Task: SequenceClassification
Browse files- .gitattributes +1 -0
- README.md +202 -0
- adapter_config.json +38 -0
- adapter_model.safetensors +3 -0
- special_tokens_map.json +28 -0
- tokenizer.json +3 -0
- tokenizer.model +3 -0
- tokenizer_config.json +1757 -0
- trainer_state-gemma-bf16-QLORA-super_glue-rte-sequence_classification.json +2602 -0
- training_args.bin +3 -0
.gitattributes
CHANGED
|
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
README.md
ADDED
|
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: peft
|
| 3 |
+
base_model: google/gemma-7b-it
|
| 4 |
+
---
|
| 5 |
+
|
| 6 |
+
# Model Card for Model ID
|
| 7 |
+
|
| 8 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
| 9 |
+
|
| 10 |
+
|
| 11 |
+
|
| 12 |
+
## Model Details
|
| 13 |
+
|
| 14 |
+
### Model Description
|
| 15 |
+
|
| 16 |
+
<!-- Provide a longer summary of what this model is. -->
|
| 17 |
+
|
| 18 |
+
|
| 19 |
+
|
| 20 |
+
- **Developed by:** [More Information Needed]
|
| 21 |
+
- **Funded by [optional]:** [More Information Needed]
|
| 22 |
+
- **Shared by [optional]:** [More Information Needed]
|
| 23 |
+
- **Model type:** [More Information Needed]
|
| 24 |
+
- **Language(s) (NLP):** [More Information Needed]
|
| 25 |
+
- **License:** [More Information Needed]
|
| 26 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
| 27 |
+
|
| 28 |
+
### Model Sources [optional]
|
| 29 |
+
|
| 30 |
+
<!-- Provide the basic links for the model. -->
|
| 31 |
+
|
| 32 |
+
- **Repository:** [More Information Needed]
|
| 33 |
+
- **Paper [optional]:** [More Information Needed]
|
| 34 |
+
- **Demo [optional]:** [More Information Needed]
|
| 35 |
+
|
| 36 |
+
## Uses
|
| 37 |
+
|
| 38 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
| 39 |
+
|
| 40 |
+
### Direct Use
|
| 41 |
+
|
| 42 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
| 43 |
+
|
| 44 |
+
[More Information Needed]
|
| 45 |
+
|
| 46 |
+
### Downstream Use [optional]
|
| 47 |
+
|
| 48 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
| 49 |
+
|
| 50 |
+
[More Information Needed]
|
| 51 |
+
|
| 52 |
+
### Out-of-Scope Use
|
| 53 |
+
|
| 54 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
| 55 |
+
|
| 56 |
+
[More Information Needed]
|
| 57 |
+
|
| 58 |
+
## Bias, Risks, and Limitations
|
| 59 |
+
|
| 60 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
| 61 |
+
|
| 62 |
+
[More Information Needed]
|
| 63 |
+
|
| 64 |
+
### Recommendations
|
| 65 |
+
|
| 66 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
| 67 |
+
|
| 68 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
| 69 |
+
|
| 70 |
+
## How to Get Started with the Model
|
| 71 |
+
|
| 72 |
+
Use the code below to get started with the model.
|
| 73 |
+
|
| 74 |
+
[More Information Needed]
|
| 75 |
+
|
| 76 |
+
## Training Details
|
| 77 |
+
|
| 78 |
+
### Training Data
|
| 79 |
+
|
| 80 |
+
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
| 81 |
+
|
| 82 |
+
[More Information Needed]
|
| 83 |
+
|
| 84 |
+
### Training Procedure
|
| 85 |
+
|
| 86 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
| 87 |
+
|
| 88 |
+
#### Preprocessing [optional]
|
| 89 |
+
|
| 90 |
+
[More Information Needed]
|
| 91 |
+
|
| 92 |
+
|
| 93 |
+
#### Training Hyperparameters
|
| 94 |
+
|
| 95 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
| 96 |
+
|
| 97 |
+
#### Speeds, Sizes, Times [optional]
|
| 98 |
+
|
| 99 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
| 100 |
+
|
| 101 |
+
[More Information Needed]
|
| 102 |
+
|
| 103 |
+
## Evaluation
|
| 104 |
+
|
| 105 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
| 106 |
+
|
| 107 |
+
### Testing Data, Factors & Metrics
|
| 108 |
+
|
| 109 |
+
#### Testing Data
|
| 110 |
+
|
| 111 |
+
<!-- This should link to a Dataset Card if possible. -->
|
| 112 |
+
|
| 113 |
+
[More Information Needed]
|
| 114 |
+
|
| 115 |
+
#### Factors
|
| 116 |
+
|
| 117 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
| 118 |
+
|
| 119 |
+
[More Information Needed]
|
| 120 |
+
|
| 121 |
+
#### Metrics
|
| 122 |
+
|
| 123 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
| 124 |
+
|
| 125 |
+
[More Information Needed]
|
| 126 |
+
|
| 127 |
+
### Results
|
| 128 |
+
|
| 129 |
+
[More Information Needed]
|
| 130 |
+
|
| 131 |
+
#### Summary
|
| 132 |
+
|
| 133 |
+
|
| 134 |
+
|
| 135 |
+
## Model Examination [optional]
|
| 136 |
+
|
| 137 |
+
<!-- Relevant interpretability work for the model goes here -->
|
| 138 |
+
|
| 139 |
+
[More Information Needed]
|
| 140 |
+
|
| 141 |
+
## Environmental Impact
|
| 142 |
+
|
| 143 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
| 144 |
+
|
| 145 |
+
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
| 146 |
+
|
| 147 |
+
- **Hardware Type:** [More Information Needed]
|
| 148 |
+
- **Hours used:** [More Information Needed]
|
| 149 |
+
- **Cloud Provider:** [More Information Needed]
|
| 150 |
+
- **Compute Region:** [More Information Needed]
|
| 151 |
+
- **Carbon Emitted:** [More Information Needed]
|
| 152 |
+
|
| 153 |
+
## Technical Specifications [optional]
|
| 154 |
+
|
| 155 |
+
### Model Architecture and Objective
|
| 156 |
+
|
| 157 |
+
[More Information Needed]
|
| 158 |
+
|
| 159 |
+
### Compute Infrastructure
|
| 160 |
+
|
| 161 |
+
[More Information Needed]
|
| 162 |
+
|
| 163 |
+
#### Hardware
|
| 164 |
+
|
| 165 |
+
[More Information Needed]
|
| 166 |
+
|
| 167 |
+
#### Software
|
| 168 |
+
|
| 169 |
+
[More Information Needed]
|
| 170 |
+
|
| 171 |
+
## Citation [optional]
|
| 172 |
+
|
| 173 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
| 174 |
+
|
| 175 |
+
**BibTeX:**
|
| 176 |
+
|
| 177 |
+
[More Information Needed]
|
| 178 |
+
|
| 179 |
+
**APA:**
|
| 180 |
+
|
| 181 |
+
[More Information Needed]
|
| 182 |
+
|
| 183 |
+
## Glossary [optional]
|
| 184 |
+
|
| 185 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
| 186 |
+
|
| 187 |
+
[More Information Needed]
|
| 188 |
+
|
| 189 |
+
## More Information [optional]
|
| 190 |
+
|
| 191 |
+
[More Information Needed]
|
| 192 |
+
|
| 193 |
+
## Model Card Authors [optional]
|
| 194 |
+
|
| 195 |
+
[More Information Needed]
|
| 196 |
+
|
| 197 |
+
## Model Card Contact
|
| 198 |
+
|
| 199 |
+
[More Information Needed]
|
| 200 |
+
### Framework versions
|
| 201 |
+
|
| 202 |
+
- PEFT 0.11.1
|
adapter_config.json
ADDED
|
@@ -0,0 +1,38 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "google/gemma-7b-it",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"fan_in_fan_out": false,
|
| 7 |
+
"inference_mode": true,
|
| 8 |
+
"init_lora_weights": true,
|
| 9 |
+
"layer_replication": null,
|
| 10 |
+
"layers_pattern": null,
|
| 11 |
+
"layers_to_transform": null,
|
| 12 |
+
"loftq_config": {},
|
| 13 |
+
"lora_alpha": 32,
|
| 14 |
+
"lora_dropout": 0.1,
|
| 15 |
+
"megatron_config": null,
|
| 16 |
+
"megatron_core": "megatron.core",
|
| 17 |
+
"modules_to_save": [
|
| 18 |
+
"score",
|
| 19 |
+
"classifier",
|
| 20 |
+
"score"
|
| 21 |
+
],
|
| 22 |
+
"peft_type": "LORA",
|
| 23 |
+
"r": 8,
|
| 24 |
+
"rank_pattern": {},
|
| 25 |
+
"revision": null,
|
| 26 |
+
"target_modules": [
|
| 27 |
+
"k_proj",
|
| 28 |
+
"gate_proj",
|
| 29 |
+
"up_proj",
|
| 30 |
+
"q_proj",
|
| 31 |
+
"o_proj",
|
| 32 |
+
"down_proj",
|
| 33 |
+
"v_proj"
|
| 34 |
+
],
|
| 35 |
+
"task_type": "SEQ_CLS",
|
| 36 |
+
"use_dora": false,
|
| 37 |
+
"use_rslora": false
|
| 38 |
+
}
|
adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7641b6a549500dff53108d6005c1ba4ddf3a47e1d99092ce70144c917dd4a4d4
|
| 3 |
+
size 50068480
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<start_of_turn>",
|
| 4 |
+
"<end_of_turn>"
|
| 5 |
+
],
|
| 6 |
+
"bos_token": {
|
| 7 |
+
"content": "<bos>",
|
| 8 |
+
"lstrip": false,
|
| 9 |
+
"normalized": false,
|
| 10 |
+
"rstrip": false,
|
| 11 |
+
"single_word": false
|
| 12 |
+
},
|
| 13 |
+
"eos_token": {
|
| 14 |
+
"content": "<eos>",
|
| 15 |
+
"lstrip": false,
|
| 16 |
+
"normalized": false,
|
| 17 |
+
"rstrip": false,
|
| 18 |
+
"single_word": false
|
| 19 |
+
},
|
| 20 |
+
"pad_token": "<eos>",
|
| 21 |
+
"unk_token": {
|
| 22 |
+
"content": "<unk>",
|
| 23 |
+
"lstrip": false,
|
| 24 |
+
"normalized": false,
|
| 25 |
+
"rstrip": false,
|
| 26 |
+
"single_word": false
|
| 27 |
+
}
|
| 28 |
+
}
|
tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7da53ca29fb16f6b2489482fc0bc6a394162cdab14d12764a1755ebc583fea79
|
| 3 |
+
size 17518525
|
tokenizer.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:61a7b147390c64585d6c3543dd6fc636906c9af3865a5548f27f31aee1d4c8e2
|
| 3 |
+
size 4241003
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,1757 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": true,
|
| 3 |
+
"add_eos_token": false,
|
| 4 |
+
"added_tokens_decoder": {
|
| 5 |
+
"0": {
|
| 6 |
+
"content": "<pad>",
|
| 7 |
+
"lstrip": false,
|
| 8 |
+
"normalized": false,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false,
|
| 11 |
+
"special": true
|
| 12 |
+
},
|
| 13 |
+
"1": {
|
| 14 |
+
"content": "<eos>",
|
| 15 |
+
"lstrip": false,
|
| 16 |
+
"normalized": false,
|
| 17 |
+
"rstrip": false,
|
| 18 |
+
"single_word": false,
|
| 19 |
+
"special": true
|
| 20 |
+
},
|
| 21 |
+
"2": {
|
| 22 |
+
"content": "<bos>",
|
| 23 |
+
"lstrip": false,
|
| 24 |
+
"normalized": false,
|
| 25 |
+
"rstrip": false,
|
| 26 |
+
"single_word": false,
|
| 27 |
+
"special": true
|
| 28 |
+
},
|
| 29 |
+
"3": {
|
| 30 |
+
"content": "<unk>",
|
| 31 |
+
"lstrip": false,
|
| 32 |
+
"normalized": false,
|
| 33 |
+
"rstrip": false,
|
| 34 |
+
"single_word": false,
|
| 35 |
+
"special": true
|
| 36 |
+
},
|
| 37 |
+
"4": {
|
| 38 |
+
"content": "<mask>",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": false,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false,
|
| 43 |
+
"special": false
|
| 44 |
+
},
|
| 45 |
+
"5": {
|
| 46 |
+
"content": "<2mass>",
|
| 47 |
+
"lstrip": false,
|
| 48 |
+
"normalized": false,
|
| 49 |
+
"rstrip": false,
|
| 50 |
+
"single_word": false,
|
| 51 |
+
"special": false
|
| 52 |
+
},
|
| 53 |
+
"6": {
|
| 54 |
+
"content": "[@BOS@]",
|
| 55 |
+
"lstrip": false,
|
| 56 |
+
"normalized": false,
|
| 57 |
+
"rstrip": false,
|
| 58 |
+
"single_word": false,
|
| 59 |
+
"special": false
|
| 60 |
+
},
|
| 61 |
+
"7": {
|
| 62 |
+
"content": "<unused0>",
|
| 63 |
+
"lstrip": false,
|
| 64 |
+
"normalized": false,
|
| 65 |
+
"rstrip": false,
|
| 66 |
+
"single_word": false,
|
| 67 |
+
"special": false
|
| 68 |
+
},
|
| 69 |
+
"8": {
|
| 70 |
+
"content": "<unused1>",
|
| 71 |
+
"lstrip": false,
|
| 72 |
+
"normalized": false,
|
| 73 |
+
"rstrip": false,
|
| 74 |
+
"single_word": false,
|
| 75 |
+
"special": false
|
| 76 |
+
},
|
| 77 |
+
"9": {
|
| 78 |
+
"content": "<unused2>",
|
| 79 |
+
"lstrip": false,
|
| 80 |
+
"normalized": false,
|
| 81 |
+
"rstrip": false,
|
| 82 |
+
"single_word": false,
|
| 83 |
+
"special": false
|
| 84 |
+
},
|
| 85 |
+
"10": {
|
| 86 |
+
"content": "<unused3>",
|
| 87 |
+
"lstrip": false,
|
| 88 |
+
"normalized": false,
|
| 89 |
+
"rstrip": false,
|
| 90 |
+
"single_word": false,
|
| 91 |
+
"special": false
|
| 92 |
+
},
|
| 93 |
+
"11": {
|
| 94 |
+
"content": "<unused4>",
|
| 95 |
+
"lstrip": false,
|
| 96 |
+
"normalized": false,
|
| 97 |
+
"rstrip": false,
|
| 98 |
+
"single_word": false,
|
| 99 |
+
"special": false
|
| 100 |
+
},
|
| 101 |
+
"12": {
|
| 102 |
+
"content": "<unused5>",
|
| 103 |
+
"lstrip": false,
|
| 104 |
+
"normalized": false,
|
| 105 |
+
"rstrip": false,
|
| 106 |
+
"single_word": false,
|
| 107 |
+
"special": false
|
| 108 |
+
},
|
| 109 |
+
"13": {
|
| 110 |
+
"content": "<unused6>",
|
| 111 |
+
"lstrip": false,
|
| 112 |
+
"normalized": false,
|
| 113 |
+
"rstrip": false,
|
| 114 |
+
"single_word": false,
|
| 115 |
+
"special": false
|
| 116 |
+
},
|
| 117 |
+
"14": {
|
| 118 |
+
"content": "<unused7>",
|
| 119 |
+
"lstrip": false,
|
| 120 |
+
"normalized": false,
|
| 121 |
+
"rstrip": false,
|
| 122 |
+
"single_word": false,
|
| 123 |
+
"special": false
|
| 124 |
+
},
|
| 125 |
+
"15": {
|
| 126 |
+
"content": "<unused8>",
|
| 127 |
+
"lstrip": false,
|
| 128 |
+
"normalized": false,
|
| 129 |
+
"rstrip": false,
|
| 130 |
+
"single_word": false,
|
| 131 |
+
"special": false
|
| 132 |
+
},
|
| 133 |
+
"16": {
|
| 134 |
+
"content": "<unused9>",
|
| 135 |
+
"lstrip": false,
|
| 136 |
+
"normalized": false,
|
| 137 |
+
"rstrip": false,
|
| 138 |
+
"single_word": false,
|
| 139 |
+
"special": false
|
| 140 |
+
},
|
| 141 |
+
"17": {
|
| 142 |
+
"content": "<unused10>",
|
| 143 |
+
"lstrip": false,
|
| 144 |
+
"normalized": false,
|
| 145 |
+
"rstrip": false,
|
| 146 |
+
"single_word": false,
|
| 147 |
+
"special": false
|
| 148 |
+
},
|
| 149 |
+
"18": {
|
| 150 |
+
"content": "<unused11>",
|
| 151 |
+
"lstrip": false,
|
| 152 |
+
"normalized": false,
|
| 153 |
+
"rstrip": false,
|
| 154 |
+
"single_word": false,
|
| 155 |
+
"special": false
|
| 156 |
+
},
|
| 157 |
+
"19": {
|
| 158 |
+
"content": "<unused12>",
|
| 159 |
+
"lstrip": false,
|
| 160 |
+
"normalized": false,
|
| 161 |
+
"rstrip": false,
|
| 162 |
+
"single_word": false,
|
| 163 |
+
"special": false
|
| 164 |
+
},
|
| 165 |
+
"20": {
|
| 166 |
+
"content": "<unused13>",
|
| 167 |
+
"lstrip": false,
|
| 168 |
+
"normalized": false,
|
| 169 |
+
"rstrip": false,
|
| 170 |
+
"single_word": false,
|
| 171 |
+
"special": false
|
| 172 |
+
},
|
| 173 |
+
"21": {
|
| 174 |
+
"content": "<unused14>",
|
| 175 |
+
"lstrip": false,
|
| 176 |
+
"normalized": false,
|
| 177 |
+
"rstrip": false,
|
| 178 |
+
"single_word": false,
|
| 179 |
+
"special": false
|
| 180 |
+
},
|
| 181 |
+
"22": {
|
| 182 |
+
"content": "<unused15>",
|
| 183 |
+
"lstrip": false,
|
| 184 |
+
"normalized": false,
|
| 185 |
+
"rstrip": false,
|
| 186 |
+
"single_word": false,
|
| 187 |
+
"special": false
|
| 188 |
+
},
|
| 189 |
+
"23": {
|
| 190 |
+
"content": "<unused16>",
|
| 191 |
+
"lstrip": false,
|
| 192 |
+
"normalized": false,
|
| 193 |
+
"rstrip": false,
|
| 194 |
+
"single_word": false,
|
| 195 |
+
"special": false
|
| 196 |
+
},
|
| 197 |
+
"24": {
|
| 198 |
+
"content": "<unused17>",
|
| 199 |
+
"lstrip": false,
|
| 200 |
+
"normalized": false,
|
| 201 |
+
"rstrip": false,
|
| 202 |
+
"single_word": false,
|
| 203 |
+
"special": false
|
| 204 |
+
},
|
| 205 |
+
"25": {
|
| 206 |
+
"content": "<unused18>",
|
| 207 |
+
"lstrip": false,
|
| 208 |
+
"normalized": false,
|
| 209 |
+
"rstrip": false,
|
| 210 |
+
"single_word": false,
|
| 211 |
+
"special": false
|
| 212 |
+
},
|
| 213 |
+
"26": {
|
| 214 |
+
"content": "<unused19>",
|
| 215 |
+
"lstrip": false,
|
| 216 |
+
"normalized": false,
|
| 217 |
+
"rstrip": false,
|
| 218 |
+
"single_word": false,
|
| 219 |
+
"special": false
|
| 220 |
+
},
|
| 221 |
+
"27": {
|
| 222 |
+
"content": "<unused20>",
|
| 223 |
+
"lstrip": false,
|
| 224 |
+
"normalized": false,
|
| 225 |
+
"rstrip": false,
|
| 226 |
+
"single_word": false,
|
| 227 |
+
"special": false
|
| 228 |
+
},
|
| 229 |
+
"28": {
|
| 230 |
+
"content": "<unused21>",
|
| 231 |
+
"lstrip": false,
|
| 232 |
+
"normalized": false,
|
| 233 |
+
"rstrip": false,
|
| 234 |
+
"single_word": false,
|
| 235 |
+
"special": false
|
| 236 |
+
},
|
| 237 |
+
"29": {
|
| 238 |
+
"content": "<unused22>",
|
| 239 |
+
"lstrip": false,
|
| 240 |
+
"normalized": false,
|
| 241 |
+
"rstrip": false,
|
| 242 |
+
"single_word": false,
|
| 243 |
+
"special": false
|
| 244 |
+
},
|
| 245 |
+
"30": {
|
| 246 |
+
"content": "<unused23>",
|
| 247 |
+
"lstrip": false,
|
| 248 |
+
"normalized": false,
|
| 249 |
+
"rstrip": false,
|
| 250 |
+
"single_word": false,
|
| 251 |
+
"special": false
|
| 252 |
+
},
|
| 253 |
+
"31": {
|
| 254 |
+
"content": "<unused24>",
|
| 255 |
+
"lstrip": false,
|
| 256 |
+
"normalized": false,
|
| 257 |
+
"rstrip": false,
|
| 258 |
+
"single_word": false,
|
| 259 |
+
"special": false
|
| 260 |
+
},
|
| 261 |
+
"32": {
|
| 262 |
+
"content": "<unused25>",
|
| 263 |
+
"lstrip": false,
|
| 264 |
+
"normalized": false,
|
| 265 |
+
"rstrip": false,
|
| 266 |
+
"single_word": false,
|
| 267 |
+
"special": false
|
| 268 |
+
},
|
| 269 |
+
"33": {
|
| 270 |
+
"content": "<unused26>",
|
| 271 |
+
"lstrip": false,
|
| 272 |
+
"normalized": false,
|
| 273 |
+
"rstrip": false,
|
| 274 |
+
"single_word": false,
|
| 275 |
+
"special": false
|
| 276 |
+
},
|
| 277 |
+
"34": {
|
| 278 |
+
"content": "<unused27>",
|
| 279 |
+
"lstrip": false,
|
| 280 |
+
"normalized": false,
|
| 281 |
+
"rstrip": false,
|
| 282 |
+
"single_word": false,
|
| 283 |
+
"special": false
|
| 284 |
+
},
|
| 285 |
+
"35": {
|
| 286 |
+
"content": "<unused28>",
|
| 287 |
+
"lstrip": false,
|
| 288 |
+
"normalized": false,
|
| 289 |
+
"rstrip": false,
|
| 290 |
+
"single_word": false,
|
| 291 |
+
"special": false
|
| 292 |
+
},
|
| 293 |
+
"36": {
|
| 294 |
+
"content": "<unused29>",
|
| 295 |
+
"lstrip": false,
|
| 296 |
+
"normalized": false,
|
| 297 |
+
"rstrip": false,
|
| 298 |
+
"single_word": false,
|
| 299 |
+
"special": false
|
| 300 |
+
},
|
| 301 |
+
"37": {
|
| 302 |
+
"content": "<unused30>",
|
| 303 |
+
"lstrip": false,
|
| 304 |
+
"normalized": false,
|
| 305 |
+
"rstrip": false,
|
| 306 |
+
"single_word": false,
|
| 307 |
+
"special": false
|
| 308 |
+
},
|
| 309 |
+
"38": {
|
| 310 |
+
"content": "<unused31>",
|
| 311 |
+
"lstrip": false,
|
| 312 |
+
"normalized": false,
|
| 313 |
+
"rstrip": false,
|
| 314 |
+
"single_word": false,
|
| 315 |
+
"special": false
|
| 316 |
+
},
|
| 317 |
+
"39": {
|
| 318 |
+
"content": "<unused32>",
|
| 319 |
+
"lstrip": false,
|
| 320 |
+
"normalized": false,
|
| 321 |
+
"rstrip": false,
|
| 322 |
+
"single_word": false,
|
| 323 |
+
"special": false
|
| 324 |
+
},
|
| 325 |
+
"40": {
|
| 326 |
+
"content": "<unused33>",
|
| 327 |
+
"lstrip": false,
|
| 328 |
+
"normalized": false,
|
| 329 |
+
"rstrip": false,
|
| 330 |
+
"single_word": false,
|
| 331 |
+
"special": false
|
| 332 |
+
},
|
| 333 |
+
"41": {
|
| 334 |
+
"content": "<unused34>",
|
| 335 |
+
"lstrip": false,
|
| 336 |
+
"normalized": false,
|
| 337 |
+
"rstrip": false,
|
| 338 |
+
"single_word": false,
|
| 339 |
+
"special": false
|
| 340 |
+
},
|
| 341 |
+
"42": {
|
| 342 |
+
"content": "<unused35>",
|
| 343 |
+
"lstrip": false,
|
| 344 |
+
"normalized": false,
|
| 345 |
+
"rstrip": false,
|
| 346 |
+
"single_word": false,
|
| 347 |
+
"special": false
|
| 348 |
+
},
|
| 349 |
+
"43": {
|
| 350 |
+
"content": "<unused36>",
|
| 351 |
+
"lstrip": false,
|
| 352 |
+
"normalized": false,
|
| 353 |
+
"rstrip": false,
|
| 354 |
+
"single_word": false,
|
| 355 |
+
"special": false
|
| 356 |
+
},
|
| 357 |
+
"44": {
|
| 358 |
+
"content": "<unused37>",
|
| 359 |
+
"lstrip": false,
|
| 360 |
+
"normalized": false,
|
| 361 |
+
"rstrip": false,
|
| 362 |
+
"single_word": false,
|
| 363 |
+
"special": false
|
| 364 |
+
},
|
| 365 |
+
"45": {
|
| 366 |
+
"content": "<unused38>",
|
| 367 |
+
"lstrip": false,
|
| 368 |
+
"normalized": false,
|
| 369 |
+
"rstrip": false,
|
| 370 |
+
"single_word": false,
|
| 371 |
+
"special": false
|
| 372 |
+
},
|
| 373 |
+
"46": {
|
| 374 |
+
"content": "<unused39>",
|
| 375 |
+
"lstrip": false,
|
| 376 |
+
"normalized": false,
|
| 377 |
+
"rstrip": false,
|
| 378 |
+
"single_word": false,
|
| 379 |
+
"special": false
|
| 380 |
+
},
|
| 381 |
+
"47": {
|
| 382 |
+
"content": "<unused40>",
|
| 383 |
+
"lstrip": false,
|
| 384 |
+
"normalized": false,
|
| 385 |
+
"rstrip": false,
|
| 386 |
+
"single_word": false,
|
| 387 |
+
"special": false
|
| 388 |
+
},
|
| 389 |
+
"48": {
|
| 390 |
+
"content": "<unused41>",
|
| 391 |
+
"lstrip": false,
|
| 392 |
+
"normalized": false,
|
| 393 |
+
"rstrip": false,
|
| 394 |
+
"single_word": false,
|
| 395 |
+
"special": false
|
| 396 |
+
},
|
| 397 |
+
"49": {
|
| 398 |
+
"content": "<unused42>",
|
| 399 |
+
"lstrip": false,
|
| 400 |
+
"normalized": false,
|
| 401 |
+
"rstrip": false,
|
| 402 |
+
"single_word": false,
|
| 403 |
+
"special": false
|
| 404 |
+
},
|
| 405 |
+
"50": {
|
| 406 |
+
"content": "<unused43>",
|
| 407 |
+
"lstrip": false,
|
| 408 |
+
"normalized": false,
|
| 409 |
+
"rstrip": false,
|
| 410 |
+
"single_word": false,
|
| 411 |
+
"special": false
|
| 412 |
+
},
|
| 413 |
+
"51": {
|
| 414 |
+
"content": "<unused44>",
|
| 415 |
+
"lstrip": false,
|
| 416 |
+
"normalized": false,
|
| 417 |
+
"rstrip": false,
|
| 418 |
+
"single_word": false,
|
| 419 |
+
"special": false
|
| 420 |
+
},
|
| 421 |
+
"52": {
|
| 422 |
+
"content": "<unused45>",
|
| 423 |
+
"lstrip": false,
|
| 424 |
+
"normalized": false,
|
| 425 |
+
"rstrip": false,
|
| 426 |
+
"single_word": false,
|
| 427 |
+
"special": false
|
| 428 |
+
},
|
| 429 |
+
"53": {
|
| 430 |
+
"content": "<unused46>",
|
| 431 |
+
"lstrip": false,
|
| 432 |
+
"normalized": false,
|
| 433 |
+
"rstrip": false,
|
| 434 |
+
"single_word": false,
|
| 435 |
+
"special": false
|
| 436 |
+
},
|
| 437 |
+
"54": {
|
| 438 |
+
"content": "<unused47>",
|
| 439 |
+
"lstrip": false,
|
| 440 |
+
"normalized": false,
|
| 441 |
+
"rstrip": false,
|
| 442 |
+
"single_word": false,
|
| 443 |
+
"special": false
|
| 444 |
+
},
|
| 445 |
+
"55": {
|
| 446 |
+
"content": "<unused48>",
|
| 447 |
+
"lstrip": false,
|
| 448 |
+
"normalized": false,
|
| 449 |
+
"rstrip": false,
|
| 450 |
+
"single_word": false,
|
| 451 |
+
"special": false
|
| 452 |
+
},
|
| 453 |
+
"56": {
|
| 454 |
+
"content": "<unused49>",
|
| 455 |
+
"lstrip": false,
|
| 456 |
+
"normalized": false,
|
| 457 |
+
"rstrip": false,
|
| 458 |
+
"single_word": false,
|
| 459 |
+
"special": false
|
| 460 |
+
},
|
| 461 |
+
"57": {
|
| 462 |
+
"content": "<unused50>",
|
| 463 |
+
"lstrip": false,
|
| 464 |
+
"normalized": false,
|
| 465 |
+
"rstrip": false,
|
| 466 |
+
"single_word": false,
|
| 467 |
+
"special": false
|
| 468 |
+
},
|
| 469 |
+
"58": {
|
| 470 |
+
"content": "<unused51>",
|
| 471 |
+
"lstrip": false,
|
| 472 |
+
"normalized": false,
|
| 473 |
+
"rstrip": false,
|
| 474 |
+
"single_word": false,
|
| 475 |
+
"special": false
|
| 476 |
+
},
|
| 477 |
+
"59": {
|
| 478 |
+
"content": "<unused52>",
|
| 479 |
+
"lstrip": false,
|
| 480 |
+
"normalized": false,
|
| 481 |
+
"rstrip": false,
|
| 482 |
+
"single_word": false,
|
| 483 |
+
"special": false
|
| 484 |
+
},
|
| 485 |
+
"60": {
|
| 486 |
+
"content": "<unused53>",
|
| 487 |
+
"lstrip": false,
|
| 488 |
+
"normalized": false,
|
| 489 |
+
"rstrip": false,
|
| 490 |
+
"single_word": false,
|
| 491 |
+
"special": false
|
| 492 |
+
},
|
| 493 |
+
"61": {
|
| 494 |
+
"content": "<unused54>",
|
| 495 |
+
"lstrip": false,
|
| 496 |
+
"normalized": false,
|
| 497 |
+
"rstrip": false,
|
| 498 |
+
"single_word": false,
|
| 499 |
+
"special": false
|
| 500 |
+
},
|
| 501 |
+
"62": {
|
| 502 |
+
"content": "<unused55>",
|
| 503 |
+
"lstrip": false,
|
| 504 |
+
"normalized": false,
|
| 505 |
+
"rstrip": false,
|
| 506 |
+
"single_word": false,
|
| 507 |
+
"special": false
|
| 508 |
+
},
|
| 509 |
+
"63": {
|
| 510 |
+
"content": "<unused56>",
|
| 511 |
+
"lstrip": false,
|
| 512 |
+
"normalized": false,
|
| 513 |
+
"rstrip": false,
|
| 514 |
+
"single_word": false,
|
| 515 |
+
"special": false
|
| 516 |
+
},
|
| 517 |
+
"64": {
|
| 518 |
+
"content": "<unused57>",
|
| 519 |
+
"lstrip": false,
|
| 520 |
+
"normalized": false,
|
| 521 |
+
"rstrip": false,
|
| 522 |
+
"single_word": false,
|
| 523 |
+
"special": false
|
| 524 |
+
},
|
| 525 |
+
"65": {
|
| 526 |
+
"content": "<unused58>",
|
| 527 |
+
"lstrip": false,
|
| 528 |
+
"normalized": false,
|
| 529 |
+
"rstrip": false,
|
| 530 |
+
"single_word": false,
|
| 531 |
+
"special": false
|
| 532 |
+
},
|
| 533 |
+
"66": {
|
| 534 |
+
"content": "<unused59>",
|
| 535 |
+
"lstrip": false,
|
| 536 |
+
"normalized": false,
|
| 537 |
+
"rstrip": false,
|
| 538 |
+
"single_word": false,
|
| 539 |
+
"special": false
|
| 540 |
+
},
|
| 541 |
+
"67": {
|
| 542 |
+
"content": "<unused60>",
|
| 543 |
+
"lstrip": false,
|
| 544 |
+
"normalized": false,
|
| 545 |
+
"rstrip": false,
|
| 546 |
+
"single_word": false,
|
| 547 |
+
"special": false
|
| 548 |
+
},
|
| 549 |
+
"68": {
|
| 550 |
+
"content": "<unused61>",
|
| 551 |
+
"lstrip": false,
|
| 552 |
+
"normalized": false,
|
| 553 |
+
"rstrip": false,
|
| 554 |
+
"single_word": false,
|
| 555 |
+
"special": false
|
| 556 |
+
},
|
| 557 |
+
"69": {
|
| 558 |
+
"content": "<unused62>",
|
| 559 |
+
"lstrip": false,
|
| 560 |
+
"normalized": false,
|
| 561 |
+
"rstrip": false,
|
| 562 |
+
"single_word": false,
|
| 563 |
+
"special": false
|
| 564 |
+
},
|
| 565 |
+
"70": {
|
| 566 |
+
"content": "<unused63>",
|
| 567 |
+
"lstrip": false,
|
| 568 |
+
"normalized": false,
|
| 569 |
+
"rstrip": false,
|
| 570 |
+
"single_word": false,
|
| 571 |
+
"special": false
|
| 572 |
+
},
|
| 573 |
+
"71": {
|
| 574 |
+
"content": "<unused64>",
|
| 575 |
+
"lstrip": false,
|
| 576 |
+
"normalized": false,
|
| 577 |
+
"rstrip": false,
|
| 578 |
+
"single_word": false,
|
| 579 |
+
"special": false
|
| 580 |
+
},
|
| 581 |
+
"72": {
|
| 582 |
+
"content": "<unused65>",
|
| 583 |
+
"lstrip": false,
|
| 584 |
+
"normalized": false,
|
| 585 |
+
"rstrip": false,
|
| 586 |
+
"single_word": false,
|
| 587 |
+
"special": false
|
| 588 |
+
},
|
| 589 |
+
"73": {
|
| 590 |
+
"content": "<unused66>",
|
| 591 |
+
"lstrip": false,
|
| 592 |
+
"normalized": false,
|
| 593 |
+
"rstrip": false,
|
| 594 |
+
"single_word": false,
|
| 595 |
+
"special": false
|
| 596 |
+
},
|
| 597 |
+
"74": {
|
| 598 |
+
"content": "<unused67>",
|
| 599 |
+
"lstrip": false,
|
| 600 |
+
"normalized": false,
|
| 601 |
+
"rstrip": false,
|
| 602 |
+
"single_word": false,
|
| 603 |
+
"special": false
|
| 604 |
+
},
|
| 605 |
+
"75": {
|
| 606 |
+
"content": "<unused68>",
|
| 607 |
+
"lstrip": false,
|
| 608 |
+
"normalized": false,
|
| 609 |
+
"rstrip": false,
|
| 610 |
+
"single_word": false,
|
| 611 |
+
"special": false
|
| 612 |
+
},
|
| 613 |
+
"76": {
|
| 614 |
+
"content": "<unused69>",
|
| 615 |
+
"lstrip": false,
|
| 616 |
+
"normalized": false,
|
| 617 |
+
"rstrip": false,
|
| 618 |
+
"single_word": false,
|
| 619 |
+
"special": false
|
| 620 |
+
},
|
| 621 |
+
"77": {
|
| 622 |
+
"content": "<unused70>",
|
| 623 |
+
"lstrip": false,
|
| 624 |
+
"normalized": false,
|
| 625 |
+
"rstrip": false,
|
| 626 |
+
"single_word": false,
|
| 627 |
+
"special": false
|
| 628 |
+
},
|
| 629 |
+
"78": {
|
| 630 |
+
"content": "<unused71>",
|
| 631 |
+
"lstrip": false,
|
| 632 |
+
"normalized": false,
|
| 633 |
+
"rstrip": false,
|
| 634 |
+
"single_word": false,
|
| 635 |
+
"special": false
|
| 636 |
+
},
|
| 637 |
+
"79": {
|
| 638 |
+
"content": "<unused72>",
|
| 639 |
+
"lstrip": false,
|
| 640 |
+
"normalized": false,
|
| 641 |
+
"rstrip": false,
|
| 642 |
+
"single_word": false,
|
| 643 |
+
"special": false
|
| 644 |
+
},
|
| 645 |
+
"80": {
|
| 646 |
+
"content": "<unused73>",
|
| 647 |
+
"lstrip": false,
|
| 648 |
+
"normalized": false,
|
| 649 |
+
"rstrip": false,
|
| 650 |
+
"single_word": false,
|
| 651 |
+
"special": false
|
| 652 |
+
},
|
| 653 |
+
"81": {
|
| 654 |
+
"content": "<unused74>",
|
| 655 |
+
"lstrip": false,
|
| 656 |
+
"normalized": false,
|
| 657 |
+
"rstrip": false,
|
| 658 |
+
"single_word": false,
|
| 659 |
+
"special": false
|
| 660 |
+
},
|
| 661 |
+
"82": {
|
| 662 |
+
"content": "<unused75>",
|
| 663 |
+
"lstrip": false,
|
| 664 |
+
"normalized": false,
|
| 665 |
+
"rstrip": false,
|
| 666 |
+
"single_word": false,
|
| 667 |
+
"special": false
|
| 668 |
+
},
|
| 669 |
+
"83": {
|
| 670 |
+
"content": "<unused76>",
|
| 671 |
+
"lstrip": false,
|
| 672 |
+
"normalized": false,
|
| 673 |
+
"rstrip": false,
|
| 674 |
+
"single_word": false,
|
| 675 |
+
"special": false
|
| 676 |
+
},
|
| 677 |
+
"84": {
|
| 678 |
+
"content": "<unused77>",
|
| 679 |
+
"lstrip": false,
|
| 680 |
+
"normalized": false,
|
| 681 |
+
"rstrip": false,
|
| 682 |
+
"single_word": false,
|
| 683 |
+
"special": false
|
| 684 |
+
},
|
| 685 |
+
"85": {
|
| 686 |
+
"content": "<unused78>",
|
| 687 |
+
"lstrip": false,
|
| 688 |
+
"normalized": false,
|
| 689 |
+
"rstrip": false,
|
| 690 |
+
"single_word": false,
|
| 691 |
+
"special": false
|
| 692 |
+
},
|
| 693 |
+
"86": {
|
| 694 |
+
"content": "<unused79>",
|
| 695 |
+
"lstrip": false,
|
| 696 |
+
"normalized": false,
|
| 697 |
+
"rstrip": false,
|
| 698 |
+
"single_word": false,
|
| 699 |
+
"special": false
|
| 700 |
+
},
|
| 701 |
+
"87": {
|
| 702 |
+
"content": "<unused80>",
|
| 703 |
+
"lstrip": false,
|
| 704 |
+
"normalized": false,
|
| 705 |
+
"rstrip": false,
|
| 706 |
+
"single_word": false,
|
| 707 |
+
"special": false
|
| 708 |
+
},
|
| 709 |
+
"88": {
|
| 710 |
+
"content": "<unused81>",
|
| 711 |
+
"lstrip": false,
|
| 712 |
+
"normalized": false,
|
| 713 |
+
"rstrip": false,
|
| 714 |
+
"single_word": false,
|
| 715 |
+
"special": false
|
| 716 |
+
},
|
| 717 |
+
"89": {
|
| 718 |
+
"content": "<unused82>",
|
| 719 |
+
"lstrip": false,
|
| 720 |
+
"normalized": false,
|
| 721 |
+
"rstrip": false,
|
| 722 |
+
"single_word": false,
|
| 723 |
+
"special": false
|
| 724 |
+
},
|
| 725 |
+
"90": {
|
| 726 |
+
"content": "<unused83>",
|
| 727 |
+
"lstrip": false,
|
| 728 |
+
"normalized": false,
|
| 729 |
+
"rstrip": false,
|
| 730 |
+
"single_word": false,
|
| 731 |
+
"special": false
|
| 732 |
+
},
|
| 733 |
+
"91": {
|
| 734 |
+
"content": "<unused84>",
|
| 735 |
+
"lstrip": false,
|
| 736 |
+
"normalized": false,
|
| 737 |
+
"rstrip": false,
|
| 738 |
+
"single_word": false,
|
| 739 |
+
"special": false
|
| 740 |
+
},
|
| 741 |
+
"92": {
|
| 742 |
+
"content": "<unused85>",
|
| 743 |
+
"lstrip": false,
|
| 744 |
+
"normalized": false,
|
| 745 |
+
"rstrip": false,
|
| 746 |
+
"single_word": false,
|
| 747 |
+
"special": false
|
| 748 |
+
},
|
| 749 |
+
"93": {
|
| 750 |
+
"content": "<unused86>",
|
| 751 |
+
"lstrip": false,
|
| 752 |
+
"normalized": false,
|
| 753 |
+
"rstrip": false,
|
| 754 |
+
"single_word": false,
|
| 755 |
+
"special": false
|
| 756 |
+
},
|
| 757 |
+
"94": {
|
| 758 |
+
"content": "<unused87>",
|
| 759 |
+
"lstrip": false,
|
| 760 |
+
"normalized": false,
|
| 761 |
+
"rstrip": false,
|
| 762 |
+
"single_word": false,
|
| 763 |
+
"special": false
|
| 764 |
+
},
|
| 765 |
+
"95": {
|
| 766 |
+
"content": "<unused88>",
|
| 767 |
+
"lstrip": false,
|
| 768 |
+
"normalized": false,
|
| 769 |
+
"rstrip": false,
|
| 770 |
+
"single_word": false,
|
| 771 |
+
"special": false
|
| 772 |
+
},
|
| 773 |
+
"96": {
|
| 774 |
+
"content": "<unused89>",
|
| 775 |
+
"lstrip": false,
|
| 776 |
+
"normalized": false,
|
| 777 |
+
"rstrip": false,
|
| 778 |
+
"single_word": false,
|
| 779 |
+
"special": false
|
| 780 |
+
},
|
| 781 |
+
"97": {
|
| 782 |
+
"content": "<unused90>",
|
| 783 |
+
"lstrip": false,
|
| 784 |
+
"normalized": false,
|
| 785 |
+
"rstrip": false,
|
| 786 |
+
"single_word": false,
|
| 787 |
+
"special": false
|
| 788 |
+
},
|
| 789 |
+
"98": {
|
| 790 |
+
"content": "<unused91>",
|
| 791 |
+
"lstrip": false,
|
| 792 |
+
"normalized": false,
|
| 793 |
+
"rstrip": false,
|
| 794 |
+
"single_word": false,
|
| 795 |
+
"special": false
|
| 796 |
+
},
|
| 797 |
+
"99": {
|
| 798 |
+
"content": "<unused92>",
|
| 799 |
+
"lstrip": false,
|
| 800 |
+
"normalized": false,
|
| 801 |
+
"rstrip": false,
|
| 802 |
+
"single_word": false,
|
| 803 |
+
"special": false
|
| 804 |
+
},
|
| 805 |
+
"100": {
|
| 806 |
+
"content": "<unused93>",
|
| 807 |
+
"lstrip": false,
|
| 808 |
+
"normalized": false,
|
| 809 |
+
"rstrip": false,
|
| 810 |
+
"single_word": false,
|
| 811 |
+
"special": false
|
| 812 |
+
},
|
| 813 |
+
"101": {
|
| 814 |
+
"content": "<unused94>",
|
| 815 |
+
"lstrip": false,
|
| 816 |
+
"normalized": false,
|
| 817 |
+
"rstrip": false,
|
| 818 |
+
"single_word": false,
|
| 819 |
+
"special": false
|
| 820 |
+
},
|
| 821 |
+
"102": {
|
| 822 |
+
"content": "<unused95>",
|
| 823 |
+
"lstrip": false,
|
| 824 |
+
"normalized": false,
|
| 825 |
+
"rstrip": false,
|
| 826 |
+
"single_word": false,
|
| 827 |
+
"special": false
|
| 828 |
+
},
|
| 829 |
+
"103": {
|
| 830 |
+
"content": "<unused96>",
|
| 831 |
+
"lstrip": false,
|
| 832 |
+
"normalized": false,
|
| 833 |
+
"rstrip": false,
|
| 834 |
+
"single_word": false,
|
| 835 |
+
"special": false
|
| 836 |
+
},
|
| 837 |
+
"104": {
|
| 838 |
+
"content": "<unused97>",
|
| 839 |
+
"lstrip": false,
|
| 840 |
+
"normalized": false,
|
| 841 |
+
"rstrip": false,
|
| 842 |
+
"single_word": false,
|
| 843 |
+
"special": false
|
| 844 |
+
},
|
| 845 |
+
"105": {
|
| 846 |
+
"content": "<unused98>",
|
| 847 |
+
"lstrip": false,
|
| 848 |
+
"normalized": false,
|
| 849 |
+
"rstrip": false,
|
| 850 |
+
"single_word": false,
|
| 851 |
+
"special": false
|
| 852 |
+
},
|
| 853 |
+
"106": {
|
| 854 |
+
"content": "<start_of_turn>",
|
| 855 |
+
"lstrip": false,
|
| 856 |
+
"normalized": false,
|
| 857 |
+
"rstrip": false,
|
| 858 |
+
"single_word": false,
|
| 859 |
+
"special": true
|
| 860 |
+
},
|
| 861 |
+
"107": {
|
| 862 |
+
"content": "<end_of_turn>",
|
| 863 |
+
"lstrip": false,
|
| 864 |
+
"normalized": false,
|
| 865 |
+
"rstrip": false,
|
| 866 |
+
"single_word": false,
|
| 867 |
+
"special": true
|
| 868 |
+
},
|
| 869 |
+
"108": {
|
| 870 |
+
"content": "\n",
|
| 871 |
+
"lstrip": false,
|
| 872 |
+
"normalized": false,
|
| 873 |
+
"rstrip": false,
|
| 874 |
+
"single_word": false,
|
| 875 |
+
"special": false
|
| 876 |
+
},
|
| 877 |
+
"109": {
|
| 878 |
+
"content": "\n\n",
|
| 879 |
+
"lstrip": false,
|
| 880 |
+
"normalized": false,
|
| 881 |
+
"rstrip": false,
|
| 882 |
+
"single_word": false,
|
| 883 |
+
"special": false
|
| 884 |
+
},
|
| 885 |
+
"110": {
|
| 886 |
+
"content": "\n\n\n",
|
| 887 |
+
"lstrip": false,
|
| 888 |
+
"normalized": false,
|
| 889 |
+
"rstrip": false,
|
| 890 |
+
"single_word": false,
|
| 891 |
+
"special": false
|
| 892 |
+
},
|
| 893 |
+
"111": {
|
| 894 |
+
"content": "\n\n\n\n",
|
| 895 |
+
"lstrip": false,
|
| 896 |
+
"normalized": false,
|
| 897 |
+
"rstrip": false,
|
| 898 |
+
"single_word": false,
|
| 899 |
+
"special": false
|
| 900 |
+
},
|
| 901 |
+
"112": {
|
| 902 |
+
"content": "\n\n\n\n\n",
|
| 903 |
+
"lstrip": false,
|
| 904 |
+
"normalized": false,
|
| 905 |
+
"rstrip": false,
|
| 906 |
+
"single_word": false,
|
| 907 |
+
"special": false
|
| 908 |
+
},
|
| 909 |
+
"113": {
|
| 910 |
+
"content": "\n\n\n\n\n\n",
|
| 911 |
+
"lstrip": false,
|
| 912 |
+
"normalized": false,
|
| 913 |
+
"rstrip": false,
|
| 914 |
+
"single_word": false,
|
| 915 |
+
"special": false
|
| 916 |
+
},
|
| 917 |
+
"114": {
|
| 918 |
+
"content": "\n\n\n\n\n\n\n",
|
| 919 |
+
"lstrip": false,
|
| 920 |
+
"normalized": false,
|
| 921 |
+
"rstrip": false,
|
| 922 |
+
"single_word": false,
|
| 923 |
+
"special": false
|
| 924 |
+
},
|
| 925 |
+
"115": {
|
| 926 |
+
"content": "\n\n\n\n\n\n\n\n",
|
| 927 |
+
"lstrip": false,
|
| 928 |
+
"normalized": false,
|
| 929 |
+
"rstrip": false,
|
| 930 |
+
"single_word": false,
|
| 931 |
+
"special": false
|
| 932 |
+
},
|
| 933 |
+
"116": {
|
| 934 |
+
"content": "\n\n\n\n\n\n\n\n\n",
|
| 935 |
+
"lstrip": false,
|
| 936 |
+
"normalized": false,
|
| 937 |
+
"rstrip": false,
|
| 938 |
+
"single_word": false,
|
| 939 |
+
"special": false
|
| 940 |
+
},
|
| 941 |
+
"117": {
|
| 942 |
+
"content": "\n\n\n\n\n\n\n\n\n\n",
|
| 943 |
+
"lstrip": false,
|
| 944 |
+
"normalized": false,
|
| 945 |
+
"rstrip": false,
|
| 946 |
+
"single_word": false,
|
| 947 |
+
"special": false
|
| 948 |
+
},
|
| 949 |
+
"118": {
|
| 950 |
+
"content": "\n\n\n\n\n\n\n\n\n\n\n",
|
| 951 |
+
"lstrip": false,
|
| 952 |
+
"normalized": false,
|
| 953 |
+
"rstrip": false,
|
| 954 |
+
"single_word": false,
|
| 955 |
+
"special": false
|
| 956 |
+
},
|
| 957 |
+
"119": {
|
| 958 |
+
"content": "\n\n\n\n\n\n\n\n\n\n\n\n",
|
| 959 |
+
"lstrip": false,
|
| 960 |
+
"normalized": false,
|
| 961 |
+
"rstrip": false,
|
| 962 |
+
"single_word": false,
|
| 963 |
+
"special": false
|
| 964 |
+
},
|
| 965 |
+
"120": {
|
| 966 |
+
"content": "\n\n\n\n\n\n\n\n\n\n\n\n\n",
|
| 967 |
+
"lstrip": false,
|
| 968 |
+
"normalized": false,
|
| 969 |
+
"rstrip": false,
|
| 970 |
+
"single_word": false,
|
| 971 |
+
"special": false
|
| 972 |
+
},
|
| 973 |
+
"121": {
|
| 974 |
+
"content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
|
| 975 |
+
"lstrip": false,
|
| 976 |
+
"normalized": false,
|
| 977 |
+
"rstrip": false,
|
| 978 |
+
"single_word": false,
|
| 979 |
+
"special": false
|
| 980 |
+
},
|
| 981 |
+
"122": {
|
| 982 |
+
"content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
|
| 983 |
+
"lstrip": false,
|
| 984 |
+
"normalized": false,
|
| 985 |
+
"rstrip": false,
|
| 986 |
+
"single_word": false,
|
| 987 |
+
"special": false
|
| 988 |
+
},
|
| 989 |
+
"123": {
|
| 990 |
+
"content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
|
| 991 |
+
"lstrip": false,
|
| 992 |
+
"normalized": false,
|
| 993 |
+
"rstrip": false,
|
| 994 |
+
"single_word": false,
|
| 995 |
+
"special": false
|
| 996 |
+
},
|
| 997 |
+
"124": {
|
| 998 |
+
"content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
|
| 999 |
+
"lstrip": false,
|
| 1000 |
+
"normalized": false,
|
| 1001 |
+
"rstrip": false,
|
| 1002 |
+
"single_word": false,
|
| 1003 |
+
"special": false
|
| 1004 |
+
},
|
| 1005 |
+
"125": {
|
| 1006 |
+
"content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
|
| 1007 |
+
"lstrip": false,
|
| 1008 |
+
"normalized": false,
|
| 1009 |
+
"rstrip": false,
|
| 1010 |
+
"single_word": false,
|
| 1011 |
+
"special": false
|
| 1012 |
+
},
|
| 1013 |
+
"126": {
|
| 1014 |
+
"content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
|
| 1015 |
+
"lstrip": false,
|
| 1016 |
+
"normalized": false,
|
| 1017 |
+
"rstrip": false,
|
| 1018 |
+
"single_word": false,
|
| 1019 |
+
"special": false
|
| 1020 |
+
},
|
| 1021 |
+
"127": {
|
| 1022 |
+
"content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
|
| 1023 |
+
"lstrip": false,
|
| 1024 |
+
"normalized": false,
|
| 1025 |
+
"rstrip": false,
|
| 1026 |
+
"single_word": false,
|
| 1027 |
+
"special": false
|
| 1028 |
+
},
|
| 1029 |
+
"128": {
|
| 1030 |
+
"content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
|
| 1031 |
+
"lstrip": false,
|
| 1032 |
+
"normalized": false,
|
| 1033 |
+
"rstrip": false,
|
| 1034 |
+
"single_word": false,
|
| 1035 |
+
"special": false
|
| 1036 |
+
},
|
| 1037 |
+
"129": {
|
| 1038 |
+
"content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
|
| 1039 |
+
"lstrip": false,
|
| 1040 |
+
"normalized": false,
|
| 1041 |
+
"rstrip": false,
|
| 1042 |
+
"single_word": false,
|
| 1043 |
+
"special": false
|
| 1044 |
+
},
|
| 1045 |
+
"130": {
|
| 1046 |
+
"content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
|
| 1047 |
+
"lstrip": false,
|
| 1048 |
+
"normalized": false,
|
| 1049 |
+
"rstrip": false,
|
| 1050 |
+
"single_word": false,
|
| 1051 |
+
"special": false
|
| 1052 |
+
},
|
| 1053 |
+
"131": {
|
| 1054 |
+
"content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
|
| 1055 |
+
"lstrip": false,
|
| 1056 |
+
"normalized": false,
|
| 1057 |
+
"rstrip": false,
|
| 1058 |
+
"single_word": false,
|
| 1059 |
+
"special": false
|
| 1060 |
+
},
|
| 1061 |
+
"132": {
|
| 1062 |
+
"content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
|
| 1063 |
+
"lstrip": false,
|
| 1064 |
+
"normalized": false,
|
| 1065 |
+
"rstrip": false,
|
| 1066 |
+
"single_word": false,
|
| 1067 |
+
"special": false
|
| 1068 |
+
},
|
| 1069 |
+
"133": {
|
| 1070 |
+
"content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
|
| 1071 |
+
"lstrip": false,
|
| 1072 |
+
"normalized": false,
|
| 1073 |
+
"rstrip": false,
|
| 1074 |
+
"single_word": false,
|
| 1075 |
+
"special": false
|
| 1076 |
+
},
|
| 1077 |
+
"134": {
|
| 1078 |
+
"content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
|
| 1079 |
+
"lstrip": false,
|
| 1080 |
+
"normalized": false,
|
| 1081 |
+
"rstrip": false,
|
| 1082 |
+
"single_word": false,
|
| 1083 |
+
"special": false
|
| 1084 |
+
},
|
| 1085 |
+
"135": {
|
| 1086 |
+
"content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
|
| 1087 |
+
"lstrip": false,
|
| 1088 |
+
"normalized": false,
|
| 1089 |
+
"rstrip": false,
|
| 1090 |
+
"single_word": false,
|
| 1091 |
+
"special": false
|
| 1092 |
+
},
|
| 1093 |
+
"136": {
|
| 1094 |
+
"content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
|
| 1095 |
+
"lstrip": false,
|
| 1096 |
+
"normalized": false,
|
| 1097 |
+
"rstrip": false,
|
| 1098 |
+
"single_word": false,
|
| 1099 |
+
"special": false
|
| 1100 |
+
},
|
| 1101 |
+
"137": {
|
| 1102 |
+
"content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
|
| 1103 |
+
"lstrip": false,
|
| 1104 |
+
"normalized": false,
|
| 1105 |
+
"rstrip": false,
|
| 1106 |
+
"single_word": false,
|
| 1107 |
+
"special": false
|
| 1108 |
+
},
|
| 1109 |
+
"138": {
|
| 1110 |
+
"content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
|
| 1111 |
+
"lstrip": false,
|
| 1112 |
+
"normalized": false,
|
| 1113 |
+
"rstrip": false,
|
| 1114 |
+
"single_word": false,
|
| 1115 |
+
"special": false
|
| 1116 |
+
},
|
| 1117 |
+
"139": {
|
| 1118 |
+
"content": "▁▁",
|
| 1119 |
+
"lstrip": false,
|
| 1120 |
+
"normalized": false,
|
| 1121 |
+
"rstrip": false,
|
| 1122 |
+
"single_word": false,
|
| 1123 |
+
"special": false
|
| 1124 |
+
},
|
| 1125 |
+
"140": {
|
| 1126 |
+
"content": "▁▁▁",
|
| 1127 |
+
"lstrip": false,
|
| 1128 |
+
"normalized": false,
|
| 1129 |
+
"rstrip": false,
|
| 1130 |
+
"single_word": false,
|
| 1131 |
+
"special": false
|
| 1132 |
+
},
|
| 1133 |
+
"141": {
|
| 1134 |
+
"content": "▁▁▁▁",
|
| 1135 |
+
"lstrip": false,
|
| 1136 |
+
"normalized": false,
|
| 1137 |
+
"rstrip": false,
|
| 1138 |
+
"single_word": false,
|
| 1139 |
+
"special": false
|
| 1140 |
+
},
|
| 1141 |
+
"142": {
|
| 1142 |
+
"content": "▁▁▁▁▁",
|
| 1143 |
+
"lstrip": false,
|
| 1144 |
+
"normalized": false,
|
| 1145 |
+
"rstrip": false,
|
| 1146 |
+
"single_word": false,
|
| 1147 |
+
"special": false
|
| 1148 |
+
},
|
| 1149 |
+
"143": {
|
| 1150 |
+
"content": "▁▁▁▁▁▁",
|
| 1151 |
+
"lstrip": false,
|
| 1152 |
+
"normalized": false,
|
| 1153 |
+
"rstrip": false,
|
| 1154 |
+
"single_word": false,
|
| 1155 |
+
"special": false
|
| 1156 |
+
},
|
| 1157 |
+
"144": {
|
| 1158 |
+
"content": "▁▁▁▁▁▁▁",
|
| 1159 |
+
"lstrip": false,
|
| 1160 |
+
"normalized": false,
|
| 1161 |
+
"rstrip": false,
|
| 1162 |
+
"single_word": false,
|
| 1163 |
+
"special": false
|
| 1164 |
+
},
|
| 1165 |
+
"145": {
|
| 1166 |
+
"content": "▁▁▁▁▁▁▁▁",
|
| 1167 |
+
"lstrip": false,
|
| 1168 |
+
"normalized": false,
|
| 1169 |
+
"rstrip": false,
|
| 1170 |
+
"single_word": false,
|
| 1171 |
+
"special": false
|
| 1172 |
+
},
|
| 1173 |
+
"146": {
|
| 1174 |
+
"content": "▁▁▁▁▁▁▁▁▁",
|
| 1175 |
+
"lstrip": false,
|
| 1176 |
+
"normalized": false,
|
| 1177 |
+
"rstrip": false,
|
| 1178 |
+
"single_word": false,
|
| 1179 |
+
"special": false
|
| 1180 |
+
},
|
| 1181 |
+
"147": {
|
| 1182 |
+
"content": "▁▁▁▁▁▁▁▁▁▁",
|
| 1183 |
+
"lstrip": false,
|
| 1184 |
+
"normalized": false,
|
| 1185 |
+
"rstrip": false,
|
| 1186 |
+
"single_word": false,
|
| 1187 |
+
"special": false
|
| 1188 |
+
},
|
| 1189 |
+
"148": {
|
| 1190 |
+
"content": "▁▁▁▁▁▁▁▁▁▁▁",
|
| 1191 |
+
"lstrip": false,
|
| 1192 |
+
"normalized": false,
|
| 1193 |
+
"rstrip": false,
|
| 1194 |
+
"single_word": false,
|
| 1195 |
+
"special": false
|
| 1196 |
+
},
|
| 1197 |
+
"149": {
|
| 1198 |
+
"content": "▁▁▁▁▁▁▁▁▁▁▁▁",
|
| 1199 |
+
"lstrip": false,
|
| 1200 |
+
"normalized": false,
|
| 1201 |
+
"rstrip": false,
|
| 1202 |
+
"single_word": false,
|
| 1203 |
+
"special": false
|
| 1204 |
+
},
|
| 1205 |
+
"150": {
|
| 1206 |
+
"content": "▁▁▁▁▁▁▁▁▁▁▁▁▁",
|
| 1207 |
+
"lstrip": false,
|
| 1208 |
+
"normalized": false,
|
| 1209 |
+
"rstrip": false,
|
| 1210 |
+
"single_word": false,
|
| 1211 |
+
"special": false
|
| 1212 |
+
},
|
| 1213 |
+
"151": {
|
| 1214 |
+
"content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
|
| 1215 |
+
"lstrip": false,
|
| 1216 |
+
"normalized": false,
|
| 1217 |
+
"rstrip": false,
|
| 1218 |
+
"single_word": false,
|
| 1219 |
+
"special": false
|
| 1220 |
+
},
|
| 1221 |
+
"152": {
|
| 1222 |
+
"content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
|
| 1223 |
+
"lstrip": false,
|
| 1224 |
+
"normalized": false,
|
| 1225 |
+
"rstrip": false,
|
| 1226 |
+
"single_word": false,
|
| 1227 |
+
"special": false
|
| 1228 |
+
},
|
| 1229 |
+
"153": {
|
| 1230 |
+
"content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
|
| 1231 |
+
"lstrip": false,
|
| 1232 |
+
"normalized": false,
|
| 1233 |
+
"rstrip": false,
|
| 1234 |
+
"single_word": false,
|
| 1235 |
+
"special": false
|
| 1236 |
+
},
|
| 1237 |
+
"154": {
|
| 1238 |
+
"content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
|
| 1239 |
+
"lstrip": false,
|
| 1240 |
+
"normalized": false,
|
| 1241 |
+
"rstrip": false,
|
| 1242 |
+
"single_word": false,
|
| 1243 |
+
"special": false
|
| 1244 |
+
},
|
| 1245 |
+
"155": {
|
| 1246 |
+
"content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
|
| 1247 |
+
"lstrip": false,
|
| 1248 |
+
"normalized": false,
|
| 1249 |
+
"rstrip": false,
|
| 1250 |
+
"single_word": false,
|
| 1251 |
+
"special": false
|
| 1252 |
+
},
|
| 1253 |
+
"156": {
|
| 1254 |
+
"content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
|
| 1255 |
+
"lstrip": false,
|
| 1256 |
+
"normalized": false,
|
| 1257 |
+
"rstrip": false,
|
| 1258 |
+
"single_word": false,
|
| 1259 |
+
"special": false
|
| 1260 |
+
},
|
| 1261 |
+
"157": {
|
| 1262 |
+
"content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
|
| 1263 |
+
"lstrip": false,
|
| 1264 |
+
"normalized": false,
|
| 1265 |
+
"rstrip": false,
|
| 1266 |
+
"single_word": false,
|
| 1267 |
+
"special": false
|
| 1268 |
+
},
|
| 1269 |
+
"158": {
|
| 1270 |
+
"content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
|
| 1271 |
+
"lstrip": false,
|
| 1272 |
+
"normalized": false,
|
| 1273 |
+
"rstrip": false,
|
| 1274 |
+
"single_word": false,
|
| 1275 |
+
"special": false
|
| 1276 |
+
},
|
| 1277 |
+
"159": {
|
| 1278 |
+
"content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
|
| 1279 |
+
"lstrip": false,
|
| 1280 |
+
"normalized": false,
|
| 1281 |
+
"rstrip": false,
|
| 1282 |
+
"single_word": false,
|
| 1283 |
+
"special": false
|
| 1284 |
+
},
|
| 1285 |
+
"160": {
|
| 1286 |
+
"content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
|
| 1287 |
+
"lstrip": false,
|
| 1288 |
+
"normalized": false,
|
| 1289 |
+
"rstrip": false,
|
| 1290 |
+
"single_word": false,
|
| 1291 |
+
"special": false
|
| 1292 |
+
},
|
| 1293 |
+
"161": {
|
| 1294 |
+
"content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
|
| 1295 |
+
"lstrip": false,
|
| 1296 |
+
"normalized": false,
|
| 1297 |
+
"rstrip": false,
|
| 1298 |
+
"single_word": false,
|
| 1299 |
+
"special": false
|
| 1300 |
+
},
|
| 1301 |
+
"162": {
|
| 1302 |
+
"content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
|
| 1303 |
+
"lstrip": false,
|
| 1304 |
+
"normalized": false,
|
| 1305 |
+
"rstrip": false,
|
| 1306 |
+
"single_word": false,
|
| 1307 |
+
"special": false
|
| 1308 |
+
},
|
| 1309 |
+
"163": {
|
| 1310 |
+
"content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
|
| 1311 |
+
"lstrip": false,
|
| 1312 |
+
"normalized": false,
|
| 1313 |
+
"rstrip": false,
|
| 1314 |
+
"single_word": false,
|
| 1315 |
+
"special": false
|
| 1316 |
+
},
|
| 1317 |
+
"164": {
|
| 1318 |
+
"content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
|
| 1319 |
+
"lstrip": false,
|
| 1320 |
+
"normalized": false,
|
| 1321 |
+
"rstrip": false,
|
| 1322 |
+
"single_word": false,
|
| 1323 |
+
"special": false
|
| 1324 |
+
},
|
| 1325 |
+
"165": {
|
| 1326 |
+
"content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
|
| 1327 |
+
"lstrip": false,
|
| 1328 |
+
"normalized": false,
|
| 1329 |
+
"rstrip": false,
|
| 1330 |
+
"single_word": false,
|
| 1331 |
+
"special": false
|
| 1332 |
+
},
|
| 1333 |
+
"166": {
|
| 1334 |
+
"content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
|
| 1335 |
+
"lstrip": false,
|
| 1336 |
+
"normalized": false,
|
| 1337 |
+
"rstrip": false,
|
| 1338 |
+
"single_word": false,
|
| 1339 |
+
"special": false
|
| 1340 |
+
},
|
| 1341 |
+
"167": {
|
| 1342 |
+
"content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
|
| 1343 |
+
"lstrip": false,
|
| 1344 |
+
"normalized": false,
|
| 1345 |
+
"rstrip": false,
|
| 1346 |
+
"single_word": false,
|
| 1347 |
+
"special": false
|
| 1348 |
+
},
|
| 1349 |
+
"168": {
|
| 1350 |
+
"content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
|
| 1351 |
+
"lstrip": false,
|
| 1352 |
+
"normalized": false,
|
| 1353 |
+
"rstrip": false,
|
| 1354 |
+
"single_word": false,
|
| 1355 |
+
"special": false
|
| 1356 |
+
},
|
| 1357 |
+
"169": {
|
| 1358 |
+
"content": "<table>",
|
| 1359 |
+
"lstrip": false,
|
| 1360 |
+
"normalized": false,
|
| 1361 |
+
"rstrip": false,
|
| 1362 |
+
"single_word": false,
|
| 1363 |
+
"special": false
|
| 1364 |
+
},
|
| 1365 |
+
"170": {
|
| 1366 |
+
"content": "<caption>",
|
| 1367 |
+
"lstrip": false,
|
| 1368 |
+
"normalized": false,
|
| 1369 |
+
"rstrip": false,
|
| 1370 |
+
"single_word": false,
|
| 1371 |
+
"special": false
|
| 1372 |
+
},
|
| 1373 |
+
"171": {
|
| 1374 |
+
"content": "<thead>",
|
| 1375 |
+
"lstrip": false,
|
| 1376 |
+
"normalized": false,
|
| 1377 |
+
"rstrip": false,
|
| 1378 |
+
"single_word": false,
|
| 1379 |
+
"special": false
|
| 1380 |
+
},
|
| 1381 |
+
"172": {
|
| 1382 |
+
"content": "<tbody>",
|
| 1383 |
+
"lstrip": false,
|
| 1384 |
+
"normalized": false,
|
| 1385 |
+
"rstrip": false,
|
| 1386 |
+
"single_word": false,
|
| 1387 |
+
"special": false
|
| 1388 |
+
},
|
| 1389 |
+
"173": {
|
| 1390 |
+
"content": "<tfoot>",
|
| 1391 |
+
"lstrip": false,
|
| 1392 |
+
"normalized": false,
|
| 1393 |
+
"rstrip": false,
|
| 1394 |
+
"single_word": false,
|
| 1395 |
+
"special": false
|
| 1396 |
+
},
|
| 1397 |
+
"174": {
|
| 1398 |
+
"content": "<tr>",
|
| 1399 |
+
"lstrip": false,
|
| 1400 |
+
"normalized": false,
|
| 1401 |
+
"rstrip": false,
|
| 1402 |
+
"single_word": false,
|
| 1403 |
+
"special": false
|
| 1404 |
+
},
|
| 1405 |
+
"175": {
|
| 1406 |
+
"content": "<th>",
|
| 1407 |
+
"lstrip": false,
|
| 1408 |
+
"normalized": false,
|
| 1409 |
+
"rstrip": false,
|
| 1410 |
+
"single_word": false,
|
| 1411 |
+
"special": false
|
| 1412 |
+
},
|
| 1413 |
+
"176": {
|
| 1414 |
+
"content": "<td>",
|
| 1415 |
+
"lstrip": false,
|
| 1416 |
+
"normalized": false,
|
| 1417 |
+
"rstrip": false,
|
| 1418 |
+
"single_word": false,
|
| 1419 |
+
"special": false
|
| 1420 |
+
},
|
| 1421 |
+
"177": {
|
| 1422 |
+
"content": "</table>",
|
| 1423 |
+
"lstrip": false,
|
| 1424 |
+
"normalized": false,
|
| 1425 |
+
"rstrip": false,
|
| 1426 |
+
"single_word": false,
|
| 1427 |
+
"special": false
|
| 1428 |
+
},
|
| 1429 |
+
"178": {
|
| 1430 |
+
"content": "</caption>",
|
| 1431 |
+
"lstrip": false,
|
| 1432 |
+
"normalized": false,
|
| 1433 |
+
"rstrip": false,
|
| 1434 |
+
"single_word": false,
|
| 1435 |
+
"special": false
|
| 1436 |
+
},
|
| 1437 |
+
"179": {
|
| 1438 |
+
"content": "</thead>",
|
| 1439 |
+
"lstrip": false,
|
| 1440 |
+
"normalized": false,
|
| 1441 |
+
"rstrip": false,
|
| 1442 |
+
"single_word": false,
|
| 1443 |
+
"special": false
|
| 1444 |
+
},
|
| 1445 |
+
"180": {
|
| 1446 |
+
"content": "</tbody>",
|
| 1447 |
+
"lstrip": false,
|
| 1448 |
+
"normalized": false,
|
| 1449 |
+
"rstrip": false,
|
| 1450 |
+
"single_word": false,
|
| 1451 |
+
"special": false
|
| 1452 |
+
},
|
| 1453 |
+
"181": {
|
| 1454 |
+
"content": "</tfoot>",
|
| 1455 |
+
"lstrip": false,
|
| 1456 |
+
"normalized": false,
|
| 1457 |
+
"rstrip": false,
|
| 1458 |
+
"single_word": false,
|
| 1459 |
+
"special": false
|
| 1460 |
+
},
|
| 1461 |
+
"182": {
|
| 1462 |
+
"content": "</tr>",
|
| 1463 |
+
"lstrip": false,
|
| 1464 |
+
"normalized": false,
|
| 1465 |
+
"rstrip": false,
|
| 1466 |
+
"single_word": false,
|
| 1467 |
+
"special": false
|
| 1468 |
+
},
|
| 1469 |
+
"183": {
|
| 1470 |
+
"content": "</th>",
|
| 1471 |
+
"lstrip": false,
|
| 1472 |
+
"normalized": false,
|
| 1473 |
+
"rstrip": false,
|
| 1474 |
+
"single_word": false,
|
| 1475 |
+
"special": false
|
| 1476 |
+
},
|
| 1477 |
+
"184": {
|
| 1478 |
+
"content": "</td>",
|
| 1479 |
+
"lstrip": false,
|
| 1480 |
+
"normalized": false,
|
| 1481 |
+
"rstrip": false,
|
| 1482 |
+
"single_word": false,
|
| 1483 |
+
"special": false
|
| 1484 |
+
},
|
| 1485 |
+
"185": {
|
| 1486 |
+
"content": "<h1>",
|
| 1487 |
+
"lstrip": false,
|
| 1488 |
+
"normalized": false,
|
| 1489 |
+
"rstrip": false,
|
| 1490 |
+
"single_word": false,
|
| 1491 |
+
"special": false
|
| 1492 |
+
},
|
| 1493 |
+
"186": {
|
| 1494 |
+
"content": "<h2>",
|
| 1495 |
+
"lstrip": false,
|
| 1496 |
+
"normalized": false,
|
| 1497 |
+
"rstrip": false,
|
| 1498 |
+
"single_word": false,
|
| 1499 |
+
"special": false
|
| 1500 |
+
},
|
| 1501 |
+
"187": {
|
| 1502 |
+
"content": "<h3>",
|
| 1503 |
+
"lstrip": false,
|
| 1504 |
+
"normalized": false,
|
| 1505 |
+
"rstrip": false,
|
| 1506 |
+
"single_word": false,
|
| 1507 |
+
"special": false
|
| 1508 |
+
},
|
| 1509 |
+
"188": {
|
| 1510 |
+
"content": "<h4>",
|
| 1511 |
+
"lstrip": false,
|
| 1512 |
+
"normalized": false,
|
| 1513 |
+
"rstrip": false,
|
| 1514 |
+
"single_word": false,
|
| 1515 |
+
"special": false
|
| 1516 |
+
},
|
| 1517 |
+
"189": {
|
| 1518 |
+
"content": "<h5>",
|
| 1519 |
+
"lstrip": false,
|
| 1520 |
+
"normalized": false,
|
| 1521 |
+
"rstrip": false,
|
| 1522 |
+
"single_word": false,
|
| 1523 |
+
"special": false
|
| 1524 |
+
},
|
| 1525 |
+
"190": {
|
| 1526 |
+
"content": "<h6>",
|
| 1527 |
+
"lstrip": false,
|
| 1528 |
+
"normalized": false,
|
| 1529 |
+
"rstrip": false,
|
| 1530 |
+
"single_word": false,
|
| 1531 |
+
"special": false
|
| 1532 |
+
},
|
| 1533 |
+
"191": {
|
| 1534 |
+
"content": "<blockquote>",
|
| 1535 |
+
"lstrip": false,
|
| 1536 |
+
"normalized": false,
|
| 1537 |
+
"rstrip": false,
|
| 1538 |
+
"single_word": false,
|
| 1539 |
+
"special": false
|
| 1540 |
+
},
|
| 1541 |
+
"192": {
|
| 1542 |
+
"content": "</h1>",
|
| 1543 |
+
"lstrip": false,
|
| 1544 |
+
"normalized": false,
|
| 1545 |
+
"rstrip": false,
|
| 1546 |
+
"single_word": false,
|
| 1547 |
+
"special": false
|
| 1548 |
+
},
|
| 1549 |
+
"193": {
|
| 1550 |
+
"content": "</h2>",
|
| 1551 |
+
"lstrip": false,
|
| 1552 |
+
"normalized": false,
|
| 1553 |
+
"rstrip": false,
|
| 1554 |
+
"single_word": false,
|
| 1555 |
+
"special": false
|
| 1556 |
+
},
|
| 1557 |
+
"194": {
|
| 1558 |
+
"content": "</h3>",
|
| 1559 |
+
"lstrip": false,
|
| 1560 |
+
"normalized": false,
|
| 1561 |
+
"rstrip": false,
|
| 1562 |
+
"single_word": false,
|
| 1563 |
+
"special": false
|
| 1564 |
+
},
|
| 1565 |
+
"195": {
|
| 1566 |
+
"content": "</h4>",
|
| 1567 |
+
"lstrip": false,
|
| 1568 |
+
"normalized": false,
|
| 1569 |
+
"rstrip": false,
|
| 1570 |
+
"single_word": false,
|
| 1571 |
+
"special": false
|
| 1572 |
+
},
|
| 1573 |
+
"196": {
|
| 1574 |
+
"content": "</h5>",
|
| 1575 |
+
"lstrip": false,
|
| 1576 |
+
"normalized": false,
|
| 1577 |
+
"rstrip": false,
|
| 1578 |
+
"single_word": false,
|
| 1579 |
+
"special": false
|
| 1580 |
+
},
|
| 1581 |
+
"197": {
|
| 1582 |
+
"content": "</h6>",
|
| 1583 |
+
"lstrip": false,
|
| 1584 |
+
"normalized": false,
|
| 1585 |
+
"rstrip": false,
|
| 1586 |
+
"single_word": false,
|
| 1587 |
+
"special": false
|
| 1588 |
+
},
|
| 1589 |
+
"198": {
|
| 1590 |
+
"content": "</blockquote>",
|
| 1591 |
+
"lstrip": false,
|
| 1592 |
+
"normalized": false,
|
| 1593 |
+
"rstrip": false,
|
| 1594 |
+
"single_word": false,
|
| 1595 |
+
"special": false
|
| 1596 |
+
},
|
| 1597 |
+
"199": {
|
| 1598 |
+
"content": "<strong>",
|
| 1599 |
+
"lstrip": false,
|
| 1600 |
+
"normalized": false,
|
| 1601 |
+
"rstrip": false,
|
| 1602 |
+
"single_word": false,
|
| 1603 |
+
"special": false
|
| 1604 |
+
},
|
| 1605 |
+
"200": {
|
| 1606 |
+
"content": "<em>",
|
| 1607 |
+
"lstrip": false,
|
| 1608 |
+
"normalized": false,
|
| 1609 |
+
"rstrip": false,
|
| 1610 |
+
"single_word": false,
|
| 1611 |
+
"special": false
|
| 1612 |
+
},
|
| 1613 |
+
"201": {
|
| 1614 |
+
"content": "<b>",
|
| 1615 |
+
"lstrip": false,
|
| 1616 |
+
"normalized": false,
|
| 1617 |
+
"rstrip": false,
|
| 1618 |
+
"single_word": false,
|
| 1619 |
+
"special": false
|
| 1620 |
+
},
|
| 1621 |
+
"202": {
|
| 1622 |
+
"content": "<i>",
|
| 1623 |
+
"lstrip": false,
|
| 1624 |
+
"normalized": false,
|
| 1625 |
+
"rstrip": false,
|
| 1626 |
+
"single_word": false,
|
| 1627 |
+
"special": false
|
| 1628 |
+
},
|
| 1629 |
+
"203": {
|
| 1630 |
+
"content": "<u>",
|
| 1631 |
+
"lstrip": false,
|
| 1632 |
+
"normalized": false,
|
| 1633 |
+
"rstrip": false,
|
| 1634 |
+
"single_word": false,
|
| 1635 |
+
"special": false
|
| 1636 |
+
},
|
| 1637 |
+
"204": {
|
| 1638 |
+
"content": "<s>",
|
| 1639 |
+
"lstrip": false,
|
| 1640 |
+
"normalized": false,
|
| 1641 |
+
"rstrip": false,
|
| 1642 |
+
"single_word": false,
|
| 1643 |
+
"special": false
|
| 1644 |
+
},
|
| 1645 |
+
"205": {
|
| 1646 |
+
"content": "<sub>",
|
| 1647 |
+
"lstrip": false,
|
| 1648 |
+
"normalized": false,
|
| 1649 |
+
"rstrip": false,
|
| 1650 |
+
"single_word": false,
|
| 1651 |
+
"special": false
|
| 1652 |
+
},
|
| 1653 |
+
"206": {
|
| 1654 |
+
"content": "<sup>",
|
| 1655 |
+
"lstrip": false,
|
| 1656 |
+
"normalized": false,
|
| 1657 |
+
"rstrip": false,
|
| 1658 |
+
"single_word": false,
|
| 1659 |
+
"special": false
|
| 1660 |
+
},
|
| 1661 |
+
"207": {
|
| 1662 |
+
"content": "<code>",
|
| 1663 |
+
"lstrip": false,
|
| 1664 |
+
"normalized": false,
|
| 1665 |
+
"rstrip": false,
|
| 1666 |
+
"single_word": false,
|
| 1667 |
+
"special": false
|
| 1668 |
+
},
|
| 1669 |
+
"208": {
|
| 1670 |
+
"content": "</strong>",
|
| 1671 |
+
"lstrip": false,
|
| 1672 |
+
"normalized": false,
|
| 1673 |
+
"rstrip": false,
|
| 1674 |
+
"single_word": false,
|
| 1675 |
+
"special": false
|
| 1676 |
+
},
|
| 1677 |
+
"209": {
|
| 1678 |
+
"content": "</em>",
|
| 1679 |
+
"lstrip": false,
|
| 1680 |
+
"normalized": false,
|
| 1681 |
+
"rstrip": false,
|
| 1682 |
+
"single_word": false,
|
| 1683 |
+
"special": false
|
| 1684 |
+
},
|
| 1685 |
+
"210": {
|
| 1686 |
+
"content": "</b>",
|
| 1687 |
+
"lstrip": false,
|
| 1688 |
+
"normalized": false,
|
| 1689 |
+
"rstrip": false,
|
| 1690 |
+
"single_word": false,
|
| 1691 |
+
"special": false
|
| 1692 |
+
},
|
| 1693 |
+
"211": {
|
| 1694 |
+
"content": "</i>",
|
| 1695 |
+
"lstrip": false,
|
| 1696 |
+
"normalized": false,
|
| 1697 |
+
"rstrip": false,
|
| 1698 |
+
"single_word": false,
|
| 1699 |
+
"special": false
|
| 1700 |
+
},
|
| 1701 |
+
"212": {
|
| 1702 |
+
"content": "</u>",
|
| 1703 |
+
"lstrip": false,
|
| 1704 |
+
"normalized": false,
|
| 1705 |
+
"rstrip": false,
|
| 1706 |
+
"single_word": false,
|
| 1707 |
+
"special": false
|
| 1708 |
+
},
|
| 1709 |
+
"213": {
|
| 1710 |
+
"content": "</s>",
|
| 1711 |
+
"lstrip": false,
|
| 1712 |
+
"normalized": false,
|
| 1713 |
+
"rstrip": false,
|
| 1714 |
+
"single_word": false,
|
| 1715 |
+
"special": false
|
| 1716 |
+
},
|
| 1717 |
+
"214": {
|
| 1718 |
+
"content": "</sub>",
|
| 1719 |
+
"lstrip": false,
|
| 1720 |
+
"normalized": false,
|
| 1721 |
+
"rstrip": false,
|
| 1722 |
+
"single_word": false,
|
| 1723 |
+
"special": false
|
| 1724 |
+
},
|
| 1725 |
+
"215": {
|
| 1726 |
+
"content": "</sup>",
|
| 1727 |
+
"lstrip": false,
|
| 1728 |
+
"normalized": false,
|
| 1729 |
+
"rstrip": false,
|
| 1730 |
+
"single_word": false,
|
| 1731 |
+
"special": false
|
| 1732 |
+
},
|
| 1733 |
+
"216": {
|
| 1734 |
+
"content": "</code>",
|
| 1735 |
+
"lstrip": false,
|
| 1736 |
+
"normalized": false,
|
| 1737 |
+
"rstrip": false,
|
| 1738 |
+
"single_word": false,
|
| 1739 |
+
"special": false
|
| 1740 |
+
}
|
| 1741 |
+
},
|
| 1742 |
+
"additional_special_tokens": [
|
| 1743 |
+
"<start_of_turn>",
|
| 1744 |
+
"<end_of_turn>"
|
| 1745 |
+
],
|
| 1746 |
+
"bos_token": "<bos>",
|
| 1747 |
+
"chat_template": "{{ bos_token }}{% if messages[0]['role'] == 'system' %}{{ raise_exception('System role not supported') }}{% endif %}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if (message['role'] == 'assistant') %}{% set role = 'model' %}{% else %}{% set role = message['role'] %}{% endif %}{{ '<start_of_turn>' + role + '\n' + message['content'] | trim + '<end_of_turn>\n' }}{% endfor %}{% if add_generation_prompt %}{{'<start_of_turn>model\n'}}{% endif %}",
|
| 1748 |
+
"clean_up_tokenization_spaces": false,
|
| 1749 |
+
"eos_token": "<eos>",
|
| 1750 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 1751 |
+
"pad_token": "<eos>",
|
| 1752 |
+
"sp_model_kwargs": {},
|
| 1753 |
+
"spaces_between_special_tokens": false,
|
| 1754 |
+
"tokenizer_class": "GemmaTokenizer",
|
| 1755 |
+
"unk_token": "<unk>",
|
| 1756 |
+
"use_default_system_prompt": false
|
| 1757 |
+
}
|
trainer_state-gemma-bf16-QLORA-super_glue-rte-sequence_classification.json
ADDED
|
@@ -0,0 +1,2602 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 10.0,
|
| 5 |
+
"eval_steps": 1,
|
| 6 |
+
"global_step": 160,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.0625,
|
| 13 |
+
"grad_norm": 268.0,
|
| 14 |
+
"learning_rate": 2.5e-05,
|
| 15 |
+
"loss": 2.5702,
|
| 16 |
+
"step": 1
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.0625,
|
| 20 |
+
"eval_accuracy": 0.508,
|
| 21 |
+
"eval_loss": 2.8505053520202637,
|
| 22 |
+
"eval_runtime": 4.8412,
|
| 23 |
+
"eval_samples_per_second": 51.64,
|
| 24 |
+
"eval_steps_per_second": 1.652,
|
| 25 |
+
"step": 1
|
| 26 |
+
},
|
| 27 |
+
{
|
| 28 |
+
"epoch": 0.125,
|
| 29 |
+
"grad_norm": 227.0,
|
| 30 |
+
"learning_rate": 5e-05,
|
| 31 |
+
"loss": 2.6389,
|
| 32 |
+
"step": 2
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.125,
|
| 36 |
+
"eval_accuracy": 0.528,
|
| 37 |
+
"eval_loss": 2.2588462829589844,
|
| 38 |
+
"eval_runtime": 4.8967,
|
| 39 |
+
"eval_samples_per_second": 51.054,
|
| 40 |
+
"eval_steps_per_second": 1.634,
|
| 41 |
+
"step": 2
|
| 42 |
+
},
|
| 43 |
+
{
|
| 44 |
+
"epoch": 0.1875,
|
| 45 |
+
"grad_norm": 236.0,
|
| 46 |
+
"learning_rate": 4.968354430379747e-05,
|
| 47 |
+
"loss": 2.3551,
|
| 48 |
+
"step": 3
|
| 49 |
+
},
|
| 50 |
+
{
|
| 51 |
+
"epoch": 0.1875,
|
| 52 |
+
"eval_accuracy": 0.536,
|
| 53 |
+
"eval_loss": 1.4990876913070679,
|
| 54 |
+
"eval_runtime": 4.8929,
|
| 55 |
+
"eval_samples_per_second": 51.095,
|
| 56 |
+
"eval_steps_per_second": 1.635,
|
| 57 |
+
"step": 3
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 0.25,
|
| 61 |
+
"grad_norm": 89.0,
|
| 62 |
+
"learning_rate": 4.936708860759494e-05,
|
| 63 |
+
"loss": 1.5552,
|
| 64 |
+
"step": 4
|
| 65 |
+
},
|
| 66 |
+
{
|
| 67 |
+
"epoch": 0.25,
|
| 68 |
+
"eval_accuracy": 0.544,
|
| 69 |
+
"eval_loss": 1.8495231866836548,
|
| 70 |
+
"eval_runtime": 4.8705,
|
| 71 |
+
"eval_samples_per_second": 51.33,
|
| 72 |
+
"eval_steps_per_second": 1.643,
|
| 73 |
+
"step": 4
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.3125,
|
| 77 |
+
"grad_norm": 130.0,
|
| 78 |
+
"learning_rate": 4.905063291139241e-05,
|
| 79 |
+
"loss": 1.6022,
|
| 80 |
+
"step": 5
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.3125,
|
| 84 |
+
"eval_accuracy": 0.552,
|
| 85 |
+
"eval_loss": 1.5980929136276245,
|
| 86 |
+
"eval_runtime": 4.8961,
|
| 87 |
+
"eval_samples_per_second": 51.061,
|
| 88 |
+
"eval_steps_per_second": 1.634,
|
| 89 |
+
"step": 5
|
| 90 |
+
},
|
| 91 |
+
{
|
| 92 |
+
"epoch": 0.375,
|
| 93 |
+
"grad_norm": 190.0,
|
| 94 |
+
"learning_rate": 4.8734177215189874e-05,
|
| 95 |
+
"loss": 1.8478,
|
| 96 |
+
"step": 6
|
| 97 |
+
},
|
| 98 |
+
{
|
| 99 |
+
"epoch": 0.375,
|
| 100 |
+
"eval_accuracy": 0.62,
|
| 101 |
+
"eval_loss": 1.179288625717163,
|
| 102 |
+
"eval_runtime": 4.8667,
|
| 103 |
+
"eval_samples_per_second": 51.37,
|
| 104 |
+
"eval_steps_per_second": 1.644,
|
| 105 |
+
"step": 6
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 0.4375,
|
| 109 |
+
"grad_norm": 92.5,
|
| 110 |
+
"learning_rate": 4.8417721518987346e-05,
|
| 111 |
+
"loss": 1.1437,
|
| 112 |
+
"step": 7
|
| 113 |
+
},
|
| 114 |
+
{
|
| 115 |
+
"epoch": 0.4375,
|
| 116 |
+
"eval_accuracy": 0.624,
|
| 117 |
+
"eval_loss": 1.0324233770370483,
|
| 118 |
+
"eval_runtime": 4.8984,
|
| 119 |
+
"eval_samples_per_second": 51.037,
|
| 120 |
+
"eval_steps_per_second": 1.633,
|
| 121 |
+
"step": 7
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.5,
|
| 125 |
+
"grad_norm": 52.25,
|
| 126 |
+
"learning_rate": 4.810126582278481e-05,
|
| 127 |
+
"loss": 0.7386,
|
| 128 |
+
"step": 8
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.5,
|
| 132 |
+
"eval_accuracy": 0.628,
|
| 133 |
+
"eval_loss": 1.0248664617538452,
|
| 134 |
+
"eval_runtime": 4.8699,
|
| 135 |
+
"eval_samples_per_second": 51.335,
|
| 136 |
+
"eval_steps_per_second": 1.643,
|
| 137 |
+
"step": 8
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 0.5625,
|
| 141 |
+
"grad_norm": 69.0,
|
| 142 |
+
"learning_rate": 4.778481012658228e-05,
|
| 143 |
+
"loss": 1.0636,
|
| 144 |
+
"step": 9
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 0.5625,
|
| 148 |
+
"eval_accuracy": 0.656,
|
| 149 |
+
"eval_loss": 0.9664216041564941,
|
| 150 |
+
"eval_runtime": 4.8671,
|
| 151 |
+
"eval_samples_per_second": 51.365,
|
| 152 |
+
"eval_steps_per_second": 1.644,
|
| 153 |
+
"step": 9
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 0.625,
|
| 157 |
+
"grad_norm": 104.0,
|
| 158 |
+
"learning_rate": 4.7468354430379746e-05,
|
| 159 |
+
"loss": 0.9956,
|
| 160 |
+
"step": 10
|
| 161 |
+
},
|
| 162 |
+
{
|
| 163 |
+
"epoch": 0.625,
|
| 164 |
+
"eval_accuracy": 0.696,
|
| 165 |
+
"eval_loss": 0.8491688966751099,
|
| 166 |
+
"eval_runtime": 4.8707,
|
| 167 |
+
"eval_samples_per_second": 51.328,
|
| 168 |
+
"eval_steps_per_second": 1.642,
|
| 169 |
+
"step": 10
|
| 170 |
+
},
|
| 171 |
+
{
|
| 172 |
+
"epoch": 0.6875,
|
| 173 |
+
"grad_norm": 51.75,
|
| 174 |
+
"learning_rate": 4.715189873417722e-05,
|
| 175 |
+
"loss": 0.7195,
|
| 176 |
+
"step": 11
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 0.6875,
|
| 180 |
+
"eval_accuracy": 0.724,
|
| 181 |
+
"eval_loss": 0.7724543809890747,
|
| 182 |
+
"eval_runtime": 4.8634,
|
| 183 |
+
"eval_samples_per_second": 51.405,
|
| 184 |
+
"eval_steps_per_second": 1.645,
|
| 185 |
+
"step": 11
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.75,
|
| 189 |
+
"grad_norm": 24.625,
|
| 190 |
+
"learning_rate": 4.683544303797468e-05,
|
| 191 |
+
"loss": 0.7704,
|
| 192 |
+
"step": 12
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.75,
|
| 196 |
+
"eval_accuracy": 0.728,
|
| 197 |
+
"eval_loss": 0.7519556283950806,
|
| 198 |
+
"eval_runtime": 4.8881,
|
| 199 |
+
"eval_samples_per_second": 51.144,
|
| 200 |
+
"eval_steps_per_second": 1.637,
|
| 201 |
+
"step": 12
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 0.8125,
|
| 205 |
+
"grad_norm": 18.625,
|
| 206 |
+
"learning_rate": 4.6518987341772154e-05,
|
| 207 |
+
"loss": 0.4636,
|
| 208 |
+
"step": 13
|
| 209 |
+
},
|
| 210 |
+
{
|
| 211 |
+
"epoch": 0.8125,
|
| 212 |
+
"eval_accuracy": 0.744,
|
| 213 |
+
"eval_loss": 0.7026970386505127,
|
| 214 |
+
"eval_runtime": 4.8695,
|
| 215 |
+
"eval_samples_per_second": 51.34,
|
| 216 |
+
"eval_steps_per_second": 1.643,
|
| 217 |
+
"step": 13
|
| 218 |
+
},
|
| 219 |
+
{
|
| 220 |
+
"epoch": 0.875,
|
| 221 |
+
"grad_norm": 22.25,
|
| 222 |
+
"learning_rate": 4.6202531645569625e-05,
|
| 223 |
+
"loss": 0.771,
|
| 224 |
+
"step": 14
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 0.875,
|
| 228 |
+
"eval_accuracy": 0.788,
|
| 229 |
+
"eval_loss": 0.6045461893081665,
|
| 230 |
+
"eval_runtime": 4.8902,
|
| 231 |
+
"eval_samples_per_second": 51.123,
|
| 232 |
+
"eval_steps_per_second": 1.636,
|
| 233 |
+
"step": 14
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.9375,
|
| 237 |
+
"grad_norm": 15.5,
|
| 238 |
+
"learning_rate": 4.588607594936709e-05,
|
| 239 |
+
"loss": 0.7138,
|
| 240 |
+
"step": 15
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.9375,
|
| 244 |
+
"eval_accuracy": 0.82,
|
| 245 |
+
"eval_loss": 0.5602908730506897,
|
| 246 |
+
"eval_runtime": 4.8902,
|
| 247 |
+
"eval_samples_per_second": 51.123,
|
| 248 |
+
"eval_steps_per_second": 1.636,
|
| 249 |
+
"step": 15
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 1.0,
|
| 253 |
+
"grad_norm": 30.875,
|
| 254 |
+
"learning_rate": 4.556962025316456e-05,
|
| 255 |
+
"loss": 0.7263,
|
| 256 |
+
"step": 16
|
| 257 |
+
},
|
| 258 |
+
{
|
| 259 |
+
"epoch": 1.0,
|
| 260 |
+
"eval_accuracy": 0.804,
|
| 261 |
+
"eval_loss": 0.5666066408157349,
|
| 262 |
+
"eval_runtime": 4.8404,
|
| 263 |
+
"eval_samples_per_second": 51.649,
|
| 264 |
+
"eval_steps_per_second": 1.653,
|
| 265 |
+
"step": 16
|
| 266 |
+
},
|
| 267 |
+
{
|
| 268 |
+
"epoch": 1.0625,
|
| 269 |
+
"grad_norm": 77.5,
|
| 270 |
+
"learning_rate": 4.525316455696203e-05,
|
| 271 |
+
"loss": 0.3919,
|
| 272 |
+
"step": 17
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 1.0625,
|
| 276 |
+
"eval_accuracy": 0.808,
|
| 277 |
+
"eval_loss": 0.5534331202507019,
|
| 278 |
+
"eval_runtime": 4.816,
|
| 279 |
+
"eval_samples_per_second": 51.911,
|
| 280 |
+
"eval_steps_per_second": 1.661,
|
| 281 |
+
"step": 17
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 1.125,
|
| 285 |
+
"grad_norm": 44.5,
|
| 286 |
+
"learning_rate": 4.49367088607595e-05,
|
| 287 |
+
"loss": 0.2448,
|
| 288 |
+
"step": 18
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"epoch": 1.125,
|
| 292 |
+
"eval_accuracy": 0.836,
|
| 293 |
+
"eval_loss": 0.5073856711387634,
|
| 294 |
+
"eval_runtime": 4.8889,
|
| 295 |
+
"eval_samples_per_second": 51.137,
|
| 296 |
+
"eval_steps_per_second": 1.636,
|
| 297 |
+
"step": 18
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 1.1875,
|
| 301 |
+
"grad_norm": 31.75,
|
| 302 |
+
"learning_rate": 4.462025316455696e-05,
|
| 303 |
+
"loss": 0.2112,
|
| 304 |
+
"step": 19
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 1.1875,
|
| 308 |
+
"eval_accuracy": 0.852,
|
| 309 |
+
"eval_loss": 0.4510812759399414,
|
| 310 |
+
"eval_runtime": 4.8632,
|
| 311 |
+
"eval_samples_per_second": 51.407,
|
| 312 |
+
"eval_steps_per_second": 1.645,
|
| 313 |
+
"step": 19
|
| 314 |
+
},
|
| 315 |
+
{
|
| 316 |
+
"epoch": 1.25,
|
| 317 |
+
"grad_norm": 33.25,
|
| 318 |
+
"learning_rate": 4.430379746835443e-05,
|
| 319 |
+
"loss": 0.335,
|
| 320 |
+
"step": 20
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 1.25,
|
| 324 |
+
"eval_accuracy": 0.828,
|
| 325 |
+
"eval_loss": 0.4451099932193756,
|
| 326 |
+
"eval_runtime": 4.8972,
|
| 327 |
+
"eval_samples_per_second": 51.05,
|
| 328 |
+
"eval_steps_per_second": 1.634,
|
| 329 |
+
"step": 20
|
| 330 |
+
},
|
| 331 |
+
{
|
| 332 |
+
"epoch": 1.3125,
|
| 333 |
+
"grad_norm": 17.375,
|
| 334 |
+
"learning_rate": 4.3987341772151904e-05,
|
| 335 |
+
"loss": 0.196,
|
| 336 |
+
"step": 21
|
| 337 |
+
},
|
| 338 |
+
{
|
| 339 |
+
"epoch": 1.3125,
|
| 340 |
+
"eval_accuracy": 0.82,
|
| 341 |
+
"eval_loss": 0.47517192363739014,
|
| 342 |
+
"eval_runtime": 4.8852,
|
| 343 |
+
"eval_samples_per_second": 51.175,
|
| 344 |
+
"eval_steps_per_second": 1.638,
|
| 345 |
+
"step": 21
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 1.375,
|
| 349 |
+
"grad_norm": 45.75,
|
| 350 |
+
"learning_rate": 4.367088607594937e-05,
|
| 351 |
+
"loss": 0.1765,
|
| 352 |
+
"step": 22
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 1.375,
|
| 356 |
+
"eval_accuracy": 0.82,
|
| 357 |
+
"eval_loss": 0.4687165319919586,
|
| 358 |
+
"eval_runtime": 4.8161,
|
| 359 |
+
"eval_samples_per_second": 51.909,
|
| 360 |
+
"eval_steps_per_second": 1.661,
|
| 361 |
+
"step": 22
|
| 362 |
+
},
|
| 363 |
+
{
|
| 364 |
+
"epoch": 1.4375,
|
| 365 |
+
"grad_norm": 18.625,
|
| 366 |
+
"learning_rate": 4.3354430379746834e-05,
|
| 367 |
+
"loss": 0.2245,
|
| 368 |
+
"step": 23
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 1.4375,
|
| 372 |
+
"eval_accuracy": 0.824,
|
| 373 |
+
"eval_loss": 0.4411630928516388,
|
| 374 |
+
"eval_runtime": 4.8861,
|
| 375 |
+
"eval_samples_per_second": 51.165,
|
| 376 |
+
"eval_steps_per_second": 1.637,
|
| 377 |
+
"step": 23
|
| 378 |
+
},
|
| 379 |
+
{
|
| 380 |
+
"epoch": 1.5,
|
| 381 |
+
"grad_norm": 10.0,
|
| 382 |
+
"learning_rate": 4.3037974683544305e-05,
|
| 383 |
+
"loss": 0.137,
|
| 384 |
+
"step": 24
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 1.5,
|
| 388 |
+
"eval_accuracy": 0.844,
|
| 389 |
+
"eval_loss": 0.4266666769981384,
|
| 390 |
+
"eval_runtime": 4.8898,
|
| 391 |
+
"eval_samples_per_second": 51.127,
|
| 392 |
+
"eval_steps_per_second": 1.636,
|
| 393 |
+
"step": 24
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 1.5625,
|
| 397 |
+
"grad_norm": 13.125,
|
| 398 |
+
"learning_rate": 4.2721518987341776e-05,
|
| 399 |
+
"loss": 0.1957,
|
| 400 |
+
"step": 25
|
| 401 |
+
},
|
| 402 |
+
{
|
| 403 |
+
"epoch": 1.5625,
|
| 404 |
+
"eval_accuracy": 0.86,
|
| 405 |
+
"eval_loss": 0.42926496267318726,
|
| 406 |
+
"eval_runtime": 4.8436,
|
| 407 |
+
"eval_samples_per_second": 51.614,
|
| 408 |
+
"eval_steps_per_second": 1.652,
|
| 409 |
+
"step": 25
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 1.625,
|
| 413 |
+
"grad_norm": 62.0,
|
| 414 |
+
"learning_rate": 4.240506329113924e-05,
|
| 415 |
+
"loss": 0.3881,
|
| 416 |
+
"step": 26
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 1.625,
|
| 420 |
+
"eval_accuracy": 0.864,
|
| 421 |
+
"eval_loss": 0.43251192569732666,
|
| 422 |
+
"eval_runtime": 4.8871,
|
| 423 |
+
"eval_samples_per_second": 51.155,
|
| 424 |
+
"eval_steps_per_second": 1.637,
|
| 425 |
+
"step": 26
|
| 426 |
+
},
|
| 427 |
+
{
|
| 428 |
+
"epoch": 1.6875,
|
| 429 |
+
"grad_norm": 7.9375,
|
| 430 |
+
"learning_rate": 4.208860759493671e-05,
|
| 431 |
+
"loss": 0.1298,
|
| 432 |
+
"step": 27
|
| 433 |
+
},
|
| 434 |
+
{
|
| 435 |
+
"epoch": 1.6875,
|
| 436 |
+
"eval_accuracy": 0.856,
|
| 437 |
+
"eval_loss": 0.46340441703796387,
|
| 438 |
+
"eval_runtime": 4.8777,
|
| 439 |
+
"eval_samples_per_second": 51.254,
|
| 440 |
+
"eval_steps_per_second": 1.64,
|
| 441 |
+
"step": 27
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 1.75,
|
| 445 |
+
"grad_norm": 13.625,
|
| 446 |
+
"learning_rate": 4.177215189873418e-05,
|
| 447 |
+
"loss": 0.1124,
|
| 448 |
+
"step": 28
|
| 449 |
+
},
|
| 450 |
+
{
|
| 451 |
+
"epoch": 1.75,
|
| 452 |
+
"eval_accuracy": 0.86,
|
| 453 |
+
"eval_loss": 0.46482232213020325,
|
| 454 |
+
"eval_runtime": 4.8682,
|
| 455 |
+
"eval_samples_per_second": 51.353,
|
| 456 |
+
"eval_steps_per_second": 1.643,
|
| 457 |
+
"step": 28
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 1.8125,
|
| 461 |
+
"grad_norm": 59.25,
|
| 462 |
+
"learning_rate": 4.145569620253165e-05,
|
| 463 |
+
"loss": 0.2744,
|
| 464 |
+
"step": 29
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 1.8125,
|
| 468 |
+
"eval_accuracy": 0.848,
|
| 469 |
+
"eval_loss": 0.43966910243034363,
|
| 470 |
+
"eval_runtime": 4.8941,
|
| 471 |
+
"eval_samples_per_second": 51.082,
|
| 472 |
+
"eval_steps_per_second": 1.635,
|
| 473 |
+
"step": 29
|
| 474 |
+
},
|
| 475 |
+
{
|
| 476 |
+
"epoch": 1.875,
|
| 477 |
+
"grad_norm": 5.28125,
|
| 478 |
+
"learning_rate": 4.113924050632912e-05,
|
| 479 |
+
"loss": 0.0496,
|
| 480 |
+
"step": 30
|
| 481 |
+
},
|
| 482 |
+
{
|
| 483 |
+
"epoch": 1.875,
|
| 484 |
+
"eval_accuracy": 0.844,
|
| 485 |
+
"eval_loss": 0.4173106849193573,
|
| 486 |
+
"eval_runtime": 4.8998,
|
| 487 |
+
"eval_samples_per_second": 51.023,
|
| 488 |
+
"eval_steps_per_second": 1.633,
|
| 489 |
+
"step": 30
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 1.9375,
|
| 493 |
+
"grad_norm": 29.625,
|
| 494 |
+
"learning_rate": 4.0822784810126584e-05,
|
| 495 |
+
"loss": 0.1658,
|
| 496 |
+
"step": 31
|
| 497 |
+
},
|
| 498 |
+
{
|
| 499 |
+
"epoch": 1.9375,
|
| 500 |
+
"eval_accuracy": 0.832,
|
| 501 |
+
"eval_loss": 0.41856226325035095,
|
| 502 |
+
"eval_runtime": 4.8693,
|
| 503 |
+
"eval_samples_per_second": 51.343,
|
| 504 |
+
"eval_steps_per_second": 1.643,
|
| 505 |
+
"step": 31
|
| 506 |
+
},
|
| 507 |
+
{
|
| 508 |
+
"epoch": 2.0,
|
| 509 |
+
"grad_norm": 12.625,
|
| 510 |
+
"learning_rate": 4.050632911392405e-05,
|
| 511 |
+
"loss": 0.1718,
|
| 512 |
+
"step": 32
|
| 513 |
+
},
|
| 514 |
+
{
|
| 515 |
+
"epoch": 2.0,
|
| 516 |
+
"eval_accuracy": 0.836,
|
| 517 |
+
"eval_loss": 0.4255797863006592,
|
| 518 |
+
"eval_runtime": 4.8685,
|
| 519 |
+
"eval_samples_per_second": 51.35,
|
| 520 |
+
"eval_steps_per_second": 1.643,
|
| 521 |
+
"step": 32
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 2.0625,
|
| 525 |
+
"grad_norm": 14.125,
|
| 526 |
+
"learning_rate": 4.018987341772152e-05,
|
| 527 |
+
"loss": 0.0979,
|
| 528 |
+
"step": 33
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 2.0625,
|
| 532 |
+
"eval_accuracy": 0.836,
|
| 533 |
+
"eval_loss": 0.4206787645816803,
|
| 534 |
+
"eval_runtime": 4.8232,
|
| 535 |
+
"eval_samples_per_second": 51.833,
|
| 536 |
+
"eval_steps_per_second": 1.659,
|
| 537 |
+
"step": 33
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 2.125,
|
| 541 |
+
"grad_norm": 4.65625,
|
| 542 |
+
"learning_rate": 3.987341772151899e-05,
|
| 543 |
+
"loss": 0.0284,
|
| 544 |
+
"step": 34
|
| 545 |
+
},
|
| 546 |
+
{
|
| 547 |
+
"epoch": 2.125,
|
| 548 |
+
"eval_accuracy": 0.844,
|
| 549 |
+
"eval_loss": 0.41741058230400085,
|
| 550 |
+
"eval_runtime": 4.8675,
|
| 551 |
+
"eval_samples_per_second": 51.361,
|
| 552 |
+
"eval_steps_per_second": 1.644,
|
| 553 |
+
"step": 34
|
| 554 |
+
},
|
| 555 |
+
{
|
| 556 |
+
"epoch": 2.1875,
|
| 557 |
+
"grad_norm": 8.875,
|
| 558 |
+
"learning_rate": 3.9556962025316456e-05,
|
| 559 |
+
"loss": 0.0558,
|
| 560 |
+
"step": 35
|
| 561 |
+
},
|
| 562 |
+
{
|
| 563 |
+
"epoch": 2.1875,
|
| 564 |
+
"eval_accuracy": 0.844,
|
| 565 |
+
"eval_loss": 0.4207935929298401,
|
| 566 |
+
"eval_runtime": 4.7688,
|
| 567 |
+
"eval_samples_per_second": 52.424,
|
| 568 |
+
"eval_steps_per_second": 1.678,
|
| 569 |
+
"step": 35
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 2.25,
|
| 573 |
+
"grad_norm": 4.75,
|
| 574 |
+
"learning_rate": 3.924050632911392e-05,
|
| 575 |
+
"loss": 0.1725,
|
| 576 |
+
"step": 36
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 2.25,
|
| 580 |
+
"eval_accuracy": 0.84,
|
| 581 |
+
"eval_loss": 0.43104878067970276,
|
| 582 |
+
"eval_runtime": 4.8634,
|
| 583 |
+
"eval_samples_per_second": 51.404,
|
| 584 |
+
"eval_steps_per_second": 1.645,
|
| 585 |
+
"step": 36
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 2.3125,
|
| 589 |
+
"grad_norm": 11.25,
|
| 590 |
+
"learning_rate": 3.89240506329114e-05,
|
| 591 |
+
"loss": 0.0363,
|
| 592 |
+
"step": 37
|
| 593 |
+
},
|
| 594 |
+
{
|
| 595 |
+
"epoch": 2.3125,
|
| 596 |
+
"eval_accuracy": 0.852,
|
| 597 |
+
"eval_loss": 0.4319431185722351,
|
| 598 |
+
"eval_runtime": 4.8918,
|
| 599 |
+
"eval_samples_per_second": 51.106,
|
| 600 |
+
"eval_steps_per_second": 1.635,
|
| 601 |
+
"step": 37
|
| 602 |
+
},
|
| 603 |
+
{
|
| 604 |
+
"epoch": 2.375,
|
| 605 |
+
"grad_norm": 10.125,
|
| 606 |
+
"learning_rate": 3.8607594936708864e-05,
|
| 607 |
+
"loss": 0.0429,
|
| 608 |
+
"step": 38
|
| 609 |
+
},
|
| 610 |
+
{
|
| 611 |
+
"epoch": 2.375,
|
| 612 |
+
"eval_accuracy": 0.856,
|
| 613 |
+
"eval_loss": 0.4509444534778595,
|
| 614 |
+
"eval_runtime": 4.8964,
|
| 615 |
+
"eval_samples_per_second": 51.058,
|
| 616 |
+
"eval_steps_per_second": 1.634,
|
| 617 |
+
"step": 38
|
| 618 |
+
},
|
| 619 |
+
{
|
| 620 |
+
"epoch": 2.4375,
|
| 621 |
+
"grad_norm": 8.3125,
|
| 622 |
+
"learning_rate": 3.829113924050633e-05,
|
| 623 |
+
"loss": 0.0468,
|
| 624 |
+
"step": 39
|
| 625 |
+
},
|
| 626 |
+
{
|
| 627 |
+
"epoch": 2.4375,
|
| 628 |
+
"eval_accuracy": 0.856,
|
| 629 |
+
"eval_loss": 0.4592805802822113,
|
| 630 |
+
"eval_runtime": 4.8908,
|
| 631 |
+
"eval_samples_per_second": 51.117,
|
| 632 |
+
"eval_steps_per_second": 1.636,
|
| 633 |
+
"step": 39
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 2.5,
|
| 637 |
+
"grad_norm": 16.5,
|
| 638 |
+
"learning_rate": 3.79746835443038e-05,
|
| 639 |
+
"loss": 0.0525,
|
| 640 |
+
"step": 40
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 2.5,
|
| 644 |
+
"eval_accuracy": 0.864,
|
| 645 |
+
"eval_loss": 0.4509994387626648,
|
| 646 |
+
"eval_runtime": 4.8936,
|
| 647 |
+
"eval_samples_per_second": 51.088,
|
| 648 |
+
"eval_steps_per_second": 1.635,
|
| 649 |
+
"step": 40
|
| 650 |
+
},
|
| 651 |
+
{
|
| 652 |
+
"epoch": 2.5625,
|
| 653 |
+
"grad_norm": 3.609375,
|
| 654 |
+
"learning_rate": 3.765822784810127e-05,
|
| 655 |
+
"loss": 0.0232,
|
| 656 |
+
"step": 41
|
| 657 |
+
},
|
| 658 |
+
{
|
| 659 |
+
"epoch": 2.5625,
|
| 660 |
+
"eval_accuracy": 0.852,
|
| 661 |
+
"eval_loss": 0.45242950320243835,
|
| 662 |
+
"eval_runtime": 4.8925,
|
| 663 |
+
"eval_samples_per_second": 51.099,
|
| 664 |
+
"eval_steps_per_second": 1.635,
|
| 665 |
+
"step": 41
|
| 666 |
+
},
|
| 667 |
+
{
|
| 668 |
+
"epoch": 2.625,
|
| 669 |
+
"grad_norm": 1.734375,
|
| 670 |
+
"learning_rate": 3.7341772151898736e-05,
|
| 671 |
+
"loss": 0.0137,
|
| 672 |
+
"step": 42
|
| 673 |
+
},
|
| 674 |
+
{
|
| 675 |
+
"epoch": 2.625,
|
| 676 |
+
"eval_accuracy": 0.852,
|
| 677 |
+
"eval_loss": 0.46332496404647827,
|
| 678 |
+
"eval_runtime": 4.8687,
|
| 679 |
+
"eval_samples_per_second": 51.349,
|
| 680 |
+
"eval_steps_per_second": 1.643,
|
| 681 |
+
"step": 42
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 2.6875,
|
| 685 |
+
"grad_norm": 4.75,
|
| 686 |
+
"learning_rate": 3.70253164556962e-05,
|
| 687 |
+
"loss": 0.0202,
|
| 688 |
+
"step": 43
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 2.6875,
|
| 692 |
+
"eval_accuracy": 0.86,
|
| 693 |
+
"eval_loss": 0.5035133957862854,
|
| 694 |
+
"eval_runtime": 4.8899,
|
| 695 |
+
"eval_samples_per_second": 51.126,
|
| 696 |
+
"eval_steps_per_second": 1.636,
|
| 697 |
+
"step": 43
|
| 698 |
+
},
|
| 699 |
+
{
|
| 700 |
+
"epoch": 2.75,
|
| 701 |
+
"grad_norm": 15.6875,
|
| 702 |
+
"learning_rate": 3.670886075949367e-05,
|
| 703 |
+
"loss": 0.0383,
|
| 704 |
+
"step": 44
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 2.75,
|
| 708 |
+
"eval_accuracy": 0.852,
|
| 709 |
+
"eval_loss": 0.5293290615081787,
|
| 710 |
+
"eval_runtime": 4.8882,
|
| 711 |
+
"eval_samples_per_second": 51.144,
|
| 712 |
+
"eval_steps_per_second": 1.637,
|
| 713 |
+
"step": 44
|
| 714 |
+
},
|
| 715 |
+
{
|
| 716 |
+
"epoch": 2.8125,
|
| 717 |
+
"grad_norm": 24.75,
|
| 718 |
+
"learning_rate": 3.639240506329114e-05,
|
| 719 |
+
"loss": 0.073,
|
| 720 |
+
"step": 45
|
| 721 |
+
},
|
| 722 |
+
{
|
| 723 |
+
"epoch": 2.8125,
|
| 724 |
+
"eval_accuracy": 0.856,
|
| 725 |
+
"eval_loss": 0.5254361033439636,
|
| 726 |
+
"eval_runtime": 4.865,
|
| 727 |
+
"eval_samples_per_second": 51.387,
|
| 728 |
+
"eval_steps_per_second": 1.644,
|
| 729 |
+
"step": 45
|
| 730 |
+
},
|
| 731 |
+
{
|
| 732 |
+
"epoch": 2.875,
|
| 733 |
+
"grad_norm": 28.25,
|
| 734 |
+
"learning_rate": 3.607594936708861e-05,
|
| 735 |
+
"loss": 0.0725,
|
| 736 |
+
"step": 46
|
| 737 |
+
},
|
| 738 |
+
{
|
| 739 |
+
"epoch": 2.875,
|
| 740 |
+
"eval_accuracy": 0.864,
|
| 741 |
+
"eval_loss": 0.5004922151565552,
|
| 742 |
+
"eval_runtime": 4.895,
|
| 743 |
+
"eval_samples_per_second": 51.072,
|
| 744 |
+
"eval_steps_per_second": 1.634,
|
| 745 |
+
"step": 46
|
| 746 |
+
},
|
| 747 |
+
{
|
| 748 |
+
"epoch": 2.9375,
|
| 749 |
+
"grad_norm": 16.375,
|
| 750 |
+
"learning_rate": 3.575949367088608e-05,
|
| 751 |
+
"loss": 0.0516,
|
| 752 |
+
"step": 47
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"epoch": 2.9375,
|
| 756 |
+
"eval_accuracy": 0.864,
|
| 757 |
+
"eval_loss": 0.463413268327713,
|
| 758 |
+
"eval_runtime": 4.8708,
|
| 759 |
+
"eval_samples_per_second": 51.326,
|
| 760 |
+
"eval_steps_per_second": 1.642,
|
| 761 |
+
"step": 47
|
| 762 |
+
},
|
| 763 |
+
{
|
| 764 |
+
"epoch": 3.0,
|
| 765 |
+
"grad_norm": 10.875,
|
| 766 |
+
"learning_rate": 3.5443037974683544e-05,
|
| 767 |
+
"loss": 0.0255,
|
| 768 |
+
"step": 48
|
| 769 |
+
},
|
| 770 |
+
{
|
| 771 |
+
"epoch": 3.0,
|
| 772 |
+
"eval_accuracy": 0.868,
|
| 773 |
+
"eval_loss": 0.4455827474594116,
|
| 774 |
+
"eval_runtime": 4.8928,
|
| 775 |
+
"eval_samples_per_second": 51.096,
|
| 776 |
+
"eval_steps_per_second": 1.635,
|
| 777 |
+
"step": 48
|
| 778 |
+
},
|
| 779 |
+
{
|
| 780 |
+
"epoch": 3.0625,
|
| 781 |
+
"grad_norm": 7.9375,
|
| 782 |
+
"learning_rate": 3.5126582278481015e-05,
|
| 783 |
+
"loss": 0.0191,
|
| 784 |
+
"step": 49
|
| 785 |
+
},
|
| 786 |
+
{
|
| 787 |
+
"epoch": 3.0625,
|
| 788 |
+
"eval_accuracy": 0.868,
|
| 789 |
+
"eval_loss": 0.45068883895874023,
|
| 790 |
+
"eval_runtime": 4.8384,
|
| 791 |
+
"eval_samples_per_second": 51.67,
|
| 792 |
+
"eval_steps_per_second": 1.653,
|
| 793 |
+
"step": 49
|
| 794 |
+
},
|
| 795 |
+
{
|
| 796 |
+
"epoch": 3.125,
|
| 797 |
+
"grad_norm": 0.23828125,
|
| 798 |
+
"learning_rate": 3.4810126582278487e-05,
|
| 799 |
+
"loss": 0.0021,
|
| 800 |
+
"step": 50
|
| 801 |
+
},
|
| 802 |
+
{
|
| 803 |
+
"epoch": 3.125,
|
| 804 |
+
"eval_accuracy": 0.868,
|
| 805 |
+
"eval_loss": 0.4584948718547821,
|
| 806 |
+
"eval_runtime": 4.838,
|
| 807 |
+
"eval_samples_per_second": 51.675,
|
| 808 |
+
"eval_steps_per_second": 1.654,
|
| 809 |
+
"step": 50
|
| 810 |
+
},
|
| 811 |
+
{
|
| 812 |
+
"epoch": 3.1875,
|
| 813 |
+
"grad_norm": 1.4453125,
|
| 814 |
+
"learning_rate": 3.449367088607595e-05,
|
| 815 |
+
"loss": 0.0034,
|
| 816 |
+
"step": 51
|
| 817 |
+
},
|
| 818 |
+
{
|
| 819 |
+
"epoch": 3.1875,
|
| 820 |
+
"eval_accuracy": 0.864,
|
| 821 |
+
"eval_loss": 0.4626566767692566,
|
| 822 |
+
"eval_runtime": 4.8918,
|
| 823 |
+
"eval_samples_per_second": 51.105,
|
| 824 |
+
"eval_steps_per_second": 1.635,
|
| 825 |
+
"step": 51
|
| 826 |
+
},
|
| 827 |
+
{
|
| 828 |
+
"epoch": 3.25,
|
| 829 |
+
"grad_norm": 1.2890625,
|
| 830 |
+
"learning_rate": 3.4177215189873416e-05,
|
| 831 |
+
"loss": 0.0057,
|
| 832 |
+
"step": 52
|
| 833 |
+
},
|
| 834 |
+
{
|
| 835 |
+
"epoch": 3.25,
|
| 836 |
+
"eval_accuracy": 0.864,
|
| 837 |
+
"eval_loss": 0.46148645877838135,
|
| 838 |
+
"eval_runtime": 4.8885,
|
| 839 |
+
"eval_samples_per_second": 51.141,
|
| 840 |
+
"eval_steps_per_second": 1.637,
|
| 841 |
+
"step": 52
|
| 842 |
+
},
|
| 843 |
+
{
|
| 844 |
+
"epoch": 3.3125,
|
| 845 |
+
"grad_norm": 2.984375,
|
| 846 |
+
"learning_rate": 3.386075949367089e-05,
|
| 847 |
+
"loss": 0.0123,
|
| 848 |
+
"step": 53
|
| 849 |
+
},
|
| 850 |
+
{
|
| 851 |
+
"epoch": 3.3125,
|
| 852 |
+
"eval_accuracy": 0.852,
|
| 853 |
+
"eval_loss": 0.4723862409591675,
|
| 854 |
+
"eval_runtime": 4.8923,
|
| 855 |
+
"eval_samples_per_second": 51.101,
|
| 856 |
+
"eval_steps_per_second": 1.635,
|
| 857 |
+
"step": 53
|
| 858 |
+
},
|
| 859 |
+
{
|
| 860 |
+
"epoch": 3.375,
|
| 861 |
+
"grad_norm": 5.75,
|
| 862 |
+
"learning_rate": 3.354430379746836e-05,
|
| 863 |
+
"loss": 0.0111,
|
| 864 |
+
"step": 54
|
| 865 |
+
},
|
| 866 |
+
{
|
| 867 |
+
"epoch": 3.375,
|
| 868 |
+
"eval_accuracy": 0.856,
|
| 869 |
+
"eval_loss": 0.463609904050827,
|
| 870 |
+
"eval_runtime": 4.8347,
|
| 871 |
+
"eval_samples_per_second": 51.71,
|
| 872 |
+
"eval_steps_per_second": 1.655,
|
| 873 |
+
"step": 54
|
| 874 |
+
},
|
| 875 |
+
{
|
| 876 |
+
"epoch": 3.4375,
|
| 877 |
+
"grad_norm": 4.21875,
|
| 878 |
+
"learning_rate": 3.322784810126582e-05,
|
| 879 |
+
"loss": 0.0072,
|
| 880 |
+
"step": 55
|
| 881 |
+
},
|
| 882 |
+
{
|
| 883 |
+
"epoch": 3.4375,
|
| 884 |
+
"eval_accuracy": 0.88,
|
| 885 |
+
"eval_loss": 0.44373881816864014,
|
| 886 |
+
"eval_runtime": 4.8346,
|
| 887 |
+
"eval_samples_per_second": 51.71,
|
| 888 |
+
"eval_steps_per_second": 1.655,
|
| 889 |
+
"step": 55
|
| 890 |
+
},
|
| 891 |
+
{
|
| 892 |
+
"epoch": 3.5,
|
| 893 |
+
"grad_norm": 2.6875,
|
| 894 |
+
"learning_rate": 3.291139240506329e-05,
|
| 895 |
+
"loss": 0.0044,
|
| 896 |
+
"step": 56
|
| 897 |
+
},
|
| 898 |
+
{
|
| 899 |
+
"epoch": 3.5,
|
| 900 |
+
"eval_accuracy": 0.896,
|
| 901 |
+
"eval_loss": 0.4286611080169678,
|
| 902 |
+
"eval_runtime": 4.8885,
|
| 903 |
+
"eval_samples_per_second": 51.14,
|
| 904 |
+
"eval_steps_per_second": 1.636,
|
| 905 |
+
"step": 56
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"epoch": 3.5625,
|
| 909 |
+
"grad_norm": 0.34375,
|
| 910 |
+
"learning_rate": 3.2594936708860766e-05,
|
| 911 |
+
"loss": 0.0013,
|
| 912 |
+
"step": 57
|
| 913 |
+
},
|
| 914 |
+
{
|
| 915 |
+
"epoch": 3.5625,
|
| 916 |
+
"eval_accuracy": 0.892,
|
| 917 |
+
"eval_loss": 0.4324968755245209,
|
| 918 |
+
"eval_runtime": 4.882,
|
| 919 |
+
"eval_samples_per_second": 51.209,
|
| 920 |
+
"eval_steps_per_second": 1.639,
|
| 921 |
+
"step": 57
|
| 922 |
+
},
|
| 923 |
+
{
|
| 924 |
+
"epoch": 3.625,
|
| 925 |
+
"grad_norm": 0.111328125,
|
| 926 |
+
"learning_rate": 3.227848101265823e-05,
|
| 927 |
+
"loss": 0.0005,
|
| 928 |
+
"step": 58
|
| 929 |
+
},
|
| 930 |
+
{
|
| 931 |
+
"epoch": 3.625,
|
| 932 |
+
"eval_accuracy": 0.896,
|
| 933 |
+
"eval_loss": 0.45419201254844666,
|
| 934 |
+
"eval_runtime": 4.8691,
|
| 935 |
+
"eval_samples_per_second": 51.344,
|
| 936 |
+
"eval_steps_per_second": 1.643,
|
| 937 |
+
"step": 58
|
| 938 |
+
},
|
| 939 |
+
{
|
| 940 |
+
"epoch": 3.6875,
|
| 941 |
+
"grad_norm": 1.3984375,
|
| 942 |
+
"learning_rate": 3.1962025316455695e-05,
|
| 943 |
+
"loss": 0.0045,
|
| 944 |
+
"step": 59
|
| 945 |
+
},
|
| 946 |
+
{
|
| 947 |
+
"epoch": 3.6875,
|
| 948 |
+
"eval_accuracy": 0.892,
|
| 949 |
+
"eval_loss": 0.4625495672225952,
|
| 950 |
+
"eval_runtime": 4.8885,
|
| 951 |
+
"eval_samples_per_second": 51.14,
|
| 952 |
+
"eval_steps_per_second": 1.636,
|
| 953 |
+
"step": 59
|
| 954 |
+
},
|
| 955 |
+
{
|
| 956 |
+
"epoch": 3.75,
|
| 957 |
+
"grad_norm": 0.287109375,
|
| 958 |
+
"learning_rate": 3.1645569620253167e-05,
|
| 959 |
+
"loss": 0.0018,
|
| 960 |
+
"step": 60
|
| 961 |
+
},
|
| 962 |
+
{
|
| 963 |
+
"epoch": 3.75,
|
| 964 |
+
"eval_accuracy": 0.888,
|
| 965 |
+
"eval_loss": 0.4779915511608124,
|
| 966 |
+
"eval_runtime": 4.8965,
|
| 967 |
+
"eval_samples_per_second": 51.057,
|
| 968 |
+
"eval_steps_per_second": 1.634,
|
| 969 |
+
"step": 60
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 3.8125,
|
| 973 |
+
"grad_norm": 2.109375,
|
| 974 |
+
"learning_rate": 3.132911392405064e-05,
|
| 975 |
+
"loss": 0.0039,
|
| 976 |
+
"step": 61
|
| 977 |
+
},
|
| 978 |
+
{
|
| 979 |
+
"epoch": 3.8125,
|
| 980 |
+
"eval_accuracy": 0.892,
|
| 981 |
+
"eval_loss": 0.47442150115966797,
|
| 982 |
+
"eval_runtime": 4.8755,
|
| 983 |
+
"eval_samples_per_second": 51.277,
|
| 984 |
+
"eval_steps_per_second": 1.641,
|
| 985 |
+
"step": 61
|
| 986 |
+
},
|
| 987 |
+
{
|
| 988 |
+
"epoch": 3.875,
|
| 989 |
+
"grad_norm": 0.201171875,
|
| 990 |
+
"learning_rate": 3.10126582278481e-05,
|
| 991 |
+
"loss": 0.0007,
|
| 992 |
+
"step": 62
|
| 993 |
+
},
|
| 994 |
+
{
|
| 995 |
+
"epoch": 3.875,
|
| 996 |
+
"eval_accuracy": 0.896,
|
| 997 |
+
"eval_loss": 0.47328320145606995,
|
| 998 |
+
"eval_runtime": 4.8693,
|
| 999 |
+
"eval_samples_per_second": 51.342,
|
| 1000 |
+
"eval_steps_per_second": 1.643,
|
| 1001 |
+
"step": 62
|
| 1002 |
+
},
|
| 1003 |
+
{
|
| 1004 |
+
"epoch": 3.9375,
|
| 1005 |
+
"grad_norm": 0.56640625,
|
| 1006 |
+
"learning_rate": 3.0696202531645574e-05,
|
| 1007 |
+
"loss": 0.0009,
|
| 1008 |
+
"step": 63
|
| 1009 |
+
},
|
| 1010 |
+
{
|
| 1011 |
+
"epoch": 3.9375,
|
| 1012 |
+
"eval_accuracy": 0.896,
|
| 1013 |
+
"eval_loss": 0.4680858850479126,
|
| 1014 |
+
"eval_runtime": 4.8481,
|
| 1015 |
+
"eval_samples_per_second": 51.567,
|
| 1016 |
+
"eval_steps_per_second": 1.65,
|
| 1017 |
+
"step": 63
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 4.0,
|
| 1021 |
+
"grad_norm": 0.259765625,
|
| 1022 |
+
"learning_rate": 3.0379746835443042e-05,
|
| 1023 |
+
"loss": 0.0011,
|
| 1024 |
+
"step": 64
|
| 1025 |
+
},
|
| 1026 |
+
{
|
| 1027 |
+
"epoch": 4.0,
|
| 1028 |
+
"eval_accuracy": 0.9,
|
| 1029 |
+
"eval_loss": 0.46620070934295654,
|
| 1030 |
+
"eval_runtime": 4.8197,
|
| 1031 |
+
"eval_samples_per_second": 51.871,
|
| 1032 |
+
"eval_steps_per_second": 1.66,
|
| 1033 |
+
"step": 64
|
| 1034 |
+
},
|
| 1035 |
+
{
|
| 1036 |
+
"epoch": 4.0625,
|
| 1037 |
+
"grad_norm": 0.01483154296875,
|
| 1038 |
+
"learning_rate": 3.0063291139240506e-05,
|
| 1039 |
+
"loss": 0.0001,
|
| 1040 |
+
"step": 65
|
| 1041 |
+
},
|
| 1042 |
+
{
|
| 1043 |
+
"epoch": 4.0625,
|
| 1044 |
+
"eval_accuracy": 0.904,
|
| 1045 |
+
"eval_loss": 0.47483450174331665,
|
| 1046 |
+
"eval_runtime": 4.8902,
|
| 1047 |
+
"eval_samples_per_second": 51.123,
|
| 1048 |
+
"eval_steps_per_second": 1.636,
|
| 1049 |
+
"step": 65
|
| 1050 |
+
},
|
| 1051 |
+
{
|
| 1052 |
+
"epoch": 4.125,
|
| 1053 |
+
"grad_norm": 0.197265625,
|
| 1054 |
+
"learning_rate": 2.9746835443037974e-05,
|
| 1055 |
+
"loss": 0.0004,
|
| 1056 |
+
"step": 66
|
| 1057 |
+
},
|
| 1058 |
+
{
|
| 1059 |
+
"epoch": 4.125,
|
| 1060 |
+
"eval_accuracy": 0.9,
|
| 1061 |
+
"eval_loss": 0.4847821593284607,
|
| 1062 |
+
"eval_runtime": 4.8909,
|
| 1063 |
+
"eval_samples_per_second": 51.116,
|
| 1064 |
+
"eval_steps_per_second": 1.636,
|
| 1065 |
+
"step": 66
|
| 1066 |
+
},
|
| 1067 |
+
{
|
| 1068 |
+
"epoch": 4.1875,
|
| 1069 |
+
"grad_norm": 0.283203125,
|
| 1070 |
+
"learning_rate": 2.9430379746835446e-05,
|
| 1071 |
+
"loss": 0.0008,
|
| 1072 |
+
"step": 67
|
| 1073 |
+
},
|
| 1074 |
+
{
|
| 1075 |
+
"epoch": 4.1875,
|
| 1076 |
+
"eval_accuracy": 0.9,
|
| 1077 |
+
"eval_loss": 0.49961230158805847,
|
| 1078 |
+
"eval_runtime": 4.8722,
|
| 1079 |
+
"eval_samples_per_second": 51.312,
|
| 1080 |
+
"eval_steps_per_second": 1.642,
|
| 1081 |
+
"step": 67
|
| 1082 |
+
},
|
| 1083 |
+
{
|
| 1084 |
+
"epoch": 4.25,
|
| 1085 |
+
"grad_norm": 0.06103515625,
|
| 1086 |
+
"learning_rate": 2.9113924050632914e-05,
|
| 1087 |
+
"loss": 0.0001,
|
| 1088 |
+
"step": 68
|
| 1089 |
+
},
|
| 1090 |
+
{
|
| 1091 |
+
"epoch": 4.25,
|
| 1092 |
+
"eval_accuracy": 0.904,
|
| 1093 |
+
"eval_loss": 0.5119830965995789,
|
| 1094 |
+
"eval_runtime": 4.872,
|
| 1095 |
+
"eval_samples_per_second": 51.314,
|
| 1096 |
+
"eval_steps_per_second": 1.642,
|
| 1097 |
+
"step": 68
|
| 1098 |
+
},
|
| 1099 |
+
{
|
| 1100 |
+
"epoch": 4.3125,
|
| 1101 |
+
"grad_norm": 0.10302734375,
|
| 1102 |
+
"learning_rate": 2.879746835443038e-05,
|
| 1103 |
+
"loss": 0.0002,
|
| 1104 |
+
"step": 69
|
| 1105 |
+
},
|
| 1106 |
+
{
|
| 1107 |
+
"epoch": 4.3125,
|
| 1108 |
+
"eval_accuracy": 0.904,
|
| 1109 |
+
"eval_loss": 0.5265066623687744,
|
| 1110 |
+
"eval_runtime": 4.8698,
|
| 1111 |
+
"eval_samples_per_second": 51.337,
|
| 1112 |
+
"eval_steps_per_second": 1.643,
|
| 1113 |
+
"step": 69
|
| 1114 |
+
},
|
| 1115 |
+
{
|
| 1116 |
+
"epoch": 4.375,
|
| 1117 |
+
"grad_norm": 0.1904296875,
|
| 1118 |
+
"learning_rate": 2.848101265822785e-05,
|
| 1119 |
+
"loss": 0.0003,
|
| 1120 |
+
"step": 70
|
| 1121 |
+
},
|
| 1122 |
+
{
|
| 1123 |
+
"epoch": 4.375,
|
| 1124 |
+
"eval_accuracy": 0.904,
|
| 1125 |
+
"eval_loss": 0.53618323802948,
|
| 1126 |
+
"eval_runtime": 4.904,
|
| 1127 |
+
"eval_samples_per_second": 50.978,
|
| 1128 |
+
"eval_steps_per_second": 1.631,
|
| 1129 |
+
"step": 70
|
| 1130 |
+
},
|
| 1131 |
+
{
|
| 1132 |
+
"epoch": 4.4375,
|
| 1133 |
+
"grad_norm": 0.31640625,
|
| 1134 |
+
"learning_rate": 2.8164556962025318e-05,
|
| 1135 |
+
"loss": 0.0005,
|
| 1136 |
+
"step": 71
|
| 1137 |
+
},
|
| 1138 |
+
{
|
| 1139 |
+
"epoch": 4.4375,
|
| 1140 |
+
"eval_accuracy": 0.9,
|
| 1141 |
+
"eval_loss": 0.5419101119041443,
|
| 1142 |
+
"eval_runtime": 4.8958,
|
| 1143 |
+
"eval_samples_per_second": 51.064,
|
| 1144 |
+
"eval_steps_per_second": 1.634,
|
| 1145 |
+
"step": 71
|
| 1146 |
+
},
|
| 1147 |
+
{
|
| 1148 |
+
"epoch": 4.5,
|
| 1149 |
+
"grad_norm": 0.55859375,
|
| 1150 |
+
"learning_rate": 2.7848101265822786e-05,
|
| 1151 |
+
"loss": 0.001,
|
| 1152 |
+
"step": 72
|
| 1153 |
+
},
|
| 1154 |
+
{
|
| 1155 |
+
"epoch": 4.5,
|
| 1156 |
+
"eval_accuracy": 0.9,
|
| 1157 |
+
"eval_loss": 0.5409899950027466,
|
| 1158 |
+
"eval_runtime": 4.8722,
|
| 1159 |
+
"eval_samples_per_second": 51.311,
|
| 1160 |
+
"eval_steps_per_second": 1.642,
|
| 1161 |
+
"step": 72
|
| 1162 |
+
},
|
| 1163 |
+
{
|
| 1164 |
+
"epoch": 4.5625,
|
| 1165 |
+
"grad_norm": 0.1376953125,
|
| 1166 |
+
"learning_rate": 2.7531645569620257e-05,
|
| 1167 |
+
"loss": 0.0002,
|
| 1168 |
+
"step": 73
|
| 1169 |
+
},
|
| 1170 |
+
{
|
| 1171 |
+
"epoch": 4.5625,
|
| 1172 |
+
"eval_accuracy": 0.904,
|
| 1173 |
+
"eval_loss": 0.5402071475982666,
|
| 1174 |
+
"eval_runtime": 4.8891,
|
| 1175 |
+
"eval_samples_per_second": 51.135,
|
| 1176 |
+
"eval_steps_per_second": 1.636,
|
| 1177 |
+
"step": 73
|
| 1178 |
+
},
|
| 1179 |
+
{
|
| 1180 |
+
"epoch": 4.625,
|
| 1181 |
+
"grad_norm": 0.107421875,
|
| 1182 |
+
"learning_rate": 2.7215189873417722e-05,
|
| 1183 |
+
"loss": 0.0002,
|
| 1184 |
+
"step": 74
|
| 1185 |
+
},
|
| 1186 |
+
{
|
| 1187 |
+
"epoch": 4.625,
|
| 1188 |
+
"eval_accuracy": 0.904,
|
| 1189 |
+
"eval_loss": 0.5370295643806458,
|
| 1190 |
+
"eval_runtime": 4.8731,
|
| 1191 |
+
"eval_samples_per_second": 51.303,
|
| 1192 |
+
"eval_steps_per_second": 1.642,
|
| 1193 |
+
"step": 74
|
| 1194 |
+
},
|
| 1195 |
+
{
|
| 1196 |
+
"epoch": 4.6875,
|
| 1197 |
+
"grad_norm": 0.34765625,
|
| 1198 |
+
"learning_rate": 2.689873417721519e-05,
|
| 1199 |
+
"loss": 0.0005,
|
| 1200 |
+
"step": 75
|
| 1201 |
+
},
|
| 1202 |
+
{
|
| 1203 |
+
"epoch": 4.6875,
|
| 1204 |
+
"eval_accuracy": 0.904,
|
| 1205 |
+
"eval_loss": 0.5307853817939758,
|
| 1206 |
+
"eval_runtime": 4.868,
|
| 1207 |
+
"eval_samples_per_second": 51.355,
|
| 1208 |
+
"eval_steps_per_second": 1.643,
|
| 1209 |
+
"step": 75
|
| 1210 |
+
},
|
| 1211 |
+
{
|
| 1212 |
+
"epoch": 4.75,
|
| 1213 |
+
"grad_norm": 0.0732421875,
|
| 1214 |
+
"learning_rate": 2.6582278481012658e-05,
|
| 1215 |
+
"loss": 0.0001,
|
| 1216 |
+
"step": 76
|
| 1217 |
+
},
|
| 1218 |
+
{
|
| 1219 |
+
"epoch": 4.75,
|
| 1220 |
+
"eval_accuracy": 0.9,
|
| 1221 |
+
"eval_loss": 0.5289453268051147,
|
| 1222 |
+
"eval_runtime": 4.8663,
|
| 1223 |
+
"eval_samples_per_second": 51.374,
|
| 1224 |
+
"eval_steps_per_second": 1.644,
|
| 1225 |
+
"step": 76
|
| 1226 |
+
},
|
| 1227 |
+
{
|
| 1228 |
+
"epoch": 4.8125,
|
| 1229 |
+
"grad_norm": 0.038818359375,
|
| 1230 |
+
"learning_rate": 2.626582278481013e-05,
|
| 1231 |
+
"loss": 0.0002,
|
| 1232 |
+
"step": 77
|
| 1233 |
+
},
|
| 1234 |
+
{
|
| 1235 |
+
"epoch": 4.8125,
|
| 1236 |
+
"eval_accuracy": 0.896,
|
| 1237 |
+
"eval_loss": 0.5269708037376404,
|
| 1238 |
+
"eval_runtime": 4.9075,
|
| 1239 |
+
"eval_samples_per_second": 50.942,
|
| 1240 |
+
"eval_steps_per_second": 1.63,
|
| 1241 |
+
"step": 77
|
| 1242 |
+
},
|
| 1243 |
+
{
|
| 1244 |
+
"epoch": 4.875,
|
| 1245 |
+
"grad_norm": 0.015380859375,
|
| 1246 |
+
"learning_rate": 2.5949367088607597e-05,
|
| 1247 |
+
"loss": 0.0,
|
| 1248 |
+
"step": 78
|
| 1249 |
+
},
|
| 1250 |
+
{
|
| 1251 |
+
"epoch": 4.875,
|
| 1252 |
+
"eval_accuracy": 0.896,
|
| 1253 |
+
"eval_loss": 0.5278732776641846,
|
| 1254 |
+
"eval_runtime": 4.899,
|
| 1255 |
+
"eval_samples_per_second": 51.031,
|
| 1256 |
+
"eval_steps_per_second": 1.633,
|
| 1257 |
+
"step": 78
|
| 1258 |
+
},
|
| 1259 |
+
{
|
| 1260 |
+
"epoch": 4.9375,
|
| 1261 |
+
"grad_norm": 0.056884765625,
|
| 1262 |
+
"learning_rate": 2.5632911392405062e-05,
|
| 1263 |
+
"loss": 0.0001,
|
| 1264 |
+
"step": 79
|
| 1265 |
+
},
|
| 1266 |
+
{
|
| 1267 |
+
"epoch": 4.9375,
|
| 1268 |
+
"eval_accuracy": 0.896,
|
| 1269 |
+
"eval_loss": 0.5320713520050049,
|
| 1270 |
+
"eval_runtime": 4.824,
|
| 1271 |
+
"eval_samples_per_second": 51.825,
|
| 1272 |
+
"eval_steps_per_second": 1.658,
|
| 1273 |
+
"step": 79
|
| 1274 |
+
},
|
| 1275 |
+
{
|
| 1276 |
+
"epoch": 5.0,
|
| 1277 |
+
"grad_norm": 0.01025390625,
|
| 1278 |
+
"learning_rate": 2.5316455696202533e-05,
|
| 1279 |
+
"loss": 0.0,
|
| 1280 |
+
"step": 80
|
| 1281 |
+
},
|
| 1282 |
+
{
|
| 1283 |
+
"epoch": 5.0,
|
| 1284 |
+
"eval_accuracy": 0.896,
|
| 1285 |
+
"eval_loss": 0.5385279059410095,
|
| 1286 |
+
"eval_runtime": 4.8713,
|
| 1287 |
+
"eval_samples_per_second": 51.321,
|
| 1288 |
+
"eval_steps_per_second": 1.642,
|
| 1289 |
+
"step": 80
|
| 1290 |
+
},
|
| 1291 |
+
{
|
| 1292 |
+
"epoch": 5.0625,
|
| 1293 |
+
"grad_norm": 0.03076171875,
|
| 1294 |
+
"learning_rate": 2.5e-05,
|
| 1295 |
+
"loss": 0.0001,
|
| 1296 |
+
"step": 81
|
| 1297 |
+
},
|
| 1298 |
+
{
|
| 1299 |
+
"epoch": 5.0625,
|
| 1300 |
+
"eval_accuracy": 0.9,
|
| 1301 |
+
"eval_loss": 0.5427132248878479,
|
| 1302 |
+
"eval_runtime": 4.8863,
|
| 1303 |
+
"eval_samples_per_second": 51.163,
|
| 1304 |
+
"eval_steps_per_second": 1.637,
|
| 1305 |
+
"step": 81
|
| 1306 |
+
},
|
| 1307 |
+
{
|
| 1308 |
+
"epoch": 5.125,
|
| 1309 |
+
"grad_norm": 0.010986328125,
|
| 1310 |
+
"learning_rate": 2.468354430379747e-05,
|
| 1311 |
+
"loss": 0.0,
|
| 1312 |
+
"step": 82
|
| 1313 |
+
},
|
| 1314 |
+
{
|
| 1315 |
+
"epoch": 5.125,
|
| 1316 |
+
"eval_accuracy": 0.9,
|
| 1317 |
+
"eval_loss": 0.5424291491508484,
|
| 1318 |
+
"eval_runtime": 4.869,
|
| 1319 |
+
"eval_samples_per_second": 51.345,
|
| 1320 |
+
"eval_steps_per_second": 1.643,
|
| 1321 |
+
"step": 82
|
| 1322 |
+
},
|
| 1323 |
+
{
|
| 1324 |
+
"epoch": 5.1875,
|
| 1325 |
+
"grad_norm": 0.00860595703125,
|
| 1326 |
+
"learning_rate": 2.4367088607594937e-05,
|
| 1327 |
+
"loss": 0.0,
|
| 1328 |
+
"step": 83
|
| 1329 |
+
},
|
| 1330 |
+
{
|
| 1331 |
+
"epoch": 5.1875,
|
| 1332 |
+
"eval_accuracy": 0.904,
|
| 1333 |
+
"eval_loss": 0.5434779524803162,
|
| 1334 |
+
"eval_runtime": 4.8938,
|
| 1335 |
+
"eval_samples_per_second": 51.085,
|
| 1336 |
+
"eval_steps_per_second": 1.635,
|
| 1337 |
+
"step": 83
|
| 1338 |
+
},
|
| 1339 |
+
{
|
| 1340 |
+
"epoch": 5.25,
|
| 1341 |
+
"grad_norm": 0.046630859375,
|
| 1342 |
+
"learning_rate": 2.4050632911392405e-05,
|
| 1343 |
+
"loss": 0.0001,
|
| 1344 |
+
"step": 84
|
| 1345 |
+
},
|
| 1346 |
+
{
|
| 1347 |
+
"epoch": 5.25,
|
| 1348 |
+
"eval_accuracy": 0.9,
|
| 1349 |
+
"eval_loss": 0.552955687046051,
|
| 1350 |
+
"eval_runtime": 4.8992,
|
| 1351 |
+
"eval_samples_per_second": 51.028,
|
| 1352 |
+
"eval_steps_per_second": 1.633,
|
| 1353 |
+
"step": 84
|
| 1354 |
+
},
|
| 1355 |
+
{
|
| 1356 |
+
"epoch": 5.3125,
|
| 1357 |
+
"grad_norm": 0.0242919921875,
|
| 1358 |
+
"learning_rate": 2.3734177215189873e-05,
|
| 1359 |
+
"loss": 0.0001,
|
| 1360 |
+
"step": 85
|
| 1361 |
+
},
|
| 1362 |
+
{
|
| 1363 |
+
"epoch": 5.3125,
|
| 1364 |
+
"eval_accuracy": 0.908,
|
| 1365 |
+
"eval_loss": 0.5524942874908447,
|
| 1366 |
+
"eval_runtime": 4.8893,
|
| 1367 |
+
"eval_samples_per_second": 51.132,
|
| 1368 |
+
"eval_steps_per_second": 1.636,
|
| 1369 |
+
"step": 85
|
| 1370 |
+
},
|
| 1371 |
+
{
|
| 1372 |
+
"epoch": 5.375,
|
| 1373 |
+
"grad_norm": 0.10302734375,
|
| 1374 |
+
"learning_rate": 2.341772151898734e-05,
|
| 1375 |
+
"loss": 0.0002,
|
| 1376 |
+
"step": 86
|
| 1377 |
+
},
|
| 1378 |
+
{
|
| 1379 |
+
"epoch": 5.375,
|
| 1380 |
+
"eval_accuracy": 0.904,
|
| 1381 |
+
"eval_loss": 0.5556187629699707,
|
| 1382 |
+
"eval_runtime": 4.8844,
|
| 1383 |
+
"eval_samples_per_second": 51.184,
|
| 1384 |
+
"eval_steps_per_second": 1.638,
|
| 1385 |
+
"step": 86
|
| 1386 |
+
},
|
| 1387 |
+
{
|
| 1388 |
+
"epoch": 5.4375,
|
| 1389 |
+
"grad_norm": 0.058837890625,
|
| 1390 |
+
"learning_rate": 2.3101265822784813e-05,
|
| 1391 |
+
"loss": 0.0001,
|
| 1392 |
+
"step": 87
|
| 1393 |
+
},
|
| 1394 |
+
{
|
| 1395 |
+
"epoch": 5.4375,
|
| 1396 |
+
"eval_accuracy": 0.904,
|
| 1397 |
+
"eval_loss": 0.5552673935890198,
|
| 1398 |
+
"eval_runtime": 4.8868,
|
| 1399 |
+
"eval_samples_per_second": 51.158,
|
| 1400 |
+
"eval_steps_per_second": 1.637,
|
| 1401 |
+
"step": 87
|
| 1402 |
+
},
|
| 1403 |
+
{
|
| 1404 |
+
"epoch": 5.5,
|
| 1405 |
+
"grad_norm": 0.049560546875,
|
| 1406 |
+
"learning_rate": 2.278481012658228e-05,
|
| 1407 |
+
"loss": 0.0001,
|
| 1408 |
+
"step": 88
|
| 1409 |
+
},
|
| 1410 |
+
{
|
| 1411 |
+
"epoch": 5.5,
|
| 1412 |
+
"eval_accuracy": 0.908,
|
| 1413 |
+
"eval_loss": 0.5524196624755859,
|
| 1414 |
+
"eval_runtime": 4.8881,
|
| 1415 |
+
"eval_samples_per_second": 51.145,
|
| 1416 |
+
"eval_steps_per_second": 1.637,
|
| 1417 |
+
"step": 88
|
| 1418 |
+
},
|
| 1419 |
+
{
|
| 1420 |
+
"epoch": 5.5625,
|
| 1421 |
+
"grad_norm": 0.1201171875,
|
| 1422 |
+
"learning_rate": 2.246835443037975e-05,
|
| 1423 |
+
"loss": 0.0002,
|
| 1424 |
+
"step": 89
|
| 1425 |
+
},
|
| 1426 |
+
{
|
| 1427 |
+
"epoch": 5.5625,
|
| 1428 |
+
"eval_accuracy": 0.904,
|
| 1429 |
+
"eval_loss": 0.5546653866767883,
|
| 1430 |
+
"eval_runtime": 4.888,
|
| 1431 |
+
"eval_samples_per_second": 51.145,
|
| 1432 |
+
"eval_steps_per_second": 1.637,
|
| 1433 |
+
"step": 89
|
| 1434 |
+
},
|
| 1435 |
+
{
|
| 1436 |
+
"epoch": 5.625,
|
| 1437 |
+
"grad_norm": 0.011474609375,
|
| 1438 |
+
"learning_rate": 2.2151898734177217e-05,
|
| 1439 |
+
"loss": 0.0,
|
| 1440 |
+
"step": 90
|
| 1441 |
+
},
|
| 1442 |
+
{
|
| 1443 |
+
"epoch": 5.625,
|
| 1444 |
+
"eval_accuracy": 0.908,
|
| 1445 |
+
"eval_loss": 0.5581926107406616,
|
| 1446 |
+
"eval_runtime": 4.8965,
|
| 1447 |
+
"eval_samples_per_second": 51.056,
|
| 1448 |
+
"eval_steps_per_second": 1.634,
|
| 1449 |
+
"step": 90
|
| 1450 |
+
},
|
| 1451 |
+
{
|
| 1452 |
+
"epoch": 5.6875,
|
| 1453 |
+
"grad_norm": 0.00494384765625,
|
| 1454 |
+
"learning_rate": 2.1835443037974685e-05,
|
| 1455 |
+
"loss": 0.0,
|
| 1456 |
+
"step": 91
|
| 1457 |
+
},
|
| 1458 |
+
{
|
| 1459 |
+
"epoch": 5.6875,
|
| 1460 |
+
"eval_accuracy": 0.904,
|
| 1461 |
+
"eval_loss": 0.5577874779701233,
|
| 1462 |
+
"eval_runtime": 4.8978,
|
| 1463 |
+
"eval_samples_per_second": 51.043,
|
| 1464 |
+
"eval_steps_per_second": 1.633,
|
| 1465 |
+
"step": 91
|
| 1466 |
+
},
|
| 1467 |
+
{
|
| 1468 |
+
"epoch": 5.75,
|
| 1469 |
+
"grad_norm": 0.001556396484375,
|
| 1470 |
+
"learning_rate": 2.1518987341772153e-05,
|
| 1471 |
+
"loss": 0.0,
|
| 1472 |
+
"step": 92
|
| 1473 |
+
},
|
| 1474 |
+
{
|
| 1475 |
+
"epoch": 5.75,
|
| 1476 |
+
"eval_accuracy": 0.908,
|
| 1477 |
+
"eval_loss": 0.5564088821411133,
|
| 1478 |
+
"eval_runtime": 4.9024,
|
| 1479 |
+
"eval_samples_per_second": 50.995,
|
| 1480 |
+
"eval_steps_per_second": 1.632,
|
| 1481 |
+
"step": 92
|
| 1482 |
+
},
|
| 1483 |
+
{
|
| 1484 |
+
"epoch": 5.8125,
|
| 1485 |
+
"grad_norm": 0.04248046875,
|
| 1486 |
+
"learning_rate": 2.120253164556962e-05,
|
| 1487 |
+
"loss": 0.0001,
|
| 1488 |
+
"step": 93
|
| 1489 |
+
},
|
| 1490 |
+
{
|
| 1491 |
+
"epoch": 5.8125,
|
| 1492 |
+
"eval_accuracy": 0.904,
|
| 1493 |
+
"eval_loss": 0.5549535155296326,
|
| 1494 |
+
"eval_runtime": 4.868,
|
| 1495 |
+
"eval_samples_per_second": 51.355,
|
| 1496 |
+
"eval_steps_per_second": 1.643,
|
| 1497 |
+
"step": 93
|
| 1498 |
+
},
|
| 1499 |
+
{
|
| 1500 |
+
"epoch": 5.875,
|
| 1501 |
+
"grad_norm": 0.0031890869140625,
|
| 1502 |
+
"learning_rate": 2.088607594936709e-05,
|
| 1503 |
+
"loss": 0.0,
|
| 1504 |
+
"step": 94
|
| 1505 |
+
},
|
| 1506 |
+
{
|
| 1507 |
+
"epoch": 5.875,
|
| 1508 |
+
"eval_accuracy": 0.908,
|
| 1509 |
+
"eval_loss": 0.5585831999778748,
|
| 1510 |
+
"eval_runtime": 4.8902,
|
| 1511 |
+
"eval_samples_per_second": 51.123,
|
| 1512 |
+
"eval_steps_per_second": 1.636,
|
| 1513 |
+
"step": 94
|
| 1514 |
+
},
|
| 1515 |
+
{
|
| 1516 |
+
"epoch": 5.9375,
|
| 1517 |
+
"grad_norm": 0.0191650390625,
|
| 1518 |
+
"learning_rate": 2.056962025316456e-05,
|
| 1519 |
+
"loss": 0.0,
|
| 1520 |
+
"step": 95
|
| 1521 |
+
},
|
| 1522 |
+
{
|
| 1523 |
+
"epoch": 5.9375,
|
| 1524 |
+
"eval_accuracy": 0.9,
|
| 1525 |
+
"eval_loss": 0.5561901330947876,
|
| 1526 |
+
"eval_runtime": 4.899,
|
| 1527 |
+
"eval_samples_per_second": 51.031,
|
| 1528 |
+
"eval_steps_per_second": 1.633,
|
| 1529 |
+
"step": 95
|
| 1530 |
+
},
|
| 1531 |
+
{
|
| 1532 |
+
"epoch": 6.0,
|
| 1533 |
+
"grad_norm": 0.0301513671875,
|
| 1534 |
+
"learning_rate": 2.0253164556962025e-05,
|
| 1535 |
+
"loss": 0.0001,
|
| 1536 |
+
"step": 96
|
| 1537 |
+
},
|
| 1538 |
+
{
|
| 1539 |
+
"epoch": 6.0,
|
| 1540 |
+
"eval_accuracy": 0.908,
|
| 1541 |
+
"eval_loss": 0.557356595993042,
|
| 1542 |
+
"eval_runtime": 4.8952,
|
| 1543 |
+
"eval_samples_per_second": 51.071,
|
| 1544 |
+
"eval_steps_per_second": 1.634,
|
| 1545 |
+
"step": 96
|
| 1546 |
+
},
|
| 1547 |
+
{
|
| 1548 |
+
"epoch": 6.0625,
|
| 1549 |
+
"grad_norm": 0.0029754638671875,
|
| 1550 |
+
"learning_rate": 1.9936708860759496e-05,
|
| 1551 |
+
"loss": 0.0,
|
| 1552 |
+
"step": 97
|
| 1553 |
+
},
|
| 1554 |
+
{
|
| 1555 |
+
"epoch": 6.0625,
|
| 1556 |
+
"eval_accuracy": 0.9,
|
| 1557 |
+
"eval_loss": 0.557080090045929,
|
| 1558 |
+
"eval_runtime": 4.8905,
|
| 1559 |
+
"eval_samples_per_second": 51.119,
|
| 1560 |
+
"eval_steps_per_second": 1.636,
|
| 1561 |
+
"step": 97
|
| 1562 |
+
},
|
| 1563 |
+
{
|
| 1564 |
+
"epoch": 6.125,
|
| 1565 |
+
"grad_norm": 0.013427734375,
|
| 1566 |
+
"learning_rate": 1.962025316455696e-05,
|
| 1567 |
+
"loss": 0.0,
|
| 1568 |
+
"step": 98
|
| 1569 |
+
},
|
| 1570 |
+
{
|
| 1571 |
+
"epoch": 6.125,
|
| 1572 |
+
"eval_accuracy": 0.9,
|
| 1573 |
+
"eval_loss": 0.5583979487419128,
|
| 1574 |
+
"eval_runtime": 4.8684,
|
| 1575 |
+
"eval_samples_per_second": 51.352,
|
| 1576 |
+
"eval_steps_per_second": 1.643,
|
| 1577 |
+
"step": 98
|
| 1578 |
+
},
|
| 1579 |
+
{
|
| 1580 |
+
"epoch": 6.1875,
|
| 1581 |
+
"grad_norm": 0.0205078125,
|
| 1582 |
+
"learning_rate": 1.9303797468354432e-05,
|
| 1583 |
+
"loss": 0.0,
|
| 1584 |
+
"step": 99
|
| 1585 |
+
},
|
| 1586 |
+
{
|
| 1587 |
+
"epoch": 6.1875,
|
| 1588 |
+
"eval_accuracy": 0.904,
|
| 1589 |
+
"eval_loss": 0.5552465319633484,
|
| 1590 |
+
"eval_runtime": 4.8752,
|
| 1591 |
+
"eval_samples_per_second": 51.28,
|
| 1592 |
+
"eval_steps_per_second": 1.641,
|
| 1593 |
+
"step": 99
|
| 1594 |
+
},
|
| 1595 |
+
{
|
| 1596 |
+
"epoch": 6.25,
|
| 1597 |
+
"grad_norm": 0.03857421875,
|
| 1598 |
+
"learning_rate": 1.89873417721519e-05,
|
| 1599 |
+
"loss": 0.0001,
|
| 1600 |
+
"step": 100
|
| 1601 |
+
},
|
| 1602 |
+
{
|
| 1603 |
+
"epoch": 6.25,
|
| 1604 |
+
"eval_accuracy": 0.904,
|
| 1605 |
+
"eval_loss": 0.5585227608680725,
|
| 1606 |
+
"eval_runtime": 4.8896,
|
| 1607 |
+
"eval_samples_per_second": 51.129,
|
| 1608 |
+
"eval_steps_per_second": 1.636,
|
| 1609 |
+
"step": 100
|
| 1610 |
+
},
|
| 1611 |
+
{
|
| 1612 |
+
"epoch": 6.3125,
|
| 1613 |
+
"grad_norm": 0.047607421875,
|
| 1614 |
+
"learning_rate": 1.8670886075949368e-05,
|
| 1615 |
+
"loss": 0.0001,
|
| 1616 |
+
"step": 101
|
| 1617 |
+
},
|
| 1618 |
+
{
|
| 1619 |
+
"epoch": 6.3125,
|
| 1620 |
+
"eval_accuracy": 0.9,
|
| 1621 |
+
"eval_loss": 0.5532352328300476,
|
| 1622 |
+
"eval_runtime": 4.8702,
|
| 1623 |
+
"eval_samples_per_second": 51.332,
|
| 1624 |
+
"eval_steps_per_second": 1.643,
|
| 1625 |
+
"step": 101
|
| 1626 |
+
},
|
| 1627 |
+
{
|
| 1628 |
+
"epoch": 6.375,
|
| 1629 |
+
"grad_norm": 0.00836181640625,
|
| 1630 |
+
"learning_rate": 1.8354430379746836e-05,
|
| 1631 |
+
"loss": 0.0,
|
| 1632 |
+
"step": 102
|
| 1633 |
+
},
|
| 1634 |
+
{
|
| 1635 |
+
"epoch": 6.375,
|
| 1636 |
+
"eval_accuracy": 0.896,
|
| 1637 |
+
"eval_loss": 0.555249035358429,
|
| 1638 |
+
"eval_runtime": 4.8964,
|
| 1639 |
+
"eval_samples_per_second": 51.058,
|
| 1640 |
+
"eval_steps_per_second": 1.634,
|
| 1641 |
+
"step": 102
|
| 1642 |
+
},
|
| 1643 |
+
{
|
| 1644 |
+
"epoch": 6.4375,
|
| 1645 |
+
"grad_norm": 0.01055908203125,
|
| 1646 |
+
"learning_rate": 1.8037974683544304e-05,
|
| 1647 |
+
"loss": 0.0,
|
| 1648 |
+
"step": 103
|
| 1649 |
+
},
|
| 1650 |
+
{
|
| 1651 |
+
"epoch": 6.4375,
|
| 1652 |
+
"eval_accuracy": 0.896,
|
| 1653 |
+
"eval_loss": 0.556434690952301,
|
| 1654 |
+
"eval_runtime": 4.9004,
|
| 1655 |
+
"eval_samples_per_second": 51.016,
|
| 1656 |
+
"eval_steps_per_second": 1.633,
|
| 1657 |
+
"step": 103
|
| 1658 |
+
},
|
| 1659 |
+
{
|
| 1660 |
+
"epoch": 6.5,
|
| 1661 |
+
"grad_norm": 0.022216796875,
|
| 1662 |
+
"learning_rate": 1.7721518987341772e-05,
|
| 1663 |
+
"loss": 0.0,
|
| 1664 |
+
"step": 104
|
| 1665 |
+
},
|
| 1666 |
+
{
|
| 1667 |
+
"epoch": 6.5,
|
| 1668 |
+
"eval_accuracy": 0.9,
|
| 1669 |
+
"eval_loss": 0.5526236891746521,
|
| 1670 |
+
"eval_runtime": 4.87,
|
| 1671 |
+
"eval_samples_per_second": 51.335,
|
| 1672 |
+
"eval_steps_per_second": 1.643,
|
| 1673 |
+
"step": 104
|
| 1674 |
+
},
|
| 1675 |
+
{
|
| 1676 |
+
"epoch": 6.5625,
|
| 1677 |
+
"grad_norm": 0.0027618408203125,
|
| 1678 |
+
"learning_rate": 1.7405063291139243e-05,
|
| 1679 |
+
"loss": 0.0,
|
| 1680 |
+
"step": 105
|
| 1681 |
+
},
|
| 1682 |
+
{
|
| 1683 |
+
"epoch": 6.5625,
|
| 1684 |
+
"eval_accuracy": 0.904,
|
| 1685 |
+
"eval_loss": 0.5563039779663086,
|
| 1686 |
+
"eval_runtime": 4.892,
|
| 1687 |
+
"eval_samples_per_second": 51.104,
|
| 1688 |
+
"eval_steps_per_second": 1.635,
|
| 1689 |
+
"step": 105
|
| 1690 |
+
},
|
| 1691 |
+
{
|
| 1692 |
+
"epoch": 6.625,
|
| 1693 |
+
"grad_norm": 0.007110595703125,
|
| 1694 |
+
"learning_rate": 1.7088607594936708e-05,
|
| 1695 |
+
"loss": 0.0,
|
| 1696 |
+
"step": 106
|
| 1697 |
+
},
|
| 1698 |
+
{
|
| 1699 |
+
"epoch": 6.625,
|
| 1700 |
+
"eval_accuracy": 0.892,
|
| 1701 |
+
"eval_loss": 0.5540825724601746,
|
| 1702 |
+
"eval_runtime": 4.8978,
|
| 1703 |
+
"eval_samples_per_second": 51.043,
|
| 1704 |
+
"eval_steps_per_second": 1.633,
|
| 1705 |
+
"step": 106
|
| 1706 |
+
},
|
| 1707 |
+
{
|
| 1708 |
+
"epoch": 6.6875,
|
| 1709 |
+
"grad_norm": 0.0031890869140625,
|
| 1710 |
+
"learning_rate": 1.677215189873418e-05,
|
| 1711 |
+
"loss": 0.0,
|
| 1712 |
+
"step": 107
|
| 1713 |
+
},
|
| 1714 |
+
{
|
| 1715 |
+
"epoch": 6.6875,
|
| 1716 |
+
"eval_accuracy": 0.9,
|
| 1717 |
+
"eval_loss": 0.5545496940612793,
|
| 1718 |
+
"eval_runtime": 4.8688,
|
| 1719 |
+
"eval_samples_per_second": 51.347,
|
| 1720 |
+
"eval_steps_per_second": 1.643,
|
| 1721 |
+
"step": 107
|
| 1722 |
+
},
|
| 1723 |
+
{
|
| 1724 |
+
"epoch": 6.75,
|
| 1725 |
+
"grad_norm": 0.0223388671875,
|
| 1726 |
+
"learning_rate": 1.6455696202531644e-05,
|
| 1727 |
+
"loss": 0.0,
|
| 1728 |
+
"step": 108
|
| 1729 |
+
},
|
| 1730 |
+
{
|
| 1731 |
+
"epoch": 6.75,
|
| 1732 |
+
"eval_accuracy": 0.904,
|
| 1733 |
+
"eval_loss": 0.5558124780654907,
|
| 1734 |
+
"eval_runtime": 4.8649,
|
| 1735 |
+
"eval_samples_per_second": 51.389,
|
| 1736 |
+
"eval_steps_per_second": 1.644,
|
| 1737 |
+
"step": 108
|
| 1738 |
+
},
|
| 1739 |
+
{
|
| 1740 |
+
"epoch": 6.8125,
|
| 1741 |
+
"grad_norm": 0.007354736328125,
|
| 1742 |
+
"learning_rate": 1.6139240506329115e-05,
|
| 1743 |
+
"loss": 0.0,
|
| 1744 |
+
"step": 109
|
| 1745 |
+
},
|
| 1746 |
+
{
|
| 1747 |
+
"epoch": 6.8125,
|
| 1748 |
+
"eval_accuracy": 0.904,
|
| 1749 |
+
"eval_loss": 0.5552881956100464,
|
| 1750 |
+
"eval_runtime": 4.8707,
|
| 1751 |
+
"eval_samples_per_second": 51.327,
|
| 1752 |
+
"eval_steps_per_second": 1.642,
|
| 1753 |
+
"step": 109
|
| 1754 |
+
},
|
| 1755 |
+
{
|
| 1756 |
+
"epoch": 6.875,
|
| 1757 |
+
"grad_norm": 0.006011962890625,
|
| 1758 |
+
"learning_rate": 1.5822784810126583e-05,
|
| 1759 |
+
"loss": 0.0,
|
| 1760 |
+
"step": 110
|
| 1761 |
+
},
|
| 1762 |
+
{
|
| 1763 |
+
"epoch": 6.875,
|
| 1764 |
+
"eval_accuracy": 0.896,
|
| 1765 |
+
"eval_loss": 0.5591185092926025,
|
| 1766 |
+
"eval_runtime": 4.8653,
|
| 1767 |
+
"eval_samples_per_second": 51.384,
|
| 1768 |
+
"eval_steps_per_second": 1.644,
|
| 1769 |
+
"step": 110
|
| 1770 |
+
},
|
| 1771 |
+
{
|
| 1772 |
+
"epoch": 6.9375,
|
| 1773 |
+
"grad_norm": 0.03759765625,
|
| 1774 |
+
"learning_rate": 1.550632911392405e-05,
|
| 1775 |
+
"loss": 0.0001,
|
| 1776 |
+
"step": 111
|
| 1777 |
+
},
|
| 1778 |
+
{
|
| 1779 |
+
"epoch": 6.9375,
|
| 1780 |
+
"eval_accuracy": 0.904,
|
| 1781 |
+
"eval_loss": 0.5544008612632751,
|
| 1782 |
+
"eval_runtime": 4.8902,
|
| 1783 |
+
"eval_samples_per_second": 51.122,
|
| 1784 |
+
"eval_steps_per_second": 1.636,
|
| 1785 |
+
"step": 111
|
| 1786 |
+
},
|
| 1787 |
+
{
|
| 1788 |
+
"epoch": 7.0,
|
| 1789 |
+
"grad_norm": 0.00213623046875,
|
| 1790 |
+
"learning_rate": 1.5189873417721521e-05,
|
| 1791 |
+
"loss": 0.0,
|
| 1792 |
+
"step": 112
|
| 1793 |
+
},
|
| 1794 |
+
{
|
| 1795 |
+
"epoch": 7.0,
|
| 1796 |
+
"eval_accuracy": 0.896,
|
| 1797 |
+
"eval_loss": 0.5563123822212219,
|
| 1798 |
+
"eval_runtime": 4.8882,
|
| 1799 |
+
"eval_samples_per_second": 51.143,
|
| 1800 |
+
"eval_steps_per_second": 1.637,
|
| 1801 |
+
"step": 112
|
| 1802 |
+
},
|
| 1803 |
+
{
|
| 1804 |
+
"epoch": 7.0625,
|
| 1805 |
+
"grad_norm": 0.018798828125,
|
| 1806 |
+
"learning_rate": 1.4873417721518987e-05,
|
| 1807 |
+
"loss": 0.0,
|
| 1808 |
+
"step": 113
|
| 1809 |
+
},
|
| 1810 |
+
{
|
| 1811 |
+
"epoch": 7.0625,
|
| 1812 |
+
"eval_accuracy": 0.896,
|
| 1813 |
+
"eval_loss": 0.55401611328125,
|
| 1814 |
+
"eval_runtime": 4.8635,
|
| 1815 |
+
"eval_samples_per_second": 51.403,
|
| 1816 |
+
"eval_steps_per_second": 1.645,
|
| 1817 |
+
"step": 113
|
| 1818 |
+
},
|
| 1819 |
+
{
|
| 1820 |
+
"epoch": 7.125,
|
| 1821 |
+
"grad_norm": 0.0458984375,
|
| 1822 |
+
"learning_rate": 1.4556962025316457e-05,
|
| 1823 |
+
"loss": 0.0001,
|
| 1824 |
+
"step": 114
|
| 1825 |
+
},
|
| 1826 |
+
{
|
| 1827 |
+
"epoch": 7.125,
|
| 1828 |
+
"eval_accuracy": 0.896,
|
| 1829 |
+
"eval_loss": 0.5561829805374146,
|
| 1830 |
+
"eval_runtime": 4.8843,
|
| 1831 |
+
"eval_samples_per_second": 51.184,
|
| 1832 |
+
"eval_steps_per_second": 1.638,
|
| 1833 |
+
"step": 114
|
| 1834 |
+
},
|
| 1835 |
+
{
|
| 1836 |
+
"epoch": 7.1875,
|
| 1837 |
+
"grad_norm": 0.01336669921875,
|
| 1838 |
+
"learning_rate": 1.4240506329113925e-05,
|
| 1839 |
+
"loss": 0.0,
|
| 1840 |
+
"step": 115
|
| 1841 |
+
},
|
| 1842 |
+
{
|
| 1843 |
+
"epoch": 7.1875,
|
| 1844 |
+
"eval_accuracy": 0.9,
|
| 1845 |
+
"eval_loss": 0.5537428855895996,
|
| 1846 |
+
"eval_runtime": 4.8887,
|
| 1847 |
+
"eval_samples_per_second": 51.138,
|
| 1848 |
+
"eval_steps_per_second": 1.636,
|
| 1849 |
+
"step": 115
|
| 1850 |
+
},
|
| 1851 |
+
{
|
| 1852 |
+
"epoch": 7.25,
|
| 1853 |
+
"grad_norm": 0.0113525390625,
|
| 1854 |
+
"learning_rate": 1.3924050632911393e-05,
|
| 1855 |
+
"loss": 0.0,
|
| 1856 |
+
"step": 116
|
| 1857 |
+
},
|
| 1858 |
+
{
|
| 1859 |
+
"epoch": 7.25,
|
| 1860 |
+
"eval_accuracy": 0.896,
|
| 1861 |
+
"eval_loss": 0.5549358129501343,
|
| 1862 |
+
"eval_runtime": 4.8909,
|
| 1863 |
+
"eval_samples_per_second": 51.115,
|
| 1864 |
+
"eval_steps_per_second": 1.636,
|
| 1865 |
+
"step": 116
|
| 1866 |
+
},
|
| 1867 |
+
{
|
| 1868 |
+
"epoch": 7.3125,
|
| 1869 |
+
"grad_norm": 0.00762939453125,
|
| 1870 |
+
"learning_rate": 1.3607594936708861e-05,
|
| 1871 |
+
"loss": 0.0,
|
| 1872 |
+
"step": 117
|
| 1873 |
+
},
|
| 1874 |
+
{
|
| 1875 |
+
"epoch": 7.3125,
|
| 1876 |
+
"eval_accuracy": 0.904,
|
| 1877 |
+
"eval_loss": 0.5518209338188171,
|
| 1878 |
+
"eval_runtime": 4.8812,
|
| 1879 |
+
"eval_samples_per_second": 51.217,
|
| 1880 |
+
"eval_steps_per_second": 1.639,
|
| 1881 |
+
"step": 117
|
| 1882 |
+
},
|
| 1883 |
+
{
|
| 1884 |
+
"epoch": 7.375,
|
| 1885 |
+
"grad_norm": 0.0038604736328125,
|
| 1886 |
+
"learning_rate": 1.3291139240506329e-05,
|
| 1887 |
+
"loss": 0.0,
|
| 1888 |
+
"step": 118
|
| 1889 |
+
},
|
| 1890 |
+
{
|
| 1891 |
+
"epoch": 7.375,
|
| 1892 |
+
"eval_accuracy": 0.9,
|
| 1893 |
+
"eval_loss": 0.5559548139572144,
|
| 1894 |
+
"eval_runtime": 4.889,
|
| 1895 |
+
"eval_samples_per_second": 51.135,
|
| 1896 |
+
"eval_steps_per_second": 1.636,
|
| 1897 |
+
"step": 118
|
| 1898 |
+
},
|
| 1899 |
+
{
|
| 1900 |
+
"epoch": 7.4375,
|
| 1901 |
+
"grad_norm": 0.0196533203125,
|
| 1902 |
+
"learning_rate": 1.2974683544303799e-05,
|
| 1903 |
+
"loss": 0.0,
|
| 1904 |
+
"step": 119
|
| 1905 |
+
},
|
| 1906 |
+
{
|
| 1907 |
+
"epoch": 7.4375,
|
| 1908 |
+
"eval_accuracy": 0.896,
|
| 1909 |
+
"eval_loss": 0.5553652048110962,
|
| 1910 |
+
"eval_runtime": 4.8764,
|
| 1911 |
+
"eval_samples_per_second": 51.268,
|
| 1912 |
+
"eval_steps_per_second": 1.641,
|
| 1913 |
+
"step": 119
|
| 1914 |
+
},
|
| 1915 |
+
{
|
| 1916 |
+
"epoch": 7.5,
|
| 1917 |
+
"grad_norm": 0.00958251953125,
|
| 1918 |
+
"learning_rate": 1.2658227848101267e-05,
|
| 1919 |
+
"loss": 0.0,
|
| 1920 |
+
"step": 120
|
| 1921 |
+
},
|
| 1922 |
+
{
|
| 1923 |
+
"epoch": 7.5,
|
| 1924 |
+
"eval_accuracy": 0.9,
|
| 1925 |
+
"eval_loss": 0.5554091930389404,
|
| 1926 |
+
"eval_runtime": 4.8866,
|
| 1927 |
+
"eval_samples_per_second": 51.161,
|
| 1928 |
+
"eval_steps_per_second": 1.637,
|
| 1929 |
+
"step": 120
|
| 1930 |
+
},
|
| 1931 |
+
{
|
| 1932 |
+
"epoch": 7.5625,
|
| 1933 |
+
"grad_norm": 0.0029754638671875,
|
| 1934 |
+
"learning_rate": 1.2341772151898735e-05,
|
| 1935 |
+
"loss": 0.0,
|
| 1936 |
+
"step": 121
|
| 1937 |
+
},
|
| 1938 |
+
{
|
| 1939 |
+
"epoch": 7.5625,
|
| 1940 |
+
"eval_accuracy": 0.9,
|
| 1941 |
+
"eval_loss": 0.5547875761985779,
|
| 1942 |
+
"eval_runtime": 4.8661,
|
| 1943 |
+
"eval_samples_per_second": 51.376,
|
| 1944 |
+
"eval_steps_per_second": 1.644,
|
| 1945 |
+
"step": 121
|
| 1946 |
+
},
|
| 1947 |
+
{
|
| 1948 |
+
"epoch": 7.625,
|
| 1949 |
+
"grad_norm": 0.001556396484375,
|
| 1950 |
+
"learning_rate": 1.2025316455696203e-05,
|
| 1951 |
+
"loss": 0.0,
|
| 1952 |
+
"step": 122
|
| 1953 |
+
},
|
| 1954 |
+
{
|
| 1955 |
+
"epoch": 7.625,
|
| 1956 |
+
"eval_accuracy": 0.9,
|
| 1957 |
+
"eval_loss": 0.55680251121521,
|
| 1958 |
+
"eval_runtime": 4.8915,
|
| 1959 |
+
"eval_samples_per_second": 51.109,
|
| 1960 |
+
"eval_steps_per_second": 1.635,
|
| 1961 |
+
"step": 122
|
| 1962 |
+
},
|
| 1963 |
+
{
|
| 1964 |
+
"epoch": 7.6875,
|
| 1965 |
+
"grad_norm": 0.0174560546875,
|
| 1966 |
+
"learning_rate": 1.170886075949367e-05,
|
| 1967 |
+
"loss": 0.0001,
|
| 1968 |
+
"step": 123
|
| 1969 |
+
},
|
| 1970 |
+
{
|
| 1971 |
+
"epoch": 7.6875,
|
| 1972 |
+
"eval_accuracy": 0.9,
|
| 1973 |
+
"eval_loss": 0.5555019378662109,
|
| 1974 |
+
"eval_runtime": 4.8666,
|
| 1975 |
+
"eval_samples_per_second": 51.371,
|
| 1976 |
+
"eval_steps_per_second": 1.644,
|
| 1977 |
+
"step": 123
|
| 1978 |
+
},
|
| 1979 |
+
{
|
| 1980 |
+
"epoch": 7.75,
|
| 1981 |
+
"grad_norm": 0.02734375,
|
| 1982 |
+
"learning_rate": 1.139240506329114e-05,
|
| 1983 |
+
"loss": 0.0001,
|
| 1984 |
+
"step": 124
|
| 1985 |
+
},
|
| 1986 |
+
{
|
| 1987 |
+
"epoch": 7.75,
|
| 1988 |
+
"eval_accuracy": 0.896,
|
| 1989 |
+
"eval_loss": 0.5568622946739197,
|
| 1990 |
+
"eval_runtime": 4.865,
|
| 1991 |
+
"eval_samples_per_second": 51.387,
|
| 1992 |
+
"eval_steps_per_second": 1.644,
|
| 1993 |
+
"step": 124
|
| 1994 |
+
},
|
| 1995 |
+
{
|
| 1996 |
+
"epoch": 7.8125,
|
| 1997 |
+
"grad_norm": 0.0242919921875,
|
| 1998 |
+
"learning_rate": 1.1075949367088608e-05,
|
| 1999 |
+
"loss": 0.0,
|
| 2000 |
+
"step": 125
|
| 2001 |
+
},
|
| 2002 |
+
{
|
| 2003 |
+
"epoch": 7.8125,
|
| 2004 |
+
"eval_accuracy": 0.9,
|
| 2005 |
+
"eval_loss": 0.5577536821365356,
|
| 2006 |
+
"eval_runtime": 4.8877,
|
| 2007 |
+
"eval_samples_per_second": 51.149,
|
| 2008 |
+
"eval_steps_per_second": 1.637,
|
| 2009 |
+
"step": 125
|
| 2010 |
+
},
|
| 2011 |
+
{
|
| 2012 |
+
"epoch": 7.875,
|
| 2013 |
+
"grad_norm": 0.0020904541015625,
|
| 2014 |
+
"learning_rate": 1.0759493670886076e-05,
|
| 2015 |
+
"loss": 0.0,
|
| 2016 |
+
"step": 126
|
| 2017 |
+
},
|
| 2018 |
+
{
|
| 2019 |
+
"epoch": 7.875,
|
| 2020 |
+
"eval_accuracy": 0.896,
|
| 2021 |
+
"eval_loss": 0.5592789649963379,
|
| 2022 |
+
"eval_runtime": 4.8614,
|
| 2023 |
+
"eval_samples_per_second": 51.425,
|
| 2024 |
+
"eval_steps_per_second": 1.646,
|
| 2025 |
+
"step": 126
|
| 2026 |
+
},
|
| 2027 |
+
{
|
| 2028 |
+
"epoch": 7.9375,
|
| 2029 |
+
"grad_norm": 0.00732421875,
|
| 2030 |
+
"learning_rate": 1.0443037974683544e-05,
|
| 2031 |
+
"loss": 0.0,
|
| 2032 |
+
"step": 127
|
| 2033 |
+
},
|
| 2034 |
+
{
|
| 2035 |
+
"epoch": 7.9375,
|
| 2036 |
+
"eval_accuracy": 0.9,
|
| 2037 |
+
"eval_loss": 0.556476891040802,
|
| 2038 |
+
"eval_runtime": 4.892,
|
| 2039 |
+
"eval_samples_per_second": 51.104,
|
| 2040 |
+
"eval_steps_per_second": 1.635,
|
| 2041 |
+
"step": 127
|
| 2042 |
+
},
|
| 2043 |
+
{
|
| 2044 |
+
"epoch": 8.0,
|
| 2045 |
+
"grad_norm": 0.001861572265625,
|
| 2046 |
+
"learning_rate": 1.0126582278481012e-05,
|
| 2047 |
+
"loss": 0.0,
|
| 2048 |
+
"step": 128
|
| 2049 |
+
},
|
| 2050 |
+
{
|
| 2051 |
+
"epoch": 8.0,
|
| 2052 |
+
"eval_accuracy": 0.9,
|
| 2053 |
+
"eval_loss": 0.555403470993042,
|
| 2054 |
+
"eval_runtime": 4.8901,
|
| 2055 |
+
"eval_samples_per_second": 51.123,
|
| 2056 |
+
"eval_steps_per_second": 1.636,
|
| 2057 |
+
"step": 128
|
| 2058 |
+
},
|
| 2059 |
+
{
|
| 2060 |
+
"epoch": 8.0625,
|
| 2061 |
+
"grad_norm": 0.0111083984375,
|
| 2062 |
+
"learning_rate": 9.81012658227848e-06,
|
| 2063 |
+
"loss": 0.0,
|
| 2064 |
+
"step": 129
|
| 2065 |
+
},
|
| 2066 |
+
{
|
| 2067 |
+
"epoch": 8.0625,
|
| 2068 |
+
"eval_accuracy": 0.904,
|
| 2069 |
+
"eval_loss": 0.5534031987190247,
|
| 2070 |
+
"eval_runtime": 4.8858,
|
| 2071 |
+
"eval_samples_per_second": 51.169,
|
| 2072 |
+
"eval_steps_per_second": 1.637,
|
| 2073 |
+
"step": 129
|
| 2074 |
+
},
|
| 2075 |
+
{
|
| 2076 |
+
"epoch": 8.125,
|
| 2077 |
+
"grad_norm": 0.00604248046875,
|
| 2078 |
+
"learning_rate": 9.49367088607595e-06,
|
| 2079 |
+
"loss": 0.0,
|
| 2080 |
+
"step": 130
|
| 2081 |
+
},
|
| 2082 |
+
{
|
| 2083 |
+
"epoch": 8.125,
|
| 2084 |
+
"eval_accuracy": 0.9,
|
| 2085 |
+
"eval_loss": 0.5557398796081543,
|
| 2086 |
+
"eval_runtime": 4.8638,
|
| 2087 |
+
"eval_samples_per_second": 51.4,
|
| 2088 |
+
"eval_steps_per_second": 1.645,
|
| 2089 |
+
"step": 130
|
| 2090 |
+
},
|
| 2091 |
+
{
|
| 2092 |
+
"epoch": 8.1875,
|
| 2093 |
+
"grad_norm": 0.008544921875,
|
| 2094 |
+
"learning_rate": 9.177215189873418e-06,
|
| 2095 |
+
"loss": 0.0,
|
| 2096 |
+
"step": 131
|
| 2097 |
+
},
|
| 2098 |
+
{
|
| 2099 |
+
"epoch": 8.1875,
|
| 2100 |
+
"eval_accuracy": 0.9,
|
| 2101 |
+
"eval_loss": 0.5564188361167908,
|
| 2102 |
+
"eval_runtime": 4.8832,
|
| 2103 |
+
"eval_samples_per_second": 51.196,
|
| 2104 |
+
"eval_steps_per_second": 1.638,
|
| 2105 |
+
"step": 131
|
| 2106 |
+
},
|
| 2107 |
+
{
|
| 2108 |
+
"epoch": 8.25,
|
| 2109 |
+
"grad_norm": 0.003875732421875,
|
| 2110 |
+
"learning_rate": 8.860759493670886e-06,
|
| 2111 |
+
"loss": 0.0,
|
| 2112 |
+
"step": 132
|
| 2113 |
+
},
|
| 2114 |
+
{
|
| 2115 |
+
"epoch": 8.25,
|
| 2116 |
+
"eval_accuracy": 0.9,
|
| 2117 |
+
"eval_loss": 0.5545617938041687,
|
| 2118 |
+
"eval_runtime": 4.8916,
|
| 2119 |
+
"eval_samples_per_second": 51.108,
|
| 2120 |
+
"eval_steps_per_second": 1.635,
|
| 2121 |
+
"step": 132
|
| 2122 |
+
},
|
| 2123 |
+
{
|
| 2124 |
+
"epoch": 8.3125,
|
| 2125 |
+
"grad_norm": 0.0322265625,
|
| 2126 |
+
"learning_rate": 8.544303797468354e-06,
|
| 2127 |
+
"loss": 0.0001,
|
| 2128 |
+
"step": 133
|
| 2129 |
+
},
|
| 2130 |
+
{
|
| 2131 |
+
"epoch": 8.3125,
|
| 2132 |
+
"eval_accuracy": 0.9,
|
| 2133 |
+
"eval_loss": 0.5550633668899536,
|
| 2134 |
+
"eval_runtime": 4.8868,
|
| 2135 |
+
"eval_samples_per_second": 51.158,
|
| 2136 |
+
"eval_steps_per_second": 1.637,
|
| 2137 |
+
"step": 133
|
| 2138 |
+
},
|
| 2139 |
+
{
|
| 2140 |
+
"epoch": 8.375,
|
| 2141 |
+
"grad_norm": 0.0296630859375,
|
| 2142 |
+
"learning_rate": 8.227848101265822e-06,
|
| 2143 |
+
"loss": 0.0001,
|
| 2144 |
+
"step": 134
|
| 2145 |
+
},
|
| 2146 |
+
{
|
| 2147 |
+
"epoch": 8.375,
|
| 2148 |
+
"eval_accuracy": 0.9,
|
| 2149 |
+
"eval_loss": 0.553980827331543,
|
| 2150 |
+
"eval_runtime": 4.8628,
|
| 2151 |
+
"eval_samples_per_second": 51.411,
|
| 2152 |
+
"eval_steps_per_second": 1.645,
|
| 2153 |
+
"step": 134
|
| 2154 |
+
},
|
| 2155 |
+
{
|
| 2156 |
+
"epoch": 8.4375,
|
| 2157 |
+
"grad_norm": 0.00396728515625,
|
| 2158 |
+
"learning_rate": 7.911392405063292e-06,
|
| 2159 |
+
"loss": 0.0,
|
| 2160 |
+
"step": 135
|
| 2161 |
+
},
|
| 2162 |
+
{
|
| 2163 |
+
"epoch": 8.4375,
|
| 2164 |
+
"eval_accuracy": 0.9,
|
| 2165 |
+
"eval_loss": 0.5577096939086914,
|
| 2166 |
+
"eval_runtime": 4.8664,
|
| 2167 |
+
"eval_samples_per_second": 51.372,
|
| 2168 |
+
"eval_steps_per_second": 1.644,
|
| 2169 |
+
"step": 135
|
| 2170 |
+
},
|
| 2171 |
+
{
|
| 2172 |
+
"epoch": 8.5,
|
| 2173 |
+
"grad_norm": 0.00089263916015625,
|
| 2174 |
+
"learning_rate": 7.5949367088607605e-06,
|
| 2175 |
+
"loss": 0.0,
|
| 2176 |
+
"step": 136
|
| 2177 |
+
},
|
| 2178 |
+
{
|
| 2179 |
+
"epoch": 8.5,
|
| 2180 |
+
"eval_accuracy": 0.9,
|
| 2181 |
+
"eval_loss": 0.5528184771537781,
|
| 2182 |
+
"eval_runtime": 4.8633,
|
| 2183 |
+
"eval_samples_per_second": 51.405,
|
| 2184 |
+
"eval_steps_per_second": 1.645,
|
| 2185 |
+
"step": 136
|
| 2186 |
+
},
|
| 2187 |
+
{
|
| 2188 |
+
"epoch": 8.5625,
|
| 2189 |
+
"grad_norm": 0.01080322265625,
|
| 2190 |
+
"learning_rate": 7.2784810126582285e-06,
|
| 2191 |
+
"loss": 0.0,
|
| 2192 |
+
"step": 137
|
| 2193 |
+
},
|
| 2194 |
+
{
|
| 2195 |
+
"epoch": 8.5625,
|
| 2196 |
+
"eval_accuracy": 0.896,
|
| 2197 |
+
"eval_loss": 0.5544995069503784,
|
| 2198 |
+
"eval_runtime": 4.8638,
|
| 2199 |
+
"eval_samples_per_second": 51.4,
|
| 2200 |
+
"eval_steps_per_second": 1.645,
|
| 2201 |
+
"step": 137
|
| 2202 |
+
},
|
| 2203 |
+
{
|
| 2204 |
+
"epoch": 8.625,
|
| 2205 |
+
"grad_norm": 0.006561279296875,
|
| 2206 |
+
"learning_rate": 6.9620253164556965e-06,
|
| 2207 |
+
"loss": 0.0,
|
| 2208 |
+
"step": 138
|
| 2209 |
+
},
|
| 2210 |
+
{
|
| 2211 |
+
"epoch": 8.625,
|
| 2212 |
+
"eval_accuracy": 0.896,
|
| 2213 |
+
"eval_loss": 0.5562748908996582,
|
| 2214 |
+
"eval_runtime": 4.8677,
|
| 2215 |
+
"eval_samples_per_second": 51.359,
|
| 2216 |
+
"eval_steps_per_second": 1.643,
|
| 2217 |
+
"step": 138
|
| 2218 |
+
},
|
| 2219 |
+
{
|
| 2220 |
+
"epoch": 8.6875,
|
| 2221 |
+
"grad_norm": 0.01007080078125,
|
| 2222 |
+
"learning_rate": 6.6455696202531645e-06,
|
| 2223 |
+
"loss": 0.0,
|
| 2224 |
+
"step": 139
|
| 2225 |
+
},
|
| 2226 |
+
{
|
| 2227 |
+
"epoch": 8.6875,
|
| 2228 |
+
"eval_accuracy": 0.9,
|
| 2229 |
+
"eval_loss": 0.5547692775726318,
|
| 2230 |
+
"eval_runtime": 4.8897,
|
| 2231 |
+
"eval_samples_per_second": 51.128,
|
| 2232 |
+
"eval_steps_per_second": 1.636,
|
| 2233 |
+
"step": 139
|
| 2234 |
+
},
|
| 2235 |
+
{
|
| 2236 |
+
"epoch": 8.75,
|
| 2237 |
+
"grad_norm": 0.01171875,
|
| 2238 |
+
"learning_rate": 6.329113924050633e-06,
|
| 2239 |
+
"loss": 0.0,
|
| 2240 |
+
"step": 140
|
| 2241 |
+
},
|
| 2242 |
+
{
|
| 2243 |
+
"epoch": 8.75,
|
| 2244 |
+
"eval_accuracy": 0.9,
|
| 2245 |
+
"eval_loss": 0.5561813712120056,
|
| 2246 |
+
"eval_runtime": 4.8875,
|
| 2247 |
+
"eval_samples_per_second": 51.151,
|
| 2248 |
+
"eval_steps_per_second": 1.637,
|
| 2249 |
+
"step": 140
|
| 2250 |
+
},
|
| 2251 |
+
{
|
| 2252 |
+
"epoch": 8.8125,
|
| 2253 |
+
"grad_norm": 0.0166015625,
|
| 2254 |
+
"learning_rate": 6.012658227848101e-06,
|
| 2255 |
+
"loss": 0.0,
|
| 2256 |
+
"step": 141
|
| 2257 |
+
},
|
| 2258 |
+
{
|
| 2259 |
+
"epoch": 8.8125,
|
| 2260 |
+
"eval_accuracy": 0.896,
|
| 2261 |
+
"eval_loss": 0.5564705729484558,
|
| 2262 |
+
"eval_runtime": 4.8825,
|
| 2263 |
+
"eval_samples_per_second": 51.203,
|
| 2264 |
+
"eval_steps_per_second": 1.638,
|
| 2265 |
+
"step": 141
|
| 2266 |
+
},
|
| 2267 |
+
{
|
| 2268 |
+
"epoch": 8.875,
|
| 2269 |
+
"grad_norm": 0.002777099609375,
|
| 2270 |
+
"learning_rate": 5.69620253164557e-06,
|
| 2271 |
+
"loss": 0.0,
|
| 2272 |
+
"step": 142
|
| 2273 |
+
},
|
| 2274 |
+
{
|
| 2275 |
+
"epoch": 8.875,
|
| 2276 |
+
"eval_accuracy": 0.896,
|
| 2277 |
+
"eval_loss": 0.5576943159103394,
|
| 2278 |
+
"eval_runtime": 4.8931,
|
| 2279 |
+
"eval_samples_per_second": 51.092,
|
| 2280 |
+
"eval_steps_per_second": 1.635,
|
| 2281 |
+
"step": 142
|
| 2282 |
+
},
|
| 2283 |
+
{
|
| 2284 |
+
"epoch": 8.9375,
|
| 2285 |
+
"grad_norm": 0.048583984375,
|
| 2286 |
+
"learning_rate": 5.379746835443038e-06,
|
| 2287 |
+
"loss": 0.0001,
|
| 2288 |
+
"step": 143
|
| 2289 |
+
},
|
| 2290 |
+
{
|
| 2291 |
+
"epoch": 8.9375,
|
| 2292 |
+
"eval_accuracy": 0.9,
|
| 2293 |
+
"eval_loss": 0.5525559186935425,
|
| 2294 |
+
"eval_runtime": 4.8612,
|
| 2295 |
+
"eval_samples_per_second": 51.427,
|
| 2296 |
+
"eval_steps_per_second": 1.646,
|
| 2297 |
+
"step": 143
|
| 2298 |
+
},
|
| 2299 |
+
{
|
| 2300 |
+
"epoch": 9.0,
|
| 2301 |
+
"grad_norm": 0.0019683837890625,
|
| 2302 |
+
"learning_rate": 5.063291139240506e-06,
|
| 2303 |
+
"loss": 0.0,
|
| 2304 |
+
"step": 144
|
| 2305 |
+
},
|
| 2306 |
+
{
|
| 2307 |
+
"epoch": 9.0,
|
| 2308 |
+
"eval_accuracy": 0.9,
|
| 2309 |
+
"eval_loss": 0.5553069710731506,
|
| 2310 |
+
"eval_runtime": 4.8923,
|
| 2311 |
+
"eval_samples_per_second": 51.101,
|
| 2312 |
+
"eval_steps_per_second": 1.635,
|
| 2313 |
+
"step": 144
|
| 2314 |
+
},
|
| 2315 |
+
{
|
| 2316 |
+
"epoch": 9.0625,
|
| 2317 |
+
"grad_norm": 0.0279541015625,
|
| 2318 |
+
"learning_rate": 4.746835443037975e-06,
|
| 2319 |
+
"loss": 0.0,
|
| 2320 |
+
"step": 145
|
| 2321 |
+
},
|
| 2322 |
+
{
|
| 2323 |
+
"epoch": 9.0625,
|
| 2324 |
+
"eval_accuracy": 0.9,
|
| 2325 |
+
"eval_loss": 0.5583046078681946,
|
| 2326 |
+
"eval_runtime": 4.8879,
|
| 2327 |
+
"eval_samples_per_second": 51.147,
|
| 2328 |
+
"eval_steps_per_second": 1.637,
|
| 2329 |
+
"step": 145
|
| 2330 |
+
},
|
| 2331 |
+
{
|
| 2332 |
+
"epoch": 9.125,
|
| 2333 |
+
"grad_norm": 0.0130615234375,
|
| 2334 |
+
"learning_rate": 4.430379746835443e-06,
|
| 2335 |
+
"loss": 0.0,
|
| 2336 |
+
"step": 146
|
| 2337 |
+
},
|
| 2338 |
+
{
|
| 2339 |
+
"epoch": 9.125,
|
| 2340 |
+
"eval_accuracy": 0.9,
|
| 2341 |
+
"eval_loss": 0.5578604936599731,
|
| 2342 |
+
"eval_runtime": 4.8946,
|
| 2343 |
+
"eval_samples_per_second": 51.077,
|
| 2344 |
+
"eval_steps_per_second": 1.634,
|
| 2345 |
+
"step": 146
|
| 2346 |
+
},
|
| 2347 |
+
{
|
| 2348 |
+
"epoch": 9.1875,
|
| 2349 |
+
"grad_norm": 0.00732421875,
|
| 2350 |
+
"learning_rate": 4.113924050632911e-06,
|
| 2351 |
+
"loss": 0.0,
|
| 2352 |
+
"step": 147
|
| 2353 |
+
},
|
| 2354 |
+
{
|
| 2355 |
+
"epoch": 9.1875,
|
| 2356 |
+
"eval_accuracy": 0.9,
|
| 2357 |
+
"eval_loss": 0.5572697520256042,
|
| 2358 |
+
"eval_runtime": 4.8664,
|
| 2359 |
+
"eval_samples_per_second": 51.372,
|
| 2360 |
+
"eval_steps_per_second": 1.644,
|
| 2361 |
+
"step": 147
|
| 2362 |
+
},
|
| 2363 |
+
{
|
| 2364 |
+
"epoch": 9.25,
|
| 2365 |
+
"grad_norm": 0.004364013671875,
|
| 2366 |
+
"learning_rate": 3.7974683544303802e-06,
|
| 2367 |
+
"loss": 0.0,
|
| 2368 |
+
"step": 148
|
| 2369 |
+
},
|
| 2370 |
+
{
|
| 2371 |
+
"epoch": 9.25,
|
| 2372 |
+
"eval_accuracy": 0.9,
|
| 2373 |
+
"eval_loss": 0.5586851835250854,
|
| 2374 |
+
"eval_runtime": 4.8653,
|
| 2375 |
+
"eval_samples_per_second": 51.384,
|
| 2376 |
+
"eval_steps_per_second": 1.644,
|
| 2377 |
+
"step": 148
|
| 2378 |
+
},
|
| 2379 |
+
{
|
| 2380 |
+
"epoch": 9.3125,
|
| 2381 |
+
"grad_norm": 0.010986328125,
|
| 2382 |
+
"learning_rate": 3.4810126582278482e-06,
|
| 2383 |
+
"loss": 0.0,
|
| 2384 |
+
"step": 149
|
| 2385 |
+
},
|
| 2386 |
+
{
|
| 2387 |
+
"epoch": 9.3125,
|
| 2388 |
+
"eval_accuracy": 0.9,
|
| 2389 |
+
"eval_loss": 0.5570804476737976,
|
| 2390 |
+
"eval_runtime": 4.8876,
|
| 2391 |
+
"eval_samples_per_second": 51.15,
|
| 2392 |
+
"eval_steps_per_second": 1.637,
|
| 2393 |
+
"step": 149
|
| 2394 |
+
},
|
| 2395 |
+
{
|
| 2396 |
+
"epoch": 9.375,
|
| 2397 |
+
"grad_norm": 0.0025787353515625,
|
| 2398 |
+
"learning_rate": 3.1645569620253167e-06,
|
| 2399 |
+
"loss": 0.0,
|
| 2400 |
+
"step": 150
|
| 2401 |
+
},
|
| 2402 |
+
{
|
| 2403 |
+
"epoch": 9.375,
|
| 2404 |
+
"eval_accuracy": 0.9,
|
| 2405 |
+
"eval_loss": 0.5560451745986938,
|
| 2406 |
+
"eval_runtime": 4.8867,
|
| 2407 |
+
"eval_samples_per_second": 51.159,
|
| 2408 |
+
"eval_steps_per_second": 1.637,
|
| 2409 |
+
"step": 150
|
| 2410 |
+
},
|
| 2411 |
+
{
|
| 2412 |
+
"epoch": 9.4375,
|
| 2413 |
+
"grad_norm": 0.00616455078125,
|
| 2414 |
+
"learning_rate": 2.848101265822785e-06,
|
| 2415 |
+
"loss": 0.0,
|
| 2416 |
+
"step": 151
|
| 2417 |
+
},
|
| 2418 |
+
{
|
| 2419 |
+
"epoch": 9.4375,
|
| 2420 |
+
"eval_accuracy": 0.896,
|
| 2421 |
+
"eval_loss": 0.5584925413131714,
|
| 2422 |
+
"eval_runtime": 4.8614,
|
| 2423 |
+
"eval_samples_per_second": 51.425,
|
| 2424 |
+
"eval_steps_per_second": 1.646,
|
| 2425 |
+
"step": 151
|
| 2426 |
+
},
|
| 2427 |
+
{
|
| 2428 |
+
"epoch": 9.5,
|
| 2429 |
+
"grad_norm": 0.01312255859375,
|
| 2430 |
+
"learning_rate": 2.531645569620253e-06,
|
| 2431 |
+
"loss": 0.0,
|
| 2432 |
+
"step": 152
|
| 2433 |
+
},
|
| 2434 |
+
{
|
| 2435 |
+
"epoch": 9.5,
|
| 2436 |
+
"eval_accuracy": 0.9,
|
| 2437 |
+
"eval_loss": 0.5539237260818481,
|
| 2438 |
+
"eval_runtime": 4.8841,
|
| 2439 |
+
"eval_samples_per_second": 51.186,
|
| 2440 |
+
"eval_steps_per_second": 1.638,
|
| 2441 |
+
"step": 152
|
| 2442 |
+
},
|
| 2443 |
+
{
|
| 2444 |
+
"epoch": 9.5625,
|
| 2445 |
+
"grad_norm": 0.00604248046875,
|
| 2446 |
+
"learning_rate": 2.2151898734177215e-06,
|
| 2447 |
+
"loss": 0.0,
|
| 2448 |
+
"step": 153
|
| 2449 |
+
},
|
| 2450 |
+
{
|
| 2451 |
+
"epoch": 9.5625,
|
| 2452 |
+
"eval_accuracy": 0.904,
|
| 2453 |
+
"eval_loss": 0.5538834929466248,
|
| 2454 |
+
"eval_runtime": 4.8602,
|
| 2455 |
+
"eval_samples_per_second": 51.438,
|
| 2456 |
+
"eval_steps_per_second": 1.646,
|
| 2457 |
+
"step": 153
|
| 2458 |
+
},
|
| 2459 |
+
{
|
| 2460 |
+
"epoch": 9.625,
|
| 2461 |
+
"grad_norm": 0.032958984375,
|
| 2462 |
+
"learning_rate": 1.8987341772151901e-06,
|
| 2463 |
+
"loss": 0.0001,
|
| 2464 |
+
"step": 154
|
| 2465 |
+
},
|
| 2466 |
+
{
|
| 2467 |
+
"epoch": 9.625,
|
| 2468 |
+
"eval_accuracy": 0.9,
|
| 2469 |
+
"eval_loss": 0.5534281134605408,
|
| 2470 |
+
"eval_runtime": 4.8627,
|
| 2471 |
+
"eval_samples_per_second": 51.412,
|
| 2472 |
+
"eval_steps_per_second": 1.645,
|
| 2473 |
+
"step": 154
|
| 2474 |
+
},
|
| 2475 |
+
{
|
| 2476 |
+
"epoch": 9.6875,
|
| 2477 |
+
"grad_norm": 0.007354736328125,
|
| 2478 |
+
"learning_rate": 1.5822784810126583e-06,
|
| 2479 |
+
"loss": 0.0,
|
| 2480 |
+
"step": 155
|
| 2481 |
+
},
|
| 2482 |
+
{
|
| 2483 |
+
"epoch": 9.6875,
|
| 2484 |
+
"eval_accuracy": 0.9,
|
| 2485 |
+
"eval_loss": 0.5582576990127563,
|
| 2486 |
+
"eval_runtime": 4.8653,
|
| 2487 |
+
"eval_samples_per_second": 51.384,
|
| 2488 |
+
"eval_steps_per_second": 1.644,
|
| 2489 |
+
"step": 155
|
| 2490 |
+
},
|
| 2491 |
+
{
|
| 2492 |
+
"epoch": 9.75,
|
| 2493 |
+
"grad_norm": 0.00421142578125,
|
| 2494 |
+
"learning_rate": 1.2658227848101265e-06,
|
| 2495 |
+
"loss": 0.0,
|
| 2496 |
+
"step": 156
|
| 2497 |
+
},
|
| 2498 |
+
{
|
| 2499 |
+
"epoch": 9.75,
|
| 2500 |
+
"eval_accuracy": 0.896,
|
| 2501 |
+
"eval_loss": 0.5575215816497803,
|
| 2502 |
+
"eval_runtime": 4.878,
|
| 2503 |
+
"eval_samples_per_second": 51.251,
|
| 2504 |
+
"eval_steps_per_second": 1.64,
|
| 2505 |
+
"step": 156
|
| 2506 |
+
},
|
| 2507 |
+
{
|
| 2508 |
+
"epoch": 9.8125,
|
| 2509 |
+
"grad_norm": 0.00482177734375,
|
| 2510 |
+
"learning_rate": 9.493670886075951e-07,
|
| 2511 |
+
"loss": 0.0,
|
| 2512 |
+
"step": 157
|
| 2513 |
+
},
|
| 2514 |
+
{
|
| 2515 |
+
"epoch": 9.8125,
|
| 2516 |
+
"eval_accuracy": 0.896,
|
| 2517 |
+
"eval_loss": 0.5540234446525574,
|
| 2518 |
+
"eval_runtime": 4.8905,
|
| 2519 |
+
"eval_samples_per_second": 51.119,
|
| 2520 |
+
"eval_steps_per_second": 1.636,
|
| 2521 |
+
"step": 157
|
| 2522 |
+
},
|
| 2523 |
+
{
|
| 2524 |
+
"epoch": 9.875,
|
| 2525 |
+
"grad_norm": 0.0147705078125,
|
| 2526 |
+
"learning_rate": 6.329113924050633e-07,
|
| 2527 |
+
"loss": 0.0,
|
| 2528 |
+
"step": 158
|
| 2529 |
+
},
|
| 2530 |
+
{
|
| 2531 |
+
"epoch": 9.875,
|
| 2532 |
+
"eval_accuracy": 0.896,
|
| 2533 |
+
"eval_loss": 0.55516517162323,
|
| 2534 |
+
"eval_runtime": 4.8871,
|
| 2535 |
+
"eval_samples_per_second": 51.156,
|
| 2536 |
+
"eval_steps_per_second": 1.637,
|
| 2537 |
+
"step": 158
|
| 2538 |
+
},
|
| 2539 |
+
{
|
| 2540 |
+
"epoch": 9.9375,
|
| 2541 |
+
"grad_norm": 0.0033416748046875,
|
| 2542 |
+
"learning_rate": 3.1645569620253163e-07,
|
| 2543 |
+
"loss": 0.0,
|
| 2544 |
+
"step": 159
|
| 2545 |
+
},
|
| 2546 |
+
{
|
| 2547 |
+
"epoch": 9.9375,
|
| 2548 |
+
"eval_accuracy": 0.896,
|
| 2549 |
+
"eval_loss": 0.5555429458618164,
|
| 2550 |
+
"eval_runtime": 4.8568,
|
| 2551 |
+
"eval_samples_per_second": 51.474,
|
| 2552 |
+
"eval_steps_per_second": 1.647,
|
| 2553 |
+
"step": 159
|
| 2554 |
+
},
|
| 2555 |
+
{
|
| 2556 |
+
"epoch": 10.0,
|
| 2557 |
+
"grad_norm": 0.0185546875,
|
| 2558 |
+
"learning_rate": 0.0,
|
| 2559 |
+
"loss": 0.0,
|
| 2560 |
+
"step": 160
|
| 2561 |
+
},
|
| 2562 |
+
{
|
| 2563 |
+
"epoch": 10.0,
|
| 2564 |
+
"eval_accuracy": 0.896,
|
| 2565 |
+
"eval_loss": 0.557336688041687,
|
| 2566 |
+
"eval_runtime": 4.8633,
|
| 2567 |
+
"eval_samples_per_second": 51.405,
|
| 2568 |
+
"eval_steps_per_second": 1.645,
|
| 2569 |
+
"step": 160
|
| 2570 |
+
},
|
| 2571 |
+
{
|
| 2572 |
+
"epoch": 10.0,
|
| 2573 |
+
"step": 160,
|
| 2574 |
+
"total_flos": 7.024653098391962e+16,
|
| 2575 |
+
"train_loss": 0.1563696864293888,
|
| 2576 |
+
"train_runtime": 1332.2795,
|
| 2577 |
+
"train_samples_per_second": 7.506,
|
| 2578 |
+
"train_steps_per_second": 0.12
|
| 2579 |
+
}
|
| 2580 |
+
],
|
| 2581 |
+
"logging_steps": 1,
|
| 2582 |
+
"max_steps": 160,
|
| 2583 |
+
"num_input_tokens_seen": 0,
|
| 2584 |
+
"num_train_epochs": 10,
|
| 2585 |
+
"save_steps": 500,
|
| 2586 |
+
"stateful_callbacks": {
|
| 2587 |
+
"TrainerControl": {
|
| 2588 |
+
"args": {
|
| 2589 |
+
"should_epoch_stop": false,
|
| 2590 |
+
"should_evaluate": false,
|
| 2591 |
+
"should_log": false,
|
| 2592 |
+
"should_save": false,
|
| 2593 |
+
"should_training_stop": false
|
| 2594 |
+
},
|
| 2595 |
+
"attributes": {}
|
| 2596 |
+
}
|
| 2597 |
+
},
|
| 2598 |
+
"total_flos": 7.024653098391962e+16,
|
| 2599 |
+
"train_batch_size": 8,
|
| 2600 |
+
"trial_name": null,
|
| 2601 |
+
"trial_params": null
|
| 2602 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5c19267c03df5d74a3cdb6f23e76bea55b84032560f85d5c5b6c7ee207d2e01c
|
| 3 |
+
size 5176
|