|
450 |
+
},
|
451 |
+
"128056": {
|
452 |
+
"content": "<|reserved_special_token_51|>",
|
453 |
+
"lstrip": false,
|
454 |
+
"normalized": false,
|
455 |
+
"rstrip": false,
|
456 |
+
"single_word": false,
|
457 |
+
"special": true
|
458 |
+
},
|
459 |
+
"128057": {
|
460 |
+
"content": "<|reserved_special_token_52|>",
|
461 |
+
"lstrip": false,
|
462 |
+
"normalized": false,
|
463 |
+
"rstrip": false,
|
464 |
+
"single_word": false,
|
465 |
+
"special": true
|
466 |
+
},
|
467 |
+
"128058": {
|
468 |
+
"content": "<|reserved_special_token_53|>",
|
469 |
+
"lstrip": false,
|
470 |
+
"normalized": false,
|
471 |
+
"rstrip": false,
|
472 |
+
"single_word": false,
|
473 |
+
"special": true
|
474 |
+
},
|
475 |
+
"128059": {
|
476 |
+
"content": "<|reserved_special_token_54|>",
|
477 |
+
"lstrip": false,
|
478 |
+
"normalized": false,
|
479 |
+
"rstrip": false,
|
480 |
+
"single_word": false,
|
481 |
+
"special": true
|
482 |
+
},
|
483 |
+
"128060": {
|
484 |
+
"content": "<|reserved_special_token_55|>",
|
485 |
+
"lstrip": false,
|
486 |
+
"normalized": false,
|
487 |
+
"rstrip": false,
|
488 |
+
"single_word": false,
|
489 |
+
"special": true
|
490 |
+
},
|
491 |
+
"128061": {
|
492 |
+
"content": "<|reserved_special_token_56|>",
|
493 |
+
"lstrip": false,
|
494 |
+
"normalized": false,
|
495 |
+
"rstrip": false,
|
496 |
+
"single_word": false,
|
497 |
+
"special": true
|
498 |
+
},
|
499 |
+
"128062": {
|
500 |
+
"content": "<|reserved_special_token_57|>",
|
501 |
+
"lstrip": false,
|
502 |
+
"normalized": false,
|
503 |
+
"rstrip": false,
|
504 |
+
"single_word": false,
|
505 |
+
"special": true
|
506 |
+
},
|
507 |
+
"128063": {
|
508 |
+
"content": "<|reserved_special_token_58|>",
|
509 |
+
"lstrip": false,
|
510 |
+
"normalized": false,
|
511 |
+
"rstrip": false,
|
512 |
+
"single_word": false,
|
513 |
+
"special": true
|
514 |
+
},
|
515 |
+
"128064": {
|
516 |
+
"content": "<|reserved_special_token_59|>",
|
517 |
+
"lstrip": false,
|
518 |
+
"normalized": false,
|
519 |
+
"rstrip": false,
|
520 |
+
"single_word": false,
|
521 |
+
"special": true
|
522 |
+
},
|
523 |
+
"128065": {
|
524 |
+
"content": "<|reserved_special_token_60|>",
|
525 |
+
"lstrip": false,
|
526 |
+
"normalized": false,
|
527 |
+
"rstrip": false,
|
528 |
+
"single_word": false,
|
529 |
+
"special": true
|
530 |
+
},
|
531 |
+
"128066": {
|
532 |
+
"content": "<|reserved_special_token_61|>",
|
533 |
+
"lstrip": false,
|
534 |
+
"normalized": false,
|
535 |
+
"rstrip": false,
|
536 |
+
"single_word": false,
|
537 |
+
"special": true
|
538 |
+
},
|
539 |
+
"128067": {
|
540 |
+
"content": "<|reserved_special_token_62|>",
|
541 |
+
"lstrip": false,
|
542 |
+
"normalized": false,
|
543 |
+
"rstrip": false,
|
544 |
+
"single_word": false,
|
545 |
+
"special": true
|
546 |
+
},
|
547 |
+
"128068": {
|
548 |
+
"content": "<|reserved_special_token_63|>",
|
549 |
+
"lstrip": false,
|
550 |
+
"normalized": false,
|
551 |
+
"rstrip": false,
|
552 |
+
"single_word": false,
|
553 |
+
"special": true
|
554 |
+
},
|
555 |
+
"128069": {
|
556 |
+
"content": "<|reserved_special_token_64|>",
|
557 |
+
"lstrip": false,
|
558 |
+
"normalized": false,
|
559 |
+
"rstrip": false,
|
560 |
+
"single_word": false,
|
561 |
+
"special": true
|
562 |
+
},
|
563 |
+
"128070": {
|
564 |
+
"content": "<|reserved_special_token_65|>",
|
565 |
+
"lstrip": false,
|
566 |
+
"normalized": false,
|
567 |
+
"rstrip": false,
|
568 |
+
"single_word": false,
|
569 |
+
"special": true
|
570 |
+
},
|
571 |
+
"128071": {
|
572 |
+
"content": "<|reserved_special_token_66|>",
|
573 |
+
"lstrip": false,
|
574 |
+
"normalized": false,
|
575 |
+
"rstrip": false,
|
576 |
+
"single_word": false,
|
577 |
+
"special": true
|
578 |
+
},
|
579 |
+
"128072": {
|
580 |
+
"content": "<|reserved_special_token_67|>",
|
581 |
+
"lstrip": false,
|
582 |
+
"normalized": false,
|
583 |
+
"rstrip": false,
|
584 |
+
"single_word": false,
|
585 |
+
"special": true
|
586 |
+
},
|
587 |
+
"128073": {
|
588 |
+
"content": "<|reserved_special_token_68|>",
|
589 |
+
"lstrip": false,
|
590 |
+
"normalized": false,
|
591 |
+
"rstrip": false,
|
592 |
+
"single_word": false,
|
593 |
+
"special": true
|
594 |
+
},
|
595 |
+
"128074": {
|
596 |
+
"content": "<|reserved_special_token_69|>",
|
597 |
+
"lstrip": false,
|
598 |
+
"normalized": false,
|
599 |
+
"rstrip": false,
|
600 |
+
"single_word": false,
|
601 |
+
"special": true
|
602 |
+
},
|
603 |
+
"128075": {
|
604 |
+
"content": "<|reserved_special_token_70|>",
|
605 |
+
"lstrip": false,
|
606 |
+
"normalized": false,
|
607 |
+
"rstrip": false,
|
608 |
+
"single_word": false,
|
609 |
+
"special": true
|
610 |
+
},
|
611 |
+
"128076": {
|
612 |
+
"content": "<|reserved_special_token_71|>",
|
613 |
+
"lstrip": false,
|
614 |
+
"normalized": false,
|
615 |
+
"rstrip": false,
|
616 |
+
"single_word": false,
|
617 |
+
"special": true
|
618 |
+
},
|
619 |
+
"128077": {
|
620 |
+
"content": "<|reserved_special_token_72|>",
|
621 |
+
"lstrip": false,
|
622 |
+
"normalized": false,
|
623 |
+
"rstrip": false,
|
624 |
+
"single_word": false,
|
625 |
+
"special": true
|
626 |
+
},
|
627 |
+
"128078": {
|
628 |
+
"content": "<|reserved_special_token_73|>",
|
629 |
+
"lstrip": false,
|
630 |
+
"normalized": false,
|
631 |
+
"rstrip": false,
|
632 |
+
"single_word": false,
|
633 |
+
"special": true
|
634 |
+
},
|
635 |
+
"128079": {
|
636 |
+
"content": "<|reserved_special_token_74|>",
|
637 |
+
"lstrip": false,
|
638 |
+
"normalized": false,
|
639 |
+
"rstrip": false,
|
640 |
+
"single_word": false,
|
641 |
+
"special": true
|
642 |
+
},
|
643 |
+
"128080": {
|
644 |
+
"content": "<|reserved_special_token_75|>",
|
645 |
+
"lstrip": false,
|
646 |
+
"normalized": false,
|
647 |
+
"rstrip": false,
|
648 |
+
"single_word": false,
|
649 |
+
"special": true
|
650 |
+
},
|
651 |
+
"128081": {
|
652 |
+
"content": "<|reserved_special_token_76|>",
|
653 |
+
"lstrip": false,
|
654 |
+
"normalized": false,
|
655 |
+
"rstrip": false,
|
656 |
+
"single_word": false,
|
657 |
+
"special": true
|
658 |
+
},
|
659 |
+
"128082": {
|
660 |
+
"content": "<|reserved_special_token_77|>",
|
661 |
+
"lstrip": false,
|
662 |
+
"normalized": false,
|
663 |
+
"rstrip": false,
|
664 |
+
"single_word": false,
|
665 |
+
"special": true
|
666 |
+
},
|
667 |
+
"128083": {
|
668 |
+
"content": "<|reserved_special_token_78|>",
|
669 |
+
"lstrip": false,
|
670 |
+
"normalized": false,
|
671 |
+
"rstrip": false,
|
672 |
+
"single_word": false,
|
673 |
+
"special": true
|
674 |
+
},
|
675 |
+
"128084": {
|
676 |
+
"content": "<|reserved_special_token_79|>",
|
677 |
+
"lstrip": false,
|
678 |
+
"normalized": false,
|
679 |
+
"rstrip": false,
|
680 |
+
"single_word": false,
|
681 |
+
"special": true
|
682 |
+
},
|
683 |
+
"128085": {
|
684 |
+
"content": "<|reserved_special_token_80|>",
|
685 |
+
"lstrip": false,
|
686 |
+
"normalized": false,
|
687 |
+
"rstrip": false,
|
688 |
+
"single_word": false,
|
689 |
+
"special": true
|
690 |
+
},
|
691 |
+
"128086": {
|
692 |
+
"content": "<|reserved_special_token_81|>",
|
693 |
+
"lstrip": false,
|
694 |
+
"normalized": false,
|
695 |
+
"rstrip": false,
|
696 |
+
"single_word": false,
|
697 |
+
"special": true
|
698 |
+
},
|
699 |
+
"128087": {
|
700 |
+
"content": "<|reserved_special_token_82|>",
|
701 |
+
"lstrip": false,
|
702 |
+
"normalized": false,
|
703 |
+
"rstrip": false,
|
704 |
+
"single_word": false,
|
705 |
+
"special": true
|
706 |
+
},
|
707 |
+
"128088": {
|
708 |
+
"content": "<|reserved_special_token_83|>",
|
709 |
+
"lstrip": false,
|
710 |
+
"normalized": false,
|
711 |
+
"rstrip": false,
|
712 |
+
"single_word": false,
|
713 |
+
"special": true
|
714 |
+
},
|
715 |
+
"128089": {
|
716 |
+
"content": "<|reserved_special_token_84|>",
|
717 |
+
"lstrip": false,
|
718 |
+
"normalized": false,
|
719 |
+
"rstrip": false,
|
720 |
+
"single_word": false,
|
721 |
+
"special": true
|
722 |
+
},
|
723 |
+
"128090": {
|
724 |
+
"content": "<|reserved_special_token_85|>",
|
725 |
+
"lstrip": false,
|
726 |
+
"normalized": false,
|
727 |
+
"rstrip": false,
|
728 |
+
"single_word": false,
|
729 |
+
"special": true
|
730 |
+
},
|
731 |
+
"128091": {
|
732 |
+
"content": "<|reserved_special_token_86|>",
|
733 |
+
"lstrip": false,
|
734 |
+
"normalized": false,
|
735 |
+
"rstrip": false,
|
736 |
+
"single_word": false,
|
737 |
+
"special": true
|
738 |
+
},
|
739 |
+
"128092": {
|
740 |
+
"content": "<|reserved_special_token_87|>",
|
741 |
+
"lstrip": false,
|
742 |
+
"normalized": false,
|
743 |
+
"rstrip": false,
|
744 |
+
"single_word": false,
|
745 |
+
"special": true
|
746 |
+
},
|
747 |
+
"128093": {
|
748 |
+
"content": "<|reserved_special_token_88|>",
|
749 |
+
"lstrip": false,
|
750 |
+
"normalized": false,
|
751 |
+
"rstrip": false,
|
752 |
+
"single_word": false,
|
753 |
+
"special": true
|
754 |
+
},
|
755 |
+
"128094": {
|
756 |
+
"content": "<|reserved_special_token_89|>",
|
757 |
+
"lstrip": false,
|
758 |
+
"normalized": false,
|
759 |
+
"rstrip": false,
|
760 |
+
"single_word": false,
|
761 |
+
"special": true
|
762 |
+
},
|
763 |
+
"128095": {
|
764 |
+
"content": "<|reserved_special_token_90|>",
|
765 |
+
"lstrip": false,
|
766 |
+
"normalized": false,
|
767 |
+
"rstrip": false,
|
768 |
+
"single_word": false,
|
769 |
+
"special": true
|
770 |
+
},
|
771 |
+
"128096": {
|
772 |
+
"content": "<|reserved_special_token_91|>",
|
773 |
+
"lstrip": false,
|
774 |
+
"normalized": false,
|
775 |
+
"rstrip": false,
|
776 |
+
"single_word": false,
|
777 |
+
"special": true
|
778 |
+
},
|
779 |
+
"128097": {
|
780 |
+
"content": "<|reserved_special_token_92|>",
|
781 |
+
"lstrip": false,
|
782 |
+
"normalized": false,
|
783 |
+
"rstrip": false,
|
784 |
+
"single_word": false,
|
785 |
+
"special": true
|
786 |
+
},
|
787 |
+
"128098": {
|
788 |
+
"content": "<|reserved_special_token_93|>",
|
789 |
+
"lstrip": false,
|
790 |
+
"normalized": false,
|
791 |
+
"rstrip": false,
|
792 |
+
"single_word": false,
|
793 |
+
"special": true
|
794 |
+
},
|
795 |
+
"128099": {
|
796 |
+
"content": "<|reserved_special_token_94|>",
|
797 |
+
"lstrip": false,
|
798 |
+
"normalized": false,
|
799 |
+
"rstrip": false,
|
800 |
+
"single_word": false,
|
801 |
+
"special": true
|
802 |
+
},
|
803 |
+
"128100": {
|
804 |
+
"content": "<|reserved_special_token_95|>",
|
805 |
+
"lstrip": false,
|
806 |
+
"normalized": false,
|
807 |
+
"rstrip": false,
|
808 |
+
"single_word": false,
|
809 |
+
"special": true
|
810 |
+
},
|
811 |
+
"128101": {
|
812 |
+
"content": "<|reserved_special_token_96|>",
|
813 |
+
"lstrip": false,
|
814 |
+
"normalized": false,
|
815 |
+
"rstrip": false,
|
816 |
+
"single_word": false,
|
817 |
+
"special": true
|
818 |
+
},
|
819 |
+
"128102": {
|
820 |
+
"content": "<|reserved_special_token_97|>",
|
821 |
+
"lstrip": false,
|
822 |
+
"normalized": false,
|
823 |
+
"rstrip": false,
|
824 |
+
"single_word": false,
|
825 |
+
"special": true
|
826 |
+
},
|
827 |
+
"128103": {
|
828 |
+
"content": "<|reserved_special_token_98|>",
|
829 |
+
"lstrip": false,
|
830 |
+
"normalized": false,
|
831 |
+
"rstrip": false,
|
832 |
+
"single_word": false,
|
833 |
+
"special": true
|
834 |
+
},
|
835 |
+
"128104": {
|
836 |
+
"content": "<|reserved_special_token_99|>",
|
837 |
+
"lstrip": false,
|
838 |
+
"normalized": false,
|
839 |
+
"rstrip": false,
|
840 |
+
"single_word": false,
|
841 |
+
"special": true
|
842 |
+
},
|
843 |
+
"128105": {
|
844 |
+
"content": "<|reserved_special_token_100|>",
|
845 |
+
"lstrip": false,
|
846 |
+
"normalized": false,
|
847 |
+
"rstrip": false,
|
848 |
+
"single_word": false,
|
849 |
+
"special": true
|
850 |
+
},
|
851 |
+
"128106": {
|
852 |
+
"content": "<|reserved_special_token_101|>",
|
853 |
+
"lstrip": false,
|
854 |
+
"normalized": false,
|
855 |
+
"rstrip": false,
|
856 |
+
"single_word": false,
|
857 |
+
"special": true
|
858 |
+
},
|
859 |
+
"128107": {
|
860 |
+
"content": "<|reserved_special_token_102|>",
|
861 |
+
"lstrip": false,
|
862 |
+
"normalized": false,
|
863 |
+
"rstrip": false,
|
864 |
+
"single_word": false,
|
865 |
+
"special": true
|
866 |
+
},
|
867 |
+
"128108": {
|
868 |
+
"content": "<|reserved_special_token_103|>",
|
869 |
+
"lstrip": false,
|
870 |
+
"normalized": false,
|
871 |
+
"rstrip": false,
|
872 |
+
"single_word": false,
|
873 |
+
"special": true
|
874 |
+
},
|
875 |
+
"128109": {
|
876 |
+
"content": "<|reserved_special_token_104|>",
|
877 |
+
"lstrip": false,
|
878 |
+
"normalized": false,
|
879 |
+
"rstrip": false,
|
880 |
+
"single_word": false,
|
881 |
+
"special": true
|
882 |
+
},
|
883 |
+
"128110": {
|
884 |
+
"content": "<|reserved_special_token_105|>",
|
885 |
+
"lstrip": false,
|
886 |
+
"normalized": false,
|
887 |
+
"rstrip": false,
|
888 |
+
"single_word": false,
|
889 |
+
"special": true
|
890 |
+
},
|
891 |
+
"128111": {
|
892 |
+
"content": "<|reserved_special_token_106|>",
|
893 |
+
"lstrip": false,
|
894 |
+
"normalized": false,
|
895 |
+
"rstrip": false,
|
896 |
+
"single_word": false,
|
897 |
+
"special": true
|
898 |
+
},
|
899 |
+
"128112": {
|
900 |
+
"content": "<|reserved_special_token_107|>",
|
901 |
+
"lstrip": false,
|
902 |
+
"normalized": false,
|
903 |
+
"rstrip": false,
|
904 |
+
"single_word": false,
|
905 |
+
"special": true
|
906 |
+
},
|
907 |
+
"128113": {
|
908 |
+
"content": "<|reserved_special_token_108|>",
|
909 |
+
"lstrip": false,
|
910 |
+
"normalized": false,
|
911 |
+
"rstrip": false,
|
912 |
+
"single_word": false,
|
913 |
+
"special": true
|
914 |
+
},
|
915 |
+
"128114": {
|
916 |
+
"content": "<|reserved_special_token_109|>",
|
917 |
+
"lstrip": false,
|
918 |
+
"normalized": false,
|
919 |
+
"rstrip": false,
|
920 |
+
"single_word": false,
|
921 |
+
"special": true
|
922 |
+
},
|
923 |
+
"128115": {
|
924 |
+
"content": "<|reserved_special_token_110|>",
|
925 |
+
"lstrip": false,
|
926 |
+
"normalized": false,
|
927 |
+
"rstrip": false,
|
928 |
+
"single_word": false,
|
929 |
+
"special": true
|
930 |
+
},
|
931 |
+
"128116": {
|
932 |
+
"content": "<|reserved_special_token_111|>",
|
933 |
+
"lstrip": false,
|
934 |
+
"normalized": false,
|
935 |
+
"rstrip": false,
|
936 |
+
"single_word": false,
|
937 |
+
"special": true
|
938 |
+
},
|
939 |
+
"128117": {
|
940 |
+
"content": "<|reserved_special_token_112|>",
|
941 |
+
"lstrip": false,
|
942 |
+
"normalized": false,
|
943 |
+
"rstrip": false,
|
944 |
+
"single_word": false,
|
945 |
+
"special": true
|
946 |
+
},
|
947 |
+
"128118": {
|
948 |
+
"content": "<|reserved_special_token_113|>",
|
949 |
+
"lstrip": false,
|
950 |
+
"normalized": false,
|
951 |
+
"rstrip": false,
|
952 |
+
"single_word": false,
|
953 |
+
"special": true
|
954 |
+
},
|
955 |
+
"128119": {
|
956 |
+
"content": "<|reserved_special_token_114|>",
|
957 |
+
"lstrip": false,
|
958 |
+
"normalized": false,
|
959 |
+
"rstrip": false,
|
960 |
+
"single_word": false,
|
961 |
+
"special": true
|
962 |
+
},
|
963 |
+
"128120": {
|
964 |
+
"content": "<|reserved_special_token_115|>",
|
965 |
+
"lstrip": false,
|
966 |
+
"normalized": false,
|
967 |
+
"rstrip": false,
|
968 |
+
"single_word": false,
|
969 |
+
"special": true
|
970 |
+
},
|
971 |
+
"128121": {
|
972 |
+
"content": "<|reserved_special_token_116|>",
|
973 |
+
"lstrip": false,
|
974 |
+
"normalized": false,
|
975 |
+
"rstrip": false,
|
976 |
+
"single_word": false,
|
977 |
+
"special": true
|
978 |
+
},
|
979 |
+
"128122": {
|
980 |
+
"content": "<|reserved_special_token_117|>",
|
981 |
+
"lstrip": false,
|
982 |
+
"normalized": false,
|
983 |
+
"rstrip": false,
|
984 |
+
"single_word": false,
|
985 |
+
"special": true
|
986 |
+
},
|
987 |
+
"128123": {
|
988 |
+
"content": "<|reserved_special_token_118|>",
|
989 |
+
"lstrip": false,
|
990 |
+
"normalized": false,
|
991 |
+
"rstrip": false,
|
992 |
+
"single_word": false,
|
993 |
+
"special": true
|
994 |
+
},
|
995 |
+
"128124": {
|
996 |
+
"content": "<|reserved_special_token_119|>",
|
997 |
+
"lstrip": false,
|
998 |
+
"normalized": false,
|
999 |
+
"rstrip": false,
|
1000 |
+
"single_word": false,
|
1001 |
+
"special": true
|
1002 |
+
},
|
1003 |
+
"128125": {
|
1004 |
+
"content": "<|reserved_special_token_120|>",
|
1005 |
+
"lstrip": false,
|
1006 |
+
"normalized": false,
|
1007 |
+
"rstrip": false,
|
1008 |
+
"single_word": false,
|
1009 |
+
"special": true
|
1010 |
+
},
|
1011 |
+
"128126": {
|
1012 |
+
"content": "<|reserved_special_token_121|>",
|
1013 |
+
"lstrip": false,
|
1014 |
+
"normalized": false,
|
1015 |
+
"rstrip": false,
|
1016 |
+
"single_word": false,
|
1017 |
+
"special": true
|
1018 |
+
},
|
1019 |
+
"128127": {
|
1020 |
+
"content": "<|reserved_special_token_122|>",
|
1021 |
+
"lstrip": false,
|
1022 |
+
"normalized": false,
|
1023 |
+
"rstrip": false,
|
1024 |
+
"single_word": false,
|
1025 |
+
"special": true
|
1026 |
+
},
|
1027 |
+
"128128": {
|
1028 |
+
"content": "<|reserved_special_token_123|>",
|
1029 |
+
"lstrip": false,
|
1030 |
+
"normalized": false,
|
1031 |
+
"rstrip": false,
|
1032 |
+
"single_word": false,
|
1033 |
+
"special": true
|
1034 |
+
},
|
1035 |
+
"128129": {
|
1036 |
+
"content": "<|reserved_special_token_124|>",
|
1037 |
+
"lstrip": false,
|
1038 |
+
"normalized": false,
|
1039 |
+
"rstrip": false,
|
1040 |
+
"single_word": false,
|
1041 |
+
"special": true
|
1042 |
+
},
|
1043 |
+
"128130": {
|
1044 |
+
"content": "<|reserved_special_token_125|>",
|
1045 |
+
"lstrip": false,
|
1046 |
+
"normalized": false,
|
1047 |
+
"rstrip": false,
|
1048 |
+
"single_word": false,
|
1049 |
+
"special": true
|
1050 |
+
},
|
1051 |
+
"128131": {
|
1052 |
+
"content": "<|reserved_special_token_126|>",
|
1053 |
+
"lstrip": false,
|
1054 |
+
"normalized": false,
|
1055 |
+
"rstrip": false,
|
1056 |
+
"single_word": false,
|
1057 |
+
"special": true
|
1058 |
+
},
|
1059 |
+
"128132": {
|
1060 |
+
"content": "<|reserved_special_token_127|>",
|
1061 |
+
"lstrip": false,
|
1062 |
+
"normalized": false,
|
1063 |
+
"rstrip": false,
|
1064 |
+
"single_word": false,
|
1065 |
+
"special": true
|
1066 |
+
},
|
1067 |
+
"128133": {
|
1068 |
+
"content": "<|reserved_special_token_128|>",
|
1069 |
+
"lstrip": false,
|
1070 |
+
"normalized": false,
|
1071 |
+
"rstrip": false,
|
1072 |
+
"single_word": false,
|
1073 |
+
"special": true
|
1074 |
+
},
|
1075 |
+
"128134": {
|
1076 |
+
"content": "<|reserved_special_token_129|>",
|
1077 |
+
"lstrip": false,
|
1078 |
+
"normalized": false,
|
1079 |
+
"rstrip": false,
|
1080 |
+
"single_word": false,
|
1081 |
+
"special": true
|
1082 |
+
},
|
1083 |
+
"128135": {
|
1084 |
+
"content": "<|reserved_special_token_130|>",
|
1085 |
+
"lstrip": false,
|
1086 |
+
"normalized": false,
|
1087 |
+
"rstrip": false,
|
1088 |
+
"single_word": false,
|
1089 |
+
"special": true
|
1090 |
+
},
|
1091 |
+
"128136": {
|
1092 |
+
"content": "<|reserved_special_token_131|>",
|
1093 |
+
"lstrip": false,
|
1094 |
+
"normalized": false,
|
1095 |
+
"rstrip": false,
|
1096 |
+
"single_word": false,
|
1097 |
+
"special": true
|
1098 |
+
},
|
1099 |
+
"128137": {
|
1100 |
+
"content": "<|reserved_special_token_132|>",
|
1101 |
+
"lstrip": false,
|
1102 |
+
"normalized": false,
|
1103 |
+
"rstrip": false,
|
1104 |
+
"single_word": false,
|
1105 |
+
"special": true
|
1106 |
+
},
|
1107 |
+
"128138": {
|
1108 |
+
"content": "<|reserved_special_token_133|>",
|
1109 |
+
"lstrip": false,
|
1110 |
+
"normalized": false,
|
1111 |
+
"rstrip": false,
|
1112 |
+
"single_word": false,
|
1113 |
+
"special": true
|
1114 |
+
},
|
1115 |
+
"128139": {
|
1116 |
+
"content": "<|reserved_special_token_134|>",
|
1117 |
+
"lstrip": false,
|
1118 |
+
"normalized": false,
|
1119 |
+
"rstrip": false,
|
1120 |
+
"single_word": false,
|
1121 |
+
"special": true
|
1122 |
+
},
|
1123 |
+
"128140": {
|
1124 |
+
"content": "<|reserved_special_token_135|>",
|
1125 |
+
"lstrip": false,
|
1126 |
+
"normalized": false,
|
1127 |
+
"rstrip": false,
|
1128 |
+
"single_word": false,
|
1129 |
+
"special": true
|
1130 |
+
},
|
1131 |
+
"128141": {
|
1132 |
+
"content": "<|reserved_special_token_136|>",
|
1133 |
+
"lstrip": false,
|
1134 |
+
"normalized": false,
|
1135 |
+
"rstrip": false,
|
1136 |
+
"single_word": false,
|
1137 |
+
"special": true
|
1138 |
+
},
|
1139 |
+
"128142": {
|
1140 |
+
"content": "<|reserved_special_token_137|>",
|
1141 |
+
"lstrip": false,
|
1142 |
+
"normalized": false,
|
1143 |
+
"rstrip": false,
|
1144 |
+
"single_word": false,
|
1145 |
+
"special": true
|
1146 |
+
},
|
1147 |
+
"128143": {
|
1148 |
+
"content": "<|reserved_special_token_138|>",
|
1149 |
+
"lstrip": false,
|
1150 |
+
"normalized": false,
|
1151 |
+
"rstrip": false,
|
1152 |
+
"single_word": false,
|
1153 |
+
"special": true
|
1154 |
+
},
|
1155 |
+
"128144": {
|
1156 |
+
"content": "<|reserved_special_token_139|>",
|
1157 |
+
"lstrip": false,
|
1158 |
+
"normalized": false,
|
1159 |
+
"rstrip": false,
|
1160 |
+
"single_word": false,
|
1161 |
+
"special": true
|
1162 |
+
},
|
1163 |
+
"128145": {
|
1164 |
+
"content": "<|reserved_special_token_140|>",
|
1165 |
+
"lstrip": false,
|
1166 |
+
"normalized": false,
|
1167 |
+
"rstrip": false,
|
1168 |
+
"single_word": false,
|
1169 |
+
"special": true
|
1170 |
+
},
|
1171 |
+
"128146": {
|
1172 |
+
"content": "<|reserved_special_token_141|>",
|
1173 |
+
"lstrip": false,
|
1174 |
+
"normalized": false,
|
1175 |
+
"rstrip": false,
|
1176 |
+
"single_word": false,
|
1177 |
+
"special": true
|
1178 |
+
},
|
1179 |
+
"128147": {
|
1180 |
+
"content": "<|reserved_special_token_142|>",
|
1181 |
+
"lstrip": false,
|
1182 |
+
"normalized": false,
|
1183 |
+
"rstrip": false,
|
1184 |
+
"single_word": false,
|
1185 |
+
"special": true
|
1186 |
+
},
|
1187 |
+
"128148": {
|
1188 |
+
"content": "<|reserved_special_token_143|>",
|
1189 |
+
"lstrip": false,
|
1190 |
+
"normalized": false,
|
1191 |
+
"rstrip": false,
|
1192 |
+
"single_word": false,
|
1193 |
+
"special": true
|
1194 |
+
},
|
1195 |
+
"128149": {
|
1196 |
+
"content": "<|reserved_special_token_144|>",
|
1197 |
+
"lstrip": false,
|
1198 |
+
"normalized": false,
|
1199 |
+
"rstrip": false,
|
1200 |
+
"single_word": false,
|
1201 |
+
"special": true
|
1202 |
+
},
|
1203 |
+
"128150": {
|
1204 |
+
"content": "<|reserved_special_token_145|>",
|
1205 |
+
"lstrip": false,
|
1206 |
+
"normalized": false,
|
1207 |
+
"rstrip": false,
|
1208 |
+
"single_word": false,
|
1209 |
+
"special": true
|
1210 |
+
},
|
1211 |
+
"128151": {
|
1212 |
+
"content": "<|reserved_special_token_146|>",
|
1213 |
+
"lstrip": false,
|
1214 |
+
"normalized": false,
|
1215 |
+
"rstrip": false,
|
1216 |
+
"single_word": false,
|
1217 |
+
"special": true
|
1218 |
+
},
|
1219 |
+
"128152": {
|
1220 |
+
"content": "<|reserved_special_token_147|>",
|
1221 |
+
"lstrip": false,
|
1222 |
+
"normalized": false,
|
1223 |
+
"rstrip": false,
|
1224 |
+
"single_word": false,
|
1225 |
+
"special": true
|
1226 |
+
},
|
1227 |
+
"128153": {
|
1228 |
+
"content": "<|reserved_special_token_148|>",
|
1229 |
+
"lstrip": false,
|
1230 |
+
"normalized": false,
|
1231 |
+
"rstrip": false,
|
1232 |
+
"single_word": false,
|
1233 |
+
"special": true
|
1234 |
+
},
|
1235 |
+
"128154": {
|
1236 |
+
"content": "<|reserved_special_token_149|>",
|
1237 |
+
"lstrip": false,
|
1238 |
+
"normalized": false,
|
1239 |
+
"rstrip": false,
|
1240 |
+
"single_word": false,
|
1241 |
+
"special": true
|
1242 |
+
},
|
1243 |
+
"128155": {
|
1244 |
+
"content": "<|reserved_special_token_150|>",
|
1245 |
+
"lstrip": false,
|
1246 |
+
"normalized": false,
|
1247 |
+
"rstrip": false,
|
1248 |
+
"single_word": false,
|
1249 |
+
"special": true
|
1250 |
+
},
|
1251 |
+
"128156": {
|
1252 |
+
"content": "<|reserved_special_token_151|>",
|
1253 |
+
"lstrip": false,
|
1254 |
+
"normalized": false,
|
1255 |
+
"rstrip": false,
|
1256 |
+
"single_word": false,
|
1257 |
+
"special": true
|
1258 |
+
},
|
1259 |
+
"128157": {
|
1260 |
+
"content": "<|reserved_special_token_152|>",
|
1261 |
+
"lstrip": false,
|
1262 |
+
"normalized": false,
|
1263 |
+
"rstrip": false,
|
1264 |
+
"single_word": false,
|
1265 |
+
"special": true
|
1266 |
+
},
|
1267 |
+
"128158": {
|
1268 |
+
"content": "<|reserved_special_token_153|>",
|
1269 |
+
"lstrip": false,
|
1270 |
+
"normalized": false,
|
1271 |
+
"rstrip": false,
|
1272 |
+
"single_word": false,
|
1273 |
+
"special": true
|
1274 |
+
},
|
1275 |
+
"128159": {
|
1276 |
+
"content": "<|reserved_special_token_154|>",
|
1277 |
+
"lstrip": false,
|
1278 |
+
"normalized": false,
|
1279 |
+
"rstrip": false,
|
1280 |
+
"single_word": false,
|
1281 |
+
"special": true
|
1282 |
+
},
|
1283 |
+
"128160": {
|
1284 |
+
"content": "<|reserved_special_token_155|>",
|
1285 |
+
"lstrip": false,
|
1286 |
+
"normalized": false,
|
1287 |
+
"rstrip": false,
|
1288 |
+
"single_word": false,
|
1289 |
+
"special": true
|
1290 |
+
},
|
1291 |
+
"128161": {
|
1292 |
+
"content": "<|reserved_special_token_156|>",
|
1293 |
+
"lstrip": false,
|
1294 |
+
"normalized": false,
|
1295 |
+
"rstrip": false,
|
1296 |
+
"single_word": false,
|
1297 |
+
"special": true
|
1298 |
+
},
|
1299 |
+
"128162": {
|
1300 |
+
"content": "<|reserved_special_token_157|>",
|
1301 |
+
"lstrip": false,
|
1302 |
+
"normalized": false,
|
1303 |
+
"rstrip": false,
|
1304 |
+
"single_word": false,
|
1305 |
+
"special": true
|
1306 |
+
},
|
1307 |
+
"128163": {
|
1308 |
+
"content": "<|reserved_special_token_158|>",
|
1309 |
+
"lstrip": false,
|
1310 |
+
"normalized": false,
|
1311 |
+
"rstrip": false,
|
1312 |
+
"single_word": false,
|
1313 |
+
"special": true
|
1314 |
+
},
|
1315 |
+
"128164": {
|
1316 |
+
"content": "<|reserved_special_token_159|>",
|
1317 |
+
"lstrip": false,
|
1318 |
+
"normalized": false,
|
1319 |
+
"rstrip": false,
|
1320 |
+
"single_word": false,
|
1321 |
+
"special": true
|
1322 |
+
},
|
1323 |
+
"128165": {
|
1324 |
+
"content": "<|reserved_special_token_160|>",
|
1325 |
+
"lstrip": false,
|
1326 |
+
"normalized": false,
|
1327 |
+
"rstrip": false,
|
1328 |
+
"single_word": false,
|
1329 |
+
"special": true
|
1330 |
+
},
|
1331 |
+
"128166": {
|
1332 |
+
"content": "<|reserved_special_token_161|>",
|
1333 |
+
"lstrip": false,
|
1334 |
+
"normalized": false,
|
1335 |
+
"rstrip": false,
|
1336 |
+
"single_word": false,
|
1337 |
+
"special": true
|
1338 |
+
},
|
1339 |
+
"128167": {
|
1340 |
+
"content": "<|reserved_special_token_162|>",
|
1341 |
+
"lstrip": false,
|
1342 |
+
"normalized": false,
|
1343 |
+
"rstrip": false,
|
1344 |
+
"single_word": false,
|
1345 |
+
"special": true
|
1346 |
+
},
|
1347 |
+
"128168": {
|
1348 |
+
"content": "<|reserved_special_token_163|>",
|
1349 |
+
"lstrip": false,
|
1350 |
+
"normalized": false,
|
1351 |
+
"rstrip": false,
|
1352 |
+
"single_word": false,
|
1353 |
+
"special": true
|
1354 |
+
},
|
1355 |
+
"128169": {
|
1356 |
+
"content": "<|reserved_special_token_164|>",
|
1357 |
+
"lstrip": false,
|
1358 |
+
"normalized": false,
|
1359 |
+
"rstrip": false,
|
1360 |
+
"single_word": false,
|
1361 |
+
"special": true
|
1362 |
+
},
|
1363 |
+
"128170": {
|
1364 |
+
"content": "<|reserved_special_token_165|>",
|
1365 |
+
"lstrip": false,
|
1366 |
+
"normalized": false,
|
1367 |
+
"rstrip": false,
|
1368 |
+
"single_word": false,
|
1369 |
+
"special": true
|
1370 |
+
},
|
1371 |
+
"128171": {
|
1372 |
+
"content": "<|reserved_special_token_166|>",
|
1373 |
+
"lstrip": false,
|
1374 |
+
"normalized": false,
|
1375 |
+
"rstrip": false,
|
1376 |
+
"single_word": false,
|
1377 |
+
"special": true
|
1378 |
+
},
|
1379 |
+
"128172": {
|
1380 |
+
"content": "<|reserved_special_token_167|>",
|
1381 |
+
"lstrip": false,
|
1382 |
+
"normalized": false,
|
1383 |
+
"rstrip": false,
|
1384 |
+
"single_word": false,
|
1385 |
+
"special": true
|
1386 |
+
},
|
1387 |
+
"128173": {
|
1388 |
+
"content": "<|reserved_special_token_168|>",
|
1389 |
+
"lstrip": false,
|
1390 |
+
"normalized": false,
|
1391 |
+
"rstrip": false,
|
1392 |
+
"single_word": false,
|
1393 |
+
"special": true
|
1394 |
+
},
|
1395 |
+
"128174": {
|
1396 |
+
"content": "<|reserved_special_token_169|>",
|
1397 |
+
"lstrip": false,
|
1398 |
+
"normalized": false,
|
1399 |
+
"rstrip": false,
|
1400 |
+
"single_word": false,
|
1401 |
+
"special": true
|
1402 |
+
},
|
1403 |
+
"128175": {
|
1404 |
+
"content": "<|reserved_special_token_170|>",
|
1405 |
+
"lstrip": false,
|
1406 |
+
"normalized": false,
|
1407 |
+
"rstrip": false,
|
1408 |
+
"single_word": false,
|
1409 |
+
"special": true
|
1410 |
+
},
|
1411 |
+
"128176": {
|
1412 |
+
"content": "<|reserved_special_token_171|>",
|
1413 |
+
"lstrip": false,
|
1414 |
+
"normalized": false,
|
1415 |
+
"rstrip": false,
|
1416 |
+
"single_word": false,
|
1417 |
+
"special": true
|
1418 |
+
},
|
1419 |
+
"128177": {
|
1420 |
+
"content": "<|reserved_special_token_172|>",
|
1421 |
+
"lstrip": false,
|
1422 |
+
"normalized": false,
|
1423 |
+
"rstrip": false,
|
1424 |
+
"single_word": false,
|
1425 |
+
"special": true
|
1426 |
+
},
|
1427 |
+
"128178": {
|
1428 |
+
"content": "<|reserved_special_token_173|>",
|
1429 |
+
"lstrip": false,
|
1430 |
+
"normalized": false,
|
1431 |
+
"rstrip": false,
|
1432 |
+
"single_word": false,
|
1433 |
+
"special": true
|
1434 |
+
},
|
1435 |
+
"128179": {
|
1436 |
+
"content": "<|reserved_special_token_174|>",
|
1437 |
+
"lstrip": false,
|
1438 |
+
"normalized": false,
|
1439 |
+
"rstrip": false,
|
1440 |
+
"single_word": false,
|
1441 |
+
"special": true
|
1442 |
+
},
|
1443 |
+
"128180": {
|
1444 |
+
"content": "<|reserved_special_token_175|>",
|
1445 |
+
"lstrip": false,
|
1446 |
+
"normalized": false,
|
1447 |
+
"rstrip": false,
|
1448 |
+
"single_word": false,
|
1449 |
+
"special": true
|
1450 |
+
},
|
1451 |
+
"128181": {
|
1452 |
+
"content": "<|reserved_special_token_176|>",
|
1453 |
+
"lstrip": false,
|
1454 |
+
"normalized": false,
|
1455 |
+
"rstrip": false,
|
1456 |
+
"single_word": false,
|
1457 |
+
"special": true
|
1458 |
+
},
|
1459 |
+
"128182": {
|
1460 |
+
"content": "<|reserved_special_token_177|>",
|
1461 |
+
"lstrip": false,
|
1462 |
+
"normalized": false,
|
1463 |
+
"rstrip": false,
|
1464 |
+
"single_word": false,
|
1465 |
+
"special": true
|
1466 |
+
},
|
1467 |
+
"128183": {
|
1468 |
+
"content": "<|reserved_special_token_178|>",
|
1469 |
+
"lstrip": false,
|
1470 |
+
"normalized": false,
|
1471 |
+
"rstrip": false,
|
1472 |
+
"single_word": false,
|
1473 |
+
"special": true
|
1474 |
+
},
|
1475 |
+
"128184": {
|
1476 |
+
"content": "<|reserved_special_token_179|>",
|
1477 |
+
"lstrip": false,
|
1478 |
+
"normalized": false,
|
1479 |
+
"rstrip": false,
|
1480 |
+
"single_word": false,
|
1481 |
+
"special": true
|
1482 |
+
},
|
1483 |
+
"128185": {
|
1484 |
+
"content": "<|reserved_special_token_180|>",
|
1485 |
+
"lstrip": false,
|
1486 |
+
"normalized": false,
|
1487 |
+
"rstrip": false,
|
1488 |
+
"single_word": false,
|
1489 |
+
"special": true
|
1490 |
+
},
|
1491 |
+
"128186": {
|
1492 |
+
"content": "<|reserved_special_token_181|>",
|
1493 |
+
"lstrip": false,
|
1494 |
+
"normalized": false,
|
1495 |
+
"rstrip": false,
|
1496 |
+
"single_word": false,
|
1497 |
+
"special": true
|
1498 |
+
},
|
1499 |
+
"128187": {
|
1500 |
+
"content": "<|reserved_special_token_182|>",
|
1501 |
+
"lstrip": false,
|
1502 |
+
"normalized": false,
|
1503 |
+
"rstrip": false,
|
1504 |
+
"single_word": false,
|
1505 |
+
"special": true
|
1506 |
+
},
|
1507 |
+
"128188": {
|
1508 |
+
"content": "<|reserved_special_token_183|>",
|
1509 |
+
"lstrip": false,
|
1510 |
+
"normalized": false,
|
1511 |
+
"rstrip": false,
|
1512 |
+
"single_word": false,
|
1513 |
+
"special": true
|
1514 |
+
},
|
1515 |
+
"128189": {
|
1516 |
+
"content": "<|reserved_special_token_184|>",
|
1517 |
+
"lstrip": false,
|
1518 |
+
"normalized": false,
|
1519 |
+
"rstrip": false,
|
1520 |
+
"single_word": false,
|
1521 |
+
"special": true
|
1522 |
+
},
|
1523 |
+
"128190": {
|
1524 |
+
"content": "<|reserved_special_token_185|>",
|
1525 |
+
"lstrip": false,
|
1526 |
+
"normalized": false,
|
1527 |
+
"rstrip": false,
|
1528 |
+
"single_word": false,
|
1529 |
+
"special": true
|
1530 |
+
},
|
1531 |
+
"128191": {
|
1532 |
+
"content": "<|reserved_special_token_186|>",
|
1533 |
+
"lstrip": false,
|
1534 |
+
"normalized": false,
|
1535 |
+
"rstrip": false,
|
1536 |
+
"single_word": false,
|
1537 |
+
"special": true
|
1538 |
+
},
|
1539 |
+
"128192": {
|
1540 |
+
"content": "<|reserved_special_token_187|>",
|
1541 |
+
"lstrip": false,
|
1542 |
+
"normalized": false,
|
1543 |
+
"rstrip": false,
|
1544 |
+
"single_word": false,
|
1545 |
+
"special": true
|
1546 |
+
},
|
1547 |
+
"128193": {
|
1548 |
+
"content": "<|reserved_special_token_188|>",
|
1549 |
+
"lstrip": false,
|
1550 |
+
"normalized": false,
|
1551 |
+
"rstrip": false,
|
1552 |
+
"single_word": false,
|
1553 |
+
"special": true
|
1554 |
+
},
|
1555 |
+
"128194": {
|
1556 |
+
"content": "<|reserved_special_token_189|>",
|
1557 |
+
"lstrip": false,
|
1558 |
+
"normalized": false,
|
1559 |
+
"rstrip": false,
|
1560 |
+
"single_word": false,
|
1561 |
+
"special": true
|
1562 |
+
},
|
1563 |
+
"128195": {
|
1564 |
+
"content": "<|reserved_special_token_190|>",
|
1565 |
+
"lstrip": false,
|
1566 |
+
"normalized": false,
|
1567 |
+
"rstrip": false,
|
1568 |
+
"single_word": false,
|
1569 |
+
"special": true
|
1570 |
+
},
|
1571 |
+
"128196": {
|
1572 |
+
"content": "<|reserved_special_token_191|>",
|
1573 |
+
"lstrip": false,
|
1574 |
+
"normalized": false,
|
1575 |
+
"rstrip": false,
|
1576 |
+
"single_word": false,
|
1577 |
+
"special": true
|
1578 |
+
},
|
1579 |
+
"128197": {
|
1580 |
+
"content": "<|reserved_special_token_192|>",
|
1581 |
+
"lstrip": false,
|
1582 |
+
"normalized": false,
|
1583 |
+
"rstrip": false,
|
1584 |
+
"single_word": false,
|
1585 |
+
"special": true
|
1586 |
+
},
|
1587 |
+
"128198": {
|
1588 |
+
"content": "<|reserved_special_token_193|>",
|
1589 |
+
"lstrip": false,
|
1590 |
+
"normalized": false,
|
1591 |
+
"rstrip": false,
|
1592 |
+
"single_word": false,
|
1593 |
+
"special": true
|
1594 |
+
},
|
1595 |
+
"128199": {
|
1596 |
+
"content": "<|reserved_special_token_194|>",
|
1597 |
+
"lstrip": false,
|
1598 |
+
"normalized": false,
|
1599 |
+
"rstrip": false,
|
1600 |
+
"single_word": false,
|
1601 |
+
"special": true
|
1602 |
+
},
|
1603 |
+
"128200": {
|
1604 |
+
"content": "<|reserved_special_token_195|>",
|
1605 |
+
"lstrip": false,
|
1606 |
+
"normalized": false,
|
1607 |
+
"rstrip": false,
|
1608 |
+
"single_word": false,
|
1609 |
+
"special": true
|
1610 |
+
},
|
1611 |
+
"128201": {
|
1612 |
+
"content": "<|reserved_special_token_196|>",
|
1613 |
+
"lstrip": false,
|
1614 |
+
"normalized": false,
|
1615 |
+
"rstrip": false,
|
1616 |
+
"single_word": false,
|
1617 |
+
"special": true
|
1618 |
+
},
|
1619 |
+
"128202": {
|
1620 |
+
"content": "<|reserved_special_token_197|>",
|
1621 |
+
"lstrip": false,
|
1622 |
+
"normalized": false,
|
1623 |
+
"rstrip": false,
|
1624 |
+
"single_word": false,
|
1625 |
+
"special": true
|
1626 |
+
},
|
1627 |
+
"128203": {
|
1628 |
+
"content": "<|reserved_special_token_198|>",
|
1629 |
+
"lstrip": false,
|
1630 |
+
"normalized": false,
|
1631 |
+
"rstrip": false,
|
1632 |
+
"single_word": false,
|
1633 |
+
"special": true
|
1634 |
+
},
|
1635 |
+
"128204": {
|
1636 |
+
"content": "<|reserved_special_token_199|>",
|
1637 |
+
"lstrip": false,
|
1638 |
+
"normalized": false,
|
1639 |
+
"rstrip": false,
|
1640 |
+
"single_word": false,
|
1641 |
+
"special": true
|
1642 |
+
},
|
1643 |
+
"128205": {
|
1644 |
+
"content": "<|reserved_special_token_200|>",
|
1645 |
+
"lstrip": false,
|
1646 |
+
"normalized": false,
|
1647 |
+
"rstrip": false,
|
1648 |
+
"single_word": false,
|
1649 |
+
"special": true
|
1650 |
+
},
|
1651 |
+
"128206": {
|
1652 |
+
"content": "<|reserved_special_token_201|>",
|
1653 |
+
"lstrip": false,
|
1654 |
+
"normalized": false,
|
1655 |
+
"rstrip": false,
|
1656 |
+
"single_word": false,
|
1657 |
+
"special": true
|
1658 |
+
},
|
1659 |
+
"128207": {
|
1660 |
+
"content": "<|reserved_special_token_202|>",
|
1661 |
+
"lstrip": false,
|
1662 |
+
"normalized": false,
|
1663 |
+
"rstrip": false,
|
1664 |
+
"single_word": false,
|
1665 |
+
"special": true
|
1666 |
+
},
|
1667 |
+
"128208": {
|
1668 |
+
"content": "<|reserved_special_token_203|>",
|
1669 |
+
"lstrip": false,
|
1670 |
+
"normalized": false,
|
1671 |
+
"rstrip": false,
|
1672 |
+
"single_word": false,
|
1673 |
+
"special": true
|
1674 |
+
},
|
1675 |
+
"128209": {
|
1676 |
+
"content": "<|reserved_special_token_204|>",
|
1677 |
+
"lstrip": false,
|
1678 |
+
"normalized": false,
|
1679 |
+
"rstrip": false,
|
1680 |
+
"single_word": false,
|
1681 |
+
"special": true
|
1682 |
+
},
|
1683 |
+
"128210": {
|
1684 |
+
"content": "<|reserved_special_token_205|>",
|
1685 |
+
"lstrip": false,
|
1686 |
+
"normalized": false,
|
1687 |
+
"rstrip": false,
|
1688 |
+
"single_word": false,
|
1689 |
+
"special": true
|
1690 |
+
},
|
1691 |
+
"128211": {
|
1692 |
+
"content": "<|reserved_special_token_206|>",
|
1693 |
+
"lstrip": false,
|
1694 |
+
"normalized": false,
|
1695 |
+
"rstrip": false,
|
1696 |
+
"single_word": false,
|
1697 |
+
"special": true
|
1698 |
+
},
|
1699 |
+
"128212": {
|
1700 |
+
"content": "<|reserved_special_token_207|>",
|
1701 |
+
"lstrip": false,
|
1702 |
+
"normalized": false,
|
1703 |
+
"rstrip": false,
|
1704 |
+
"single_word": false,
|
1705 |
+
"special": true
|
1706 |
+
},
|
1707 |
+
"128213": {
|
1708 |
+
"content": "<|reserved_special_token_208|>",
|
1709 |
+
"lstrip": false,
|
1710 |
+
"normalized": false,
|
1711 |
+
"rstrip": false,
|
1712 |
+
"single_word": false,
|
1713 |
+
"special": true
|
1714 |
+
},
|
1715 |
+
"128214": {
|
1716 |
+
"content": "<|reserved_special_token_209|>",
|
1717 |
+
"lstrip": false,
|
1718 |
+
"normalized": false,
|
1719 |
+
"rstrip": false,
|
1720 |
+
"single_word": false,
|
1721 |
+
"special": true
|
1722 |
+
},
|
1723 |
+
"128215": {
|
1724 |
+
"content": "<|reserved_special_token_210|>",
|
1725 |
+
"lstrip": false,
|
1726 |
+
"normalized": false,
|
1727 |
+
"rstrip": false,
|
1728 |
+
"single_word": false,
|
1729 |
+
"special": true
|
1730 |
+
},
|
1731 |
+
"128216": {
|
1732 |
+
"content": "<|reserved_special_token_211|>",
|
1733 |
+
"lstrip": false,
|
1734 |
+
"normalized": false,
|
1735 |
+
"rstrip": false,
|
1736 |
+
"single_word": false,
|
1737 |
+
"special": true
|
1738 |
+
},
|
1739 |
+
"128217": {
|
1740 |
+
"content": "<|reserved_special_token_212|>",
|
1741 |
+
"lstrip": false,
|
1742 |
+
"normalized": false,
|
1743 |
+
"rstrip": false,
|
1744 |
+
"single_word": false,
|
1745 |
+
"special": true
|
1746 |
+
},
|
1747 |
+
"128218": {
|
1748 |
+
"content": "<|reserved_special_token_213|>",
|
1749 |
+
"lstrip": false,
|
1750 |
+
"normalized": false,
|
1751 |
+
"rstrip": false,
|
1752 |
+
"single_word": false,
|
1753 |
+
"special": true
|
1754 |
+
},
|
1755 |
+
"128219": {
|
1756 |
+
"content": "<|reserved_special_token_214|>",
|
1757 |
+
"lstrip": false,
|
1758 |
+
"normalized": false,
|
1759 |
+
"rstrip": false,
|
1760 |
+
"single_word": false,
|
1761 |
+
"special": true
|
1762 |
+
},
|
1763 |
+
"128220": {
|
1764 |
+
"content": "<|reserved_special_token_215|>",
|
1765 |
+
"lstrip": false,
|
1766 |
+
"normalized": false,
|
1767 |
+
"rstrip": false,
|
1768 |
+
"single_word": false,
|
1769 |
+
"special": true
|
1770 |
+
},
|
1771 |
+
"128221": {
|
1772 |
+
"content": "<|reserved_special_token_216|>",
|
1773 |
+
"lstrip": false,
|
1774 |
+
"normalized": false,
|
1775 |
+
"rstrip": false,
|
1776 |
+
"single_word": false,
|
1777 |
+
"special": true
|
1778 |
+
},
|
1779 |
+
"128222": {
|
1780 |
+
"content": "<|reserved_special_token_217|>",
|
1781 |
+
"lstrip": false,
|
1782 |
+
"normalized": false,
|
1783 |
+
"rstrip": false,
|
1784 |
+
"single_word": false,
|
1785 |
+
"special": true
|
1786 |
+
},
|
1787 |
+
"128223": {
|
1788 |
+
"content": "<|reserved_special_token_218|>",
|
1789 |
+
"lstrip": false,
|
1790 |
+
"normalized": false,
|
1791 |
+
"rstrip": false,
|
1792 |
+
"single_word": false,
|
1793 |
+
"special": true
|
1794 |
+
},
|
1795 |
+
"128224": {
|
1796 |
+
"content": "<|reserved_special_token_219|>",
|
1797 |
+
"lstrip": false,
|
1798 |
+
"normalized": false,
|
1799 |
+
"rstrip": false,
|
1800 |
+
"single_word": false,
|
1801 |
+
"special": true
|
1802 |
+
},
|
1803 |
+
"128225": {
|
1804 |
+
"content": "<|reserved_special_token_220|>",
|
1805 |
+
"lstrip": false,
|
1806 |
+
"normalized": false,
|
1807 |
+
"rstrip": false,
|
1808 |
+
"single_word": false,
|
1809 |
+
"special": true
|
1810 |
+
},
|
1811 |
+
"128226": {
|
1812 |
+
"content": "<|reserved_special_token_221|>",
|
1813 |
+
"lstrip": false,
|
1814 |
+
"normalized": false,
|
1815 |
+
"rstrip": false,
|
1816 |
+
"single_word": false,
|
1817 |
+
"special": true
|
1818 |
+
},
|
1819 |
+
"128227": {
|
1820 |
+
"content": "<|reserved_special_token_222|>",
|
1821 |
+
"lstrip": false,
|
1822 |
+
"normalized": false,
|
1823 |
+
"rstrip": false,
|
1824 |
+
"single_word": false,
|
1825 |
+
"special": true
|
1826 |
+
},
|
1827 |
+
"128228": {
|
1828 |
+
"content": "<|reserved_special_token_223|>",
|
1829 |
+
"lstrip": false,
|
1830 |
+
"normalized": false,
|
1831 |
+
"rstrip": false,
|
1832 |
+
"single_word": false,
|
1833 |
+
"special": true
|
1834 |
+
},
|
1835 |
+
"128229": {
|
1836 |
+
"content": "<|reserved_special_token_224|>",
|
1837 |
+
"lstrip": false,
|
1838 |
+
"normalized": false,
|
1839 |
+
"rstrip": false,
|
1840 |
+
"single_word": false,
|
1841 |
+
"special": true
|
1842 |
+
},
|
1843 |
+
"128230": {
|
1844 |
+
"content": "<|reserved_special_token_225|>",
|
1845 |
+
"lstrip": false,
|
1846 |
+
"normalized": false,
|
1847 |
+
"rstrip": false,
|
1848 |
+
"single_word": false,
|
1849 |
+
"special": true
|
1850 |
+
},
|
1851 |
+
"128231": {
|
1852 |
+
"content": "<|reserved_special_token_226|>",
|
1853 |
+
"lstrip": false,
|
1854 |
+
"normalized": false,
|
1855 |
+
"rstrip": false,
|
1856 |
+
"single_word": false,
|
1857 |
+
"special": true
|
1858 |
+
},
|
1859 |
+
"128232": {
|
1860 |
+
"content": "<|reserved_special_token_227|>",
|
1861 |
+
"lstrip": false,
|
1862 |
+
"normalized": false,
|
1863 |
+
"rstrip": false,
|
1864 |
+
"single_word": false,
|
1865 |
+
"special": true
|
1866 |
+
},
|
1867 |
+
"128233": {
|
1868 |
+
"content": "<|reserved_special_token_228|>",
|
1869 |
+
"lstrip": false,
|
1870 |
+
"normalized": false,
|
1871 |
+
"rstrip": false,
|
1872 |
+
"single_word": false,
|
1873 |
+
"special": true
|
1874 |
+
},
|
1875 |
+
"128234": {
|
1876 |
+
"content": "<|reserved_special_token_229|>",
|
1877 |
+
"lstrip": false,
|
1878 |
+
"normalized": false,
|
1879 |
+
"rstrip": false,
|
1880 |
+
"single_word": false,
|
1881 |
+
"special": true
|
1882 |
+
},
|
1883 |
+
"128235": {
|
1884 |
+
"content": "<|reserved_special_token_230|>",
|
1885 |
+
"lstrip": false,
|
1886 |
+
"normalized": false,
|
1887 |
+
"rstrip": false,
|
1888 |
+
"single_word": false,
|
1889 |
+
"special": true
|
1890 |
+
},
|
1891 |
+
"128236": {
|
1892 |
+
"content": "<|reserved_special_token_231|>",
|
1893 |
+
"lstrip": false,
|
1894 |
+
"normalized": false,
|
1895 |
+
"rstrip": false,
|
1896 |
+
"single_word": false,
|
1897 |
+
"special": true
|
1898 |
+
},
|
1899 |
+
"128237": {
|
1900 |
+
"content": "<|reserved_special_token_232|>",
|
1901 |
+
"lstrip": false,
|
1902 |
+
"normalized": false,
|
1903 |
+
"rstrip": false,
|
1904 |
+
"single_word": false,
|
1905 |
+
"special": true
|
1906 |
+
},
|
1907 |
+
"128238": {
|
1908 |
+
"content": "<|reserved_special_token_233|>",
|
1909 |
+
"lstrip": false,
|
1910 |
+
"normalized": false,
|
1911 |
+
"rstrip": false,
|
1912 |
+
"single_word": false,
|
1913 |
+
"special": true
|
1914 |
+
},
|
1915 |
+
"128239": {
|
1916 |
+
"content": "<|reserved_special_token_234|>",
|
1917 |
+
"lstrip": false,
|
1918 |
+
"normalized": false,
|
1919 |
+
"rstrip": false,
|
1920 |
+
"single_word": false,
|
1921 |
+
"special": true
|
1922 |
+
},
|
1923 |
+
"128240": {
|
1924 |
+
"content": "<|reserved_special_token_235|>",
|
1925 |
+
"lstrip": false,
|
1926 |
+
"normalized": false,
|
1927 |
+
"rstrip": false,
|
1928 |
+
"single_word": false,
|
1929 |
+
"special": true
|
1930 |
+
},
|
1931 |
+
"128241": {
|
1932 |
+
"content": "<|reserved_special_token_236|>",
|
1933 |
+
"lstrip": false,
|
1934 |
+
"normalized": false,
|
1935 |
+
"rstrip": false,
|
1936 |
+
"single_word": false,
|
1937 |
+
"special": true
|
1938 |
+
},
|
1939 |
+
"128242": {
|
1940 |
+
"content": "<|reserved_special_token_237|>",
|
1941 |
+
"lstrip": false,
|
1942 |
+
"normalized": false,
|
1943 |
+
"rstrip": false,
|
1944 |
+
"single_word": false,
|
1945 |
+
"special": true
|
1946 |
+
},
|
1947 |
+
"128243": {
|
1948 |
+
"content": "<|reserved_special_token_238|>",
|
1949 |
+
"lstrip": false,
|
1950 |
+
"normalized": false,
|
1951 |
+
"rstrip": false,
|
1952 |
+
"single_word": false,
|
1953 |
+
"special": true
|
1954 |
+
},
|
1955 |
+
"128244": {
|
1956 |
+
"content": "<|reserved_special_token_239|>",
|
1957 |
+
"lstrip": false,
|
1958 |
+
"normalized": false,
|
1959 |
+
"rstrip": false,
|
1960 |
+
"single_word": false,
|
1961 |
+
"special": true
|
1962 |
+
},
|
1963 |
+
"128245": {
|
1964 |
+
"content": "<|reserved_special_token_240|>",
|
1965 |
+
"lstrip": false,
|
1966 |
+
"normalized": false,
|
1967 |
+
"rstrip": false,
|
1968 |
+
"single_word": false,
|
1969 |
+
"special": true
|
1970 |
+
},
|
1971 |
+
"128246": {
|
1972 |
+
"content": "<|reserved_special_token_241|>",
|
1973 |
+
"lstrip": false,
|
1974 |
+
"normalized": false,
|
1975 |
+
"rstrip": false,
|
1976 |
+
"single_word": false,
|
1977 |
+
"special": true
|
1978 |
+
},
|
1979 |
+
"128247": {
|
1980 |
+
"content": "<|reserved_special_token_242|>",
|
1981 |
+
"lstrip": false,
|
1982 |
+
"normalized": false,
|
1983 |
+
"rstrip": false,
|
1984 |
+
"single_word": false,
|
1985 |
+
"special": true
|
1986 |
+
},
|
1987 |
+
"128248": {
|
1988 |
+
"content": "<|reserved_special_token_243|>",
|
1989 |
+
"lstrip": false,
|
1990 |
+
"normalized": false,
|
1991 |
+
"rstrip": false,
|
1992 |
+
"single_word": false,
|
1993 |
+
"special": true
|
1994 |
+
},
|
1995 |
+
"128249": {
|
1996 |
+
"content": "<|reserved_special_token_244|>",
|
1997 |
+
"lstrip": false,
|
1998 |
+
"normalized": false,
|
1999 |
+
"rstrip": false,
|
2000 |
+
"single_word": false,
|
2001 |
+
"special": true
|
2002 |
+
},
|
2003 |
+
"128250": {
|
2004 |
+
"content": "<|reserved_special_token_245|>",
|
2005 |
+
"lstrip": false,
|
2006 |
+
"normalized": false,
|
2007 |
+
"rstrip": false,
|
2008 |
+
"single_word": false,
|
2009 |
+
"special": true
|
2010 |
+
},
|
2011 |
+
"128251": {
|
2012 |
+
"content": "<|reserved_special_token_246|>",
|
2013 |
+
"lstrip": false,
|
2014 |
+
"normalized": false,
|
2015 |
+
"rstrip": false,
|
2016 |
+
"single_word": false,
|
2017 |
+
"special": true
|
2018 |
+
},
|
2019 |
+
"128252": {
|
2020 |
+
"content": "<|reserved_special_token_247|>",
|
2021 |
+
"lstrip": false,
|
2022 |
+
"normalized": false,
|
2023 |
+
"rstrip": false,
|
2024 |
+
"single_word": false,
|
2025 |
+
"special": true
|
2026 |
+
},
|
2027 |
+
"128253": {
|
2028 |
+
"content": "<|reserved_special_token_248|>",
|
2029 |
+
"lstrip": false,
|
2030 |
+
"normalized": false,
|
2031 |
+
"rstrip": false,
|
2032 |
+
"single_word": false,
|
2033 |
+
"special": true
|
2034 |
+
},
|
2035 |
+
"128254": {
|
2036 |
+
"content": "<|reserved_special_token_249|>",
|
2037 |
+
"lstrip": false,
|
2038 |
+
"normalized": false,
|
2039 |
+
"rstrip": false,
|
2040 |
+
"single_word": false,
|
2041 |
+
"special": true
|
2042 |
+
},
|
2043 |
+
"128255": {
|
2044 |
+
"content": "<|reserved_special_token_250|>",
|
2045 |
+
"lstrip": false,
|
2046 |
+
"normalized": false,
|
2047 |
+
"rstrip": false,
|
2048 |
+
"single_word": false,
|
2049 |
+
"special": true
|
2050 |
+
}
|
2051 |
+
},
|
2052 |
+
"bos_token": "<|begin_of_text|>",
|
2053 |
+
"chat_template": "{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{% endif %}",
|
2054 |
+
"clean_up_tokenization_spaces": true,
|
2055 |
+
"eos_token": "<|eot_id|>",
|
2056 |
+
"model_input_names": [
|
2057 |
+
"input_ids",
|
2058 |
+
"attention_mask"
|
2059 |
+
],
|
2060 |
+
"model_max_length": 8192,
|
2061 |
+
"pad_token": "<|eot_id|>",
|
2062 |
+
"padding_side": "right",
|
2063 |
+
"tokenizer_class": "PreTrainedTokenizerFast"
|
2064 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,1265 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 14.842105263157894,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 705,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.08421052631578947,
|
13 |
+
"grad_norm": 64.44918823242188,
|
14 |
+
"learning_rate": 1.6666666666666667e-05,
|
15 |
+
"loss": 5.9893,
|
16 |
+
"step": 4
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.16842105263157894,
|
20 |
+
"grad_norm": 1.1460206508636475,
|
21 |
+
"learning_rate": 3.888888888888889e-05,
|
22 |
+
"loss": 1.7662,
|
23 |
+
"step": 8
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.25263157894736843,
|
27 |
+
"grad_norm": 0.8948838710784912,
|
28 |
+
"learning_rate": 6.111111111111112e-05,
|
29 |
+
"loss": 0.8212,
|
30 |
+
"step": 12
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 0.3368421052631579,
|
34 |
+
"grad_norm": 0.5042845606803894,
|
35 |
+
"learning_rate": 8.333333333333334e-05,
|
36 |
+
"loss": 0.533,
|
37 |
+
"step": 16
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 0.42105263157894735,
|
41 |
+
"grad_norm": 0.5063032507896423,
|
42 |
+
"learning_rate": 0.00010555555555555557,
|
43 |
+
"loss": 0.425,
|
44 |
+
"step": 20
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.5052631578947369,
|
48 |
+
"grad_norm": 0.4761255383491516,
|
49 |
+
"learning_rate": 0.00012777777777777776,
|
50 |
+
"loss": 0.3875,
|
51 |
+
"step": 24
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.5894736842105263,
|
55 |
+
"grad_norm": 0.4021145701408386,
|
56 |
+
"learning_rate": 0.00015000000000000001,
|
57 |
+
"loss": 0.3799,
|
58 |
+
"step": 28
|
59 |
+
},
|
60 |
+
{
|
61 |
+
"epoch": 0.6736842105263158,
|
62 |
+
"grad_norm": 0.441383421421051,
|
63 |
+
"learning_rate": 0.00017222222222222224,
|
64 |
+
"loss": 0.3438,
|
65 |
+
"step": 32
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 0.7578947368421053,
|
69 |
+
"grad_norm": 0.3923978805541992,
|
70 |
+
"learning_rate": 0.00019444444444444446,
|
71 |
+
"loss": 0.2952,
|
72 |
+
"step": 36
|
73 |
+
},
|
74 |
+
{
|
75 |
+
"epoch": 0.8421052631578947,
|
76 |
+
"grad_norm": 0.39148256182670593,
|
77 |
+
"learning_rate": 0.00019999007677495127,
|
78 |
+
"loss": 0.2766,
|
79 |
+
"step": 40
|
80 |
+
},
|
81 |
+
{
|
82 |
+
"epoch": 0.9263157894736842,
|
83 |
+
"grad_norm": 0.3753437101840973,
|
84 |
+
"learning_rate": 0.0001999459775237086,
|
85 |
+
"loss": 0.329,
|
86 |
+
"step": 44
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 1.0105263157894737,
|
90 |
+
"grad_norm": 0.49228230118751526,
|
91 |
+
"learning_rate": 0.00019986661520865405,
|
92 |
+
"loss": 0.2808,
|
93 |
+
"step": 48
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 1.0947368421052632,
|
97 |
+
"grad_norm": 0.3359147608280182,
|
98 |
+
"learning_rate": 0.00019975201783049805,
|
99 |
+
"loss": 0.2385,
|
100 |
+
"step": 52
|
101 |
+
},
|
102 |
+
{
|
103 |
+
"epoch": 1.1789473684210527,
|
104 |
+
"grad_norm": 0.33956533670425415,
|
105 |
+
"learning_rate": 0.00019960222582162976,
|
106 |
+
"loss": 0.224,
|
107 |
+
"step": 56
|
108 |
+
},
|
109 |
+
{
|
110 |
+
"epoch": 1.263157894736842,
|
111 |
+
"grad_norm": 0.29228124022483826,
|
112 |
+
"learning_rate": 0.00019941729203185165,
|
113 |
+
"loss": 0.2062,
|
114 |
+
"step": 60
|
115 |
+
},
|
116 |
+
{
|
117 |
+
"epoch": 1.3473684210526315,
|
118 |
+
"grad_norm": 0.3463740944862366,
|
119 |
+
"learning_rate": 0.00019919728170973296,
|
120 |
+
"loss": 0.2335,
|
121 |
+
"step": 64
|
122 |
+
},
|
123 |
+
{
|
124 |
+
"epoch": 1.431578947368421,
|
125 |
+
"grad_norm": 0.30409345030784607,
|
126 |
+
"learning_rate": 0.00019894227247958845,
|
127 |
+
"loss": 0.2242,
|
128 |
+
"step": 68
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 1.5157894736842106,
|
132 |
+
"grad_norm": 0.3040483593940735,
|
133 |
+
"learning_rate": 0.00019865235431409123,
|
134 |
+
"loss": 0.1707,
|
135 |
+
"step": 72
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 1.6,
|
139 |
+
"grad_norm": 0.3167271614074707,
|
140 |
+
"learning_rate": 0.00019832762950252813,
|
141 |
+
"loss": 0.2288,
|
142 |
+
"step": 76
|
143 |
+
},
|
144 |
+
{
|
145 |
+
"epoch": 1.6842105263157894,
|
146 |
+
"grad_norm": 0.4126874804496765,
|
147 |
+
"learning_rate": 0.00019796821261471018,
|
148 |
+
"loss": 0.202,
|
149 |
+
"step": 80
|
150 |
+
},
|
151 |
+
{
|
152 |
+
"epoch": 1.768421052631579,
|
153 |
+
"grad_norm": 0.3122522830963135,
|
154 |
+
"learning_rate": 0.00019757423046054968,
|
155 |
+
"loss": 0.2209,
|
156 |
+
"step": 84
|
157 |
+
},
|
158 |
+
{
|
159 |
+
"epoch": 1.8526315789473684,
|
160 |
+
"grad_norm": 0.348960280418396,
|
161 |
+
"learning_rate": 0.00019714582204531918,
|
162 |
+
"loss": 0.1551,
|
163 |
+
"step": 88
|
164 |
+
},
|
165 |
+
{
|
166 |
+
"epoch": 1.936842105263158,
|
167 |
+
"grad_norm": 0.413482666015625,
|
168 |
+
"learning_rate": 0.00019668313852060735,
|
169 |
+
"loss": 0.1818,
|
170 |
+
"step": 92
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 2.0210526315789474,
|
174 |
+
"grad_norm": 0.2502991259098053,
|
175 |
+
"learning_rate": 0.00019618634313098952,
|
176 |
+
"loss": 0.1355,
|
177 |
+
"step": 96
|
178 |
+
},
|
179 |
+
{
|
180 |
+
"epoch": 2.1052631578947367,
|
181 |
+
"grad_norm": 0.33105117082595825,
|
182 |
+
"learning_rate": 0.00019565561115643152,
|
183 |
+
"loss": 0.1286,
|
184 |
+
"step": 100
|
185 |
+
},
|
186 |
+
{
|
187 |
+
"epoch": 2.1894736842105265,
|
188 |
+
"grad_norm": 0.3156004548072815,
|
189 |
+
"learning_rate": 0.00019509112985044717,
|
190 |
+
"loss": 0.0978,
|
191 |
+
"step": 104
|
192 |
+
},
|
193 |
+
{
|
194 |
+
"epoch": 2.2736842105263158,
|
195 |
+
"grad_norm": 0.39305001497268677,
|
196 |
+
"learning_rate": 0.00019449309837403137,
|
197 |
+
"loss": 0.1227,
|
198 |
+
"step": 108
|
199 |
+
},
|
200 |
+
{
|
201 |
+
"epoch": 2.3578947368421055,
|
202 |
+
"grad_norm": 0.3099610209465027,
|
203 |
+
"learning_rate": 0.00019386172772539162,
|
204 |
+
"loss": 0.1346,
|
205 |
+
"step": 112
|
206 |
+
},
|
207 |
+
{
|
208 |
+
"epoch": 2.442105263157895,
|
209 |
+
"grad_norm": 0.2809341847896576,
|
210 |
+
"learning_rate": 0.00019319724066550373,
|
211 |
+
"loss": 0.1223,
|
212 |
+
"step": 116
|
213 |
+
},
|
214 |
+
{
|
215 |
+
"epoch": 2.526315789473684,
|
216 |
+
"grad_norm": 0.40614527463912964,
|
217 |
+
"learning_rate": 0.00019249987163951667,
|
218 |
+
"loss": 0.1353,
|
219 |
+
"step": 120
|
220 |
+
},
|
221 |
+
{
|
222 |
+
"epoch": 2.610526315789474,
|
223 |
+
"grad_norm": 0.23737777769565582,
|
224 |
+
"learning_rate": 0.00019176986669403555,
|
225 |
+
"loss": 0.112,
|
226 |
+
"step": 124
|
227 |
+
},
|
228 |
+
{
|
229 |
+
"epoch": 2.694736842105263,
|
230 |
+
"grad_norm": 0.2852821350097656,
|
231 |
+
"learning_rate": 0.00019100748339031113,
|
232 |
+
"loss": 0.1349,
|
233 |
+
"step": 128
|
234 |
+
},
|
235 |
+
{
|
236 |
+
"epoch": 2.7789473684210524,
|
237 |
+
"grad_norm": 0.43856674432754517,
|
238 |
+
"learning_rate": 0.00019021299071336664,
|
239 |
+
"loss": 0.1179,
|
240 |
+
"step": 132
|
241 |
+
},
|
242 |
+
{
|
243 |
+
"epoch": 2.863157894736842,
|
244 |
+
"grad_norm": 0.3141747713088989,
|
245 |
+
"learning_rate": 0.00018938666897709425,
|
246 |
+
"loss": 0.1306,
|
247 |
+
"step": 136
|
248 |
+
},
|
249 |
+
{
|
250 |
+
"epoch": 2.9473684210526314,
|
251 |
+
"grad_norm": 0.2711346447467804,
|
252 |
+
"learning_rate": 0.00018852880972535432,
|
253 |
+
"loss": 0.1551,
|
254 |
+
"step": 140
|
255 |
+
},
|
256 |
+
{
|
257 |
+
"epoch": 3.031578947368421,
|
258 |
+
"grad_norm": 0.25603431463241577,
|
259 |
+
"learning_rate": 0.0001876397156291125,
|
260 |
+
"loss": 0.0794,
|
261 |
+
"step": 144
|
262 |
+
},
|
263 |
+
{
|
264 |
+
"epoch": 3.1157894736842104,
|
265 |
+
"grad_norm": 0.42339861392974854,
|
266 |
+
"learning_rate": 0.00018671970037965118,
|
267 |
+
"loss": 0.0744,
|
268 |
+
"step": 148
|
269 |
+
},
|
270 |
+
{
|
271 |
+
"epoch": 3.2,
|
272 |
+
"grad_norm": 0.2693917751312256,
|
273 |
+
"learning_rate": 0.0001857690885778923,
|
274 |
+
"loss": 0.0696,
|
275 |
+
"step": 152
|
276 |
+
},
|
277 |
+
{
|
278 |
+
"epoch": 3.2842105263157895,
|
279 |
+
"grad_norm": 0.2737679183483124,
|
280 |
+
"learning_rate": 0.0001847882156198713,
|
281 |
+
"loss": 0.0653,
|
282 |
+
"step": 156
|
283 |
+
},
|
284 |
+
{
|
285 |
+
"epoch": 3.3684210526315788,
|
286 |
+
"grad_norm": 0.4129018187522888,
|
287 |
+
"learning_rate": 0.00018377742757840244,
|
288 |
+
"loss": 0.0806,
|
289 |
+
"step": 160
|
290 |
+
},
|
291 |
+
{
|
292 |
+
"epoch": 3.4526315789473685,
|
293 |
+
"grad_norm": 0.3873012065887451,
|
294 |
+
"learning_rate": 0.00018273708108097677,
|
295 |
+
"loss": 0.0752,
|
296 |
+
"step": 164
|
297 |
+
},
|
298 |
+
{
|
299 |
+
"epoch": 3.536842105263158,
|
300 |
+
"grad_norm": 0.3241969645023346,
|
301 |
+
"learning_rate": 0.0001816675431839365,
|
302 |
+
"loss": 0.0772,
|
303 |
+
"step": 168
|
304 |
+
},
|
305 |
+
{
|
306 |
+
"epoch": 3.6210526315789475,
|
307 |
+
"grad_norm": 0.3158609867095947,
|
308 |
+
"learning_rate": 0.0001805691912429696,
|
309 |
+
"loss": 0.0802,
|
310 |
+
"step": 172
|
311 |
+
},
|
312 |
+
{
|
313 |
+
"epoch": 3.705263157894737,
|
314 |
+
"grad_norm": 0.3270516097545624,
|
315 |
+
"learning_rate": 0.00017944241277997077,
|
316 |
+
"loss": 0.0712,
|
317 |
+
"step": 176
|
318 |
+
},
|
319 |
+
{
|
320 |
+
"epoch": 3.7894736842105265,
|
321 |
+
"grad_norm": 0.30987676978111267,
|
322 |
+
"learning_rate": 0.00017828760534631565,
|
323 |
+
"loss": 0.0699,
|
324 |
+
"step": 180
|
325 |
+
},
|
326 |
+
{
|
327 |
+
"epoch": 3.873684210526316,
|
328 |
+
"grad_norm": 0.28480827808380127,
|
329 |
+
"learning_rate": 0.0001771051763825959,
|
330 |
+
"loss": 0.0858,
|
331 |
+
"step": 184
|
332 |
+
},
|
333 |
+
{
|
334 |
+
"epoch": 3.957894736842105,
|
335 |
+
"grad_norm": 0.24550119042396545,
|
336 |
+
"learning_rate": 0.0001758955430748658,
|
337 |
+
"loss": 0.0619,
|
338 |
+
"step": 188
|
339 |
+
},
|
340 |
+
{
|
341 |
+
"epoch": 4.042105263157895,
|
342 |
+
"grad_norm": 0.3428252041339874,
|
343 |
+
"learning_rate": 0.00017465913220744998,
|
344 |
+
"loss": 0.0585,
|
345 |
+
"step": 192
|
346 |
+
},
|
347 |
+
{
|
348 |
+
"epoch": 4.126315789473685,
|
349 |
+
"grad_norm": 0.32337552309036255,
|
350 |
+
"learning_rate": 0.00017339638001236492,
|
351 |
+
"loss": 0.0518,
|
352 |
+
"step": 196
|
353 |
+
},
|
354 |
+
{
|
355 |
+
"epoch": 4.2105263157894735,
|
356 |
+
"grad_norm": 0.2767057716846466,
|
357 |
+
"learning_rate": 0.00017210773201540707,
|
358 |
+
"loss": 0.0435,
|
359 |
+
"step": 200
|
360 |
+
},
|
361 |
+
{
|
362 |
+
"epoch": 4.294736842105263,
|
363 |
+
"grad_norm": 0.22791585326194763,
|
364 |
+
"learning_rate": 0.00017079364287896174,
|
365 |
+
"loss": 0.0471,
|
366 |
+
"step": 204
|
367 |
+
},
|
368 |
+
{
|
369 |
+
"epoch": 4.378947368421053,
|
370 |
+
"grad_norm": 0.3095114231109619,
|
371 |
+
"learning_rate": 0.00016945457624158871,
|
372 |
+
"loss": 0.0401,
|
373 |
+
"step": 208
|
374 |
+
},
|
375 |
+
{
|
376 |
+
"epoch": 4.463157894736842,
|
377 |
+
"grad_norm": 0.2641872465610504,
|
378 |
+
"learning_rate": 0.0001680910045544406,
|
379 |
+
"loss": 0.0447,
|
380 |
+
"step": 212
|
381 |
+
},
|
382 |
+
{
|
383 |
+
"epoch": 4.5473684210526315,
|
384 |
+
"grad_norm": 0.3095775842666626,
|
385 |
+
"learning_rate": 0.00016670340891457216,
|
386 |
+
"loss": 0.052,
|
387 |
+
"step": 216
|
388 |
+
},
|
389 |
+
{
|
390 |
+
"epoch": 4.631578947368421,
|
391 |
+
"grad_norm": 0.292422890663147,
|
392 |
+
"learning_rate": 0.00016529227889519886,
|
393 |
+
"loss": 0.0439,
|
394 |
+
"step": 220
|
395 |
+
},
|
396 |
+
{
|
397 |
+
"epoch": 4.715789473684211,
|
398 |
+
"grad_norm": 0.2715825140476227,
|
399 |
+
"learning_rate": 0.0001638581123729652,
|
400 |
+
"loss": 0.039,
|
401 |
+
"step": 224
|
402 |
+
},
|
403 |
+
{
|
404 |
+
"epoch": 4.8,
|
405 |
+
"grad_norm": 0.17827194929122925,
|
406 |
+
"learning_rate": 0.00016240141535228323,
|
407 |
+
"loss": 0.0424,
|
408 |
+
"step": 228
|
409 |
+
},
|
410 |
+
{
|
411 |
+
"epoch": 4.88421052631579,
|
412 |
+
"grad_norm": 0.21712446212768555,
|
413 |
+
"learning_rate": 0.0001609227017868033,
|
414 |
+
"loss": 0.0502,
|
415 |
+
"step": 232
|
416 |
+
},
|
417 |
+
{
|
418 |
+
"epoch": 4.968421052631579,
|
419 |
+
"grad_norm": 0.45244210958480835,
|
420 |
+
"learning_rate": 0.00015942249339808058,
|
421 |
+
"loss": 0.0548,
|
422 |
+
"step": 236
|
423 |
+
},
|
424 |
+
{
|
425 |
+
"epoch": 5.052631578947368,
|
426 |
+
"grad_norm": 0.20093843340873718,
|
427 |
+
"learning_rate": 0.00015790131949150035,
|
428 |
+
"loss": 0.0284,
|
429 |
+
"step": 240
|
430 |
+
},
|
431 |
+
{
|
432 |
+
"epoch": 5.136842105263158,
|
433 |
+
"grad_norm": 0.3055751919746399,
|
434 |
+
"learning_rate": 0.00015635971676952797,
|
435 |
+
"loss": 0.0304,
|
436 |
+
"step": 244
|
437 |
+
},
|
438 |
+
{
|
439 |
+
"epoch": 5.221052631578948,
|
440 |
+
"grad_norm": 0.21160796284675598,
|
441 |
+
"learning_rate": 0.00015479822914234875,
|
442 |
+
"loss": 0.0291,
|
443 |
+
"step": 248
|
444 |
+
},
|
445 |
+
{
|
446 |
+
"epoch": 5.3052631578947365,
|
447 |
+
"grad_norm": 0.19923457503318787,
|
448 |
+
"learning_rate": 0.0001532174075359649,
|
449 |
+
"loss": 0.0291,
|
450 |
+
"step": 252
|
451 |
+
},
|
452 |
+
{
|
453 |
+
"epoch": 5.389473684210526,
|
454 |
+
"grad_norm": 0.21759603917598724,
|
455 |
+
"learning_rate": 0.00015161780969781728,
|
456 |
+
"loss": 0.0322,
|
457 |
+
"step": 256
|
458 |
+
},
|
459 |
+
{
|
460 |
+
"epoch": 5.473684210526316,
|
461 |
+
"grad_norm": 0.1476200670003891,
|
462 |
+
"learning_rate": 0.00015000000000000001,
|
463 |
+
"loss": 0.03,
|
464 |
+
"step": 260
|
465 |
+
},
|
466 |
+
{
|
467 |
+
"epoch": 5.557894736842105,
|
468 |
+
"grad_norm": 0.1323111355304718,
|
469 |
+
"learning_rate": 0.00014836454924013824,
|
470 |
+
"loss": 0.0297,
|
471 |
+
"step": 264
|
472 |
+
},
|
473 |
+
{
|
474 |
+
"epoch": 5.6421052631578945,
|
475 |
+
"grad_norm": 0.1873178780078888,
|
476 |
+
"learning_rate": 0.00014671203443999845,
|
477 |
+
"loss": 0.031,
|
478 |
+
"step": 268
|
479 |
+
},
|
480 |
+
{
|
481 |
+
"epoch": 5.726315789473684,
|
482 |
+
"grad_norm": 0.18353727459907532,
|
483 |
+
"learning_rate": 0.00014504303864190307,
|
484 |
+
"loss": 0.0294,
|
485 |
+
"step": 272
|
486 |
+
},
|
487 |
+
{
|
488 |
+
"epoch": 5.810526315789474,
|
489 |
+
"grad_norm": 0.177791565656662,
|
490 |
+
"learning_rate": 0.00014335815070302054,
|
491 |
+
"loss": 0.0306,
|
492 |
+
"step": 276
|
493 |
+
},
|
494 |
+
{
|
495 |
+
"epoch": 5.894736842105263,
|
496 |
+
"grad_norm": 0.17418071627616882,
|
497 |
+
"learning_rate": 0.0001416579650876043,
|
498 |
+
"loss": 0.0307,
|
499 |
+
"step": 280
|
500 |
+
},
|
501 |
+
{
|
502 |
+
"epoch": 5.978947368421053,
|
503 |
+
"grad_norm": 0.20067432522773743,
|
504 |
+
"learning_rate": 0.00013994308165725288,
|
505 |
+
"loss": 0.0305,
|
506 |
+
"step": 284
|
507 |
+
},
|
508 |
+
{
|
509 |
+
"epoch": 6.063157894736842,
|
510 |
+
"grad_norm": 0.1422828584909439,
|
511 |
+
"learning_rate": 0.00013821410545926613,
|
512 |
+
"loss": 0.0297,
|
513 |
+
"step": 288
|
514 |
+
},
|
515 |
+
{
|
516 |
+
"epoch": 6.147368421052631,
|
517 |
+
"grad_norm": 0.16031205654144287,
|
518 |
+
"learning_rate": 0.00013647164651317176,
|
519 |
+
"loss": 0.0233,
|
520 |
+
"step": 292
|
521 |
+
},
|
522 |
+
{
|
523 |
+
"epoch": 6.231578947368421,
|
524 |
+
"grad_norm": 0.14059369266033173,
|
525 |
+
"learning_rate": 0.0001347163195954973,
|
526 |
+
"loss": 0.0216,
|
527 |
+
"step": 296
|
528 |
+
},
|
529 |
+
{
|
530 |
+
"epoch": 6.315789473684211,
|
531 |
+
"grad_norm": 0.15955083072185516,
|
532 |
+
"learning_rate": 0.00013294874402286402,
|
533 |
+
"loss": 0.023,
|
534 |
+
"step": 300
|
535 |
+
},
|
536 |
+
{
|
537 |
+
"epoch": 6.4,
|
538 |
+
"grad_norm": 0.0965215414762497,
|
539 |
+
"learning_rate": 0.00013116954343347882,
|
540 |
+
"loss": 0.0227,
|
541 |
+
"step": 304
|
542 |
+
},
|
543 |
+
{
|
544 |
+
"epoch": 6.484210526315789,
|
545 |
+
"grad_norm": 0.11703325808048248,
|
546 |
+
"learning_rate": 0.00012937934556710143,
|
547 |
+
"loss": 0.0237,
|
548 |
+
"step": 308
|
549 |
+
},
|
550 |
+
{
|
551 |
+
"epoch": 6.568421052631579,
|
552 |
+
"grad_norm": 0.13229094445705414,
|
553 |
+
"learning_rate": 0.0001275787820435645,
|
554 |
+
"loss": 0.0233,
|
555 |
+
"step": 312
|
556 |
+
},
|
557 |
+
{
|
558 |
+
"epoch": 6.652631578947369,
|
559 |
+
"grad_norm": 0.15599046647548676,
|
560 |
+
"learning_rate": 0.00012576848813992475,
|
561 |
+
"loss": 0.024,
|
562 |
+
"step": 316
|
563 |
+
},
|
564 |
+
{
|
565 |
+
"epoch": 6.7368421052631575,
|
566 |
+
"grad_norm": 0.14043009281158447,
|
567 |
+
"learning_rate": 0.00012394910256632356,
|
568 |
+
"loss": 0.0222,
|
569 |
+
"step": 320
|
570 |
+
},
|
571 |
+
{
|
572 |
+
"epoch": 6.821052631578947,
|
573 |
+
"grad_norm": 0.10719907283782959,
|
574 |
+
"learning_rate": 0.00012212126724063676,
|
575 |
+
"loss": 0.0234,
|
576 |
+
"step": 324
|
577 |
+
},
|
578 |
+
{
|
579 |
+
"epoch": 6.905263157894737,
|
580 |
+
"grad_norm": 0.1136666014790535,
|
581 |
+
"learning_rate": 0.000120285627061992,
|
582 |
+
"loss": 0.0217,
|
583 |
+
"step": 328
|
584 |
+
},
|
585 |
+
{
|
586 |
+
"epoch": 6.989473684210527,
|
587 |
+
"grad_norm": 0.11610202491283417,
|
588 |
+
"learning_rate": 0.00011844282968323501,
|
589 |
+
"loss": 0.0221,
|
590 |
+
"step": 332
|
591 |
+
},
|
592 |
+
{
|
593 |
+
"epoch": 7.073684210526316,
|
594 |
+
"grad_norm": 0.04680392146110535,
|
595 |
+
"learning_rate": 0.00011659352528242366,
|
596 |
+
"loss": 0.0186,
|
597 |
+
"step": 336
|
598 |
+
},
|
599 |
+
{
|
600 |
+
"epoch": 7.157894736842105,
|
601 |
+
"grad_norm": 0.1080232560634613,
|
602 |
+
"learning_rate": 0.00011473836633343144,
|
603 |
+
"loss": 0.0181,
|
604 |
+
"step": 340
|
605 |
+
},
|
606 |
+
{
|
607 |
+
"epoch": 7.242105263157895,
|
608 |
+
"grad_norm": 0.07934293150901794,
|
609 |
+
"learning_rate": 0.00011287800737574072,
|
610 |
+
"loss": 0.0175,
|
611 |
+
"step": 344
|
612 |
+
},
|
613 |
+
{
|
614 |
+
"epoch": 7.326315789473684,
|
615 |
+
"grad_norm": 0.11348960548639297,
|
616 |
+
"learning_rate": 0.00011101310478350754,
|
617 |
+
"loss": 0.0191,
|
618 |
+
"step": 348
|
619 |
+
},
|
620 |
+
{
|
621 |
+
"epoch": 7.410526315789474,
|
622 |
+
"grad_norm": 0.1111045703291893,
|
623 |
+
"learning_rate": 0.00010914431653397856,
|
624 |
+
"loss": 0.0183,
|
625 |
+
"step": 352
|
626 |
+
},
|
627 |
+
{
|
628 |
+
"epoch": 7.494736842105263,
|
629 |
+
"grad_norm": 0.10023918747901917,
|
630 |
+
"learning_rate": 0.00010727230197534299,
|
631 |
+
"loss": 0.0201,
|
632 |
+
"step": 356
|
633 |
+
},
|
634 |
+
{
|
635 |
+
"epoch": 7.578947368421053,
|
636 |
+
"grad_norm": 0.1350473314523697,
|
637 |
+
"learning_rate": 0.00010539772159410036,
|
638 |
+
"loss": 0.019,
|
639 |
+
"step": 360
|
640 |
+
},
|
641 |
+
{
|
642 |
+
"epoch": 7.663157894736842,
|
643 |
+
"grad_norm": 0.09026475250720978,
|
644 |
+
"learning_rate": 0.00010352123678202685,
|
645 |
+
"loss": 0.0184,
|
646 |
+
"step": 364
|
647 |
+
},
|
648 |
+
{
|
649 |
+
"epoch": 7.747368421052632,
|
650 |
+
"grad_norm": 0.08861108869314194,
|
651 |
+
"learning_rate": 0.00010164350960282252,
|
652 |
+
"loss": 0.0187,
|
653 |
+
"step": 368
|
654 |
+
},
|
655 |
+
{
|
656 |
+
"epoch": 7.831578947368421,
|
657 |
+
"grad_norm": 0.07832619547843933,
|
658 |
+
"learning_rate": 9.976520255852065e-05,
|
659 |
+
"loss": 0.0192,
|
660 |
+
"step": 372
|
661 |
+
},
|
662 |
+
{
|
663 |
+
"epoch": 7.91578947368421,
|
664 |
+
"grad_norm": 0.10778514295816422,
|
665 |
+
"learning_rate": 9.788697835574347e-05,
|
666 |
+
"loss": 0.0204,
|
667 |
+
"step": 376
|
668 |
+
},
|
669 |
+
{
|
670 |
+
"epoch": 8.0,
|
671 |
+
"grad_norm": 0.09410171210765839,
|
672 |
+
"learning_rate": 9.600949967188484e-05,
|
673 |
+
"loss": 0.0189,
|
674 |
+
"step": 380
|
675 |
+
},
|
676 |
+
{
|
677 |
+
"epoch": 8.08421052631579,
|
678 |
+
"grad_norm": 0.04481295123696327,
|
679 |
+
"learning_rate": 9.413342892130376e-05,
|
680 |
+
"loss": 0.0151,
|
681 |
+
"step": 384
|
682 |
+
},
|
683 |
+
{
|
684 |
+
"epoch": 8.16842105263158,
|
685 |
+
"grad_norm": 0.055971067398786545,
|
686 |
+
"learning_rate": 9.225942802161042e-05,
|
687 |
+
"loss": 0.0158,
|
688 |
+
"step": 388
|
689 |
+
},
|
690 |
+
{
|
691 |
+
"epoch": 8.25263157894737,
|
692 |
+
"grad_norm": 0.07519485801458359,
|
693 |
+
"learning_rate": 9.038815816012767e-05,
|
694 |
+
"loss": 0.0162,
|
695 |
+
"step": 392
|
696 |
+
},
|
697 |
+
{
|
698 |
+
"epoch": 8.336842105263157,
|
699 |
+
"grad_norm": 0.06743883341550827,
|
700 |
+
"learning_rate": 8.852027956061015e-05,
|
701 |
+
"loss": 0.0155,
|
702 |
+
"step": 396
|
703 |
+
},
|
704 |
+
{
|
705 |
+
"epoch": 8.421052631578947,
|
706 |
+
"grad_norm": 0.05589531734585762,
|
707 |
+
"learning_rate": 8.665645125030311e-05,
|
708 |
+
"loss": 0.0166,
|
709 |
+
"step": 400
|
710 |
+
},
|
711 |
+
{
|
712 |
+
"epoch": 8.505263157894737,
|
713 |
+
"grad_norm": 0.05887574702501297,
|
714 |
+
"learning_rate": 8.479733082742384e-05,
|
715 |
+
"loss": 0.0164,
|
716 |
+
"step": 404
|
717 |
+
},
|
718 |
+
{
|
719 |
+
"epoch": 8.589473684210526,
|
720 |
+
"grad_norm": 0.057513728737831116,
|
721 |
+
"learning_rate": 8.294357422914685e-05,
|
722 |
+
"loss": 0.0172,
|
723 |
+
"step": 408
|
724 |
+
},
|
725 |
+
{
|
726 |
+
"epoch": 8.673684210526316,
|
727 |
+
"grad_norm": 0.05391902104020119,
|
728 |
+
"learning_rate": 8.10958355001755e-05,
|
729 |
+
"loss": 0.0167,
|
730 |
+
"step": 412
|
731 |
+
},
|
732 |
+
{
|
733 |
+
"epoch": 8.757894736842106,
|
734 |
+
"grad_norm": 0.047253336757421494,
|
735 |
+
"learning_rate": 7.925476656198095e-05,
|
736 |
+
"loss": 0.0166,
|
737 |
+
"step": 416
|
738 |
+
},
|
739 |
+
{
|
740 |
+
"epoch": 8.842105263157894,
|
741 |
+
"grad_norm": 0.04581145569682121,
|
742 |
+
"learning_rate": 7.74210169827906e-05,
|
743 |
+
"loss": 0.0184,
|
744 |
+
"step": 420
|
745 |
+
},
|
746 |
+
{
|
747 |
+
"epoch": 8.926315789473684,
|
748 |
+
"grad_norm": 0.05937978997826576,
|
749 |
+
"learning_rate": 7.55952337484064e-05,
|
750 |
+
"loss": 0.0162,
|
751 |
+
"step": 424
|
752 |
+
},
|
753 |
+
{
|
754 |
+
"epoch": 9.010526315789473,
|
755 |
+
"grad_norm": 0.043958455324172974,
|
756 |
+
"learning_rate": 7.377806103393473e-05,
|
757 |
+
"loss": 0.0171,
|
758 |
+
"step": 428
|
759 |
+
},
|
760 |
+
{
|
761 |
+
"epoch": 9.094736842105263,
|
762 |
+
"grad_norm": 0.035407859832048416,
|
763 |
+
"learning_rate": 7.197013997650762e-05,
|
764 |
+
"loss": 0.0145,
|
765 |
+
"step": 432
|
766 |
+
},
|
767 |
+
{
|
768 |
+
"epoch": 9.178947368421053,
|
769 |
+
"grad_norm": 0.0361582450568676,
|
770 |
+
"learning_rate": 7.017210844907598e-05,
|
771 |
+
"loss": 0.0148,
|
772 |
+
"step": 436
|
773 |
+
},
|
774 |
+
{
|
775 |
+
"epoch": 9.263157894736842,
|
776 |
+
"grad_norm": 0.04210333898663521,
|
777 |
+
"learning_rate": 6.838460083535445e-05,
|
778 |
+
"loss": 0.0147,
|
779 |
+
"step": 440
|
780 |
+
},
|
781 |
+
{
|
782 |
+
"epoch": 9.347368421052632,
|
783 |
+
"grad_norm": 0.043872371315956116,
|
784 |
+
"learning_rate": 6.660824780599744e-05,
|
785 |
+
"loss": 0.0144,
|
786 |
+
"step": 444
|
787 |
+
},
|
788 |
+
{
|
789 |
+
"epoch": 9.431578947368422,
|
790 |
+
"grad_norm": 0.04811229929327965,
|
791 |
+
"learning_rate": 6.484367609608503e-05,
|
792 |
+
"loss": 0.0148,
|
793 |
+
"step": 448
|
794 |
+
},
|
795 |
+
{
|
796 |
+
"epoch": 9.51578947368421,
|
797 |
+
"grad_norm": 0.05032840371131897,
|
798 |
+
"learning_rate": 6.309150828399754e-05,
|
799 |
+
"loss": 0.0152,
|
800 |
+
"step": 452
|
801 |
+
},
|
802 |
+
{
|
803 |
+
"epoch": 9.6,
|
804 |
+
"grad_norm": 0.04303669556975365,
|
805 |
+
"learning_rate": 6.135236257175668e-05,
|
806 |
+
"loss": 0.0172,
|
807 |
+
"step": 456
|
808 |
+
},
|
809 |
+
{
|
810 |
+
"epoch": 9.68421052631579,
|
811 |
+
"grad_norm": 0.04116836190223694,
|
812 |
+
"learning_rate": 5.962685256691071e-05,
|
813 |
+
"loss": 0.0154,
|
814 |
+
"step": 460
|
815 |
+
},
|
816 |
+
{
|
817 |
+
"epoch": 9.76842105263158,
|
818 |
+
"grad_norm": 0.04266192391514778,
|
819 |
+
"learning_rate": 5.791558706604074e-05,
|
820 |
+
"loss": 0.0153,
|
821 |
+
"step": 464
|
822 |
+
},
|
823 |
+
{
|
824 |
+
"epoch": 9.852631578947369,
|
825 |
+
"grad_norm": 0.04463796690106392,
|
826 |
+
"learning_rate": 5.621916983996429e-05,
|
827 |
+
"loss": 0.0156,
|
828 |
+
"step": 468
|
829 |
+
},
|
830 |
+
{
|
831 |
+
"epoch": 9.936842105263159,
|
832 |
+
"grad_norm": 0.0458030104637146,
|
833 |
+
"learning_rate": 5.453819942071211e-05,
|
834 |
+
"loss": 0.0159,
|
835 |
+
"step": 472
|
836 |
+
},
|
837 |
+
{
|
838 |
+
"epoch": 10.021052631578947,
|
839 |
+
"grad_norm": 0.03369244933128357,
|
840 |
+
"learning_rate": 5.2873268890353424e-05,
|
841 |
+
"loss": 0.0148,
|
842 |
+
"step": 476
|
843 |
+
},
|
844 |
+
{
|
845 |
+
"epoch": 10.105263157894736,
|
846 |
+
"grad_norm": 0.03552337363362312,
|
847 |
+
"learning_rate": 5.12249656717439e-05,
|
848 |
+
"loss": 0.0136,
|
849 |
+
"step": 480
|
850 |
+
},
|
851 |
+
{
|
852 |
+
"epoch": 10.189473684210526,
|
853 |
+
"grad_norm": 0.04354244843125343,
|
854 |
+
"learning_rate": 4.959387132127054e-05,
|
855 |
+
"loss": 0.0144,
|
856 |
+
"step": 484
|
857 |
+
},
|
858 |
+
{
|
859 |
+
"epoch": 10.273684210526316,
|
860 |
+
"grad_norm": 0.034174419939517975,
|
861 |
+
"learning_rate": 4.7980561323666115e-05,
|
862 |
+
"loss": 0.0132,
|
863 |
+
"step": 488
|
864 |
+
},
|
865 |
+
{
|
866 |
+
"epoch": 10.357894736842105,
|
867 |
+
"grad_norm": 0.0367300920188427,
|
868 |
+
"learning_rate": 4.638560488896589e-05,
|
869 |
+
"loss": 0.0146,
|
870 |
+
"step": 492
|
871 |
+
},
|
872 |
+
{
|
873 |
+
"epoch": 10.442105263157895,
|
874 |
+
"grad_norm": 0.03937629610300064,
|
875 |
+
"learning_rate": 4.48095647516783e-05,
|
876 |
+
"loss": 0.0143,
|
877 |
+
"step": 496
|
878 |
+
},
|
879 |
+
{
|
880 |
+
"epoch": 10.526315789473685,
|
881 |
+
"grad_norm": 0.045526400208473206,
|
882 |
+
"learning_rate": 4.3252996972240324e-05,
|
883 |
+
"loss": 0.0142,
|
884 |
+
"step": 500
|
885 |
+
},
|
886 |
+
{
|
887 |
+
"epoch": 10.610526315789473,
|
888 |
+
"grad_norm": 0.04123491421341896,
|
889 |
+
"learning_rate": 4.171645074082737e-05,
|
890 |
+
"loss": 0.0148,
|
891 |
+
"step": 504
|
892 |
+
},
|
893 |
+
{
|
894 |
+
"epoch": 10.694736842105263,
|
895 |
+
"grad_norm": 0.0411781445145607,
|
896 |
+
"learning_rate": 4.0200468183587556e-05,
|
897 |
+
"loss": 0.0147,
|
898 |
+
"step": 508
|
899 |
+
},
|
900 |
+
{
|
901 |
+
"epoch": 10.778947368421052,
|
902 |
+
"grad_norm": 0.04118568077683449,
|
903 |
+
"learning_rate": 3.8705584171367885e-05,
|
904 |
+
"loss": 0.0152,
|
905 |
+
"step": 512
|
906 |
+
},
|
907 |
+
{
|
908 |
+
"epoch": 10.863157894736842,
|
909 |
+
"grad_norm": 0.04070712625980377,
|
910 |
+
"learning_rate": 3.723232613100046e-05,
|
911 |
+
"loss": 0.015,
|
912 |
+
"step": 516
|
913 |
+
},
|
914 |
+
{
|
915 |
+
"epoch": 10.947368421052632,
|
916 |
+
"grad_norm": 0.037149183452129364,
|
917 |
+
"learning_rate": 3.578121385921533e-05,
|
918 |
+
"loss": 0.0147,
|
919 |
+
"step": 520
|
920 |
+
},
|
921 |
+
{
|
922 |
+
"epoch": 11.031578947368422,
|
923 |
+
"grad_norm": 0.04417663812637329,
|
924 |
+
"learning_rate": 3.435275933924487e-05,
|
925 |
+
"loss": 0.0143,
|
926 |
+
"step": 524
|
927 |
+
},
|
928 |
+
{
|
929 |
+
"epoch": 11.115789473684211,
|
930 |
+
"grad_norm": 0.03727949410676956,
|
931 |
+
"learning_rate": 3.294746656018532e-05,
|
932 |
+
"loss": 0.0136,
|
933 |
+
"step": 528
|
934 |
+
},
|
935 |
+
{
|
936 |
+
"epoch": 11.2,
|
937 |
+
"grad_norm": 0.03517484292387962,
|
938 |
+
"learning_rate": 3.156583133917884e-05,
|
939 |
+
"loss": 0.0135,
|
940 |
+
"step": 532
|
941 |
+
},
|
942 |
+
{
|
943 |
+
"epoch": 11.284210526315789,
|
944 |
+
"grad_norm": 0.04109984263777733,
|
945 |
+
"learning_rate": 3.0208341146478602e-05,
|
946 |
+
"loss": 0.0134,
|
947 |
+
"step": 536
|
948 |
+
},
|
949 |
+
{
|
950 |
+
"epoch": 11.368421052631579,
|
951 |
+
"grad_norm": 0.038387149572372437,
|
952 |
+
"learning_rate": 2.8875474933458847e-05,
|
953 |
+
"loss": 0.0137,
|
954 |
+
"step": 540
|
955 |
+
},
|
956 |
+
{
|
957 |
+
"epoch": 11.452631578947368,
|
958 |
+
"grad_norm": 0.038690097630023956,
|
959 |
+
"learning_rate": 2.7567702963630803e-05,
|
960 |
+
"loss": 0.0137,
|
961 |
+
"step": 544
|
962 |
+
},
|
963 |
+
{
|
964 |
+
"epoch": 11.536842105263158,
|
965 |
+
"grad_norm": 0.04456111416220665,
|
966 |
+
"learning_rate": 2.6285486646723634e-05,
|
967 |
+
"loss": 0.0143,
|
968 |
+
"step": 548
|
969 |
+
},
|
970 |
+
{
|
971 |
+
"epoch": 11.621052631578948,
|
972 |
+
"grad_norm": 0.03415576368570328,
|
973 |
+
"learning_rate": 2.5029278375889387e-05,
|
974 |
+
"loss": 0.0142,
|
975 |
+
"step": 552
|
976 |
+
},
|
977 |
+
{
|
978 |
+
"epoch": 11.705263157894738,
|
979 |
+
"grad_norm": 0.042495112866163254,
|
980 |
+
"learning_rate": 2.379952136808903e-05,
|
981 |
+
"loss": 0.014,
|
982 |
+
"step": 556
|
983 |
+
},
|
984 |
+
{
|
985 |
+
"epoch": 11.789473684210526,
|
986 |
+
"grad_norm": 0.04094533994793892,
|
987 |
+
"learning_rate": 2.2596649507716018e-05,
|
988 |
+
"loss": 0.0138,
|
989 |
+
"step": 560
|
990 |
+
},
|
991 |
+
{
|
992 |
+
"epoch": 11.873684210526315,
|
993 |
+
"grad_norm": 0.0460105761885643,
|
994 |
+
"learning_rate": 2.1421087193512756e-05,
|
995 |
+
"loss": 0.0146,
|
996 |
+
"step": 564
|
997 |
+
},
|
998 |
+
{
|
999 |
+
"epoch": 11.957894736842105,
|
1000 |
+
"grad_norm": 0.03978003188967705,
|
1001 |
+
"learning_rate": 2.0273249188833654e-05,
|
1002 |
+
"loss": 0.0144,
|
1003 |
+
"step": 568
|
1004 |
+
},
|
1005 |
+
{
|
1006 |
+
"epoch": 12.042105263157895,
|
1007 |
+
"grad_norm": 0.038386404514312744,
|
1008 |
+
"learning_rate": 1.915354047530791e-05,
|
1009 |
+
"loss": 0.0137,
|
1010 |
+
"step": 572
|
1011 |
+
},
|
1012 |
+
{
|
1013 |
+
"epoch": 12.126315789473685,
|
1014 |
+
"grad_norm": 0.040764693170785904,
|
1015 |
+
"learning_rate": 1.806235610995327e-05,
|
1016 |
+
"loss": 0.0131,
|
1017 |
+
"step": 576
|
1018 |
+
},
|
1019 |
+
{
|
1020 |
+
"epoch": 12.210526315789474,
|
1021 |
+
"grad_norm": 0.03799861669540405,
|
1022 |
+
"learning_rate": 1.700008108579154e-05,
|
1023 |
+
"loss": 0.0132,
|
1024 |
+
"step": 580
|
1025 |
+
},
|
1026 |
+
{
|
1027 |
+
"epoch": 12.294736842105262,
|
1028 |
+
"grad_norm": 0.04342568293213844,
|
1029 |
+
"learning_rate": 1.59670901960149e-05,
|
1030 |
+
"loss": 0.0137,
|
1031 |
+
"step": 584
|
1032 |
+
},
|
1033 |
+
{
|
1034 |
+
"epoch": 12.378947368421052,
|
1035 |
+
"grad_norm": 0.03906482830643654,
|
1036 |
+
"learning_rate": 1.4963747901750936e-05,
|
1037 |
+
"loss": 0.0133,
|
1038 |
+
"step": 588
|
1039 |
+
},
|
1040 |
+
{
|
1041 |
+
"epoch": 12.463157894736842,
|
1042 |
+
"grad_norm": 0.037218380719423294,
|
1043 |
+
"learning_rate": 1.3990408203472938e-05,
|
1044 |
+
"loss": 0.0134,
|
1045 |
+
"step": 592
|
1046 |
+
},
|
1047 |
+
{
|
1048 |
+
"epoch": 12.547368421052632,
|
1049 |
+
"grad_norm": 0.041138604283332825,
|
1050 |
+
"learning_rate": 1.304741451610103e-05,
|
1051 |
+
"loss": 0.0136,
|
1052 |
+
"step": 596
|
1053 |
+
},
|
1054 |
+
{
|
1055 |
+
"epoch": 12.631578947368421,
|
1056 |
+
"grad_norm": 0.03980677202343941,
|
1057 |
+
"learning_rate": 1.2135099547838192e-05,
|
1058 |
+
"loss": 0.0135,
|
1059 |
+
"step": 600
|
1060 |
+
},
|
1061 |
+
{
|
1062 |
+
"epoch": 12.715789473684211,
|
1063 |
+
"grad_norm": 0.04195684567093849,
|
1064 |
+
"learning_rate": 1.1253785182783572e-05,
|
1065 |
+
"loss": 0.0136,
|
1066 |
+
"step": 604
|
1067 |
+
},
|
1068 |
+
{
|
1069 |
+
"epoch": 12.8,
|
1070 |
+
"grad_norm": 0.03899657726287842,
|
1071 |
+
"learning_rate": 1.0403782367365088e-05,
|
1072 |
+
"loss": 0.0136,
|
1073 |
+
"step": 608
|
1074 |
+
},
|
1075 |
+
{
|
1076 |
+
"epoch": 12.884210526315789,
|
1077 |
+
"grad_norm": 0.04153283312916756,
|
1078 |
+
"learning_rate": 9.585391000630828e-06,
|
1079 |
+
"loss": 0.0138,
|
1080 |
+
"step": 612
|
1081 |
+
},
|
1082 |
+
{
|
1083 |
+
"epoch": 12.968421052631578,
|
1084 |
+
"grad_norm": 0.04069840535521507,
|
1085 |
+
"learning_rate": 8.798899828438333e-06,
|
1086 |
+
"loss": 0.0136,
|
1087 |
+
"step": 616
|
1088 |
+
},
|
1089 |
+
{
|
1090 |
+
"epoch": 13.052631578947368,
|
1091 |
+
"grad_norm": 0.038807112723588943,
|
1092 |
+
"learning_rate": 8.044586341578886e-06,
|
1093 |
+
"loss": 0.0135,
|
1094 |
+
"step": 620
|
1095 |
+
},
|
1096 |
+
{
|
1097 |
+
"epoch": 13.136842105263158,
|
1098 |
+
"grad_norm": 0.03619793429970741,
|
1099 |
+
"learning_rate": 7.32271667787302e-06,
|
1100 |
+
"loss": 0.0129,
|
1101 |
+
"step": 624
|
1102 |
+
},
|
1103 |
+
{
|
1104 |
+
"epoch": 13.221052631578948,
|
1105 |
+
"grad_norm": 0.04398636892437935,
|
1106 |
+
"learning_rate": 6.633545528271212e-06,
|
1107 |
+
"loss": 0.0136,
|
1108 |
+
"step": 628
|
1109 |
+
},
|
1110 |
+
{
|
1111 |
+
"epoch": 13.305263157894737,
|
1112 |
+
"grad_norm": 0.04213196039199829,
|
1113 |
+
"learning_rate": 5.977316046993642e-06,
|
1114 |
+
"loss": 0.0136,
|
1115 |
+
"step": 632
|
1116 |
+
},
|
1117 |
+
{
|
1118 |
+
"epoch": 13.389473684210527,
|
1119 |
+
"grad_norm": 0.03905045613646507,
|
1120 |
+
"learning_rate": 5.354259765740177e-06,
|
1121 |
+
"loss": 0.0131,
|
1122 |
+
"step": 636
|
1123 |
+
},
|
1124 |
+
{
|
1125 |
+
"epoch": 13.473684210526315,
|
1126 |
+
"grad_norm": 0.035913437604904175,
|
1127 |
+
"learning_rate": 4.764596512001162e-06,
|
1128 |
+
"loss": 0.0131,
|
1129 |
+
"step": 640
|
1130 |
+
},
|
1131 |
+
{
|
1132 |
+
"epoch": 13.557894736842105,
|
1133 |
+
"grad_norm": 0.034688446670770645,
|
1134 |
+
"learning_rate": 4.2085343314974715e-06,
|
1135 |
+
"loss": 0.0129,
|
1136 |
+
"step": 644
|
1137 |
+
},
|
1138 |
+
{
|
1139 |
+
"epoch": 13.642105263157895,
|
1140 |
+
"grad_norm": 0.03610476851463318,
|
1141 |
+
"learning_rate": 3.686269414777643e-06,
|
1142 |
+
"loss": 0.013,
|
1143 |
+
"step": 648
|
1144 |
+
},
|
1145 |
+
{
|
1146 |
+
"epoch": 13.726315789473684,
|
1147 |
+
"grad_norm": 0.03774738684296608,
|
1148 |
+
"learning_rate": 3.197986027997657e-06,
|
1149 |
+
"loss": 0.0133,
|
1150 |
+
"step": 652
|
1151 |
+
},
|
1152 |
+
{
|
1153 |
+
"epoch": 13.810526315789474,
|
1154 |
+
"grad_norm": 0.04130537807941437,
|
1155 |
+
"learning_rate": 2.743856447907944e-06,
|
1156 |
+
"loss": 0.0132,
|
1157 |
+
"step": 656
|
1158 |
+
},
|
1159 |
+
{
|
1160 |
+
"epoch": 13.894736842105264,
|
1161 |
+
"grad_norm": 0.04178741201758385,
|
1162 |
+
"learning_rate": 2.32404090107049e-06,
|
1163 |
+
"loss": 0.0131,
|
1164 |
+
"step": 660
|
1165 |
+
},
|
1166 |
+
{
|
1167 |
+
"epoch": 13.978947368421053,
|
1168 |
+
"grad_norm": 0.041015882045030594,
|
1169 |
+
"learning_rate": 1.9386875073274636e-06,
|
1170 |
+
"loss": 0.0133,
|
1171 |
+
"step": 664
|
1172 |
+
},
|
1173 |
+
{
|
1174 |
+
"epoch": 14.063157894736841,
|
1175 |
+
"grad_norm": 0.040738049894571304,
|
1176 |
+
"learning_rate": 1.5879322275414332e-06,
|
1177 |
+
"loss": 0.0131,
|
1178 |
+
"step": 668
|
1179 |
+
},
|
1180 |
+
{
|
1181 |
+
"epoch": 14.147368421052631,
|
1182 |
+
"grad_norm": 0.03942083567380905,
|
1183 |
+
"learning_rate": 1.2718988156254607e-06,
|
1184 |
+
"loss": 0.0131,
|
1185 |
+
"step": 672
|
1186 |
+
},
|
1187 |
+
{
|
1188 |
+
"epoch": 14.23157894736842,
|
1189 |
+
"grad_norm": 0.03392017260193825,
|
1190 |
+
"learning_rate": 9.906987748800944e-07,
|
1191 |
+
"loss": 0.0131,
|
1192 |
+
"step": 676
|
1193 |
+
},
|
1194 |
+
{
|
1195 |
+
"epoch": 14.31578947368421,
|
1196 |
+
"grad_norm": 0.037095777690410614,
|
1197 |
+
"learning_rate": 7.444313186526608e-07,
|
1198 |
+
"loss": 0.0131,
|
1199 |
+
"step": 680
|
1200 |
+
},
|
1201 |
+
{
|
1202 |
+
"epoch": 14.4,
|
1203 |
+
"grad_norm": 0.03976672887802124,
|
1204 |
+
"learning_rate": 5.331833353326432e-07,
|
1205 |
+
"loss": 0.0129,
|
1206 |
+
"step": 684
|
1207 |
+
},
|
1208 |
+
{
|
1209 |
+
"epoch": 14.48421052631579,
|
1210 |
+
"grad_norm": 0.035997770726680756,
|
1211 |
+
"learning_rate": 3.570293576956596e-07,
|
1212 |
+
"loss": 0.0129,
|
1213 |
+
"step": 688
|
1214 |
+
},
|
1215 |
+
{
|
1216 |
+
"epoch": 14.568421052631578,
|
1217 |
+
"grad_norm": 0.03750745207071304,
|
1218 |
+
"learning_rate": 2.1603153660668674e-07,
|
1219 |
+
"loss": 0.0133,
|
1220 |
+
"step": 692
|
1221 |
+
},
|
1222 |
+
{
|
1223 |
+
"epoch": 14.652631578947368,
|
1224 |
+
"grad_norm": 0.0350378155708313,
|
1225 |
+
"learning_rate": 1.1023961909192304e-07,
|
1226 |
+
"loss": 0.0129,
|
1227 |
+
"step": 696
|
1228 |
+
},
|
1229 |
+
{
|
1230 |
+
"epoch": 14.736842105263158,
|
1231 |
+
"grad_norm": 0.040333278477191925,
|
1232 |
+
"learning_rate": 3.9690930786995264e-08,
|
1233 |
+
"loss": 0.013,
|
1234 |
+
"step": 700
|
1235 |
+
},
|
1236 |
+
{
|
1237 |
+
"epoch": 14.821052631578947,
|
1238 |
+
"grad_norm": 0.03885936737060547,
|
1239 |
+
"learning_rate": 4.410362767626186e-09,
|
1240 |
+
"loss": 0.013,
|
1241 |
+
"step": 704
|
1242 |
+
}
|
1243 |
+
],
|
1244 |
+
"logging_steps": 4,
|
1245 |
+
"max_steps": 705,
|
1246 |
+
"num_input_tokens_seen": 0,
|
1247 |
+
"num_train_epochs": 15,
|
1248 |
+
"save_steps": 500,
|
1249 |
+
"stateful_callbacks": {
|
1250 |
+
"TrainerControl": {
|
1251 |
+
"args": {
|
1252 |
+
"should_epoch_stop": false,
|
1253 |
+
"should_evaluate": false,
|
1254 |
+
"should_log": false,
|
1255 |
+
"should_save": true,
|
1256 |
+
"should_training_stop": true
|
1257 |
+
},
|
1258 |
+
"attributes": {}
|
1259 |
+
}
|
1260 |
+
},
|
1261 |
+
"total_flos": 2.830218222769275e+17,
|
1262 |
+
"train_batch_size": 4,
|
1263 |
+
"trial_name": null,
|
1264 |
+
"trial_params": null
|
1265 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1865c04ec4e6a9a9e3f62f86b6af36162bdd71edddc66eeabbb392b01c82e410
|
3 |
+
size 5304
|