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-multirc-sequence_classification.json +2274 -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 |
+
"o_proj",
|
| 28 |
+
"up_proj",
|
| 29 |
+
"q_proj",
|
| 30 |
+
"v_proj",
|
| 31 |
+
"k_proj",
|
| 32 |
+
"down_proj",
|
| 33 |
+
"gate_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 sha256:1c8eb89a180a7d62fc673a5aa20ea2b239a0153223afd58bc2e5738fc2184438
|
| 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 sha256:62aac1caf8a9d4c3f0bbcea6f3b568dc4c31697217cfb0a518a27db2e4da992a
|
| 3 |
+
size 17518624
|
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-multirc-sequence_classification.json
ADDED
|
@@ -0,0 +1,2274 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 1.984,
|
| 5 |
+
"eval_steps": 1,
|
| 6 |
+
"global_step": 124,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.016,
|
| 13 |
+
"grad_norm": 376.0,
|
| 14 |
+
"learning_rate": 2.5e-05,
|
| 15 |
+
"loss": 4.2913,
|
| 16 |
+
"step": 1
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.016,
|
| 20 |
+
"eval_exact_match": 0.0,
|
| 21 |
+
"eval_f1_a": 0.0,
|
| 22 |
+
"eval_f1_m": 0.35077572820670067,
|
| 23 |
+
"eval_loss": 3.1777186393737793,
|
| 24 |
+
"eval_runtime": 12.3576,
|
| 25 |
+
"eval_samples_per_second": 20.23,
|
| 26 |
+
"eval_steps_per_second": 2.589,
|
| 27 |
+
"step": 1
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 0.032,
|
| 31 |
+
"grad_norm": 282.0,
|
| 32 |
+
"learning_rate": 5e-05,
|
| 33 |
+
"loss": 3.3791,
|
| 34 |
+
"step": 2
|
| 35 |
+
},
|
| 36 |
+
{
|
| 37 |
+
"epoch": 0.032,
|
| 38 |
+
"eval_exact_match": 0.0,
|
| 39 |
+
"eval_f1_a": 0.0,
|
| 40 |
+
"eval_f1_m": 0.35077572820670067,
|
| 41 |
+
"eval_loss": 2.2114670276641846,
|
| 42 |
+
"eval_runtime": 12.332,
|
| 43 |
+
"eval_samples_per_second": 20.272,
|
| 44 |
+
"eval_steps_per_second": 2.595,
|
| 45 |
+
"step": 2
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.048,
|
| 49 |
+
"grad_norm": 280.0,
|
| 50 |
+
"learning_rate": 4.959016393442623e-05,
|
| 51 |
+
"loss": 2.2976,
|
| 52 |
+
"step": 3
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.048,
|
| 56 |
+
"eval_exact_match": 0.02040816326530612,
|
| 57 |
+
"eval_f1_a": 0.5754985754985755,
|
| 58 |
+
"eval_f1_m": 0.30537274516866364,
|
| 59 |
+
"eval_loss": 2.476294994354248,
|
| 60 |
+
"eval_runtime": 12.3232,
|
| 61 |
+
"eval_samples_per_second": 20.287,
|
| 62 |
+
"eval_steps_per_second": 2.597,
|
| 63 |
+
"step": 3
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 0.064,
|
| 67 |
+
"grad_norm": 342.0,
|
| 68 |
+
"learning_rate": 4.918032786885246e-05,
|
| 69 |
+
"loss": 1.8659,
|
| 70 |
+
"step": 4
|
| 71 |
+
},
|
| 72 |
+
{
|
| 73 |
+
"epoch": 0.064,
|
| 74 |
+
"eval_exact_match": 0.02040816326530612,
|
| 75 |
+
"eval_f1_a": 0.5754985754985755,
|
| 76 |
+
"eval_f1_m": 0.30537274516866364,
|
| 77 |
+
"eval_loss": 2.1439428329467773,
|
| 78 |
+
"eval_runtime": 12.4357,
|
| 79 |
+
"eval_samples_per_second": 20.103,
|
| 80 |
+
"eval_steps_per_second": 2.573,
|
| 81 |
+
"step": 4
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 0.08,
|
| 85 |
+
"grad_norm": 249.0,
|
| 86 |
+
"learning_rate": 4.8770491803278687e-05,
|
| 87 |
+
"loss": 1.1086,
|
| 88 |
+
"step": 5
|
| 89 |
+
},
|
| 90 |
+
{
|
| 91 |
+
"epoch": 0.08,
|
| 92 |
+
"eval_exact_match": 0.20408163265306123,
|
| 93 |
+
"eval_f1_a": 0.6484375,
|
| 94 |
+
"eval_f1_m": 0.5686948538989354,
|
| 95 |
+
"eval_loss": 0.6527036428451538,
|
| 96 |
+
"eval_runtime": 12.3192,
|
| 97 |
+
"eval_samples_per_second": 20.293,
|
| 98 |
+
"eval_steps_per_second": 2.598,
|
| 99 |
+
"step": 5
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 0.096,
|
| 103 |
+
"grad_norm": 23.5,
|
| 104 |
+
"learning_rate": 4.836065573770492e-05,
|
| 105 |
+
"loss": 0.4556,
|
| 106 |
+
"step": 6
|
| 107 |
+
},
|
| 108 |
+
{
|
| 109 |
+
"epoch": 0.096,
|
| 110 |
+
"eval_exact_match": 0.0,
|
| 111 |
+
"eval_f1_a": 0.019417475728155338,
|
| 112 |
+
"eval_f1_m": 0.35666332133919176,
|
| 113 |
+
"eval_loss": 0.9704605340957642,
|
| 114 |
+
"eval_runtime": 12.3182,
|
| 115 |
+
"eval_samples_per_second": 20.295,
|
| 116 |
+
"eval_steps_per_second": 2.598,
|
| 117 |
+
"step": 6
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 0.112,
|
| 121 |
+
"grad_norm": 448.0,
|
| 122 |
+
"learning_rate": 4.795081967213115e-05,
|
| 123 |
+
"loss": 2.1277,
|
| 124 |
+
"step": 7
|
| 125 |
+
},
|
| 126 |
+
{
|
| 127 |
+
"epoch": 0.112,
|
| 128 |
+
"eval_exact_match": 0.0,
|
| 129 |
+
"eval_f1_a": 0.038461538461538464,
|
| 130 |
+
"eval_f1_m": 0.3612551580738857,
|
| 131 |
+
"eval_loss": 0.9133706092834473,
|
| 132 |
+
"eval_runtime": 12.3172,
|
| 133 |
+
"eval_samples_per_second": 20.297,
|
| 134 |
+
"eval_steps_per_second": 2.598,
|
| 135 |
+
"step": 7
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.128,
|
| 139 |
+
"grad_norm": 282.0,
|
| 140 |
+
"learning_rate": 4.754098360655738e-05,
|
| 141 |
+
"loss": 1.4203,
|
| 142 |
+
"step": 8
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.128,
|
| 146 |
+
"eval_exact_match": 0.1836734693877551,
|
| 147 |
+
"eval_f1_a": 0.6473429951690822,
|
| 148 |
+
"eval_f1_m": 0.6107647171422682,
|
| 149 |
+
"eval_loss": 0.603775680065155,
|
| 150 |
+
"eval_runtime": 12.3078,
|
| 151 |
+
"eval_samples_per_second": 20.312,
|
| 152 |
+
"eval_steps_per_second": 2.6,
|
| 153 |
+
"step": 8
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 0.144,
|
| 157 |
+
"grad_norm": 132.0,
|
| 158 |
+
"learning_rate": 4.713114754098361e-05,
|
| 159 |
+
"loss": 0.4897,
|
| 160 |
+
"step": 9
|
| 161 |
+
},
|
| 162 |
+
{
|
| 163 |
+
"epoch": 0.144,
|
| 164 |
+
"eval_exact_match": 0.2653061224489796,
|
| 165 |
+
"eval_f1_a": 0.6867924528301886,
|
| 166 |
+
"eval_f1_m": 0.6092514061901817,
|
| 167 |
+
"eval_loss": 0.9327998757362366,
|
| 168 |
+
"eval_runtime": 12.2131,
|
| 169 |
+
"eval_samples_per_second": 20.47,
|
| 170 |
+
"eval_steps_per_second": 2.62,
|
| 171 |
+
"step": 9
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.16,
|
| 175 |
+
"grad_norm": 33.25,
|
| 176 |
+
"learning_rate": 4.672131147540984e-05,
|
| 177 |
+
"loss": 0.5593,
|
| 178 |
+
"step": 10
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.16,
|
| 182 |
+
"eval_exact_match": 0.22448979591836735,
|
| 183 |
+
"eval_f1_a": 0.6953405017921147,
|
| 184 |
+
"eval_f1_m": 0.5742497864946845,
|
| 185 |
+
"eval_loss": 1.1231226921081543,
|
| 186 |
+
"eval_runtime": 12.3233,
|
| 187 |
+
"eval_samples_per_second": 20.287,
|
| 188 |
+
"eval_steps_per_second": 2.597,
|
| 189 |
+
"step": 10
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 0.176,
|
| 193 |
+
"grad_norm": 186.0,
|
| 194 |
+
"learning_rate": 4.631147540983607e-05,
|
| 195 |
+
"loss": 0.7926,
|
| 196 |
+
"step": 11
|
| 197 |
+
},
|
| 198 |
+
{
|
| 199 |
+
"epoch": 0.176,
|
| 200 |
+
"eval_exact_match": 0.24489795918367346,
|
| 201 |
+
"eval_f1_a": 0.7022900763358778,
|
| 202 |
+
"eval_f1_m": 0.6231004256514461,
|
| 203 |
+
"eval_loss": 0.9066404104232788,
|
| 204 |
+
"eval_runtime": 12.3156,
|
| 205 |
+
"eval_samples_per_second": 20.299,
|
| 206 |
+
"eval_steps_per_second": 2.598,
|
| 207 |
+
"step": 11
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 0.192,
|
| 211 |
+
"grad_norm": 210.0,
|
| 212 |
+
"learning_rate": 4.59016393442623e-05,
|
| 213 |
+
"loss": 1.3277,
|
| 214 |
+
"step": 12
|
| 215 |
+
},
|
| 216 |
+
{
|
| 217 |
+
"epoch": 0.192,
|
| 218 |
+
"eval_exact_match": 0.2857142857142857,
|
| 219 |
+
"eval_f1_a": 0.6991150442477877,
|
| 220 |
+
"eval_f1_m": 0.6591490708837647,
|
| 221 |
+
"eval_loss": 0.6181139945983887,
|
| 222 |
+
"eval_runtime": 12.3229,
|
| 223 |
+
"eval_samples_per_second": 20.287,
|
| 224 |
+
"eval_steps_per_second": 2.597,
|
| 225 |
+
"step": 12
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 0.208,
|
| 229 |
+
"grad_norm": 22.125,
|
| 230 |
+
"learning_rate": 4.549180327868853e-05,
|
| 231 |
+
"loss": 0.3132,
|
| 232 |
+
"step": 13
|
| 233 |
+
},
|
| 234 |
+
{
|
| 235 |
+
"epoch": 0.208,
|
| 236 |
+
"eval_exact_match": 0.2857142857142857,
|
| 237 |
+
"eval_f1_a": 0.6219512195121951,
|
| 238 |
+
"eval_f1_m": 0.6366888780154085,
|
| 239 |
+
"eval_loss": 0.6456747055053711,
|
| 240 |
+
"eval_runtime": 12.2235,
|
| 241 |
+
"eval_samples_per_second": 20.452,
|
| 242 |
+
"eval_steps_per_second": 2.618,
|
| 243 |
+
"step": 13
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 0.224,
|
| 247 |
+
"grad_norm": 219.0,
|
| 248 |
+
"learning_rate": 4.508196721311476e-05,
|
| 249 |
+
"loss": 0.9243,
|
| 250 |
+
"step": 14
|
| 251 |
+
},
|
| 252 |
+
{
|
| 253 |
+
"epoch": 0.224,
|
| 254 |
+
"eval_exact_match": 0.14285714285714285,
|
| 255 |
+
"eval_f1_a": 0.4822695035460994,
|
| 256 |
+
"eval_f1_m": 0.5554760715475,
|
| 257 |
+
"eval_loss": 0.8351603746414185,
|
| 258 |
+
"eval_runtime": 12.4211,
|
| 259 |
+
"eval_samples_per_second": 20.127,
|
| 260 |
+
"eval_steps_per_second": 2.576,
|
| 261 |
+
"step": 14
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.24,
|
| 265 |
+
"grad_norm": 296.0,
|
| 266 |
+
"learning_rate": 4.467213114754098e-05,
|
| 267 |
+
"loss": 1.6468,
|
| 268 |
+
"step": 15
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 0.24,
|
| 272 |
+
"eval_exact_match": 0.16326530612244897,
|
| 273 |
+
"eval_f1_a": 0.4822695035460994,
|
| 274 |
+
"eval_f1_m": 0.5518317566786953,
|
| 275 |
+
"eval_loss": 0.8677384257316589,
|
| 276 |
+
"eval_runtime": 12.3246,
|
| 277 |
+
"eval_samples_per_second": 20.285,
|
| 278 |
+
"eval_steps_per_second": 2.596,
|
| 279 |
+
"step": 15
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 0.256,
|
| 283 |
+
"grad_norm": 229.0,
|
| 284 |
+
"learning_rate": 4.426229508196721e-05,
|
| 285 |
+
"loss": 1.1329,
|
| 286 |
+
"step": 16
|
| 287 |
+
},
|
| 288 |
+
{
|
| 289 |
+
"epoch": 0.256,
|
| 290 |
+
"eval_exact_match": 0.20408163265306123,
|
| 291 |
+
"eval_f1_a": 0.5138888888888888,
|
| 292 |
+
"eval_f1_m": 0.5648599982783655,
|
| 293 |
+
"eval_loss": 0.7419898509979248,
|
| 294 |
+
"eval_runtime": 12.3194,
|
| 295 |
+
"eval_samples_per_second": 20.293,
|
| 296 |
+
"eval_steps_per_second": 2.598,
|
| 297 |
+
"step": 16
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.272,
|
| 301 |
+
"grad_norm": 114.5,
|
| 302 |
+
"learning_rate": 4.3852459016393444e-05,
|
| 303 |
+
"loss": 0.7247,
|
| 304 |
+
"step": 17
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 0.272,
|
| 308 |
+
"eval_exact_match": 0.2653061224489796,
|
| 309 |
+
"eval_f1_a": 0.6163522012578616,
|
| 310 |
+
"eval_f1_m": 0.6251350123799102,
|
| 311 |
+
"eval_loss": 0.5582619905471802,
|
| 312 |
+
"eval_runtime": 12.3213,
|
| 313 |
+
"eval_samples_per_second": 20.29,
|
| 314 |
+
"eval_steps_per_second": 2.597,
|
| 315 |
+
"step": 17
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"epoch": 0.288,
|
| 319 |
+
"grad_norm": 195.0,
|
| 320 |
+
"learning_rate": 4.3442622950819674e-05,
|
| 321 |
+
"loss": 0.8305,
|
| 322 |
+
"step": 18
|
| 323 |
+
},
|
| 324 |
+
{
|
| 325 |
+
"epoch": 0.288,
|
| 326 |
+
"eval_exact_match": 0.2857142857142857,
|
| 327 |
+
"eval_f1_a": 0.7048458149779736,
|
| 328 |
+
"eval_f1_m": 0.6374393480335857,
|
| 329 |
+
"eval_loss": 0.5930992364883423,
|
| 330 |
+
"eval_runtime": 12.3234,
|
| 331 |
+
"eval_samples_per_second": 20.287,
|
| 332 |
+
"eval_steps_per_second": 2.597,
|
| 333 |
+
"step": 18
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 0.304,
|
| 337 |
+
"grad_norm": 13.1875,
|
| 338 |
+
"learning_rate": 4.3032786885245904e-05,
|
| 339 |
+
"loss": 0.324,
|
| 340 |
+
"step": 19
|
| 341 |
+
},
|
| 342 |
+
{
|
| 343 |
+
"epoch": 0.304,
|
| 344 |
+
"eval_exact_match": 0.12244897959183673,
|
| 345 |
+
"eval_f1_a": 0.638888888888889,
|
| 346 |
+
"eval_f1_m": 0.49413981709900057,
|
| 347 |
+
"eval_loss": 0.7574265003204346,
|
| 348 |
+
"eval_runtime": 12.3235,
|
| 349 |
+
"eval_samples_per_second": 20.286,
|
| 350 |
+
"eval_steps_per_second": 2.597,
|
| 351 |
+
"step": 19
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 0.32,
|
| 355 |
+
"grad_norm": 107.5,
|
| 356 |
+
"learning_rate": 4.262295081967213e-05,
|
| 357 |
+
"loss": 0.4232,
|
| 358 |
+
"step": 20
|
| 359 |
+
},
|
| 360 |
+
{
|
| 361 |
+
"epoch": 0.32,
|
| 362 |
+
"eval_exact_match": 0.12244897959183673,
|
| 363 |
+
"eval_f1_a": 0.6548042704626335,
|
| 364 |
+
"eval_f1_m": 0.506408840592514,
|
| 365 |
+
"eval_loss": 0.788853645324707,
|
| 366 |
+
"eval_runtime": 12.3258,
|
| 367 |
+
"eval_samples_per_second": 20.283,
|
| 368 |
+
"eval_steps_per_second": 2.596,
|
| 369 |
+
"step": 20
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 0.336,
|
| 373 |
+
"grad_norm": 126.5,
|
| 374 |
+
"learning_rate": 4.2213114754098365e-05,
|
| 375 |
+
"loss": 0.5104,
|
| 376 |
+
"step": 21
|
| 377 |
+
},
|
| 378 |
+
{
|
| 379 |
+
"epoch": 0.336,
|
| 380 |
+
"eval_exact_match": 0.2653061224489796,
|
| 381 |
+
"eval_f1_a": 0.6938775510204082,
|
| 382 |
+
"eval_f1_m": 0.6276129499418815,
|
| 383 |
+
"eval_loss": 0.6996061205863953,
|
| 384 |
+
"eval_runtime": 12.3173,
|
| 385 |
+
"eval_samples_per_second": 20.297,
|
| 386 |
+
"eval_steps_per_second": 2.598,
|
| 387 |
+
"step": 21
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.352,
|
| 391 |
+
"grad_norm": 12.4375,
|
| 392 |
+
"learning_rate": 4.1803278688524595e-05,
|
| 393 |
+
"loss": 0.5181,
|
| 394 |
+
"step": 22
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 0.352,
|
| 398 |
+
"eval_exact_match": 0.2653061224489796,
|
| 399 |
+
"eval_f1_a": 0.7142857142857143,
|
| 400 |
+
"eval_f1_m": 0.6636356007604508,
|
| 401 |
+
"eval_loss": 0.6774892807006836,
|
| 402 |
+
"eval_runtime": 12.3133,
|
| 403 |
+
"eval_samples_per_second": 20.303,
|
| 404 |
+
"eval_steps_per_second": 2.599,
|
| 405 |
+
"step": 22
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 0.368,
|
| 409 |
+
"grad_norm": 118.5,
|
| 410 |
+
"learning_rate": 4.1393442622950826e-05,
|
| 411 |
+
"loss": 0.3815,
|
| 412 |
+
"step": 23
|
| 413 |
+
},
|
| 414 |
+
{
|
| 415 |
+
"epoch": 0.368,
|
| 416 |
+
"eval_exact_match": 0.32653061224489793,
|
| 417 |
+
"eval_f1_a": 0.7037037037037037,
|
| 418 |
+
"eval_f1_m": 0.690495332332067,
|
| 419 |
+
"eval_loss": 0.6105913519859314,
|
| 420 |
+
"eval_runtime": 12.3133,
|
| 421 |
+
"eval_samples_per_second": 20.303,
|
| 422 |
+
"eval_steps_per_second": 2.599,
|
| 423 |
+
"step": 23
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 0.384,
|
| 427 |
+
"grad_norm": 34.75,
|
| 428 |
+
"learning_rate": 4.098360655737705e-05,
|
| 429 |
+
"loss": 0.6494,
|
| 430 |
+
"step": 24
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 0.384,
|
| 434 |
+
"eval_exact_match": 0.30612244897959184,
|
| 435 |
+
"eval_f1_a": 0.6878306878306879,
|
| 436 |
+
"eval_f1_m": 0.685211330619494,
|
| 437 |
+
"eval_loss": 0.5590341091156006,
|
| 438 |
+
"eval_runtime": 12.312,
|
| 439 |
+
"eval_samples_per_second": 20.305,
|
| 440 |
+
"eval_steps_per_second": 2.599,
|
| 441 |
+
"step": 24
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 0.4,
|
| 445 |
+
"grad_norm": 96.0,
|
| 446 |
+
"learning_rate": 4.057377049180328e-05,
|
| 447 |
+
"loss": 0.5222,
|
| 448 |
+
"step": 25
|
| 449 |
+
},
|
| 450 |
+
{
|
| 451 |
+
"epoch": 0.4,
|
| 452 |
+
"eval_exact_match": 0.30612244897959184,
|
| 453 |
+
"eval_f1_a": 0.6775956284153005,
|
| 454 |
+
"eval_f1_m": 0.6791293740273332,
|
| 455 |
+
"eval_loss": 0.5570459961891174,
|
| 456 |
+
"eval_runtime": 12.4193,
|
| 457 |
+
"eval_samples_per_second": 20.13,
|
| 458 |
+
"eval_steps_per_second": 2.577,
|
| 459 |
+
"step": 25
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 0.416,
|
| 463 |
+
"grad_norm": 33.5,
|
| 464 |
+
"learning_rate": 4.016393442622951e-05,
|
| 465 |
+
"loss": 0.3375,
|
| 466 |
+
"step": 26
|
| 467 |
+
},
|
| 468 |
+
{
|
| 469 |
+
"epoch": 0.416,
|
| 470 |
+
"eval_exact_match": 0.30612244897959184,
|
| 471 |
+
"eval_f1_a": 0.6813186813186813,
|
| 472 |
+
"eval_f1_m": 0.6876327753878774,
|
| 473 |
+
"eval_loss": 0.5533034205436707,
|
| 474 |
+
"eval_runtime": 12.313,
|
| 475 |
+
"eval_samples_per_second": 20.304,
|
| 476 |
+
"eval_steps_per_second": 2.599,
|
| 477 |
+
"step": 26
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 0.432,
|
| 481 |
+
"grad_norm": 112.0,
|
| 482 |
+
"learning_rate": 3.975409836065574e-05,
|
| 483 |
+
"loss": 0.5844,
|
| 484 |
+
"step": 27
|
| 485 |
+
},
|
| 486 |
+
{
|
| 487 |
+
"epoch": 0.432,
|
| 488 |
+
"eval_exact_match": 0.30612244897959184,
|
| 489 |
+
"eval_f1_a": 0.6871794871794872,
|
| 490 |
+
"eval_f1_m": 0.6866896708733443,
|
| 491 |
+
"eval_loss": 0.5548486709594727,
|
| 492 |
+
"eval_runtime": 12.2374,
|
| 493 |
+
"eval_samples_per_second": 20.429,
|
| 494 |
+
"eval_steps_per_second": 2.615,
|
| 495 |
+
"step": 27
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 0.448,
|
| 499 |
+
"grad_norm": 27.125,
|
| 500 |
+
"learning_rate": 3.934426229508197e-05,
|
| 501 |
+
"loss": 0.2711,
|
| 502 |
+
"step": 28
|
| 503 |
+
},
|
| 504 |
+
{
|
| 505 |
+
"epoch": 0.448,
|
| 506 |
+
"eval_exact_match": 0.30612244897959184,
|
| 507 |
+
"eval_f1_a": 0.696969696969697,
|
| 508 |
+
"eval_f1_m": 0.6901043700863629,
|
| 509 |
+
"eval_loss": 0.5596827864646912,
|
| 510 |
+
"eval_runtime": 12.3346,
|
| 511 |
+
"eval_samples_per_second": 20.268,
|
| 512 |
+
"eval_steps_per_second": 2.594,
|
| 513 |
+
"step": 28
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.464,
|
| 517 |
+
"grad_norm": 14.875,
|
| 518 |
+
"learning_rate": 3.89344262295082e-05,
|
| 519 |
+
"loss": 0.2332,
|
| 520 |
+
"step": 29
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 0.464,
|
| 524 |
+
"eval_exact_match": 0.32653061224489793,
|
| 525 |
+
"eval_f1_a": 0.7128712871287128,
|
| 526 |
+
"eval_f1_m": 0.7052883924132425,
|
| 527 |
+
"eval_loss": 0.5786635279655457,
|
| 528 |
+
"eval_runtime": 12.2393,
|
| 529 |
+
"eval_samples_per_second": 20.426,
|
| 530 |
+
"eval_steps_per_second": 2.615,
|
| 531 |
+
"step": 29
|
| 532 |
+
},
|
| 533 |
+
{
|
| 534 |
+
"epoch": 0.48,
|
| 535 |
+
"grad_norm": 79.5,
|
| 536 |
+
"learning_rate": 3.8524590163934424e-05,
|
| 537 |
+
"loss": 0.3991,
|
| 538 |
+
"step": 30
|
| 539 |
+
},
|
| 540 |
+
{
|
| 541 |
+
"epoch": 0.48,
|
| 542 |
+
"eval_exact_match": 0.3469387755102041,
|
| 543 |
+
"eval_f1_a": 0.7208121827411168,
|
| 544 |
+
"eval_f1_m": 0.7176142751472883,
|
| 545 |
+
"eval_loss": 0.5726993680000305,
|
| 546 |
+
"eval_runtime": 12.3367,
|
| 547 |
+
"eval_samples_per_second": 20.265,
|
| 548 |
+
"eval_steps_per_second": 2.594,
|
| 549 |
+
"step": 30
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 0.496,
|
| 553 |
+
"grad_norm": 13.5625,
|
| 554 |
+
"learning_rate": 3.8114754098360655e-05,
|
| 555 |
+
"loss": 0.503,
|
| 556 |
+
"step": 31
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 0.496,
|
| 560 |
+
"eval_exact_match": 0.32653061224489793,
|
| 561 |
+
"eval_f1_a": 0.7046632124352332,
|
| 562 |
+
"eval_f1_m": 0.6947441747261675,
|
| 563 |
+
"eval_loss": 0.5508583188056946,
|
| 564 |
+
"eval_runtime": 12.3324,
|
| 565 |
+
"eval_samples_per_second": 20.272,
|
| 566 |
+
"eval_steps_per_second": 2.595,
|
| 567 |
+
"step": 31
|
| 568 |
+
},
|
| 569 |
+
{
|
| 570 |
+
"epoch": 0.512,
|
| 571 |
+
"grad_norm": 14.5625,
|
| 572 |
+
"learning_rate": 3.7704918032786885e-05,
|
| 573 |
+
"loss": 0.1043,
|
| 574 |
+
"step": 32
|
| 575 |
+
},
|
| 576 |
+
{
|
| 577 |
+
"epoch": 0.512,
|
| 578 |
+
"eval_exact_match": 0.32653061224489793,
|
| 579 |
+
"eval_f1_a": 0.7263681592039801,
|
| 580 |
+
"eval_f1_m": 0.7167535412433371,
|
| 581 |
+
"eval_loss": 0.5476462841033936,
|
| 582 |
+
"eval_runtime": 12.3423,
|
| 583 |
+
"eval_samples_per_second": 20.256,
|
| 584 |
+
"eval_steps_per_second": 2.593,
|
| 585 |
+
"step": 32
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 0.528,
|
| 589 |
+
"grad_norm": 49.25,
|
| 590 |
+
"learning_rate": 3.729508196721312e-05,
|
| 591 |
+
"loss": 0.251,
|
| 592 |
+
"step": 33
|
| 593 |
+
},
|
| 594 |
+
{
|
| 595 |
+
"epoch": 0.528,
|
| 596 |
+
"eval_exact_match": 0.30612244897959184,
|
| 597 |
+
"eval_f1_a": 0.7289719626168225,
|
| 598 |
+
"eval_f1_m": 0.697900285655388,
|
| 599 |
+
"eval_loss": 0.5704118013381958,
|
| 600 |
+
"eval_runtime": 12.4426,
|
| 601 |
+
"eval_samples_per_second": 20.092,
|
| 602 |
+
"eval_steps_per_second": 2.572,
|
| 603 |
+
"step": 33
|
| 604 |
+
},
|
| 605 |
+
{
|
| 606 |
+
"epoch": 0.544,
|
| 607 |
+
"grad_norm": 109.0,
|
| 608 |
+
"learning_rate": 3.6885245901639346e-05,
|
| 609 |
+
"loss": 0.7414,
|
| 610 |
+
"step": 34
|
| 611 |
+
},
|
| 612 |
+
{
|
| 613 |
+
"epoch": 0.544,
|
| 614 |
+
"eval_exact_match": 0.30612244897959184,
|
| 615 |
+
"eval_f1_a": 0.7339449541284404,
|
| 616 |
+
"eval_f1_m": 0.6975358541685073,
|
| 617 |
+
"eval_loss": 0.570320188999176,
|
| 618 |
+
"eval_runtime": 12.3441,
|
| 619 |
+
"eval_samples_per_second": 20.253,
|
| 620 |
+
"eval_steps_per_second": 2.592,
|
| 621 |
+
"step": 34
|
| 622 |
+
},
|
| 623 |
+
{
|
| 624 |
+
"epoch": 0.56,
|
| 625 |
+
"grad_norm": 94.5,
|
| 626 |
+
"learning_rate": 3.6475409836065576e-05,
|
| 627 |
+
"loss": 0.3785,
|
| 628 |
+
"step": 35
|
| 629 |
+
},
|
| 630 |
+
{
|
| 631 |
+
"epoch": 0.56,
|
| 632 |
+
"eval_exact_match": 0.32653061224489793,
|
| 633 |
+
"eval_f1_a": 0.7454545454545454,
|
| 634 |
+
"eval_f1_m": 0.7021843802456048,
|
| 635 |
+
"eval_loss": 0.5453792214393616,
|
| 636 |
+
"eval_runtime": 12.3452,
|
| 637 |
+
"eval_samples_per_second": 20.251,
|
| 638 |
+
"eval_steps_per_second": 2.592,
|
| 639 |
+
"step": 35
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 0.576,
|
| 643 |
+
"grad_norm": 67.0,
|
| 644 |
+
"learning_rate": 3.6065573770491806e-05,
|
| 645 |
+
"loss": 0.6673,
|
| 646 |
+
"step": 36
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 0.576,
|
| 650 |
+
"eval_exact_match": 0.3469387755102041,
|
| 651 |
+
"eval_f1_a": 0.751131221719457,
|
| 652 |
+
"eval_f1_m": 0.7089871013340403,
|
| 653 |
+
"eval_loss": 0.5370164513587952,
|
| 654 |
+
"eval_runtime": 12.4345,
|
| 655 |
+
"eval_samples_per_second": 20.105,
|
| 656 |
+
"eval_steps_per_second": 2.573,
|
| 657 |
+
"step": 36
|
| 658 |
+
},
|
| 659 |
+
{
|
| 660 |
+
"epoch": 0.592,
|
| 661 |
+
"grad_norm": 86.0,
|
| 662 |
+
"learning_rate": 3.5655737704918037e-05,
|
| 663 |
+
"loss": 0.6621,
|
| 664 |
+
"step": 37
|
| 665 |
+
},
|
| 666 |
+
{
|
| 667 |
+
"epoch": 0.592,
|
| 668 |
+
"eval_exact_match": 0.30612244897959184,
|
| 669 |
+
"eval_f1_a": 0.7465437788018433,
|
| 670 |
+
"eval_f1_m": 0.6957055982566187,
|
| 671 |
+
"eval_loss": 0.5155858397483826,
|
| 672 |
+
"eval_runtime": 12.3376,
|
| 673 |
+
"eval_samples_per_second": 20.263,
|
| 674 |
+
"eval_steps_per_second": 2.594,
|
| 675 |
+
"step": 37
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 0.608,
|
| 679 |
+
"grad_norm": 27.25,
|
| 680 |
+
"learning_rate": 3.524590163934427e-05,
|
| 681 |
+
"loss": 1.1275,
|
| 682 |
+
"step": 38
|
| 683 |
+
},
|
| 684 |
+
{
|
| 685 |
+
"epoch": 0.608,
|
| 686 |
+
"eval_exact_match": 0.3469387755102041,
|
| 687 |
+
"eval_f1_a": 0.7534883720930233,
|
| 688 |
+
"eval_f1_m": 0.7037392879229614,
|
| 689 |
+
"eval_loss": 0.4928358197212219,
|
| 690 |
+
"eval_runtime": 12.3343,
|
| 691 |
+
"eval_samples_per_second": 20.269,
|
| 692 |
+
"eval_steps_per_second": 2.594,
|
| 693 |
+
"step": 38
|
| 694 |
+
},
|
| 695 |
+
{
|
| 696 |
+
"epoch": 0.624,
|
| 697 |
+
"grad_norm": 28.375,
|
| 698 |
+
"learning_rate": 3.483606557377049e-05,
|
| 699 |
+
"loss": 0.1335,
|
| 700 |
+
"step": 39
|
| 701 |
+
},
|
| 702 |
+
{
|
| 703 |
+
"epoch": 0.624,
|
| 704 |
+
"eval_exact_match": 0.30612244897959184,
|
| 705 |
+
"eval_f1_a": 0.7300000000000001,
|
| 706 |
+
"eval_f1_m": 0.7049014194422356,
|
| 707 |
+
"eval_loss": 0.48726317286491394,
|
| 708 |
+
"eval_runtime": 12.3304,
|
| 709 |
+
"eval_samples_per_second": 20.275,
|
| 710 |
+
"eval_steps_per_second": 2.595,
|
| 711 |
+
"step": 39
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 0.64,
|
| 715 |
+
"grad_norm": 89.0,
|
| 716 |
+
"learning_rate": 3.442622950819672e-05,
|
| 717 |
+
"loss": 0.3428,
|
| 718 |
+
"step": 40
|
| 719 |
+
},
|
| 720 |
+
{
|
| 721 |
+
"epoch": 0.64,
|
| 722 |
+
"eval_exact_match": 0.14285714285714285,
|
| 723 |
+
"eval_f1_a": 0.5161290322580644,
|
| 724 |
+
"eval_f1_m": 0.554482422339565,
|
| 725 |
+
"eval_loss": 0.5513813495635986,
|
| 726 |
+
"eval_runtime": 12.3276,
|
| 727 |
+
"eval_samples_per_second": 20.28,
|
| 728 |
+
"eval_steps_per_second": 2.596,
|
| 729 |
+
"step": 40
|
| 730 |
+
},
|
| 731 |
+
{
|
| 732 |
+
"epoch": 0.656,
|
| 733 |
+
"grad_norm": 154.0,
|
| 734 |
+
"learning_rate": 3.401639344262295e-05,
|
| 735 |
+
"loss": 0.8522,
|
| 736 |
+
"step": 41
|
| 737 |
+
},
|
| 738 |
+
{
|
| 739 |
+
"epoch": 0.656,
|
| 740 |
+
"eval_exact_match": 0.08163265306122448,
|
| 741 |
+
"eval_f1_a": 0.39416058394160586,
|
| 742 |
+
"eval_f1_m": 0.49742443097785227,
|
| 743 |
+
"eval_loss": 0.6181958913803101,
|
| 744 |
+
"eval_runtime": 12.3308,
|
| 745 |
+
"eval_samples_per_second": 20.274,
|
| 746 |
+
"eval_steps_per_second": 2.595,
|
| 747 |
+
"step": 41
|
| 748 |
+
},
|
| 749 |
+
{
|
| 750 |
+
"epoch": 0.672,
|
| 751 |
+
"grad_norm": 223.0,
|
| 752 |
+
"learning_rate": 3.360655737704918e-05,
|
| 753 |
+
"loss": 0.5658,
|
| 754 |
+
"step": 42
|
| 755 |
+
},
|
| 756 |
+
{
|
| 757 |
+
"epoch": 0.672,
|
| 758 |
+
"eval_exact_match": 0.08163265306122448,
|
| 759 |
+
"eval_f1_a": 0.33587786259541985,
|
| 760 |
+
"eval_f1_m": 0.4630655359046716,
|
| 761 |
+
"eval_loss": 0.6285732984542847,
|
| 762 |
+
"eval_runtime": 12.3287,
|
| 763 |
+
"eval_samples_per_second": 20.278,
|
| 764 |
+
"eval_steps_per_second": 2.596,
|
| 765 |
+
"step": 42
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 0.688,
|
| 769 |
+
"grad_norm": 114.5,
|
| 770 |
+
"learning_rate": 3.319672131147541e-05,
|
| 771 |
+
"loss": 0.41,
|
| 772 |
+
"step": 43
|
| 773 |
+
},
|
| 774 |
+
{
|
| 775 |
+
"epoch": 0.688,
|
| 776 |
+
"eval_exact_match": 0.08163265306122448,
|
| 777 |
+
"eval_f1_a": 0.4285714285714286,
|
| 778 |
+
"eval_f1_m": 0.5117096905362211,
|
| 779 |
+
"eval_loss": 0.5897620916366577,
|
| 780 |
+
"eval_runtime": 12.3292,
|
| 781 |
+
"eval_samples_per_second": 20.277,
|
| 782 |
+
"eval_steps_per_second": 2.595,
|
| 783 |
+
"step": 43
|
| 784 |
+
},
|
| 785 |
+
{
|
| 786 |
+
"epoch": 0.704,
|
| 787 |
+
"grad_norm": 197.0,
|
| 788 |
+
"learning_rate": 3.2786885245901635e-05,
|
| 789 |
+
"loss": 1.0016,
|
| 790 |
+
"step": 44
|
| 791 |
+
},
|
| 792 |
+
{
|
| 793 |
+
"epoch": 0.704,
|
| 794 |
+
"eval_exact_match": 0.20408163265306123,
|
| 795 |
+
"eval_f1_a": 0.5802469135802469,
|
| 796 |
+
"eval_f1_m": 0.6031337709909137,
|
| 797 |
+
"eval_loss": 0.5237689018249512,
|
| 798 |
+
"eval_runtime": 12.4326,
|
| 799 |
+
"eval_samples_per_second": 20.108,
|
| 800 |
+
"eval_steps_per_second": 2.574,
|
| 801 |
+
"step": 44
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 0.72,
|
| 805 |
+
"grad_norm": 12.75,
|
| 806 |
+
"learning_rate": 3.237704918032787e-05,
|
| 807 |
+
"loss": 0.2076,
|
| 808 |
+
"step": 45
|
| 809 |
+
},
|
| 810 |
+
{
|
| 811 |
+
"epoch": 0.72,
|
| 812 |
+
"eval_exact_match": 0.3877551020408163,
|
| 813 |
+
"eval_f1_a": 0.7236180904522613,
|
| 814 |
+
"eval_f1_m": 0.7064332226397052,
|
| 815 |
+
"eval_loss": 0.4820278286933899,
|
| 816 |
+
"eval_runtime": 12.2296,
|
| 817 |
+
"eval_samples_per_second": 20.442,
|
| 818 |
+
"eval_steps_per_second": 2.617,
|
| 819 |
+
"step": 45
|
| 820 |
+
},
|
| 821 |
+
{
|
| 822 |
+
"epoch": 0.736,
|
| 823 |
+
"grad_norm": 19.5,
|
| 824 |
+
"learning_rate": 3.19672131147541e-05,
|
| 825 |
+
"loss": 0.2442,
|
| 826 |
+
"step": 46
|
| 827 |
+
},
|
| 828 |
+
{
|
| 829 |
+
"epoch": 0.736,
|
| 830 |
+
"eval_exact_match": 0.32653061224489793,
|
| 831 |
+
"eval_f1_a": 0.7272727272727273,
|
| 832 |
+
"eval_f1_m": 0.6827760108372352,
|
| 833 |
+
"eval_loss": 0.5127883553504944,
|
| 834 |
+
"eval_runtime": 12.2259,
|
| 835 |
+
"eval_samples_per_second": 20.448,
|
| 836 |
+
"eval_steps_per_second": 2.617,
|
| 837 |
+
"step": 46
|
| 838 |
+
},
|
| 839 |
+
{
|
| 840 |
+
"epoch": 0.752,
|
| 841 |
+
"grad_norm": 20.125,
|
| 842 |
+
"learning_rate": 3.155737704918033e-05,
|
| 843 |
+
"loss": 1.1899,
|
| 844 |
+
"step": 47
|
| 845 |
+
},
|
| 846 |
+
{
|
| 847 |
+
"epoch": 0.752,
|
| 848 |
+
"eval_exact_match": 0.32653061224489793,
|
| 849 |
+
"eval_f1_a": 0.7301587301587302,
|
| 850 |
+
"eval_f1_m": 0.6798730747710341,
|
| 851 |
+
"eval_loss": 0.5977119207382202,
|
| 852 |
+
"eval_runtime": 12.2307,
|
| 853 |
+
"eval_samples_per_second": 20.44,
|
| 854 |
+
"eval_steps_per_second": 2.616,
|
| 855 |
+
"step": 47
|
| 856 |
+
},
|
| 857 |
+
{
|
| 858 |
+
"epoch": 0.768,
|
| 859 |
+
"grad_norm": 220.0,
|
| 860 |
+
"learning_rate": 3.114754098360656e-05,
|
| 861 |
+
"loss": 0.8358,
|
| 862 |
+
"step": 48
|
| 863 |
+
},
|
| 864 |
+
{
|
| 865 |
+
"epoch": 0.768,
|
| 866 |
+
"eval_exact_match": 0.2653061224489796,
|
| 867 |
+
"eval_f1_a": 0.7203065134099617,
|
| 868 |
+
"eval_f1_m": 0.6656674957695367,
|
| 869 |
+
"eval_loss": 0.6618979573249817,
|
| 870 |
+
"eval_runtime": 12.3327,
|
| 871 |
+
"eval_samples_per_second": 20.271,
|
| 872 |
+
"eval_steps_per_second": 2.595,
|
| 873 |
+
"step": 48
|
| 874 |
+
},
|
| 875 |
+
{
|
| 876 |
+
"epoch": 0.784,
|
| 877 |
+
"grad_norm": 185.0,
|
| 878 |
+
"learning_rate": 3.073770491803279e-05,
|
| 879 |
+
"loss": 0.6181,
|
| 880 |
+
"step": 49
|
| 881 |
+
},
|
| 882 |
+
{
|
| 883 |
+
"epoch": 0.784,
|
| 884 |
+
"eval_exact_match": 0.24489795918367346,
|
| 885 |
+
"eval_f1_a": 0.712121212121212,
|
| 886 |
+
"eval_f1_m": 0.6566752408589144,
|
| 887 |
+
"eval_loss": 0.6790361404418945,
|
| 888 |
+
"eval_runtime": 12.3332,
|
| 889 |
+
"eval_samples_per_second": 20.271,
|
| 890 |
+
"eval_steps_per_second": 2.595,
|
| 891 |
+
"step": 49
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 0.8,
|
| 895 |
+
"grad_norm": 48.75,
|
| 896 |
+
"learning_rate": 3.0327868852459017e-05,
|
| 897 |
+
"loss": 1.0863,
|
| 898 |
+
"step": 50
|
| 899 |
+
},
|
| 900 |
+
{
|
| 901 |
+
"epoch": 0.8,
|
| 902 |
+
"eval_exact_match": 0.2857142857142857,
|
| 903 |
+
"eval_f1_a": 0.7153846153846154,
|
| 904 |
+
"eval_f1_m": 0.6606701122007244,
|
| 905 |
+
"eval_loss": 0.6473947763442993,
|
| 906 |
+
"eval_runtime": 12.3332,
|
| 907 |
+
"eval_samples_per_second": 20.27,
|
| 908 |
+
"eval_steps_per_second": 2.595,
|
| 909 |
+
"step": 50
|
| 910 |
+
},
|
| 911 |
+
{
|
| 912 |
+
"epoch": 0.816,
|
| 913 |
+
"grad_norm": 134.0,
|
| 914 |
+
"learning_rate": 2.9918032786885248e-05,
|
| 915 |
+
"loss": 0.3845,
|
| 916 |
+
"step": 51
|
| 917 |
+
},
|
| 918 |
+
{
|
| 919 |
+
"epoch": 0.816,
|
| 920 |
+
"eval_exact_match": 0.32653061224489793,
|
| 921 |
+
"eval_f1_a": 0.7294117647058824,
|
| 922 |
+
"eval_f1_m": 0.678717937391407,
|
| 923 |
+
"eval_loss": 0.5836625695228577,
|
| 924 |
+
"eval_runtime": 12.339,
|
| 925 |
+
"eval_samples_per_second": 20.261,
|
| 926 |
+
"eval_steps_per_second": 2.593,
|
| 927 |
+
"step": 51
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"epoch": 0.832,
|
| 931 |
+
"grad_norm": 74.0,
|
| 932 |
+
"learning_rate": 2.9508196721311478e-05,
|
| 933 |
+
"loss": 0.5115,
|
| 934 |
+
"step": 52
|
| 935 |
+
},
|
| 936 |
+
{
|
| 937 |
+
"epoch": 0.832,
|
| 938 |
+
"eval_exact_match": 0.3469387755102041,
|
| 939 |
+
"eval_f1_a": 0.7372881355932204,
|
| 940 |
+
"eval_f1_m": 0.6891863238802014,
|
| 941 |
+
"eval_loss": 0.5151972770690918,
|
| 942 |
+
"eval_runtime": 12.3367,
|
| 943 |
+
"eval_samples_per_second": 20.265,
|
| 944 |
+
"eval_steps_per_second": 2.594,
|
| 945 |
+
"step": 52
|
| 946 |
+
},
|
| 947 |
+
{
|
| 948 |
+
"epoch": 0.848,
|
| 949 |
+
"grad_norm": 256.0,
|
| 950 |
+
"learning_rate": 2.9098360655737705e-05,
|
| 951 |
+
"loss": 0.6891,
|
| 952 |
+
"step": 53
|
| 953 |
+
},
|
| 954 |
+
{
|
| 955 |
+
"epoch": 0.848,
|
| 956 |
+
"eval_exact_match": 0.3673469387755102,
|
| 957 |
+
"eval_f1_a": 0.7272727272727274,
|
| 958 |
+
"eval_f1_m": 0.7045895147935964,
|
| 959 |
+
"eval_loss": 0.4679683744907379,
|
| 960 |
+
"eval_runtime": 12.3357,
|
| 961 |
+
"eval_samples_per_second": 20.266,
|
| 962 |
+
"eval_steps_per_second": 2.594,
|
| 963 |
+
"step": 53
|
| 964 |
+
},
|
| 965 |
+
{
|
| 966 |
+
"epoch": 0.864,
|
| 967 |
+
"grad_norm": 79.5,
|
| 968 |
+
"learning_rate": 2.8688524590163935e-05,
|
| 969 |
+
"loss": 0.5393,
|
| 970 |
+
"step": 54
|
| 971 |
+
},
|
| 972 |
+
{
|
| 973 |
+
"epoch": 0.864,
|
| 974 |
+
"eval_exact_match": 0.3673469387755102,
|
| 975 |
+
"eval_f1_a": 0.707182320441989,
|
| 976 |
+
"eval_f1_m": 0.6976624849073828,
|
| 977 |
+
"eval_loss": 0.4734865725040436,
|
| 978 |
+
"eval_runtime": 12.4329,
|
| 979 |
+
"eval_samples_per_second": 20.108,
|
| 980 |
+
"eval_steps_per_second": 2.574,
|
| 981 |
+
"step": 54
|
| 982 |
+
},
|
| 983 |
+
{
|
| 984 |
+
"epoch": 0.88,
|
| 985 |
+
"grad_norm": 75.0,
|
| 986 |
+
"learning_rate": 2.8278688524590162e-05,
|
| 987 |
+
"loss": 0.3111,
|
| 988 |
+
"step": 55
|
| 989 |
+
},
|
| 990 |
+
{
|
| 991 |
+
"epoch": 0.88,
|
| 992 |
+
"eval_exact_match": 0.24489795918367346,
|
| 993 |
+
"eval_f1_a": 0.6181818181818182,
|
| 994 |
+
"eval_f1_m": 0.6299465840282166,
|
| 995 |
+
"eval_loss": 0.5052010416984558,
|
| 996 |
+
"eval_runtime": 12.3374,
|
| 997 |
+
"eval_samples_per_second": 20.264,
|
| 998 |
+
"eval_steps_per_second": 2.594,
|
| 999 |
+
"step": 55
|
| 1000 |
+
},
|
| 1001 |
+
{
|
| 1002 |
+
"epoch": 0.896,
|
| 1003 |
+
"grad_norm": 40.75,
|
| 1004 |
+
"learning_rate": 2.7868852459016392e-05,
|
| 1005 |
+
"loss": 0.4355,
|
| 1006 |
+
"step": 56
|
| 1007 |
+
},
|
| 1008 |
+
{
|
| 1009 |
+
"epoch": 0.896,
|
| 1010 |
+
"eval_exact_match": 0.20408163265306123,
|
| 1011 |
+
"eval_f1_a": 0.5503355704697986,
|
| 1012 |
+
"eval_f1_m": 0.5819880233145538,
|
| 1013 |
+
"eval_loss": 0.5698792338371277,
|
| 1014 |
+
"eval_runtime": 12.3364,
|
| 1015 |
+
"eval_samples_per_second": 20.265,
|
| 1016 |
+
"eval_steps_per_second": 2.594,
|
| 1017 |
+
"step": 56
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 0.912,
|
| 1021 |
+
"grad_norm": 109.0,
|
| 1022 |
+
"learning_rate": 2.7459016393442626e-05,
|
| 1023 |
+
"loss": 0.4511,
|
| 1024 |
+
"step": 57
|
| 1025 |
+
},
|
| 1026 |
+
{
|
| 1027 |
+
"epoch": 0.912,
|
| 1028 |
+
"eval_exact_match": 0.12244897959183673,
|
| 1029 |
+
"eval_f1_a": 0.4492753623188406,
|
| 1030 |
+
"eval_f1_m": 0.5171135553788614,
|
| 1031 |
+
"eval_loss": 0.6130319833755493,
|
| 1032 |
+
"eval_runtime": 12.2415,
|
| 1033 |
+
"eval_samples_per_second": 20.422,
|
| 1034 |
+
"eval_steps_per_second": 2.614,
|
| 1035 |
+
"step": 57
|
| 1036 |
+
},
|
| 1037 |
+
{
|
| 1038 |
+
"epoch": 0.928,
|
| 1039 |
+
"grad_norm": 258.0,
|
| 1040 |
+
"learning_rate": 2.7049180327868856e-05,
|
| 1041 |
+
"loss": 1.3501,
|
| 1042 |
+
"step": 58
|
| 1043 |
+
},
|
| 1044 |
+
{
|
| 1045 |
+
"epoch": 0.928,
|
| 1046 |
+
"eval_exact_match": 0.14285714285714285,
|
| 1047 |
+
"eval_f1_a": 0.4748201438848921,
|
| 1048 |
+
"eval_f1_m": 0.5406240584812012,
|
| 1049 |
+
"eval_loss": 0.6232966184616089,
|
| 1050 |
+
"eval_runtime": 12.3304,
|
| 1051 |
+
"eval_samples_per_second": 20.275,
|
| 1052 |
+
"eval_steps_per_second": 2.595,
|
| 1053 |
+
"step": 58
|
| 1054 |
+
},
|
| 1055 |
+
{
|
| 1056 |
+
"epoch": 0.944,
|
| 1057 |
+
"grad_norm": 208.0,
|
| 1058 |
+
"learning_rate": 2.6639344262295087e-05,
|
| 1059 |
+
"loss": 0.5805,
|
| 1060 |
+
"step": 59
|
| 1061 |
+
},
|
| 1062 |
+
{
|
| 1063 |
+
"epoch": 0.944,
|
| 1064 |
+
"eval_exact_match": 0.16326530612244897,
|
| 1065 |
+
"eval_f1_a": 0.5034965034965034,
|
| 1066 |
+
"eval_f1_m": 0.5562379230746576,
|
| 1067 |
+
"eval_loss": 0.6023154258728027,
|
| 1068 |
+
"eval_runtime": 12.3275,
|
| 1069 |
+
"eval_samples_per_second": 20.28,
|
| 1070 |
+
"eval_steps_per_second": 2.596,
|
| 1071 |
+
"step": 59
|
| 1072 |
+
},
|
| 1073 |
+
{
|
| 1074 |
+
"epoch": 0.96,
|
| 1075 |
+
"grad_norm": 200.0,
|
| 1076 |
+
"learning_rate": 2.6229508196721314e-05,
|
| 1077 |
+
"loss": 0.7816,
|
| 1078 |
+
"step": 60
|
| 1079 |
+
},
|
| 1080 |
+
{
|
| 1081 |
+
"epoch": 0.96,
|
| 1082 |
+
"eval_exact_match": 0.20408163265306123,
|
| 1083 |
+
"eval_f1_a": 0.5657894736842105,
|
| 1084 |
+
"eval_f1_m": 0.5914713404509321,
|
| 1085 |
+
"eval_loss": 0.5609907507896423,
|
| 1086 |
+
"eval_runtime": 12.3311,
|
| 1087 |
+
"eval_samples_per_second": 20.274,
|
| 1088 |
+
"eval_steps_per_second": 2.595,
|
| 1089 |
+
"step": 60
|
| 1090 |
+
},
|
| 1091 |
+
{
|
| 1092 |
+
"epoch": 0.976,
|
| 1093 |
+
"grad_norm": 121.5,
|
| 1094 |
+
"learning_rate": 2.5819672131147544e-05,
|
| 1095 |
+
"loss": 0.36,
|
| 1096 |
+
"step": 61
|
| 1097 |
+
},
|
| 1098 |
+
{
|
| 1099 |
+
"epoch": 0.976,
|
| 1100 |
+
"eval_exact_match": 0.24489795918367346,
|
| 1101 |
+
"eval_f1_a": 0.6296296296296297,
|
| 1102 |
+
"eval_f1_m": 0.6420398195908398,
|
| 1103 |
+
"eval_loss": 0.510808527469635,
|
| 1104 |
+
"eval_runtime": 12.2463,
|
| 1105 |
+
"eval_samples_per_second": 20.414,
|
| 1106 |
+
"eval_steps_per_second": 2.613,
|
| 1107 |
+
"step": 61
|
| 1108 |
+
},
|
| 1109 |
+
{
|
| 1110 |
+
"epoch": 0.992,
|
| 1111 |
+
"grad_norm": 89.5,
|
| 1112 |
+
"learning_rate": 2.540983606557377e-05,
|
| 1113 |
+
"loss": 0.7232,
|
| 1114 |
+
"step": 62
|
| 1115 |
+
},
|
| 1116 |
+
{
|
| 1117 |
+
"epoch": 0.992,
|
| 1118 |
+
"eval_exact_match": 0.3673469387755102,
|
| 1119 |
+
"eval_f1_a": 0.707182320441989,
|
| 1120 |
+
"eval_f1_m": 0.6995737255941337,
|
| 1121 |
+
"eval_loss": 0.4643671214580536,
|
| 1122 |
+
"eval_runtime": 12.3245,
|
| 1123 |
+
"eval_samples_per_second": 20.285,
|
| 1124 |
+
"eval_steps_per_second": 2.596,
|
| 1125 |
+
"step": 62
|
| 1126 |
+
},
|
| 1127 |
+
{
|
| 1128 |
+
"epoch": 1.008,
|
| 1129 |
+
"grad_norm": 113.5,
|
| 1130 |
+
"learning_rate": 2.5e-05,
|
| 1131 |
+
"loss": 0.3122,
|
| 1132 |
+
"step": 63
|
| 1133 |
+
},
|
| 1134 |
+
{
|
| 1135 |
+
"epoch": 1.008,
|
| 1136 |
+
"eval_exact_match": 0.42857142857142855,
|
| 1137 |
+
"eval_f1_a": 0.751269035532995,
|
| 1138 |
+
"eval_f1_m": 0.7261010531418695,
|
| 1139 |
+
"eval_loss": 0.4434533715248108,
|
| 1140 |
+
"eval_runtime": 12.3335,
|
| 1141 |
+
"eval_samples_per_second": 20.27,
|
| 1142 |
+
"eval_steps_per_second": 2.595,
|
| 1143 |
+
"step": 63
|
| 1144 |
+
},
|
| 1145 |
+
{
|
| 1146 |
+
"epoch": 1.024,
|
| 1147 |
+
"grad_norm": 18.25,
|
| 1148 |
+
"learning_rate": 2.459016393442623e-05,
|
| 1149 |
+
"loss": 0.3171,
|
| 1150 |
+
"step": 64
|
| 1151 |
+
},
|
| 1152 |
+
{
|
| 1153 |
+
"epoch": 1.024,
|
| 1154 |
+
"eval_exact_match": 0.32653061224489793,
|
| 1155 |
+
"eval_f1_a": 0.7339449541284404,
|
| 1156 |
+
"eval_f1_m": 0.6932083222899549,
|
| 1157 |
+
"eval_loss": 0.4687900245189667,
|
| 1158 |
+
"eval_runtime": 12.3312,
|
| 1159 |
+
"eval_samples_per_second": 20.274,
|
| 1160 |
+
"eval_steps_per_second": 2.595,
|
| 1161 |
+
"step": 64
|
| 1162 |
+
},
|
| 1163 |
+
{
|
| 1164 |
+
"epoch": 1.04,
|
| 1165 |
+
"grad_norm": 47.75,
|
| 1166 |
+
"learning_rate": 2.418032786885246e-05,
|
| 1167 |
+
"loss": 0.3128,
|
| 1168 |
+
"step": 65
|
| 1169 |
+
},
|
| 1170 |
+
{
|
| 1171 |
+
"epoch": 1.04,
|
| 1172 |
+
"eval_exact_match": 0.32653061224489793,
|
| 1173 |
+
"eval_f1_a": 0.7377049180327868,
|
| 1174 |
+
"eval_f1_m": 0.6916600406396326,
|
| 1175 |
+
"eval_loss": 0.5542958974838257,
|
| 1176 |
+
"eval_runtime": 12.3367,
|
| 1177 |
+
"eval_samples_per_second": 20.265,
|
| 1178 |
+
"eval_steps_per_second": 2.594,
|
| 1179 |
+
"step": 65
|
| 1180 |
+
},
|
| 1181 |
+
{
|
| 1182 |
+
"epoch": 1.056,
|
| 1183 |
+
"grad_norm": 64.5,
|
| 1184 |
+
"learning_rate": 2.377049180327869e-05,
|
| 1185 |
+
"loss": 0.3816,
|
| 1186 |
+
"step": 66
|
| 1187 |
+
},
|
| 1188 |
+
{
|
| 1189 |
+
"epoch": 1.056,
|
| 1190 |
+
"eval_exact_match": 0.24489795918367346,
|
| 1191 |
+
"eval_f1_a": 0.7084870848708487,
|
| 1192 |
+
"eval_f1_m": 0.6366897841387638,
|
| 1193 |
+
"eval_loss": 0.7233641147613525,
|
| 1194 |
+
"eval_runtime": 12.3398,
|
| 1195 |
+
"eval_samples_per_second": 20.26,
|
| 1196 |
+
"eval_steps_per_second": 2.593,
|
| 1197 |
+
"step": 66
|
| 1198 |
+
},
|
| 1199 |
+
{
|
| 1200 |
+
"epoch": 1.072,
|
| 1201 |
+
"grad_norm": 108.0,
|
| 1202 |
+
"learning_rate": 2.336065573770492e-05,
|
| 1203 |
+
"loss": 0.4357,
|
| 1204 |
+
"step": 67
|
| 1205 |
+
},
|
| 1206 |
+
{
|
| 1207 |
+
"epoch": 1.072,
|
| 1208 |
+
"eval_exact_match": 0.22448979591836735,
|
| 1209 |
+
"eval_f1_a": 0.6978417266187049,
|
| 1210 |
+
"eval_f1_m": 0.6151021880613716,
|
| 1211 |
+
"eval_loss": 0.8721888661384583,
|
| 1212 |
+
"eval_runtime": 12.4324,
|
| 1213 |
+
"eval_samples_per_second": 20.109,
|
| 1214 |
+
"eval_steps_per_second": 2.574,
|
| 1215 |
+
"step": 67
|
| 1216 |
+
},
|
| 1217 |
+
{
|
| 1218 |
+
"epoch": 1.088,
|
| 1219 |
+
"grad_norm": 197.0,
|
| 1220 |
+
"learning_rate": 2.295081967213115e-05,
|
| 1221 |
+
"loss": 0.6305,
|
| 1222 |
+
"step": 68
|
| 1223 |
+
},
|
| 1224 |
+
{
|
| 1225 |
+
"epoch": 1.088,
|
| 1226 |
+
"eval_exact_match": 0.16326530612244897,
|
| 1227 |
+
"eval_f1_a": 0.6783216783216783,
|
| 1228 |
+
"eval_f1_m": 0.5768347298959543,
|
| 1229 |
+
"eval_loss": 0.9692529439926147,
|
| 1230 |
+
"eval_runtime": 12.3383,
|
| 1231 |
+
"eval_samples_per_second": 20.262,
|
| 1232 |
+
"eval_steps_per_second": 2.594,
|
| 1233 |
+
"step": 68
|
| 1234 |
+
},
|
| 1235 |
+
{
|
| 1236 |
+
"epoch": 1.104,
|
| 1237 |
+
"grad_norm": 260.0,
|
| 1238 |
+
"learning_rate": 2.254098360655738e-05,
|
| 1239 |
+
"loss": 0.8817,
|
| 1240 |
+
"step": 69
|
| 1241 |
+
},
|
| 1242 |
+
{
|
| 1243 |
+
"epoch": 1.104,
|
| 1244 |
+
"eval_exact_match": 0.16326530612244897,
|
| 1245 |
+
"eval_f1_a": 0.6759581881533101,
|
| 1246 |
+
"eval_f1_m": 0.5696183634959144,
|
| 1247 |
+
"eval_loss": 1.0210760831832886,
|
| 1248 |
+
"eval_runtime": 12.2519,
|
| 1249 |
+
"eval_samples_per_second": 20.405,
|
| 1250 |
+
"eval_steps_per_second": 2.612,
|
| 1251 |
+
"step": 69
|
| 1252 |
+
},
|
| 1253 |
+
{
|
| 1254 |
+
"epoch": 1.12,
|
| 1255 |
+
"grad_norm": 172.0,
|
| 1256 |
+
"learning_rate": 2.2131147540983607e-05,
|
| 1257 |
+
"loss": 0.7075,
|
| 1258 |
+
"step": 70
|
| 1259 |
+
},
|
| 1260 |
+
{
|
| 1261 |
+
"epoch": 1.12,
|
| 1262 |
+
"eval_exact_match": 0.16326530612244897,
|
| 1263 |
+
"eval_f1_a": 0.6853146853146854,
|
| 1264 |
+
"eval_f1_m": 0.5790823688782871,
|
| 1265 |
+
"eval_loss": 1.0169488191604614,
|
| 1266 |
+
"eval_runtime": 12.2458,
|
| 1267 |
+
"eval_samples_per_second": 20.415,
|
| 1268 |
+
"eval_steps_per_second": 2.613,
|
| 1269 |
+
"step": 70
|
| 1270 |
+
},
|
| 1271 |
+
{
|
| 1272 |
+
"epoch": 1.1360000000000001,
|
| 1273 |
+
"grad_norm": 187.0,
|
| 1274 |
+
"learning_rate": 2.1721311475409837e-05,
|
| 1275 |
+
"loss": 0.4686,
|
| 1276 |
+
"step": 71
|
| 1277 |
+
},
|
| 1278 |
+
{
|
| 1279 |
+
"epoch": 1.1360000000000001,
|
| 1280 |
+
"eval_exact_match": 0.20408163265306123,
|
| 1281 |
+
"eval_f1_a": 0.692857142857143,
|
| 1282 |
+
"eval_f1_m": 0.6007134022440144,
|
| 1283 |
+
"eval_loss": 0.9803246855735779,
|
| 1284 |
+
"eval_runtime": 12.3409,
|
| 1285 |
+
"eval_samples_per_second": 20.258,
|
| 1286 |
+
"eval_steps_per_second": 2.593,
|
| 1287 |
+
"step": 71
|
| 1288 |
+
},
|
| 1289 |
+
{
|
| 1290 |
+
"epoch": 1.152,
|
| 1291 |
+
"grad_norm": 139.0,
|
| 1292 |
+
"learning_rate": 2.1311475409836064e-05,
|
| 1293 |
+
"loss": 0.7498,
|
| 1294 |
+
"step": 72
|
| 1295 |
+
},
|
| 1296 |
+
{
|
| 1297 |
+
"epoch": 1.152,
|
| 1298 |
+
"eval_exact_match": 0.22448979591836735,
|
| 1299 |
+
"eval_f1_a": 0.7003610108303248,
|
| 1300 |
+
"eval_f1_m": 0.6187465029301763,
|
| 1301 |
+
"eval_loss": 0.9064192771911621,
|
| 1302 |
+
"eval_runtime": 12.4412,
|
| 1303 |
+
"eval_samples_per_second": 20.095,
|
| 1304 |
+
"eval_steps_per_second": 2.572,
|
| 1305 |
+
"step": 72
|
| 1306 |
+
},
|
| 1307 |
+
{
|
| 1308 |
+
"epoch": 1.168,
|
| 1309 |
+
"grad_norm": 132.0,
|
| 1310 |
+
"learning_rate": 2.0901639344262298e-05,
|
| 1311 |
+
"loss": 0.5164,
|
| 1312 |
+
"step": 73
|
| 1313 |
+
},
|
| 1314 |
+
{
|
| 1315 |
+
"epoch": 1.168,
|
| 1316 |
+
"eval_exact_match": 0.2653061224489796,
|
| 1317 |
+
"eval_f1_a": 0.7058823529411764,
|
| 1318 |
+
"eval_f1_m": 0.6373082133286214,
|
| 1319 |
+
"eval_loss": 0.8129245638847351,
|
| 1320 |
+
"eval_runtime": 12.3485,
|
| 1321 |
+
"eval_samples_per_second": 20.245,
|
| 1322 |
+
"eval_steps_per_second": 2.591,
|
| 1323 |
+
"step": 73
|
| 1324 |
+
},
|
| 1325 |
+
{
|
| 1326 |
+
"epoch": 1.184,
|
| 1327 |
+
"grad_norm": 74.0,
|
| 1328 |
+
"learning_rate": 2.0491803278688525e-05,
|
| 1329 |
+
"loss": 0.3558,
|
| 1330 |
+
"step": 74
|
| 1331 |
+
},
|
| 1332 |
+
{
|
| 1333 |
+
"epoch": 1.184,
|
| 1334 |
+
"eval_exact_match": 0.3469387755102041,
|
| 1335 |
+
"eval_f1_a": 0.7335907335907335,
|
| 1336 |
+
"eval_f1_m": 0.6795896280590158,
|
| 1337 |
+
"eval_loss": 0.708591878414154,
|
| 1338 |
+
"eval_runtime": 12.3356,
|
| 1339 |
+
"eval_samples_per_second": 20.267,
|
| 1340 |
+
"eval_steps_per_second": 2.594,
|
| 1341 |
+
"step": 74
|
| 1342 |
+
},
|
| 1343 |
+
{
|
| 1344 |
+
"epoch": 1.2,
|
| 1345 |
+
"grad_norm": 23.75,
|
| 1346 |
+
"learning_rate": 2.0081967213114755e-05,
|
| 1347 |
+
"loss": 0.2078,
|
| 1348 |
+
"step": 75
|
| 1349 |
+
},
|
| 1350 |
+
{
|
| 1351 |
+
"epoch": 1.2,
|
| 1352 |
+
"eval_exact_match": 0.32653061224489793,
|
| 1353 |
+
"eval_f1_a": 0.736842105263158,
|
| 1354 |
+
"eval_f1_m": 0.6910879936390141,
|
| 1355 |
+
"eval_loss": 0.6179347634315491,
|
| 1356 |
+
"eval_runtime": 12.1319,
|
| 1357 |
+
"eval_samples_per_second": 20.607,
|
| 1358 |
+
"eval_steps_per_second": 2.638,
|
| 1359 |
+
"step": 75
|
| 1360 |
+
},
|
| 1361 |
+
{
|
| 1362 |
+
"epoch": 1.216,
|
| 1363 |
+
"grad_norm": 67.5,
|
| 1364 |
+
"learning_rate": 1.9672131147540985e-05,
|
| 1365 |
+
"loss": 0.4554,
|
| 1366 |
+
"step": 76
|
| 1367 |
+
},
|
| 1368 |
+
{
|
| 1369 |
+
"epoch": 1.216,
|
| 1370 |
+
"eval_exact_match": 0.3469387755102041,
|
| 1371 |
+
"eval_f1_a": 0.7404255319148937,
|
| 1372 |
+
"eval_f1_m": 0.6999057631710693,
|
| 1373 |
+
"eval_loss": 0.5416720509529114,
|
| 1374 |
+
"eval_runtime": 12.3386,
|
| 1375 |
+
"eval_samples_per_second": 20.262,
|
| 1376 |
+
"eval_steps_per_second": 2.593,
|
| 1377 |
+
"step": 76
|
| 1378 |
+
},
|
| 1379 |
+
{
|
| 1380 |
+
"epoch": 1.232,
|
| 1381 |
+
"grad_norm": 15.375,
|
| 1382 |
+
"learning_rate": 1.9262295081967212e-05,
|
| 1383 |
+
"loss": 0.474,
|
| 1384 |
+
"step": 77
|
| 1385 |
+
},
|
| 1386 |
+
{
|
| 1387 |
+
"epoch": 1.232,
|
| 1388 |
+
"eval_exact_match": 0.3469387755102041,
|
| 1389 |
+
"eval_f1_a": 0.7454545454545454,
|
| 1390 |
+
"eval_f1_m": 0.6985886562417175,
|
| 1391 |
+
"eval_loss": 0.47036615014076233,
|
| 1392 |
+
"eval_runtime": 12.1382,
|
| 1393 |
+
"eval_samples_per_second": 20.596,
|
| 1394 |
+
"eval_steps_per_second": 2.636,
|
| 1395 |
+
"step": 77
|
| 1396 |
+
},
|
| 1397 |
+
{
|
| 1398 |
+
"epoch": 1.248,
|
| 1399 |
+
"grad_norm": 69.5,
|
| 1400 |
+
"learning_rate": 1.8852459016393442e-05,
|
| 1401 |
+
"loss": 0.2118,
|
| 1402 |
+
"step": 78
|
| 1403 |
+
},
|
| 1404 |
+
{
|
| 1405 |
+
"epoch": 1.248,
|
| 1406 |
+
"eval_exact_match": 0.42857142857142855,
|
| 1407 |
+
"eval_f1_a": 0.7714285714285715,
|
| 1408 |
+
"eval_f1_m": 0.7349028522497911,
|
| 1409 |
+
"eval_loss": 0.4449598491191864,
|
| 1410 |
+
"eval_runtime": 12.3417,
|
| 1411 |
+
"eval_samples_per_second": 20.257,
|
| 1412 |
+
"eval_steps_per_second": 2.593,
|
| 1413 |
+
"step": 78
|
| 1414 |
+
},
|
| 1415 |
+
{
|
| 1416 |
+
"epoch": 1.264,
|
| 1417 |
+
"grad_norm": 89.5,
|
| 1418 |
+
"learning_rate": 1.8442622950819673e-05,
|
| 1419 |
+
"loss": 0.3961,
|
| 1420 |
+
"step": 79
|
| 1421 |
+
},
|
| 1422 |
+
{
|
| 1423 |
+
"epoch": 1.264,
|
| 1424 |
+
"eval_exact_match": 0.3877551020408163,
|
| 1425 |
+
"eval_f1_a": 0.7609756097560977,
|
| 1426 |
+
"eval_f1_m": 0.7192161013589586,
|
| 1427 |
+
"eval_loss": 0.43572884798049927,
|
| 1428 |
+
"eval_runtime": 12.1292,
|
| 1429 |
+
"eval_samples_per_second": 20.611,
|
| 1430 |
+
"eval_steps_per_second": 2.638,
|
| 1431 |
+
"step": 79
|
| 1432 |
+
},
|
| 1433 |
+
{
|
| 1434 |
+
"epoch": 1.28,
|
| 1435 |
+
"grad_norm": 43.5,
|
| 1436 |
+
"learning_rate": 1.8032786885245903e-05,
|
| 1437 |
+
"loss": 0.1135,
|
| 1438 |
+
"step": 80
|
| 1439 |
+
},
|
| 1440 |
+
{
|
| 1441 |
+
"epoch": 1.28,
|
| 1442 |
+
"eval_exact_match": 0.42857142857142855,
|
| 1443 |
+
"eval_f1_a": 0.7676767676767676,
|
| 1444 |
+
"eval_f1_m": 0.7345044144864072,
|
| 1445 |
+
"eval_loss": 0.42786112427711487,
|
| 1446 |
+
"eval_runtime": 12.1258,
|
| 1447 |
+
"eval_samples_per_second": 20.617,
|
| 1448 |
+
"eval_steps_per_second": 2.639,
|
| 1449 |
+
"step": 80
|
| 1450 |
+
},
|
| 1451 |
+
{
|
| 1452 |
+
"epoch": 1.296,
|
| 1453 |
+
"grad_norm": 66.0,
|
| 1454 |
+
"learning_rate": 1.7622950819672133e-05,
|
| 1455 |
+
"loss": 0.3855,
|
| 1456 |
+
"step": 81
|
| 1457 |
+
},
|
| 1458 |
+
{
|
| 1459 |
+
"epoch": 1.296,
|
| 1460 |
+
"eval_exact_match": 0.40816326530612246,
|
| 1461 |
+
"eval_f1_a": 0.7564766839378239,
|
| 1462 |
+
"eval_f1_m": 0.7204516871683738,
|
| 1463 |
+
"eval_loss": 0.42685583233833313,
|
| 1464 |
+
"eval_runtime": 12.2231,
|
| 1465 |
+
"eval_samples_per_second": 20.453,
|
| 1466 |
+
"eval_steps_per_second": 2.618,
|
| 1467 |
+
"step": 81
|
| 1468 |
+
},
|
| 1469 |
+
{
|
| 1470 |
+
"epoch": 1.312,
|
| 1471 |
+
"grad_norm": 71.5,
|
| 1472 |
+
"learning_rate": 1.721311475409836e-05,
|
| 1473 |
+
"loss": 0.2578,
|
| 1474 |
+
"step": 82
|
| 1475 |
+
},
|
| 1476 |
+
{
|
| 1477 |
+
"epoch": 1.312,
|
| 1478 |
+
"eval_exact_match": 0.40816326530612246,
|
| 1479 |
+
"eval_f1_a": 0.7564766839378239,
|
| 1480 |
+
"eval_f1_m": 0.7221188975090536,
|
| 1481 |
+
"eval_loss": 0.4235145151615143,
|
| 1482 |
+
"eval_runtime": 12.2206,
|
| 1483 |
+
"eval_samples_per_second": 20.457,
|
| 1484 |
+
"eval_steps_per_second": 2.619,
|
| 1485 |
+
"step": 82
|
| 1486 |
+
},
|
| 1487 |
+
{
|
| 1488 |
+
"epoch": 1.328,
|
| 1489 |
+
"grad_norm": 15.75,
|
| 1490 |
+
"learning_rate": 1.680327868852459e-05,
|
| 1491 |
+
"loss": 0.2663,
|
| 1492 |
+
"step": 83
|
| 1493 |
+
},
|
| 1494 |
+
{
|
| 1495 |
+
"epoch": 1.328,
|
| 1496 |
+
"eval_exact_match": 0.42857142857142855,
|
| 1497 |
+
"eval_f1_a": 0.7731958762886598,
|
| 1498 |
+
"eval_f1_m": 0.735714372329018,
|
| 1499 |
+
"eval_loss": 0.42393288016319275,
|
| 1500 |
+
"eval_runtime": 12.3217,
|
| 1501 |
+
"eval_samples_per_second": 20.289,
|
| 1502 |
+
"eval_steps_per_second": 2.597,
|
| 1503 |
+
"step": 83
|
| 1504 |
+
},
|
| 1505 |
+
{
|
| 1506 |
+
"epoch": 1.3439999999999999,
|
| 1507 |
+
"grad_norm": 176.0,
|
| 1508 |
+
"learning_rate": 1.6393442622950818e-05,
|
| 1509 |
+
"loss": 0.7327,
|
| 1510 |
+
"step": 84
|
| 1511 |
+
},
|
| 1512 |
+
{
|
| 1513 |
+
"epoch": 1.3439999999999999,
|
| 1514 |
+
"eval_exact_match": 0.42857142857142855,
|
| 1515 |
+
"eval_f1_a": 0.7692307692307692,
|
| 1516 |
+
"eval_f1_m": 0.7348173102074662,
|
| 1517 |
+
"eval_loss": 0.42331308126449585,
|
| 1518 |
+
"eval_runtime": 12.2302,
|
| 1519 |
+
"eval_samples_per_second": 20.441,
|
| 1520 |
+
"eval_steps_per_second": 2.616,
|
| 1521 |
+
"step": 84
|
| 1522 |
+
},
|
| 1523 |
+
{
|
| 1524 |
+
"epoch": 1.3599999999999999,
|
| 1525 |
+
"grad_norm": 128.0,
|
| 1526 |
+
"learning_rate": 1.598360655737705e-05,
|
| 1527 |
+
"loss": 0.4978,
|
| 1528 |
+
"step": 85
|
| 1529 |
+
},
|
| 1530 |
+
{
|
| 1531 |
+
"epoch": 1.3599999999999999,
|
| 1532 |
+
"eval_exact_match": 0.40816326530612246,
|
| 1533 |
+
"eval_f1_a": 0.7761194029850748,
|
| 1534 |
+
"eval_f1_m": 0.7298315063621186,
|
| 1535 |
+
"eval_loss": 0.4208895266056061,
|
| 1536 |
+
"eval_runtime": 12.2265,
|
| 1537 |
+
"eval_samples_per_second": 20.447,
|
| 1538 |
+
"eval_steps_per_second": 2.617,
|
| 1539 |
+
"step": 85
|
| 1540 |
+
},
|
| 1541 |
+
{
|
| 1542 |
+
"epoch": 1.376,
|
| 1543 |
+
"grad_norm": 46.75,
|
| 1544 |
+
"learning_rate": 1.557377049180328e-05,
|
| 1545 |
+
"loss": 0.1779,
|
| 1546 |
+
"step": 86
|
| 1547 |
+
},
|
| 1548 |
+
{
|
| 1549 |
+
"epoch": 1.376,
|
| 1550 |
+
"eval_exact_match": 0.42857142857142855,
|
| 1551 |
+
"eval_f1_a": 0.7707317073170732,
|
| 1552 |
+
"eval_f1_m": 0.737048325823836,
|
| 1553 |
+
"eval_loss": 0.423691064119339,
|
| 1554 |
+
"eval_runtime": 12.3332,
|
| 1555 |
+
"eval_samples_per_second": 20.27,
|
| 1556 |
+
"eval_steps_per_second": 2.595,
|
| 1557 |
+
"step": 86
|
| 1558 |
+
},
|
| 1559 |
+
{
|
| 1560 |
+
"epoch": 1.392,
|
| 1561 |
+
"grad_norm": 136.0,
|
| 1562 |
+
"learning_rate": 1.5163934426229509e-05,
|
| 1563 |
+
"loss": 0.4363,
|
| 1564 |
+
"step": 87
|
| 1565 |
+
},
|
| 1566 |
+
{
|
| 1567 |
+
"epoch": 1.392,
|
| 1568 |
+
"eval_exact_match": 0.42857142857142855,
|
| 1569 |
+
"eval_f1_a": 0.7714285714285715,
|
| 1570 |
+
"eval_f1_m": 0.7422886637172352,
|
| 1571 |
+
"eval_loss": 0.4328218996524811,
|
| 1572 |
+
"eval_runtime": 12.3404,
|
| 1573 |
+
"eval_samples_per_second": 20.259,
|
| 1574 |
+
"eval_steps_per_second": 2.593,
|
| 1575 |
+
"step": 87
|
| 1576 |
+
},
|
| 1577 |
+
{
|
| 1578 |
+
"epoch": 1.408,
|
| 1579 |
+
"grad_norm": 26.125,
|
| 1580 |
+
"learning_rate": 1.4754098360655739e-05,
|
| 1581 |
+
"loss": 0.0689,
|
| 1582 |
+
"step": 88
|
| 1583 |
+
},
|
| 1584 |
+
{
|
| 1585 |
+
"epoch": 1.408,
|
| 1586 |
+
"eval_exact_match": 0.40816326530612246,
|
| 1587 |
+
"eval_f1_a": 0.7605633802816901,
|
| 1588 |
+
"eval_f1_m": 0.7356714713857571,
|
| 1589 |
+
"eval_loss": 0.4407349228858948,
|
| 1590 |
+
"eval_runtime": 12.4417,
|
| 1591 |
+
"eval_samples_per_second": 20.094,
|
| 1592 |
+
"eval_steps_per_second": 2.572,
|
| 1593 |
+
"step": 88
|
| 1594 |
+
},
|
| 1595 |
+
{
|
| 1596 |
+
"epoch": 1.424,
|
| 1597 |
+
"grad_norm": 86.5,
|
| 1598 |
+
"learning_rate": 1.4344262295081968e-05,
|
| 1599 |
+
"loss": 0.281,
|
| 1600 |
+
"step": 89
|
| 1601 |
+
},
|
| 1602 |
+
{
|
| 1603 |
+
"epoch": 1.424,
|
| 1604 |
+
"eval_exact_match": 0.40816326530612246,
|
| 1605 |
+
"eval_f1_a": 0.7605633802816901,
|
| 1606 |
+
"eval_f1_m": 0.7356714713857571,
|
| 1607 |
+
"eval_loss": 0.4479525685310364,
|
| 1608 |
+
"eval_runtime": 12.1312,
|
| 1609 |
+
"eval_samples_per_second": 20.608,
|
| 1610 |
+
"eval_steps_per_second": 2.638,
|
| 1611 |
+
"step": 89
|
| 1612 |
+
},
|
| 1613 |
+
{
|
| 1614 |
+
"epoch": 1.44,
|
| 1615 |
+
"grad_norm": 22.5,
|
| 1616 |
+
"learning_rate": 1.3934426229508196e-05,
|
| 1617 |
+
"loss": 0.0549,
|
| 1618 |
+
"step": 90
|
| 1619 |
+
},
|
| 1620 |
+
{
|
| 1621 |
+
"epoch": 1.44,
|
| 1622 |
+
"eval_exact_match": 0.3469387755102041,
|
| 1623 |
+
"eval_f1_a": 0.7431192660550459,
|
| 1624 |
+
"eval_f1_m": 0.7090495672128325,
|
| 1625 |
+
"eval_loss": 0.45782843232154846,
|
| 1626 |
+
"eval_runtime": 12.1361,
|
| 1627 |
+
"eval_samples_per_second": 20.6,
|
| 1628 |
+
"eval_steps_per_second": 2.637,
|
| 1629 |
+
"step": 90
|
| 1630 |
+
},
|
| 1631 |
+
{
|
| 1632 |
+
"epoch": 1.456,
|
| 1633 |
+
"grad_norm": 29.25,
|
| 1634 |
+
"learning_rate": 1.3524590163934428e-05,
|
| 1635 |
+
"loss": 0.2931,
|
| 1636 |
+
"step": 91
|
| 1637 |
+
},
|
| 1638 |
+
{
|
| 1639 |
+
"epoch": 1.456,
|
| 1640 |
+
"eval_exact_match": 0.40816326530612246,
|
| 1641 |
+
"eval_f1_a": 0.7589285714285714,
|
| 1642 |
+
"eval_f1_m": 0.7325594473553658,
|
| 1643 |
+
"eval_loss": 0.47645771503448486,
|
| 1644 |
+
"eval_runtime": 12.1323,
|
| 1645 |
+
"eval_samples_per_second": 20.606,
|
| 1646 |
+
"eval_steps_per_second": 2.638,
|
| 1647 |
+
"step": 91
|
| 1648 |
+
},
|
| 1649 |
+
{
|
| 1650 |
+
"epoch": 1.472,
|
| 1651 |
+
"grad_norm": 22.75,
|
| 1652 |
+
"learning_rate": 1.3114754098360657e-05,
|
| 1653 |
+
"loss": 0.1225,
|
| 1654 |
+
"step": 92
|
| 1655 |
+
},
|
| 1656 |
+
{
|
| 1657 |
+
"epoch": 1.472,
|
| 1658 |
+
"eval_exact_match": 0.40816326530612246,
|
| 1659 |
+
"eval_f1_a": 0.7665198237885461,
|
| 1660 |
+
"eval_f1_m": 0.7343735063122818,
|
| 1661 |
+
"eval_loss": 0.48858800530433655,
|
| 1662 |
+
"eval_runtime": 12.2469,
|
| 1663 |
+
"eval_samples_per_second": 20.413,
|
| 1664 |
+
"eval_steps_per_second": 2.613,
|
| 1665 |
+
"step": 92
|
| 1666 |
+
},
|
| 1667 |
+
{
|
| 1668 |
+
"epoch": 1.488,
|
| 1669 |
+
"grad_norm": 63.25,
|
| 1670 |
+
"learning_rate": 1.2704918032786885e-05,
|
| 1671 |
+
"loss": 0.2799,
|
| 1672 |
+
"step": 93
|
| 1673 |
+
},
|
| 1674 |
+
{
|
| 1675 |
+
"epoch": 1.488,
|
| 1676 |
+
"eval_exact_match": 0.3877551020408163,
|
| 1677 |
+
"eval_f1_a": 0.7532467532467533,
|
| 1678 |
+
"eval_f1_m": 0.7212782682170437,
|
| 1679 |
+
"eval_loss": 0.5019795298576355,
|
| 1680 |
+
"eval_runtime": 12.2367,
|
| 1681 |
+
"eval_samples_per_second": 20.43,
|
| 1682 |
+
"eval_steps_per_second": 2.615,
|
| 1683 |
+
"step": 93
|
| 1684 |
+
},
|
| 1685 |
+
{
|
| 1686 |
+
"epoch": 1.504,
|
| 1687 |
+
"grad_norm": 22.875,
|
| 1688 |
+
"learning_rate": 1.2295081967213116e-05,
|
| 1689 |
+
"loss": 0.5501,
|
| 1690 |
+
"step": 94
|
| 1691 |
+
},
|
| 1692 |
+
{
|
| 1693 |
+
"epoch": 1.504,
|
| 1694 |
+
"eval_exact_match": 0.3877551020408163,
|
| 1695 |
+
"eval_f1_a": 0.7639484978540773,
|
| 1696 |
+
"eval_f1_m": 0.7284049284049283,
|
| 1697 |
+
"eval_loss": 0.5218287110328674,
|
| 1698 |
+
"eval_runtime": 12.4334,
|
| 1699 |
+
"eval_samples_per_second": 20.107,
|
| 1700 |
+
"eval_steps_per_second": 2.574,
|
| 1701 |
+
"step": 94
|
| 1702 |
+
},
|
| 1703 |
+
{
|
| 1704 |
+
"epoch": 1.52,
|
| 1705 |
+
"grad_norm": 68.0,
|
| 1706 |
+
"learning_rate": 1.1885245901639344e-05,
|
| 1707 |
+
"loss": 0.2724,
|
| 1708 |
+
"step": 95
|
| 1709 |
+
},
|
| 1710 |
+
{
|
| 1711 |
+
"epoch": 1.52,
|
| 1712 |
+
"eval_exact_match": 0.3673469387755102,
|
| 1713 |
+
"eval_f1_a": 0.7606837606837606,
|
| 1714 |
+
"eval_f1_m": 0.7243232957518672,
|
| 1715 |
+
"eval_loss": 0.527504563331604,
|
| 1716 |
+
"eval_runtime": 12.3301,
|
| 1717 |
+
"eval_samples_per_second": 20.276,
|
| 1718 |
+
"eval_steps_per_second": 2.595,
|
| 1719 |
+
"step": 95
|
| 1720 |
+
},
|
| 1721 |
+
{
|
| 1722 |
+
"epoch": 1.536,
|
| 1723 |
+
"grad_norm": 56.75,
|
| 1724 |
+
"learning_rate": 1.1475409836065575e-05,
|
| 1725 |
+
"loss": 0.1853,
|
| 1726 |
+
"step": 96
|
| 1727 |
+
},
|
| 1728 |
+
{
|
| 1729 |
+
"epoch": 1.536,
|
| 1730 |
+
"eval_exact_match": 0.3673469387755102,
|
| 1731 |
+
"eval_f1_a": 0.7606837606837606,
|
| 1732 |
+
"eval_f1_m": 0.7243232957518672,
|
| 1733 |
+
"eval_loss": 0.527137041091919,
|
| 1734 |
+
"eval_runtime": 12.3335,
|
| 1735 |
+
"eval_samples_per_second": 20.27,
|
| 1736 |
+
"eval_steps_per_second": 2.595,
|
| 1737 |
+
"step": 96
|
| 1738 |
+
},
|
| 1739 |
+
{
|
| 1740 |
+
"epoch": 1.552,
|
| 1741 |
+
"grad_norm": 87.5,
|
| 1742 |
+
"learning_rate": 1.1065573770491803e-05,
|
| 1743 |
+
"loss": 0.5676,
|
| 1744 |
+
"step": 97
|
| 1745 |
+
},
|
| 1746 |
+
{
|
| 1747 |
+
"epoch": 1.552,
|
| 1748 |
+
"eval_exact_match": 0.3877551020408163,
|
| 1749 |
+
"eval_f1_a": 0.7586206896551724,
|
| 1750 |
+
"eval_f1_m": 0.7252465221852976,
|
| 1751 |
+
"eval_loss": 0.5166082978248596,
|
| 1752 |
+
"eval_runtime": 12.2337,
|
| 1753 |
+
"eval_samples_per_second": 20.435,
|
| 1754 |
+
"eval_steps_per_second": 2.616,
|
| 1755 |
+
"step": 97
|
| 1756 |
+
},
|
| 1757 |
+
{
|
| 1758 |
+
"epoch": 1.568,
|
| 1759 |
+
"grad_norm": 7.71875,
|
| 1760 |
+
"learning_rate": 1.0655737704918032e-05,
|
| 1761 |
+
"loss": 0.1345,
|
| 1762 |
+
"step": 98
|
| 1763 |
+
},
|
| 1764 |
+
{
|
| 1765 |
+
"epoch": 1.568,
|
| 1766 |
+
"eval_exact_match": 0.3877551020408163,
|
| 1767 |
+
"eval_f1_a": 0.7586206896551724,
|
| 1768 |
+
"eval_f1_m": 0.7252465221852976,
|
| 1769 |
+
"eval_loss": 0.5162422060966492,
|
| 1770 |
+
"eval_runtime": 12.2202,
|
| 1771 |
+
"eval_samples_per_second": 20.458,
|
| 1772 |
+
"eval_steps_per_second": 2.619,
|
| 1773 |
+
"step": 98
|
| 1774 |
+
},
|
| 1775 |
+
{
|
| 1776 |
+
"epoch": 1.584,
|
| 1777 |
+
"grad_norm": 35.5,
|
| 1778 |
+
"learning_rate": 1.0245901639344262e-05,
|
| 1779 |
+
"loss": 0.121,
|
| 1780 |
+
"step": 99
|
| 1781 |
+
},
|
| 1782 |
+
{
|
| 1783 |
+
"epoch": 1.584,
|
| 1784 |
+
"eval_exact_match": 0.3673469387755102,
|
| 1785 |
+
"eval_f1_a": 0.7510917030567686,
|
| 1786 |
+
"eval_f1_m": 0.7178769076728262,
|
| 1787 |
+
"eval_loss": 0.5063967108726501,
|
| 1788 |
+
"eval_runtime": 12.3225,
|
| 1789 |
+
"eval_samples_per_second": 20.288,
|
| 1790 |
+
"eval_steps_per_second": 2.597,
|
| 1791 |
+
"step": 99
|
| 1792 |
+
},
|
| 1793 |
+
{
|
| 1794 |
+
"epoch": 1.6,
|
| 1795 |
+
"grad_norm": 35.25,
|
| 1796 |
+
"learning_rate": 9.836065573770493e-06,
|
| 1797 |
+
"loss": 0.2948,
|
| 1798 |
+
"step": 100
|
| 1799 |
+
},
|
| 1800 |
+
{
|
| 1801 |
+
"epoch": 1.6,
|
| 1802 |
+
"eval_exact_match": 0.3877551020408163,
|
| 1803 |
+
"eval_f1_a": 0.7545454545454545,
|
| 1804 |
+
"eval_f1_m": 0.7360903835393632,
|
| 1805 |
+
"eval_loss": 0.489773690700531,
|
| 1806 |
+
"eval_runtime": 12.3279,
|
| 1807 |
+
"eval_samples_per_second": 20.279,
|
| 1808 |
+
"eval_steps_per_second": 2.596,
|
| 1809 |
+
"step": 100
|
| 1810 |
+
},
|
| 1811 |
+
{
|
| 1812 |
+
"epoch": 1.616,
|
| 1813 |
+
"grad_norm": 49.25,
|
| 1814 |
+
"learning_rate": 9.426229508196721e-06,
|
| 1815 |
+
"loss": 0.1889,
|
| 1816 |
+
"step": 101
|
| 1817 |
+
},
|
| 1818 |
+
{
|
| 1819 |
+
"epoch": 1.616,
|
| 1820 |
+
"eval_exact_match": 0.3877551020408163,
|
| 1821 |
+
"eval_f1_a": 0.7592592592592593,
|
| 1822 |
+
"eval_f1_m": 0.7374295772254957,
|
| 1823 |
+
"eval_loss": 0.4733395278453827,
|
| 1824 |
+
"eval_runtime": 12.4338,
|
| 1825 |
+
"eval_samples_per_second": 20.107,
|
| 1826 |
+
"eval_steps_per_second": 2.574,
|
| 1827 |
+
"step": 101
|
| 1828 |
+
},
|
| 1829 |
+
{
|
| 1830 |
+
"epoch": 1.6320000000000001,
|
| 1831 |
+
"grad_norm": 38.25,
|
| 1832 |
+
"learning_rate": 9.016393442622952e-06,
|
| 1833 |
+
"loss": 0.2526,
|
| 1834 |
+
"step": 102
|
| 1835 |
+
},
|
| 1836 |
+
{
|
| 1837 |
+
"epoch": 1.6320000000000001,
|
| 1838 |
+
"eval_exact_match": 0.40816326530612246,
|
| 1839 |
+
"eval_f1_a": 0.7641509433962265,
|
| 1840 |
+
"eval_f1_m": 0.7369701726844585,
|
| 1841 |
+
"eval_loss": 0.46001869440078735,
|
| 1842 |
+
"eval_runtime": 12.3208,
|
| 1843 |
+
"eval_samples_per_second": 20.291,
|
| 1844 |
+
"eval_steps_per_second": 2.597,
|
| 1845 |
+
"step": 102
|
| 1846 |
+
},
|
| 1847 |
+
{
|
| 1848 |
+
"epoch": 1.6480000000000001,
|
| 1849 |
+
"grad_norm": 27.5,
|
| 1850 |
+
"learning_rate": 8.60655737704918e-06,
|
| 1851 |
+
"loss": 0.4107,
|
| 1852 |
+
"step": 103
|
| 1853 |
+
},
|
| 1854 |
+
{
|
| 1855 |
+
"epoch": 1.6480000000000001,
|
| 1856 |
+
"eval_exact_match": 0.42857142857142855,
|
| 1857 |
+
"eval_f1_a": 0.7677725118483413,
|
| 1858 |
+
"eval_f1_m": 0.7392128279883383,
|
| 1859 |
+
"eval_loss": 0.4517432153224945,
|
| 1860 |
+
"eval_runtime": 12.3285,
|
| 1861 |
+
"eval_samples_per_second": 20.278,
|
| 1862 |
+
"eval_steps_per_second": 2.596,
|
| 1863 |
+
"step": 103
|
| 1864 |
+
},
|
| 1865 |
+
{
|
| 1866 |
+
"epoch": 1.6640000000000001,
|
| 1867 |
+
"grad_norm": 23.625,
|
| 1868 |
+
"learning_rate": 8.196721311475409e-06,
|
| 1869 |
+
"loss": 0.0592,
|
| 1870 |
+
"step": 104
|
| 1871 |
+
},
|
| 1872 |
+
{
|
| 1873 |
+
"epoch": 1.6640000000000001,
|
| 1874 |
+
"eval_exact_match": 0.40816326530612246,
|
| 1875 |
+
"eval_f1_a": 0.7655502392344496,
|
| 1876 |
+
"eval_f1_m": 0.7372419530582798,
|
| 1877 |
+
"eval_loss": 0.4405694901943207,
|
| 1878 |
+
"eval_runtime": 12.3348,
|
| 1879 |
+
"eval_samples_per_second": 20.268,
|
| 1880 |
+
"eval_steps_per_second": 2.594,
|
| 1881 |
+
"step": 104
|
| 1882 |
+
},
|
| 1883 |
+
{
|
| 1884 |
+
"epoch": 1.6800000000000002,
|
| 1885 |
+
"grad_norm": 36.75,
|
| 1886 |
+
"learning_rate": 7.78688524590164e-06,
|
| 1887 |
+
"loss": 0.2891,
|
| 1888 |
+
"step": 105
|
| 1889 |
+
},
|
| 1890 |
+
{
|
| 1891 |
+
"epoch": 1.6800000000000002,
|
| 1892 |
+
"eval_exact_match": 0.42857142857142855,
|
| 1893 |
+
"eval_f1_a": 0.7766990291262137,
|
| 1894 |
+
"eval_f1_m": 0.743977677651147,
|
| 1895 |
+
"eval_loss": 0.43581634759902954,
|
| 1896 |
+
"eval_runtime": 12.3382,
|
| 1897 |
+
"eval_samples_per_second": 20.262,
|
| 1898 |
+
"eval_steps_per_second": 2.594,
|
| 1899 |
+
"step": 105
|
| 1900 |
+
},
|
| 1901 |
+
{
|
| 1902 |
+
"epoch": 1.696,
|
| 1903 |
+
"grad_norm": 14.1875,
|
| 1904 |
+
"learning_rate": 7.3770491803278695e-06,
|
| 1905 |
+
"loss": 0.3938,
|
| 1906 |
+
"step": 106
|
| 1907 |
+
},
|
| 1908 |
+
{
|
| 1909 |
+
"epoch": 1.696,
|
| 1910 |
+
"eval_exact_match": 0.42857142857142855,
|
| 1911 |
+
"eval_f1_a": 0.7804878048780488,
|
| 1912 |
+
"eval_f1_m": 0.7487395824130517,
|
| 1913 |
+
"eval_loss": 0.43115320801734924,
|
| 1914 |
+
"eval_runtime": 12.3282,
|
| 1915 |
+
"eval_samples_per_second": 20.279,
|
| 1916 |
+
"eval_steps_per_second": 2.596,
|
| 1917 |
+
"step": 106
|
| 1918 |
+
},
|
| 1919 |
+
{
|
| 1920 |
+
"epoch": 1.712,
|
| 1921 |
+
"grad_norm": 99.5,
|
| 1922 |
+
"learning_rate": 6.967213114754098e-06,
|
| 1923 |
+
"loss": 0.3288,
|
| 1924 |
+
"step": 107
|
| 1925 |
+
},
|
| 1926 |
+
{
|
| 1927 |
+
"epoch": 1.712,
|
| 1928 |
+
"eval_exact_match": 0.40816326530612246,
|
| 1929 |
+
"eval_f1_a": 0.7745098039215688,
|
| 1930 |
+
"eval_f1_m": 0.735134140236181,
|
| 1931 |
+
"eval_loss": 0.42852962017059326,
|
| 1932 |
+
"eval_runtime": 12.3363,
|
| 1933 |
+
"eval_samples_per_second": 20.265,
|
| 1934 |
+
"eval_steps_per_second": 2.594,
|
| 1935 |
+
"step": 107
|
| 1936 |
+
},
|
| 1937 |
+
{
|
| 1938 |
+
"epoch": 1.728,
|
| 1939 |
+
"grad_norm": 16.875,
|
| 1940 |
+
"learning_rate": 6.557377049180328e-06,
|
| 1941 |
+
"loss": 0.7464,
|
| 1942 |
+
"step": 108
|
| 1943 |
+
},
|
| 1944 |
+
{
|
| 1945 |
+
"epoch": 1.728,
|
| 1946 |
+
"eval_exact_match": 0.42857142857142855,
|
| 1947 |
+
"eval_f1_a": 0.7783251231527093,
|
| 1948 |
+
"eval_f1_m": 0.7419368613246163,
|
| 1949 |
+
"eval_loss": 0.42252594232559204,
|
| 1950 |
+
"eval_runtime": 12.3399,
|
| 1951 |
+
"eval_samples_per_second": 20.26,
|
| 1952 |
+
"eval_steps_per_second": 2.593,
|
| 1953 |
+
"step": 108
|
| 1954 |
+
},
|
| 1955 |
+
{
|
| 1956 |
+
"epoch": 1.744,
|
| 1957 |
+
"grad_norm": 45.5,
|
| 1958 |
+
"learning_rate": 6.147540983606558e-06,
|
| 1959 |
+
"loss": 0.4251,
|
| 1960 |
+
"step": 109
|
| 1961 |
+
},
|
| 1962 |
+
{
|
| 1963 |
+
"epoch": 1.744,
|
| 1964 |
+
"eval_exact_match": 0.42857142857142855,
|
| 1965 |
+
"eval_f1_a": 0.7783251231527093,
|
| 1966 |
+
"eval_f1_m": 0.7419368613246163,
|
| 1967 |
+
"eval_loss": 0.4160401225090027,
|
| 1968 |
+
"eval_runtime": 12.3384,
|
| 1969 |
+
"eval_samples_per_second": 20.262,
|
| 1970 |
+
"eval_steps_per_second": 2.594,
|
| 1971 |
+
"step": 109
|
| 1972 |
+
},
|
| 1973 |
+
{
|
| 1974 |
+
"epoch": 1.76,
|
| 1975 |
+
"grad_norm": 21.375,
|
| 1976 |
+
"learning_rate": 5.737704918032787e-06,
|
| 1977 |
+
"loss": 0.0894,
|
| 1978 |
+
"step": 110
|
| 1979 |
+
},
|
| 1980 |
+
{
|
| 1981 |
+
"epoch": 1.76,
|
| 1982 |
+
"eval_exact_match": 0.42857142857142855,
|
| 1983 |
+
"eval_f1_a": 0.7821782178217822,
|
| 1984 |
+
"eval_f1_m": 0.7470389021409428,
|
| 1985 |
+
"eval_loss": 0.4141208529472351,
|
| 1986 |
+
"eval_runtime": 12.4515,
|
| 1987 |
+
"eval_samples_per_second": 20.078,
|
| 1988 |
+
"eval_steps_per_second": 2.57,
|
| 1989 |
+
"step": 110
|
| 1990 |
+
},
|
| 1991 |
+
{
|
| 1992 |
+
"epoch": 1.776,
|
| 1993 |
+
"grad_norm": 2.796875,
|
| 1994 |
+
"learning_rate": 5.327868852459016e-06,
|
| 1995 |
+
"loss": 0.0424,
|
| 1996 |
+
"step": 111
|
| 1997 |
+
},
|
| 1998 |
+
{
|
| 1999 |
+
"epoch": 1.776,
|
| 2000 |
+
"eval_exact_match": 0.42857142857142855,
|
| 2001 |
+
"eval_f1_a": 0.7860696517412936,
|
| 2002 |
+
"eval_f1_m": 0.7480854746160868,
|
| 2003 |
+
"eval_loss": 0.41257748007774353,
|
| 2004 |
+
"eval_runtime": 12.242,
|
| 2005 |
+
"eval_samples_per_second": 20.422,
|
| 2006 |
+
"eval_steps_per_second": 2.614,
|
| 2007 |
+
"step": 111
|
| 2008 |
+
},
|
| 2009 |
+
{
|
| 2010 |
+
"epoch": 1.792,
|
| 2011 |
+
"grad_norm": 24.375,
|
| 2012 |
+
"learning_rate": 4.918032786885246e-06,
|
| 2013 |
+
"loss": 0.0746,
|
| 2014 |
+
"step": 112
|
| 2015 |
+
},
|
| 2016 |
+
{
|
| 2017 |
+
"epoch": 1.792,
|
| 2018 |
+
"eval_exact_match": 0.42857142857142855,
|
| 2019 |
+
"eval_f1_a": 0.7899999999999999,
|
| 2020 |
+
"eval_f1_m": 0.7509361386912407,
|
| 2021 |
+
"eval_loss": 0.41321831941604614,
|
| 2022 |
+
"eval_runtime": 12.3339,
|
| 2023 |
+
"eval_samples_per_second": 20.269,
|
| 2024 |
+
"eval_steps_per_second": 2.594,
|
| 2025 |
+
"step": 112
|
| 2026 |
+
},
|
| 2027 |
+
{
|
| 2028 |
+
"epoch": 1.808,
|
| 2029 |
+
"grad_norm": 23.5,
|
| 2030 |
+
"learning_rate": 4.508196721311476e-06,
|
| 2031 |
+
"loss": 0.1043,
|
| 2032 |
+
"step": 113
|
| 2033 |
+
},
|
| 2034 |
+
{
|
| 2035 |
+
"epoch": 1.808,
|
| 2036 |
+
"eval_exact_match": 0.42857142857142855,
|
| 2037 |
+
"eval_f1_a": 0.7899999999999999,
|
| 2038 |
+
"eval_f1_m": 0.7509361386912407,
|
| 2039 |
+
"eval_loss": 0.4108130633831024,
|
| 2040 |
+
"eval_runtime": 12.3269,
|
| 2041 |
+
"eval_samples_per_second": 20.281,
|
| 2042 |
+
"eval_steps_per_second": 2.596,
|
| 2043 |
+
"step": 113
|
| 2044 |
+
},
|
| 2045 |
+
{
|
| 2046 |
+
"epoch": 1.8239999999999998,
|
| 2047 |
+
"grad_norm": 94.0,
|
| 2048 |
+
"learning_rate": 4.098360655737704e-06,
|
| 2049 |
+
"loss": 0.3243,
|
| 2050 |
+
"step": 114
|
| 2051 |
+
},
|
| 2052 |
+
{
|
| 2053 |
+
"epoch": 1.8239999999999998,
|
| 2054 |
+
"eval_exact_match": 0.42857142857142855,
|
| 2055 |
+
"eval_f1_a": 0.7899999999999999,
|
| 2056 |
+
"eval_f1_m": 0.7509361386912407,
|
| 2057 |
+
"eval_loss": 0.4123730957508087,
|
| 2058 |
+
"eval_runtime": 12.4417,
|
| 2059 |
+
"eval_samples_per_second": 20.094,
|
| 2060 |
+
"eval_steps_per_second": 2.572,
|
| 2061 |
+
"step": 114
|
| 2062 |
+
},
|
| 2063 |
+
{
|
| 2064 |
+
"epoch": 1.8399999999999999,
|
| 2065 |
+
"grad_norm": 10.25,
|
| 2066 |
+
"learning_rate": 3.6885245901639347e-06,
|
| 2067 |
+
"loss": 0.1225,
|
| 2068 |
+
"step": 115
|
| 2069 |
+
},
|
| 2070 |
+
{
|
| 2071 |
+
"epoch": 1.8399999999999999,
|
| 2072 |
+
"eval_exact_match": 0.42857142857142855,
|
| 2073 |
+
"eval_f1_a": 0.7939698492462313,
|
| 2074 |
+
"eval_f1_m": 0.7594395400517849,
|
| 2075 |
+
"eval_loss": 0.4144425094127655,
|
| 2076 |
+
"eval_runtime": 12.4354,
|
| 2077 |
+
"eval_samples_per_second": 20.104,
|
| 2078 |
+
"eval_steps_per_second": 2.573,
|
| 2079 |
+
"step": 115
|
| 2080 |
+
},
|
| 2081 |
+
{
|
| 2082 |
+
"epoch": 1.8559999999999999,
|
| 2083 |
+
"grad_norm": 51.0,
|
| 2084 |
+
"learning_rate": 3.278688524590164e-06,
|
| 2085 |
+
"loss": 0.1299,
|
| 2086 |
+
"step": 116
|
| 2087 |
+
},
|
| 2088 |
+
{
|
| 2089 |
+
"epoch": 1.8559999999999999,
|
| 2090 |
+
"eval_exact_match": 0.40816326530612246,
|
| 2091 |
+
"eval_f1_a": 0.787878787878788,
|
| 2092 |
+
"eval_f1_m": 0.7573015419954194,
|
| 2093 |
+
"eval_loss": 0.41330641508102417,
|
| 2094 |
+
"eval_runtime": 12.3207,
|
| 2095 |
+
"eval_samples_per_second": 20.291,
|
| 2096 |
+
"eval_steps_per_second": 2.597,
|
| 2097 |
+
"step": 116
|
| 2098 |
+
},
|
| 2099 |
+
{
|
| 2100 |
+
"epoch": 1.8719999999999999,
|
| 2101 |
+
"grad_norm": 43.75,
|
| 2102 |
+
"learning_rate": 2.8688524590163937e-06,
|
| 2103 |
+
"loss": 0.1566,
|
| 2104 |
+
"step": 117
|
| 2105 |
+
},
|
| 2106 |
+
{
|
| 2107 |
+
"epoch": 1.8719999999999999,
|
| 2108 |
+
"eval_exact_match": 0.42857142857142855,
|
| 2109 |
+
"eval_f1_a": 0.7899999999999999,
|
| 2110 |
+
"eval_f1_m": 0.7509361386912407,
|
| 2111 |
+
"eval_loss": 0.4137237071990967,
|
| 2112 |
+
"eval_runtime": 12.3234,
|
| 2113 |
+
"eval_samples_per_second": 20.287,
|
| 2114 |
+
"eval_steps_per_second": 2.597,
|
| 2115 |
+
"step": 117
|
| 2116 |
+
},
|
| 2117 |
+
{
|
| 2118 |
+
"epoch": 1.888,
|
| 2119 |
+
"grad_norm": 17.125,
|
| 2120 |
+
"learning_rate": 2.459016393442623e-06,
|
| 2121 |
+
"loss": 0.2109,
|
| 2122 |
+
"step": 118
|
| 2123 |
+
},
|
| 2124 |
+
{
|
| 2125 |
+
"epoch": 1.888,
|
| 2126 |
+
"eval_exact_match": 0.42857142857142855,
|
| 2127 |
+
"eval_f1_a": 0.7899999999999999,
|
| 2128 |
+
"eval_f1_m": 0.7509361386912407,
|
| 2129 |
+
"eval_loss": 0.4149090349674225,
|
| 2130 |
+
"eval_runtime": 12.3269,
|
| 2131 |
+
"eval_samples_per_second": 20.281,
|
| 2132 |
+
"eval_steps_per_second": 2.596,
|
| 2133 |
+
"step": 118
|
| 2134 |
+
},
|
| 2135 |
+
{
|
| 2136 |
+
"epoch": 1.904,
|
| 2137 |
+
"grad_norm": 33.25,
|
| 2138 |
+
"learning_rate": 2.049180327868852e-06,
|
| 2139 |
+
"loss": 0.1705,
|
| 2140 |
+
"step": 119
|
| 2141 |
+
},
|
| 2142 |
+
{
|
| 2143 |
+
"epoch": 1.904,
|
| 2144 |
+
"eval_exact_match": 0.42857142857142855,
|
| 2145 |
+
"eval_f1_a": 0.7899999999999999,
|
| 2146 |
+
"eval_f1_m": 0.7509361386912407,
|
| 2147 |
+
"eval_loss": 0.4163377285003662,
|
| 2148 |
+
"eval_runtime": 12.3321,
|
| 2149 |
+
"eval_samples_per_second": 20.272,
|
| 2150 |
+
"eval_steps_per_second": 2.595,
|
| 2151 |
+
"step": 119
|
| 2152 |
+
},
|
| 2153 |
+
{
|
| 2154 |
+
"epoch": 1.92,
|
| 2155 |
+
"grad_norm": 34.25,
|
| 2156 |
+
"learning_rate": 1.639344262295082e-06,
|
| 2157 |
+
"loss": 0.4294,
|
| 2158 |
+
"step": 120
|
| 2159 |
+
},
|
| 2160 |
+
{
|
| 2161 |
+
"epoch": 1.92,
|
| 2162 |
+
"eval_exact_match": 0.42857142857142855,
|
| 2163 |
+
"eval_f1_a": 0.7899999999999999,
|
| 2164 |
+
"eval_f1_m": 0.7509361386912407,
|
| 2165 |
+
"eval_loss": 0.4143233895301819,
|
| 2166 |
+
"eval_runtime": 12.3236,
|
| 2167 |
+
"eval_samples_per_second": 20.286,
|
| 2168 |
+
"eval_steps_per_second": 2.597,
|
| 2169 |
+
"step": 120
|
| 2170 |
+
},
|
| 2171 |
+
{
|
| 2172 |
+
"epoch": 1.936,
|
| 2173 |
+
"grad_norm": 33.75,
|
| 2174 |
+
"learning_rate": 1.2295081967213116e-06,
|
| 2175 |
+
"loss": 0.1035,
|
| 2176 |
+
"step": 121
|
| 2177 |
+
},
|
| 2178 |
+
{
|
| 2179 |
+
"epoch": 1.936,
|
| 2180 |
+
"eval_exact_match": 0.42857142857142855,
|
| 2181 |
+
"eval_f1_a": 0.7860696517412936,
|
| 2182 |
+
"eval_f1_m": 0.7498895662160967,
|
| 2183 |
+
"eval_loss": 0.4134996831417084,
|
| 2184 |
+
"eval_runtime": 12.4257,
|
| 2185 |
+
"eval_samples_per_second": 20.12,
|
| 2186 |
+
"eval_steps_per_second": 2.575,
|
| 2187 |
+
"step": 121
|
| 2188 |
+
},
|
| 2189 |
+
{
|
| 2190 |
+
"epoch": 1.952,
|
| 2191 |
+
"grad_norm": 57.0,
|
| 2192 |
+
"learning_rate": 8.19672131147541e-07,
|
| 2193 |
+
"loss": 0.6236,
|
| 2194 |
+
"step": 122
|
| 2195 |
+
},
|
| 2196 |
+
{
|
| 2197 |
+
"epoch": 1.952,
|
| 2198 |
+
"eval_exact_match": 0.42857142857142855,
|
| 2199 |
+
"eval_f1_a": 0.7899999999999999,
|
| 2200 |
+
"eval_f1_m": 0.7509361386912407,
|
| 2201 |
+
"eval_loss": 0.41498681902885437,
|
| 2202 |
+
"eval_runtime": 12.3361,
|
| 2203 |
+
"eval_samples_per_second": 20.266,
|
| 2204 |
+
"eval_steps_per_second": 2.594,
|
| 2205 |
+
"step": 122
|
| 2206 |
+
},
|
| 2207 |
+
{
|
| 2208 |
+
"epoch": 1.968,
|
| 2209 |
+
"grad_norm": 27.25,
|
| 2210 |
+
"learning_rate": 4.098360655737705e-07,
|
| 2211 |
+
"loss": 0.2073,
|
| 2212 |
+
"step": 123
|
| 2213 |
+
},
|
| 2214 |
+
{
|
| 2215 |
+
"epoch": 1.968,
|
| 2216 |
+
"eval_exact_match": 0.42857142857142855,
|
| 2217 |
+
"eval_f1_a": 0.7899999999999999,
|
| 2218 |
+
"eval_f1_m": 0.7509361386912407,
|
| 2219 |
+
"eval_loss": 0.4136035144329071,
|
| 2220 |
+
"eval_runtime": 12.3383,
|
| 2221 |
+
"eval_samples_per_second": 20.262,
|
| 2222 |
+
"eval_steps_per_second": 2.594,
|
| 2223 |
+
"step": 123
|
| 2224 |
+
},
|
| 2225 |
+
{
|
| 2226 |
+
"epoch": 1.984,
|
| 2227 |
+
"grad_norm": 37.25,
|
| 2228 |
+
"learning_rate": 0.0,
|
| 2229 |
+
"loss": 0.1092,
|
| 2230 |
+
"step": 124
|
| 2231 |
+
},
|
| 2232 |
+
{
|
| 2233 |
+
"epoch": 1.984,
|
| 2234 |
+
"eval_exact_match": 0.42857142857142855,
|
| 2235 |
+
"eval_f1_a": 0.7860696517412936,
|
| 2236 |
+
"eval_f1_m": 0.7498895662160967,
|
| 2237 |
+
"eval_loss": 0.41635873913764954,
|
| 2238 |
+
"eval_runtime": 12.4351,
|
| 2239 |
+
"eval_samples_per_second": 20.104,
|
| 2240 |
+
"eval_steps_per_second": 2.573,
|
| 2241 |
+
"step": 124
|
| 2242 |
+
},
|
| 2243 |
+
{
|
| 2244 |
+
"epoch": 1.984,
|
| 2245 |
+
"step": 124,
|
| 2246 |
+
"total_flos": 4.424015634916966e+16,
|
| 2247 |
+
"train_loss": 0.5627710280879852,
|
| 2248 |
+
"train_runtime": 1868.9509,
|
| 2249 |
+
"train_samples_per_second": 1.07,
|
| 2250 |
+
"train_steps_per_second": 0.066
|
| 2251 |
+
}
|
| 2252 |
+
],
|
| 2253 |
+
"logging_steps": 1,
|
| 2254 |
+
"max_steps": 124,
|
| 2255 |
+
"num_input_tokens_seen": 0,
|
| 2256 |
+
"num_train_epochs": 2,
|
| 2257 |
+
"save_steps": 500,
|
| 2258 |
+
"stateful_callbacks": {
|
| 2259 |
+
"TrainerControl": {
|
| 2260 |
+
"args": {
|
| 2261 |
+
"should_epoch_stop": false,
|
| 2262 |
+
"should_evaluate": false,
|
| 2263 |
+
"should_log": false,
|
| 2264 |
+
"should_save": false,
|
| 2265 |
+
"should_training_stop": false
|
| 2266 |
+
},
|
| 2267 |
+
"attributes": {}
|
| 2268 |
+
}
|
| 2269 |
+
},
|
| 2270 |
+
"total_flos": 4.424015634916966e+16,
|
| 2271 |
+
"train_batch_size": 2,
|
| 2272 |
+
"trial_name": null,
|
| 2273 |
+
"trial_params": null
|
| 2274 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9f07f9b14f38c6973c6332f119b790315354076df0c7e7f94c4f95e77157b3f5
|
| 3 |
+
size 5176
|