Upload folder using huggingface_hub
Browse files- README.md +202 -3
- adapter_config.json +37 -0
- adapter_model.safetensors +3 -0
- optimizer.pt +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +34 -0
- tokenizer.model +3 -0
- tokenizer_config.json +2016 -0
- trainer_state.json +2346 -0
- training_args.bin +3 -0
README.md
CHANGED
@@ -1,3 +1,202 @@
|
|
1 |
-
---
|
2 |
-
|
3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
base_model: google/gemma-2-9b-it
|
3 |
+
library_name: peft
|
4 |
+
---
|
5 |
+
|
6 |
+
# Model Card for Model ID
|
7 |
+
|
8 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
9 |
+
|
10 |
+
|
11 |
+
|
12 |
+
## Model Details
|
13 |
+
|
14 |
+
### Model Description
|
15 |
+
|
16 |
+
<!-- Provide a longer summary of what this model is. -->
|
17 |
+
|
18 |
+
|
19 |
+
|
20 |
+
- **Developed by:** [More Information Needed]
|
21 |
+
- **Funded by [optional]:** [More Information Needed]
|
22 |
+
- **Shared by [optional]:** [More Information Needed]
|
23 |
+
- **Model type:** [More Information Needed]
|
24 |
+
- **Language(s) (NLP):** [More Information Needed]
|
25 |
+
- **License:** [More Information Needed]
|
26 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
27 |
+
|
28 |
+
### Model Sources [optional]
|
29 |
+
|
30 |
+
<!-- Provide the basic links for the model. -->
|
31 |
+
|
32 |
+
- **Repository:** [More Information Needed]
|
33 |
+
- **Paper [optional]:** [More Information Needed]
|
34 |
+
- **Demo [optional]:** [More Information Needed]
|
35 |
+
|
36 |
+
## Uses
|
37 |
+
|
38 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
39 |
+
|
40 |
+
### Direct Use
|
41 |
+
|
42 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
43 |
+
|
44 |
+
[More Information Needed]
|
45 |
+
|
46 |
+
### Downstream Use [optional]
|
47 |
+
|
48 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
49 |
+
|
50 |
+
[More Information Needed]
|
51 |
+
|
52 |
+
### Out-of-Scope Use
|
53 |
+
|
54 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
55 |
+
|
56 |
+
[More Information Needed]
|
57 |
+
|
58 |
+
## Bias, Risks, and Limitations
|
59 |
+
|
60 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
61 |
+
|
62 |
+
[More Information Needed]
|
63 |
+
|
64 |
+
### Recommendations
|
65 |
+
|
66 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
67 |
+
|
68 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
69 |
+
|
70 |
+
## How to Get Started with the Model
|
71 |
+
|
72 |
+
Use the code below to get started with the model.
|
73 |
+
|
74 |
+
[More Information Needed]
|
75 |
+
|
76 |
+
## Training Details
|
77 |
+
|
78 |
+
### Training Data
|
79 |
+
|
80 |
+
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
81 |
+
|
82 |
+
[More Information Needed]
|
83 |
+
|
84 |
+
### Training Procedure
|
85 |
+
|
86 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
87 |
+
|
88 |
+
#### Preprocessing [optional]
|
89 |
+
|
90 |
+
[More Information Needed]
|
91 |
+
|
92 |
+
|
93 |
+
#### Training Hyperparameters
|
94 |
+
|
95 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
96 |
+
|
97 |
+
#### Speeds, Sizes, Times [optional]
|
98 |
+
|
99 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
100 |
+
|
101 |
+
[More Information Needed]
|
102 |
+
|
103 |
+
## Evaluation
|
104 |
+
|
105 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
106 |
+
|
107 |
+
### Testing Data, Factors & Metrics
|
108 |
+
|
109 |
+
#### Testing Data
|
110 |
+
|
111 |
+
<!-- This should link to a Dataset Card if possible. -->
|
112 |
+
|
113 |
+
[More Information Needed]
|
114 |
+
|
115 |
+
#### Factors
|
116 |
+
|
117 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
118 |
+
|
119 |
+
[More Information Needed]
|
120 |
+
|
121 |
+
#### Metrics
|
122 |
+
|
123 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
124 |
+
|
125 |
+
[More Information Needed]
|
126 |
+
|
127 |
+
### Results
|
128 |
+
|
129 |
+
[More Information Needed]
|
130 |
+
|
131 |
+
#### Summary
|
132 |
+
|
133 |
+
|
134 |
+
|
135 |
+
## Model Examination [optional]
|
136 |
+
|
137 |
+
<!-- Relevant interpretability work for the model goes here -->
|
138 |
+
|
139 |
+
[More Information Needed]
|
140 |
+
|
141 |
+
## Environmental Impact
|
142 |
+
|
143 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
144 |
+
|
145 |
+
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
146 |
+
|
147 |
+
- **Hardware Type:** [More Information Needed]
|
148 |
+
- **Hours used:** [More Information Needed]
|
149 |
+
- **Cloud Provider:** [More Information Needed]
|
150 |
+
- **Compute Region:** [More Information Needed]
|
151 |
+
- **Carbon Emitted:** [More Information Needed]
|
152 |
+
|
153 |
+
## Technical Specifications [optional]
|
154 |
+
|
155 |
+
### Model Architecture and Objective
|
156 |
+
|
157 |
+
[More Information Needed]
|
158 |
+
|
159 |
+
### Compute Infrastructure
|
160 |
+
|
161 |
+
[More Information Needed]
|
162 |
+
|
163 |
+
#### Hardware
|
164 |
+
|
165 |
+
[More Information Needed]
|
166 |
+
|
167 |
+
#### Software
|
168 |
+
|
169 |
+
[More Information Needed]
|
170 |
+
|
171 |
+
## Citation [optional]
|
172 |
+
|
173 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
174 |
+
|
175 |
+
**BibTeX:**
|
176 |
+
|
177 |
+
[More Information Needed]
|
178 |
+
|
179 |
+
**APA:**
|
180 |
+
|
181 |
+
[More Information Needed]
|
182 |
+
|
183 |
+
## Glossary [optional]
|
184 |
+
|
185 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
186 |
+
|
187 |
+
[More Information Needed]
|
188 |
+
|
189 |
+
## More Information [optional]
|
190 |
+
|
191 |
+
[More Information Needed]
|
192 |
+
|
193 |
+
## Model Card Authors [optional]
|
194 |
+
|
195 |
+
[More Information Needed]
|
196 |
+
|
197 |
+
## Model Card Contact
|
198 |
+
|
199 |
+
[More Information Needed]
|
200 |
+
### Framework versions
|
201 |
+
|
202 |
+
- PEFT 0.14.0
|
adapter_config.json
ADDED
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "google/gemma-2-9b-it",
|
5 |
+
"bias": "none",
|
6 |
+
"eva_config": null,
|
7 |
+
"exclude_modules": null,
|
8 |
+
"fan_in_fan_out": false,
|
9 |
+
"inference_mode": true,
|
10 |
+
"init_lora_weights": true,
|
11 |
+
"layer_replication": null,
|
12 |
+
"layers_pattern": null,
|
13 |
+
"layers_to_transform": null,
|
14 |
+
"loftq_config": {},
|
15 |
+
"lora_alpha": 16,
|
16 |
+
"lora_bias": false,
|
17 |
+
"lora_dropout": 0.05,
|
18 |
+
"megatron_config": null,
|
19 |
+
"megatron_core": "megatron.core",
|
20 |
+
"modules_to_save": null,
|
21 |
+
"peft_type": "LORA",
|
22 |
+
"r": 16,
|
23 |
+
"rank_pattern": {},
|
24 |
+
"revision": null,
|
25 |
+
"target_modules": [
|
26 |
+
"gate_proj",
|
27 |
+
"q_proj",
|
28 |
+
"down_proj",
|
29 |
+
"v_proj",
|
30 |
+
"o_proj",
|
31 |
+
"k_proj",
|
32 |
+
"up_proj"
|
33 |
+
],
|
34 |
+
"task_type": "CAUSAL_LM",
|
35 |
+
"use_dora": false,
|
36 |
+
"use_rslora": false
|
37 |
+
}
|
adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:10c391ce4d560f44409bbec5dcc7cbf716ff6910ab777ce512e4ec2879df0c16
|
3 |
+
size 216151256
|
optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:034abe2e96a24e54f12c425593751597b0ff80082ebaa06d936206eb04b77d54
|
3 |
+
size 110413252
|
rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a918cf63d229df503d965d3d4a4a352d9ad8d2695297a6bd12ae294b1e49bb58
|
3 |
+
size 14244
|
scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1b8e869b8345fbc3bfaaa014e33e41906b5b0e8f0bba3402e51b046fbf20abe2
|
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.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 +1,2016 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": false,
|
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 |
+
"255968": {
|
1742 |
+
"content": "[toxicity=0]",
|
1743 |
+
"lstrip": false,
|
1744 |
+
"normalized": false,
|
1745 |
+
"rstrip": false,
|
1746 |
+
"single_word": false,
|
1747 |
+
"special": false
|
1748 |
+
},
|
1749 |
+
"255969": {
|
1750 |
+
"content": "\t\t",
|
1751 |
+
"lstrip": false,
|
1752 |
+
"normalized": false,
|
1753 |
+
"rstrip": false,
|
1754 |
+
"single_word": false,
|
1755 |
+
"special": false
|
1756 |
+
},
|
1757 |
+
"255970": {
|
1758 |
+
"content": "\t\t\t",
|
1759 |
+
"lstrip": false,
|
1760 |
+
"normalized": false,
|
1761 |
+
"rstrip": false,
|
1762 |
+
"single_word": false,
|
1763 |
+
"special": false
|
1764 |
+
},
|
1765 |
+
"255971": {
|
1766 |
+
"content": "\t\t\t\t",
|
1767 |
+
"lstrip": false,
|
1768 |
+
"normalized": false,
|
1769 |
+
"rstrip": false,
|
1770 |
+
"single_word": false,
|
1771 |
+
"special": false
|
1772 |
+
},
|
1773 |
+
"255972": {
|
1774 |
+
"content": "\t\t\t\t\t",
|
1775 |
+
"lstrip": false,
|
1776 |
+
"normalized": false,
|
1777 |
+
"rstrip": false,
|
1778 |
+
"single_word": false,
|
1779 |
+
"special": false
|
1780 |
+
},
|
1781 |
+
"255973": {
|
1782 |
+
"content": "\t\t\t\t\t\t",
|
1783 |
+
"lstrip": false,
|
1784 |
+
"normalized": false,
|
1785 |
+
"rstrip": false,
|
1786 |
+
"single_word": false,
|
1787 |
+
"special": false
|
1788 |
+
},
|
1789 |
+
"255974": {
|
1790 |
+
"content": "\t\t\t\t\t\t\t",
|
1791 |
+
"lstrip": false,
|
1792 |
+
"normalized": false,
|
1793 |
+
"rstrip": false,
|
1794 |
+
"single_word": false,
|
1795 |
+
"special": false
|
1796 |
+
},
|
1797 |
+
"255975": {
|
1798 |
+
"content": "\t\t\t\t\t\t\t\t",
|
1799 |
+
"lstrip": false,
|
1800 |
+
"normalized": false,
|
1801 |
+
"rstrip": false,
|
1802 |
+
"single_word": false,
|
1803 |
+
"special": false
|
1804 |
+
},
|
1805 |
+
"255976": {
|
1806 |
+
"content": "\t\t\t\t\t\t\t\t\t",
|
1807 |
+
"lstrip": false,
|
1808 |
+
"normalized": false,
|
1809 |
+
"rstrip": false,
|
1810 |
+
"single_word": false,
|
1811 |
+
"special": false
|
1812 |
+
},
|
1813 |
+
"255977": {
|
1814 |
+
"content": "\t\t\t\t\t\t\t\t\t\t",
|
1815 |
+
"lstrip": false,
|
1816 |
+
"normalized": false,
|
1817 |
+
"rstrip": false,
|
1818 |
+
"single_word": false,
|
1819 |
+
"special": false
|
1820 |
+
},
|
1821 |
+
"255978": {
|
1822 |
+
"content": "\t\t\t\t\t\t\t\t\t\t\t",
|
1823 |
+
"lstrip": false,
|
1824 |
+
"normalized": false,
|
1825 |
+
"rstrip": false,
|
1826 |
+
"single_word": false,
|
1827 |
+
"special": false
|
1828 |
+
},
|
1829 |
+
"255979": {
|
1830 |
+
"content": "\t\t\t\t\t\t\t\t\t\t\t\t",
|
1831 |
+
"lstrip": false,
|
1832 |
+
"normalized": false,
|
1833 |
+
"rstrip": false,
|
1834 |
+
"single_word": false,
|
1835 |
+
"special": false
|
1836 |
+
},
|
1837 |
+
"255980": {
|
1838 |
+
"content": "\t\t\t\t\t\t\t\t\t\t\t\t\t",
|
1839 |
+
"lstrip": false,
|
1840 |
+
"normalized": false,
|
1841 |
+
"rstrip": false,
|
1842 |
+
"single_word": false,
|
1843 |
+
"special": false
|
1844 |
+
},
|
1845 |
+
"255981": {
|
1846 |
+
"content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
|
1847 |
+
"lstrip": false,
|
1848 |
+
"normalized": false,
|
1849 |
+
"rstrip": false,
|
1850 |
+
"single_word": false,
|
1851 |
+
"special": false
|
1852 |
+
},
|
1853 |
+
"255982": {
|
1854 |
+
"content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
|
1855 |
+
"lstrip": false,
|
1856 |
+
"normalized": false,
|
1857 |
+
"rstrip": false,
|
1858 |
+
"single_word": false,
|
1859 |
+
"special": false
|
1860 |
+
},
|
1861 |
+
"255983": {
|
1862 |
+
"content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
|
1863 |
+
"lstrip": false,
|
1864 |
+
"normalized": false,
|
1865 |
+
"rstrip": false,
|
1866 |
+
"single_word": false,
|
1867 |
+
"special": false
|
1868 |
+
},
|
1869 |
+
"255984": {
|
1870 |
+
"content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
|
1871 |
+
"lstrip": false,
|
1872 |
+
"normalized": false,
|
1873 |
+
"rstrip": false,
|
1874 |
+
"single_word": false,
|
1875 |
+
"special": false
|
1876 |
+
},
|
1877 |
+
"255985": {
|
1878 |
+
"content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
|
1879 |
+
"lstrip": false,
|
1880 |
+
"normalized": false,
|
1881 |
+
"rstrip": false,
|
1882 |
+
"single_word": false,
|
1883 |
+
"special": false
|
1884 |
+
},
|
1885 |
+
"255986": {
|
1886 |
+
"content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
|
1887 |
+
"lstrip": false,
|
1888 |
+
"normalized": false,
|
1889 |
+
"rstrip": false,
|
1890 |
+
"single_word": false,
|
1891 |
+
"special": false
|
1892 |
+
},
|
1893 |
+
"255987": {
|
1894 |
+
"content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
|
1895 |
+
"lstrip": false,
|
1896 |
+
"normalized": false,
|
1897 |
+
"rstrip": false,
|
1898 |
+
"single_word": false,
|
1899 |
+
"special": false
|
1900 |
+
},
|
1901 |
+
"255988": {
|
1902 |
+
"content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
|
1903 |
+
"lstrip": false,
|
1904 |
+
"normalized": false,
|
1905 |
+
"rstrip": false,
|
1906 |
+
"single_word": false,
|
1907 |
+
"special": false
|
1908 |
+
},
|
1909 |
+
"255989": {
|
1910 |
+
"content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
|
1911 |
+
"lstrip": false,
|
1912 |
+
"normalized": false,
|
1913 |
+
"rstrip": false,
|
1914 |
+
"single_word": false,
|
1915 |
+
"special": false
|
1916 |
+
},
|
1917 |
+
"255990": {
|
1918 |
+
"content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
|
1919 |
+
"lstrip": false,
|
1920 |
+
"normalized": false,
|
1921 |
+
"rstrip": false,
|
1922 |
+
"single_word": false,
|
1923 |
+
"special": false
|
1924 |
+
},
|
1925 |
+
"255991": {
|
1926 |
+
"content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
|
1927 |
+
"lstrip": false,
|
1928 |
+
"normalized": false,
|
1929 |
+
"rstrip": false,
|
1930 |
+
"single_word": false,
|
1931 |
+
"special": false
|
1932 |
+
},
|
1933 |
+
"255992": {
|
1934 |
+
"content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
|
1935 |
+
"lstrip": false,
|
1936 |
+
"normalized": false,
|
1937 |
+
"rstrip": false,
|
1938 |
+
"single_word": false,
|
1939 |
+
"special": false
|
1940 |
+
},
|
1941 |
+
"255993": {
|
1942 |
+
"content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
|
1943 |
+
"lstrip": false,
|
1944 |
+
"normalized": false,
|
1945 |
+
"rstrip": false,
|
1946 |
+
"single_word": false,
|
1947 |
+
"special": false
|
1948 |
+
},
|
1949 |
+
"255994": {
|
1950 |
+
"content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
|
1951 |
+
"lstrip": false,
|
1952 |
+
"normalized": false,
|
1953 |
+
"rstrip": false,
|
1954 |
+
"single_word": false,
|
1955 |
+
"special": false
|
1956 |
+
},
|
1957 |
+
"255995": {
|
1958 |
+
"content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
|
1959 |
+
"lstrip": false,
|
1960 |
+
"normalized": false,
|
1961 |
+
"rstrip": false,
|
1962 |
+
"single_word": false,
|
1963 |
+
"special": false
|
1964 |
+
},
|
1965 |
+
"255996": {
|
1966 |
+
"content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
|
1967 |
+
"lstrip": false,
|
1968 |
+
"normalized": false,
|
1969 |
+
"rstrip": false,
|
1970 |
+
"single_word": false,
|
1971 |
+
"special": false
|
1972 |
+
},
|
1973 |
+
"255997": {
|
1974 |
+
"content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
|
1975 |
+
"lstrip": false,
|
1976 |
+
"normalized": false,
|
1977 |
+
"rstrip": false,
|
1978 |
+
"single_word": false,
|
1979 |
+
"special": false
|
1980 |
+
},
|
1981 |
+
"255998": {
|
1982 |
+
"content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
|
1983 |
+
"lstrip": false,
|
1984 |
+
"normalized": false,
|
1985 |
+
"rstrip": false,
|
1986 |
+
"single_word": false,
|
1987 |
+
"special": false
|
1988 |
+
},
|
1989 |
+
"255999": {
|
1990 |
+
"content": "<unused99>",
|
1991 |
+
"lstrip": false,
|
1992 |
+
"normalized": false,
|
1993 |
+
"rstrip": false,
|
1994 |
+
"single_word": false,
|
1995 |
+
"special": false
|
1996 |
+
}
|
1997 |
+
},
|
1998 |
+
"additional_special_tokens": [
|
1999 |
+
"<start_of_turn>",
|
2000 |
+
"<end_of_turn>"
|
2001 |
+
],
|
2002 |
+
"bos_token": "<bos>",
|
2003 |
+
"chat_template": "{{ bos_token }}{% if messages[0]['role'] == 'system' %}{{ raise_exception('System role not supported') }}{% endif %}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if (message['role'] == 'assistant') %}{% set role = 'model' %}{% else %}{% set role = message['role'] %}{% endif %}{{ '<start_of_turn>' + role + '\n' + message['content'] | trim + '<end_of_turn>\n' }}{% endfor %}{% if add_generation_prompt %}{{'<start_of_turn>model\n'}}{% endif %}",
|
2004 |
+
"clean_up_tokenization_spaces": false,
|
2005 |
+
"eos_token": "<eos>",
|
2006 |
+
"extra_special_tokens": {},
|
2007 |
+
"max_sequence_length": 3072,
|
2008 |
+
"model_max_length": 3072,
|
2009 |
+
"pad_token": "<pad>",
|
2010 |
+
"padding_side": "right",
|
2011 |
+
"sp_model_kwargs": {},
|
2012 |
+
"spaces_between_special_tokens": false,
|
2013 |
+
"tokenizer_class": "GemmaTokenizer",
|
2014 |
+
"unk_token": "<unk>",
|
2015 |
+
"use_default_system_prompt": false
|
2016 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,2346 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 1.300666093826294,
|
3 |
+
"best_model_checkpoint": "4bit_repro_03022025/host10_seed_42_full_det_fp16_no_flash_attn_fix_pad_gemma-2-9b-it-l16-cot-4ep-lr3e04-ws20-bs4-ga4-fp16-11022025/checkpoint-109",
|
4 |
+
"epoch": 3.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 327,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.009195402298850575,
|
13 |
+
"grad_norm": 0.9957932233810425,
|
14 |
+
"learning_rate": 1.4999999999999999e-05,
|
15 |
+
"loss": 2.3724,
|
16 |
+
"step": 1
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.01839080459770115,
|
20 |
+
"grad_norm": 0.7591073513031006,
|
21 |
+
"learning_rate": 2.9999999999999997e-05,
|
22 |
+
"loss": 2.3711,
|
23 |
+
"step": 2
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.027586206896551724,
|
27 |
+
"grad_norm": 0.9023211002349854,
|
28 |
+
"learning_rate": 4.4999999999999996e-05,
|
29 |
+
"loss": 2.2454,
|
30 |
+
"step": 3
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 0.0367816091954023,
|
34 |
+
"grad_norm": 0.7705220580101013,
|
35 |
+
"learning_rate": 5.9999999999999995e-05,
|
36 |
+
"loss": 2.1252,
|
37 |
+
"step": 4
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 0.04597701149425287,
|
41 |
+
"grad_norm": 0.8994729518890381,
|
42 |
+
"learning_rate": 7.5e-05,
|
43 |
+
"loss": 2.1776,
|
44 |
+
"step": 5
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.05517241379310345,
|
48 |
+
"grad_norm": 0.8370222449302673,
|
49 |
+
"learning_rate": 8.999999999999999e-05,
|
50 |
+
"loss": 2.0403,
|
51 |
+
"step": 6
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.06436781609195402,
|
55 |
+
"grad_norm": 0.4772511124610901,
|
56 |
+
"learning_rate": 0.00010499999999999999,
|
57 |
+
"loss": 2.0642,
|
58 |
+
"step": 7
|
59 |
+
},
|
60 |
+
{
|
61 |
+
"epoch": 0.0735632183908046,
|
62 |
+
"grad_norm": 0.3877703547477722,
|
63 |
+
"learning_rate": 0.00011999999999999999,
|
64 |
+
"loss": 2.0111,
|
65 |
+
"step": 8
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 0.08275862068965517,
|
69 |
+
"grad_norm": 0.4768696129322052,
|
70 |
+
"learning_rate": 0.000135,
|
71 |
+
"loss": 1.8875,
|
72 |
+
"step": 9
|
73 |
+
},
|
74 |
+
{
|
75 |
+
"epoch": 0.09195402298850575,
|
76 |
+
"grad_norm": 0.6014317870140076,
|
77 |
+
"learning_rate": 0.00015,
|
78 |
+
"loss": 1.672,
|
79 |
+
"step": 10
|
80 |
+
},
|
81 |
+
{
|
82 |
+
"epoch": 0.10114942528735632,
|
83 |
+
"grad_norm": 0.6302416324615479,
|
84 |
+
"learning_rate": 0.000165,
|
85 |
+
"loss": 1.7088,
|
86 |
+
"step": 11
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 0.1103448275862069,
|
90 |
+
"grad_norm": 0.5539880990982056,
|
91 |
+
"learning_rate": 0.00017999999999999998,
|
92 |
+
"loss": 1.6913,
|
93 |
+
"step": 12
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 0.11954022988505747,
|
97 |
+
"grad_norm": 0.6798604130744934,
|
98 |
+
"learning_rate": 0.000195,
|
99 |
+
"loss": 1.4942,
|
100 |
+
"step": 13
|
101 |
+
},
|
102 |
+
{
|
103 |
+
"epoch": 0.12873563218390804,
|
104 |
+
"grad_norm": 0.4399753510951996,
|
105 |
+
"learning_rate": 0.00020999999999999998,
|
106 |
+
"loss": 1.6453,
|
107 |
+
"step": 14
|
108 |
+
},
|
109 |
+
{
|
110 |
+
"epoch": 0.13793103448275862,
|
111 |
+
"grad_norm": 0.37119659781455994,
|
112 |
+
"learning_rate": 0.000225,
|
113 |
+
"loss": 1.6376,
|
114 |
+
"step": 15
|
115 |
+
},
|
116 |
+
{
|
117 |
+
"epoch": 0.1471264367816092,
|
118 |
+
"grad_norm": 0.38230371475219727,
|
119 |
+
"learning_rate": 0.00023999999999999998,
|
120 |
+
"loss": 1.8295,
|
121 |
+
"step": 16
|
122 |
+
},
|
123 |
+
{
|
124 |
+
"epoch": 0.15632183908045977,
|
125 |
+
"grad_norm": 0.4516810476779938,
|
126 |
+
"learning_rate": 0.00025499999999999996,
|
127 |
+
"loss": 1.3166,
|
128 |
+
"step": 17
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 0.16551724137931034,
|
132 |
+
"grad_norm": 0.6360406875610352,
|
133 |
+
"learning_rate": 0.00027,
|
134 |
+
"loss": 1.3089,
|
135 |
+
"step": 18
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 0.17471264367816092,
|
139 |
+
"grad_norm": 0.3828903138637543,
|
140 |
+
"learning_rate": 0.000285,
|
141 |
+
"loss": 1.3322,
|
142 |
+
"step": 19
|
143 |
+
},
|
144 |
+
{
|
145 |
+
"epoch": 0.1839080459770115,
|
146 |
+
"grad_norm": 0.3432200253009796,
|
147 |
+
"learning_rate": 0.0003,
|
148 |
+
"loss": 1.5339,
|
149 |
+
"step": 20
|
150 |
+
},
|
151 |
+
{
|
152 |
+
"epoch": 0.19310344827586207,
|
153 |
+
"grad_norm": 0.278246134519577,
|
154 |
+
"learning_rate": 0.00029927184466019415,
|
155 |
+
"loss": 1.6185,
|
156 |
+
"step": 21
|
157 |
+
},
|
158 |
+
{
|
159 |
+
"epoch": 0.20229885057471264,
|
160 |
+
"grad_norm": 0.278033047914505,
|
161 |
+
"learning_rate": 0.00029854368932038833,
|
162 |
+
"loss": 1.5488,
|
163 |
+
"step": 22
|
164 |
+
},
|
165 |
+
{
|
166 |
+
"epoch": 0.21149425287356322,
|
167 |
+
"grad_norm": 0.35856395959854126,
|
168 |
+
"learning_rate": 0.0002978155339805825,
|
169 |
+
"loss": 1.3512,
|
170 |
+
"step": 23
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 0.2206896551724138,
|
174 |
+
"grad_norm": 0.3614782989025116,
|
175 |
+
"learning_rate": 0.0002970873786407767,
|
176 |
+
"loss": 1.4487,
|
177 |
+
"step": 24
|
178 |
+
},
|
179 |
+
{
|
180 |
+
"epoch": 0.22988505747126436,
|
181 |
+
"grad_norm": 0.30157631635665894,
|
182 |
+
"learning_rate": 0.00029635922330097087,
|
183 |
+
"loss": 1.6049,
|
184 |
+
"step": 25
|
185 |
+
},
|
186 |
+
{
|
187 |
+
"epoch": 0.23908045977011494,
|
188 |
+
"grad_norm": 0.35453277826309204,
|
189 |
+
"learning_rate": 0.00029563106796116505,
|
190 |
+
"loss": 1.449,
|
191 |
+
"step": 26
|
192 |
+
},
|
193 |
+
{
|
194 |
+
"epoch": 0.2482758620689655,
|
195 |
+
"grad_norm": 0.436924546957016,
|
196 |
+
"learning_rate": 0.0002949029126213592,
|
197 |
+
"loss": 1.3822,
|
198 |
+
"step": 27
|
199 |
+
},
|
200 |
+
{
|
201 |
+
"epoch": 0.2574712643678161,
|
202 |
+
"grad_norm": 0.3903788626194,
|
203 |
+
"learning_rate": 0.00029417475728155335,
|
204 |
+
"loss": 1.33,
|
205 |
+
"step": 28
|
206 |
+
},
|
207 |
+
{
|
208 |
+
"epoch": 0.26666666666666666,
|
209 |
+
"grad_norm": 0.39776864647865295,
|
210 |
+
"learning_rate": 0.00029344660194174753,
|
211 |
+
"loss": 1.5852,
|
212 |
+
"step": 29
|
213 |
+
},
|
214 |
+
{
|
215 |
+
"epoch": 0.27586206896551724,
|
216 |
+
"grad_norm": 0.3369416296482086,
|
217 |
+
"learning_rate": 0.0002927184466019417,
|
218 |
+
"loss": 1.7242,
|
219 |
+
"step": 30
|
220 |
+
},
|
221 |
+
{
|
222 |
+
"epoch": 0.2850574712643678,
|
223 |
+
"grad_norm": 0.3887549936771393,
|
224 |
+
"learning_rate": 0.0002919902912621359,
|
225 |
+
"loss": 1.5086,
|
226 |
+
"step": 31
|
227 |
+
},
|
228 |
+
{
|
229 |
+
"epoch": 0.2942528735632184,
|
230 |
+
"grad_norm": 0.3567999005317688,
|
231 |
+
"learning_rate": 0.00029126213592233006,
|
232 |
+
"loss": 1.2896,
|
233 |
+
"step": 32
|
234 |
+
},
|
235 |
+
{
|
236 |
+
"epoch": 0.30344827586206896,
|
237 |
+
"grad_norm": 0.45827871561050415,
|
238 |
+
"learning_rate": 0.00029053398058252424,
|
239 |
+
"loss": 1.1841,
|
240 |
+
"step": 33
|
241 |
+
},
|
242 |
+
{
|
243 |
+
"epoch": 0.31264367816091954,
|
244 |
+
"grad_norm": 0.45487773418426514,
|
245 |
+
"learning_rate": 0.0002898058252427184,
|
246 |
+
"loss": 1.5209,
|
247 |
+
"step": 34
|
248 |
+
},
|
249 |
+
{
|
250 |
+
"epoch": 0.3218390804597701,
|
251 |
+
"grad_norm": 0.44364598393440247,
|
252 |
+
"learning_rate": 0.0002890776699029126,
|
253 |
+
"loss": 1.5646,
|
254 |
+
"step": 35
|
255 |
+
},
|
256 |
+
{
|
257 |
+
"epoch": 0.3310344827586207,
|
258 |
+
"grad_norm": 0.4502098560333252,
|
259 |
+
"learning_rate": 0.0002883495145631068,
|
260 |
+
"loss": 1.3928,
|
261 |
+
"step": 36
|
262 |
+
},
|
263 |
+
{
|
264 |
+
"epoch": 0.34022988505747126,
|
265 |
+
"grad_norm": 0.36199966073036194,
|
266 |
+
"learning_rate": 0.00028762135922330096,
|
267 |
+
"loss": 1.4251,
|
268 |
+
"step": 37
|
269 |
+
},
|
270 |
+
{
|
271 |
+
"epoch": 0.34942528735632183,
|
272 |
+
"grad_norm": 0.3491019308567047,
|
273 |
+
"learning_rate": 0.00028689320388349513,
|
274 |
+
"loss": 1.5562,
|
275 |
+
"step": 38
|
276 |
+
},
|
277 |
+
{
|
278 |
+
"epoch": 0.3586206896551724,
|
279 |
+
"grad_norm": 0.5400763750076294,
|
280 |
+
"learning_rate": 0.0002861650485436893,
|
281 |
+
"loss": 1.2608,
|
282 |
+
"step": 39
|
283 |
+
},
|
284 |
+
{
|
285 |
+
"epoch": 0.367816091954023,
|
286 |
+
"grad_norm": 0.3730115592479706,
|
287 |
+
"learning_rate": 0.0002854368932038835,
|
288 |
+
"loss": 1.5525,
|
289 |
+
"step": 40
|
290 |
+
},
|
291 |
+
{
|
292 |
+
"epoch": 0.37701149425287356,
|
293 |
+
"grad_norm": 0.3588751554489136,
|
294 |
+
"learning_rate": 0.00028470873786407767,
|
295 |
+
"loss": 1.3468,
|
296 |
+
"step": 41
|
297 |
+
},
|
298 |
+
{
|
299 |
+
"epoch": 0.38620689655172413,
|
300 |
+
"grad_norm": 0.5940146446228027,
|
301 |
+
"learning_rate": 0.00028398058252427185,
|
302 |
+
"loss": 1.185,
|
303 |
+
"step": 42
|
304 |
+
},
|
305 |
+
{
|
306 |
+
"epoch": 0.3954022988505747,
|
307 |
+
"grad_norm": 0.394444078207016,
|
308 |
+
"learning_rate": 0.00028325242718446603,
|
309 |
+
"loss": 1.3057,
|
310 |
+
"step": 43
|
311 |
+
},
|
312 |
+
{
|
313 |
+
"epoch": 0.4045977011494253,
|
314 |
+
"grad_norm": 0.4431244730949402,
|
315 |
+
"learning_rate": 0.00028252427184466015,
|
316 |
+
"loss": 1.3147,
|
317 |
+
"step": 44
|
318 |
+
},
|
319 |
+
{
|
320 |
+
"epoch": 0.41379310344827586,
|
321 |
+
"grad_norm": 0.4967786371707916,
|
322 |
+
"learning_rate": 0.00028179611650485433,
|
323 |
+
"loss": 1.1773,
|
324 |
+
"step": 45
|
325 |
+
},
|
326 |
+
{
|
327 |
+
"epoch": 0.42298850574712643,
|
328 |
+
"grad_norm": 0.38681459426879883,
|
329 |
+
"learning_rate": 0.0002810679611650485,
|
330 |
+
"loss": 1.4481,
|
331 |
+
"step": 46
|
332 |
+
},
|
333 |
+
{
|
334 |
+
"epoch": 0.432183908045977,
|
335 |
+
"grad_norm": 0.4664541780948639,
|
336 |
+
"learning_rate": 0.0002803398058252427,
|
337 |
+
"loss": 1.3254,
|
338 |
+
"step": 47
|
339 |
+
},
|
340 |
+
{
|
341 |
+
"epoch": 0.4413793103448276,
|
342 |
+
"grad_norm": 0.433729350566864,
|
343 |
+
"learning_rate": 0.00027961165048543687,
|
344 |
+
"loss": 1.2067,
|
345 |
+
"step": 48
|
346 |
+
},
|
347 |
+
{
|
348 |
+
"epoch": 0.45057471264367815,
|
349 |
+
"grad_norm": 0.4609008729457855,
|
350 |
+
"learning_rate": 0.00027888349514563105,
|
351 |
+
"loss": 1.1925,
|
352 |
+
"step": 49
|
353 |
+
},
|
354 |
+
{
|
355 |
+
"epoch": 0.45977011494252873,
|
356 |
+
"grad_norm": 0.5346646904945374,
|
357 |
+
"learning_rate": 0.0002781553398058252,
|
358 |
+
"loss": 1.1117,
|
359 |
+
"step": 50
|
360 |
+
},
|
361 |
+
{
|
362 |
+
"epoch": 0.4689655172413793,
|
363 |
+
"grad_norm": 0.4348887801170349,
|
364 |
+
"learning_rate": 0.0002774271844660194,
|
365 |
+
"loss": 1.3088,
|
366 |
+
"step": 51
|
367 |
+
},
|
368 |
+
{
|
369 |
+
"epoch": 0.4781609195402299,
|
370 |
+
"grad_norm": 0.4136529266834259,
|
371 |
+
"learning_rate": 0.0002766990291262136,
|
372 |
+
"loss": 1.1332,
|
373 |
+
"step": 52
|
374 |
+
},
|
375 |
+
{
|
376 |
+
"epoch": 0.48735632183908045,
|
377 |
+
"grad_norm": 0.580917239189148,
|
378 |
+
"learning_rate": 0.00027597087378640776,
|
379 |
+
"loss": 1.1903,
|
380 |
+
"step": 53
|
381 |
+
},
|
382 |
+
{
|
383 |
+
"epoch": 0.496551724137931,
|
384 |
+
"grad_norm": 0.5748546719551086,
|
385 |
+
"learning_rate": 0.00027524271844660194,
|
386 |
+
"loss": 1.0639,
|
387 |
+
"step": 54
|
388 |
+
},
|
389 |
+
{
|
390 |
+
"epoch": 0.5057471264367817,
|
391 |
+
"grad_norm": 0.45053598284721375,
|
392 |
+
"learning_rate": 0.0002745145631067961,
|
393 |
+
"loss": 1.2918,
|
394 |
+
"step": 55
|
395 |
+
},
|
396 |
+
{
|
397 |
+
"epoch": 0.5149425287356322,
|
398 |
+
"grad_norm": 0.5989317893981934,
|
399 |
+
"learning_rate": 0.0002737864077669903,
|
400 |
+
"loss": 1.2734,
|
401 |
+
"step": 56
|
402 |
+
},
|
403 |
+
{
|
404 |
+
"epoch": 0.5241379310344828,
|
405 |
+
"grad_norm": 0.5094353556632996,
|
406 |
+
"learning_rate": 0.0002730582524271845,
|
407 |
+
"loss": 1.063,
|
408 |
+
"step": 57
|
409 |
+
},
|
410 |
+
{
|
411 |
+
"epoch": 0.5333333333333333,
|
412 |
+
"grad_norm": 0.5418046712875366,
|
413 |
+
"learning_rate": 0.00027233009708737865,
|
414 |
+
"loss": 1.1931,
|
415 |
+
"step": 58
|
416 |
+
},
|
417 |
+
{
|
418 |
+
"epoch": 0.542528735632184,
|
419 |
+
"grad_norm": 0.5898640155792236,
|
420 |
+
"learning_rate": 0.0002716019417475728,
|
421 |
+
"loss": 1.1561,
|
422 |
+
"step": 59
|
423 |
+
},
|
424 |
+
{
|
425 |
+
"epoch": 0.5517241379310345,
|
426 |
+
"grad_norm": 0.5417141914367676,
|
427 |
+
"learning_rate": 0.00027087378640776696,
|
428 |
+
"loss": 1.1772,
|
429 |
+
"step": 60
|
430 |
+
},
|
431 |
+
{
|
432 |
+
"epoch": 0.5609195402298851,
|
433 |
+
"grad_norm": 0.5419390201568604,
|
434 |
+
"learning_rate": 0.00027014563106796114,
|
435 |
+
"loss": 1.1019,
|
436 |
+
"step": 61
|
437 |
+
},
|
438 |
+
{
|
439 |
+
"epoch": 0.5701149425287356,
|
440 |
+
"grad_norm": 0.5117617845535278,
|
441 |
+
"learning_rate": 0.0002694174757281553,
|
442 |
+
"loss": 1.026,
|
443 |
+
"step": 62
|
444 |
+
},
|
445 |
+
{
|
446 |
+
"epoch": 0.5793103448275863,
|
447 |
+
"grad_norm": 0.6913059949874878,
|
448 |
+
"learning_rate": 0.0002686893203883495,
|
449 |
+
"loss": 1.0382,
|
450 |
+
"step": 63
|
451 |
+
},
|
452 |
+
{
|
453 |
+
"epoch": 0.5885057471264368,
|
454 |
+
"grad_norm": 0.7260013818740845,
|
455 |
+
"learning_rate": 0.00026796116504854367,
|
456 |
+
"loss": 1.0667,
|
457 |
+
"step": 64
|
458 |
+
},
|
459 |
+
{
|
460 |
+
"epoch": 0.5977011494252874,
|
461 |
+
"grad_norm": 0.831520676612854,
|
462 |
+
"learning_rate": 0.00026723300970873785,
|
463 |
+
"loss": 1.2295,
|
464 |
+
"step": 65
|
465 |
+
},
|
466 |
+
{
|
467 |
+
"epoch": 0.6068965517241379,
|
468 |
+
"grad_norm": 0.5325063467025757,
|
469 |
+
"learning_rate": 0.00026650485436893203,
|
470 |
+
"loss": 0.8899,
|
471 |
+
"step": 66
|
472 |
+
},
|
473 |
+
{
|
474 |
+
"epoch": 0.6160919540229886,
|
475 |
+
"grad_norm": 0.5867132544517517,
|
476 |
+
"learning_rate": 0.0002657766990291262,
|
477 |
+
"loss": 1.1095,
|
478 |
+
"step": 67
|
479 |
+
},
|
480 |
+
{
|
481 |
+
"epoch": 0.6252873563218391,
|
482 |
+
"grad_norm": 0.6068809628486633,
|
483 |
+
"learning_rate": 0.0002650485436893204,
|
484 |
+
"loss": 1.075,
|
485 |
+
"step": 68
|
486 |
+
},
|
487 |
+
{
|
488 |
+
"epoch": 0.6344827586206897,
|
489 |
+
"grad_norm": 0.6909754872322083,
|
490 |
+
"learning_rate": 0.00026432038834951456,
|
491 |
+
"loss": 1.1673,
|
492 |
+
"step": 69
|
493 |
+
},
|
494 |
+
{
|
495 |
+
"epoch": 0.6436781609195402,
|
496 |
+
"grad_norm": 0.7632415294647217,
|
497 |
+
"learning_rate": 0.00026359223300970874,
|
498 |
+
"loss": 1.1162,
|
499 |
+
"step": 70
|
500 |
+
},
|
501 |
+
{
|
502 |
+
"epoch": 0.6528735632183909,
|
503 |
+
"grad_norm": 0.6888180375099182,
|
504 |
+
"learning_rate": 0.0002628640776699029,
|
505 |
+
"loss": 0.8784,
|
506 |
+
"step": 71
|
507 |
+
},
|
508 |
+
{
|
509 |
+
"epoch": 0.6620689655172414,
|
510 |
+
"grad_norm": 0.6300679445266724,
|
511 |
+
"learning_rate": 0.00026213592233009705,
|
512 |
+
"loss": 0.8871,
|
513 |
+
"step": 72
|
514 |
+
},
|
515 |
+
{
|
516 |
+
"epoch": 0.671264367816092,
|
517 |
+
"grad_norm": 0.6151922941207886,
|
518 |
+
"learning_rate": 0.0002614077669902912,
|
519 |
+
"loss": 0.9701,
|
520 |
+
"step": 73
|
521 |
+
},
|
522 |
+
{
|
523 |
+
"epoch": 0.6804597701149425,
|
524 |
+
"grad_norm": 0.6928962469100952,
|
525 |
+
"learning_rate": 0.0002606796116504854,
|
526 |
+
"loss": 1.0456,
|
527 |
+
"step": 74
|
528 |
+
},
|
529 |
+
{
|
530 |
+
"epoch": 0.6896551724137931,
|
531 |
+
"grad_norm": 0.848274827003479,
|
532 |
+
"learning_rate": 0.0002599514563106796,
|
533 |
+
"loss": 1.1089,
|
534 |
+
"step": 75
|
535 |
+
},
|
536 |
+
{
|
537 |
+
"epoch": 0.6988505747126437,
|
538 |
+
"grad_norm": 1.1162086725234985,
|
539 |
+
"learning_rate": 0.00025922330097087376,
|
540 |
+
"loss": 1.1541,
|
541 |
+
"step": 76
|
542 |
+
},
|
543 |
+
{
|
544 |
+
"epoch": 0.7080459770114943,
|
545 |
+
"grad_norm": 0.6158594489097595,
|
546 |
+
"learning_rate": 0.00025849514563106794,
|
547 |
+
"loss": 1.1431,
|
548 |
+
"step": 77
|
549 |
+
},
|
550 |
+
{
|
551 |
+
"epoch": 0.7172413793103448,
|
552 |
+
"grad_norm": 0.6790457367897034,
|
553 |
+
"learning_rate": 0.0002577669902912621,
|
554 |
+
"loss": 0.9188,
|
555 |
+
"step": 78
|
556 |
+
},
|
557 |
+
{
|
558 |
+
"epoch": 0.7264367816091954,
|
559 |
+
"grad_norm": 0.844353973865509,
|
560 |
+
"learning_rate": 0.0002570388349514563,
|
561 |
+
"loss": 1.2385,
|
562 |
+
"step": 79
|
563 |
+
},
|
564 |
+
{
|
565 |
+
"epoch": 0.735632183908046,
|
566 |
+
"grad_norm": 0.645825207233429,
|
567 |
+
"learning_rate": 0.0002563106796116505,
|
568 |
+
"loss": 1.0516,
|
569 |
+
"step": 80
|
570 |
+
},
|
571 |
+
{
|
572 |
+
"epoch": 0.7448275862068966,
|
573 |
+
"grad_norm": 0.5313035249710083,
|
574 |
+
"learning_rate": 0.0002555825242718446,
|
575 |
+
"loss": 1.046,
|
576 |
+
"step": 81
|
577 |
+
},
|
578 |
+
{
|
579 |
+
"epoch": 0.7540229885057471,
|
580 |
+
"grad_norm": 0.6045447587966919,
|
581 |
+
"learning_rate": 0.0002548543689320388,
|
582 |
+
"loss": 0.9456,
|
583 |
+
"step": 82
|
584 |
+
},
|
585 |
+
{
|
586 |
+
"epoch": 0.7632183908045977,
|
587 |
+
"grad_norm": 1.1198372840881348,
|
588 |
+
"learning_rate": 0.00025412621359223296,
|
589 |
+
"loss": 1.1684,
|
590 |
+
"step": 83
|
591 |
+
},
|
592 |
+
{
|
593 |
+
"epoch": 0.7724137931034483,
|
594 |
+
"grad_norm": 0.6908996105194092,
|
595 |
+
"learning_rate": 0.00025339805825242714,
|
596 |
+
"loss": 1.1155,
|
597 |
+
"step": 84
|
598 |
+
},
|
599 |
+
{
|
600 |
+
"epoch": 0.7816091954022989,
|
601 |
+
"grad_norm": 0.5916021466255188,
|
602 |
+
"learning_rate": 0.0002526699029126213,
|
603 |
+
"loss": 1.0781,
|
604 |
+
"step": 85
|
605 |
+
},
|
606 |
+
{
|
607 |
+
"epoch": 0.7908045977011494,
|
608 |
+
"grad_norm": 0.8320909738540649,
|
609 |
+
"learning_rate": 0.0002519417475728155,
|
610 |
+
"loss": 0.7954,
|
611 |
+
"step": 86
|
612 |
+
},
|
613 |
+
{
|
614 |
+
"epoch": 0.8,
|
615 |
+
"grad_norm": 0.6855669617652893,
|
616 |
+
"learning_rate": 0.00025121359223300967,
|
617 |
+
"loss": 0.8968,
|
618 |
+
"step": 87
|
619 |
+
},
|
620 |
+
{
|
621 |
+
"epoch": 0.8091954022988506,
|
622 |
+
"grad_norm": 0.6343971490859985,
|
623 |
+
"learning_rate": 0.00025048543689320385,
|
624 |
+
"loss": 0.9878,
|
625 |
+
"step": 88
|
626 |
+
},
|
627 |
+
{
|
628 |
+
"epoch": 0.8183908045977012,
|
629 |
+
"grad_norm": 0.5901280641555786,
|
630 |
+
"learning_rate": 0.00024975728155339803,
|
631 |
+
"loss": 1.0158,
|
632 |
+
"step": 89
|
633 |
+
},
|
634 |
+
{
|
635 |
+
"epoch": 0.8275862068965517,
|
636 |
+
"grad_norm": 0.5881906151771545,
|
637 |
+
"learning_rate": 0.0002490291262135922,
|
638 |
+
"loss": 0.9432,
|
639 |
+
"step": 90
|
640 |
+
},
|
641 |
+
{
|
642 |
+
"epoch": 0.8367816091954023,
|
643 |
+
"grad_norm": 0.749911367893219,
|
644 |
+
"learning_rate": 0.0002483009708737864,
|
645 |
+
"loss": 0.8734,
|
646 |
+
"step": 91
|
647 |
+
},
|
648 |
+
{
|
649 |
+
"epoch": 0.8459770114942529,
|
650 |
+
"grad_norm": 0.6801809668540955,
|
651 |
+
"learning_rate": 0.00024757281553398056,
|
652 |
+
"loss": 0.7291,
|
653 |
+
"step": 92
|
654 |
+
},
|
655 |
+
{
|
656 |
+
"epoch": 0.8551724137931035,
|
657 |
+
"grad_norm": 0.5692021250724792,
|
658 |
+
"learning_rate": 0.00024684466019417474,
|
659 |
+
"loss": 0.976,
|
660 |
+
"step": 93
|
661 |
+
},
|
662 |
+
{
|
663 |
+
"epoch": 0.864367816091954,
|
664 |
+
"grad_norm": 0.8974186182022095,
|
665 |
+
"learning_rate": 0.0002461165048543689,
|
666 |
+
"loss": 0.8702,
|
667 |
+
"step": 94
|
668 |
+
},
|
669 |
+
{
|
670 |
+
"epoch": 0.8735632183908046,
|
671 |
+
"grad_norm": 0.7381451725959778,
|
672 |
+
"learning_rate": 0.0002453883495145631,
|
673 |
+
"loss": 0.832,
|
674 |
+
"step": 95
|
675 |
+
},
|
676 |
+
{
|
677 |
+
"epoch": 0.8827586206896552,
|
678 |
+
"grad_norm": 0.5254162549972534,
|
679 |
+
"learning_rate": 0.0002446601941747572,
|
680 |
+
"loss": 0.7984,
|
681 |
+
"step": 96
|
682 |
+
},
|
683 |
+
{
|
684 |
+
"epoch": 0.8919540229885058,
|
685 |
+
"grad_norm": 0.6398109197616577,
|
686 |
+
"learning_rate": 0.00024393203883495143,
|
687 |
+
"loss": 0.9934,
|
688 |
+
"step": 97
|
689 |
+
},
|
690 |
+
{
|
691 |
+
"epoch": 0.9011494252873563,
|
692 |
+
"grad_norm": 0.6260827779769897,
|
693 |
+
"learning_rate": 0.0002432038834951456,
|
694 |
+
"loss": 1.049,
|
695 |
+
"step": 98
|
696 |
+
},
|
697 |
+
{
|
698 |
+
"epoch": 0.9103448275862069,
|
699 |
+
"grad_norm": 0.7606930136680603,
|
700 |
+
"learning_rate": 0.0002424757281553398,
|
701 |
+
"loss": 0.8291,
|
702 |
+
"step": 99
|
703 |
+
},
|
704 |
+
{
|
705 |
+
"epoch": 0.9195402298850575,
|
706 |
+
"grad_norm": 0.5728839039802551,
|
707 |
+
"learning_rate": 0.00024174757281553394,
|
708 |
+
"loss": 0.9048,
|
709 |
+
"step": 100
|
710 |
+
},
|
711 |
+
{
|
712 |
+
"epoch": 0.9287356321839081,
|
713 |
+
"grad_norm": 0.8986696600914001,
|
714 |
+
"learning_rate": 0.00024101941747572812,
|
715 |
+
"loss": 0.8363,
|
716 |
+
"step": 101
|
717 |
+
},
|
718 |
+
{
|
719 |
+
"epoch": 0.9379310344827586,
|
720 |
+
"grad_norm": 1.1614326238632202,
|
721 |
+
"learning_rate": 0.0002402912621359223,
|
722 |
+
"loss": 0.8226,
|
723 |
+
"step": 102
|
724 |
+
},
|
725 |
+
{
|
726 |
+
"epoch": 0.9471264367816092,
|
727 |
+
"grad_norm": 0.6037288904190063,
|
728 |
+
"learning_rate": 0.00023956310679611648,
|
729 |
+
"loss": 0.9164,
|
730 |
+
"step": 103
|
731 |
+
},
|
732 |
+
{
|
733 |
+
"epoch": 0.9563218390804598,
|
734 |
+
"grad_norm": 0.5823872685432434,
|
735 |
+
"learning_rate": 0.00023883495145631065,
|
736 |
+
"loss": 0.9207,
|
737 |
+
"step": 104
|
738 |
+
},
|
739 |
+
{
|
740 |
+
"epoch": 0.9655172413793104,
|
741 |
+
"grad_norm": 0.6235625147819519,
|
742 |
+
"learning_rate": 0.00023810679611650483,
|
743 |
+
"loss": 0.762,
|
744 |
+
"step": 105
|
745 |
+
},
|
746 |
+
{
|
747 |
+
"epoch": 0.9747126436781609,
|
748 |
+
"grad_norm": 0.5390623807907104,
|
749 |
+
"learning_rate": 0.000237378640776699,
|
750 |
+
"loss": 1.0991,
|
751 |
+
"step": 106
|
752 |
+
},
|
753 |
+
{
|
754 |
+
"epoch": 0.9839080459770115,
|
755 |
+
"grad_norm": 0.5815601944923401,
|
756 |
+
"learning_rate": 0.0002366504854368932,
|
757 |
+
"loss": 0.9363,
|
758 |
+
"step": 107
|
759 |
+
},
|
760 |
+
{
|
761 |
+
"epoch": 0.993103448275862,
|
762 |
+
"grad_norm": 0.5816079378128052,
|
763 |
+
"learning_rate": 0.00023592233009708734,
|
764 |
+
"loss": 0.7259,
|
765 |
+
"step": 108
|
766 |
+
},
|
767 |
+
{
|
768 |
+
"epoch": 1.0,
|
769 |
+
"grad_norm": 2.0381648540496826,
|
770 |
+
"learning_rate": 0.00023519417475728152,
|
771 |
+
"loss": 0.8426,
|
772 |
+
"step": 109
|
773 |
+
},
|
774 |
+
{
|
775 |
+
"epoch": 1.0,
|
776 |
+
"eval_loss": 1.300666093826294,
|
777 |
+
"eval_runtime": 94.5929,
|
778 |
+
"eval_samples_per_second": 3.51,
|
779 |
+
"eval_steps_per_second": 1.755,
|
780 |
+
"step": 109
|
781 |
+
},
|
782 |
+
{
|
783 |
+
"epoch": 1.0091954022988505,
|
784 |
+
"grad_norm": 0.5967744588851929,
|
785 |
+
"learning_rate": 0.0002344660194174757,
|
786 |
+
"loss": 0.7901,
|
787 |
+
"step": 110
|
788 |
+
},
|
789 |
+
{
|
790 |
+
"epoch": 1.018390804597701,
|
791 |
+
"grad_norm": 0.5640788078308105,
|
792 |
+
"learning_rate": 0.00023373786407766988,
|
793 |
+
"loss": 0.6748,
|
794 |
+
"step": 111
|
795 |
+
},
|
796 |
+
{
|
797 |
+
"epoch": 1.0275862068965518,
|
798 |
+
"grad_norm": 0.5988382697105408,
|
799 |
+
"learning_rate": 0.00023300970873786406,
|
800 |
+
"loss": 0.7256,
|
801 |
+
"step": 112
|
802 |
+
},
|
803 |
+
{
|
804 |
+
"epoch": 1.0367816091954023,
|
805 |
+
"grad_norm": 0.8283673524856567,
|
806 |
+
"learning_rate": 0.00023228155339805823,
|
807 |
+
"loss": 0.5817,
|
808 |
+
"step": 113
|
809 |
+
},
|
810 |
+
{
|
811 |
+
"epoch": 1.0459770114942528,
|
812 |
+
"grad_norm": 0.5982439517974854,
|
813 |
+
"learning_rate": 0.0002315533980582524,
|
814 |
+
"loss": 0.8342,
|
815 |
+
"step": 114
|
816 |
+
},
|
817 |
+
{
|
818 |
+
"epoch": 1.0551724137931036,
|
819 |
+
"grad_norm": 0.9253256916999817,
|
820 |
+
"learning_rate": 0.0002308252427184466,
|
821 |
+
"loss": 0.6173,
|
822 |
+
"step": 115
|
823 |
+
},
|
824 |
+
{
|
825 |
+
"epoch": 1.064367816091954,
|
826 |
+
"grad_norm": 0.58003830909729,
|
827 |
+
"learning_rate": 0.00023009708737864074,
|
828 |
+
"loss": 0.6153,
|
829 |
+
"step": 116
|
830 |
+
},
|
831 |
+
{
|
832 |
+
"epoch": 1.0735632183908046,
|
833 |
+
"grad_norm": 0.9149603843688965,
|
834 |
+
"learning_rate": 0.00022936893203883492,
|
835 |
+
"loss": 0.7499,
|
836 |
+
"step": 117
|
837 |
+
},
|
838 |
+
{
|
839 |
+
"epoch": 1.0827586206896551,
|
840 |
+
"grad_norm": 0.4855748414993286,
|
841 |
+
"learning_rate": 0.0002286407766990291,
|
842 |
+
"loss": 0.8476,
|
843 |
+
"step": 118
|
844 |
+
},
|
845 |
+
{
|
846 |
+
"epoch": 1.0919540229885056,
|
847 |
+
"grad_norm": 0.5189658403396606,
|
848 |
+
"learning_rate": 0.00022791262135922328,
|
849 |
+
"loss": 0.6332,
|
850 |
+
"step": 119
|
851 |
+
},
|
852 |
+
{
|
853 |
+
"epoch": 1.1011494252873564,
|
854 |
+
"grad_norm": 0.6228414177894592,
|
855 |
+
"learning_rate": 0.00022718446601941746,
|
856 |
+
"loss": 0.6543,
|
857 |
+
"step": 120
|
858 |
+
},
|
859 |
+
{
|
860 |
+
"epoch": 1.110344827586207,
|
861 |
+
"grad_norm": 0.7163541913032532,
|
862 |
+
"learning_rate": 0.00022645631067961164,
|
863 |
+
"loss": 0.5062,
|
864 |
+
"step": 121
|
865 |
+
},
|
866 |
+
{
|
867 |
+
"epoch": 1.1195402298850574,
|
868 |
+
"grad_norm": 0.6037282347679138,
|
869 |
+
"learning_rate": 0.00022572815533980582,
|
870 |
+
"loss": 0.4752,
|
871 |
+
"step": 122
|
872 |
+
},
|
873 |
+
{
|
874 |
+
"epoch": 1.1287356321839082,
|
875 |
+
"grad_norm": 0.5334956049919128,
|
876 |
+
"learning_rate": 0.000225,
|
877 |
+
"loss": 0.5978,
|
878 |
+
"step": 123
|
879 |
+
},
|
880 |
+
{
|
881 |
+
"epoch": 1.1379310344827587,
|
882 |
+
"grad_norm": 0.6316633224487305,
|
883 |
+
"learning_rate": 0.00022427184466019415,
|
884 |
+
"loss": 0.631,
|
885 |
+
"step": 124
|
886 |
+
},
|
887 |
+
{
|
888 |
+
"epoch": 1.1471264367816092,
|
889 |
+
"grad_norm": 0.5869876742362976,
|
890 |
+
"learning_rate": 0.00022354368932038832,
|
891 |
+
"loss": 0.6083,
|
892 |
+
"step": 125
|
893 |
+
},
|
894 |
+
{
|
895 |
+
"epoch": 1.1563218390804597,
|
896 |
+
"grad_norm": 0.8843062520027161,
|
897 |
+
"learning_rate": 0.0002228155339805825,
|
898 |
+
"loss": 0.5106,
|
899 |
+
"step": 126
|
900 |
+
},
|
901 |
+
{
|
902 |
+
"epoch": 1.1655172413793102,
|
903 |
+
"grad_norm": 0.9645463228225708,
|
904 |
+
"learning_rate": 0.00022208737864077668,
|
905 |
+
"loss": 0.6352,
|
906 |
+
"step": 127
|
907 |
+
},
|
908 |
+
{
|
909 |
+
"epoch": 1.174712643678161,
|
910 |
+
"grad_norm": 0.4931183457374573,
|
911 |
+
"learning_rate": 0.00022135922330097086,
|
912 |
+
"loss": 0.6054,
|
913 |
+
"step": 128
|
914 |
+
},
|
915 |
+
{
|
916 |
+
"epoch": 1.1839080459770115,
|
917 |
+
"grad_norm": 0.5451965928077698,
|
918 |
+
"learning_rate": 0.00022063106796116504,
|
919 |
+
"loss": 0.6165,
|
920 |
+
"step": 129
|
921 |
+
},
|
922 |
+
{
|
923 |
+
"epoch": 1.193103448275862,
|
924 |
+
"grad_norm": 0.44423708319664,
|
925 |
+
"learning_rate": 0.00021990291262135922,
|
926 |
+
"loss": 0.57,
|
927 |
+
"step": 130
|
928 |
+
},
|
929 |
+
{
|
930 |
+
"epoch": 1.2022988505747128,
|
931 |
+
"grad_norm": 0.6561571955680847,
|
932 |
+
"learning_rate": 0.00021917475728155337,
|
933 |
+
"loss": 0.5627,
|
934 |
+
"step": 131
|
935 |
+
},
|
936 |
+
{
|
937 |
+
"epoch": 1.2114942528735633,
|
938 |
+
"grad_norm": 0.4954622983932495,
|
939 |
+
"learning_rate": 0.00021844660194174755,
|
940 |
+
"loss": 0.6054,
|
941 |
+
"step": 132
|
942 |
+
},
|
943 |
+
{
|
944 |
+
"epoch": 1.2206896551724138,
|
945 |
+
"grad_norm": 0.49996840953826904,
|
946 |
+
"learning_rate": 0.00021771844660194173,
|
947 |
+
"loss": 0.7044,
|
948 |
+
"step": 133
|
949 |
+
},
|
950 |
+
{
|
951 |
+
"epoch": 1.2298850574712643,
|
952 |
+
"grad_norm": 0.6132878065109253,
|
953 |
+
"learning_rate": 0.0002169902912621359,
|
954 |
+
"loss": 0.5854,
|
955 |
+
"step": 134
|
956 |
+
},
|
957 |
+
{
|
958 |
+
"epoch": 1.2390804597701148,
|
959 |
+
"grad_norm": 0.619061291217804,
|
960 |
+
"learning_rate": 0.00021626213592233008,
|
961 |
+
"loss": 0.7435,
|
962 |
+
"step": 135
|
963 |
+
},
|
964 |
+
{
|
965 |
+
"epoch": 1.2482758620689656,
|
966 |
+
"grad_norm": 0.5794959664344788,
|
967 |
+
"learning_rate": 0.00021553398058252426,
|
968 |
+
"loss": 0.8223,
|
969 |
+
"step": 136
|
970 |
+
},
|
971 |
+
{
|
972 |
+
"epoch": 1.257471264367816,
|
973 |
+
"grad_norm": 0.595934271812439,
|
974 |
+
"learning_rate": 0.00021480582524271844,
|
975 |
+
"loss": 0.4924,
|
976 |
+
"step": 137
|
977 |
+
},
|
978 |
+
{
|
979 |
+
"epoch": 1.2666666666666666,
|
980 |
+
"grad_norm": 0.7381154298782349,
|
981 |
+
"learning_rate": 0.00021407766990291262,
|
982 |
+
"loss": 0.5804,
|
983 |
+
"step": 138
|
984 |
+
},
|
985 |
+
{
|
986 |
+
"epoch": 1.2758620689655173,
|
987 |
+
"grad_norm": 0.6467525362968445,
|
988 |
+
"learning_rate": 0.00021334951456310677,
|
989 |
+
"loss": 0.6435,
|
990 |
+
"step": 139
|
991 |
+
},
|
992 |
+
{
|
993 |
+
"epoch": 1.2850574712643679,
|
994 |
+
"grad_norm": 0.5511316657066345,
|
995 |
+
"learning_rate": 0.00021262135922330095,
|
996 |
+
"loss": 0.6627,
|
997 |
+
"step": 140
|
998 |
+
},
|
999 |
+
{
|
1000 |
+
"epoch": 1.2942528735632184,
|
1001 |
+
"grad_norm": 0.6253796815872192,
|
1002 |
+
"learning_rate": 0.00021189320388349513,
|
1003 |
+
"loss": 0.7729,
|
1004 |
+
"step": 141
|
1005 |
+
},
|
1006 |
+
{
|
1007 |
+
"epoch": 1.303448275862069,
|
1008 |
+
"grad_norm": 0.4994090795516968,
|
1009 |
+
"learning_rate": 0.0002111650485436893,
|
1010 |
+
"loss": 0.4122,
|
1011 |
+
"step": 142
|
1012 |
+
},
|
1013 |
+
{
|
1014 |
+
"epoch": 1.3126436781609194,
|
1015 |
+
"grad_norm": 0.35405322909355164,
|
1016 |
+
"learning_rate": 0.00021043689320388349,
|
1017 |
+
"loss": 0.3711,
|
1018 |
+
"step": 143
|
1019 |
+
},
|
1020 |
+
{
|
1021 |
+
"epoch": 1.3218390804597702,
|
1022 |
+
"grad_norm": 0.5248880982398987,
|
1023 |
+
"learning_rate": 0.00020970873786407766,
|
1024 |
+
"loss": 0.6734,
|
1025 |
+
"step": 144
|
1026 |
+
},
|
1027 |
+
{
|
1028 |
+
"epoch": 1.3310344827586207,
|
1029 |
+
"grad_norm": 0.44895875453948975,
|
1030 |
+
"learning_rate": 0.00020898058252427184,
|
1031 |
+
"loss": 0.3438,
|
1032 |
+
"step": 145
|
1033 |
+
},
|
1034 |
+
{
|
1035 |
+
"epoch": 1.3402298850574712,
|
1036 |
+
"grad_norm": 0.4654625654220581,
|
1037 |
+
"learning_rate": 0.00020825242718446602,
|
1038 |
+
"loss": 0.4324,
|
1039 |
+
"step": 146
|
1040 |
+
},
|
1041 |
+
{
|
1042 |
+
"epoch": 1.349425287356322,
|
1043 |
+
"grad_norm": 0.4388936460018158,
|
1044 |
+
"learning_rate": 0.00020752427184466017,
|
1045 |
+
"loss": 0.4578,
|
1046 |
+
"step": 147
|
1047 |
+
},
|
1048 |
+
{
|
1049 |
+
"epoch": 1.3586206896551725,
|
1050 |
+
"grad_norm": 0.4960116744041443,
|
1051 |
+
"learning_rate": 0.00020679611650485435,
|
1052 |
+
"loss": 0.5942,
|
1053 |
+
"step": 148
|
1054 |
+
},
|
1055 |
+
{
|
1056 |
+
"epoch": 1.367816091954023,
|
1057 |
+
"grad_norm": 0.590185284614563,
|
1058 |
+
"learning_rate": 0.00020606796116504853,
|
1059 |
+
"loss": 0.4179,
|
1060 |
+
"step": 149
|
1061 |
+
},
|
1062 |
+
{
|
1063 |
+
"epoch": 1.3770114942528735,
|
1064 |
+
"grad_norm": 0.5173139572143555,
|
1065 |
+
"learning_rate": 0.0002053398058252427,
|
1066 |
+
"loss": 0.5081,
|
1067 |
+
"step": 150
|
1068 |
+
},
|
1069 |
+
{
|
1070 |
+
"epoch": 1.386206896551724,
|
1071 |
+
"grad_norm": 0.5537795424461365,
|
1072 |
+
"learning_rate": 0.0002046116504854369,
|
1073 |
+
"loss": 0.6486,
|
1074 |
+
"step": 151
|
1075 |
+
},
|
1076 |
+
{
|
1077 |
+
"epoch": 1.3954022988505748,
|
1078 |
+
"grad_norm": 0.593481183052063,
|
1079 |
+
"learning_rate": 0.00020388349514563107,
|
1080 |
+
"loss": 0.5944,
|
1081 |
+
"step": 152
|
1082 |
+
},
|
1083 |
+
{
|
1084 |
+
"epoch": 1.4045977011494253,
|
1085 |
+
"grad_norm": 0.5522420406341553,
|
1086 |
+
"learning_rate": 0.00020315533980582524,
|
1087 |
+
"loss": 0.8094,
|
1088 |
+
"step": 153
|
1089 |
+
},
|
1090 |
+
{
|
1091 |
+
"epoch": 1.4137931034482758,
|
1092 |
+
"grad_norm": 0.6627272963523865,
|
1093 |
+
"learning_rate": 0.00020242718446601942,
|
1094 |
+
"loss": 0.4802,
|
1095 |
+
"step": 154
|
1096 |
+
},
|
1097 |
+
{
|
1098 |
+
"epoch": 1.4229885057471265,
|
1099 |
+
"grad_norm": 0.3878915011882782,
|
1100 |
+
"learning_rate": 0.00020169902912621357,
|
1101 |
+
"loss": 0.4832,
|
1102 |
+
"step": 155
|
1103 |
+
},
|
1104 |
+
{
|
1105 |
+
"epoch": 1.432183908045977,
|
1106 |
+
"grad_norm": 0.5121778845787048,
|
1107 |
+
"learning_rate": 0.00020097087378640775,
|
1108 |
+
"loss": 0.6316,
|
1109 |
+
"step": 156
|
1110 |
+
},
|
1111 |
+
{
|
1112 |
+
"epoch": 1.4413793103448276,
|
1113 |
+
"grad_norm": 0.41354355216026306,
|
1114 |
+
"learning_rate": 0.00020024271844660193,
|
1115 |
+
"loss": 0.5819,
|
1116 |
+
"step": 157
|
1117 |
+
},
|
1118 |
+
{
|
1119 |
+
"epoch": 1.450574712643678,
|
1120 |
+
"grad_norm": 0.35058164596557617,
|
1121 |
+
"learning_rate": 0.0001995145631067961,
|
1122 |
+
"loss": 0.4422,
|
1123 |
+
"step": 158
|
1124 |
+
},
|
1125 |
+
{
|
1126 |
+
"epoch": 1.4597701149425286,
|
1127 |
+
"grad_norm": 0.5187242031097412,
|
1128 |
+
"learning_rate": 0.0001987864077669903,
|
1129 |
+
"loss": 0.5037,
|
1130 |
+
"step": 159
|
1131 |
+
},
|
1132 |
+
{
|
1133 |
+
"epoch": 1.4689655172413794,
|
1134 |
+
"grad_norm": 0.7884855270385742,
|
1135 |
+
"learning_rate": 0.00019805825242718447,
|
1136 |
+
"loss": 0.687,
|
1137 |
+
"step": 160
|
1138 |
+
},
|
1139 |
+
{
|
1140 |
+
"epoch": 1.4781609195402299,
|
1141 |
+
"grad_norm": 0.6305707693099976,
|
1142 |
+
"learning_rate": 0.00019733009708737865,
|
1143 |
+
"loss": 0.6576,
|
1144 |
+
"step": 161
|
1145 |
+
},
|
1146 |
+
{
|
1147 |
+
"epoch": 1.4873563218390804,
|
1148 |
+
"grad_norm": 0.5323311686515808,
|
1149 |
+
"learning_rate": 0.0001966019417475728,
|
1150 |
+
"loss": 0.5083,
|
1151 |
+
"step": 162
|
1152 |
+
},
|
1153 |
+
{
|
1154 |
+
"epoch": 1.4965517241379311,
|
1155 |
+
"grad_norm": 0.4653192162513733,
|
1156 |
+
"learning_rate": 0.00019587378640776698,
|
1157 |
+
"loss": 0.4232,
|
1158 |
+
"step": 163
|
1159 |
+
},
|
1160 |
+
{
|
1161 |
+
"epoch": 1.5057471264367817,
|
1162 |
+
"grad_norm": 0.42282363772392273,
|
1163 |
+
"learning_rate": 0.00019514563106796116,
|
1164 |
+
"loss": 0.46,
|
1165 |
+
"step": 164
|
1166 |
+
},
|
1167 |
+
{
|
1168 |
+
"epoch": 1.5149425287356322,
|
1169 |
+
"grad_norm": 0.5382373929023743,
|
1170 |
+
"learning_rate": 0.00019441747572815533,
|
1171 |
+
"loss": 0.6501,
|
1172 |
+
"step": 165
|
1173 |
+
},
|
1174 |
+
{
|
1175 |
+
"epoch": 1.524137931034483,
|
1176 |
+
"grad_norm": 0.49478620290756226,
|
1177 |
+
"learning_rate": 0.0001936893203883495,
|
1178 |
+
"loss": 0.6337,
|
1179 |
+
"step": 166
|
1180 |
+
},
|
1181 |
+
{
|
1182 |
+
"epoch": 1.5333333333333332,
|
1183 |
+
"grad_norm": 0.3653823435306549,
|
1184 |
+
"learning_rate": 0.0001929611650485437,
|
1185 |
+
"loss": 0.5887,
|
1186 |
+
"step": 167
|
1187 |
+
},
|
1188 |
+
{
|
1189 |
+
"epoch": 1.542528735632184,
|
1190 |
+
"grad_norm": 0.8347523808479309,
|
1191 |
+
"learning_rate": 0.00019223300970873787,
|
1192 |
+
"loss": 0.5192,
|
1193 |
+
"step": 168
|
1194 |
+
},
|
1195 |
+
{
|
1196 |
+
"epoch": 1.5517241379310345,
|
1197 |
+
"grad_norm": 0.559551477432251,
|
1198 |
+
"learning_rate": 0.00019150485436893205,
|
1199 |
+
"loss": 0.3474,
|
1200 |
+
"step": 169
|
1201 |
+
},
|
1202 |
+
{
|
1203 |
+
"epoch": 1.560919540229885,
|
1204 |
+
"grad_norm": 0.42149192094802856,
|
1205 |
+
"learning_rate": 0.0001907766990291262,
|
1206 |
+
"loss": 0.407,
|
1207 |
+
"step": 170
|
1208 |
+
},
|
1209 |
+
{
|
1210 |
+
"epoch": 1.5701149425287357,
|
1211 |
+
"grad_norm": 0.5364254117012024,
|
1212 |
+
"learning_rate": 0.00019004854368932038,
|
1213 |
+
"loss": 0.7923,
|
1214 |
+
"step": 171
|
1215 |
+
},
|
1216 |
+
{
|
1217 |
+
"epoch": 1.5793103448275863,
|
1218 |
+
"grad_norm": 0.5137253999710083,
|
1219 |
+
"learning_rate": 0.00018932038834951456,
|
1220 |
+
"loss": 0.5499,
|
1221 |
+
"step": 172
|
1222 |
+
},
|
1223 |
+
{
|
1224 |
+
"epoch": 1.5885057471264368,
|
1225 |
+
"grad_norm": 0.5608237981796265,
|
1226 |
+
"learning_rate": 0.00018859223300970874,
|
1227 |
+
"loss": 0.5724,
|
1228 |
+
"step": 173
|
1229 |
+
},
|
1230 |
+
{
|
1231 |
+
"epoch": 1.5977011494252875,
|
1232 |
+
"grad_norm": 0.34653526544570923,
|
1233 |
+
"learning_rate": 0.00018786407766990291,
|
1234 |
+
"loss": 0.3985,
|
1235 |
+
"step": 174
|
1236 |
+
},
|
1237 |
+
{
|
1238 |
+
"epoch": 1.6068965517241378,
|
1239 |
+
"grad_norm": 0.6667991876602173,
|
1240 |
+
"learning_rate": 0.00018713592233009707,
|
1241 |
+
"loss": 0.6257,
|
1242 |
+
"step": 175
|
1243 |
+
},
|
1244 |
+
{
|
1245 |
+
"epoch": 1.6160919540229886,
|
1246 |
+
"grad_norm": 0.5803218483924866,
|
1247 |
+
"learning_rate": 0.00018640776699029122,
|
1248 |
+
"loss": 0.7256,
|
1249 |
+
"step": 176
|
1250 |
+
},
|
1251 |
+
{
|
1252 |
+
"epoch": 1.625287356321839,
|
1253 |
+
"grad_norm": 0.3350389897823334,
|
1254 |
+
"learning_rate": 0.0001856796116504854,
|
1255 |
+
"loss": 0.3256,
|
1256 |
+
"step": 177
|
1257 |
+
},
|
1258 |
+
{
|
1259 |
+
"epoch": 1.6344827586206896,
|
1260 |
+
"grad_norm": 0.2988188862800598,
|
1261 |
+
"learning_rate": 0.00018495145631067957,
|
1262 |
+
"loss": 0.325,
|
1263 |
+
"step": 178
|
1264 |
+
},
|
1265 |
+
{
|
1266 |
+
"epoch": 1.6436781609195403,
|
1267 |
+
"grad_norm": 0.540225088596344,
|
1268 |
+
"learning_rate": 0.00018422330097087375,
|
1269 |
+
"loss": 0.7405,
|
1270 |
+
"step": 179
|
1271 |
+
},
|
1272 |
+
{
|
1273 |
+
"epoch": 1.6528735632183909,
|
1274 |
+
"grad_norm": 0.46998921036720276,
|
1275 |
+
"learning_rate": 0.00018349514563106793,
|
1276 |
+
"loss": 0.5965,
|
1277 |
+
"step": 180
|
1278 |
+
},
|
1279 |
+
{
|
1280 |
+
"epoch": 1.6620689655172414,
|
1281 |
+
"grad_norm": 0.42614537477493286,
|
1282 |
+
"learning_rate": 0.0001827669902912621,
|
1283 |
+
"loss": 0.5187,
|
1284 |
+
"step": 181
|
1285 |
+
},
|
1286 |
+
{
|
1287 |
+
"epoch": 1.6712643678160921,
|
1288 |
+
"grad_norm": 0.5146321058273315,
|
1289 |
+
"learning_rate": 0.0001820388349514563,
|
1290 |
+
"loss": 0.6134,
|
1291 |
+
"step": 182
|
1292 |
+
},
|
1293 |
+
{
|
1294 |
+
"epoch": 1.6804597701149424,
|
1295 |
+
"grad_norm": 0.5366286635398865,
|
1296 |
+
"learning_rate": 0.00018131067961165047,
|
1297 |
+
"loss": 0.4942,
|
1298 |
+
"step": 183
|
1299 |
+
},
|
1300 |
+
{
|
1301 |
+
"epoch": 1.6896551724137931,
|
1302 |
+
"grad_norm": 0.5794548392295837,
|
1303 |
+
"learning_rate": 0.00018058252427184462,
|
1304 |
+
"loss": 0.6949,
|
1305 |
+
"step": 184
|
1306 |
+
},
|
1307 |
+
{
|
1308 |
+
"epoch": 1.6988505747126437,
|
1309 |
+
"grad_norm": 0.4413406550884247,
|
1310 |
+
"learning_rate": 0.0001798543689320388,
|
1311 |
+
"loss": 0.5908,
|
1312 |
+
"step": 185
|
1313 |
+
},
|
1314 |
+
{
|
1315 |
+
"epoch": 1.7080459770114942,
|
1316 |
+
"grad_norm": 0.5551508069038391,
|
1317 |
+
"learning_rate": 0.00017912621359223298,
|
1318 |
+
"loss": 0.4899,
|
1319 |
+
"step": 186
|
1320 |
+
},
|
1321 |
+
{
|
1322 |
+
"epoch": 1.717241379310345,
|
1323 |
+
"grad_norm": 0.5020127892494202,
|
1324 |
+
"learning_rate": 0.00017839805825242716,
|
1325 |
+
"loss": 0.3787,
|
1326 |
+
"step": 187
|
1327 |
+
},
|
1328 |
+
{
|
1329 |
+
"epoch": 1.7264367816091954,
|
1330 |
+
"grad_norm": 0.5126776695251465,
|
1331 |
+
"learning_rate": 0.00017766990291262133,
|
1332 |
+
"loss": 0.4694,
|
1333 |
+
"step": 188
|
1334 |
+
},
|
1335 |
+
{
|
1336 |
+
"epoch": 1.735632183908046,
|
1337 |
+
"grad_norm": 0.5620916485786438,
|
1338 |
+
"learning_rate": 0.0001769417475728155,
|
1339 |
+
"loss": 0.5547,
|
1340 |
+
"step": 189
|
1341 |
+
},
|
1342 |
+
{
|
1343 |
+
"epoch": 1.7448275862068967,
|
1344 |
+
"grad_norm": 0.4924725294113159,
|
1345 |
+
"learning_rate": 0.0001762135922330097,
|
1346 |
+
"loss": 0.5656,
|
1347 |
+
"step": 190
|
1348 |
+
},
|
1349 |
+
{
|
1350 |
+
"epoch": 1.754022988505747,
|
1351 |
+
"grad_norm": 0.3647457957267761,
|
1352 |
+
"learning_rate": 0.00017548543689320387,
|
1353 |
+
"loss": 0.5137,
|
1354 |
+
"step": 191
|
1355 |
+
},
|
1356 |
+
{
|
1357 |
+
"epoch": 1.7632183908045977,
|
1358 |
+
"grad_norm": 0.4956059455871582,
|
1359 |
+
"learning_rate": 0.00017475728155339802,
|
1360 |
+
"loss": 0.6375,
|
1361 |
+
"step": 192
|
1362 |
+
},
|
1363 |
+
{
|
1364 |
+
"epoch": 1.7724137931034483,
|
1365 |
+
"grad_norm": 0.3766675591468811,
|
1366 |
+
"learning_rate": 0.0001740291262135922,
|
1367 |
+
"loss": 0.5081,
|
1368 |
+
"step": 193
|
1369 |
+
},
|
1370 |
+
{
|
1371 |
+
"epoch": 1.7816091954022988,
|
1372 |
+
"grad_norm": 0.3699629604816437,
|
1373 |
+
"learning_rate": 0.00017330097087378638,
|
1374 |
+
"loss": 0.3969,
|
1375 |
+
"step": 194
|
1376 |
+
},
|
1377 |
+
{
|
1378 |
+
"epoch": 1.7908045977011495,
|
1379 |
+
"grad_norm": 0.35047248005867004,
|
1380 |
+
"learning_rate": 0.00017257281553398056,
|
1381 |
+
"loss": 0.4473,
|
1382 |
+
"step": 195
|
1383 |
+
},
|
1384 |
+
{
|
1385 |
+
"epoch": 1.8,
|
1386 |
+
"grad_norm": 0.5037795901298523,
|
1387 |
+
"learning_rate": 0.00017184466019417474,
|
1388 |
+
"loss": 0.4882,
|
1389 |
+
"step": 196
|
1390 |
+
},
|
1391 |
+
{
|
1392 |
+
"epoch": 1.8091954022988506,
|
1393 |
+
"grad_norm": 0.46976998448371887,
|
1394 |
+
"learning_rate": 0.00017111650485436891,
|
1395 |
+
"loss": 0.5307,
|
1396 |
+
"step": 197
|
1397 |
+
},
|
1398 |
+
{
|
1399 |
+
"epoch": 1.8183908045977013,
|
1400 |
+
"grad_norm": 0.5248985290527344,
|
1401 |
+
"learning_rate": 0.0001703883495145631,
|
1402 |
+
"loss": 0.5062,
|
1403 |
+
"step": 198
|
1404 |
+
},
|
1405 |
+
{
|
1406 |
+
"epoch": 1.8275862068965516,
|
1407 |
+
"grad_norm": 0.4395950436592102,
|
1408 |
+
"learning_rate": 0.00016966019417475724,
|
1409 |
+
"loss": 0.5184,
|
1410 |
+
"step": 199
|
1411 |
+
},
|
1412 |
+
{
|
1413 |
+
"epoch": 1.8367816091954023,
|
1414 |
+
"grad_norm": 0.31456464529037476,
|
1415 |
+
"learning_rate": 0.00016893203883495142,
|
1416 |
+
"loss": 0.3707,
|
1417 |
+
"step": 200
|
1418 |
+
},
|
1419 |
+
{
|
1420 |
+
"epoch": 1.8459770114942529,
|
1421 |
+
"grad_norm": 0.39423462748527527,
|
1422 |
+
"learning_rate": 0.0001682038834951456,
|
1423 |
+
"loss": 0.3915,
|
1424 |
+
"step": 201
|
1425 |
+
},
|
1426 |
+
{
|
1427 |
+
"epoch": 1.8551724137931034,
|
1428 |
+
"grad_norm": 0.3807072937488556,
|
1429 |
+
"learning_rate": 0.00016747572815533978,
|
1430 |
+
"loss": 0.4203,
|
1431 |
+
"step": 202
|
1432 |
+
},
|
1433 |
+
{
|
1434 |
+
"epoch": 1.8643678160919541,
|
1435 |
+
"grad_norm": 0.49600493907928467,
|
1436 |
+
"learning_rate": 0.00016674757281553396,
|
1437 |
+
"loss": 0.5633,
|
1438 |
+
"step": 203
|
1439 |
+
},
|
1440 |
+
{
|
1441 |
+
"epoch": 1.8735632183908046,
|
1442 |
+
"grad_norm": 0.4472233057022095,
|
1443 |
+
"learning_rate": 0.00016601941747572814,
|
1444 |
+
"loss": 0.5791,
|
1445 |
+
"step": 204
|
1446 |
+
},
|
1447 |
+
{
|
1448 |
+
"epoch": 1.8827586206896552,
|
1449 |
+
"grad_norm": 0.48306939005851746,
|
1450 |
+
"learning_rate": 0.00016529126213592232,
|
1451 |
+
"loss": 0.4091,
|
1452 |
+
"step": 205
|
1453 |
+
},
|
1454 |
+
{
|
1455 |
+
"epoch": 1.891954022988506,
|
1456 |
+
"grad_norm": 0.40710389614105225,
|
1457 |
+
"learning_rate": 0.0001645631067961165,
|
1458 |
+
"loss": 0.5302,
|
1459 |
+
"step": 206
|
1460 |
+
},
|
1461 |
+
{
|
1462 |
+
"epoch": 1.9011494252873562,
|
1463 |
+
"grad_norm": 0.37706899642944336,
|
1464 |
+
"learning_rate": 0.00016383495145631065,
|
1465 |
+
"loss": 0.416,
|
1466 |
+
"step": 207
|
1467 |
+
},
|
1468 |
+
{
|
1469 |
+
"epoch": 1.910344827586207,
|
1470 |
+
"grad_norm": 0.5805254578590393,
|
1471 |
+
"learning_rate": 0.00016310679611650483,
|
1472 |
+
"loss": 0.6861,
|
1473 |
+
"step": 208
|
1474 |
+
},
|
1475 |
+
{
|
1476 |
+
"epoch": 1.9195402298850575,
|
1477 |
+
"grad_norm": 0.44542425870895386,
|
1478 |
+
"learning_rate": 0.000162378640776699,
|
1479 |
+
"loss": 0.5468,
|
1480 |
+
"step": 209
|
1481 |
+
},
|
1482 |
+
{
|
1483 |
+
"epoch": 1.928735632183908,
|
1484 |
+
"grad_norm": 0.44782838225364685,
|
1485 |
+
"learning_rate": 0.00016165048543689318,
|
1486 |
+
"loss": 0.4827,
|
1487 |
+
"step": 210
|
1488 |
+
},
|
1489 |
+
{
|
1490 |
+
"epoch": 1.9379310344827587,
|
1491 |
+
"grad_norm": 0.30875957012176514,
|
1492 |
+
"learning_rate": 0.00016092233009708736,
|
1493 |
+
"loss": 0.3472,
|
1494 |
+
"step": 211
|
1495 |
+
},
|
1496 |
+
{
|
1497 |
+
"epoch": 1.9471264367816092,
|
1498 |
+
"grad_norm": 0.4443942904472351,
|
1499 |
+
"learning_rate": 0.00016019417475728154,
|
1500 |
+
"loss": 0.5595,
|
1501 |
+
"step": 212
|
1502 |
+
},
|
1503 |
+
{
|
1504 |
+
"epoch": 1.9563218390804598,
|
1505 |
+
"grad_norm": 0.32429659366607666,
|
1506 |
+
"learning_rate": 0.00015946601941747572,
|
1507 |
+
"loss": 0.374,
|
1508 |
+
"step": 213
|
1509 |
+
},
|
1510 |
+
{
|
1511 |
+
"epoch": 1.9655172413793105,
|
1512 |
+
"grad_norm": 0.339242160320282,
|
1513 |
+
"learning_rate": 0.0001587378640776699,
|
1514 |
+
"loss": 0.4155,
|
1515 |
+
"step": 214
|
1516 |
+
},
|
1517 |
+
{
|
1518 |
+
"epoch": 1.9747126436781608,
|
1519 |
+
"grad_norm": 0.5646737813949585,
|
1520 |
+
"learning_rate": 0.00015800970873786405,
|
1521 |
+
"loss": 0.8037,
|
1522 |
+
"step": 215
|
1523 |
+
},
|
1524 |
+
{
|
1525 |
+
"epoch": 1.9839080459770115,
|
1526 |
+
"grad_norm": 0.5335783958435059,
|
1527 |
+
"learning_rate": 0.00015728155339805823,
|
1528 |
+
"loss": 0.7524,
|
1529 |
+
"step": 216
|
1530 |
+
},
|
1531 |
+
{
|
1532 |
+
"epoch": 1.993103448275862,
|
1533 |
+
"grad_norm": 0.46629971265792847,
|
1534 |
+
"learning_rate": 0.0001565533980582524,
|
1535 |
+
"loss": 0.598,
|
1536 |
+
"step": 217
|
1537 |
+
},
|
1538 |
+
{
|
1539 |
+
"epoch": 2.0,
|
1540 |
+
"grad_norm": 0.7031301856040955,
|
1541 |
+
"learning_rate": 0.00015582524271844658,
|
1542 |
+
"loss": 0.7793,
|
1543 |
+
"step": 218
|
1544 |
+
},
|
1545 |
+
{
|
1546 |
+
"epoch": 2.0,
|
1547 |
+
"eval_loss": 1.3836089372634888,
|
1548 |
+
"eval_runtime": 94.5395,
|
1549 |
+
"eval_samples_per_second": 3.512,
|
1550 |
+
"eval_steps_per_second": 1.756,
|
1551 |
+
"step": 218
|
1552 |
+
},
|
1553 |
+
{
|
1554 |
+
"epoch": 2.0091954022988507,
|
1555 |
+
"grad_norm": 0.3298664093017578,
|
1556 |
+
"learning_rate": 0.00015509708737864076,
|
1557 |
+
"loss": 0.3196,
|
1558 |
+
"step": 219
|
1559 |
+
},
|
1560 |
+
{
|
1561 |
+
"epoch": 2.018390804597701,
|
1562 |
+
"grad_norm": 0.4151831567287445,
|
1563 |
+
"learning_rate": 0.00015436893203883494,
|
1564 |
+
"loss": 0.4209,
|
1565 |
+
"step": 220
|
1566 |
+
},
|
1567 |
+
{
|
1568 |
+
"epoch": 2.027586206896552,
|
1569 |
+
"grad_norm": 0.35617533326148987,
|
1570 |
+
"learning_rate": 0.00015364077669902912,
|
1571 |
+
"loss": 0.4023,
|
1572 |
+
"step": 221
|
1573 |
+
},
|
1574 |
+
{
|
1575 |
+
"epoch": 2.036781609195402,
|
1576 |
+
"grad_norm": 0.41707131266593933,
|
1577 |
+
"learning_rate": 0.0001529126213592233,
|
1578 |
+
"loss": 0.4355,
|
1579 |
+
"step": 222
|
1580 |
+
},
|
1581 |
+
{
|
1582 |
+
"epoch": 2.045977011494253,
|
1583 |
+
"grad_norm": 0.3739112913608551,
|
1584 |
+
"learning_rate": 0.00015218446601941745,
|
1585 |
+
"loss": 0.3309,
|
1586 |
+
"step": 223
|
1587 |
+
},
|
1588 |
+
{
|
1589 |
+
"epoch": 2.0551724137931036,
|
1590 |
+
"grad_norm": 0.529603123664856,
|
1591 |
+
"learning_rate": 0.00015145631067961163,
|
1592 |
+
"loss": 0.3706,
|
1593 |
+
"step": 224
|
1594 |
+
},
|
1595 |
+
{
|
1596 |
+
"epoch": 2.064367816091954,
|
1597 |
+
"grad_norm": 0.4731467664241791,
|
1598 |
+
"learning_rate": 0.0001507281553398058,
|
1599 |
+
"loss": 0.379,
|
1600 |
+
"step": 225
|
1601 |
+
},
|
1602 |
+
{
|
1603 |
+
"epoch": 2.0735632183908046,
|
1604 |
+
"grad_norm": 0.5218953490257263,
|
1605 |
+
"learning_rate": 0.00015,
|
1606 |
+
"loss": 0.3467,
|
1607 |
+
"step": 226
|
1608 |
+
},
|
1609 |
+
{
|
1610 |
+
"epoch": 2.0827586206896553,
|
1611 |
+
"grad_norm": 0.7507036924362183,
|
1612 |
+
"learning_rate": 0.00014927184466019417,
|
1613 |
+
"loss": 0.6107,
|
1614 |
+
"step": 227
|
1615 |
+
},
|
1616 |
+
{
|
1617 |
+
"epoch": 2.0919540229885056,
|
1618 |
+
"grad_norm": 0.44099223613739014,
|
1619 |
+
"learning_rate": 0.00014854368932038834,
|
1620 |
+
"loss": 0.3186,
|
1621 |
+
"step": 228
|
1622 |
+
},
|
1623 |
+
{
|
1624 |
+
"epoch": 2.1011494252873564,
|
1625 |
+
"grad_norm": 0.4234969913959503,
|
1626 |
+
"learning_rate": 0.00014781553398058252,
|
1627 |
+
"loss": 0.3482,
|
1628 |
+
"step": 229
|
1629 |
+
},
|
1630 |
+
{
|
1631 |
+
"epoch": 2.110344827586207,
|
1632 |
+
"grad_norm": 0.49509719014167786,
|
1633 |
+
"learning_rate": 0.00014708737864077667,
|
1634 |
+
"loss": 0.3985,
|
1635 |
+
"step": 230
|
1636 |
+
},
|
1637 |
+
{
|
1638 |
+
"epoch": 2.1195402298850574,
|
1639 |
+
"grad_norm": 0.43987375497817993,
|
1640 |
+
"learning_rate": 0.00014635922330097085,
|
1641 |
+
"loss": 0.3618,
|
1642 |
+
"step": 231
|
1643 |
+
},
|
1644 |
+
{
|
1645 |
+
"epoch": 2.128735632183908,
|
1646 |
+
"grad_norm": 0.6162170767784119,
|
1647 |
+
"learning_rate": 0.00014563106796116503,
|
1648 |
+
"loss": 0.4423,
|
1649 |
+
"step": 232
|
1650 |
+
},
|
1651 |
+
{
|
1652 |
+
"epoch": 2.1379310344827585,
|
1653 |
+
"grad_norm": 0.3867994248867035,
|
1654 |
+
"learning_rate": 0.0001449029126213592,
|
1655 |
+
"loss": 0.3419,
|
1656 |
+
"step": 233
|
1657 |
+
},
|
1658 |
+
{
|
1659 |
+
"epoch": 2.147126436781609,
|
1660 |
+
"grad_norm": 0.7177544832229614,
|
1661 |
+
"learning_rate": 0.0001441747572815534,
|
1662 |
+
"loss": 0.4747,
|
1663 |
+
"step": 234
|
1664 |
+
},
|
1665 |
+
{
|
1666 |
+
"epoch": 2.15632183908046,
|
1667 |
+
"grad_norm": 0.5735111236572266,
|
1668 |
+
"learning_rate": 0.00014344660194174757,
|
1669 |
+
"loss": 0.4305,
|
1670 |
+
"step": 235
|
1671 |
+
},
|
1672 |
+
{
|
1673 |
+
"epoch": 2.1655172413793102,
|
1674 |
+
"grad_norm": 0.5527003407478333,
|
1675 |
+
"learning_rate": 0.00014271844660194175,
|
1676 |
+
"loss": 0.3601,
|
1677 |
+
"step": 236
|
1678 |
+
},
|
1679 |
+
{
|
1680 |
+
"epoch": 2.174712643678161,
|
1681 |
+
"grad_norm": 0.5799367427825928,
|
1682 |
+
"learning_rate": 0.00014199029126213592,
|
1683 |
+
"loss": 0.4681,
|
1684 |
+
"step": 237
|
1685 |
+
},
|
1686 |
+
{
|
1687 |
+
"epoch": 2.1839080459770113,
|
1688 |
+
"grad_norm": 0.5536375045776367,
|
1689 |
+
"learning_rate": 0.00014126213592233008,
|
1690 |
+
"loss": 0.4431,
|
1691 |
+
"step": 238
|
1692 |
+
},
|
1693 |
+
{
|
1694 |
+
"epoch": 2.193103448275862,
|
1695 |
+
"grad_norm": 0.45677146315574646,
|
1696 |
+
"learning_rate": 0.00014053398058252425,
|
1697 |
+
"loss": 0.3618,
|
1698 |
+
"step": 239
|
1699 |
+
},
|
1700 |
+
{
|
1701 |
+
"epoch": 2.2022988505747128,
|
1702 |
+
"grad_norm": 0.464231938123703,
|
1703 |
+
"learning_rate": 0.00013980582524271843,
|
1704 |
+
"loss": 0.3164,
|
1705 |
+
"step": 240
|
1706 |
+
},
|
1707 |
+
{
|
1708 |
+
"epoch": 2.211494252873563,
|
1709 |
+
"grad_norm": 0.7074082493782043,
|
1710 |
+
"learning_rate": 0.0001390776699029126,
|
1711 |
+
"loss": 0.5988,
|
1712 |
+
"step": 241
|
1713 |
+
},
|
1714 |
+
{
|
1715 |
+
"epoch": 2.220689655172414,
|
1716 |
+
"grad_norm": 0.4413163363933563,
|
1717 |
+
"learning_rate": 0.0001383495145631068,
|
1718 |
+
"loss": 0.2946,
|
1719 |
+
"step": 242
|
1720 |
+
},
|
1721 |
+
{
|
1722 |
+
"epoch": 2.2298850574712645,
|
1723 |
+
"grad_norm": 0.3606387972831726,
|
1724 |
+
"learning_rate": 0.00013762135922330097,
|
1725 |
+
"loss": 0.2709,
|
1726 |
+
"step": 243
|
1727 |
+
},
|
1728 |
+
{
|
1729 |
+
"epoch": 2.239080459770115,
|
1730 |
+
"grad_norm": 0.6036794185638428,
|
1731 |
+
"learning_rate": 0.00013689320388349515,
|
1732 |
+
"loss": 0.5043,
|
1733 |
+
"step": 244
|
1734 |
+
},
|
1735 |
+
{
|
1736 |
+
"epoch": 2.2482758620689656,
|
1737 |
+
"grad_norm": 0.7041867971420288,
|
1738 |
+
"learning_rate": 0.00013616504854368933,
|
1739 |
+
"loss": 0.6161,
|
1740 |
+
"step": 245
|
1741 |
+
},
|
1742 |
+
{
|
1743 |
+
"epoch": 2.2574712643678163,
|
1744 |
+
"grad_norm": 0.36813509464263916,
|
1745 |
+
"learning_rate": 0.00013543689320388348,
|
1746 |
+
"loss": 0.2538,
|
1747 |
+
"step": 246
|
1748 |
+
},
|
1749 |
+
{
|
1750 |
+
"epoch": 2.2666666666666666,
|
1751 |
+
"grad_norm": 0.6574187874794006,
|
1752 |
+
"learning_rate": 0.00013470873786407766,
|
1753 |
+
"loss": 0.5472,
|
1754 |
+
"step": 247
|
1755 |
+
},
|
1756 |
+
{
|
1757 |
+
"epoch": 2.2758620689655173,
|
1758 |
+
"grad_norm": 0.3584626317024231,
|
1759 |
+
"learning_rate": 0.00013398058252427184,
|
1760 |
+
"loss": 0.2486,
|
1761 |
+
"step": 248
|
1762 |
+
},
|
1763 |
+
{
|
1764 |
+
"epoch": 2.2850574712643676,
|
1765 |
+
"grad_norm": 0.7730153203010559,
|
1766 |
+
"learning_rate": 0.00013325242718446601,
|
1767 |
+
"loss": 0.4867,
|
1768 |
+
"step": 249
|
1769 |
+
},
|
1770 |
+
{
|
1771 |
+
"epoch": 2.2942528735632184,
|
1772 |
+
"grad_norm": 0.6601793766021729,
|
1773 |
+
"learning_rate": 0.0001325242718446602,
|
1774 |
+
"loss": 0.6158,
|
1775 |
+
"step": 250
|
1776 |
+
},
|
1777 |
+
{
|
1778 |
+
"epoch": 2.303448275862069,
|
1779 |
+
"grad_norm": 0.42591384053230286,
|
1780 |
+
"learning_rate": 0.00013179611650485437,
|
1781 |
+
"loss": 0.3484,
|
1782 |
+
"step": 251
|
1783 |
+
},
|
1784 |
+
{
|
1785 |
+
"epoch": 2.3126436781609194,
|
1786 |
+
"grad_norm": 0.3791221082210541,
|
1787 |
+
"learning_rate": 0.00013106796116504852,
|
1788 |
+
"loss": 0.2861,
|
1789 |
+
"step": 252
|
1790 |
+
},
|
1791 |
+
{
|
1792 |
+
"epoch": 2.32183908045977,
|
1793 |
+
"grad_norm": 0.5107592940330505,
|
1794 |
+
"learning_rate": 0.0001303398058252427,
|
1795 |
+
"loss": 0.4219,
|
1796 |
+
"step": 253
|
1797 |
+
},
|
1798 |
+
{
|
1799 |
+
"epoch": 2.3310344827586205,
|
1800 |
+
"grad_norm": 0.43515774607658386,
|
1801 |
+
"learning_rate": 0.00012961165048543688,
|
1802 |
+
"loss": 0.32,
|
1803 |
+
"step": 254
|
1804 |
+
},
|
1805 |
+
{
|
1806 |
+
"epoch": 2.340229885057471,
|
1807 |
+
"grad_norm": 0.45249196887016296,
|
1808 |
+
"learning_rate": 0.00012888349514563106,
|
1809 |
+
"loss": 0.3144,
|
1810 |
+
"step": 255
|
1811 |
+
},
|
1812 |
+
{
|
1813 |
+
"epoch": 2.349425287356322,
|
1814 |
+
"grad_norm": 0.5824540853500366,
|
1815 |
+
"learning_rate": 0.00012815533980582524,
|
1816 |
+
"loss": 0.4423,
|
1817 |
+
"step": 256
|
1818 |
+
},
|
1819 |
+
{
|
1820 |
+
"epoch": 2.3586206896551722,
|
1821 |
+
"grad_norm": 0.680497407913208,
|
1822 |
+
"learning_rate": 0.0001274271844660194,
|
1823 |
+
"loss": 0.579,
|
1824 |
+
"step": 257
|
1825 |
+
},
|
1826 |
+
{
|
1827 |
+
"epoch": 2.367816091954023,
|
1828 |
+
"grad_norm": 0.45555397868156433,
|
1829 |
+
"learning_rate": 0.00012669902912621357,
|
1830 |
+
"loss": 0.3296,
|
1831 |
+
"step": 258
|
1832 |
+
},
|
1833 |
+
{
|
1834 |
+
"epoch": 2.3770114942528737,
|
1835 |
+
"grad_norm": 0.5558891892433167,
|
1836 |
+
"learning_rate": 0.00012597087378640775,
|
1837 |
+
"loss": 0.4183,
|
1838 |
+
"step": 259
|
1839 |
+
},
|
1840 |
+
{
|
1841 |
+
"epoch": 2.386206896551724,
|
1842 |
+
"grad_norm": 0.6155978441238403,
|
1843 |
+
"learning_rate": 0.00012524271844660192,
|
1844 |
+
"loss": 0.4989,
|
1845 |
+
"step": 260
|
1846 |
+
},
|
1847 |
+
{
|
1848 |
+
"epoch": 2.3954022988505748,
|
1849 |
+
"grad_norm": 0.5432369709014893,
|
1850 |
+
"learning_rate": 0.0001245145631067961,
|
1851 |
+
"loss": 0.4149,
|
1852 |
+
"step": 261
|
1853 |
+
},
|
1854 |
+
{
|
1855 |
+
"epoch": 2.4045977011494255,
|
1856 |
+
"grad_norm": 0.3622282147407532,
|
1857 |
+
"learning_rate": 0.00012378640776699028,
|
1858 |
+
"loss": 0.2948,
|
1859 |
+
"step": 262
|
1860 |
+
},
|
1861 |
+
{
|
1862 |
+
"epoch": 2.413793103448276,
|
1863 |
+
"grad_norm": 0.42852282524108887,
|
1864 |
+
"learning_rate": 0.00012305825242718446,
|
1865 |
+
"loss": 0.2617,
|
1866 |
+
"step": 263
|
1867 |
+
},
|
1868 |
+
{
|
1869 |
+
"epoch": 2.4229885057471265,
|
1870 |
+
"grad_norm": 0.3979598879814148,
|
1871 |
+
"learning_rate": 0.0001223300970873786,
|
1872 |
+
"loss": 0.221,
|
1873 |
+
"step": 264
|
1874 |
+
},
|
1875 |
+
{
|
1876 |
+
"epoch": 2.432183908045977,
|
1877 |
+
"grad_norm": 0.4943128526210785,
|
1878 |
+
"learning_rate": 0.0001216019417475728,
|
1879 |
+
"loss": 0.31,
|
1880 |
+
"step": 265
|
1881 |
+
},
|
1882 |
+
{
|
1883 |
+
"epoch": 2.4413793103448276,
|
1884 |
+
"grad_norm": 0.5944445133209229,
|
1885 |
+
"learning_rate": 0.00012087378640776697,
|
1886 |
+
"loss": 0.5284,
|
1887 |
+
"step": 266
|
1888 |
+
},
|
1889 |
+
{
|
1890 |
+
"epoch": 2.4505747126436783,
|
1891 |
+
"grad_norm": 0.5441230535507202,
|
1892 |
+
"learning_rate": 0.00012014563106796115,
|
1893 |
+
"loss": 0.4091,
|
1894 |
+
"step": 267
|
1895 |
+
},
|
1896 |
+
{
|
1897 |
+
"epoch": 2.4597701149425286,
|
1898 |
+
"grad_norm": 0.3592386543750763,
|
1899 |
+
"learning_rate": 0.00011941747572815533,
|
1900 |
+
"loss": 0.2881,
|
1901 |
+
"step": 268
|
1902 |
+
},
|
1903 |
+
{
|
1904 |
+
"epoch": 2.4689655172413794,
|
1905 |
+
"grad_norm": 0.4022001028060913,
|
1906 |
+
"learning_rate": 0.0001186893203883495,
|
1907 |
+
"loss": 0.3005,
|
1908 |
+
"step": 269
|
1909 |
+
},
|
1910 |
+
{
|
1911 |
+
"epoch": 2.4781609195402297,
|
1912 |
+
"grad_norm": 0.3709545433521271,
|
1913 |
+
"learning_rate": 0.00011796116504854367,
|
1914 |
+
"loss": 0.261,
|
1915 |
+
"step": 270
|
1916 |
+
},
|
1917 |
+
{
|
1918 |
+
"epoch": 2.4873563218390804,
|
1919 |
+
"grad_norm": 0.4119846522808075,
|
1920 |
+
"learning_rate": 0.00011723300970873785,
|
1921 |
+
"loss": 0.284,
|
1922 |
+
"step": 271
|
1923 |
+
},
|
1924 |
+
{
|
1925 |
+
"epoch": 2.496551724137931,
|
1926 |
+
"grad_norm": 0.5992346405982971,
|
1927 |
+
"learning_rate": 0.00011650485436893203,
|
1928 |
+
"loss": 0.6485,
|
1929 |
+
"step": 272
|
1930 |
+
},
|
1931 |
+
{
|
1932 |
+
"epoch": 2.5057471264367814,
|
1933 |
+
"grad_norm": 0.3555474579334259,
|
1934 |
+
"learning_rate": 0.0001157766990291262,
|
1935 |
+
"loss": 0.2032,
|
1936 |
+
"step": 273
|
1937 |
+
},
|
1938 |
+
{
|
1939 |
+
"epoch": 2.514942528735632,
|
1940 |
+
"grad_norm": 0.40004169940948486,
|
1941 |
+
"learning_rate": 0.00011504854368932037,
|
1942 |
+
"loss": 0.3559,
|
1943 |
+
"step": 274
|
1944 |
+
},
|
1945 |
+
{
|
1946 |
+
"epoch": 2.524137931034483,
|
1947 |
+
"grad_norm": 0.5196751356124878,
|
1948 |
+
"learning_rate": 0.00011432038834951455,
|
1949 |
+
"loss": 0.3952,
|
1950 |
+
"step": 275
|
1951 |
+
},
|
1952 |
+
{
|
1953 |
+
"epoch": 2.533333333333333,
|
1954 |
+
"grad_norm": 0.2508908808231354,
|
1955 |
+
"learning_rate": 0.00011359223300970873,
|
1956 |
+
"loss": 0.1867,
|
1957 |
+
"step": 276
|
1958 |
+
},
|
1959 |
+
{
|
1960 |
+
"epoch": 2.542528735632184,
|
1961 |
+
"grad_norm": 0.5024006366729736,
|
1962 |
+
"learning_rate": 0.00011286407766990291,
|
1963 |
+
"loss": 0.4146,
|
1964 |
+
"step": 277
|
1965 |
+
},
|
1966 |
+
{
|
1967 |
+
"epoch": 2.5517241379310347,
|
1968 |
+
"grad_norm": 0.48392558097839355,
|
1969 |
+
"learning_rate": 0.00011213592233009707,
|
1970 |
+
"loss": 0.404,
|
1971 |
+
"step": 278
|
1972 |
+
},
|
1973 |
+
{
|
1974 |
+
"epoch": 2.560919540229885,
|
1975 |
+
"grad_norm": 0.3421654999256134,
|
1976 |
+
"learning_rate": 0.00011140776699029125,
|
1977 |
+
"loss": 0.2727,
|
1978 |
+
"step": 279
|
1979 |
+
},
|
1980 |
+
{
|
1981 |
+
"epoch": 2.5701149425287357,
|
1982 |
+
"grad_norm": 0.32812729477882385,
|
1983 |
+
"learning_rate": 0.00011067961165048543,
|
1984 |
+
"loss": 0.2466,
|
1985 |
+
"step": 280
|
1986 |
+
},
|
1987 |
+
{
|
1988 |
+
"epoch": 2.5793103448275865,
|
1989 |
+
"grad_norm": 0.3916667401790619,
|
1990 |
+
"learning_rate": 0.00010995145631067961,
|
1991 |
+
"loss": 0.2962,
|
1992 |
+
"step": 281
|
1993 |
+
},
|
1994 |
+
{
|
1995 |
+
"epoch": 2.5885057471264368,
|
1996 |
+
"grad_norm": 0.41674014925956726,
|
1997 |
+
"learning_rate": 0.00010922330097087377,
|
1998 |
+
"loss": 0.3091,
|
1999 |
+
"step": 282
|
2000 |
+
},
|
2001 |
+
{
|
2002 |
+
"epoch": 2.5977011494252875,
|
2003 |
+
"grad_norm": 0.5579612851142883,
|
2004 |
+
"learning_rate": 0.00010849514563106795,
|
2005 |
+
"loss": 0.4515,
|
2006 |
+
"step": 283
|
2007 |
+
},
|
2008 |
+
{
|
2009 |
+
"epoch": 2.606896551724138,
|
2010 |
+
"grad_norm": 0.31362155079841614,
|
2011 |
+
"learning_rate": 0.00010776699029126213,
|
2012 |
+
"loss": 0.209,
|
2013 |
+
"step": 284
|
2014 |
+
},
|
2015 |
+
{
|
2016 |
+
"epoch": 2.6160919540229886,
|
2017 |
+
"grad_norm": 0.3783795237541199,
|
2018 |
+
"learning_rate": 0.00010703883495145631,
|
2019 |
+
"loss": 0.2683,
|
2020 |
+
"step": 285
|
2021 |
+
},
|
2022 |
+
{
|
2023 |
+
"epoch": 2.625287356321839,
|
2024 |
+
"grad_norm": 0.4127572178840637,
|
2025 |
+
"learning_rate": 0.00010631067961165047,
|
2026 |
+
"loss": 0.3164,
|
2027 |
+
"step": 286
|
2028 |
+
},
|
2029 |
+
{
|
2030 |
+
"epoch": 2.6344827586206896,
|
2031 |
+
"grad_norm": 0.42433518171310425,
|
2032 |
+
"learning_rate": 0.00010558252427184465,
|
2033 |
+
"loss": 0.2813,
|
2034 |
+
"step": 287
|
2035 |
+
},
|
2036 |
+
{
|
2037 |
+
"epoch": 2.6436781609195403,
|
2038 |
+
"grad_norm": 0.26535582542419434,
|
2039 |
+
"learning_rate": 0.00010485436893203883,
|
2040 |
+
"loss": 0.1638,
|
2041 |
+
"step": 288
|
2042 |
+
},
|
2043 |
+
{
|
2044 |
+
"epoch": 2.6528735632183906,
|
2045 |
+
"grad_norm": 0.47647133469581604,
|
2046 |
+
"learning_rate": 0.00010412621359223301,
|
2047 |
+
"loss": 0.3998,
|
2048 |
+
"step": 289
|
2049 |
+
},
|
2050 |
+
{
|
2051 |
+
"epoch": 2.6620689655172414,
|
2052 |
+
"grad_norm": 0.4837816059589386,
|
2053 |
+
"learning_rate": 0.00010339805825242718,
|
2054 |
+
"loss": 0.3634,
|
2055 |
+
"step": 290
|
2056 |
+
},
|
2057 |
+
{
|
2058 |
+
"epoch": 2.671264367816092,
|
2059 |
+
"grad_norm": 0.5139144062995911,
|
2060 |
+
"learning_rate": 0.00010266990291262135,
|
2061 |
+
"loss": 0.4553,
|
2062 |
+
"step": 291
|
2063 |
+
},
|
2064 |
+
{
|
2065 |
+
"epoch": 2.6804597701149424,
|
2066 |
+
"grad_norm": 0.42559128999710083,
|
2067 |
+
"learning_rate": 0.00010194174757281553,
|
2068 |
+
"loss": 0.2803,
|
2069 |
+
"step": 292
|
2070 |
+
},
|
2071 |
+
{
|
2072 |
+
"epoch": 2.689655172413793,
|
2073 |
+
"grad_norm": 0.5253325700759888,
|
2074 |
+
"learning_rate": 0.00010121359223300971,
|
2075 |
+
"loss": 0.4476,
|
2076 |
+
"step": 293
|
2077 |
+
},
|
2078 |
+
{
|
2079 |
+
"epoch": 2.698850574712644,
|
2080 |
+
"grad_norm": 0.42015260457992554,
|
2081 |
+
"learning_rate": 0.00010048543689320388,
|
2082 |
+
"loss": 0.3619,
|
2083 |
+
"step": 294
|
2084 |
+
},
|
2085 |
+
{
|
2086 |
+
"epoch": 2.708045977011494,
|
2087 |
+
"grad_norm": 0.7167945504188538,
|
2088 |
+
"learning_rate": 9.975728155339806e-05,
|
2089 |
+
"loss": 0.6277,
|
2090 |
+
"step": 295
|
2091 |
+
},
|
2092 |
+
{
|
2093 |
+
"epoch": 2.717241379310345,
|
2094 |
+
"grad_norm": 0.596862256526947,
|
2095 |
+
"learning_rate": 9.902912621359223e-05,
|
2096 |
+
"loss": 0.454,
|
2097 |
+
"step": 296
|
2098 |
+
},
|
2099 |
+
{
|
2100 |
+
"epoch": 2.7264367816091957,
|
2101 |
+
"grad_norm": 0.391558974981308,
|
2102 |
+
"learning_rate": 9.83009708737864e-05,
|
2103 |
+
"loss": 0.3283,
|
2104 |
+
"step": 297
|
2105 |
+
},
|
2106 |
+
{
|
2107 |
+
"epoch": 2.735632183908046,
|
2108 |
+
"grad_norm": 0.4755273759365082,
|
2109 |
+
"learning_rate": 9.757281553398058e-05,
|
2110 |
+
"loss": 0.4141,
|
2111 |
+
"step": 298
|
2112 |
+
},
|
2113 |
+
{
|
2114 |
+
"epoch": 2.7448275862068967,
|
2115 |
+
"grad_norm": 0.37474825978279114,
|
2116 |
+
"learning_rate": 9.684466019417476e-05,
|
2117 |
+
"loss": 0.285,
|
2118 |
+
"step": 299
|
2119 |
+
},
|
2120 |
+
{
|
2121 |
+
"epoch": 2.754022988505747,
|
2122 |
+
"grad_norm": 0.47797009348869324,
|
2123 |
+
"learning_rate": 9.611650485436893e-05,
|
2124 |
+
"loss": 0.3485,
|
2125 |
+
"step": 300
|
2126 |
+
},
|
2127 |
+
{
|
2128 |
+
"epoch": 2.7632183908045977,
|
2129 |
+
"grad_norm": 0.4562835395336151,
|
2130 |
+
"learning_rate": 9.53883495145631e-05,
|
2131 |
+
"loss": 0.3423,
|
2132 |
+
"step": 301
|
2133 |
+
},
|
2134 |
+
{
|
2135 |
+
"epoch": 2.772413793103448,
|
2136 |
+
"grad_norm": 0.6650474667549133,
|
2137 |
+
"learning_rate": 9.466019417475728e-05,
|
2138 |
+
"loss": 0.4271,
|
2139 |
+
"step": 302
|
2140 |
+
},
|
2141 |
+
{
|
2142 |
+
"epoch": 2.781609195402299,
|
2143 |
+
"grad_norm": 0.4036124050617218,
|
2144 |
+
"learning_rate": 9.393203883495146e-05,
|
2145 |
+
"loss": 0.2785,
|
2146 |
+
"step": 303
|
2147 |
+
},
|
2148 |
+
{
|
2149 |
+
"epoch": 2.7908045977011495,
|
2150 |
+
"grad_norm": 0.6422847509384155,
|
2151 |
+
"learning_rate": 9.320388349514561e-05,
|
2152 |
+
"loss": 0.4546,
|
2153 |
+
"step": 304
|
2154 |
+
},
|
2155 |
+
{
|
2156 |
+
"epoch": 2.8,
|
2157 |
+
"grad_norm": 0.4403219521045685,
|
2158 |
+
"learning_rate": 9.247572815533979e-05,
|
2159 |
+
"loss": 0.2975,
|
2160 |
+
"step": 305
|
2161 |
+
},
|
2162 |
+
{
|
2163 |
+
"epoch": 2.8091954022988506,
|
2164 |
+
"grad_norm": 0.34099337458610535,
|
2165 |
+
"learning_rate": 9.174757281553397e-05,
|
2166 |
+
"loss": 0.2092,
|
2167 |
+
"step": 306
|
2168 |
+
},
|
2169 |
+
{
|
2170 |
+
"epoch": 2.8183908045977013,
|
2171 |
+
"grad_norm": 0.6565693020820618,
|
2172 |
+
"learning_rate": 9.101941747572814e-05,
|
2173 |
+
"loss": 0.589,
|
2174 |
+
"step": 307
|
2175 |
+
},
|
2176 |
+
{
|
2177 |
+
"epoch": 2.8275862068965516,
|
2178 |
+
"grad_norm": 0.29657208919525146,
|
2179 |
+
"learning_rate": 9.029126213592231e-05,
|
2180 |
+
"loss": 0.2206,
|
2181 |
+
"step": 308
|
2182 |
+
},
|
2183 |
+
{
|
2184 |
+
"epoch": 2.8367816091954023,
|
2185 |
+
"grad_norm": 0.35843998193740845,
|
2186 |
+
"learning_rate": 8.956310679611649e-05,
|
2187 |
+
"loss": 0.2576,
|
2188 |
+
"step": 309
|
2189 |
+
},
|
2190 |
+
{
|
2191 |
+
"epoch": 2.845977011494253,
|
2192 |
+
"grad_norm": 0.39961719512939453,
|
2193 |
+
"learning_rate": 8.883495145631067e-05,
|
2194 |
+
"loss": 0.2589,
|
2195 |
+
"step": 310
|
2196 |
+
},
|
2197 |
+
{
|
2198 |
+
"epoch": 2.8551724137931034,
|
2199 |
+
"grad_norm": 0.2650497257709503,
|
2200 |
+
"learning_rate": 8.810679611650485e-05,
|
2201 |
+
"loss": 0.1499,
|
2202 |
+
"step": 311
|
2203 |
+
},
|
2204 |
+
{
|
2205 |
+
"epoch": 2.864367816091954,
|
2206 |
+
"grad_norm": 0.6040882468223572,
|
2207 |
+
"learning_rate": 8.737864077669901e-05,
|
2208 |
+
"loss": 0.5003,
|
2209 |
+
"step": 312
|
2210 |
+
},
|
2211 |
+
{
|
2212 |
+
"epoch": 2.873563218390805,
|
2213 |
+
"grad_norm": 0.36157143115997314,
|
2214 |
+
"learning_rate": 8.665048543689319e-05,
|
2215 |
+
"loss": 0.3019,
|
2216 |
+
"step": 313
|
2217 |
+
},
|
2218 |
+
{
|
2219 |
+
"epoch": 2.882758620689655,
|
2220 |
+
"grad_norm": 0.34061622619628906,
|
2221 |
+
"learning_rate": 8.592233009708737e-05,
|
2222 |
+
"loss": 0.26,
|
2223 |
+
"step": 314
|
2224 |
+
},
|
2225 |
+
{
|
2226 |
+
"epoch": 2.891954022988506,
|
2227 |
+
"grad_norm": 0.6060124635696411,
|
2228 |
+
"learning_rate": 8.519417475728155e-05,
|
2229 |
+
"loss": 0.5343,
|
2230 |
+
"step": 315
|
2231 |
+
},
|
2232 |
+
{
|
2233 |
+
"epoch": 2.901149425287356,
|
2234 |
+
"grad_norm": 0.536323070526123,
|
2235 |
+
"learning_rate": 8.446601941747571e-05,
|
2236 |
+
"loss": 0.3762,
|
2237 |
+
"step": 316
|
2238 |
+
},
|
2239 |
+
{
|
2240 |
+
"epoch": 2.910344827586207,
|
2241 |
+
"grad_norm": 0.6887696981430054,
|
2242 |
+
"learning_rate": 8.373786407766989e-05,
|
2243 |
+
"loss": 0.613,
|
2244 |
+
"step": 317
|
2245 |
+
},
|
2246 |
+
{
|
2247 |
+
"epoch": 2.9195402298850572,
|
2248 |
+
"grad_norm": 0.3895469009876251,
|
2249 |
+
"learning_rate": 8.300970873786407e-05,
|
2250 |
+
"loss": 0.2919,
|
2251 |
+
"step": 318
|
2252 |
+
},
|
2253 |
+
{
|
2254 |
+
"epoch": 2.928735632183908,
|
2255 |
+
"grad_norm": 0.43969079852104187,
|
2256 |
+
"learning_rate": 8.228155339805825e-05,
|
2257 |
+
"loss": 0.2747,
|
2258 |
+
"step": 319
|
2259 |
+
},
|
2260 |
+
{
|
2261 |
+
"epoch": 2.9379310344827587,
|
2262 |
+
"grad_norm": 0.6681087017059326,
|
2263 |
+
"learning_rate": 8.155339805825241e-05,
|
2264 |
+
"loss": 0.5428,
|
2265 |
+
"step": 320
|
2266 |
+
},
|
2267 |
+
{
|
2268 |
+
"epoch": 2.947126436781609,
|
2269 |
+
"grad_norm": 0.5340582132339478,
|
2270 |
+
"learning_rate": 8.082524271844659e-05,
|
2271 |
+
"loss": 0.3636,
|
2272 |
+
"step": 321
|
2273 |
+
},
|
2274 |
+
{
|
2275 |
+
"epoch": 2.9563218390804598,
|
2276 |
+
"grad_norm": 0.4719969630241394,
|
2277 |
+
"learning_rate": 8.009708737864077e-05,
|
2278 |
+
"loss": 0.3629,
|
2279 |
+
"step": 322
|
2280 |
+
},
|
2281 |
+
{
|
2282 |
+
"epoch": 2.9655172413793105,
|
2283 |
+
"grad_norm": 0.4452765882015228,
|
2284 |
+
"learning_rate": 7.936893203883495e-05,
|
2285 |
+
"loss": 0.3002,
|
2286 |
+
"step": 323
|
2287 |
+
},
|
2288 |
+
{
|
2289 |
+
"epoch": 2.974712643678161,
|
2290 |
+
"grad_norm": 0.5446481704711914,
|
2291 |
+
"learning_rate": 7.864077669902911e-05,
|
2292 |
+
"loss": 0.426,
|
2293 |
+
"step": 324
|
2294 |
+
},
|
2295 |
+
{
|
2296 |
+
"epoch": 2.9839080459770115,
|
2297 |
+
"grad_norm": 0.6985622048377991,
|
2298 |
+
"learning_rate": 7.791262135922329e-05,
|
2299 |
+
"loss": 0.467,
|
2300 |
+
"step": 325
|
2301 |
+
},
|
2302 |
+
{
|
2303 |
+
"epoch": 2.9931034482758623,
|
2304 |
+
"grad_norm": 0.6391457915306091,
|
2305 |
+
"learning_rate": 7.718446601941747e-05,
|
2306 |
+
"loss": 0.428,
|
2307 |
+
"step": 326
|
2308 |
+
},
|
2309 |
+
{
|
2310 |
+
"epoch": 3.0,
|
2311 |
+
"grad_norm": 0.7811146378517151,
|
2312 |
+
"learning_rate": 7.645631067961165e-05,
|
2313 |
+
"loss": 0.5441,
|
2314 |
+
"step": 327
|
2315 |
+
},
|
2316 |
+
{
|
2317 |
+
"epoch": 3.0,
|
2318 |
+
"eval_loss": 1.4894534349441528,
|
2319 |
+
"eval_runtime": 94.563,
|
2320 |
+
"eval_samples_per_second": 3.511,
|
2321 |
+
"eval_steps_per_second": 1.755,
|
2322 |
+
"step": 327
|
2323 |
+
}
|
2324 |
+
],
|
2325 |
+
"logging_steps": 1,
|
2326 |
+
"max_steps": 432,
|
2327 |
+
"num_input_tokens_seen": 0,
|
2328 |
+
"num_train_epochs": 4,
|
2329 |
+
"save_steps": 500,
|
2330 |
+
"stateful_callbacks": {
|
2331 |
+
"TrainerControl": {
|
2332 |
+
"args": {
|
2333 |
+
"should_epoch_stop": false,
|
2334 |
+
"should_evaluate": false,
|
2335 |
+
"should_log": false,
|
2336 |
+
"should_save": true,
|
2337 |
+
"should_training_stop": false
|
2338 |
+
},
|
2339 |
+
"attributes": {}
|
2340 |
+
}
|
2341 |
+
},
|
2342 |
+
"total_flos": 2.99509837713236e+17,
|
2343 |
+
"train_batch_size": 4,
|
2344 |
+
"trial_name": null,
|
2345 |
+
"trial_params": null
|
2346 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6e4fdbc1fe4d34be8d72e405631f421e51847135da84149b8f547047c8317de0
|
3 |
+
size 5816
|