Upload folder using huggingface_hub
Browse files- .gitattributes +1 -0
- README.md +202 -0
- adapter_config.json +29 -0
- adapter_model.safetensors +3 -0
- optimizer.pt +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +34 -0
- tokenizer.json +3 -0
- tokenizer.model +3 -0
- tokenizer_config.json +1756 -0
- trainer_state.json +1433 -0
- training_args.bin +3 -0
.gitattributes
CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
36 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
README.md
ADDED
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
base_model: google/gemma-2b
|
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 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "google/gemma-2b",
|
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": 8,
|
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": 4,
|
20 |
+
"rank_pattern": {},
|
21 |
+
"revision": null,
|
22 |
+
"target_modules": [
|
23 |
+
"q_proj",
|
24 |
+
"v_proj"
|
25 |
+
],
|
26 |
+
"task_type": "CAUSAL_LM",
|
27 |
+
"use_dora": false,
|
28 |
+
"use_rslora": false
|
29 |
+
}
|
adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e883c68580b5e6cbf881d8742eb5e0b72d5a193e69e82a8c182365cdd1bdaf98
|
3 |
+
size 1852600
|
optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:82ccffdb4a7b654d1e4ccf338fd193138b6dcc634a4a4f127e4205b579d8fcb5
|
3 |
+
size 1108346
|
rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b357a46ab4bf93a5983dcfbf8e6f5fe8bbe265957362ecb629448f6d178ae3e9
|
3 |
+
size 14244
|
scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0cc2554971d8fa40cfa76cd454291d90c8073bcf41866a6c48309d0340f04edf
|
3 |
+
size 1064
|
special_tokens_map.json
ADDED
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"<start_of_turn>",
|
4 |
+
"<end_of_turn>"
|
5 |
+
],
|
6 |
+
"bos_token": {
|
7 |
+
"content": "<bos>",
|
8 |
+
"lstrip": false,
|
9 |
+
"normalized": false,
|
10 |
+
"rstrip": false,
|
11 |
+
"single_word": false
|
12 |
+
},
|
13 |
+
"eos_token": {
|
14 |
+
"content": "<eos>",
|
15 |
+
"lstrip": false,
|
16 |
+
"normalized": false,
|
17 |
+
"rstrip": false,
|
18 |
+
"single_word": false
|
19 |
+
},
|
20 |
+
"pad_token": {
|
21 |
+
"content": "<pad>",
|
22 |
+
"lstrip": false,
|
23 |
+
"normalized": false,
|
24 |
+
"rstrip": false,
|
25 |
+
"single_word": false
|
26 |
+
},
|
27 |
+
"unk_token": {
|
28 |
+
"content": "<unk>",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false
|
33 |
+
}
|
34 |
+
}
|
tokenizer.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7da53ca29fb16f6b2489482fc0bc6a394162cdab14d12764a1755ebc583fea79
|
3 |
+
size 17518525
|
tokenizer.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:61a7b147390c64585d6c3543dd6fc636906c9af3865a5548f27f31aee1d4c8e2
|
3 |
+
size 4241003
|
tokenizer_config.json
ADDED
@@ -0,0 +1,1756 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": true,
|
3 |
+
"add_eos_token": false,
|
4 |
+
"added_tokens_decoder": {
|
5 |
+
"0": {
|
6 |
+
"content": "<pad>",
|
7 |
+
"lstrip": false,
|
8 |
+
"normalized": false,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false,
|
11 |
+
"special": true
|
12 |
+
},
|
13 |
+
"1": {
|
14 |
+
"content": "<eos>",
|
15 |
+
"lstrip": false,
|
16 |
+
"normalized": false,
|
17 |
+
"rstrip": false,
|
18 |
+
"single_word": false,
|
19 |
+
"special": true
|
20 |
+
},
|
21 |
+
"2": {
|
22 |
+
"content": "<bos>",
|
23 |
+
"lstrip": false,
|
24 |
+
"normalized": false,
|
25 |
+
"rstrip": false,
|
26 |
+
"single_word": false,
|
27 |
+
"special": true
|
28 |
+
},
|
29 |
+
"3": {
|
30 |
+
"content": "<unk>",
|
31 |
+
"lstrip": false,
|
32 |
+
"normalized": false,
|
33 |
+
"rstrip": false,
|
34 |
+
"single_word": false,
|
35 |
+
"special": true
|
36 |
+
},
|
37 |
+
"4": {
|
38 |
+
"content": "<mask>",
|
39 |
+
"lstrip": false,
|
40 |
+
"normalized": false,
|
41 |
+
"rstrip": false,
|
42 |
+
"single_word": false,
|
43 |
+
"special": false
|
44 |
+
},
|
45 |
+
"5": {
|
46 |
+
"content": "<2mass>",
|
47 |
+
"lstrip": false,
|
48 |
+
"normalized": false,
|
49 |
+
"rstrip": false,
|
50 |
+
"single_word": false,
|
51 |
+
"special": false
|
52 |
+
},
|
53 |
+
"6": {
|
54 |
+
"content": "[@BOS@]",
|
55 |
+
"lstrip": false,
|
56 |
+
"normalized": false,
|
57 |
+
"rstrip": false,
|
58 |
+
"single_word": false,
|
59 |
+
"special": false
|
60 |
+
},
|
61 |
+
"7": {
|
62 |
+
"content": "<unused0>",
|
63 |
+
"lstrip": false,
|
64 |
+
"normalized": false,
|
65 |
+
"rstrip": false,
|
66 |
+
"single_word": false,
|
67 |
+
"special": false
|
68 |
+
},
|
69 |
+
"8": {
|
70 |
+
"content": "<unused1>",
|
71 |
+
"lstrip": false,
|
72 |
+
"normalized": false,
|
73 |
+
"rstrip": false,
|
74 |
+
"single_word": false,
|
75 |
+
"special": false
|
76 |
+
},
|
77 |
+
"9": {
|
78 |
+
"content": "<unused2>",
|
79 |
+
"lstrip": false,
|
80 |
+
"normalized": false,
|
81 |
+
"rstrip": false,
|
82 |
+
"single_word": false,
|
83 |
+
"special": false
|
84 |
+
},
|
85 |
+
"10": {
|
86 |
+
"content": "<unused3>",
|
87 |
+
"lstrip": false,
|
88 |
+
"normalized": false,
|
89 |
+
"rstrip": false,
|
90 |
+
"single_word": false,
|
91 |
+
"special": false
|
92 |
+
},
|
93 |
+
"11": {
|
94 |
+
"content": "<unused4>",
|
95 |
+
"lstrip": false,
|
96 |
+
"normalized": false,
|
97 |
+
"rstrip": false,
|
98 |
+
"single_word": false,
|
99 |
+
"special": false
|
100 |
+
},
|
101 |
+
"12": {
|
102 |
+
"content": "<unused5>",
|
103 |
+
"lstrip": false,
|
104 |
+
"normalized": false,
|
105 |
+
"rstrip": false,
|
106 |
+
"single_word": false,
|
107 |
+
"special": false
|
108 |
+
},
|
109 |
+
"13": {
|
110 |
+
"content": "<unused6>",
|
111 |
+
"lstrip": false,
|
112 |
+
"normalized": false,
|
113 |
+
"rstrip": false,
|
114 |
+
"single_word": false,
|
115 |
+
"special": false
|
116 |
+
},
|
117 |
+
"14": {
|
118 |
+
"content": "<unused7>",
|
119 |
+
"lstrip": false,
|
120 |
+
"normalized": false,
|
121 |
+
"rstrip": false,
|
122 |
+
"single_word": false,
|
123 |
+
"special": false
|
124 |
+
},
|
125 |
+
"15": {
|
126 |
+
"content": "<unused8>",
|
127 |
+
"lstrip": false,
|
128 |
+
"normalized": false,
|
129 |
+
"rstrip": false,
|
130 |
+
"single_word": false,
|
131 |
+
"special": false
|
132 |
+
},
|
133 |
+
"16": {
|
134 |
+
"content": "<unused9>",
|
135 |
+
"lstrip": false,
|
136 |
+
"normalized": false,
|
137 |
+
"rstrip": false,
|
138 |
+
"single_word": false,
|
139 |
+
"special": false
|
140 |
+
},
|
141 |
+
"17": {
|
142 |
+
"content": "<unused10>",
|
143 |
+
"lstrip": false,
|
144 |
+
"normalized": false,
|
145 |
+
"rstrip": false,
|
146 |
+
"single_word": false,
|
147 |
+
"special": false
|
148 |
+
},
|
149 |
+
"18": {
|
150 |
+
"content": "<unused11>",
|
151 |
+
"lstrip": false,
|
152 |
+
"normalized": false,
|
153 |
+
"rstrip": false,
|
154 |
+
"single_word": false,
|
155 |
+
"special": false
|
156 |
+
},
|
157 |
+
"19": {
|
158 |
+
"content": "<unused12>",
|
159 |
+
"lstrip": false,
|
160 |
+
"normalized": false,
|
161 |
+
"rstrip": false,
|
162 |
+
"single_word": false,
|
163 |
+
"special": false
|
164 |
+
},
|
165 |
+
"20": {
|
166 |
+
"content": "<unused13>",
|
167 |
+
"lstrip": false,
|
168 |
+
"normalized": false,
|
169 |
+
"rstrip": false,
|
170 |
+
"single_word": false,
|
171 |
+
"special": false
|
172 |
+
},
|
173 |
+
"21": {
|
174 |
+
"content": "<unused14>",
|
175 |
+
"lstrip": false,
|
176 |
+
"normalized": false,
|
177 |
+
"rstrip": false,
|
178 |
+
"single_word": false,
|
179 |
+
"special": false
|
180 |
+
},
|
181 |
+
"22": {
|
182 |
+
"content": "<unused15>",
|
183 |
+
"lstrip": false,
|
184 |
+
"normalized": false,
|
185 |
+
"rstrip": false,
|
186 |
+
"single_word": false,
|
187 |
+
"special": false
|
188 |
+
},
|
189 |
+
"23": {
|
190 |
+
"content": "<unused16>",
|
191 |
+
"lstrip": false,
|
192 |
+
"normalized": false,
|
193 |
+
"rstrip": false,
|
194 |
+
"single_word": false,
|
195 |
+
"special": false
|
196 |
+
},
|
197 |
+
"24": {
|
198 |
+
"content": "<unused17>",
|
199 |
+
"lstrip": false,
|
200 |
+
"normalized": false,
|
201 |
+
"rstrip": false,
|
202 |
+
"single_word": false,
|
203 |
+
"special": false
|
204 |
+
},
|
205 |
+
"25": {
|
206 |
+
"content": "<unused18>",
|
207 |
+
"lstrip": false,
|
208 |
+
"normalized": false,
|
209 |
+
"rstrip": false,
|
210 |
+
"single_word": false,
|
211 |
+
"special": false
|
212 |
+
},
|
213 |
+
"26": {
|
214 |
+
"content": "<unused19>",
|
215 |
+
"lstrip": false,
|
216 |
+
"normalized": false,
|
217 |
+
"rstrip": false,
|
218 |
+
"single_word": false,
|
219 |
+
"special": false
|
220 |
+
},
|
221 |
+
"27": {
|
222 |
+
"content": "<unused20>",
|
223 |
+
"lstrip": false,
|
224 |
+
"normalized": false,
|
225 |
+
"rstrip": false,
|
226 |
+
"single_word": false,
|
227 |
+
"special": false
|
228 |
+
},
|
229 |
+
"28": {
|
230 |
+
"content": "<unused21>",
|
231 |
+
"lstrip": false,
|
232 |
+
"normalized": false,
|
233 |
+
"rstrip": false,
|
234 |
+
"single_word": false,
|
235 |
+
"special": false
|
236 |
+
},
|
237 |
+
"29": {
|
238 |
+
"content": "<unused22>",
|
239 |
+
"lstrip": false,
|
240 |
+
"normalized": false,
|
241 |
+
"rstrip": false,
|
242 |
+
"single_word": false,
|
243 |
+
"special": false
|
244 |
+
},
|
245 |
+
"30": {
|
246 |
+
"content": "<unused23>",
|
247 |
+
"lstrip": false,
|
248 |
+
"normalized": false,
|
249 |
+
"rstrip": false,
|
250 |
+
"single_word": false,
|
251 |
+
"special": false
|
252 |
+
},
|
253 |
+
"31": {
|
254 |
+
"content": "<unused24>",
|
255 |
+
"lstrip": false,
|
256 |
+
"normalized": false,
|
257 |
+
"rstrip": false,
|
258 |
+
"single_word": false,
|
259 |
+
"special": false
|
260 |
+
},
|
261 |
+
"32": {
|
262 |
+
"content": "<unused25>",
|
263 |
+
"lstrip": false,
|
264 |
+
"normalized": false,
|
265 |
+
"rstrip": false,
|
266 |
+
"single_word": false,
|
267 |
+
"special": false
|
268 |
+
},
|
269 |
+
"33": {
|
270 |
+
"content": "<unused26>",
|
271 |
+
"lstrip": false,
|
272 |
+
"normalized": false,
|
273 |
+
"rstrip": false,
|
274 |
+
"single_word": false,
|
275 |
+
"special": false
|
276 |
+
},
|
277 |
+
"34": {
|
278 |
+
"content": "<unused27>",
|
279 |
+
"lstrip": false,
|
280 |
+
"normalized": false,
|
281 |
+
"rstrip": false,
|
282 |
+
"single_word": false,
|
283 |
+
"special": false
|
284 |
+
},
|
285 |
+
"35": {
|
286 |
+
"content": "<unused28>",
|
287 |
+
"lstrip": false,
|
288 |
+
"normalized": false,
|
289 |
+
"rstrip": false,
|
290 |
+
"single_word": false,
|
291 |
+
"special": false
|
292 |
+
},
|
293 |
+
"36": {
|
294 |
+
"content": "<unused29>",
|
295 |
+
"lstrip": false,
|
296 |
+
"normalized": false,
|
297 |
+
"rstrip": false,
|
298 |
+
"single_word": false,
|
299 |
+
"special": false
|
300 |
+
},
|
301 |
+
"37": {
|
302 |
+
"content": "<unused30>",
|
303 |
+
"lstrip": false,
|
304 |
+
"normalized": false,
|
305 |
+
"rstrip": false,
|
306 |
+
"single_word": false,
|
307 |
+
"special": false
|
308 |
+
},
|
309 |
+
"38": {
|
310 |
+
"content": "<unused31>",
|
311 |
+
"lstrip": false,
|
312 |
+
"normalized": false,
|
313 |
+
"rstrip": false,
|
314 |
+
"single_word": false,
|
315 |
+
"special": false
|
316 |
+
},
|
317 |
+
"39": {
|
318 |
+
"content": "<unused32>",
|
319 |
+
"lstrip": false,
|
320 |
+
"normalized": false,
|
321 |
+
"rstrip": false,
|
322 |
+
"single_word": false,
|
323 |
+
"special": false
|
324 |
+
},
|
325 |
+
"40": {
|
326 |
+
"content": "<unused33>",
|
327 |
+
"lstrip": false,
|
328 |
+
"normalized": false,
|
329 |
+
"rstrip": false,
|
330 |
+
"single_word": false,
|
331 |
+
"special": false
|
332 |
+
},
|
333 |
+
"41": {
|
334 |
+
"content": "<unused34>",
|
335 |
+
"lstrip": false,
|
336 |
+
"normalized": false,
|
337 |
+
"rstrip": false,
|
338 |
+
"single_word": false,
|
339 |
+
"special": false
|
340 |
+
},
|
341 |
+
"42": {
|
342 |
+
"content": "<unused35>",
|
343 |
+
"lstrip": false,
|
344 |
+
"normalized": false,
|
345 |
+
"rstrip": false,
|
346 |
+
"single_word": false,
|
347 |
+
"special": false
|
348 |
+
},
|
349 |
+
"43": {
|
350 |
+
"content": "<unused36>",
|
351 |
+
"lstrip": false,
|
352 |
+
"normalized": false,
|
353 |
+
"rstrip": false,
|
354 |
+
"single_word": false,
|
355 |
+
"special": false
|
356 |
+
},
|
357 |
+
"44": {
|
358 |
+
"content": "<unused37>",
|
359 |
+
"lstrip": false,
|
360 |
+
"normalized": false,
|
361 |
+
"rstrip": false,
|
362 |
+
"single_word": false,
|
363 |
+
"special": false
|
364 |
+
},
|
365 |
+
"45": {
|
366 |
+
"content": "<unused38>",
|
367 |
+
"lstrip": false,
|
368 |
+
"normalized": false,
|
369 |
+
"rstrip": false,
|
370 |
+
"single_word": false,
|
371 |
+
"special": false
|
372 |
+
},
|
373 |
+
"46": {
|
374 |
+
"content": "<unused39>",
|
375 |
+
"lstrip": false,
|
376 |
+
"normalized": false,
|
377 |
+
"rstrip": false,
|
378 |
+
"single_word": false,
|
379 |
+
"special": false
|
380 |
+
},
|
381 |
+
"47": {
|
382 |
+
"content": "<unused40>",
|
383 |
+
"lstrip": false,
|
384 |
+
"normalized": false,
|
385 |
+
"rstrip": false,
|
386 |
+
"single_word": false,
|
387 |
+
"special": false
|
388 |
+
},
|
389 |
+
"48": {
|
390 |
+
"content": "<unused41>",
|
391 |
+
"lstrip": false,
|
392 |
+
"normalized": false,
|
393 |
+
"rstrip": false,
|
394 |
+
"single_word": false,
|
395 |
+
"special": false
|
396 |
+
},
|
397 |
+
"49": {
|
398 |
+
"content": "<unused42>",
|
399 |
+
"lstrip": false,
|
400 |
+
"normalized": false,
|
401 |
+
"rstrip": false,
|
402 |
+
"single_word": false,
|
403 |
+
"special": false
|
404 |
+
},
|
405 |
+
"50": {
|
406 |
+
"content": "<unused43>",
|
407 |
+
"lstrip": false,
|
408 |
+
"normalized": false,
|
409 |
+
"rstrip": false,
|
410 |
+
"single_word": false,
|
411 |
+
"special": false
|
412 |
+
},
|
413 |
+
"51": {
|
414 |
+
"content": "<unused44>",
|
415 |
+
"lstrip": false,
|
416 |
+
"normalized": false,
|
417 |
+
"rstrip": false,
|
418 |
+
"single_word": false,
|
419 |
+
"special": false
|
420 |
+
},
|
421 |
+
"52": {
|
422 |
+
"content": "<unused45>",
|
423 |
+
"lstrip": false,
|
424 |
+
"normalized": false,
|
425 |
+
"rstrip": false,
|
426 |
+
"single_word": false,
|
427 |
+
"special": false
|
428 |
+
},
|
429 |
+
"53": {
|
430 |
+
"content": "<unused46>",
|
431 |
+
"lstrip": false,
|
432 |
+
"normalized": false,
|
433 |
+
"rstrip": false,
|
434 |
+
"single_word": false,
|
435 |
+
"special": false
|
436 |
+
},
|
437 |
+
"54": {
|
438 |
+
"content": "<unused47>",
|
439 |
+
"lstrip": false,
|
440 |
+
"normalized": false,
|
441 |
+
"rstrip": false,
|
442 |
+
"single_word": false,
|
443 |
+
"special": false
|
444 |
+
},
|
445 |
+
"55": {
|
446 |
+
"content": "<unused48>",
|
447 |
+
"lstrip": false,
|
448 |
+
"normalized": false,
|
449 |
+
"rstrip": false,
|
450 |
+
"single_word": false,
|
451 |
+
"special": false
|
452 |
+
},
|
453 |
+
"56": {
|
454 |
+
"content": "<unused49>",
|
455 |
+
"lstrip": false,
|
456 |
+
"normalized": false,
|
457 |
+
"rstrip": false,
|
458 |
+
"single_word": false,
|
459 |
+
"special": false
|
460 |
+
},
|
461 |
+
"57": {
|
462 |
+
"content": "<unused50>",
|
463 |
+
"lstrip": false,
|
464 |
+
"normalized": false,
|
465 |
+
"rstrip": false,
|
466 |
+
"single_word": false,
|
467 |
+
"special": false
|
468 |
+
},
|
469 |
+
"58": {
|
470 |
+
"content": "<unused51>",
|
471 |
+
"lstrip": false,
|
472 |
+
"normalized": false,
|
473 |
+
"rstrip": false,
|
474 |
+
"single_word": false,
|
475 |
+
"special": false
|
476 |
+
},
|
477 |
+
"59": {
|
478 |
+
"content": "<unused52>",
|
479 |
+
"lstrip": false,
|
480 |
+
"normalized": false,
|
481 |
+
"rstrip": false,
|
482 |
+
"single_word": false,
|
483 |
+
"special": false
|
484 |
+
},
|
485 |
+
"60": {
|
486 |
+
"content": "<unused53>",
|
487 |
+
"lstrip": false,
|
488 |
+
"normalized": false,
|
489 |
+
"rstrip": false,
|
490 |
+
"single_word": false,
|
491 |
+
"special": false
|
492 |
+
},
|
493 |
+
"61": {
|
494 |
+
"content": "<unused54>",
|
495 |
+
"lstrip": false,
|
496 |
+
"normalized": false,
|
497 |
+
"rstrip": false,
|
498 |
+
"single_word": false,
|
499 |
+
"special": false
|
500 |
+
},
|
501 |
+
"62": {
|
502 |
+
"content": "<unused55>",
|
503 |
+
"lstrip": false,
|
504 |
+
"normalized": false,
|
505 |
+
"rstrip": false,
|
506 |
+
"single_word": false,
|
507 |
+
"special": false
|
508 |
+
},
|
509 |
+
"63": {
|
510 |
+
"content": "<unused56>",
|
511 |
+
"lstrip": false,
|
512 |
+
"normalized": false,
|
513 |
+
"rstrip": false,
|
514 |
+
"single_word": false,
|
515 |
+
"special": false
|
516 |
+
},
|
517 |
+
"64": {
|
518 |
+
"content": "<unused57>",
|
519 |
+
"lstrip": false,
|
520 |
+
"normalized": false,
|
521 |
+
"rstrip": false,
|
522 |
+
"single_word": false,
|
523 |
+
"special": false
|
524 |
+
},
|
525 |
+
"65": {
|
526 |
+
"content": "<unused58>",
|
527 |
+
"lstrip": false,
|
528 |
+
"normalized": false,
|
529 |
+
"rstrip": false,
|
530 |
+
"single_word": false,
|
531 |
+
"special": false
|
532 |
+
},
|
533 |
+
"66": {
|
534 |
+
"content": "<unused59>",
|
535 |
+
"lstrip": false,
|
536 |
+
"normalized": false,
|
537 |
+
"rstrip": false,
|
538 |
+
"single_word": false,
|
539 |
+
"special": false
|
540 |
+
},
|
541 |
+
"67": {
|
542 |
+
"content": "<unused60>",
|
543 |
+
"lstrip": false,
|
544 |
+
"normalized": false,
|
545 |
+
"rstrip": false,
|
546 |
+
"single_word": false,
|
547 |
+
"special": false
|
548 |
+
},
|
549 |
+
"68": {
|
550 |
+
"content": "<unused61>",
|
551 |
+
"lstrip": false,
|
552 |
+
"normalized": false,
|
553 |
+
"rstrip": false,
|
554 |
+
"single_word": false,
|
555 |
+
"special": false
|
556 |
+
},
|
557 |
+
"69": {
|
558 |
+
"content": "<unused62>",
|
559 |
+
"lstrip": false,
|
560 |
+
"normalized": false,
|
561 |
+
"rstrip": false,
|
562 |
+
"single_word": false,
|
563 |
+
"special": false
|
564 |
+
},
|
565 |
+
"70": {
|
566 |
+
"content": "<unused63>",
|
567 |
+
"lstrip": false,
|
568 |
+
"normalized": false,
|
569 |
+
"rstrip": false,
|
570 |
+
"single_word": false,
|
571 |
+
"special": false
|
572 |
+
},
|
573 |
+
"71": {
|
574 |
+
"content": "<unused64>",
|
575 |
+
"lstrip": false,
|
576 |
+
"normalized": false,
|
577 |
+
"rstrip": false,
|
578 |
+
"single_word": false,
|
579 |
+
"special": false
|
580 |
+
},
|
581 |
+
"72": {
|
582 |
+
"content": "<unused65>",
|
583 |
+
"lstrip": false,
|
584 |
+
"normalized": false,
|
585 |
+
"rstrip": false,
|
586 |
+
"single_word": false,
|
587 |
+
"special": false
|
588 |
+
},
|
589 |
+
"73": {
|
590 |
+
"content": "<unused66>",
|
591 |
+
"lstrip": false,
|
592 |
+
"normalized": false,
|
593 |
+
"rstrip": false,
|
594 |
+
"single_word": false,
|
595 |
+
"special": false
|
596 |
+
},
|
597 |
+
"74": {
|
598 |
+
"content": "<unused67>",
|
599 |
+
"lstrip": false,
|
600 |
+
"normalized": false,
|
601 |
+
"rstrip": false,
|
602 |
+
"single_word": false,
|
603 |
+
"special": false
|
604 |
+
},
|
605 |
+
"75": {
|
606 |
+
"content": "<unused68>",
|
607 |
+
"lstrip": false,
|
608 |
+
"normalized": false,
|
609 |
+
"rstrip": false,
|
610 |
+
"single_word": false,
|
611 |
+
"special": false
|
612 |
+
},
|
613 |
+
"76": {
|
614 |
+
"content": "<unused69>",
|
615 |
+
"lstrip": false,
|
616 |
+
"normalized": false,
|
617 |
+
"rstrip": false,
|
618 |
+
"single_word": false,
|
619 |
+
"special": false
|
620 |
+
},
|
621 |
+
"77": {
|
622 |
+
"content": "<unused70>",
|
623 |
+
"lstrip": false,
|
624 |
+
"normalized": false,
|
625 |
+
"rstrip": false,
|
626 |
+
"single_word": false,
|
627 |
+
"special": false
|
628 |
+
},
|
629 |
+
"78": {
|
630 |
+
"content": "<unused71>",
|
631 |
+
"lstrip": false,
|
632 |
+
"normalized": false,
|
633 |
+
"rstrip": false,
|
634 |
+
"single_word": false,
|
635 |
+
"special": false
|
636 |
+
},
|
637 |
+
"79": {
|
638 |
+
"content": "<unused72>",
|
639 |
+
"lstrip": false,
|
640 |
+
"normalized": false,
|
641 |
+
"rstrip": false,
|
642 |
+
"single_word": false,
|
643 |
+
"special": false
|
644 |
+
},
|
645 |
+
"80": {
|
646 |
+
"content": "<unused73>",
|
647 |
+
"lstrip": false,
|
648 |
+
"normalized": false,
|
649 |
+
"rstrip": false,
|
650 |
+
"single_word": false,
|
651 |
+
"special": false
|
652 |
+
},
|
653 |
+
"81": {
|
654 |
+
"content": "<unused74>",
|
655 |
+
"lstrip": false,
|
656 |
+
"normalized": false,
|
657 |
+
"rstrip": false,
|
658 |
+
"single_word": false,
|
659 |
+
"special": false
|
660 |
+
},
|
661 |
+
"82": {
|
662 |
+
"content": "<unused75>",
|
663 |
+
"lstrip": false,
|
664 |
+
"normalized": false,
|
665 |
+
"rstrip": false,
|
666 |
+
"single_word": false,
|
667 |
+
"special": false
|
668 |
+
},
|
669 |
+
"83": {
|
670 |
+
"content": "<unused76>",
|
671 |
+
"lstrip": false,
|
672 |
+
"normalized": false,
|
673 |
+
"rstrip": false,
|
674 |
+
"single_word": false,
|
675 |
+
"special": false
|
676 |
+
},
|
677 |
+
"84": {
|
678 |
+
"content": "<unused77>",
|
679 |
+
"lstrip": false,
|
680 |
+
"normalized": false,
|
681 |
+
"rstrip": false,
|
682 |
+
"single_word": false,
|
683 |
+
"special": false
|
684 |
+
},
|
685 |
+
"85": {
|
686 |
+
"content": "<unused78>",
|
687 |
+
"lstrip": false,
|
688 |
+
"normalized": false,
|
689 |
+
"rstrip": false,
|
690 |
+
"single_word": false,
|
691 |
+
"special": false
|
692 |
+
},
|
693 |
+
"86": {
|
694 |
+
"content": "<unused79>",
|
695 |
+
"lstrip": false,
|
696 |
+
"normalized": false,
|
697 |
+
"rstrip": false,
|
698 |
+
"single_word": false,
|
699 |
+
"special": false
|
700 |
+
},
|
701 |
+
"87": {
|
702 |
+
"content": "<unused80>",
|
703 |
+
"lstrip": false,
|
704 |
+
"normalized": false,
|
705 |
+
"rstrip": false,
|
706 |
+
"single_word": false,
|
707 |
+
"special": false
|
708 |
+
},
|
709 |
+
"88": {
|
710 |
+
"content": "<unused81>",
|
711 |
+
"lstrip": false,
|
712 |
+
"normalized": false,
|
713 |
+
"rstrip": false,
|
714 |
+
"single_word": false,
|
715 |
+
"special": false
|
716 |
+
},
|
717 |
+
"89": {
|
718 |
+
"content": "<unused82>",
|
719 |
+
"lstrip": false,
|
720 |
+
"normalized": false,
|
721 |
+
"rstrip": false,
|
722 |
+
"single_word": false,
|
723 |
+
"special": false
|
724 |
+
},
|
725 |
+
"90": {
|
726 |
+
"content": "<unused83>",
|
727 |
+
"lstrip": false,
|
728 |
+
"normalized": false,
|
729 |
+
"rstrip": false,
|
730 |
+
"single_word": false,
|
731 |
+
"special": false
|
732 |
+
},
|
733 |
+
"91": {
|
734 |
+
"content": "<unused84>",
|
735 |
+
"lstrip": false,
|
736 |
+
"normalized": false,
|
737 |
+
"rstrip": false,
|
738 |
+
"single_word": false,
|
739 |
+
"special": false
|
740 |
+
},
|
741 |
+
"92": {
|
742 |
+
"content": "<unused85>",
|
743 |
+
"lstrip": false,
|
744 |
+
"normalized": false,
|
745 |
+
"rstrip": false,
|
746 |
+
"single_word": false,
|
747 |
+
"special": false
|
748 |
+
},
|
749 |
+
"93": {
|
750 |
+
"content": "<unused86>",
|
751 |
+
"lstrip": false,
|
752 |
+
"normalized": false,
|
753 |
+
"rstrip": false,
|
754 |
+
"single_word": false,
|
755 |
+
"special": false
|
756 |
+
},
|
757 |
+
"94": {
|
758 |
+
"content": "<unused87>",
|
759 |
+
"lstrip": false,
|
760 |
+
"normalized": false,
|
761 |
+
"rstrip": false,
|
762 |
+
"single_word": false,
|
763 |
+
"special": false
|
764 |
+
},
|
765 |
+
"95": {
|
766 |
+
"content": "<unused88>",
|
767 |
+
"lstrip": false,
|
768 |
+
"normalized": false,
|
769 |
+
"rstrip": false,
|
770 |
+
"single_word": false,
|
771 |
+
"special": false
|
772 |
+
},
|
773 |
+
"96": {
|
774 |
+
"content": "<unused89>",
|
775 |
+
"lstrip": false,
|
776 |
+
"normalized": false,
|
777 |
+
"rstrip": false,
|
778 |
+
"single_word": false,
|
779 |
+
"special": false
|
780 |
+
},
|
781 |
+
"97": {
|
782 |
+
"content": "<unused90>",
|
783 |
+
"lstrip": false,
|
784 |
+
"normalized": false,
|
785 |
+
"rstrip": false,
|
786 |
+
"single_word": false,
|
787 |
+
"special": false
|
788 |
+
},
|
789 |
+
"98": {
|
790 |
+
"content": "<unused91>",
|
791 |
+
"lstrip": false,
|
792 |
+
"normalized": false,
|
793 |
+
"rstrip": false,
|
794 |
+
"single_word": false,
|
795 |
+
"special": false
|
796 |
+
},
|
797 |
+
"99": {
|
798 |
+
"content": "<unused92>",
|
799 |
+
"lstrip": false,
|
800 |
+
"normalized": false,
|
801 |
+
"rstrip": false,
|
802 |
+
"single_word": false,
|
803 |
+
"special": false
|
804 |
+
},
|
805 |
+
"100": {
|
806 |
+
"content": "<unused93>",
|
807 |
+
"lstrip": false,
|
808 |
+
"normalized": false,
|
809 |
+
"rstrip": false,
|
810 |
+
"single_word": false,
|
811 |
+
"special": false
|
812 |
+
},
|
813 |
+
"101": {
|
814 |
+
"content": "<unused94>",
|
815 |
+
"lstrip": false,
|
816 |
+
"normalized": false,
|
817 |
+
"rstrip": false,
|
818 |
+
"single_word": false,
|
819 |
+
"special": false
|
820 |
+
},
|
821 |
+
"102": {
|
822 |
+
"content": "<unused95>",
|
823 |
+
"lstrip": false,
|
824 |
+
"normalized": false,
|
825 |
+
"rstrip": false,
|
826 |
+
"single_word": false,
|
827 |
+
"special": false
|
828 |
+
},
|
829 |
+
"103": {
|
830 |
+
"content": "<unused96>",
|
831 |
+
"lstrip": false,
|
832 |
+
"normalized": false,
|
833 |
+
"rstrip": false,
|
834 |
+
"single_word": false,
|
835 |
+
"special": false
|
836 |
+
},
|
837 |
+
"104": {
|
838 |
+
"content": "<unused97>",
|
839 |
+
"lstrip": false,
|
840 |
+
"normalized": false,
|
841 |
+
"rstrip": false,
|
842 |
+
"single_word": false,
|
843 |
+
"special": false
|
844 |
+
},
|
845 |
+
"105": {
|
846 |
+
"content": "<unused98>",
|
847 |
+
"lstrip": false,
|
848 |
+
"normalized": false,
|
849 |
+
"rstrip": false,
|
850 |
+
"single_word": false,
|
851 |
+
"special": false
|
852 |
+
},
|
853 |
+
"106": {
|
854 |
+
"content": "<start_of_turn>",
|
855 |
+
"lstrip": false,
|
856 |
+
"normalized": false,
|
857 |
+
"rstrip": false,
|
858 |
+
"single_word": false,
|
859 |
+
"special": true
|
860 |
+
},
|
861 |
+
"107": {
|
862 |
+
"content": "<end_of_turn>",
|
863 |
+
"lstrip": false,
|
864 |
+
"normalized": false,
|
865 |
+
"rstrip": false,
|
866 |
+
"single_word": false,
|
867 |
+
"special": true
|
868 |
+
},
|
869 |
+
"108": {
|
870 |
+
"content": "\n",
|
871 |
+
"lstrip": false,
|
872 |
+
"normalized": false,
|
873 |
+
"rstrip": false,
|
874 |
+
"single_word": false,
|
875 |
+
"special": false
|
876 |
+
},
|
877 |
+
"109": {
|
878 |
+
"content": "\n\n",
|
879 |
+
"lstrip": false,
|
880 |
+
"normalized": false,
|
881 |
+
"rstrip": false,
|
882 |
+
"single_word": false,
|
883 |
+
"special": false
|
884 |
+
},
|
885 |
+
"110": {
|
886 |
+
"content": "\n\n\n",
|
887 |
+
"lstrip": false,
|
888 |
+
"normalized": false,
|
889 |
+
"rstrip": false,
|
890 |
+
"single_word": false,
|
891 |
+
"special": false
|
892 |
+
},
|
893 |
+
"111": {
|
894 |
+
"content": "\n\n\n\n",
|
895 |
+
"lstrip": false,
|
896 |
+
"normalized": false,
|
897 |
+
"rstrip": false,
|
898 |
+
"single_word": false,
|
899 |
+
"special": false
|
900 |
+
},
|
901 |
+
"112": {
|
902 |
+
"content": "\n\n\n\n\n",
|
903 |
+
"lstrip": false,
|
904 |
+
"normalized": false,
|
905 |
+
"rstrip": false,
|
906 |
+
"single_word": false,
|
907 |
+
"special": false
|
908 |
+
},
|
909 |
+
"113": {
|
910 |
+
"content": "\n\n\n\n\n\n",
|
911 |
+
"lstrip": false,
|
912 |
+
"normalized": false,
|
913 |
+
"rstrip": false,
|
914 |
+
"single_word": false,
|
915 |
+
"special": false
|
916 |
+
},
|
917 |
+
"114": {
|
918 |
+
"content": "\n\n\n\n\n\n\n",
|
919 |
+
"lstrip": false,
|
920 |
+
"normalized": false,
|
921 |
+
"rstrip": false,
|
922 |
+
"single_word": false,
|
923 |
+
"special": false
|
924 |
+
},
|
925 |
+
"115": {
|
926 |
+
"content": "\n\n\n\n\n\n\n\n",
|
927 |
+
"lstrip": false,
|
928 |
+
"normalized": false,
|
929 |
+
"rstrip": false,
|
930 |
+
"single_word": false,
|
931 |
+
"special": false
|
932 |
+
},
|
933 |
+
"116": {
|
934 |
+
"content": "\n\n\n\n\n\n\n\n\n",
|
935 |
+
"lstrip": false,
|
936 |
+
"normalized": false,
|
937 |
+
"rstrip": false,
|
938 |
+
"single_word": false,
|
939 |
+
"special": false
|
940 |
+
},
|
941 |
+
"117": {
|
942 |
+
"content": "\n\n\n\n\n\n\n\n\n\n",
|
943 |
+
"lstrip": false,
|
944 |
+
"normalized": false,
|
945 |
+
"rstrip": false,
|
946 |
+
"single_word": false,
|
947 |
+
"special": false
|
948 |
+
},
|
949 |
+
"118": {
|
950 |
+
"content": "\n\n\n\n\n\n\n\n\n\n\n",
|
951 |
+
"lstrip": false,
|
952 |
+
"normalized": false,
|
953 |
+
"rstrip": false,
|
954 |
+
"single_word": false,
|
955 |
+
"special": false
|
956 |
+
},
|
957 |
+
"119": {
|
958 |
+
"content": "\n\n\n\n\n\n\n\n\n\n\n\n",
|
959 |
+
"lstrip": false,
|
960 |
+
"normalized": false,
|
961 |
+
"rstrip": false,
|
962 |
+
"single_word": false,
|
963 |
+
"special": false
|
964 |
+
},
|
965 |
+
"120": {
|
966 |
+
"content": "\n\n\n\n\n\n\n\n\n\n\n\n\n",
|
967 |
+
"lstrip": false,
|
968 |
+
"normalized": false,
|
969 |
+
"rstrip": false,
|
970 |
+
"single_word": false,
|
971 |
+
"special": false
|
972 |
+
},
|
973 |
+
"121": {
|
974 |
+
"content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
|
975 |
+
"lstrip": false,
|
976 |
+
"normalized": false,
|
977 |
+
"rstrip": false,
|
978 |
+
"single_word": false,
|
979 |
+
"special": false
|
980 |
+
},
|
981 |
+
"122": {
|
982 |
+
"content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
|
983 |
+
"lstrip": false,
|
984 |
+
"normalized": false,
|
985 |
+
"rstrip": false,
|
986 |
+
"single_word": false,
|
987 |
+
"special": false
|
988 |
+
},
|
989 |
+
"123": {
|
990 |
+
"content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
|
991 |
+
"lstrip": false,
|
992 |
+
"normalized": false,
|
993 |
+
"rstrip": false,
|
994 |
+
"single_word": false,
|
995 |
+
"special": false
|
996 |
+
},
|
997 |
+
"124": {
|
998 |
+
"content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
|
999 |
+
"lstrip": false,
|
1000 |
+
"normalized": false,
|
1001 |
+
"rstrip": false,
|
1002 |
+
"single_word": false,
|
1003 |
+
"special": false
|
1004 |
+
},
|
1005 |
+
"125": {
|
1006 |
+
"content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
|
1007 |
+
"lstrip": false,
|
1008 |
+
"normalized": false,
|
1009 |
+
"rstrip": false,
|
1010 |
+
"single_word": false,
|
1011 |
+
"special": false
|
1012 |
+
},
|
1013 |
+
"126": {
|
1014 |
+
"content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
|
1015 |
+
"lstrip": false,
|
1016 |
+
"normalized": false,
|
1017 |
+
"rstrip": false,
|
1018 |
+
"single_word": false,
|
1019 |
+
"special": false
|
1020 |
+
},
|
1021 |
+
"127": {
|
1022 |
+
"content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
|
1023 |
+
"lstrip": false,
|
1024 |
+
"normalized": false,
|
1025 |
+
"rstrip": false,
|
1026 |
+
"single_word": false,
|
1027 |
+
"special": false
|
1028 |
+
},
|
1029 |
+
"128": {
|
1030 |
+
"content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
|
1031 |
+
"lstrip": false,
|
1032 |
+
"normalized": false,
|
1033 |
+
"rstrip": false,
|
1034 |
+
"single_word": false,
|
1035 |
+
"special": false
|
1036 |
+
},
|
1037 |
+
"129": {
|
1038 |
+
"content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
|
1039 |
+
"lstrip": false,
|
1040 |
+
"normalized": false,
|
1041 |
+
"rstrip": false,
|
1042 |
+
"single_word": false,
|
1043 |
+
"special": false
|
1044 |
+
},
|
1045 |
+
"130": {
|
1046 |
+
"content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
|
1047 |
+
"lstrip": false,
|
1048 |
+
"normalized": false,
|
1049 |
+
"rstrip": false,
|
1050 |
+
"single_word": false,
|
1051 |
+
"special": false
|
1052 |
+
},
|
1053 |
+
"131": {
|
1054 |
+
"content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
|
1055 |
+
"lstrip": false,
|
1056 |
+
"normalized": false,
|
1057 |
+
"rstrip": false,
|
1058 |
+
"single_word": false,
|
1059 |
+
"special": false
|
1060 |
+
},
|
1061 |
+
"132": {
|
1062 |
+
"content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
|
1063 |
+
"lstrip": false,
|
1064 |
+
"normalized": false,
|
1065 |
+
"rstrip": false,
|
1066 |
+
"single_word": false,
|
1067 |
+
"special": false
|
1068 |
+
},
|
1069 |
+
"133": {
|
1070 |
+
"content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
|
1071 |
+
"lstrip": false,
|
1072 |
+
"normalized": false,
|
1073 |
+
"rstrip": false,
|
1074 |
+
"single_word": false,
|
1075 |
+
"special": false
|
1076 |
+
},
|
1077 |
+
"134": {
|
1078 |
+
"content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
|
1079 |
+
"lstrip": false,
|
1080 |
+
"normalized": false,
|
1081 |
+
"rstrip": false,
|
1082 |
+
"single_word": false,
|
1083 |
+
"special": false
|
1084 |
+
},
|
1085 |
+
"135": {
|
1086 |
+
"content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
|
1087 |
+
"lstrip": false,
|
1088 |
+
"normalized": false,
|
1089 |
+
"rstrip": false,
|
1090 |
+
"single_word": false,
|
1091 |
+
"special": false
|
1092 |
+
},
|
1093 |
+
"136": {
|
1094 |
+
"content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
|
1095 |
+
"lstrip": false,
|
1096 |
+
"normalized": false,
|
1097 |
+
"rstrip": false,
|
1098 |
+
"single_word": false,
|
1099 |
+
"special": false
|
1100 |
+
},
|
1101 |
+
"137": {
|
1102 |
+
"content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
|
1103 |
+
"lstrip": false,
|
1104 |
+
"normalized": false,
|
1105 |
+
"rstrip": false,
|
1106 |
+
"single_word": false,
|
1107 |
+
"special": false
|
1108 |
+
},
|
1109 |
+
"138": {
|
1110 |
+
"content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
|
1111 |
+
"lstrip": false,
|
1112 |
+
"normalized": false,
|
1113 |
+
"rstrip": false,
|
1114 |
+
"single_word": false,
|
1115 |
+
"special": false
|
1116 |
+
},
|
1117 |
+
"139": {
|
1118 |
+
"content": "▁▁",
|
1119 |
+
"lstrip": false,
|
1120 |
+
"normalized": false,
|
1121 |
+
"rstrip": false,
|
1122 |
+
"single_word": false,
|
1123 |
+
"special": false
|
1124 |
+
},
|
1125 |
+
"140": {
|
1126 |
+
"content": "▁▁▁",
|
1127 |
+
"lstrip": false,
|
1128 |
+
"normalized": false,
|
1129 |
+
"rstrip": false,
|
1130 |
+
"single_word": false,
|
1131 |
+
"special": false
|
1132 |
+
},
|
1133 |
+
"141": {
|
1134 |
+
"content": "▁▁▁▁",
|
1135 |
+
"lstrip": false,
|
1136 |
+
"normalized": false,
|
1137 |
+
"rstrip": false,
|
1138 |
+
"single_word": false,
|
1139 |
+
"special": false
|
1140 |
+
},
|
1141 |
+
"142": {
|
1142 |
+
"content": "▁▁▁▁▁",
|
1143 |
+
"lstrip": false,
|
1144 |
+
"normalized": false,
|
1145 |
+
"rstrip": false,
|
1146 |
+
"single_word": false,
|
1147 |
+
"special": false
|
1148 |
+
},
|
1149 |
+
"143": {
|
1150 |
+
"content": "▁▁▁▁▁▁",
|
1151 |
+
"lstrip": false,
|
1152 |
+
"normalized": false,
|
1153 |
+
"rstrip": false,
|
1154 |
+
"single_word": false,
|
1155 |
+
"special": false
|
1156 |
+
},
|
1157 |
+
"144": {
|
1158 |
+
"content": "▁▁▁▁▁▁▁",
|
1159 |
+
"lstrip": false,
|
1160 |
+
"normalized": false,
|
1161 |
+
"rstrip": false,
|
1162 |
+
"single_word": false,
|
1163 |
+
"special": false
|
1164 |
+
},
|
1165 |
+
"145": {
|
1166 |
+
"content": "▁▁▁▁▁▁▁▁",
|
1167 |
+
"lstrip": false,
|
1168 |
+
"normalized": false,
|
1169 |
+
"rstrip": false,
|
1170 |
+
"single_word": false,
|
1171 |
+
"special": false
|
1172 |
+
},
|
1173 |
+
"146": {
|
1174 |
+
"content": "▁▁▁▁▁▁▁▁▁",
|
1175 |
+
"lstrip": false,
|
1176 |
+
"normalized": false,
|
1177 |
+
"rstrip": false,
|
1178 |
+
"single_word": false,
|
1179 |
+
"special": false
|
1180 |
+
},
|
1181 |
+
"147": {
|
1182 |
+
"content": "▁▁▁▁▁▁▁▁▁▁",
|
1183 |
+
"lstrip": false,
|
1184 |
+
"normalized": false,
|
1185 |
+
"rstrip": false,
|
1186 |
+
"single_word": false,
|
1187 |
+
"special": false
|
1188 |
+
},
|
1189 |
+
"148": {
|
1190 |
+
"content": "▁▁▁▁▁▁▁▁▁▁▁",
|
1191 |
+
"lstrip": false,
|
1192 |
+
"normalized": false,
|
1193 |
+
"rstrip": false,
|
1194 |
+
"single_word": false,
|
1195 |
+
"special": false
|
1196 |
+
},
|
1197 |
+
"149": {
|
1198 |
+
"content": "▁▁▁▁▁▁▁▁▁▁▁▁",
|
1199 |
+
"lstrip": false,
|
1200 |
+
"normalized": false,
|
1201 |
+
"rstrip": false,
|
1202 |
+
"single_word": false,
|
1203 |
+
"special": false
|
1204 |
+
},
|
1205 |
+
"150": {
|
1206 |
+
"content": "▁▁▁▁▁▁▁▁▁▁▁▁▁",
|
1207 |
+
"lstrip": false,
|
1208 |
+
"normalized": false,
|
1209 |
+
"rstrip": false,
|
1210 |
+
"single_word": false,
|
1211 |
+
"special": false
|
1212 |
+
},
|
1213 |
+
"151": {
|
1214 |
+
"content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
|
1215 |
+
"lstrip": false,
|
1216 |
+
"normalized": false,
|
1217 |
+
"rstrip": false,
|
1218 |
+
"single_word": false,
|
1219 |
+
"special": false
|
1220 |
+
},
|
1221 |
+
"152": {
|
1222 |
+
"content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
|
1223 |
+
"lstrip": false,
|
1224 |
+
"normalized": false,
|
1225 |
+
"rstrip": false,
|
1226 |
+
"single_word": false,
|
1227 |
+
"special": false
|
1228 |
+
},
|
1229 |
+
"153": {
|
1230 |
+
"content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
|
1231 |
+
"lstrip": false,
|
1232 |
+
"normalized": false,
|
1233 |
+
"rstrip": false,
|
1234 |
+
"single_word": false,
|
1235 |
+
"special": false
|
1236 |
+
},
|
1237 |
+
"154": {
|
1238 |
+
"content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
|
1239 |
+
"lstrip": false,
|
1240 |
+
"normalized": false,
|
1241 |
+
"rstrip": false,
|
1242 |
+
"single_word": false,
|
1243 |
+
"special": false
|
1244 |
+
},
|
1245 |
+
"155": {
|
1246 |
+
"content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
|
1247 |
+
"lstrip": false,
|
1248 |
+
"normalized": false,
|
1249 |
+
"rstrip": false,
|
1250 |
+
"single_word": false,
|
1251 |
+
"special": false
|
1252 |
+
},
|
1253 |
+
"156": {
|
1254 |
+
"content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
|
1255 |
+
"lstrip": false,
|
1256 |
+
"normalized": false,
|
1257 |
+
"rstrip": false,
|
1258 |
+
"single_word": false,
|
1259 |
+
"special": false
|
1260 |
+
},
|
1261 |
+
"157": {
|
1262 |
+
"content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
|
1263 |
+
"lstrip": false,
|
1264 |
+
"normalized": false,
|
1265 |
+
"rstrip": false,
|
1266 |
+
"single_word": false,
|
1267 |
+
"special": false
|
1268 |
+
},
|
1269 |
+
"158": {
|
1270 |
+
"content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
|
1271 |
+
"lstrip": false,
|
1272 |
+
"normalized": false,
|
1273 |
+
"rstrip": false,
|
1274 |
+
"single_word": false,
|
1275 |
+
"special": false
|
1276 |
+
},
|
1277 |
+
"159": {
|
1278 |
+
"content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
|
1279 |
+
"lstrip": false,
|
1280 |
+
"normalized": false,
|
1281 |
+
"rstrip": false,
|
1282 |
+
"single_word": false,
|
1283 |
+
"special": false
|
1284 |
+
},
|
1285 |
+
"160": {
|
1286 |
+
"content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
|
1287 |
+
"lstrip": false,
|
1288 |
+
"normalized": false,
|
1289 |
+
"rstrip": false,
|
1290 |
+
"single_word": false,
|
1291 |
+
"special": false
|
1292 |
+
},
|
1293 |
+
"161": {
|
1294 |
+
"content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
|
1295 |
+
"lstrip": false,
|
1296 |
+
"normalized": false,
|
1297 |
+
"rstrip": false,
|
1298 |
+
"single_word": false,
|
1299 |
+
"special": false
|
1300 |
+
},
|
1301 |
+
"162": {
|
1302 |
+
"content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
|
1303 |
+
"lstrip": false,
|
1304 |
+
"normalized": false,
|
1305 |
+
"rstrip": false,
|
1306 |
+
"single_word": false,
|
1307 |
+
"special": false
|
1308 |
+
},
|
1309 |
+
"163": {
|
1310 |
+
"content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
|
1311 |
+
"lstrip": false,
|
1312 |
+
"normalized": false,
|
1313 |
+
"rstrip": false,
|
1314 |
+
"single_word": false,
|
1315 |
+
"special": false
|
1316 |
+
},
|
1317 |
+
"164": {
|
1318 |
+
"content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
|
1319 |
+
"lstrip": false,
|
1320 |
+
"normalized": false,
|
1321 |
+
"rstrip": false,
|
1322 |
+
"single_word": false,
|
1323 |
+
"special": false
|
1324 |
+
},
|
1325 |
+
"165": {
|
1326 |
+
"content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
|
1327 |
+
"lstrip": false,
|
1328 |
+
"normalized": false,
|
1329 |
+
"rstrip": false,
|
1330 |
+
"single_word": false,
|
1331 |
+
"special": false
|
1332 |
+
},
|
1333 |
+
"166": {
|
1334 |
+
"content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
|
1335 |
+
"lstrip": false,
|
1336 |
+
"normalized": false,
|
1337 |
+
"rstrip": false,
|
1338 |
+
"single_word": false,
|
1339 |
+
"special": false
|
1340 |
+
},
|
1341 |
+
"167": {
|
1342 |
+
"content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
|
1343 |
+
"lstrip": false,
|
1344 |
+
"normalized": false,
|
1345 |
+
"rstrip": false,
|
1346 |
+
"single_word": false,
|
1347 |
+
"special": false
|
1348 |
+
},
|
1349 |
+
"168": {
|
1350 |
+
"content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
|
1351 |
+
"lstrip": false,
|
1352 |
+
"normalized": false,
|
1353 |
+
"rstrip": false,
|
1354 |
+
"single_word": false,
|
1355 |
+
"special": false
|
1356 |
+
},
|
1357 |
+
"169": {
|
1358 |
+
"content": "<table>",
|
1359 |
+
"lstrip": false,
|
1360 |
+
"normalized": false,
|
1361 |
+
"rstrip": false,
|
1362 |
+
"single_word": false,
|
1363 |
+
"special": false
|
1364 |
+
},
|
1365 |
+
"170": {
|
1366 |
+
"content": "<caption>",
|
1367 |
+
"lstrip": false,
|
1368 |
+
"normalized": false,
|
1369 |
+
"rstrip": false,
|
1370 |
+
"single_word": false,
|
1371 |
+
"special": false
|
1372 |
+
},
|
1373 |
+
"171": {
|
1374 |
+
"content": "<thead>",
|
1375 |
+
"lstrip": false,
|
1376 |
+
"normalized": false,
|
1377 |
+
"rstrip": false,
|
1378 |
+
"single_word": false,
|
1379 |
+
"special": false
|
1380 |
+
},
|
1381 |
+
"172": {
|
1382 |
+
"content": "<tbody>",
|
1383 |
+
"lstrip": false,
|
1384 |
+
"normalized": false,
|
1385 |
+
"rstrip": false,
|
1386 |
+
"single_word": false,
|
1387 |
+
"special": false
|
1388 |
+
},
|
1389 |
+
"173": {
|
1390 |
+
"content": "<tfoot>",
|
1391 |
+
"lstrip": false,
|
1392 |
+
"normalized": false,
|
1393 |
+
"rstrip": false,
|
1394 |
+
"single_word": false,
|
1395 |
+
"special": false
|
1396 |
+
},
|
1397 |
+
"174": {
|
1398 |
+
"content": "<tr>",
|
1399 |
+
"lstrip": false,
|
1400 |
+
"normalized": false,
|
1401 |
+
"rstrip": false,
|
1402 |
+
"single_word": false,
|
1403 |
+
"special": false
|
1404 |
+
},
|
1405 |
+
"175": {
|
1406 |
+
"content": "<th>",
|
1407 |
+
"lstrip": false,
|
1408 |
+
"normalized": false,
|
1409 |
+
"rstrip": false,
|
1410 |
+
"single_word": false,
|
1411 |
+
"special": false
|
1412 |
+
},
|
1413 |
+
"176": {
|
1414 |
+
"content": "<td>",
|
1415 |
+
"lstrip": false,
|
1416 |
+
"normalized": false,
|
1417 |
+
"rstrip": false,
|
1418 |
+
"single_word": false,
|
1419 |
+
"special": false
|
1420 |
+
},
|
1421 |
+
"177": {
|
1422 |
+
"content": "</table>",
|
1423 |
+
"lstrip": false,
|
1424 |
+
"normalized": false,
|
1425 |
+
"rstrip": false,
|
1426 |
+
"single_word": false,
|
1427 |
+
"special": false
|
1428 |
+
},
|
1429 |
+
"178": {
|
1430 |
+
"content": "</caption>",
|
1431 |
+
"lstrip": false,
|
1432 |
+
"normalized": false,
|
1433 |
+
"rstrip": false,
|
1434 |
+
"single_word": false,
|
1435 |
+
"special": false
|
1436 |
+
},
|
1437 |
+
"179": {
|
1438 |
+
"content": "</thead>",
|
1439 |
+
"lstrip": false,
|
1440 |
+
"normalized": false,
|
1441 |
+
"rstrip": false,
|
1442 |
+
"single_word": false,
|
1443 |
+
"special": false
|
1444 |
+
},
|
1445 |
+
"180": {
|
1446 |
+
"content": "</tbody>",
|
1447 |
+
"lstrip": false,
|
1448 |
+
"normalized": false,
|
1449 |
+
"rstrip": false,
|
1450 |
+
"single_word": false,
|
1451 |
+
"special": false
|
1452 |
+
},
|
1453 |
+
"181": {
|
1454 |
+
"content": "</tfoot>",
|
1455 |
+
"lstrip": false,
|
1456 |
+
"normalized": false,
|
1457 |
+
"rstrip": false,
|
1458 |
+
"single_word": false,
|
1459 |
+
"special": false
|
1460 |
+
},
|
1461 |
+
"182": {
|
1462 |
+
"content": "</tr>",
|
1463 |
+
"lstrip": false,
|
1464 |
+
"normalized": false,
|
1465 |
+
"rstrip": false,
|
1466 |
+
"single_word": false,
|
1467 |
+
"special": false
|
1468 |
+
},
|
1469 |
+
"183": {
|
1470 |
+
"content": "</th>",
|
1471 |
+
"lstrip": false,
|
1472 |
+
"normalized": false,
|
1473 |
+
"rstrip": false,
|
1474 |
+
"single_word": false,
|
1475 |
+
"special": false
|
1476 |
+
},
|
1477 |
+
"184": {
|
1478 |
+
"content": "</td>",
|
1479 |
+
"lstrip": false,
|
1480 |
+
"normalized": false,
|
1481 |
+
"rstrip": false,
|
1482 |
+
"single_word": false,
|
1483 |
+
"special": false
|
1484 |
+
},
|
1485 |
+
"185": {
|
1486 |
+
"content": "<h1>",
|
1487 |
+
"lstrip": false,
|
1488 |
+
"normalized": false,
|
1489 |
+
"rstrip": false,
|
1490 |
+
"single_word": false,
|
1491 |
+
"special": false
|
1492 |
+
},
|
1493 |
+
"186": {
|
1494 |
+
"content": "<h2>",
|
1495 |
+
"lstrip": false,
|
1496 |
+
"normalized": false,
|
1497 |
+
"rstrip": false,
|
1498 |
+
"single_word": false,
|
1499 |
+
"special": false
|
1500 |
+
},
|
1501 |
+
"187": {
|
1502 |
+
"content": "<h3>",
|
1503 |
+
"lstrip": false,
|
1504 |
+
"normalized": false,
|
1505 |
+
"rstrip": false,
|
1506 |
+
"single_word": false,
|
1507 |
+
"special": false
|
1508 |
+
},
|
1509 |
+
"188": {
|
1510 |
+
"content": "<h4>",
|
1511 |
+
"lstrip": false,
|
1512 |
+
"normalized": false,
|
1513 |
+
"rstrip": false,
|
1514 |
+
"single_word": false,
|
1515 |
+
"special": false
|
1516 |
+
},
|
1517 |
+
"189": {
|
1518 |
+
"content": "<h5>",
|
1519 |
+
"lstrip": false,
|
1520 |
+
"normalized": false,
|
1521 |
+
"rstrip": false,
|
1522 |
+
"single_word": false,
|
1523 |
+
"special": false
|
1524 |
+
},
|
1525 |
+
"190": {
|
1526 |
+
"content": "<h6>",
|
1527 |
+
"lstrip": false,
|
1528 |
+
"normalized": false,
|
1529 |
+
"rstrip": false,
|
1530 |
+
"single_word": false,
|
1531 |
+
"special": false
|
1532 |
+
},
|
1533 |
+
"191": {
|
1534 |
+
"content": "<blockquote>",
|
1535 |
+
"lstrip": false,
|
1536 |
+
"normalized": false,
|
1537 |
+
"rstrip": false,
|
1538 |
+
"single_word": false,
|
1539 |
+
"special": false
|
1540 |
+
},
|
1541 |
+
"192": {
|
1542 |
+
"content": "</h1>",
|
1543 |
+
"lstrip": false,
|
1544 |
+
"normalized": false,
|
1545 |
+
"rstrip": false,
|
1546 |
+
"single_word": false,
|
1547 |
+
"special": false
|
1548 |
+
},
|
1549 |
+
"193": {
|
1550 |
+
"content": "</h2>",
|
1551 |
+
"lstrip": false,
|
1552 |
+
"normalized": false,
|
1553 |
+
"rstrip": false,
|
1554 |
+
"single_word": false,
|
1555 |
+
"special": false
|
1556 |
+
},
|
1557 |
+
"194": {
|
1558 |
+
"content": "</h3>",
|
1559 |
+
"lstrip": false,
|
1560 |
+
"normalized": false,
|
1561 |
+
"rstrip": false,
|
1562 |
+
"single_word": false,
|
1563 |
+
"special": false
|
1564 |
+
},
|
1565 |
+
"195": {
|
1566 |
+
"content": "</h4>",
|
1567 |
+
"lstrip": false,
|
1568 |
+
"normalized": false,
|
1569 |
+
"rstrip": false,
|
1570 |
+
"single_word": false,
|
1571 |
+
"special": false
|
1572 |
+
},
|
1573 |
+
"196": {
|
1574 |
+
"content": "</h5>",
|
1575 |
+
"lstrip": false,
|
1576 |
+
"normalized": false,
|
1577 |
+
"rstrip": false,
|
1578 |
+
"single_word": false,
|
1579 |
+
"special": false
|
1580 |
+
},
|
1581 |
+
"197": {
|
1582 |
+
"content": "</h6>",
|
1583 |
+
"lstrip": false,
|
1584 |
+
"normalized": false,
|
1585 |
+
"rstrip": false,
|
1586 |
+
"single_word": false,
|
1587 |
+
"special": false
|
1588 |
+
},
|
1589 |
+
"198": {
|
1590 |
+
"content": "</blockquote>",
|
1591 |
+
"lstrip": false,
|
1592 |
+
"normalized": false,
|
1593 |
+
"rstrip": false,
|
1594 |
+
"single_word": false,
|
1595 |
+
"special": false
|
1596 |
+
},
|
1597 |
+
"199": {
|
1598 |
+
"content": "<strong>",
|
1599 |
+
"lstrip": false,
|
1600 |
+
"normalized": false,
|
1601 |
+
"rstrip": false,
|
1602 |
+
"single_word": false,
|
1603 |
+
"special": false
|
1604 |
+
},
|
1605 |
+
"200": {
|
1606 |
+
"content": "<em>",
|
1607 |
+
"lstrip": false,
|
1608 |
+
"normalized": false,
|
1609 |
+
"rstrip": false,
|
1610 |
+
"single_word": false,
|
1611 |
+
"special": false
|
1612 |
+
},
|
1613 |
+
"201": {
|
1614 |
+
"content": "<b>",
|
1615 |
+
"lstrip": false,
|
1616 |
+
"normalized": false,
|
1617 |
+
"rstrip": false,
|
1618 |
+
"single_word": false,
|
1619 |
+
"special": false
|
1620 |
+
},
|
1621 |
+
"202": {
|
1622 |
+
"content": "<i>",
|
1623 |
+
"lstrip": false,
|
1624 |
+
"normalized": false,
|
1625 |
+
"rstrip": false,
|
1626 |
+
"single_word": false,
|
1627 |
+
"special": false
|
1628 |
+
},
|
1629 |
+
"203": {
|
1630 |
+
"content": "<u>",
|
1631 |
+
"lstrip": false,
|
1632 |
+
"normalized": false,
|
1633 |
+
"rstrip": false,
|
1634 |
+
"single_word": false,
|
1635 |
+
"special": false
|
1636 |
+
},
|
1637 |
+
"204": {
|
1638 |
+
"content": "<s>",
|
1639 |
+
"lstrip": false,
|
1640 |
+
"normalized": false,
|
1641 |
+
"rstrip": false,
|
1642 |
+
"single_word": false,
|
1643 |
+
"special": false
|
1644 |
+
},
|
1645 |
+
"205": {
|
1646 |
+
"content": "<sub>",
|
1647 |
+
"lstrip": false,
|
1648 |
+
"normalized": false,
|
1649 |
+
"rstrip": false,
|
1650 |
+
"single_word": false,
|
1651 |
+
"special": false
|
1652 |
+
},
|
1653 |
+
"206": {
|
1654 |
+
"content": "<sup>",
|
1655 |
+
"lstrip": false,
|
1656 |
+
"normalized": false,
|
1657 |
+
"rstrip": false,
|
1658 |
+
"single_word": false,
|
1659 |
+
"special": false
|
1660 |
+
},
|
1661 |
+
"207": {
|
1662 |
+
"content": "<code>",
|
1663 |
+
"lstrip": false,
|
1664 |
+
"normalized": false,
|
1665 |
+
"rstrip": false,
|
1666 |
+
"single_word": false,
|
1667 |
+
"special": false
|
1668 |
+
},
|
1669 |
+
"208": {
|
1670 |
+
"content": "</strong>",
|
1671 |
+
"lstrip": false,
|
1672 |
+
"normalized": false,
|
1673 |
+
"rstrip": false,
|
1674 |
+
"single_word": false,
|
1675 |
+
"special": false
|
1676 |
+
},
|
1677 |
+
"209": {
|
1678 |
+
"content": "</em>",
|
1679 |
+
"lstrip": false,
|
1680 |
+
"normalized": false,
|
1681 |
+
"rstrip": false,
|
1682 |
+
"single_word": false,
|
1683 |
+
"special": false
|
1684 |
+
},
|
1685 |
+
"210": {
|
1686 |
+
"content": "</b>",
|
1687 |
+
"lstrip": false,
|
1688 |
+
"normalized": false,
|
1689 |
+
"rstrip": false,
|
1690 |
+
"single_word": false,
|
1691 |
+
"special": false
|
1692 |
+
},
|
1693 |
+
"211": {
|
1694 |
+
"content": "</i>",
|
1695 |
+
"lstrip": false,
|
1696 |
+
"normalized": false,
|
1697 |
+
"rstrip": false,
|
1698 |
+
"single_word": false,
|
1699 |
+
"special": false
|
1700 |
+
},
|
1701 |
+
"212": {
|
1702 |
+
"content": "</u>",
|
1703 |
+
"lstrip": false,
|
1704 |
+
"normalized": false,
|
1705 |
+
"rstrip": false,
|
1706 |
+
"single_word": false,
|
1707 |
+
"special": false
|
1708 |
+
},
|
1709 |
+
"213": {
|
1710 |
+
"content": "</s>",
|
1711 |
+
"lstrip": false,
|
1712 |
+
"normalized": false,
|
1713 |
+
"rstrip": false,
|
1714 |
+
"single_word": false,
|
1715 |
+
"special": false
|
1716 |
+
},
|
1717 |
+
"214": {
|
1718 |
+
"content": "</sub>",
|
1719 |
+
"lstrip": false,
|
1720 |
+
"normalized": false,
|
1721 |
+
"rstrip": false,
|
1722 |
+
"single_word": false,
|
1723 |
+
"special": false
|
1724 |
+
},
|
1725 |
+
"215": {
|
1726 |
+
"content": "</sup>",
|
1727 |
+
"lstrip": false,
|
1728 |
+
"normalized": false,
|
1729 |
+
"rstrip": false,
|
1730 |
+
"single_word": false,
|
1731 |
+
"special": false
|
1732 |
+
},
|
1733 |
+
"216": {
|
1734 |
+
"content": "</code>",
|
1735 |
+
"lstrip": false,
|
1736 |
+
"normalized": false,
|
1737 |
+
"rstrip": false,
|
1738 |
+
"single_word": false,
|
1739 |
+
"special": false
|
1740 |
+
}
|
1741 |
+
},
|
1742 |
+
"additional_special_tokens": [
|
1743 |
+
"<start_of_turn>",
|
1744 |
+
"<end_of_turn>"
|
1745 |
+
],
|
1746 |
+
"bos_token": "<bos>",
|
1747 |
+
"clean_up_tokenization_spaces": false,
|
1748 |
+
"eos_token": "<eos>",
|
1749 |
+
"model_max_length": 1000000000000000019884624838656,
|
1750 |
+
"pad_token": "<pad>",
|
1751 |
+
"sp_model_kwargs": {},
|
1752 |
+
"spaces_between_special_tokens": false,
|
1753 |
+
"tokenizer_class": "GemmaTokenizer",
|
1754 |
+
"unk_token": "<unk>",
|
1755 |
+
"use_default_system_prompt": false
|
1756 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,1433 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 28.67383512544803,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 4000,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.14336917562724014,
|
13 |
+
"grad_norm": 0.8701110482215881,
|
14 |
+
"learning_rate": 4e-05,
|
15 |
+
"loss": 2.5146,
|
16 |
+
"step": 20
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.2867383512544803,
|
20 |
+
"grad_norm": 1.018184781074524,
|
21 |
+
"learning_rate": 8e-05,
|
22 |
+
"loss": 2.4311,
|
23 |
+
"step": 40
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.43010752688172044,
|
27 |
+
"grad_norm": 3.042095184326172,
|
28 |
+
"learning_rate": 0.00012,
|
29 |
+
"loss": 2.1109,
|
30 |
+
"step": 60
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 0.5734767025089605,
|
34 |
+
"grad_norm": 0.8230174779891968,
|
35 |
+
"learning_rate": 0.00016,
|
36 |
+
"loss": 1.8722,
|
37 |
+
"step": 80
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 0.7168458781362007,
|
41 |
+
"grad_norm": 0.8457050323486328,
|
42 |
+
"learning_rate": 0.0002,
|
43 |
+
"loss": 1.6615,
|
44 |
+
"step": 100
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.8602150537634409,
|
48 |
+
"grad_norm": 0.7940322160720825,
|
49 |
+
"learning_rate": 0.00019988455988455988,
|
50 |
+
"loss": 1.575,
|
51 |
+
"step": 120
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 1.003584229390681,
|
55 |
+
"grad_norm": 1.0075829029083252,
|
56 |
+
"learning_rate": 0.00019976911976911978,
|
57 |
+
"loss": 1.4759,
|
58 |
+
"step": 140
|
59 |
+
},
|
60 |
+
{
|
61 |
+
"epoch": 1.146953405017921,
|
62 |
+
"grad_norm": 0.8754940629005432,
|
63 |
+
"learning_rate": 0.00019965367965367966,
|
64 |
+
"loss": 1.4484,
|
65 |
+
"step": 160
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 1.2903225806451613,
|
69 |
+
"grad_norm": 1.2001057863235474,
|
70 |
+
"learning_rate": 0.00019953823953823956,
|
71 |
+
"loss": 1.4163,
|
72 |
+
"step": 180
|
73 |
+
},
|
74 |
+
{
|
75 |
+
"epoch": 1.4336917562724014,
|
76 |
+
"grad_norm": 1.1393181085586548,
|
77 |
+
"learning_rate": 0.00019942279942279943,
|
78 |
+
"loss": 1.4249,
|
79 |
+
"step": 200
|
80 |
+
},
|
81 |
+
{
|
82 |
+
"epoch": 1.5770609318996416,
|
83 |
+
"grad_norm": 1.426618218421936,
|
84 |
+
"learning_rate": 0.0001993073593073593,
|
85 |
+
"loss": 1.4,
|
86 |
+
"step": 220
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 1.7204301075268817,
|
90 |
+
"grad_norm": 1.5125058889389038,
|
91 |
+
"learning_rate": 0.0001991919191919192,
|
92 |
+
"loss": 1.4044,
|
93 |
+
"step": 240
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 1.863799283154122,
|
97 |
+
"grad_norm": 1.490069031715393,
|
98 |
+
"learning_rate": 0.00019907647907647908,
|
99 |
+
"loss": 1.3274,
|
100 |
+
"step": 260
|
101 |
+
},
|
102 |
+
{
|
103 |
+
"epoch": 2.007168458781362,
|
104 |
+
"grad_norm": 1.1766711473464966,
|
105 |
+
"learning_rate": 0.00019896103896103898,
|
106 |
+
"loss": 1.4013,
|
107 |
+
"step": 280
|
108 |
+
},
|
109 |
+
{
|
110 |
+
"epoch": 2.150537634408602,
|
111 |
+
"grad_norm": 1.7495911121368408,
|
112 |
+
"learning_rate": 0.00019884559884559885,
|
113 |
+
"loss": 1.3134,
|
114 |
+
"step": 300
|
115 |
+
},
|
116 |
+
{
|
117 |
+
"epoch": 2.293906810035842,
|
118 |
+
"grad_norm": 1.4539434909820557,
|
119 |
+
"learning_rate": 0.00019873015873015875,
|
120 |
+
"loss": 1.3187,
|
121 |
+
"step": 320
|
122 |
+
},
|
123 |
+
{
|
124 |
+
"epoch": 2.4372759856630823,
|
125 |
+
"grad_norm": 1.6635984182357788,
|
126 |
+
"learning_rate": 0.00019861471861471863,
|
127 |
+
"loss": 1.2624,
|
128 |
+
"step": 340
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 2.5806451612903225,
|
132 |
+
"grad_norm": 2.0392329692840576,
|
133 |
+
"learning_rate": 0.00019849927849927853,
|
134 |
+
"loss": 1.2672,
|
135 |
+
"step": 360
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 2.7240143369175627,
|
139 |
+
"grad_norm": 1.4355524778366089,
|
140 |
+
"learning_rate": 0.00019838383838383837,
|
141 |
+
"loss": 1.2838,
|
142 |
+
"step": 380
|
143 |
+
},
|
144 |
+
{
|
145 |
+
"epoch": 2.867383512544803,
|
146 |
+
"grad_norm": 1.7227002382278442,
|
147 |
+
"learning_rate": 0.00019826839826839827,
|
148 |
+
"loss": 1.2552,
|
149 |
+
"step": 400
|
150 |
+
},
|
151 |
+
{
|
152 |
+
"epoch": 3.010752688172043,
|
153 |
+
"grad_norm": 1.666508436203003,
|
154 |
+
"learning_rate": 0.00019815295815295815,
|
155 |
+
"loss": 1.2805,
|
156 |
+
"step": 420
|
157 |
+
},
|
158 |
+
{
|
159 |
+
"epoch": 3.154121863799283,
|
160 |
+
"grad_norm": 2.0044264793395996,
|
161 |
+
"learning_rate": 0.00019803751803751805,
|
162 |
+
"loss": 1.1947,
|
163 |
+
"step": 440
|
164 |
+
},
|
165 |
+
{
|
166 |
+
"epoch": 3.2974910394265233,
|
167 |
+
"grad_norm": 2.1593244075775146,
|
168 |
+
"learning_rate": 0.00019792207792207792,
|
169 |
+
"loss": 1.2006,
|
170 |
+
"step": 460
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 3.4408602150537635,
|
174 |
+
"grad_norm": 2.0706088542938232,
|
175 |
+
"learning_rate": 0.00019780663780663782,
|
176 |
+
"loss": 1.2535,
|
177 |
+
"step": 480
|
178 |
+
},
|
179 |
+
{
|
180 |
+
"epoch": 3.5842293906810037,
|
181 |
+
"grad_norm": 2.375523567199707,
|
182 |
+
"learning_rate": 0.0001976911976911977,
|
183 |
+
"loss": 1.1777,
|
184 |
+
"step": 500
|
185 |
+
},
|
186 |
+
{
|
187 |
+
"epoch": 3.727598566308244,
|
188 |
+
"grad_norm": 2.0333664417266846,
|
189 |
+
"learning_rate": 0.0001975757575757576,
|
190 |
+
"loss": 1.2199,
|
191 |
+
"step": 520
|
192 |
+
},
|
193 |
+
{
|
194 |
+
"epoch": 3.870967741935484,
|
195 |
+
"grad_norm": 2.0638692378997803,
|
196 |
+
"learning_rate": 0.00019746031746031747,
|
197 |
+
"loss": 1.241,
|
198 |
+
"step": 540
|
199 |
+
},
|
200 |
+
{
|
201 |
+
"epoch": 4.014336917562724,
|
202 |
+
"grad_norm": 1.829522728919983,
|
203 |
+
"learning_rate": 0.00019734487734487734,
|
204 |
+
"loss": 1.1603,
|
205 |
+
"step": 560
|
206 |
+
},
|
207 |
+
{
|
208 |
+
"epoch": 4.157706093189964,
|
209 |
+
"grad_norm": 2.5862321853637695,
|
210 |
+
"learning_rate": 0.00019722943722943722,
|
211 |
+
"loss": 1.1392,
|
212 |
+
"step": 580
|
213 |
+
},
|
214 |
+
{
|
215 |
+
"epoch": 4.301075268817204,
|
216 |
+
"grad_norm": 2.028472423553467,
|
217 |
+
"learning_rate": 0.00019711399711399712,
|
218 |
+
"loss": 1.078,
|
219 |
+
"step": 600
|
220 |
+
},
|
221 |
+
{
|
222 |
+
"epoch": 4.444444444444445,
|
223 |
+
"grad_norm": 1.7103493213653564,
|
224 |
+
"learning_rate": 0.000196998556998557,
|
225 |
+
"loss": 1.1751,
|
226 |
+
"step": 620
|
227 |
+
},
|
228 |
+
{
|
229 |
+
"epoch": 4.587813620071684,
|
230 |
+
"grad_norm": 2.320739269256592,
|
231 |
+
"learning_rate": 0.0001968831168831169,
|
232 |
+
"loss": 1.1617,
|
233 |
+
"step": 640
|
234 |
+
},
|
235 |
+
{
|
236 |
+
"epoch": 4.731182795698925,
|
237 |
+
"grad_norm": 2.6019182205200195,
|
238 |
+
"learning_rate": 0.00019676767676767677,
|
239 |
+
"loss": 1.1775,
|
240 |
+
"step": 660
|
241 |
+
},
|
242 |
+
{
|
243 |
+
"epoch": 4.874551971326165,
|
244 |
+
"grad_norm": 2.342106342315674,
|
245 |
+
"learning_rate": 0.00019665223665223667,
|
246 |
+
"loss": 1.0605,
|
247 |
+
"step": 680
|
248 |
+
},
|
249 |
+
{
|
250 |
+
"epoch": 5.017921146953405,
|
251 |
+
"grad_norm": 2.3113956451416016,
|
252 |
+
"learning_rate": 0.00019653679653679654,
|
253 |
+
"loss": 1.1429,
|
254 |
+
"step": 700
|
255 |
+
},
|
256 |
+
{
|
257 |
+
"epoch": 5.161290322580645,
|
258 |
+
"grad_norm": 2.171203851699829,
|
259 |
+
"learning_rate": 0.00019642135642135644,
|
260 |
+
"loss": 1.0781,
|
261 |
+
"step": 720
|
262 |
+
},
|
263 |
+
{
|
264 |
+
"epoch": 5.304659498207886,
|
265 |
+
"grad_norm": 2.2198007106781006,
|
266 |
+
"learning_rate": 0.00019630591630591631,
|
267 |
+
"loss": 1.0734,
|
268 |
+
"step": 740
|
269 |
+
},
|
270 |
+
{
|
271 |
+
"epoch": 5.448028673835125,
|
272 |
+
"grad_norm": 2.1445112228393555,
|
273 |
+
"learning_rate": 0.0001961904761904762,
|
274 |
+
"loss": 1.0354,
|
275 |
+
"step": 760
|
276 |
+
},
|
277 |
+
{
|
278 |
+
"epoch": 5.591397849462366,
|
279 |
+
"grad_norm": 2.0999436378479004,
|
280 |
+
"learning_rate": 0.0001960750360750361,
|
281 |
+
"loss": 1.0931,
|
282 |
+
"step": 780
|
283 |
+
},
|
284 |
+
{
|
285 |
+
"epoch": 5.734767025089606,
|
286 |
+
"grad_norm": 2.395735740661621,
|
287 |
+
"learning_rate": 0.00019595959595959596,
|
288 |
+
"loss": 1.1055,
|
289 |
+
"step": 800
|
290 |
+
},
|
291 |
+
{
|
292 |
+
"epoch": 5.878136200716845,
|
293 |
+
"grad_norm": 2.327645778656006,
|
294 |
+
"learning_rate": 0.00019584415584415586,
|
295 |
+
"loss": 1.1219,
|
296 |
+
"step": 820
|
297 |
+
},
|
298 |
+
{
|
299 |
+
"epoch": 6.021505376344086,
|
300 |
+
"grad_norm": 2.3551368713378906,
|
301 |
+
"learning_rate": 0.00019572871572871574,
|
302 |
+
"loss": 1.0061,
|
303 |
+
"step": 840
|
304 |
+
},
|
305 |
+
{
|
306 |
+
"epoch": 6.164874551971327,
|
307 |
+
"grad_norm": 2.9338879585266113,
|
308 |
+
"learning_rate": 0.00019561327561327564,
|
309 |
+
"loss": 0.9606,
|
310 |
+
"step": 860
|
311 |
+
},
|
312 |
+
{
|
313 |
+
"epoch": 6.308243727598566,
|
314 |
+
"grad_norm": 2.6095728874206543,
|
315 |
+
"learning_rate": 0.0001954978354978355,
|
316 |
+
"loss": 0.9917,
|
317 |
+
"step": 880
|
318 |
+
},
|
319 |
+
{
|
320 |
+
"epoch": 6.451612903225806,
|
321 |
+
"grad_norm": 2.9128003120422363,
|
322 |
+
"learning_rate": 0.0001953823953823954,
|
323 |
+
"loss": 1.0127,
|
324 |
+
"step": 900
|
325 |
+
},
|
326 |
+
{
|
327 |
+
"epoch": 6.594982078853047,
|
328 |
+
"grad_norm": 2.1806392669677734,
|
329 |
+
"learning_rate": 0.00019526695526695528,
|
330 |
+
"loss": 1.0646,
|
331 |
+
"step": 920
|
332 |
+
},
|
333 |
+
{
|
334 |
+
"epoch": 6.738351254480286,
|
335 |
+
"grad_norm": 2.0614748001098633,
|
336 |
+
"learning_rate": 0.00019515151515151516,
|
337 |
+
"loss": 1.0206,
|
338 |
+
"step": 940
|
339 |
+
},
|
340 |
+
{
|
341 |
+
"epoch": 6.881720430107527,
|
342 |
+
"grad_norm": 3.0712902545928955,
|
343 |
+
"learning_rate": 0.00019503607503607503,
|
344 |
+
"loss": 1.044,
|
345 |
+
"step": 960
|
346 |
+
},
|
347 |
+
{
|
348 |
+
"epoch": 7.025089605734767,
|
349 |
+
"grad_norm": 2.756150960922241,
|
350 |
+
"learning_rate": 0.00019492063492063493,
|
351 |
+
"loss": 1.0001,
|
352 |
+
"step": 980
|
353 |
+
},
|
354 |
+
{
|
355 |
+
"epoch": 7.168458781362007,
|
356 |
+
"grad_norm": 2.4070088863372803,
|
357 |
+
"learning_rate": 0.0001948051948051948,
|
358 |
+
"loss": 1.0062,
|
359 |
+
"step": 1000
|
360 |
+
},
|
361 |
+
{
|
362 |
+
"epoch": 7.311827956989247,
|
363 |
+
"grad_norm": 3.246767520904541,
|
364 |
+
"learning_rate": 0.0001946897546897547,
|
365 |
+
"loss": 0.9447,
|
366 |
+
"step": 1020
|
367 |
+
},
|
368 |
+
{
|
369 |
+
"epoch": 7.455197132616488,
|
370 |
+
"grad_norm": 2.817984104156494,
|
371 |
+
"learning_rate": 0.00019457431457431458,
|
372 |
+
"loss": 0.9825,
|
373 |
+
"step": 1040
|
374 |
+
},
|
375 |
+
{
|
376 |
+
"epoch": 7.598566308243727,
|
377 |
+
"grad_norm": 2.8855531215667725,
|
378 |
+
"learning_rate": 0.00019445887445887448,
|
379 |
+
"loss": 0.9889,
|
380 |
+
"step": 1060
|
381 |
+
},
|
382 |
+
{
|
383 |
+
"epoch": 7.741935483870968,
|
384 |
+
"grad_norm": 3.1939897537231445,
|
385 |
+
"learning_rate": 0.00019434343434343435,
|
386 |
+
"loss": 0.9244,
|
387 |
+
"step": 1080
|
388 |
+
},
|
389 |
+
{
|
390 |
+
"epoch": 7.885304659498208,
|
391 |
+
"grad_norm": 2.6888437271118164,
|
392 |
+
"learning_rate": 0.00019422799422799425,
|
393 |
+
"loss": 0.932,
|
394 |
+
"step": 1100
|
395 |
+
},
|
396 |
+
{
|
397 |
+
"epoch": 8.028673835125447,
|
398 |
+
"grad_norm": 2.6523380279541016,
|
399 |
+
"learning_rate": 0.0001941125541125541,
|
400 |
+
"loss": 0.9283,
|
401 |
+
"step": 1120
|
402 |
+
},
|
403 |
+
{
|
404 |
+
"epoch": 8.172043010752688,
|
405 |
+
"grad_norm": 3.123074769973755,
|
406 |
+
"learning_rate": 0.000193997113997114,
|
407 |
+
"loss": 0.9142,
|
408 |
+
"step": 1140
|
409 |
+
},
|
410 |
+
{
|
411 |
+
"epoch": 8.315412186379929,
|
412 |
+
"grad_norm": 2.7300188541412354,
|
413 |
+
"learning_rate": 0.00019388167388167387,
|
414 |
+
"loss": 0.9039,
|
415 |
+
"step": 1160
|
416 |
+
},
|
417 |
+
{
|
418 |
+
"epoch": 8.45878136200717,
|
419 |
+
"grad_norm": 2.889723300933838,
|
420 |
+
"learning_rate": 0.00019376623376623377,
|
421 |
+
"loss": 0.9093,
|
422 |
+
"step": 1180
|
423 |
+
},
|
424 |
+
{
|
425 |
+
"epoch": 8.602150537634408,
|
426 |
+
"grad_norm": 2.390486717224121,
|
427 |
+
"learning_rate": 0.00019365079365079365,
|
428 |
+
"loss": 0.9247,
|
429 |
+
"step": 1200
|
430 |
+
},
|
431 |
+
{
|
432 |
+
"epoch": 8.745519713261649,
|
433 |
+
"grad_norm": 2.97426700592041,
|
434 |
+
"learning_rate": 0.00019353535353535355,
|
435 |
+
"loss": 0.8887,
|
436 |
+
"step": 1220
|
437 |
+
},
|
438 |
+
{
|
439 |
+
"epoch": 8.88888888888889,
|
440 |
+
"grad_norm": 3.086162805557251,
|
441 |
+
"learning_rate": 0.00019341991341991342,
|
442 |
+
"loss": 0.9477,
|
443 |
+
"step": 1240
|
444 |
+
},
|
445 |
+
{
|
446 |
+
"epoch": 9.03225806451613,
|
447 |
+
"grad_norm": 4.036062240600586,
|
448 |
+
"learning_rate": 0.00019330447330447332,
|
449 |
+
"loss": 0.8978,
|
450 |
+
"step": 1260
|
451 |
+
},
|
452 |
+
{
|
453 |
+
"epoch": 9.175627240143369,
|
454 |
+
"grad_norm": 3.6827592849731445,
|
455 |
+
"learning_rate": 0.0001931890331890332,
|
456 |
+
"loss": 0.8826,
|
457 |
+
"step": 1280
|
458 |
+
},
|
459 |
+
{
|
460 |
+
"epoch": 9.31899641577061,
|
461 |
+
"grad_norm": 2.9294958114624023,
|
462 |
+
"learning_rate": 0.00019307359307359307,
|
463 |
+
"loss": 0.8367,
|
464 |
+
"step": 1300
|
465 |
+
},
|
466 |
+
{
|
467 |
+
"epoch": 9.46236559139785,
|
468 |
+
"grad_norm": 2.873551607131958,
|
469 |
+
"learning_rate": 0.00019295815295815297,
|
470 |
+
"loss": 0.8517,
|
471 |
+
"step": 1320
|
472 |
+
},
|
473 |
+
{
|
474 |
+
"epoch": 9.60573476702509,
|
475 |
+
"grad_norm": 2.599212884902954,
|
476 |
+
"learning_rate": 0.00019284271284271284,
|
477 |
+
"loss": 0.8754,
|
478 |
+
"step": 1340
|
479 |
+
},
|
480 |
+
{
|
481 |
+
"epoch": 9.74910394265233,
|
482 |
+
"grad_norm": 3.3076424598693848,
|
483 |
+
"learning_rate": 0.00019272727272727274,
|
484 |
+
"loss": 0.8371,
|
485 |
+
"step": 1360
|
486 |
+
},
|
487 |
+
{
|
488 |
+
"epoch": 9.89247311827957,
|
489 |
+
"grad_norm": 3.347135066986084,
|
490 |
+
"learning_rate": 0.00019261183261183262,
|
491 |
+
"loss": 0.8566,
|
492 |
+
"step": 1380
|
493 |
+
},
|
494 |
+
{
|
495 |
+
"epoch": 10.03584229390681,
|
496 |
+
"grad_norm": 3.3262321949005127,
|
497 |
+
"learning_rate": 0.00019249639249639252,
|
498 |
+
"loss": 0.8665,
|
499 |
+
"step": 1400
|
500 |
+
},
|
501 |
+
{
|
502 |
+
"epoch": 10.17921146953405,
|
503 |
+
"grad_norm": 3.3654842376708984,
|
504 |
+
"learning_rate": 0.0001923809523809524,
|
505 |
+
"loss": 0.8058,
|
506 |
+
"step": 1420
|
507 |
+
},
|
508 |
+
{
|
509 |
+
"epoch": 10.32258064516129,
|
510 |
+
"grad_norm": 3.437192678451538,
|
511 |
+
"learning_rate": 0.0001922655122655123,
|
512 |
+
"loss": 0.8227,
|
513 |
+
"step": 1440
|
514 |
+
},
|
515 |
+
{
|
516 |
+
"epoch": 10.46594982078853,
|
517 |
+
"grad_norm": 3.4953198432922363,
|
518 |
+
"learning_rate": 0.00019215007215007217,
|
519 |
+
"loss": 0.8112,
|
520 |
+
"step": 1460
|
521 |
+
},
|
522 |
+
{
|
523 |
+
"epoch": 10.609318996415771,
|
524 |
+
"grad_norm": 3.1842894554138184,
|
525 |
+
"learning_rate": 0.00019203463203463204,
|
526 |
+
"loss": 0.7906,
|
527 |
+
"step": 1480
|
528 |
+
},
|
529 |
+
{
|
530 |
+
"epoch": 10.75268817204301,
|
531 |
+
"grad_norm": 3.4176406860351562,
|
532 |
+
"learning_rate": 0.00019191919191919191,
|
533 |
+
"loss": 0.8452,
|
534 |
+
"step": 1500
|
535 |
+
},
|
536 |
+
{
|
537 |
+
"epoch": 10.89605734767025,
|
538 |
+
"grad_norm": 2.7511439323425293,
|
539 |
+
"learning_rate": 0.00019180375180375181,
|
540 |
+
"loss": 0.8233,
|
541 |
+
"step": 1520
|
542 |
+
},
|
543 |
+
{
|
544 |
+
"epoch": 11.039426523297491,
|
545 |
+
"grad_norm": 3.739851236343384,
|
546 |
+
"learning_rate": 0.0001916883116883117,
|
547 |
+
"loss": 0.8293,
|
548 |
+
"step": 1540
|
549 |
+
},
|
550 |
+
{
|
551 |
+
"epoch": 11.182795698924732,
|
552 |
+
"grad_norm": 4.09880256652832,
|
553 |
+
"learning_rate": 0.0001915728715728716,
|
554 |
+
"loss": 0.7689,
|
555 |
+
"step": 1560
|
556 |
+
},
|
557 |
+
{
|
558 |
+
"epoch": 11.32616487455197,
|
559 |
+
"grad_norm": 3.835360288619995,
|
560 |
+
"learning_rate": 0.00019145743145743146,
|
561 |
+
"loss": 0.7774,
|
562 |
+
"step": 1580
|
563 |
+
},
|
564 |
+
{
|
565 |
+
"epoch": 11.469534050179211,
|
566 |
+
"grad_norm": 4.158806324005127,
|
567 |
+
"learning_rate": 0.00019134199134199136,
|
568 |
+
"loss": 0.7507,
|
569 |
+
"step": 1600
|
570 |
+
},
|
571 |
+
{
|
572 |
+
"epoch": 11.612903225806452,
|
573 |
+
"grad_norm": 3.1276865005493164,
|
574 |
+
"learning_rate": 0.00019122655122655124,
|
575 |
+
"loss": 0.8105,
|
576 |
+
"step": 1620
|
577 |
+
},
|
578 |
+
{
|
579 |
+
"epoch": 11.756272401433693,
|
580 |
+
"grad_norm": 3.1346616744995117,
|
581 |
+
"learning_rate": 0.00019111111111111114,
|
582 |
+
"loss": 0.78,
|
583 |
+
"step": 1640
|
584 |
+
},
|
585 |
+
{
|
586 |
+
"epoch": 11.899641577060931,
|
587 |
+
"grad_norm": 3.3458778858184814,
|
588 |
+
"learning_rate": 0.00019099567099567098,
|
589 |
+
"loss": 0.7711,
|
590 |
+
"step": 1660
|
591 |
+
},
|
592 |
+
{
|
593 |
+
"epoch": 12.043010752688172,
|
594 |
+
"grad_norm": 3.1722230911254883,
|
595 |
+
"learning_rate": 0.00019088023088023088,
|
596 |
+
"loss": 0.7746,
|
597 |
+
"step": 1680
|
598 |
+
},
|
599 |
+
{
|
600 |
+
"epoch": 12.186379928315413,
|
601 |
+
"grad_norm": 4.433016777038574,
|
602 |
+
"learning_rate": 0.00019076479076479076,
|
603 |
+
"loss": 0.7556,
|
604 |
+
"step": 1700
|
605 |
+
},
|
606 |
+
{
|
607 |
+
"epoch": 12.329749103942653,
|
608 |
+
"grad_norm": 3.0202817916870117,
|
609 |
+
"learning_rate": 0.00019064935064935066,
|
610 |
+
"loss": 0.7333,
|
611 |
+
"step": 1720
|
612 |
+
},
|
613 |
+
{
|
614 |
+
"epoch": 12.473118279569892,
|
615 |
+
"grad_norm": 3.66214656829834,
|
616 |
+
"learning_rate": 0.00019053391053391053,
|
617 |
+
"loss": 0.7353,
|
618 |
+
"step": 1740
|
619 |
+
},
|
620 |
+
{
|
621 |
+
"epoch": 12.616487455197133,
|
622 |
+
"grad_norm": 3.635371446609497,
|
623 |
+
"learning_rate": 0.00019041847041847043,
|
624 |
+
"loss": 0.7186,
|
625 |
+
"step": 1760
|
626 |
+
},
|
627 |
+
{
|
628 |
+
"epoch": 12.759856630824373,
|
629 |
+
"grad_norm": 3.1196370124816895,
|
630 |
+
"learning_rate": 0.0001903030303030303,
|
631 |
+
"loss": 0.7959,
|
632 |
+
"step": 1780
|
633 |
+
},
|
634 |
+
{
|
635 |
+
"epoch": 12.903225806451612,
|
636 |
+
"grad_norm": 4.016541481018066,
|
637 |
+
"learning_rate": 0.0001901875901875902,
|
638 |
+
"loss": 0.6809,
|
639 |
+
"step": 1800
|
640 |
+
},
|
641 |
+
{
|
642 |
+
"epoch": 13.046594982078853,
|
643 |
+
"grad_norm": 3.472865581512451,
|
644 |
+
"learning_rate": 0.00019007215007215008,
|
645 |
+
"loss": 0.7213,
|
646 |
+
"step": 1820
|
647 |
+
},
|
648 |
+
{
|
649 |
+
"epoch": 13.189964157706093,
|
650 |
+
"grad_norm": 3.9193198680877686,
|
651 |
+
"learning_rate": 0.00018995670995670995,
|
652 |
+
"loss": 0.6724,
|
653 |
+
"step": 1840
|
654 |
+
},
|
655 |
+
{
|
656 |
+
"epoch": 13.333333333333334,
|
657 |
+
"grad_norm": 3.6128931045532227,
|
658 |
+
"learning_rate": 0.00018984126984126985,
|
659 |
+
"loss": 0.6879,
|
660 |
+
"step": 1860
|
661 |
+
},
|
662 |
+
{
|
663 |
+
"epoch": 13.476702508960573,
|
664 |
+
"grad_norm": 3.895617961883545,
|
665 |
+
"learning_rate": 0.00018972582972582973,
|
666 |
+
"loss": 0.6845,
|
667 |
+
"step": 1880
|
668 |
+
},
|
669 |
+
{
|
670 |
+
"epoch": 13.620071684587813,
|
671 |
+
"grad_norm": 3.7436187267303467,
|
672 |
+
"learning_rate": 0.00018961038961038963,
|
673 |
+
"loss": 0.7148,
|
674 |
+
"step": 1900
|
675 |
+
},
|
676 |
+
{
|
677 |
+
"epoch": 13.763440860215054,
|
678 |
+
"grad_norm": 2.9357612133026123,
|
679 |
+
"learning_rate": 0.0001894949494949495,
|
680 |
+
"loss": 0.7178,
|
681 |
+
"step": 1920
|
682 |
+
},
|
683 |
+
{
|
684 |
+
"epoch": 13.906810035842295,
|
685 |
+
"grad_norm": 3.4985647201538086,
|
686 |
+
"learning_rate": 0.0001893795093795094,
|
687 |
+
"loss": 0.7267,
|
688 |
+
"step": 1940
|
689 |
+
},
|
690 |
+
{
|
691 |
+
"epoch": 14.050179211469533,
|
692 |
+
"grad_norm": 3.0033462047576904,
|
693 |
+
"learning_rate": 0.00018926406926406928,
|
694 |
+
"loss": 0.7228,
|
695 |
+
"step": 1960
|
696 |
+
},
|
697 |
+
{
|
698 |
+
"epoch": 14.193548387096774,
|
699 |
+
"grad_norm": 3.525641441345215,
|
700 |
+
"learning_rate": 0.00018914862914862918,
|
701 |
+
"loss": 0.6547,
|
702 |
+
"step": 1980
|
703 |
+
},
|
704 |
+
{
|
705 |
+
"epoch": 14.336917562724015,
|
706 |
+
"grad_norm": 4.64281702041626,
|
707 |
+
"learning_rate": 0.00018903318903318905,
|
708 |
+
"loss": 0.6672,
|
709 |
+
"step": 2000
|
710 |
+
},
|
711 |
+
{
|
712 |
+
"epoch": 14.480286738351255,
|
713 |
+
"grad_norm": 3.8177640438079834,
|
714 |
+
"learning_rate": 0.00018891774891774892,
|
715 |
+
"loss": 0.6672,
|
716 |
+
"step": 2020
|
717 |
+
},
|
718 |
+
{
|
719 |
+
"epoch": 14.623655913978494,
|
720 |
+
"grad_norm": 3.5208513736724854,
|
721 |
+
"learning_rate": 0.0001888023088023088,
|
722 |
+
"loss": 0.6649,
|
723 |
+
"step": 2040
|
724 |
+
},
|
725 |
+
{
|
726 |
+
"epoch": 14.767025089605735,
|
727 |
+
"grad_norm": 4.133231163024902,
|
728 |
+
"learning_rate": 0.0001886868686868687,
|
729 |
+
"loss": 0.683,
|
730 |
+
"step": 2060
|
731 |
+
},
|
732 |
+
{
|
733 |
+
"epoch": 14.910394265232975,
|
734 |
+
"grad_norm": 3.406191110610962,
|
735 |
+
"learning_rate": 0.00018857142857142857,
|
736 |
+
"loss": 0.6852,
|
737 |
+
"step": 2080
|
738 |
+
},
|
739 |
+
{
|
740 |
+
"epoch": 15.053763440860216,
|
741 |
+
"grad_norm": 3.38570237159729,
|
742 |
+
"learning_rate": 0.00018845598845598847,
|
743 |
+
"loss": 0.6723,
|
744 |
+
"step": 2100
|
745 |
+
},
|
746 |
+
{
|
747 |
+
"epoch": 15.197132616487455,
|
748 |
+
"grad_norm": 3.719644546508789,
|
749 |
+
"learning_rate": 0.00018834054834054834,
|
750 |
+
"loss": 0.6528,
|
751 |
+
"step": 2120
|
752 |
+
},
|
753 |
+
{
|
754 |
+
"epoch": 15.340501792114695,
|
755 |
+
"grad_norm": 3.887092113494873,
|
756 |
+
"learning_rate": 0.00018822510822510825,
|
757 |
+
"loss": 0.6116,
|
758 |
+
"step": 2140
|
759 |
+
},
|
760 |
+
{
|
761 |
+
"epoch": 15.483870967741936,
|
762 |
+
"grad_norm": 4.1723432540893555,
|
763 |
+
"learning_rate": 0.00018810966810966812,
|
764 |
+
"loss": 0.5873,
|
765 |
+
"step": 2160
|
766 |
+
},
|
767 |
+
{
|
768 |
+
"epoch": 15.627240143369175,
|
769 |
+
"grad_norm": 4.310718536376953,
|
770 |
+
"learning_rate": 0.00018799422799422802,
|
771 |
+
"loss": 0.6705,
|
772 |
+
"step": 2180
|
773 |
+
},
|
774 |
+
{
|
775 |
+
"epoch": 15.770609318996415,
|
776 |
+
"grad_norm": 4.029461860656738,
|
777 |
+
"learning_rate": 0.0001878787878787879,
|
778 |
+
"loss": 0.6342,
|
779 |
+
"step": 2200
|
780 |
+
},
|
781 |
+
{
|
782 |
+
"epoch": 15.913978494623656,
|
783 |
+
"grad_norm": 4.160161972045898,
|
784 |
+
"learning_rate": 0.00018776334776334777,
|
785 |
+
"loss": 0.636,
|
786 |
+
"step": 2220
|
787 |
+
},
|
788 |
+
{
|
789 |
+
"epoch": 16.057347670250895,
|
790 |
+
"grad_norm": 3.1228997707366943,
|
791 |
+
"learning_rate": 0.00018764790764790764,
|
792 |
+
"loss": 0.6491,
|
793 |
+
"step": 2240
|
794 |
+
},
|
795 |
+
{
|
796 |
+
"epoch": 16.200716845878137,
|
797 |
+
"grad_norm": 5.732697486877441,
|
798 |
+
"learning_rate": 0.00018753246753246754,
|
799 |
+
"loss": 0.5499,
|
800 |
+
"step": 2260
|
801 |
+
},
|
802 |
+
{
|
803 |
+
"epoch": 16.344086021505376,
|
804 |
+
"grad_norm": 3.855351448059082,
|
805 |
+
"learning_rate": 0.00018741702741702741,
|
806 |
+
"loss": 0.5809,
|
807 |
+
"step": 2280
|
808 |
+
},
|
809 |
+
{
|
810 |
+
"epoch": 16.487455197132615,
|
811 |
+
"grad_norm": 4.892947673797607,
|
812 |
+
"learning_rate": 0.00018730158730158731,
|
813 |
+
"loss": 0.5962,
|
814 |
+
"step": 2300
|
815 |
+
},
|
816 |
+
{
|
817 |
+
"epoch": 16.630824372759857,
|
818 |
+
"grad_norm": 3.2525179386138916,
|
819 |
+
"learning_rate": 0.0001871861471861472,
|
820 |
+
"loss": 0.6289,
|
821 |
+
"step": 2320
|
822 |
+
},
|
823 |
+
{
|
824 |
+
"epoch": 16.774193548387096,
|
825 |
+
"grad_norm": 3.8182177543640137,
|
826 |
+
"learning_rate": 0.0001870707070707071,
|
827 |
+
"loss": 0.6763,
|
828 |
+
"step": 2340
|
829 |
+
},
|
830 |
+
{
|
831 |
+
"epoch": 16.91756272401434,
|
832 |
+
"grad_norm": 4.179948329925537,
|
833 |
+
"learning_rate": 0.00018695526695526696,
|
834 |
+
"loss": 0.6172,
|
835 |
+
"step": 2360
|
836 |
+
},
|
837 |
+
{
|
838 |
+
"epoch": 17.060931899641577,
|
839 |
+
"grad_norm": 4.481749057769775,
|
840 |
+
"learning_rate": 0.00018683982683982686,
|
841 |
+
"loss": 0.5805,
|
842 |
+
"step": 2380
|
843 |
+
},
|
844 |
+
{
|
845 |
+
"epoch": 17.204301075268816,
|
846 |
+
"grad_norm": 3.459740400314331,
|
847 |
+
"learning_rate": 0.00018672438672438674,
|
848 |
+
"loss": 0.525,
|
849 |
+
"step": 2400
|
850 |
+
},
|
851 |
+
{
|
852 |
+
"epoch": 17.34767025089606,
|
853 |
+
"grad_norm": 4.321086883544922,
|
854 |
+
"learning_rate": 0.0001866089466089466,
|
855 |
+
"loss": 0.578,
|
856 |
+
"step": 2420
|
857 |
+
},
|
858 |
+
{
|
859 |
+
"epoch": 17.491039426523297,
|
860 |
+
"grad_norm": 3.591439962387085,
|
861 |
+
"learning_rate": 0.0001864935064935065,
|
862 |
+
"loss": 0.6128,
|
863 |
+
"step": 2440
|
864 |
+
},
|
865 |
+
{
|
866 |
+
"epoch": 17.634408602150536,
|
867 |
+
"grad_norm": 4.735933780670166,
|
868 |
+
"learning_rate": 0.00018637806637806638,
|
869 |
+
"loss": 0.5629,
|
870 |
+
"step": 2460
|
871 |
+
},
|
872 |
+
{
|
873 |
+
"epoch": 17.77777777777778,
|
874 |
+
"grad_norm": 4.053983688354492,
|
875 |
+
"learning_rate": 0.00018626262626262628,
|
876 |
+
"loss": 0.6315,
|
877 |
+
"step": 2480
|
878 |
+
},
|
879 |
+
{
|
880 |
+
"epoch": 17.921146953405017,
|
881 |
+
"grad_norm": 4.15818452835083,
|
882 |
+
"learning_rate": 0.00018614718614718616,
|
883 |
+
"loss": 0.5813,
|
884 |
+
"step": 2500
|
885 |
+
},
|
886 |
+
{
|
887 |
+
"epoch": 18.06451612903226,
|
888 |
+
"grad_norm": 4.635441303253174,
|
889 |
+
"learning_rate": 0.00018603174603174606,
|
890 |
+
"loss": 0.5661,
|
891 |
+
"step": 2520
|
892 |
+
},
|
893 |
+
{
|
894 |
+
"epoch": 18.2078853046595,
|
895 |
+
"grad_norm": 4.151346206665039,
|
896 |
+
"learning_rate": 0.00018591630591630593,
|
897 |
+
"loss": 0.5588,
|
898 |
+
"step": 2540
|
899 |
+
},
|
900 |
+
{
|
901 |
+
"epoch": 18.351254480286737,
|
902 |
+
"grad_norm": 3.2103450298309326,
|
903 |
+
"learning_rate": 0.00018580086580086583,
|
904 |
+
"loss": 0.5348,
|
905 |
+
"step": 2560
|
906 |
+
},
|
907 |
+
{
|
908 |
+
"epoch": 18.49462365591398,
|
909 |
+
"grad_norm": 3.5987372398376465,
|
910 |
+
"learning_rate": 0.00018568542568542568,
|
911 |
+
"loss": 0.5488,
|
912 |
+
"step": 2580
|
913 |
+
},
|
914 |
+
{
|
915 |
+
"epoch": 18.63799283154122,
|
916 |
+
"grad_norm": 3.638810873031616,
|
917 |
+
"learning_rate": 0.00018556998556998558,
|
918 |
+
"loss": 0.5712,
|
919 |
+
"step": 2600
|
920 |
+
},
|
921 |
+
{
|
922 |
+
"epoch": 18.781362007168457,
|
923 |
+
"grad_norm": 4.3519086837768555,
|
924 |
+
"learning_rate": 0.00018545454545454545,
|
925 |
+
"loss": 0.5295,
|
926 |
+
"step": 2620
|
927 |
+
},
|
928 |
+
{
|
929 |
+
"epoch": 18.9247311827957,
|
930 |
+
"grad_norm": 4.117532253265381,
|
931 |
+
"learning_rate": 0.00018533910533910535,
|
932 |
+
"loss": 0.588,
|
933 |
+
"step": 2640
|
934 |
+
},
|
935 |
+
{
|
936 |
+
"epoch": 19.06810035842294,
|
937 |
+
"grad_norm": 3.9326632022857666,
|
938 |
+
"learning_rate": 0.00018522366522366523,
|
939 |
+
"loss": 0.5676,
|
940 |
+
"step": 2660
|
941 |
+
},
|
942 |
+
{
|
943 |
+
"epoch": 19.211469534050178,
|
944 |
+
"grad_norm": 3.967031717300415,
|
945 |
+
"learning_rate": 0.00018510822510822513,
|
946 |
+
"loss": 0.5477,
|
947 |
+
"step": 2680
|
948 |
+
},
|
949 |
+
{
|
950 |
+
"epoch": 19.35483870967742,
|
951 |
+
"grad_norm": 3.7262048721313477,
|
952 |
+
"learning_rate": 0.000184992784992785,
|
953 |
+
"loss": 0.5448,
|
954 |
+
"step": 2700
|
955 |
+
},
|
956 |
+
{
|
957 |
+
"epoch": 19.49820788530466,
|
958 |
+
"grad_norm": 6.239511489868164,
|
959 |
+
"learning_rate": 0.0001848773448773449,
|
960 |
+
"loss": 0.4948,
|
961 |
+
"step": 2720
|
962 |
+
},
|
963 |
+
{
|
964 |
+
"epoch": 19.6415770609319,
|
965 |
+
"grad_norm": 4.259354114532471,
|
966 |
+
"learning_rate": 0.00018476190476190478,
|
967 |
+
"loss": 0.5091,
|
968 |
+
"step": 2740
|
969 |
+
},
|
970 |
+
{
|
971 |
+
"epoch": 19.78494623655914,
|
972 |
+
"grad_norm": 3.851757526397705,
|
973 |
+
"learning_rate": 0.00018464646464646465,
|
974 |
+
"loss": 0.5246,
|
975 |
+
"step": 2760
|
976 |
+
},
|
977 |
+
{
|
978 |
+
"epoch": 19.92831541218638,
|
979 |
+
"grad_norm": 4.161237716674805,
|
980 |
+
"learning_rate": 0.00018453102453102452,
|
981 |
+
"loss": 0.561,
|
982 |
+
"step": 2780
|
983 |
+
},
|
984 |
+
{
|
985 |
+
"epoch": 20.07168458781362,
|
986 |
+
"grad_norm": 3.4905500411987305,
|
987 |
+
"learning_rate": 0.00018441558441558442,
|
988 |
+
"loss": 0.5089,
|
989 |
+
"step": 2800
|
990 |
+
},
|
991 |
+
{
|
992 |
+
"epoch": 20.21505376344086,
|
993 |
+
"grad_norm": 4.338738918304443,
|
994 |
+
"learning_rate": 0.0001843001443001443,
|
995 |
+
"loss": 0.4543,
|
996 |
+
"step": 2820
|
997 |
+
},
|
998 |
+
{
|
999 |
+
"epoch": 20.3584229390681,
|
1000 |
+
"grad_norm": 3.200549840927124,
|
1001 |
+
"learning_rate": 0.0001841847041847042,
|
1002 |
+
"loss": 0.51,
|
1003 |
+
"step": 2840
|
1004 |
+
},
|
1005 |
+
{
|
1006 |
+
"epoch": 20.50179211469534,
|
1007 |
+
"grad_norm": 4.969254016876221,
|
1008 |
+
"learning_rate": 0.00018406926406926407,
|
1009 |
+
"loss": 0.5493,
|
1010 |
+
"step": 2860
|
1011 |
+
},
|
1012 |
+
{
|
1013 |
+
"epoch": 20.64516129032258,
|
1014 |
+
"grad_norm": 5.882287979125977,
|
1015 |
+
"learning_rate": 0.00018395382395382397,
|
1016 |
+
"loss": 0.5594,
|
1017 |
+
"step": 2880
|
1018 |
+
},
|
1019 |
+
{
|
1020 |
+
"epoch": 20.788530465949822,
|
1021 |
+
"grad_norm": 4.375141143798828,
|
1022 |
+
"learning_rate": 0.00018383838383838384,
|
1023 |
+
"loss": 0.4904,
|
1024 |
+
"step": 2900
|
1025 |
+
},
|
1026 |
+
{
|
1027 |
+
"epoch": 20.93189964157706,
|
1028 |
+
"grad_norm": 5.635257720947266,
|
1029 |
+
"learning_rate": 0.00018372294372294375,
|
1030 |
+
"loss": 0.5015,
|
1031 |
+
"step": 2920
|
1032 |
+
},
|
1033 |
+
{
|
1034 |
+
"epoch": 21.0752688172043,
|
1035 |
+
"grad_norm": 4.052358150482178,
|
1036 |
+
"learning_rate": 0.00018360750360750362,
|
1037 |
+
"loss": 0.5043,
|
1038 |
+
"step": 2940
|
1039 |
+
},
|
1040 |
+
{
|
1041 |
+
"epoch": 21.218637992831543,
|
1042 |
+
"grad_norm": 3.6945507526397705,
|
1043 |
+
"learning_rate": 0.0001834920634920635,
|
1044 |
+
"loss": 0.5193,
|
1045 |
+
"step": 2960
|
1046 |
+
},
|
1047 |
+
{
|
1048 |
+
"epoch": 21.36200716845878,
|
1049 |
+
"grad_norm": 3.5928592681884766,
|
1050 |
+
"learning_rate": 0.0001833766233766234,
|
1051 |
+
"loss": 0.4771,
|
1052 |
+
"step": 2980
|
1053 |
+
},
|
1054 |
+
{
|
1055 |
+
"epoch": 21.50537634408602,
|
1056 |
+
"grad_norm": 3.8914806842803955,
|
1057 |
+
"learning_rate": 0.00018326118326118327,
|
1058 |
+
"loss": 0.4604,
|
1059 |
+
"step": 3000
|
1060 |
+
},
|
1061 |
+
{
|
1062 |
+
"epoch": 21.648745519713263,
|
1063 |
+
"grad_norm": 4.555027961730957,
|
1064 |
+
"learning_rate": 0.00018314574314574317,
|
1065 |
+
"loss": 0.4799,
|
1066 |
+
"step": 3020
|
1067 |
+
},
|
1068 |
+
{
|
1069 |
+
"epoch": 21.7921146953405,
|
1070 |
+
"grad_norm": 4.636914253234863,
|
1071 |
+
"learning_rate": 0.00018303030303030304,
|
1072 |
+
"loss": 0.4556,
|
1073 |
+
"step": 3040
|
1074 |
+
},
|
1075 |
+
{
|
1076 |
+
"epoch": 21.93548387096774,
|
1077 |
+
"grad_norm": 3.740828037261963,
|
1078 |
+
"learning_rate": 0.00018291486291486294,
|
1079 |
+
"loss": 0.5132,
|
1080 |
+
"step": 3060
|
1081 |
+
},
|
1082 |
+
{
|
1083 |
+
"epoch": 22.078853046594983,
|
1084 |
+
"grad_norm": 3.5043046474456787,
|
1085 |
+
"learning_rate": 0.00018279942279942281,
|
1086 |
+
"loss": 0.4834,
|
1087 |
+
"step": 3080
|
1088 |
+
},
|
1089 |
+
{
|
1090 |
+
"epoch": 22.22222222222222,
|
1091 |
+
"grad_norm": 5.914973258972168,
|
1092 |
+
"learning_rate": 0.00018268398268398272,
|
1093 |
+
"loss": 0.4751,
|
1094 |
+
"step": 3100
|
1095 |
+
},
|
1096 |
+
{
|
1097 |
+
"epoch": 22.365591397849464,
|
1098 |
+
"grad_norm": 3.935854434967041,
|
1099 |
+
"learning_rate": 0.00018256854256854256,
|
1100 |
+
"loss": 0.4742,
|
1101 |
+
"step": 3120
|
1102 |
+
},
|
1103 |
+
{
|
1104 |
+
"epoch": 22.508960573476703,
|
1105 |
+
"grad_norm": 4.205220699310303,
|
1106 |
+
"learning_rate": 0.00018245310245310246,
|
1107 |
+
"loss": 0.4726,
|
1108 |
+
"step": 3140
|
1109 |
+
},
|
1110 |
+
{
|
1111 |
+
"epoch": 22.65232974910394,
|
1112 |
+
"grad_norm": 3.5910654067993164,
|
1113 |
+
"learning_rate": 0.00018233766233766234,
|
1114 |
+
"loss": 0.4551,
|
1115 |
+
"step": 3160
|
1116 |
+
},
|
1117 |
+
{
|
1118 |
+
"epoch": 22.795698924731184,
|
1119 |
+
"grad_norm": 4.200057029724121,
|
1120 |
+
"learning_rate": 0.00018222222222222224,
|
1121 |
+
"loss": 0.4513,
|
1122 |
+
"step": 3180
|
1123 |
+
},
|
1124 |
+
{
|
1125 |
+
"epoch": 22.939068100358423,
|
1126 |
+
"grad_norm": 3.9215588569641113,
|
1127 |
+
"learning_rate": 0.0001821067821067821,
|
1128 |
+
"loss": 0.4887,
|
1129 |
+
"step": 3200
|
1130 |
+
},
|
1131 |
+
{
|
1132 |
+
"epoch": 23.08243727598566,
|
1133 |
+
"grad_norm": 5.426336288452148,
|
1134 |
+
"learning_rate": 0.000181991341991342,
|
1135 |
+
"loss": 0.4311,
|
1136 |
+
"step": 3220
|
1137 |
+
},
|
1138 |
+
{
|
1139 |
+
"epoch": 23.225806451612904,
|
1140 |
+
"grad_norm": 5.736265182495117,
|
1141 |
+
"learning_rate": 0.00018187590187590188,
|
1142 |
+
"loss": 0.4004,
|
1143 |
+
"step": 3240
|
1144 |
+
},
|
1145 |
+
{
|
1146 |
+
"epoch": 23.369175627240143,
|
1147 |
+
"grad_norm": 5.350865840911865,
|
1148 |
+
"learning_rate": 0.00018176046176046178,
|
1149 |
+
"loss": 0.4655,
|
1150 |
+
"step": 3260
|
1151 |
+
},
|
1152 |
+
{
|
1153 |
+
"epoch": 23.512544802867385,
|
1154 |
+
"grad_norm": 3.840571165084839,
|
1155 |
+
"learning_rate": 0.00018164502164502166,
|
1156 |
+
"loss": 0.4935,
|
1157 |
+
"step": 3280
|
1158 |
+
},
|
1159 |
+
{
|
1160 |
+
"epoch": 23.655913978494624,
|
1161 |
+
"grad_norm": 4.473032474517822,
|
1162 |
+
"learning_rate": 0.00018152958152958153,
|
1163 |
+
"loss": 0.4499,
|
1164 |
+
"step": 3300
|
1165 |
+
},
|
1166 |
+
{
|
1167 |
+
"epoch": 23.799283154121863,
|
1168 |
+
"grad_norm": 4.150224685668945,
|
1169 |
+
"learning_rate": 0.0001814141414141414,
|
1170 |
+
"loss": 0.43,
|
1171 |
+
"step": 3320
|
1172 |
+
},
|
1173 |
+
{
|
1174 |
+
"epoch": 23.942652329749105,
|
1175 |
+
"grad_norm": 4.022675037384033,
|
1176 |
+
"learning_rate": 0.0001812987012987013,
|
1177 |
+
"loss": 0.4635,
|
1178 |
+
"step": 3340
|
1179 |
+
},
|
1180 |
+
{
|
1181 |
+
"epoch": 24.086021505376344,
|
1182 |
+
"grad_norm": 4.3577961921691895,
|
1183 |
+
"learning_rate": 0.00018118326118326118,
|
1184 |
+
"loss": 0.4399,
|
1185 |
+
"step": 3360
|
1186 |
+
},
|
1187 |
+
{
|
1188 |
+
"epoch": 24.229390681003583,
|
1189 |
+
"grad_norm": 4.307856559753418,
|
1190 |
+
"learning_rate": 0.00018106782106782108,
|
1191 |
+
"loss": 0.4369,
|
1192 |
+
"step": 3380
|
1193 |
+
},
|
1194 |
+
{
|
1195 |
+
"epoch": 24.372759856630825,
|
1196 |
+
"grad_norm": 3.8509104251861572,
|
1197 |
+
"learning_rate": 0.00018095238095238095,
|
1198 |
+
"loss": 0.396,
|
1199 |
+
"step": 3400
|
1200 |
+
},
|
1201 |
+
{
|
1202 |
+
"epoch": 24.516129032258064,
|
1203 |
+
"grad_norm": 4.024786949157715,
|
1204 |
+
"learning_rate": 0.00018083694083694085,
|
1205 |
+
"loss": 0.4283,
|
1206 |
+
"step": 3420
|
1207 |
+
},
|
1208 |
+
{
|
1209 |
+
"epoch": 24.659498207885306,
|
1210 |
+
"grad_norm": 4.666787624359131,
|
1211 |
+
"learning_rate": 0.00018072150072150073,
|
1212 |
+
"loss": 0.4333,
|
1213 |
+
"step": 3440
|
1214 |
+
},
|
1215 |
+
{
|
1216 |
+
"epoch": 24.802867383512545,
|
1217 |
+
"grad_norm": 3.9275686740875244,
|
1218 |
+
"learning_rate": 0.00018060606060606063,
|
1219 |
+
"loss": 0.4453,
|
1220 |
+
"step": 3460
|
1221 |
+
},
|
1222 |
+
{
|
1223 |
+
"epoch": 24.946236559139784,
|
1224 |
+
"grad_norm": 4.202296733856201,
|
1225 |
+
"learning_rate": 0.0001804906204906205,
|
1226 |
+
"loss": 0.4556,
|
1227 |
+
"step": 3480
|
1228 |
+
},
|
1229 |
+
{
|
1230 |
+
"epoch": 25.089605734767026,
|
1231 |
+
"grad_norm": 4.293205738067627,
|
1232 |
+
"learning_rate": 0.00018037518037518038,
|
1233 |
+
"loss": 0.3734,
|
1234 |
+
"step": 3500
|
1235 |
+
},
|
1236 |
+
{
|
1237 |
+
"epoch": 25.232974910394265,
|
1238 |
+
"grad_norm": 4.109980583190918,
|
1239 |
+
"learning_rate": 0.00018025974025974025,
|
1240 |
+
"loss": 0.3765,
|
1241 |
+
"step": 3520
|
1242 |
+
},
|
1243 |
+
{
|
1244 |
+
"epoch": 25.376344086021504,
|
1245 |
+
"grad_norm": 3.595794200897217,
|
1246 |
+
"learning_rate": 0.00018014430014430015,
|
1247 |
+
"loss": 0.4052,
|
1248 |
+
"step": 3540
|
1249 |
+
},
|
1250 |
+
{
|
1251 |
+
"epoch": 25.519713261648747,
|
1252 |
+
"grad_norm": 3.6639111042022705,
|
1253 |
+
"learning_rate": 0.00018002886002886002,
|
1254 |
+
"loss": 0.44,
|
1255 |
+
"step": 3560
|
1256 |
+
},
|
1257 |
+
{
|
1258 |
+
"epoch": 25.663082437275985,
|
1259 |
+
"grad_norm": 4.5247931480407715,
|
1260 |
+
"learning_rate": 0.00017991341991341992,
|
1261 |
+
"loss": 0.4004,
|
1262 |
+
"step": 3580
|
1263 |
+
},
|
1264 |
+
{
|
1265 |
+
"epoch": 25.806451612903224,
|
1266 |
+
"grad_norm": 3.711890697479248,
|
1267 |
+
"learning_rate": 0.0001797979797979798,
|
1268 |
+
"loss": 0.4452,
|
1269 |
+
"step": 3600
|
1270 |
+
},
|
1271 |
+
{
|
1272 |
+
"epoch": 25.949820788530467,
|
1273 |
+
"grad_norm": 5.131597518920898,
|
1274 |
+
"learning_rate": 0.0001796825396825397,
|
1275 |
+
"loss": 0.476,
|
1276 |
+
"step": 3620
|
1277 |
+
},
|
1278 |
+
{
|
1279 |
+
"epoch": 26.093189964157705,
|
1280 |
+
"grad_norm": 3.825037956237793,
|
1281 |
+
"learning_rate": 0.00017956709956709957,
|
1282 |
+
"loss": 0.369,
|
1283 |
+
"step": 3640
|
1284 |
+
},
|
1285 |
+
{
|
1286 |
+
"epoch": 26.236559139784948,
|
1287 |
+
"grad_norm": 4.446529865264893,
|
1288 |
+
"learning_rate": 0.00017945165945165947,
|
1289 |
+
"loss": 0.3898,
|
1290 |
+
"step": 3660
|
1291 |
+
},
|
1292 |
+
{
|
1293 |
+
"epoch": 26.379928315412187,
|
1294 |
+
"grad_norm": 3.0329320430755615,
|
1295 |
+
"learning_rate": 0.00017933621933621934,
|
1296 |
+
"loss": 0.3671,
|
1297 |
+
"step": 3680
|
1298 |
+
},
|
1299 |
+
{
|
1300 |
+
"epoch": 26.523297491039425,
|
1301 |
+
"grad_norm": 4.175711631774902,
|
1302 |
+
"learning_rate": 0.00017922077922077922,
|
1303 |
+
"loss": 0.3932,
|
1304 |
+
"step": 3700
|
1305 |
+
},
|
1306 |
+
{
|
1307 |
+
"epoch": 26.666666666666668,
|
1308 |
+
"grad_norm": 3.5688698291778564,
|
1309 |
+
"learning_rate": 0.00017910533910533912,
|
1310 |
+
"loss": 0.4308,
|
1311 |
+
"step": 3720
|
1312 |
+
},
|
1313 |
+
{
|
1314 |
+
"epoch": 26.810035842293907,
|
1315 |
+
"grad_norm": 5.509890556335449,
|
1316 |
+
"learning_rate": 0.000178989898989899,
|
1317 |
+
"loss": 0.3667,
|
1318 |
+
"step": 3740
|
1319 |
+
},
|
1320 |
+
{
|
1321 |
+
"epoch": 26.953405017921146,
|
1322 |
+
"grad_norm": 5.023184776306152,
|
1323 |
+
"learning_rate": 0.0001788744588744589,
|
1324 |
+
"loss": 0.4775,
|
1325 |
+
"step": 3760
|
1326 |
+
},
|
1327 |
+
{
|
1328 |
+
"epoch": 27.096774193548388,
|
1329 |
+
"grad_norm": 4.032219886779785,
|
1330 |
+
"learning_rate": 0.00017875901875901877,
|
1331 |
+
"loss": 0.4131,
|
1332 |
+
"step": 3780
|
1333 |
+
},
|
1334 |
+
{
|
1335 |
+
"epoch": 27.240143369175627,
|
1336 |
+
"grad_norm": 4.195873737335205,
|
1337 |
+
"learning_rate": 0.00017864357864357867,
|
1338 |
+
"loss": 0.3387,
|
1339 |
+
"step": 3800
|
1340 |
+
},
|
1341 |
+
{
|
1342 |
+
"epoch": 27.38351254480287,
|
1343 |
+
"grad_norm": 4.665581703186035,
|
1344 |
+
"learning_rate": 0.00017852813852813854,
|
1345 |
+
"loss": 0.414,
|
1346 |
+
"step": 3820
|
1347 |
+
},
|
1348 |
+
{
|
1349 |
+
"epoch": 27.526881720430108,
|
1350 |
+
"grad_norm": 4.608016490936279,
|
1351 |
+
"learning_rate": 0.00017841269841269844,
|
1352 |
+
"loss": 0.3583,
|
1353 |
+
"step": 3840
|
1354 |
+
},
|
1355 |
+
{
|
1356 |
+
"epoch": 27.670250896057347,
|
1357 |
+
"grad_norm": 7.6718854904174805,
|
1358 |
+
"learning_rate": 0.0001782972582972583,
|
1359 |
+
"loss": 0.401,
|
1360 |
+
"step": 3860
|
1361 |
+
},
|
1362 |
+
{
|
1363 |
+
"epoch": 27.81362007168459,
|
1364 |
+
"grad_norm": 6.262495994567871,
|
1365 |
+
"learning_rate": 0.0001781818181818182,
|
1366 |
+
"loss": 0.386,
|
1367 |
+
"step": 3880
|
1368 |
+
},
|
1369 |
+
{
|
1370 |
+
"epoch": 27.956989247311828,
|
1371 |
+
"grad_norm": 5.654719829559326,
|
1372 |
+
"learning_rate": 0.00017806637806637806,
|
1373 |
+
"loss": 0.3942,
|
1374 |
+
"step": 3900
|
1375 |
+
},
|
1376 |
+
{
|
1377 |
+
"epoch": 28.100358422939067,
|
1378 |
+
"grad_norm": 3.569892406463623,
|
1379 |
+
"learning_rate": 0.00017795093795093796,
|
1380 |
+
"loss": 0.3701,
|
1381 |
+
"step": 3920
|
1382 |
+
},
|
1383 |
+
{
|
1384 |
+
"epoch": 28.24372759856631,
|
1385 |
+
"grad_norm": 3.7804338932037354,
|
1386 |
+
"learning_rate": 0.00017783549783549784,
|
1387 |
+
"loss": 0.3829,
|
1388 |
+
"step": 3940
|
1389 |
+
},
|
1390 |
+
{
|
1391 |
+
"epoch": 28.387096774193548,
|
1392 |
+
"grad_norm": 5.116115093231201,
|
1393 |
+
"learning_rate": 0.00017772005772005774,
|
1394 |
+
"loss": 0.3774,
|
1395 |
+
"step": 3960
|
1396 |
+
},
|
1397 |
+
{
|
1398 |
+
"epoch": 28.530465949820787,
|
1399 |
+
"grad_norm": 4.543453693389893,
|
1400 |
+
"learning_rate": 0.0001776046176046176,
|
1401 |
+
"loss": 0.3319,
|
1402 |
+
"step": 3980
|
1403 |
+
},
|
1404 |
+
{
|
1405 |
+
"epoch": 28.67383512544803,
|
1406 |
+
"grad_norm": 4.088935852050781,
|
1407 |
+
"learning_rate": 0.0001774891774891775,
|
1408 |
+
"loss": 0.3457,
|
1409 |
+
"step": 4000
|
1410 |
+
}
|
1411 |
+
],
|
1412 |
+
"logging_steps": 20,
|
1413 |
+
"max_steps": 34750,
|
1414 |
+
"num_input_tokens_seen": 0,
|
1415 |
+
"num_train_epochs": 250,
|
1416 |
+
"save_steps": 500,
|
1417 |
+
"stateful_callbacks": {
|
1418 |
+
"TrainerControl": {
|
1419 |
+
"args": {
|
1420 |
+
"should_epoch_stop": false,
|
1421 |
+
"should_evaluate": false,
|
1422 |
+
"should_log": false,
|
1423 |
+
"should_save": true,
|
1424 |
+
"should_training_stop": false
|
1425 |
+
},
|
1426 |
+
"attributes": {}
|
1427 |
+
}
|
1428 |
+
},
|
1429 |
+
"total_flos": 5.079524906326426e+16,
|
1430 |
+
"train_batch_size": 1,
|
1431 |
+
"trial_name": null,
|
1432 |
+
"trial_params": null
|
1433 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4c258ee0280ae7ddfcc1b75e5b74216e64bb35fa37a41ed23a127e6b296370c8
|
3 |
+
size 5368
|