Upload 12 files
Browse files- README.md +204 -0
- adapter_config.json +27 -0
- adapter_model.safetensors +3 -0
- optimizer.pt +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +107 -0
- spiece.model +3 -0
- tokenizer.json +0 -0
- tokenizer_config.json +937 -0
- trainer_state.json +1611 -0
- training_args.bin +3 -0
README.md
ADDED
|
@@ -0,0 +1,204 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: peft
|
| 3 |
+
base_model: VietAI/vit5-large
|
| 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 |
+
|
| 201 |
+
|
| 202 |
+
### Framework versions
|
| 203 |
+
|
| 204 |
+
- PEFT 0.8.2
|
adapter_config.json
ADDED
|
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "VietAI/vit5-large",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"fan_in_fan_out": false,
|
| 7 |
+
"inference_mode": true,
|
| 8 |
+
"init_lora_weights": true,
|
| 9 |
+
"layers_pattern": null,
|
| 10 |
+
"layers_to_transform": null,
|
| 11 |
+
"loftq_config": {},
|
| 12 |
+
"lora_alpha": 32,
|
| 13 |
+
"lora_dropout": 0.05,
|
| 14 |
+
"megatron_config": null,
|
| 15 |
+
"megatron_core": "megatron.core",
|
| 16 |
+
"modules_to_save": null,
|
| 17 |
+
"peft_type": "LORA",
|
| 18 |
+
"r": 16,
|
| 19 |
+
"rank_pattern": {},
|
| 20 |
+
"revision": null,
|
| 21 |
+
"target_modules": [
|
| 22 |
+
"v",
|
| 23 |
+
"q"
|
| 24 |
+
],
|
| 25 |
+
"task_type": "SEQ_2_SEQ_LM",
|
| 26 |
+
"use_rslora": false
|
| 27 |
+
}
|
adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bf34ebc4b5e1ad38ec182f721b7ea8f136f09352bd524a25a34c44d877472401
|
| 3 |
+
size 18915328
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dad5f6c600ed4a67b7f383fb39584adc1245f64117ba9d644705672a7d9c605e
|
| 3 |
+
size 37990330
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:eace9b64a8a39e0ab06b10819891e4bdfc19b8568fc30c9791778773e7d09844
|
| 3 |
+
size 14244
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8c6c99a2eab71d483f3fa9abae4874e9a73dfb7358f5c4358ca7118e2bc66302
|
| 3 |
+
size 1064
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,107 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<extra_id_0>",
|
| 4 |
+
"<extra_id_1>",
|
| 5 |
+
"<extra_id_2>",
|
| 6 |
+
"<extra_id_3>",
|
| 7 |
+
"<extra_id_4>",
|
| 8 |
+
"<extra_id_5>",
|
| 9 |
+
"<extra_id_6>",
|
| 10 |
+
"<extra_id_7>",
|
| 11 |
+
"<extra_id_8>",
|
| 12 |
+
"<extra_id_9>",
|
| 13 |
+
"<extra_id_10>",
|
| 14 |
+
"<extra_id_11>",
|
| 15 |
+
"<extra_id_12>",
|
| 16 |
+
"<extra_id_13>",
|
| 17 |
+
"<extra_id_14>",
|
| 18 |
+
"<extra_id_15>",
|
| 19 |
+
"<extra_id_16>",
|
| 20 |
+
"<extra_id_17>",
|
| 21 |
+
"<extra_id_18>",
|
| 22 |
+
"<extra_id_19>",
|
| 23 |
+
"<extra_id_20>",
|
| 24 |
+
"<extra_id_21>",
|
| 25 |
+
"<extra_id_22>",
|
| 26 |
+
"<extra_id_23>",
|
| 27 |
+
"<extra_id_24>",
|
| 28 |
+
"<extra_id_25>",
|
| 29 |
+
"<extra_id_26>",
|
| 30 |
+
"<extra_id_27>",
|
| 31 |
+
"<extra_id_28>",
|
| 32 |
+
"<extra_id_29>",
|
| 33 |
+
"<extra_id_30>",
|
| 34 |
+
"<extra_id_31>",
|
| 35 |
+
"<extra_id_32>",
|
| 36 |
+
"<extra_id_33>",
|
| 37 |
+
"<extra_id_34>",
|
| 38 |
+
"<extra_id_35>",
|
| 39 |
+
"<extra_id_36>",
|
| 40 |
+
"<extra_id_37>",
|
| 41 |
+
"<extra_id_38>",
|
| 42 |
+
"<extra_id_39>",
|
| 43 |
+
"<extra_id_40>",
|
| 44 |
+
"<extra_id_41>",
|
| 45 |
+
"<extra_id_42>",
|
| 46 |
+
"<extra_id_43>",
|
| 47 |
+
"<extra_id_44>",
|
| 48 |
+
"<extra_id_45>",
|
| 49 |
+
"<extra_id_46>",
|
| 50 |
+
"<extra_id_47>",
|
| 51 |
+
"<extra_id_48>",
|
| 52 |
+
"<extra_id_49>",
|
| 53 |
+
"<extra_id_50>",
|
| 54 |
+
"<extra_id_51>",
|
| 55 |
+
"<extra_id_52>",
|
| 56 |
+
"<extra_id_53>",
|
| 57 |
+
"<extra_id_54>",
|
| 58 |
+
"<extra_id_55>",
|
| 59 |
+
"<extra_id_56>",
|
| 60 |
+
"<extra_id_57>",
|
| 61 |
+
"<extra_id_58>",
|
| 62 |
+
"<extra_id_59>",
|
| 63 |
+
"<extra_id_60>",
|
| 64 |
+
"<extra_id_61>",
|
| 65 |
+
"<extra_id_62>",
|
| 66 |
+
"<extra_id_63>",
|
| 67 |
+
"<extra_id_64>",
|
| 68 |
+
"<extra_id_65>",
|
| 69 |
+
"<extra_id_66>",
|
| 70 |
+
"<extra_id_67>",
|
| 71 |
+
"<extra_id_68>",
|
| 72 |
+
"<extra_id_69>",
|
| 73 |
+
"<extra_id_70>",
|
| 74 |
+
"<extra_id_71>",
|
| 75 |
+
"<extra_id_72>",
|
| 76 |
+
"<extra_id_73>",
|
| 77 |
+
"<extra_id_74>",
|
| 78 |
+
"<extra_id_75>",
|
| 79 |
+
"<extra_id_76>",
|
| 80 |
+
"<extra_id_77>",
|
| 81 |
+
"<extra_id_78>",
|
| 82 |
+
"<extra_id_79>",
|
| 83 |
+
"<extra_id_80>",
|
| 84 |
+
"<extra_id_81>",
|
| 85 |
+
"<extra_id_82>",
|
| 86 |
+
"<extra_id_83>",
|
| 87 |
+
"<extra_id_84>",
|
| 88 |
+
"<extra_id_85>",
|
| 89 |
+
"<extra_id_86>",
|
| 90 |
+
"<extra_id_87>",
|
| 91 |
+
"<extra_id_88>",
|
| 92 |
+
"<extra_id_89>",
|
| 93 |
+
"<extra_id_90>",
|
| 94 |
+
"<extra_id_91>",
|
| 95 |
+
"<extra_id_92>",
|
| 96 |
+
"<extra_id_93>",
|
| 97 |
+
"<extra_id_94>",
|
| 98 |
+
"<extra_id_95>",
|
| 99 |
+
"<extra_id_96>",
|
| 100 |
+
"<extra_id_97>",
|
| 101 |
+
"<extra_id_98>",
|
| 102 |
+
"<extra_id_99>"
|
| 103 |
+
],
|
| 104 |
+
"eos_token": "</s>",
|
| 105 |
+
"pad_token": "<pad>",
|
| 106 |
+
"unk_token": "<unk>"
|
| 107 |
+
}
|
spiece.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:59986b62f9f0b90edafb9b073ea7b93d21114a5841219a1ea2399ade73f729c6
|
| 3 |
+
size 820370
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,937 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "<pad>",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"1": {
|
| 12 |
+
"content": "</s>",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"2": {
|
| 20 |
+
"content": "<unk>",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"36000": {
|
| 28 |
+
"content": "<extra_id_99>",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"36001": {
|
| 36 |
+
"content": "<extra_id_98>",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
},
|
| 43 |
+
"36002": {
|
| 44 |
+
"content": "<extra_id_97>",
|
| 45 |
+
"lstrip": false,
|
| 46 |
+
"normalized": false,
|
| 47 |
+
"rstrip": false,
|
| 48 |
+
"single_word": false,
|
| 49 |
+
"special": true
|
| 50 |
+
},
|
| 51 |
+
"36003": {
|
| 52 |
+
"content": "<extra_id_96>",
|
| 53 |
+
"lstrip": false,
|
| 54 |
+
"normalized": false,
|
| 55 |
+
"rstrip": false,
|
| 56 |
+
"single_word": false,
|
| 57 |
+
"special": true
|
| 58 |
+
},
|
| 59 |
+
"36004": {
|
| 60 |
+
"content": "<extra_id_95>",
|
| 61 |
+
"lstrip": false,
|
| 62 |
+
"normalized": false,
|
| 63 |
+
"rstrip": false,
|
| 64 |
+
"single_word": false,
|
| 65 |
+
"special": true
|
| 66 |
+
},
|
| 67 |
+
"36005": {
|
| 68 |
+
"content": "<extra_id_94>",
|
| 69 |
+
"lstrip": false,
|
| 70 |
+
"normalized": false,
|
| 71 |
+
"rstrip": false,
|
| 72 |
+
"single_word": false,
|
| 73 |
+
"special": true
|
| 74 |
+
},
|
| 75 |
+
"36006": {
|
| 76 |
+
"content": "<extra_id_93>",
|
| 77 |
+
"lstrip": false,
|
| 78 |
+
"normalized": false,
|
| 79 |
+
"rstrip": false,
|
| 80 |
+
"single_word": false,
|
| 81 |
+
"special": true
|
| 82 |
+
},
|
| 83 |
+
"36007": {
|
| 84 |
+
"content": "<extra_id_92>",
|
| 85 |
+
"lstrip": false,
|
| 86 |
+
"normalized": false,
|
| 87 |
+
"rstrip": false,
|
| 88 |
+
"single_word": false,
|
| 89 |
+
"special": true
|
| 90 |
+
},
|
| 91 |
+
"36008": {
|
| 92 |
+
"content": "<extra_id_91>",
|
| 93 |
+
"lstrip": false,
|
| 94 |
+
"normalized": false,
|
| 95 |
+
"rstrip": false,
|
| 96 |
+
"single_word": false,
|
| 97 |
+
"special": true
|
| 98 |
+
},
|
| 99 |
+
"36009": {
|
| 100 |
+
"content": "<extra_id_90>",
|
| 101 |
+
"lstrip": false,
|
| 102 |
+
"normalized": false,
|
| 103 |
+
"rstrip": false,
|
| 104 |
+
"single_word": false,
|
| 105 |
+
"special": true
|
| 106 |
+
},
|
| 107 |
+
"36010": {
|
| 108 |
+
"content": "<extra_id_89>",
|
| 109 |
+
"lstrip": false,
|
| 110 |
+
"normalized": false,
|
| 111 |
+
"rstrip": false,
|
| 112 |
+
"single_word": false,
|
| 113 |
+
"special": true
|
| 114 |
+
},
|
| 115 |
+
"36011": {
|
| 116 |
+
"content": "<extra_id_88>",
|
| 117 |
+
"lstrip": false,
|
| 118 |
+
"normalized": false,
|
| 119 |
+
"rstrip": false,
|
| 120 |
+
"single_word": false,
|
| 121 |
+
"special": true
|
| 122 |
+
},
|
| 123 |
+
"36012": {
|
| 124 |
+
"content": "<extra_id_87>",
|
| 125 |
+
"lstrip": false,
|
| 126 |
+
"normalized": false,
|
| 127 |
+
"rstrip": false,
|
| 128 |
+
"single_word": false,
|
| 129 |
+
"special": true
|
| 130 |
+
},
|
| 131 |
+
"36013": {
|
| 132 |
+
"content": "<extra_id_86>",
|
| 133 |
+
"lstrip": false,
|
| 134 |
+
"normalized": false,
|
| 135 |
+
"rstrip": false,
|
| 136 |
+
"single_word": false,
|
| 137 |
+
"special": true
|
| 138 |
+
},
|
| 139 |
+
"36014": {
|
| 140 |
+
"content": "<extra_id_85>",
|
| 141 |
+
"lstrip": false,
|
| 142 |
+
"normalized": false,
|
| 143 |
+
"rstrip": false,
|
| 144 |
+
"single_word": false,
|
| 145 |
+
"special": true
|
| 146 |
+
},
|
| 147 |
+
"36015": {
|
| 148 |
+
"content": "<extra_id_84>",
|
| 149 |
+
"lstrip": false,
|
| 150 |
+
"normalized": false,
|
| 151 |
+
"rstrip": false,
|
| 152 |
+
"single_word": false,
|
| 153 |
+
"special": true
|
| 154 |
+
},
|
| 155 |
+
"36016": {
|
| 156 |
+
"content": "<extra_id_83>",
|
| 157 |
+
"lstrip": false,
|
| 158 |
+
"normalized": false,
|
| 159 |
+
"rstrip": false,
|
| 160 |
+
"single_word": false,
|
| 161 |
+
"special": true
|
| 162 |
+
},
|
| 163 |
+
"36017": {
|
| 164 |
+
"content": "<extra_id_82>",
|
| 165 |
+
"lstrip": false,
|
| 166 |
+
"normalized": false,
|
| 167 |
+
"rstrip": false,
|
| 168 |
+
"single_word": false,
|
| 169 |
+
"special": true
|
| 170 |
+
},
|
| 171 |
+
"36018": {
|
| 172 |
+
"content": "<extra_id_81>",
|
| 173 |
+
"lstrip": false,
|
| 174 |
+
"normalized": false,
|
| 175 |
+
"rstrip": false,
|
| 176 |
+
"single_word": false,
|
| 177 |
+
"special": true
|
| 178 |
+
},
|
| 179 |
+
"36019": {
|
| 180 |
+
"content": "<extra_id_80>",
|
| 181 |
+
"lstrip": false,
|
| 182 |
+
"normalized": false,
|
| 183 |
+
"rstrip": false,
|
| 184 |
+
"single_word": false,
|
| 185 |
+
"special": true
|
| 186 |
+
},
|
| 187 |
+
"36020": {
|
| 188 |
+
"content": "<extra_id_79>",
|
| 189 |
+
"lstrip": false,
|
| 190 |
+
"normalized": false,
|
| 191 |
+
"rstrip": false,
|
| 192 |
+
"single_word": false,
|
| 193 |
+
"special": true
|
| 194 |
+
},
|
| 195 |
+
"36021": {
|
| 196 |
+
"content": "<extra_id_78>",
|
| 197 |
+
"lstrip": false,
|
| 198 |
+
"normalized": false,
|
| 199 |
+
"rstrip": false,
|
| 200 |
+
"single_word": false,
|
| 201 |
+
"special": true
|
| 202 |
+
},
|
| 203 |
+
"36022": {
|
| 204 |
+
"content": "<extra_id_77>",
|
| 205 |
+
"lstrip": false,
|
| 206 |
+
"normalized": false,
|
| 207 |
+
"rstrip": false,
|
| 208 |
+
"single_word": false,
|
| 209 |
+
"special": true
|
| 210 |
+
},
|
| 211 |
+
"36023": {
|
| 212 |
+
"content": "<extra_id_76>",
|
| 213 |
+
"lstrip": false,
|
| 214 |
+
"normalized": false,
|
| 215 |
+
"rstrip": false,
|
| 216 |
+
"single_word": false,
|
| 217 |
+
"special": true
|
| 218 |
+
},
|
| 219 |
+
"36024": {
|
| 220 |
+
"content": "<extra_id_75>",
|
| 221 |
+
"lstrip": false,
|
| 222 |
+
"normalized": false,
|
| 223 |
+
"rstrip": false,
|
| 224 |
+
"single_word": false,
|
| 225 |
+
"special": true
|
| 226 |
+
},
|
| 227 |
+
"36025": {
|
| 228 |
+
"content": "<extra_id_74>",
|
| 229 |
+
"lstrip": false,
|
| 230 |
+
"normalized": false,
|
| 231 |
+
"rstrip": false,
|
| 232 |
+
"single_word": false,
|
| 233 |
+
"special": true
|
| 234 |
+
},
|
| 235 |
+
"36026": {
|
| 236 |
+
"content": "<extra_id_73>",
|
| 237 |
+
"lstrip": false,
|
| 238 |
+
"normalized": false,
|
| 239 |
+
"rstrip": false,
|
| 240 |
+
"single_word": false,
|
| 241 |
+
"special": true
|
| 242 |
+
},
|
| 243 |
+
"36027": {
|
| 244 |
+
"content": "<extra_id_72>",
|
| 245 |
+
"lstrip": false,
|
| 246 |
+
"normalized": false,
|
| 247 |
+
"rstrip": false,
|
| 248 |
+
"single_word": false,
|
| 249 |
+
"special": true
|
| 250 |
+
},
|
| 251 |
+
"36028": {
|
| 252 |
+
"content": "<extra_id_71>",
|
| 253 |
+
"lstrip": false,
|
| 254 |
+
"normalized": false,
|
| 255 |
+
"rstrip": false,
|
| 256 |
+
"single_word": false,
|
| 257 |
+
"special": true
|
| 258 |
+
},
|
| 259 |
+
"36029": {
|
| 260 |
+
"content": "<extra_id_70>",
|
| 261 |
+
"lstrip": false,
|
| 262 |
+
"normalized": false,
|
| 263 |
+
"rstrip": false,
|
| 264 |
+
"single_word": false,
|
| 265 |
+
"special": true
|
| 266 |
+
},
|
| 267 |
+
"36030": {
|
| 268 |
+
"content": "<extra_id_69>",
|
| 269 |
+
"lstrip": false,
|
| 270 |
+
"normalized": false,
|
| 271 |
+
"rstrip": false,
|
| 272 |
+
"single_word": false,
|
| 273 |
+
"special": true
|
| 274 |
+
},
|
| 275 |
+
"36031": {
|
| 276 |
+
"content": "<extra_id_68>",
|
| 277 |
+
"lstrip": false,
|
| 278 |
+
"normalized": false,
|
| 279 |
+
"rstrip": false,
|
| 280 |
+
"single_word": false,
|
| 281 |
+
"special": true
|
| 282 |
+
},
|
| 283 |
+
"36032": {
|
| 284 |
+
"content": "<extra_id_67>",
|
| 285 |
+
"lstrip": false,
|
| 286 |
+
"normalized": false,
|
| 287 |
+
"rstrip": false,
|
| 288 |
+
"single_word": false,
|
| 289 |
+
"special": true
|
| 290 |
+
},
|
| 291 |
+
"36033": {
|
| 292 |
+
"content": "<extra_id_66>",
|
| 293 |
+
"lstrip": false,
|
| 294 |
+
"normalized": false,
|
| 295 |
+
"rstrip": false,
|
| 296 |
+
"single_word": false,
|
| 297 |
+
"special": true
|
| 298 |
+
},
|
| 299 |
+
"36034": {
|
| 300 |
+
"content": "<extra_id_65>",
|
| 301 |
+
"lstrip": false,
|
| 302 |
+
"normalized": false,
|
| 303 |
+
"rstrip": false,
|
| 304 |
+
"single_word": false,
|
| 305 |
+
"special": true
|
| 306 |
+
},
|
| 307 |
+
"36035": {
|
| 308 |
+
"content": "<extra_id_64>",
|
| 309 |
+
"lstrip": false,
|
| 310 |
+
"normalized": false,
|
| 311 |
+
"rstrip": false,
|
| 312 |
+
"single_word": false,
|
| 313 |
+
"special": true
|
| 314 |
+
},
|
| 315 |
+
"36036": {
|
| 316 |
+
"content": "<extra_id_63>",
|
| 317 |
+
"lstrip": false,
|
| 318 |
+
"normalized": false,
|
| 319 |
+
"rstrip": false,
|
| 320 |
+
"single_word": false,
|
| 321 |
+
"special": true
|
| 322 |
+
},
|
| 323 |
+
"36037": {
|
| 324 |
+
"content": "<extra_id_62>",
|
| 325 |
+
"lstrip": false,
|
| 326 |
+
"normalized": false,
|
| 327 |
+
"rstrip": false,
|
| 328 |
+
"single_word": false,
|
| 329 |
+
"special": true
|
| 330 |
+
},
|
| 331 |
+
"36038": {
|
| 332 |
+
"content": "<extra_id_61>",
|
| 333 |
+
"lstrip": false,
|
| 334 |
+
"normalized": false,
|
| 335 |
+
"rstrip": false,
|
| 336 |
+
"single_word": false,
|
| 337 |
+
"special": true
|
| 338 |
+
},
|
| 339 |
+
"36039": {
|
| 340 |
+
"content": "<extra_id_60>",
|
| 341 |
+
"lstrip": false,
|
| 342 |
+
"normalized": false,
|
| 343 |
+
"rstrip": false,
|
| 344 |
+
"single_word": false,
|
| 345 |
+
"special": true
|
| 346 |
+
},
|
| 347 |
+
"36040": {
|
| 348 |
+
"content": "<extra_id_59>",
|
| 349 |
+
"lstrip": false,
|
| 350 |
+
"normalized": false,
|
| 351 |
+
"rstrip": false,
|
| 352 |
+
"single_word": false,
|
| 353 |
+
"special": true
|
| 354 |
+
},
|
| 355 |
+
"36041": {
|
| 356 |
+
"content": "<extra_id_58>",
|
| 357 |
+
"lstrip": false,
|
| 358 |
+
"normalized": false,
|
| 359 |
+
"rstrip": false,
|
| 360 |
+
"single_word": false,
|
| 361 |
+
"special": true
|
| 362 |
+
},
|
| 363 |
+
"36042": {
|
| 364 |
+
"content": "<extra_id_57>",
|
| 365 |
+
"lstrip": false,
|
| 366 |
+
"normalized": false,
|
| 367 |
+
"rstrip": false,
|
| 368 |
+
"single_word": false,
|
| 369 |
+
"special": true
|
| 370 |
+
},
|
| 371 |
+
"36043": {
|
| 372 |
+
"content": "<extra_id_56>",
|
| 373 |
+
"lstrip": false,
|
| 374 |
+
"normalized": false,
|
| 375 |
+
"rstrip": false,
|
| 376 |
+
"single_word": false,
|
| 377 |
+
"special": true
|
| 378 |
+
},
|
| 379 |
+
"36044": {
|
| 380 |
+
"content": "<extra_id_55>",
|
| 381 |
+
"lstrip": false,
|
| 382 |
+
"normalized": false,
|
| 383 |
+
"rstrip": false,
|
| 384 |
+
"single_word": false,
|
| 385 |
+
"special": true
|
| 386 |
+
},
|
| 387 |
+
"36045": {
|
| 388 |
+
"content": "<extra_id_54>",
|
| 389 |
+
"lstrip": false,
|
| 390 |
+
"normalized": false,
|
| 391 |
+
"rstrip": false,
|
| 392 |
+
"single_word": false,
|
| 393 |
+
"special": true
|
| 394 |
+
},
|
| 395 |
+
"36046": {
|
| 396 |
+
"content": "<extra_id_53>",
|
| 397 |
+
"lstrip": false,
|
| 398 |
+
"normalized": false,
|
| 399 |
+
"rstrip": false,
|
| 400 |
+
"single_word": false,
|
| 401 |
+
"special": true
|
| 402 |
+
},
|
| 403 |
+
"36047": {
|
| 404 |
+
"content": "<extra_id_52>",
|
| 405 |
+
"lstrip": false,
|
| 406 |
+
"normalized": false,
|
| 407 |
+
"rstrip": false,
|
| 408 |
+
"single_word": false,
|
| 409 |
+
"special": true
|
| 410 |
+
},
|
| 411 |
+
"36048": {
|
| 412 |
+
"content": "<extra_id_51>",
|
| 413 |
+
"lstrip": false,
|
| 414 |
+
"normalized": false,
|
| 415 |
+
"rstrip": false,
|
| 416 |
+
"single_word": false,
|
| 417 |
+
"special": true
|
| 418 |
+
},
|
| 419 |
+
"36049": {
|
| 420 |
+
"content": "<extra_id_50>",
|
| 421 |
+
"lstrip": false,
|
| 422 |
+
"normalized": false,
|
| 423 |
+
"rstrip": false,
|
| 424 |
+
"single_word": false,
|
| 425 |
+
"special": true
|
| 426 |
+
},
|
| 427 |
+
"36050": {
|
| 428 |
+
"content": "<extra_id_49>",
|
| 429 |
+
"lstrip": false,
|
| 430 |
+
"normalized": false,
|
| 431 |
+
"rstrip": false,
|
| 432 |
+
"single_word": false,
|
| 433 |
+
"special": true
|
| 434 |
+
},
|
| 435 |
+
"36051": {
|
| 436 |
+
"content": "<extra_id_48>",
|
| 437 |
+
"lstrip": false,
|
| 438 |
+
"normalized": false,
|
| 439 |
+
"rstrip": false,
|
| 440 |
+
"single_word": false,
|
| 441 |
+
"special": true
|
| 442 |
+
},
|
| 443 |
+
"36052": {
|
| 444 |
+
"content": "<extra_id_47>",
|
| 445 |
+
"lstrip": false,
|
| 446 |
+
"normalized": false,
|
| 447 |
+
"rstrip": false,
|
| 448 |
+
"single_word": false,
|
| 449 |
+
"special": true
|
| 450 |
+
},
|
| 451 |
+
"36053": {
|
| 452 |
+
"content": "<extra_id_46>",
|
| 453 |
+
"lstrip": false,
|
| 454 |
+
"normalized": false,
|
| 455 |
+
"rstrip": false,
|
| 456 |
+
"single_word": false,
|
| 457 |
+
"special": true
|
| 458 |
+
},
|
| 459 |
+
"36054": {
|
| 460 |
+
"content": "<extra_id_45>",
|
| 461 |
+
"lstrip": false,
|
| 462 |
+
"normalized": false,
|
| 463 |
+
"rstrip": false,
|
| 464 |
+
"single_word": false,
|
| 465 |
+
"special": true
|
| 466 |
+
},
|
| 467 |
+
"36055": {
|
| 468 |
+
"content": "<extra_id_44>",
|
| 469 |
+
"lstrip": false,
|
| 470 |
+
"normalized": false,
|
| 471 |
+
"rstrip": false,
|
| 472 |
+
"single_word": false,
|
| 473 |
+
"special": true
|
| 474 |
+
},
|
| 475 |
+
"36056": {
|
| 476 |
+
"content": "<extra_id_43>",
|
| 477 |
+
"lstrip": false,
|
| 478 |
+
"normalized": false,
|
| 479 |
+
"rstrip": false,
|
| 480 |
+
"single_word": false,
|
| 481 |
+
"special": true
|
| 482 |
+
},
|
| 483 |
+
"36057": {
|
| 484 |
+
"content": "<extra_id_42>",
|
| 485 |
+
"lstrip": false,
|
| 486 |
+
"normalized": false,
|
| 487 |
+
"rstrip": false,
|
| 488 |
+
"single_word": false,
|
| 489 |
+
"special": true
|
| 490 |
+
},
|
| 491 |
+
"36058": {
|
| 492 |
+
"content": "<extra_id_41>",
|
| 493 |
+
"lstrip": false,
|
| 494 |
+
"normalized": false,
|
| 495 |
+
"rstrip": false,
|
| 496 |
+
"single_word": false,
|
| 497 |
+
"special": true
|
| 498 |
+
},
|
| 499 |
+
"36059": {
|
| 500 |
+
"content": "<extra_id_40>",
|
| 501 |
+
"lstrip": false,
|
| 502 |
+
"normalized": false,
|
| 503 |
+
"rstrip": false,
|
| 504 |
+
"single_word": false,
|
| 505 |
+
"special": true
|
| 506 |
+
},
|
| 507 |
+
"36060": {
|
| 508 |
+
"content": "<extra_id_39>",
|
| 509 |
+
"lstrip": false,
|
| 510 |
+
"normalized": false,
|
| 511 |
+
"rstrip": false,
|
| 512 |
+
"single_word": false,
|
| 513 |
+
"special": true
|
| 514 |
+
},
|
| 515 |
+
"36061": {
|
| 516 |
+
"content": "<extra_id_38>",
|
| 517 |
+
"lstrip": false,
|
| 518 |
+
"normalized": false,
|
| 519 |
+
"rstrip": false,
|
| 520 |
+
"single_word": false,
|
| 521 |
+
"special": true
|
| 522 |
+
},
|
| 523 |
+
"36062": {
|
| 524 |
+
"content": "<extra_id_37>",
|
| 525 |
+
"lstrip": false,
|
| 526 |
+
"normalized": false,
|
| 527 |
+
"rstrip": false,
|
| 528 |
+
"single_word": false,
|
| 529 |
+
"special": true
|
| 530 |
+
},
|
| 531 |
+
"36063": {
|
| 532 |
+
"content": "<extra_id_36>",
|
| 533 |
+
"lstrip": false,
|
| 534 |
+
"normalized": false,
|
| 535 |
+
"rstrip": false,
|
| 536 |
+
"single_word": false,
|
| 537 |
+
"special": true
|
| 538 |
+
},
|
| 539 |
+
"36064": {
|
| 540 |
+
"content": "<extra_id_35>",
|
| 541 |
+
"lstrip": false,
|
| 542 |
+
"normalized": false,
|
| 543 |
+
"rstrip": false,
|
| 544 |
+
"single_word": false,
|
| 545 |
+
"special": true
|
| 546 |
+
},
|
| 547 |
+
"36065": {
|
| 548 |
+
"content": "<extra_id_34>",
|
| 549 |
+
"lstrip": false,
|
| 550 |
+
"normalized": false,
|
| 551 |
+
"rstrip": false,
|
| 552 |
+
"single_word": false,
|
| 553 |
+
"special": true
|
| 554 |
+
},
|
| 555 |
+
"36066": {
|
| 556 |
+
"content": "<extra_id_33>",
|
| 557 |
+
"lstrip": false,
|
| 558 |
+
"normalized": false,
|
| 559 |
+
"rstrip": false,
|
| 560 |
+
"single_word": false,
|
| 561 |
+
"special": true
|
| 562 |
+
},
|
| 563 |
+
"36067": {
|
| 564 |
+
"content": "<extra_id_32>",
|
| 565 |
+
"lstrip": false,
|
| 566 |
+
"normalized": false,
|
| 567 |
+
"rstrip": false,
|
| 568 |
+
"single_word": false,
|
| 569 |
+
"special": true
|
| 570 |
+
},
|
| 571 |
+
"36068": {
|
| 572 |
+
"content": "<extra_id_31>",
|
| 573 |
+
"lstrip": false,
|
| 574 |
+
"normalized": false,
|
| 575 |
+
"rstrip": false,
|
| 576 |
+
"single_word": false,
|
| 577 |
+
"special": true
|
| 578 |
+
},
|
| 579 |
+
"36069": {
|
| 580 |
+
"content": "<extra_id_30>",
|
| 581 |
+
"lstrip": false,
|
| 582 |
+
"normalized": false,
|
| 583 |
+
"rstrip": false,
|
| 584 |
+
"single_word": false,
|
| 585 |
+
"special": true
|
| 586 |
+
},
|
| 587 |
+
"36070": {
|
| 588 |
+
"content": "<extra_id_29>",
|
| 589 |
+
"lstrip": false,
|
| 590 |
+
"normalized": false,
|
| 591 |
+
"rstrip": false,
|
| 592 |
+
"single_word": false,
|
| 593 |
+
"special": true
|
| 594 |
+
},
|
| 595 |
+
"36071": {
|
| 596 |
+
"content": "<extra_id_28>",
|
| 597 |
+
"lstrip": false,
|
| 598 |
+
"normalized": false,
|
| 599 |
+
"rstrip": false,
|
| 600 |
+
"single_word": false,
|
| 601 |
+
"special": true
|
| 602 |
+
},
|
| 603 |
+
"36072": {
|
| 604 |
+
"content": "<extra_id_27>",
|
| 605 |
+
"lstrip": false,
|
| 606 |
+
"normalized": false,
|
| 607 |
+
"rstrip": false,
|
| 608 |
+
"single_word": false,
|
| 609 |
+
"special": true
|
| 610 |
+
},
|
| 611 |
+
"36073": {
|
| 612 |
+
"content": "<extra_id_26>",
|
| 613 |
+
"lstrip": false,
|
| 614 |
+
"normalized": false,
|
| 615 |
+
"rstrip": false,
|
| 616 |
+
"single_word": false,
|
| 617 |
+
"special": true
|
| 618 |
+
},
|
| 619 |
+
"36074": {
|
| 620 |
+
"content": "<extra_id_25>",
|
| 621 |
+
"lstrip": false,
|
| 622 |
+
"normalized": false,
|
| 623 |
+
"rstrip": false,
|
| 624 |
+
"single_word": false,
|
| 625 |
+
"special": true
|
| 626 |
+
},
|
| 627 |
+
"36075": {
|
| 628 |
+
"content": "<extra_id_24>",
|
| 629 |
+
"lstrip": false,
|
| 630 |
+
"normalized": false,
|
| 631 |
+
"rstrip": false,
|
| 632 |
+
"single_word": false,
|
| 633 |
+
"special": true
|
| 634 |
+
},
|
| 635 |
+
"36076": {
|
| 636 |
+
"content": "<extra_id_23>",
|
| 637 |
+
"lstrip": false,
|
| 638 |
+
"normalized": false,
|
| 639 |
+
"rstrip": false,
|
| 640 |
+
"single_word": false,
|
| 641 |
+
"special": true
|
| 642 |
+
},
|
| 643 |
+
"36077": {
|
| 644 |
+
"content": "<extra_id_22>",
|
| 645 |
+
"lstrip": false,
|
| 646 |
+
"normalized": false,
|
| 647 |
+
"rstrip": false,
|
| 648 |
+
"single_word": false,
|
| 649 |
+
"special": true
|
| 650 |
+
},
|
| 651 |
+
"36078": {
|
| 652 |
+
"content": "<extra_id_21>",
|
| 653 |
+
"lstrip": false,
|
| 654 |
+
"normalized": false,
|
| 655 |
+
"rstrip": false,
|
| 656 |
+
"single_word": false,
|
| 657 |
+
"special": true
|
| 658 |
+
},
|
| 659 |
+
"36079": {
|
| 660 |
+
"content": "<extra_id_20>",
|
| 661 |
+
"lstrip": false,
|
| 662 |
+
"normalized": false,
|
| 663 |
+
"rstrip": false,
|
| 664 |
+
"single_word": false,
|
| 665 |
+
"special": true
|
| 666 |
+
},
|
| 667 |
+
"36080": {
|
| 668 |
+
"content": "<extra_id_19>",
|
| 669 |
+
"lstrip": false,
|
| 670 |
+
"normalized": false,
|
| 671 |
+
"rstrip": false,
|
| 672 |
+
"single_word": false,
|
| 673 |
+
"special": true
|
| 674 |
+
},
|
| 675 |
+
"36081": {
|
| 676 |
+
"content": "<extra_id_18>",
|
| 677 |
+
"lstrip": false,
|
| 678 |
+
"normalized": false,
|
| 679 |
+
"rstrip": false,
|
| 680 |
+
"single_word": false,
|
| 681 |
+
"special": true
|
| 682 |
+
},
|
| 683 |
+
"36082": {
|
| 684 |
+
"content": "<extra_id_17>",
|
| 685 |
+
"lstrip": false,
|
| 686 |
+
"normalized": false,
|
| 687 |
+
"rstrip": false,
|
| 688 |
+
"single_word": false,
|
| 689 |
+
"special": true
|
| 690 |
+
},
|
| 691 |
+
"36083": {
|
| 692 |
+
"content": "<extra_id_16>",
|
| 693 |
+
"lstrip": false,
|
| 694 |
+
"normalized": false,
|
| 695 |
+
"rstrip": false,
|
| 696 |
+
"single_word": false,
|
| 697 |
+
"special": true
|
| 698 |
+
},
|
| 699 |
+
"36084": {
|
| 700 |
+
"content": "<extra_id_15>",
|
| 701 |
+
"lstrip": false,
|
| 702 |
+
"normalized": false,
|
| 703 |
+
"rstrip": false,
|
| 704 |
+
"single_word": false,
|
| 705 |
+
"special": true
|
| 706 |
+
},
|
| 707 |
+
"36085": {
|
| 708 |
+
"content": "<extra_id_14>",
|
| 709 |
+
"lstrip": false,
|
| 710 |
+
"normalized": false,
|
| 711 |
+
"rstrip": false,
|
| 712 |
+
"single_word": false,
|
| 713 |
+
"special": true
|
| 714 |
+
},
|
| 715 |
+
"36086": {
|
| 716 |
+
"content": "<extra_id_13>",
|
| 717 |
+
"lstrip": false,
|
| 718 |
+
"normalized": false,
|
| 719 |
+
"rstrip": false,
|
| 720 |
+
"single_word": false,
|
| 721 |
+
"special": true
|
| 722 |
+
},
|
| 723 |
+
"36087": {
|
| 724 |
+
"content": "<extra_id_12>",
|
| 725 |
+
"lstrip": false,
|
| 726 |
+
"normalized": false,
|
| 727 |
+
"rstrip": false,
|
| 728 |
+
"single_word": false,
|
| 729 |
+
"special": true
|
| 730 |
+
},
|
| 731 |
+
"36088": {
|
| 732 |
+
"content": "<extra_id_11>",
|
| 733 |
+
"lstrip": false,
|
| 734 |
+
"normalized": false,
|
| 735 |
+
"rstrip": false,
|
| 736 |
+
"single_word": false,
|
| 737 |
+
"special": true
|
| 738 |
+
},
|
| 739 |
+
"36089": {
|
| 740 |
+
"content": "<extra_id_10>",
|
| 741 |
+
"lstrip": false,
|
| 742 |
+
"normalized": false,
|
| 743 |
+
"rstrip": false,
|
| 744 |
+
"single_word": false,
|
| 745 |
+
"special": true
|
| 746 |
+
},
|
| 747 |
+
"36090": {
|
| 748 |
+
"content": "<extra_id_9>",
|
| 749 |
+
"lstrip": false,
|
| 750 |
+
"normalized": false,
|
| 751 |
+
"rstrip": false,
|
| 752 |
+
"single_word": false,
|
| 753 |
+
"special": true
|
| 754 |
+
},
|
| 755 |
+
"36091": {
|
| 756 |
+
"content": "<extra_id_8>",
|
| 757 |
+
"lstrip": false,
|
| 758 |
+
"normalized": false,
|
| 759 |
+
"rstrip": false,
|
| 760 |
+
"single_word": false,
|
| 761 |
+
"special": true
|
| 762 |
+
},
|
| 763 |
+
"36092": {
|
| 764 |
+
"content": "<extra_id_7>",
|
| 765 |
+
"lstrip": false,
|
| 766 |
+
"normalized": false,
|
| 767 |
+
"rstrip": false,
|
| 768 |
+
"single_word": false,
|
| 769 |
+
"special": true
|
| 770 |
+
},
|
| 771 |
+
"36093": {
|
| 772 |
+
"content": "<extra_id_6>",
|
| 773 |
+
"lstrip": false,
|
| 774 |
+
"normalized": false,
|
| 775 |
+
"rstrip": false,
|
| 776 |
+
"single_word": false,
|
| 777 |
+
"special": true
|
| 778 |
+
},
|
| 779 |
+
"36094": {
|
| 780 |
+
"content": "<extra_id_5>",
|
| 781 |
+
"lstrip": false,
|
| 782 |
+
"normalized": false,
|
| 783 |
+
"rstrip": false,
|
| 784 |
+
"single_word": false,
|
| 785 |
+
"special": true
|
| 786 |
+
},
|
| 787 |
+
"36095": {
|
| 788 |
+
"content": "<extra_id_4>",
|
| 789 |
+
"lstrip": false,
|
| 790 |
+
"normalized": false,
|
| 791 |
+
"rstrip": false,
|
| 792 |
+
"single_word": false,
|
| 793 |
+
"special": true
|
| 794 |
+
},
|
| 795 |
+
"36096": {
|
| 796 |
+
"content": "<extra_id_3>",
|
| 797 |
+
"lstrip": false,
|
| 798 |
+
"normalized": false,
|
| 799 |
+
"rstrip": false,
|
| 800 |
+
"single_word": false,
|
| 801 |
+
"special": true
|
| 802 |
+
},
|
| 803 |
+
"36097": {
|
| 804 |
+
"content": "<extra_id_2>",
|
| 805 |
+
"lstrip": false,
|
| 806 |
+
"normalized": false,
|
| 807 |
+
"rstrip": false,
|
| 808 |
+
"single_word": false,
|
| 809 |
+
"special": true
|
| 810 |
+
},
|
| 811 |
+
"36098": {
|
| 812 |
+
"content": "<extra_id_1>",
|
| 813 |
+
"lstrip": false,
|
| 814 |
+
"normalized": false,
|
| 815 |
+
"rstrip": false,
|
| 816 |
+
"single_word": false,
|
| 817 |
+
"special": true
|
| 818 |
+
},
|
| 819 |
+
"36099": {
|
| 820 |
+
"content": "<extra_id_0>",
|
| 821 |
+
"lstrip": false,
|
| 822 |
+
"normalized": false,
|
| 823 |
+
"rstrip": false,
|
| 824 |
+
"single_word": false,
|
| 825 |
+
"special": true
|
| 826 |
+
}
|
| 827 |
+
},
|
| 828 |
+
"additional_special_tokens": [
|
| 829 |
+
"<extra_id_0>",
|
| 830 |
+
"<extra_id_1>",
|
| 831 |
+
"<extra_id_2>",
|
| 832 |
+
"<extra_id_3>",
|
| 833 |
+
"<extra_id_4>",
|
| 834 |
+
"<extra_id_5>",
|
| 835 |
+
"<extra_id_6>",
|
| 836 |
+
"<extra_id_7>",
|
| 837 |
+
"<extra_id_8>",
|
| 838 |
+
"<extra_id_9>",
|
| 839 |
+
"<extra_id_10>",
|
| 840 |
+
"<extra_id_11>",
|
| 841 |
+
"<extra_id_12>",
|
| 842 |
+
"<extra_id_13>",
|
| 843 |
+
"<extra_id_14>",
|
| 844 |
+
"<extra_id_15>",
|
| 845 |
+
"<extra_id_16>",
|
| 846 |
+
"<extra_id_17>",
|
| 847 |
+
"<extra_id_18>",
|
| 848 |
+
"<extra_id_19>",
|
| 849 |
+
"<extra_id_20>",
|
| 850 |
+
"<extra_id_21>",
|
| 851 |
+
"<extra_id_22>",
|
| 852 |
+
"<extra_id_23>",
|
| 853 |
+
"<extra_id_24>",
|
| 854 |
+
"<extra_id_25>",
|
| 855 |
+
"<extra_id_26>",
|
| 856 |
+
"<extra_id_27>",
|
| 857 |
+
"<extra_id_28>",
|
| 858 |
+
"<extra_id_29>",
|
| 859 |
+
"<extra_id_30>",
|
| 860 |
+
"<extra_id_31>",
|
| 861 |
+
"<extra_id_32>",
|
| 862 |
+
"<extra_id_33>",
|
| 863 |
+
"<extra_id_34>",
|
| 864 |
+
"<extra_id_35>",
|
| 865 |
+
"<extra_id_36>",
|
| 866 |
+
"<extra_id_37>",
|
| 867 |
+
"<extra_id_38>",
|
| 868 |
+
"<extra_id_39>",
|
| 869 |
+
"<extra_id_40>",
|
| 870 |
+
"<extra_id_41>",
|
| 871 |
+
"<extra_id_42>",
|
| 872 |
+
"<extra_id_43>",
|
| 873 |
+
"<extra_id_44>",
|
| 874 |
+
"<extra_id_45>",
|
| 875 |
+
"<extra_id_46>",
|
| 876 |
+
"<extra_id_47>",
|
| 877 |
+
"<extra_id_48>",
|
| 878 |
+
"<extra_id_49>",
|
| 879 |
+
"<extra_id_50>",
|
| 880 |
+
"<extra_id_51>",
|
| 881 |
+
"<extra_id_52>",
|
| 882 |
+
"<extra_id_53>",
|
| 883 |
+
"<extra_id_54>",
|
| 884 |
+
"<extra_id_55>",
|
| 885 |
+
"<extra_id_56>",
|
| 886 |
+
"<extra_id_57>",
|
| 887 |
+
"<extra_id_58>",
|
| 888 |
+
"<extra_id_59>",
|
| 889 |
+
"<extra_id_60>",
|
| 890 |
+
"<extra_id_61>",
|
| 891 |
+
"<extra_id_62>",
|
| 892 |
+
"<extra_id_63>",
|
| 893 |
+
"<extra_id_64>",
|
| 894 |
+
"<extra_id_65>",
|
| 895 |
+
"<extra_id_66>",
|
| 896 |
+
"<extra_id_67>",
|
| 897 |
+
"<extra_id_68>",
|
| 898 |
+
"<extra_id_69>",
|
| 899 |
+
"<extra_id_70>",
|
| 900 |
+
"<extra_id_71>",
|
| 901 |
+
"<extra_id_72>",
|
| 902 |
+
"<extra_id_73>",
|
| 903 |
+
"<extra_id_74>",
|
| 904 |
+
"<extra_id_75>",
|
| 905 |
+
"<extra_id_76>",
|
| 906 |
+
"<extra_id_77>",
|
| 907 |
+
"<extra_id_78>",
|
| 908 |
+
"<extra_id_79>",
|
| 909 |
+
"<extra_id_80>",
|
| 910 |
+
"<extra_id_81>",
|
| 911 |
+
"<extra_id_82>",
|
| 912 |
+
"<extra_id_83>",
|
| 913 |
+
"<extra_id_84>",
|
| 914 |
+
"<extra_id_85>",
|
| 915 |
+
"<extra_id_86>",
|
| 916 |
+
"<extra_id_87>",
|
| 917 |
+
"<extra_id_88>",
|
| 918 |
+
"<extra_id_89>",
|
| 919 |
+
"<extra_id_90>",
|
| 920 |
+
"<extra_id_91>",
|
| 921 |
+
"<extra_id_92>",
|
| 922 |
+
"<extra_id_93>",
|
| 923 |
+
"<extra_id_94>",
|
| 924 |
+
"<extra_id_95>",
|
| 925 |
+
"<extra_id_96>",
|
| 926 |
+
"<extra_id_97>",
|
| 927 |
+
"<extra_id_98>",
|
| 928 |
+
"<extra_id_99>"
|
| 929 |
+
],
|
| 930 |
+
"clean_up_tokenization_spaces": true,
|
| 931 |
+
"eos_token": "</s>",
|
| 932 |
+
"extra_ids": 100,
|
| 933 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 934 |
+
"pad_token": "<pad>",
|
| 935 |
+
"tokenizer_class": "T5Tokenizer",
|
| 936 |
+
"unk_token": "<unk>"
|
| 937 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1611 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 48.63813229571984,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 12500,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 1.0,
|
| 13 |
+
"eval_bp": 0.4559528592458481,
|
| 14 |
+
"eval_counts": [
|
| 15 |
+
3210,
|
| 16 |
+
1930,
|
| 17 |
+
1488,
|
| 18 |
+
1066
|
| 19 |
+
],
|
| 20 |
+
"eval_loss": 2.412109375,
|
| 21 |
+
"eval_precisions": [
|
| 22 |
+
71.17516629711751,
|
| 23 |
+
48.44377510040161,
|
| 24 |
+
43.03065355696935,
|
| 25 |
+
36.24617477048623
|
| 26 |
+
],
|
| 27 |
+
"eval_ref_len": 8052,
|
| 28 |
+
"eval_runtime": 118.4312,
|
| 29 |
+
"eval_samples_per_second": 4.441,
|
| 30 |
+
"eval_score": 21.9569286964753,
|
| 31 |
+
"eval_steps_per_second": 0.279,
|
| 32 |
+
"eval_sys_len": 4510,
|
| 33 |
+
"eval_totals": [
|
| 34 |
+
4510,
|
| 35 |
+
3984,
|
| 36 |
+
3458,
|
| 37 |
+
2941
|
| 38 |
+
],
|
| 39 |
+
"step": 257
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 1.95,
|
| 43 |
+
"learning_rate": 1.9221789883268484e-05,
|
| 44 |
+
"loss": 2.8948,
|
| 45 |
+
"step": 500
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 2.0,
|
| 49 |
+
"eval_bp": 0.43532380297987505,
|
| 50 |
+
"eval_counts": [
|
| 51 |
+
1708,
|
| 52 |
+
541,
|
| 53 |
+
376,
|
| 54 |
+
228
|
| 55 |
+
],
|
| 56 |
+
"eval_loss": 1.5029296875,
|
| 57 |
+
"eval_precisions": [
|
| 58 |
+
38.853503184713375,
|
| 59 |
+
13.979328165374676,
|
| 60 |
+
11.24401913875598,
|
| 61 |
+
7.497533706017757
|
| 62 |
+
],
|
| 63 |
+
"eval_ref_len": 8052,
|
| 64 |
+
"eval_runtime": 115.6212,
|
| 65 |
+
"eval_samples_per_second": 4.549,
|
| 66 |
+
"eval_score": 6.3679777301051494,
|
| 67 |
+
"eval_steps_per_second": 0.285,
|
| 68 |
+
"eval_sys_len": 4396,
|
| 69 |
+
"eval_totals": [
|
| 70 |
+
4396,
|
| 71 |
+
3870,
|
| 72 |
+
3344,
|
| 73 |
+
3041
|
| 74 |
+
],
|
| 75 |
+
"step": 514
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 3.0,
|
| 79 |
+
"eval_bp": 0.5596896112039585,
|
| 80 |
+
"eval_counts": [
|
| 81 |
+
2795,
|
| 82 |
+
1858,
|
| 83 |
+
1416,
|
| 84 |
+
991
|
| 85 |
+
],
|
| 86 |
+
"eval_loss": 0.65576171875,
|
| 87 |
+
"eval_precisions": [
|
| 88 |
+
54.85770363101079,
|
| 89 |
+
40.66535346903042,
|
| 90 |
+
35.02349740291862,
|
| 91 |
+
28.177423940858688
|
| 92 |
+
],
|
| 93 |
+
"eval_ref_len": 8052,
|
| 94 |
+
"eval_runtime": 115.5065,
|
| 95 |
+
"eval_samples_per_second": 4.554,
|
| 96 |
+
"eval_score": 21.558969055160425,
|
| 97 |
+
"eval_steps_per_second": 0.286,
|
| 98 |
+
"eval_sys_len": 5095,
|
| 99 |
+
"eval_totals": [
|
| 100 |
+
5095,
|
| 101 |
+
4569,
|
| 102 |
+
4043,
|
| 103 |
+
3517
|
| 104 |
+
],
|
| 105 |
+
"step": 771
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 3.89,
|
| 109 |
+
"learning_rate": 1.8443579766536967e-05,
|
| 110 |
+
"loss": 0.8924,
|
| 111 |
+
"step": 1000
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 4.0,
|
| 115 |
+
"eval_bp": 0.6650198090145658,
|
| 116 |
+
"eval_counts": [
|
| 117 |
+
3257,
|
| 118 |
+
2161,
|
| 119 |
+
1704,
|
| 120 |
+
1256
|
| 121 |
+
],
|
| 122 |
+
"eval_loss": 0.485107421875,
|
| 123 |
+
"eval_precisions": [
|
| 124 |
+
56.950515824444835,
|
| 125 |
+
41.61371076449066,
|
| 126 |
+
36.51167773730448,
|
| 127 |
+
30.330837961844964
|
| 128 |
+
],
|
| 129 |
+
"eval_ref_len": 8052,
|
| 130 |
+
"eval_runtime": 115.5544,
|
| 131 |
+
"eval_samples_per_second": 4.552,
|
| 132 |
+
"eval_score": 26.766843398496384,
|
| 133 |
+
"eval_steps_per_second": 0.286,
|
| 134 |
+
"eval_sys_len": 5719,
|
| 135 |
+
"eval_totals": [
|
| 136 |
+
5719,
|
| 137 |
+
5193,
|
| 138 |
+
4667,
|
| 139 |
+
4141
|
| 140 |
+
],
|
| 141 |
+
"step": 1028
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 5.0,
|
| 145 |
+
"eval_bp": 0.41788118238391686,
|
| 146 |
+
"eval_counts": [
|
| 147 |
+
3699,
|
| 148 |
+
2841,
|
| 149 |
+
2368,
|
| 150 |
+
1900
|
| 151 |
+
],
|
| 152 |
+
"eval_loss": 0.293701171875,
|
| 153 |
+
"eval_precisions": [
|
| 154 |
+
86.02325581395348,
|
| 155 |
+
75.27821939586646,
|
| 156 |
+
72.9064039408867,
|
| 157 |
+
69.80161645848641
|
| 158 |
+
],
|
| 159 |
+
"eval_ref_len": 8052,
|
| 160 |
+
"eval_runtime": 115.1699,
|
| 161 |
+
"eval_samples_per_second": 4.567,
|
| 162 |
+
"eval_score": 31.661530724736487,
|
| 163 |
+
"eval_steps_per_second": 0.287,
|
| 164 |
+
"eval_sys_len": 4300,
|
| 165 |
+
"eval_totals": [
|
| 166 |
+
4300,
|
| 167 |
+
3774,
|
| 168 |
+
3248,
|
| 169 |
+
2722
|
| 170 |
+
],
|
| 171 |
+
"step": 1285
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 5.84,
|
| 175 |
+
"learning_rate": 1.766536964980545e-05,
|
| 176 |
+
"loss": 0.4295,
|
| 177 |
+
"step": 1500
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 6.0,
|
| 181 |
+
"eval_bp": 0.4089581075583404,
|
| 182 |
+
"eval_counts": [
|
| 183 |
+
3783,
|
| 184 |
+
2928,
|
| 185 |
+
2446,
|
| 186 |
+
1971
|
| 187 |
+
],
|
| 188 |
+
"eval_loss": 0.2445068359375,
|
| 189 |
+
"eval_precisions": [
|
| 190 |
+
88.9908256880734,
|
| 191 |
+
78.60402684563758,
|
| 192 |
+
76.46139418568302,
|
| 193 |
+
73.73737373737374
|
| 194 |
+
],
|
| 195 |
+
"eval_ref_len": 8052,
|
| 196 |
+
"eval_runtime": 115.449,
|
| 197 |
+
"eval_samples_per_second": 4.556,
|
| 198 |
+
"eval_score": 32.408490251125635,
|
| 199 |
+
"eval_steps_per_second": 0.286,
|
| 200 |
+
"eval_sys_len": 4251,
|
| 201 |
+
"eval_totals": [
|
| 202 |
+
4251,
|
| 203 |
+
3725,
|
| 204 |
+
3199,
|
| 205 |
+
2673
|
| 206 |
+
],
|
| 207 |
+
"step": 1542
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 7.0,
|
| 211 |
+
"eval_bp": 0.417153226107242,
|
| 212 |
+
"eval_counts": [
|
| 213 |
+
3818,
|
| 214 |
+
2965,
|
| 215 |
+
2480,
|
| 216 |
+
2002
|
| 217 |
+
],
|
| 218 |
+
"eval_loss": 0.22021484375,
|
| 219 |
+
"eval_precisions": [
|
| 220 |
+
88.8733705772812,
|
| 221 |
+
78.64721485411141,
|
| 222 |
+
76.44882860665845,
|
| 223 |
+
73.6571008094187
|
| 224 |
+
],
|
| 225 |
+
"eval_ref_len": 8052,
|
| 226 |
+
"eval_runtime": 115.4073,
|
| 227 |
+
"eval_samples_per_second": 4.558,
|
| 228 |
+
"eval_score": 33.04119304311829,
|
| 229 |
+
"eval_steps_per_second": 0.286,
|
| 230 |
+
"eval_sys_len": 4296,
|
| 231 |
+
"eval_totals": [
|
| 232 |
+
4296,
|
| 233 |
+
3770,
|
| 234 |
+
3244,
|
| 235 |
+
2718
|
| 236 |
+
],
|
| 237 |
+
"step": 1799
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 7.78,
|
| 241 |
+
"learning_rate": 1.6887159533073932e-05,
|
| 242 |
+
"loss": 0.2991,
|
| 243 |
+
"step": 2000
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 8.0,
|
| 247 |
+
"eval_bp": 0.42679131632296613,
|
| 248 |
+
"eval_counts": [
|
| 249 |
+
3874,
|
| 250 |
+
3019,
|
| 251 |
+
2524,
|
| 252 |
+
2038
|
| 253 |
+
],
|
| 254 |
+
"eval_loss": 0.2076416015625,
|
| 255 |
+
"eval_precisions": [
|
| 256 |
+
89.07794895378248,
|
| 257 |
+
78.9693957624902,
|
| 258 |
+
76.55444343342432,
|
| 259 |
+
73.54745579213281
|
| 260 |
+
],
|
| 261 |
+
"eval_ref_len": 8052,
|
| 262 |
+
"eval_runtime": 114.0107,
|
| 263 |
+
"eval_samples_per_second": 4.614,
|
| 264 |
+
"eval_score": 33.85769159645968,
|
| 265 |
+
"eval_steps_per_second": 0.289,
|
| 266 |
+
"eval_sys_len": 4349,
|
| 267 |
+
"eval_totals": [
|
| 268 |
+
4349,
|
| 269 |
+
3823,
|
| 270 |
+
3297,
|
| 271 |
+
2771
|
| 272 |
+
],
|
| 273 |
+
"step": 2056
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 9.0,
|
| 277 |
+
"eval_bp": 0.46028228872696303,
|
| 278 |
+
"eval_counts": [
|
| 279 |
+
4065,
|
| 280 |
+
3225,
|
| 281 |
+
2700,
|
| 282 |
+
2186
|
| 283 |
+
],
|
| 284 |
+
"eval_loss": 0.1663818359375,
|
| 285 |
+
"eval_precisions": [
|
| 286 |
+
89.65593295103662,
|
| 287 |
+
80.46407185628742,
|
| 288 |
+
77.54164273406089,
|
| 289 |
+
73.9512855209743
|
| 290 |
+
],
|
| 291 |
+
"eval_ref_len": 8052,
|
| 292 |
+
"eval_runtime": 114.8195,
|
| 293 |
+
"eval_samples_per_second": 4.581,
|
| 294 |
+
"eval_score": 36.91388078489759,
|
| 295 |
+
"eval_steps_per_second": 0.287,
|
| 296 |
+
"eval_sys_len": 4534,
|
| 297 |
+
"eval_totals": [
|
| 298 |
+
4534,
|
| 299 |
+
4008,
|
| 300 |
+
3482,
|
| 301 |
+
2956
|
| 302 |
+
],
|
| 303 |
+
"step": 2313
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 9.73,
|
| 307 |
+
"learning_rate": 1.6108949416342414e-05,
|
| 308 |
+
"loss": 0.2277,
|
| 309 |
+
"step": 2500
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 10.0,
|
| 313 |
+
"eval_bp": 0.5426087135017283,
|
| 314 |
+
"eval_counts": [
|
| 315 |
+
4419,
|
| 316 |
+
3611,
|
| 317 |
+
3062,
|
| 318 |
+
2525
|
| 319 |
+
],
|
| 320 |
+
"eval_loss": 0.1044921875,
|
| 321 |
+
"eval_precisions": [
|
| 322 |
+
88.43305983590155,
|
| 323 |
+
80.76492954596287,
|
| 324 |
+
77.617237008872,
|
| 325 |
+
73.85200350979818
|
| 326 |
+
],
|
| 327 |
+
"eval_ref_len": 8052,
|
| 328 |
+
"eval_runtime": 114.7152,
|
| 329 |
+
"eval_samples_per_second": 4.585,
|
| 330 |
+
"eval_score": 43.40364936643555,
|
| 331 |
+
"eval_steps_per_second": 0.288,
|
| 332 |
+
"eval_sys_len": 4997,
|
| 333 |
+
"eval_totals": [
|
| 334 |
+
4997,
|
| 335 |
+
4471,
|
| 336 |
+
3945,
|
| 337 |
+
3419
|
| 338 |
+
],
|
| 339 |
+
"step": 2570
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 11.0,
|
| 343 |
+
"eval_bp": 0.5841943959505824,
|
| 344 |
+
"eval_counts": [
|
| 345 |
+
4717,
|
| 346 |
+
3950,
|
| 347 |
+
3372,
|
| 348 |
+
2808
|
| 349 |
+
],
|
| 350 |
+
"eval_loss": 0.08892822265625,
|
| 351 |
+
"eval_precisions": [
|
| 352 |
+
90.07065113614665,
|
| 353 |
+
83.846317130121,
|
| 354 |
+
80.57347670250896,
|
| 355 |
+
76.74227931128723
|
| 356 |
+
],
|
| 357 |
+
"eval_ref_len": 8052,
|
| 358 |
+
"eval_runtime": 113.7863,
|
| 359 |
+
"eval_samples_per_second": 4.623,
|
| 360 |
+
"eval_score": 48.29263576279789,
|
| 361 |
+
"eval_steps_per_second": 0.29,
|
| 362 |
+
"eval_sys_len": 5237,
|
| 363 |
+
"eval_totals": [
|
| 364 |
+
5237,
|
| 365 |
+
4711,
|
| 366 |
+
4185,
|
| 367 |
+
3659
|
| 368 |
+
],
|
| 369 |
+
"step": 2827
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 11.67,
|
| 373 |
+
"learning_rate": 1.5330739299610897e-05,
|
| 374 |
+
"loss": 0.1405,
|
| 375 |
+
"step": 3000
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 12.0,
|
| 379 |
+
"eval_bp": 0.5586477230994942,
|
| 380 |
+
"eval_counts": [
|
| 381 |
+
4630,
|
| 382 |
+
3875,
|
| 383 |
+
3303,
|
| 384 |
+
2749
|
| 385 |
+
],
|
| 386 |
+
"eval_loss": 0.08489990234375,
|
| 387 |
+
"eval_precisions": [
|
| 388 |
+
90.98054627628218,
|
| 389 |
+
84.9222003068157,
|
| 390 |
+
81.81818181818181,
|
| 391 |
+
78.29678154371973
|
| 392 |
+
],
|
| 393 |
+
"eval_ref_len": 8052,
|
| 394 |
+
"eval_runtime": 107.8868,
|
| 395 |
+
"eval_samples_per_second": 4.875,
|
| 396 |
+
"eval_score": 46.85747814062412,
|
| 397 |
+
"eval_steps_per_second": 0.306,
|
| 398 |
+
"eval_sys_len": 5089,
|
| 399 |
+
"eval_totals": [
|
| 400 |
+
5089,
|
| 401 |
+
4563,
|
| 402 |
+
4037,
|
| 403 |
+
3511
|
| 404 |
+
],
|
| 405 |
+
"step": 3084
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 13.0,
|
| 409 |
+
"eval_bp": 0.5695616786732568,
|
| 410 |
+
"eval_counts": [
|
| 411 |
+
4747,
|
| 412 |
+
4034,
|
| 413 |
+
3464,
|
| 414 |
+
2904
|
| 415 |
+
],
|
| 416 |
+
"eval_loss": 0.08123779296875,
|
| 417 |
+
"eval_precisions": [
|
| 418 |
+
92.1389751552795,
|
| 419 |
+
87.20276696930394,
|
| 420 |
+
84.48780487804878,
|
| 421 |
+
81.2534974818131
|
| 422 |
+
],
|
| 423 |
+
"eval_ref_len": 8052,
|
| 424 |
+
"eval_runtime": 108.2759,
|
| 425 |
+
"eval_samples_per_second": 4.858,
|
| 426 |
+
"eval_score": 49.08436700451685,
|
| 427 |
+
"eval_steps_per_second": 0.305,
|
| 428 |
+
"eval_sys_len": 5152,
|
| 429 |
+
"eval_totals": [
|
| 430 |
+
5152,
|
| 431 |
+
4626,
|
| 432 |
+
4100,
|
| 433 |
+
3574
|
| 434 |
+
],
|
| 435 |
+
"step": 3341
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 13.62,
|
| 439 |
+
"learning_rate": 1.4552529182879378e-05,
|
| 440 |
+
"loss": 0.1241,
|
| 441 |
+
"step": 3500
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 14.0,
|
| 445 |
+
"eval_bp": 0.5695616786732568,
|
| 446 |
+
"eval_counts": [
|
| 447 |
+
4738,
|
| 448 |
+
4024,
|
| 449 |
+
3452,
|
| 450 |
+
2894
|
| 451 |
+
],
|
| 452 |
+
"eval_loss": 0.07525634765625,
|
| 453 |
+
"eval_precisions": [
|
| 454 |
+
91.96428571428571,
|
| 455 |
+
86.98659749243407,
|
| 456 |
+
84.1951219512195,
|
| 457 |
+
80.97369893676553
|
| 458 |
+
],
|
| 459 |
+
"eval_ref_len": 8052,
|
| 460 |
+
"eval_runtime": 107.2784,
|
| 461 |
+
"eval_samples_per_second": 4.903,
|
| 462 |
+
"eval_score": 48.94590635934059,
|
| 463 |
+
"eval_steps_per_second": 0.308,
|
| 464 |
+
"eval_sys_len": 5152,
|
| 465 |
+
"eval_totals": [
|
| 466 |
+
5152,
|
| 467 |
+
4626,
|
| 468 |
+
4100,
|
| 469 |
+
3574
|
| 470 |
+
],
|
| 471 |
+
"step": 3598
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 15.0,
|
| 475 |
+
"eval_bp": 0.5961628688829712,
|
| 476 |
+
"eval_counts": [
|
| 477 |
+
4741,
|
| 478 |
+
4006,
|
| 479 |
+
3444,
|
| 480 |
+
2891
|
| 481 |
+
],
|
| 482 |
+
"eval_loss": 0.07562255859375,
|
| 483 |
+
"eval_precisions": [
|
| 484 |
+
89.33484077633314,
|
| 485 |
+
83.79000209161264,
|
| 486 |
+
80.94007050528789,
|
| 487 |
+
77.52748726200053
|
| 488 |
+
],
|
| 489 |
+
"eval_ref_len": 8052,
|
| 490 |
+
"eval_runtime": 106.2867,
|
| 491 |
+
"eval_samples_per_second": 4.949,
|
| 492 |
+
"eval_score": 49.354074470195435,
|
| 493 |
+
"eval_steps_per_second": 0.31,
|
| 494 |
+
"eval_sys_len": 5307,
|
| 495 |
+
"eval_totals": [
|
| 496 |
+
5307,
|
| 497 |
+
4781,
|
| 498 |
+
4255,
|
| 499 |
+
3729
|
| 500 |
+
],
|
| 501 |
+
"step": 3855
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 15.56,
|
| 505 |
+
"learning_rate": 1.377431906614786e-05,
|
| 506 |
+
"loss": 0.1147,
|
| 507 |
+
"step": 4000
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 16.0,
|
| 511 |
+
"eval_bp": 0.5655838797151567,
|
| 512 |
+
"eval_counts": [
|
| 513 |
+
4743,
|
| 514 |
+
4039,
|
| 515 |
+
3477,
|
| 516 |
+
2925
|
| 517 |
+
],
|
| 518 |
+
"eval_loss": 0.06915283203125,
|
| 519 |
+
"eval_precisions": [
|
| 520 |
+
92.47416650419186,
|
| 521 |
+
87.74712144253748,
|
| 522 |
+
85.28329654157469,
|
| 523 |
+
82.37116305266122
|
| 524 |
+
],
|
| 525 |
+
"eval_ref_len": 8052,
|
| 526 |
+
"eval_runtime": 107.836,
|
| 527 |
+
"eval_samples_per_second": 4.878,
|
| 528 |
+
"eval_score": 49.143959340541095,
|
| 529 |
+
"eval_steps_per_second": 0.306,
|
| 530 |
+
"eval_sys_len": 5129,
|
| 531 |
+
"eval_totals": [
|
| 532 |
+
5129,
|
| 533 |
+
4603,
|
| 534 |
+
4077,
|
| 535 |
+
3551
|
| 536 |
+
],
|
| 537 |
+
"step": 4112
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 17.0,
|
| 541 |
+
"eval_bp": 0.5932631592602093,
|
| 542 |
+
"eval_counts": [
|
| 543 |
+
4727,
|
| 544 |
+
3996,
|
| 545 |
+
3439,
|
| 546 |
+
2892
|
| 547 |
+
],
|
| 548 |
+
"eval_loss": 0.070068359375,
|
| 549 |
+
"eval_precisions": [
|
| 550 |
+
89.35727788279773,
|
| 551 |
+
83.87909319899245,
|
| 552 |
+
81.14676734308637,
|
| 553 |
+
77.90948275862068
|
| 554 |
+
],
|
| 555 |
+
"eval_ref_len": 8052,
|
| 556 |
+
"eval_runtime": 106.6266,
|
| 557 |
+
"eval_samples_per_second": 4.933,
|
| 558 |
+
"eval_score": 49.221934768405774,
|
| 559 |
+
"eval_steps_per_second": 0.309,
|
| 560 |
+
"eval_sys_len": 5290,
|
| 561 |
+
"eval_totals": [
|
| 562 |
+
5290,
|
| 563 |
+
4764,
|
| 564 |
+
4238,
|
| 565 |
+
3712
|
| 566 |
+
],
|
| 567 |
+
"step": 4369
|
| 568 |
+
},
|
| 569 |
+
{
|
| 570 |
+
"epoch": 17.51,
|
| 571 |
+
"learning_rate": 1.2996108949416343e-05,
|
| 572 |
+
"loss": 0.1065,
|
| 573 |
+
"step": 4500
|
| 574 |
+
},
|
| 575 |
+
{
|
| 576 |
+
"epoch": 18.0,
|
| 577 |
+
"eval_bp": 0.5610779943992972,
|
| 578 |
+
"eval_counts": [
|
| 579 |
+
4753,
|
| 580 |
+
4064,
|
| 581 |
+
3505,
|
| 582 |
+
2956
|
| 583 |
+
],
|
| 584 |
+
"eval_loss": 0.0623779296875,
|
| 585 |
+
"eval_precisions": [
|
| 586 |
+
93.14128943758574,
|
| 587 |
+
88.7917850120166,
|
| 588 |
+
86.52184645766478,
|
| 589 |
+
83.8581560283688
|
| 590 |
+
],
|
| 591 |
+
"eval_ref_len": 8052,
|
| 592 |
+
"eval_runtime": 106.949,
|
| 593 |
+
"eval_samples_per_second": 4.918,
|
| 594 |
+
"eval_score": 49.382124037917905,
|
| 595 |
+
"eval_steps_per_second": 0.309,
|
| 596 |
+
"eval_sys_len": 5103,
|
| 597 |
+
"eval_totals": [
|
| 598 |
+
5103,
|
| 599 |
+
4577,
|
| 600 |
+
4051,
|
| 601 |
+
3525
|
| 602 |
+
],
|
| 603 |
+
"step": 4626
|
| 604 |
+
},
|
| 605 |
+
{
|
| 606 |
+
"epoch": 19.0,
|
| 607 |
+
"eval_bp": 0.5788702549376445,
|
| 608 |
+
"eval_counts": [
|
| 609 |
+
4784,
|
| 610 |
+
4087,
|
| 611 |
+
3529,
|
| 612 |
+
2977
|
| 613 |
+
],
|
| 614 |
+
"eval_loss": 0.060699462890625,
|
| 615 |
+
"eval_precisions": [
|
| 616 |
+
91.89396849788706,
|
| 617 |
+
87.32905982905983,
|
| 618 |
+
84.95426095329803,
|
| 619 |
+
82.05622932745314
|
| 620 |
+
],
|
| 621 |
+
"eval_ref_len": 8052,
|
| 622 |
+
"eval_runtime": 106.4771,
|
| 623 |
+
"eval_samples_per_second": 4.94,
|
| 624 |
+
"eval_score": 50.0629990425284,
|
| 625 |
+
"eval_steps_per_second": 0.31,
|
| 626 |
+
"eval_sys_len": 5206,
|
| 627 |
+
"eval_totals": [
|
| 628 |
+
5206,
|
| 629 |
+
4680,
|
| 630 |
+
4154,
|
| 631 |
+
3628
|
| 632 |
+
],
|
| 633 |
+
"step": 4883
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 19.46,
|
| 637 |
+
"learning_rate": 1.2217898832684827e-05,
|
| 638 |
+
"loss": 0.0964,
|
| 639 |
+
"step": 5000
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 20.0,
|
| 643 |
+
"eval_bp": 0.5826501698750266,
|
| 644 |
+
"eval_counts": [
|
| 645 |
+
4773,
|
| 646 |
+
4068,
|
| 647 |
+
3509,
|
| 648 |
+
2957
|
| 649 |
+
],
|
| 650 |
+
"eval_loss": 0.0595703125,
|
| 651 |
+
"eval_precisions": [
|
| 652 |
+
91.29686304514155,
|
| 653 |
+
86.51637601020842,
|
| 654 |
+
84.02777777777777,
|
| 655 |
+
81.01369863013699
|
| 656 |
+
],
|
| 657 |
+
"eval_ref_len": 8052,
|
| 658 |
+
"eval_runtime": 106.5688,
|
| 659 |
+
"eval_samples_per_second": 4.936,
|
| 660 |
+
"eval_score": 49.89324555557292,
|
| 661 |
+
"eval_steps_per_second": 0.31,
|
| 662 |
+
"eval_sys_len": 5228,
|
| 663 |
+
"eval_totals": [
|
| 664 |
+
5228,
|
| 665 |
+
4702,
|
| 666 |
+
4176,
|
| 667 |
+
3650
|
| 668 |
+
],
|
| 669 |
+
"step": 5140
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 21.0,
|
| 673 |
+
"eval_bp": 0.5824785136401668,
|
| 674 |
+
"eval_counts": [
|
| 675 |
+
4780,
|
| 676 |
+
4078,
|
| 677 |
+
3521,
|
| 678 |
+
2972
|
| 679 |
+
],
|
| 680 |
+
"eval_loss": 0.057952880859375,
|
| 681 |
+
"eval_precisions": [
|
| 682 |
+
91.4482494738856,
|
| 683 |
+
86.74750053180175,
|
| 684 |
+
84.33532934131736,
|
| 685 |
+
81.44697177308852
|
| 686 |
+
],
|
| 687 |
+
"eval_ref_len": 8052,
|
| 688 |
+
"eval_runtime": 105.7144,
|
| 689 |
+
"eval_samples_per_second": 4.976,
|
| 690 |
+
"eval_score": 50.04481904653482,
|
| 691 |
+
"eval_steps_per_second": 0.312,
|
| 692 |
+
"eval_sys_len": 5227,
|
| 693 |
+
"eval_totals": [
|
| 694 |
+
5227,
|
| 695 |
+
4701,
|
| 696 |
+
4175,
|
| 697 |
+
3649
|
| 698 |
+
],
|
| 699 |
+
"step": 5397
|
| 700 |
+
},
|
| 701 |
+
{
|
| 702 |
+
"epoch": 21.4,
|
| 703 |
+
"learning_rate": 1.1439688715953308e-05,
|
| 704 |
+
"loss": 0.0925,
|
| 705 |
+
"step": 5500
|
| 706 |
+
},
|
| 707 |
+
{
|
| 708 |
+
"epoch": 22.0,
|
| 709 |
+
"eval_bp": 0.6060221334079605,
|
| 710 |
+
"eval_counts": [
|
| 711 |
+
4800,
|
| 712 |
+
4076,
|
| 713 |
+
3514,
|
| 714 |
+
2962
|
| 715 |
+
],
|
| 716 |
+
"eval_loss": 0.060546875,
|
| 717 |
+
"eval_precisions": [
|
| 718 |
+
89.46877912395153,
|
| 719 |
+
84.23227939656954,
|
| 720 |
+
81.47461163923023,
|
| 721 |
+
78.21494586744124
|
| 722 |
+
],
|
| 723 |
+
"eval_ref_len": 8052,
|
| 724 |
+
"eval_runtime": 105.9417,
|
| 725 |
+
"eval_samples_per_second": 4.965,
|
| 726 |
+
"eval_score": 50.4491686657978,
|
| 727 |
+
"eval_steps_per_second": 0.311,
|
| 728 |
+
"eval_sys_len": 5365,
|
| 729 |
+
"eval_totals": [
|
| 730 |
+
5365,
|
| 731 |
+
4839,
|
| 732 |
+
4313,
|
| 733 |
+
3787
|
| 734 |
+
],
|
| 735 |
+
"step": 5654
|
| 736 |
+
},
|
| 737 |
+
{
|
| 738 |
+
"epoch": 23.0,
|
| 739 |
+
"eval_bp": 0.5761166700049626,
|
| 740 |
+
"eval_counts": [
|
| 741 |
+
4832,
|
| 742 |
+
4155,
|
| 743 |
+
3593,
|
| 744 |
+
3036
|
| 745 |
+
],
|
| 746 |
+
"eval_loss": 0.053558349609375,
|
| 747 |
+
"eval_precisions": [
|
| 748 |
+
93.10211946050096,
|
| 749 |
+
89.08662092624357,
|
| 750 |
+
86.82938617689705,
|
| 751 |
+
84.0531561461794
|
| 752 |
+
],
|
| 753 |
+
"eval_ref_len": 8052,
|
| 754 |
+
"eval_runtime": 106.564,
|
| 755 |
+
"eval_samples_per_second": 4.936,
|
| 756 |
+
"eval_score": 50.81695573260325,
|
| 757 |
+
"eval_steps_per_second": 0.31,
|
| 758 |
+
"eval_sys_len": 5190,
|
| 759 |
+
"eval_totals": [
|
| 760 |
+
5190,
|
| 761 |
+
4664,
|
| 762 |
+
4138,
|
| 763 |
+
3612
|
| 764 |
+
],
|
| 765 |
+
"step": 5911
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 23.35,
|
| 769 |
+
"learning_rate": 1.066147859922179e-05,
|
| 770 |
+
"loss": 0.0871,
|
| 771 |
+
"step": 6000
|
| 772 |
+
},
|
| 773 |
+
{
|
| 774 |
+
"epoch": 24.0,
|
| 775 |
+
"eval_bp": 0.5719791556804446,
|
| 776 |
+
"eval_counts": [
|
| 777 |
+
4807,
|
| 778 |
+
4125,
|
| 779 |
+
3565,
|
| 780 |
+
3012
|
| 781 |
+
],
|
| 782 |
+
"eval_loss": 0.052276611328125,
|
| 783 |
+
"eval_precisions": [
|
| 784 |
+
93.05071622144793,
|
| 785 |
+
88.90086206896552,
|
| 786 |
+
86.65532328633932,
|
| 787 |
+
83.94648829431438
|
| 788 |
+
],
|
| 789 |
+
"eval_ref_len": 8052,
|
| 790 |
+
"eval_runtime": 107.1172,
|
| 791 |
+
"eval_samples_per_second": 4.911,
|
| 792 |
+
"eval_score": 50.37743722047891,
|
| 793 |
+
"eval_steps_per_second": 0.308,
|
| 794 |
+
"eval_sys_len": 5166,
|
| 795 |
+
"eval_totals": [
|
| 796 |
+
5166,
|
| 797 |
+
4640,
|
| 798 |
+
4114,
|
| 799 |
+
3588
|
| 800 |
+
],
|
| 801 |
+
"step": 6168
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 25.0,
|
| 805 |
+
"eval_bp": 0.579214183971878,
|
| 806 |
+
"eval_counts": [
|
| 807 |
+
4838,
|
| 808 |
+
4161,
|
| 809 |
+
3602,
|
| 810 |
+
3050
|
| 811 |
+
],
|
| 812 |
+
"eval_loss": 0.050567626953125,
|
| 813 |
+
"eval_precisions": [
|
| 814 |
+
92.89554531490015,
|
| 815 |
+
88.87227680478428,
|
| 816 |
+
86.66987487969202,
|
| 817 |
+
84.02203856749311
|
| 818 |
+
],
|
| 819 |
+
"eval_ref_len": 8052,
|
| 820 |
+
"eval_runtime": 106.5446,
|
| 821 |
+
"eval_samples_per_second": 4.937,
|
| 822 |
+
"eval_score": 51.0028956058344,
|
| 823 |
+
"eval_steps_per_second": 0.31,
|
| 824 |
+
"eval_sys_len": 5208,
|
| 825 |
+
"eval_totals": [
|
| 826 |
+
5208,
|
| 827 |
+
4682,
|
| 828 |
+
4156,
|
| 829 |
+
3630
|
| 830 |
+
],
|
| 831 |
+
"step": 6425
|
| 832 |
+
},
|
| 833 |
+
{
|
| 834 |
+
"epoch": 25.29,
|
| 835 |
+
"learning_rate": 9.883268482490273e-06,
|
| 836 |
+
"loss": 0.0843,
|
| 837 |
+
"step": 6500
|
| 838 |
+
},
|
| 839 |
+
{
|
| 840 |
+
"epoch": 26.0,
|
| 841 |
+
"eval_bp": 0.5607309845734951,
|
| 842 |
+
"eval_counts": [
|
| 843 |
+
4817,
|
| 844 |
+
4157,
|
| 845 |
+
3596,
|
| 846 |
+
3042
|
| 847 |
+
],
|
| 848 |
+
"eval_loss": 0.051177978515625,
|
| 849 |
+
"eval_precisions": [
|
| 850 |
+
94.43246422270143,
|
| 851 |
+
90.86338797814207,
|
| 852 |
+
88.81205235860706,
|
| 853 |
+
86.34686346863468
|
| 854 |
+
],
|
| 855 |
+
"eval_ref_len": 8052,
|
| 856 |
+
"eval_runtime": 107.5728,
|
| 857 |
+
"eval_samples_per_second": 4.89,
|
| 858 |
+
"eval_score": 50.50236718840154,
|
| 859 |
+
"eval_steps_per_second": 0.307,
|
| 860 |
+
"eval_sys_len": 5101,
|
| 861 |
+
"eval_totals": [
|
| 862 |
+
5101,
|
| 863 |
+
4575,
|
| 864 |
+
4049,
|
| 865 |
+
3523
|
| 866 |
+
],
|
| 867 |
+
"step": 6682
|
| 868 |
+
},
|
| 869 |
+
{
|
| 870 |
+
"epoch": 27.0,
|
| 871 |
+
"eval_bp": 0.5869366550146455,
|
| 872 |
+
"eval_counts": [
|
| 873 |
+
4855,
|
| 874 |
+
4170,
|
| 875 |
+
3608,
|
| 876 |
+
3055
|
| 877 |
+
],
|
| 878 |
+
"eval_loss": 0.0489501953125,
|
| 879 |
+
"eval_precisions": [
|
| 880 |
+
92.42337711783743,
|
| 881 |
+
88.21662788237784,
|
| 882 |
+
85.88431325874792,
|
| 883 |
+
83.12925170068027
|
| 884 |
+
],
|
| 885 |
+
"eval_ref_len": 8052,
|
| 886 |
+
"eval_runtime": 109.9833,
|
| 887 |
+
"eval_samples_per_second": 4.783,
|
| 888 |
+
"eval_score": 51.26739301541927,
|
| 889 |
+
"eval_steps_per_second": 0.3,
|
| 890 |
+
"eval_sys_len": 5253,
|
| 891 |
+
"eval_totals": [
|
| 892 |
+
5253,
|
| 893 |
+
4727,
|
| 894 |
+
4201,
|
| 895 |
+
3675
|
| 896 |
+
],
|
| 897 |
+
"step": 6939
|
| 898 |
+
},
|
| 899 |
+
{
|
| 900 |
+
"epoch": 27.24,
|
| 901 |
+
"learning_rate": 9.105058365758756e-06,
|
| 902 |
+
"loss": 0.0813,
|
| 903 |
+
"step": 7000
|
| 904 |
+
},
|
| 905 |
+
{
|
| 906 |
+
"epoch": 28.0,
|
| 907 |
+
"eval_bp": 0.5641984935077309,
|
| 908 |
+
"eval_counts": [
|
| 909 |
+
4838,
|
| 910 |
+
4184,
|
| 911 |
+
3624,
|
| 912 |
+
3070
|
| 913 |
+
],
|
| 914 |
+
"eval_loss": 0.047760009765625,
|
| 915 |
+
"eval_precisions": [
|
| 916 |
+
94.47373559851592,
|
| 917 |
+
91.05549510337323,
|
| 918 |
+
89.06365200294913,
|
| 919 |
+
86.64973186565058
|
| 920 |
+
],
|
| 921 |
+
"eval_ref_len": 8052,
|
| 922 |
+
"eval_runtime": 109.0318,
|
| 923 |
+
"eval_samples_per_second": 4.824,
|
| 924 |
+
"eval_score": 50.9275946797506,
|
| 925 |
+
"eval_steps_per_second": 0.303,
|
| 926 |
+
"eval_sys_len": 5121,
|
| 927 |
+
"eval_totals": [
|
| 928 |
+
5121,
|
| 929 |
+
4595,
|
| 930 |
+
4069,
|
| 931 |
+
3543
|
| 932 |
+
],
|
| 933 |
+
"step": 7196
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 29.0,
|
| 937 |
+
"eval_bp": 0.5711161019095474,
|
| 938 |
+
"eval_counts": [
|
| 939 |
+
4838,
|
| 940 |
+
4179,
|
| 941 |
+
3625,
|
| 942 |
+
3079
|
| 943 |
+
],
|
| 944 |
+
"eval_loss": 0.0462646484375,
|
| 945 |
+
"eval_precisions": [
|
| 946 |
+
93.74152296066654,
|
| 947 |
+
90.16181229773463,
|
| 948 |
+
88.22097834022877,
|
| 949 |
+
85.93357521629919
|
| 950 |
+
],
|
| 951 |
+
"eval_ref_len": 8052,
|
| 952 |
+
"eval_runtime": 107.2897,
|
| 953 |
+
"eval_samples_per_second": 4.903,
|
| 954 |
+
"eval_score": 51.09715872720289,
|
| 955 |
+
"eval_steps_per_second": 0.308,
|
| 956 |
+
"eval_sys_len": 5161,
|
| 957 |
+
"eval_totals": [
|
| 958 |
+
5161,
|
| 959 |
+
4635,
|
| 960 |
+
4109,
|
| 961 |
+
3583
|
| 962 |
+
],
|
| 963 |
+
"step": 7453
|
| 964 |
+
},
|
| 965 |
+
{
|
| 966 |
+
"epoch": 29.18,
|
| 967 |
+
"learning_rate": 8.326848249027239e-06,
|
| 968 |
+
"loss": 0.0778,
|
| 969 |
+
"step": 7500
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 30.0,
|
| 973 |
+
"eval_bp": 0.587279163676868,
|
| 974 |
+
"eval_counts": [
|
| 975 |
+
4863,
|
| 976 |
+
4185,
|
| 977 |
+
3626,
|
| 978 |
+
3075
|
| 979 |
+
],
|
| 980 |
+
"eval_loss": 0.04534912109375,
|
| 981 |
+
"eval_precisions": [
|
| 982 |
+
92.54043767840152,
|
| 983 |
+
88.49651089025164,
|
| 984 |
+
86.27171068284558,
|
| 985 |
+
83.62795757410933
|
| 986 |
+
],
|
| 987 |
+
"eval_ref_len": 8052,
|
| 988 |
+
"eval_runtime": 108.186,
|
| 989 |
+
"eval_samples_per_second": 4.862,
|
| 990 |
+
"eval_score": 51.488944843891275,
|
| 991 |
+
"eval_steps_per_second": 0.305,
|
| 992 |
+
"eval_sys_len": 5255,
|
| 993 |
+
"eval_totals": [
|
| 994 |
+
5255,
|
| 995 |
+
4729,
|
| 996 |
+
4203,
|
| 997 |
+
3677
|
| 998 |
+
],
|
| 999 |
+
"step": 7710
|
| 1000 |
+
},
|
| 1001 |
+
{
|
| 1002 |
+
"epoch": 31.0,
|
| 1003 |
+
"eval_bp": 0.587279163676868,
|
| 1004 |
+
"eval_counts": [
|
| 1005 |
+
4847,
|
| 1006 |
+
4168,
|
| 1007 |
+
3612,
|
| 1008 |
+
3064
|
| 1009 |
+
],
|
| 1010 |
+
"eval_loss": 0.044677734375,
|
| 1011 |
+
"eval_precisions": [
|
| 1012 |
+
92.23596574690771,
|
| 1013 |
+
88.137026855572,
|
| 1014 |
+
85.93861527480371,
|
| 1015 |
+
83.32880065270601
|
| 1016 |
+
],
|
| 1017 |
+
"eval_ref_len": 8052,
|
| 1018 |
+
"eval_runtime": 106.6208,
|
| 1019 |
+
"eval_samples_per_second": 4.933,
|
| 1020 |
+
"eval_score": 51.298555626377826,
|
| 1021 |
+
"eval_steps_per_second": 0.31,
|
| 1022 |
+
"eval_sys_len": 5255,
|
| 1023 |
+
"eval_totals": [
|
| 1024 |
+
5255,
|
| 1025 |
+
4729,
|
| 1026 |
+
4203,
|
| 1027 |
+
3677
|
| 1028 |
+
],
|
| 1029 |
+
"step": 7967
|
| 1030 |
+
},
|
| 1031 |
+
{
|
| 1032 |
+
"epoch": 31.13,
|
| 1033 |
+
"learning_rate": 7.54863813229572e-06,
|
| 1034 |
+
"loss": 0.0753,
|
| 1035 |
+
"step": 8000
|
| 1036 |
+
},
|
| 1037 |
+
{
|
| 1038 |
+
"epoch": 32.0,
|
| 1039 |
+
"eval_bp": 0.5690432735111319,
|
| 1040 |
+
"eval_counts": [
|
| 1041 |
+
4866,
|
| 1042 |
+
4219,
|
| 1043 |
+
3661,
|
| 1044 |
+
3111
|
| 1045 |
+
],
|
| 1046 |
+
"eval_loss": 0.0438232421875,
|
| 1047 |
+
"eval_precisions": [
|
| 1048 |
+
94.50378714313459,
|
| 1049 |
+
91.26108587497296,
|
| 1050 |
+
89.35806687820356,
|
| 1051 |
+
87.11845421450575
|
| 1052 |
+
],
|
| 1053 |
+
"eval_ref_len": 8052,
|
| 1054 |
+
"eval_runtime": 107.5192,
|
| 1055 |
+
"eval_samples_per_second": 4.892,
|
| 1056 |
+
"eval_score": 51.50981459551784,
|
| 1057 |
+
"eval_steps_per_second": 0.307,
|
| 1058 |
+
"eval_sys_len": 5149,
|
| 1059 |
+
"eval_totals": [
|
| 1060 |
+
5149,
|
| 1061 |
+
4623,
|
| 1062 |
+
4097,
|
| 1063 |
+
3571
|
| 1064 |
+
],
|
| 1065 |
+
"step": 8224
|
| 1066 |
+
},
|
| 1067 |
+
{
|
| 1068 |
+
"epoch": 33.0,
|
| 1069 |
+
"eval_bp": 0.5881351685074624,
|
| 1070 |
+
"eval_counts": [
|
| 1071 |
+
4869,
|
| 1072 |
+
4201,
|
| 1073 |
+
3645,
|
| 1074 |
+
3097
|
| 1075 |
+
],
|
| 1076 |
+
"eval_loss": 0.04400634765625,
|
| 1077 |
+
"eval_precisions": [
|
| 1078 |
+
92.56653992395437,
|
| 1079 |
+
88.74102239121251,
|
| 1080 |
+
86.62072243346007,
|
| 1081 |
+
84.11189570885388
|
| 1082 |
+
],
|
| 1083 |
+
"eval_ref_len": 8052,
|
| 1084 |
+
"eval_runtime": 106.8688,
|
| 1085 |
+
"eval_samples_per_second": 4.922,
|
| 1086 |
+
"eval_score": 51.729891771805434,
|
| 1087 |
+
"eval_steps_per_second": 0.309,
|
| 1088 |
+
"eval_sys_len": 5260,
|
| 1089 |
+
"eval_totals": [
|
| 1090 |
+
5260,
|
| 1091 |
+
4734,
|
| 1092 |
+
4208,
|
| 1093 |
+
3682
|
| 1094 |
+
],
|
| 1095 |
+
"step": 8481
|
| 1096 |
+
},
|
| 1097 |
+
{
|
| 1098 |
+
"epoch": 33.07,
|
| 1099 |
+
"learning_rate": 6.770428015564204e-06,
|
| 1100 |
+
"loss": 0.0714,
|
| 1101 |
+
"step": 8500
|
| 1102 |
+
},
|
| 1103 |
+
{
|
| 1104 |
+
"epoch": 34.0,
|
| 1105 |
+
"eval_bp": 0.5823068423133116,
|
| 1106 |
+
"eval_counts": [
|
| 1107 |
+
4881,
|
| 1108 |
+
4226,
|
| 1109 |
+
3674,
|
| 1110 |
+
3130
|
| 1111 |
+
],
|
| 1112 |
+
"eval_loss": 0.041656494140625,
|
| 1113 |
+
"eval_precisions": [
|
| 1114 |
+
93.398392652124,
|
| 1115 |
+
89.91489361702128,
|
| 1116 |
+
88.02108289410637,
|
| 1117 |
+
85.80043859649123
|
| 1118 |
+
],
|
| 1119 |
+
"eval_ref_len": 8052,
|
| 1120 |
+
"eval_runtime": 107.0835,
|
| 1121 |
+
"eval_samples_per_second": 4.912,
|
| 1122 |
+
"eval_score": 51.96533200156475,
|
| 1123 |
+
"eval_steps_per_second": 0.308,
|
| 1124 |
+
"eval_sys_len": 5226,
|
| 1125 |
+
"eval_totals": [
|
| 1126 |
+
5226,
|
| 1127 |
+
4700,
|
| 1128 |
+
4174,
|
| 1129 |
+
3648
|
| 1130 |
+
],
|
| 1131 |
+
"step": 8738
|
| 1132 |
+
},
|
| 1133 |
+
{
|
| 1134 |
+
"epoch": 35.0,
|
| 1135 |
+
"eval_bp": 0.5862514549555176,
|
| 1136 |
+
"eval_counts": [
|
| 1137 |
+
4902,
|
| 1138 |
+
4242,
|
| 1139 |
+
3685,
|
| 1140 |
+
3133
|
| 1141 |
+
],
|
| 1142 |
+
"eval_loss": 0.042633056640625,
|
| 1143 |
+
"eval_precisions": [
|
| 1144 |
+
93.38921699371309,
|
| 1145 |
+
89.81579504552191,
|
| 1146 |
+
87.80081010245414,
|
| 1147 |
+
85.34459275401798
|
| 1148 |
+
],
|
| 1149 |
+
"eval_ref_len": 8052,
|
| 1150 |
+
"eval_runtime": 106.8404,
|
| 1151 |
+
"eval_samples_per_second": 4.923,
|
| 1152 |
+
"eval_score": 52.19933016750815,
|
| 1153 |
+
"eval_steps_per_second": 0.309,
|
| 1154 |
+
"eval_sys_len": 5249,
|
| 1155 |
+
"eval_totals": [
|
| 1156 |
+
5249,
|
| 1157 |
+
4723,
|
| 1158 |
+
4197,
|
| 1159 |
+
3671
|
| 1160 |
+
],
|
| 1161 |
+
"step": 8995
|
| 1162 |
+
},
|
| 1163 |
+
{
|
| 1164 |
+
"epoch": 35.02,
|
| 1165 |
+
"learning_rate": 5.992217898832685e-06,
|
| 1166 |
+
"loss": 0.0697,
|
| 1167 |
+
"step": 9000
|
| 1168 |
+
},
|
| 1169 |
+
{
|
| 1170 |
+
"epoch": 36.0,
|
| 1171 |
+
"eval_bp": 0.5807611221368078,
|
| 1172 |
+
"eval_counts": [
|
| 1173 |
+
4907,
|
| 1174 |
+
4257,
|
| 1175 |
+
3699,
|
| 1176 |
+
3149
|
| 1177 |
+
],
|
| 1178 |
+
"eval_loss": 0.04095458984375,
|
| 1179 |
+
"eval_precisions": [
|
| 1180 |
+
94.05788767490895,
|
| 1181 |
+
90.74824131315285,
|
| 1182 |
+
88.81152460984394,
|
| 1183 |
+
86.53476229733444
|
| 1184 |
+
],
|
| 1185 |
+
"eval_ref_len": 8052,
|
| 1186 |
+
"eval_runtime": 106.3976,
|
| 1187 |
+
"eval_samples_per_second": 4.944,
|
| 1188 |
+
"eval_score": 52.266194224133834,
|
| 1189 |
+
"eval_steps_per_second": 0.31,
|
| 1190 |
+
"eval_sys_len": 5217,
|
| 1191 |
+
"eval_totals": [
|
| 1192 |
+
5217,
|
| 1193 |
+
4691,
|
| 1194 |
+
4165,
|
| 1195 |
+
3639
|
| 1196 |
+
],
|
| 1197 |
+
"step": 9252
|
| 1198 |
+
},
|
| 1199 |
+
{
|
| 1200 |
+
"epoch": 36.96,
|
| 1201 |
+
"learning_rate": 5.214007782101168e-06,
|
| 1202 |
+
"loss": 0.0686,
|
| 1203 |
+
"step": 9500
|
| 1204 |
+
},
|
| 1205 |
+
{
|
| 1206 |
+
"epoch": 37.0,
|
| 1207 |
+
"eval_bp": 0.5983772718445015,
|
| 1208 |
+
"eval_counts": [
|
| 1209 |
+
4899,
|
| 1210 |
+
4227,
|
| 1211 |
+
3672,
|
| 1212 |
+
3123
|
| 1213 |
+
],
|
| 1214 |
+
"eval_loss": 0.042388916015625,
|
| 1215 |
+
"eval_precisions": [
|
| 1216 |
+
92.08646616541354,
|
| 1217 |
+
88.17271589486859,
|
| 1218 |
+
86.03561387066541,
|
| 1219 |
+
83.45804382683058
|
| 1220 |
+
],
|
| 1221 |
+
"eval_ref_len": 8052,
|
| 1222 |
+
"eval_runtime": 106.906,
|
| 1223 |
+
"eval_samples_per_second": 4.92,
|
| 1224 |
+
"eval_score": 52.28705860616529,
|
| 1225 |
+
"eval_steps_per_second": 0.309,
|
| 1226 |
+
"eval_sys_len": 5320,
|
| 1227 |
+
"eval_totals": [
|
| 1228 |
+
5320,
|
| 1229 |
+
4794,
|
| 1230 |
+
4268,
|
| 1231 |
+
3742
|
| 1232 |
+
],
|
| 1233 |
+
"step": 9509
|
| 1234 |
+
},
|
| 1235 |
+
{
|
| 1236 |
+
"epoch": 38.0,
|
| 1237 |
+
"eval_bp": 0.5780101703802235,
|
| 1238 |
+
"eval_counts": [
|
| 1239 |
+
4913,
|
| 1240 |
+
4273,
|
| 1241 |
+
3718,
|
| 1242 |
+
3172
|
| 1243 |
+
],
|
| 1244 |
+
"eval_loss": 0.0394287109375,
|
| 1245 |
+
"eval_precisions": [
|
| 1246 |
+
94.46260334551047,
|
| 1247 |
+
91.40106951871658,
|
| 1248 |
+
89.61195468787659,
|
| 1249 |
+
87.55175269113994
|
| 1250 |
+
],
|
| 1251 |
+
"eval_ref_len": 8052,
|
| 1252 |
+
"eval_runtime": 106.7621,
|
| 1253 |
+
"eval_samples_per_second": 4.927,
|
| 1254 |
+
"eval_score": 52.43798269679689,
|
| 1255 |
+
"eval_steps_per_second": 0.309,
|
| 1256 |
+
"eval_sys_len": 5201,
|
| 1257 |
+
"eval_totals": [
|
| 1258 |
+
5201,
|
| 1259 |
+
4675,
|
| 1260 |
+
4149,
|
| 1261 |
+
3623
|
| 1262 |
+
],
|
| 1263 |
+
"step": 9766
|
| 1264 |
+
},
|
| 1265 |
+
{
|
| 1266 |
+
"epoch": 38.91,
|
| 1267 |
+
"learning_rate": 4.43579766536965e-06,
|
| 1268 |
+
"loss": 0.0664,
|
| 1269 |
+
"step": 10000
|
| 1270 |
+
},
|
| 1271 |
+
{
|
| 1272 |
+
"epoch": 39.0,
|
| 1273 |
+
"eval_bp": 0.5975258891581067,
|
| 1274 |
+
"eval_counts": [
|
| 1275 |
+
4912,
|
| 1276 |
+
4243,
|
| 1277 |
+
3689,
|
| 1278 |
+
3141
|
| 1279 |
+
],
|
| 1280 |
+
"eval_loss": 0.040374755859375,
|
| 1281 |
+
"eval_precisions": [
|
| 1282 |
+
92.41768579492003,
|
| 1283 |
+
88.59887241595322,
|
| 1284 |
+
86.5353037766831,
|
| 1285 |
+
84.05137811078406
|
| 1286 |
+
],
|
| 1287 |
+
"eval_ref_len": 8052,
|
| 1288 |
+
"eval_runtime": 106.9692,
|
| 1289 |
+
"eval_samples_per_second": 4.917,
|
| 1290 |
+
"eval_score": 52.491270926490635,
|
| 1291 |
+
"eval_steps_per_second": 0.309,
|
| 1292 |
+
"eval_sys_len": 5315,
|
| 1293 |
+
"eval_totals": [
|
| 1294 |
+
5315,
|
| 1295 |
+
4789,
|
| 1296 |
+
4263,
|
| 1297 |
+
3737
|
| 1298 |
+
],
|
| 1299 |
+
"step": 10023
|
| 1300 |
+
},
|
| 1301 |
+
{
|
| 1302 |
+
"epoch": 40.0,
|
| 1303 |
+
"eval_bp": 0.587279163676868,
|
| 1304 |
+
"eval_counts": [
|
| 1305 |
+
4913,
|
| 1306 |
+
4259,
|
| 1307 |
+
3711,
|
| 1308 |
+
3170
|
| 1309 |
+
],
|
| 1310 |
+
"eval_loss": 0.0382080078125,
|
| 1311 |
+
"eval_precisions": [
|
| 1312 |
+
93.4919124643197,
|
| 1313 |
+
90.0613237470924,
|
| 1314 |
+
88.29407566024268,
|
| 1315 |
+
86.21158553168344
|
| 1316 |
+
],
|
| 1317 |
+
"eval_ref_len": 8052,
|
| 1318 |
+
"eval_runtime": 107.0316,
|
| 1319 |
+
"eval_samples_per_second": 4.914,
|
| 1320 |
+
"eval_score": 52.5468859983503,
|
| 1321 |
+
"eval_steps_per_second": 0.308,
|
| 1322 |
+
"eval_sys_len": 5255,
|
| 1323 |
+
"eval_totals": [
|
| 1324 |
+
5255,
|
| 1325 |
+
4729,
|
| 1326 |
+
4203,
|
| 1327 |
+
3677
|
| 1328 |
+
],
|
| 1329 |
+
"step": 10280
|
| 1330 |
+
},
|
| 1331 |
+
{
|
| 1332 |
+
"epoch": 40.86,
|
| 1333 |
+
"learning_rate": 3.6575875486381323e-06,
|
| 1334 |
+
"loss": 0.0658,
|
| 1335 |
+
"step": 10500
|
| 1336 |
+
},
|
| 1337 |
+
{
|
| 1338 |
+
"epoch": 41.0,
|
| 1339 |
+
"eval_bp": 0.5811047209098391,
|
| 1340 |
+
"eval_counts": [
|
| 1341 |
+
4921,
|
| 1342 |
+
4278,
|
| 1343 |
+
3725,
|
| 1344 |
+
3179
|
| 1345 |
+
],
|
| 1346 |
+
"eval_loss": 0.0377197265625,
|
| 1347 |
+
"eval_precisions": [
|
| 1348 |
+
94.29009388771796,
|
| 1349 |
+
91.1570424035798,
|
| 1350 |
+
89.39284857211423,
|
| 1351 |
+
87.31117824773413
|
| 1352 |
+
],
|
| 1353 |
+
"eval_ref_len": 8052,
|
| 1354 |
+
"eval_runtime": 106.7065,
|
| 1355 |
+
"eval_samples_per_second": 4.929,
|
| 1356 |
+
"eval_score": 52.59102479681527,
|
| 1357 |
+
"eval_steps_per_second": 0.309,
|
| 1358 |
+
"eval_sys_len": 5219,
|
| 1359 |
+
"eval_totals": [
|
| 1360 |
+
5219,
|
| 1361 |
+
4693,
|
| 1362 |
+
4167,
|
| 1363 |
+
3641
|
| 1364 |
+
],
|
| 1365 |
+
"step": 10537
|
| 1366 |
+
},
|
| 1367 |
+
{
|
| 1368 |
+
"epoch": 42.0,
|
| 1369 |
+
"eval_bp": 0.5817917378355022,
|
| 1370 |
+
"eval_counts": [
|
| 1371 |
+
4908,
|
| 1372 |
+
4261,
|
| 1373 |
+
3712,
|
| 1374 |
+
3169
|
| 1375 |
+
],
|
| 1376 |
+
"eval_loss": 0.037109375,
|
| 1377 |
+
"eval_precisions": [
|
| 1378 |
+
93.96898334290637,
|
| 1379 |
+
90.7174792420694,
|
| 1380 |
+
88.99544473747302,
|
| 1381 |
+
86.94101508916324
|
| 1382 |
+
],
|
| 1383 |
+
"eval_ref_len": 8052,
|
| 1384 |
+
"eval_runtime": 107.4197,
|
| 1385 |
+
"eval_samples_per_second": 4.897,
|
| 1386 |
+
"eval_score": 52.43056600057888,
|
| 1387 |
+
"eval_steps_per_second": 0.307,
|
| 1388 |
+
"eval_sys_len": 5223,
|
| 1389 |
+
"eval_totals": [
|
| 1390 |
+
5223,
|
| 1391 |
+
4697,
|
| 1392 |
+
4171,
|
| 1393 |
+
3645
|
| 1394 |
+
],
|
| 1395 |
+
"step": 10794
|
| 1396 |
+
},
|
| 1397 |
+
{
|
| 1398 |
+
"epoch": 42.8,
|
| 1399 |
+
"learning_rate": 2.879377431906615e-06,
|
| 1400 |
+
"loss": 0.0643,
|
| 1401 |
+
"step": 11000
|
| 1402 |
+
},
|
| 1403 |
+
{
|
| 1404 |
+
"epoch": 43.0,
|
| 1405 |
+
"eval_bp": 0.5804174632159932,
|
| 1406 |
+
"eval_counts": [
|
| 1407 |
+
4905,
|
| 1408 |
+
4264,
|
| 1409 |
+
3714,
|
| 1410 |
+
3172
|
| 1411 |
+
],
|
| 1412 |
+
"eval_loss": 0.037017822265625,
|
| 1413 |
+
"eval_precisions": [
|
| 1414 |
+
94.0556088207095,
|
| 1415 |
+
90.936233738537,
|
| 1416 |
+
89.21450876771559,
|
| 1417 |
+
87.21473742095134
|
| 1418 |
+
],
|
| 1419 |
+
"eval_ref_len": 8052,
|
| 1420 |
+
"eval_runtime": 106.7676,
|
| 1421 |
+
"eval_samples_per_second": 4.927,
|
| 1422 |
+
"eval_score": 52.42364666449266,
|
| 1423 |
+
"eval_steps_per_second": 0.309,
|
| 1424 |
+
"eval_sys_len": 5215,
|
| 1425 |
+
"eval_totals": [
|
| 1426 |
+
5215,
|
| 1427 |
+
4689,
|
| 1428 |
+
4163,
|
| 1429 |
+
3637
|
| 1430 |
+
],
|
| 1431 |
+
"step": 11051
|
| 1432 |
+
},
|
| 1433 |
+
{
|
| 1434 |
+
"epoch": 44.0,
|
| 1435 |
+
"eval_bp": 0.5961628688829712,
|
| 1436 |
+
"eval_counts": [
|
| 1437 |
+
4930,
|
| 1438 |
+
4270,
|
| 1439 |
+
3718,
|
| 1440 |
+
3173
|
| 1441 |
+
],
|
| 1442 |
+
"eval_loss": 0.0380859375,
|
| 1443 |
+
"eval_precisions": [
|
| 1444 |
+
92.89617486338798,
|
| 1445 |
+
89.31185944363104,
|
| 1446 |
+
87.37955346650999,
|
| 1447 |
+
85.08983641727005
|
| 1448 |
+
],
|
| 1449 |
+
"eval_ref_len": 8052,
|
| 1450 |
+
"eval_runtime": 107.4748,
|
| 1451 |
+
"eval_samples_per_second": 4.894,
|
| 1452 |
+
"eval_score": 52.834006019511406,
|
| 1453 |
+
"eval_steps_per_second": 0.307,
|
| 1454 |
+
"eval_sys_len": 5307,
|
| 1455 |
+
"eval_totals": [
|
| 1456 |
+
5307,
|
| 1457 |
+
4781,
|
| 1458 |
+
4255,
|
| 1459 |
+
3729
|
| 1460 |
+
],
|
| 1461 |
+
"step": 11308
|
| 1462 |
+
},
|
| 1463 |
+
{
|
| 1464 |
+
"epoch": 44.75,
|
| 1465 |
+
"learning_rate": 2.1011673151750974e-06,
|
| 1466 |
+
"loss": 0.0608,
|
| 1467 |
+
"step": 11500
|
| 1468 |
+
},
|
| 1469 |
+
{
|
| 1470 |
+
"epoch": 45.0,
|
| 1471 |
+
"eval_bp": 0.5757722034899391,
|
| 1472 |
+
"eval_counts": [
|
| 1473 |
+
4915,
|
| 1474 |
+
4280,
|
| 1475 |
+
3729,
|
| 1476 |
+
3186
|
| 1477 |
+
],
|
| 1478 |
+
"eval_loss": 0.036224365234375,
|
| 1479 |
+
"eval_precisions": [
|
| 1480 |
+
94.7378565921357,
|
| 1481 |
+
91.8060918060918,
|
| 1482 |
+
90.15957446808511,
|
| 1483 |
+
88.25484764542936
|
| 1484 |
+
],
|
| 1485 |
+
"eval_ref_len": 8052,
|
| 1486 |
+
"eval_runtime": 107.743,
|
| 1487 |
+
"eval_samples_per_second": 4.882,
|
| 1488 |
+
"eval_score": 52.515446703245765,
|
| 1489 |
+
"eval_steps_per_second": 0.306,
|
| 1490 |
+
"eval_sys_len": 5188,
|
| 1491 |
+
"eval_totals": [
|
| 1492 |
+
5188,
|
| 1493 |
+
4662,
|
| 1494 |
+
4136,
|
| 1495 |
+
3610
|
| 1496 |
+
],
|
| 1497 |
+
"step": 11565
|
| 1498 |
+
},
|
| 1499 |
+
{
|
| 1500 |
+
"epoch": 46.0,
|
| 1501 |
+
"eval_bp": 0.5843659009664612,
|
| 1502 |
+
"eval_counts": [
|
| 1503 |
+
4924,
|
| 1504 |
+
4278,
|
| 1505 |
+
3730,
|
| 1506 |
+
3188
|
| 1507 |
+
],
|
| 1508 |
+
"eval_loss": 0.036651611328125,
|
| 1509 |
+
"eval_precisions": [
|
| 1510 |
+
94.0053455517373,
|
| 1511 |
+
90.78947368421052,
|
| 1512 |
+
89.10654562828476,
|
| 1513 |
+
87.10382513661202
|
| 1514 |
+
],
|
| 1515 |
+
"eval_ref_len": 8052,
|
| 1516 |
+
"eval_runtime": 107.889,
|
| 1517 |
+
"eval_samples_per_second": 4.875,
|
| 1518 |
+
"eval_score": 52.71917275684773,
|
| 1519 |
+
"eval_steps_per_second": 0.306,
|
| 1520 |
+
"eval_sys_len": 5238,
|
| 1521 |
+
"eval_totals": [
|
| 1522 |
+
5238,
|
| 1523 |
+
4712,
|
| 1524 |
+
4186,
|
| 1525 |
+
3660
|
| 1526 |
+
],
|
| 1527 |
+
"step": 11822
|
| 1528 |
+
},
|
| 1529 |
+
{
|
| 1530 |
+
"epoch": 46.69,
|
| 1531 |
+
"learning_rate": 1.32295719844358e-06,
|
| 1532 |
+
"loss": 0.0622,
|
| 1533 |
+
"step": 12000
|
| 1534 |
+
},
|
| 1535 |
+
{
|
| 1536 |
+
"epoch": 47.0,
|
| 1537 |
+
"eval_bp": 0.586080116901772,
|
| 1538 |
+
"eval_counts": [
|
| 1539 |
+
4938,
|
| 1540 |
+
4295,
|
| 1541 |
+
3745,
|
| 1542 |
+
3201
|
| 1543 |
+
],
|
| 1544 |
+
"eval_loss": 0.036529541015625,
|
| 1545 |
+
"eval_precisions": [
|
| 1546 |
+
94.09298780487805,
|
| 1547 |
+
90.95722151630665,
|
| 1548 |
+
89.2516682554814,
|
| 1549 |
+
87.22070844686648
|
| 1550 |
+
],
|
| 1551 |
+
"eval_ref_len": 8052,
|
| 1552 |
+
"eval_runtime": 109.2986,
|
| 1553 |
+
"eval_samples_per_second": 4.813,
|
| 1554 |
+
"eval_score": 52.949832085516945,
|
| 1555 |
+
"eval_steps_per_second": 0.302,
|
| 1556 |
+
"eval_sys_len": 5248,
|
| 1557 |
+
"eval_totals": [
|
| 1558 |
+
5248,
|
| 1559 |
+
4722,
|
| 1560 |
+
4196,
|
| 1561 |
+
3670
|
| 1562 |
+
],
|
| 1563 |
+
"step": 12079
|
| 1564 |
+
},
|
| 1565 |
+
{
|
| 1566 |
+
"epoch": 48.0,
|
| 1567 |
+
"eval_bp": 0.5817917378355022,
|
| 1568 |
+
"eval_counts": [
|
| 1569 |
+
4925,
|
| 1570 |
+
4285,
|
| 1571 |
+
3733,
|
| 1572 |
+
3189
|
| 1573 |
+
],
|
| 1574 |
+
"eval_loss": 0.036285400390625,
|
| 1575 |
+
"eval_precisions": [
|
| 1576 |
+
94.29446678154318,
|
| 1577 |
+
91.22844368746009,
|
| 1578 |
+
89.49892112203308,
|
| 1579 |
+
87.48971193415638
|
| 1580 |
+
],
|
| 1581 |
+
"eval_ref_len": 8052,
|
| 1582 |
+
"eval_runtime": 108.6659,
|
| 1583 |
+
"eval_samples_per_second": 4.841,
|
| 1584 |
+
"eval_score": 52.70664408353883,
|
| 1585 |
+
"eval_steps_per_second": 0.304,
|
| 1586 |
+
"eval_sys_len": 5223,
|
| 1587 |
+
"eval_totals": [
|
| 1588 |
+
5223,
|
| 1589 |
+
4697,
|
| 1590 |
+
4171,
|
| 1591 |
+
3645
|
| 1592 |
+
],
|
| 1593 |
+
"step": 12336
|
| 1594 |
+
},
|
| 1595 |
+
{
|
| 1596 |
+
"epoch": 48.64,
|
| 1597 |
+
"learning_rate": 5.447470817120623e-07,
|
| 1598 |
+
"loss": 0.0625,
|
| 1599 |
+
"step": 12500
|
| 1600 |
+
}
|
| 1601 |
+
],
|
| 1602 |
+
"logging_steps": 500,
|
| 1603 |
+
"max_steps": 12850,
|
| 1604 |
+
"num_input_tokens_seen": 0,
|
| 1605 |
+
"num_train_epochs": 50,
|
| 1606 |
+
"save_steps": 500,
|
| 1607 |
+
"total_flos": 8.680648839008256e+16,
|
| 1608 |
+
"train_batch_size": 16,
|
| 1609 |
+
"trial_name": null,
|
| 1610 |
+
"trial_params": null
|
| 1611 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9add047de4104f794046934855a2514b4a1093ca88adf93227e43bed1b56d6fd
|
| 3 |
+
size 4856
|