Upload folder using huggingface_hub
Browse files- .gitattributes +1 -0
- README.md +202 -0
- adapter_config.json +34 -0
- adapter_model.safetensors +3 -0
- optimizer.pt +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +23 -0
- tokenizer.json +3 -0
- tokenizer_config.json +2064 -0
- trainer_state.json +2958 -0
- training_args.bin +3 -0
.gitattributes
CHANGED
|
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
README.md
ADDED
|
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: Bllossom/llama-3.2-Korean-Bllossom-3B
|
| 3 |
+
library_name: peft
|
| 4 |
+
---
|
| 5 |
+
|
| 6 |
+
# Model Card for Model ID
|
| 7 |
+
|
| 8 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
| 9 |
+
|
| 10 |
+
|
| 11 |
+
|
| 12 |
+
## Model Details
|
| 13 |
+
|
| 14 |
+
### Model Description
|
| 15 |
+
|
| 16 |
+
<!-- Provide a longer summary of what this model is. -->
|
| 17 |
+
|
| 18 |
+
|
| 19 |
+
|
| 20 |
+
- **Developed by:** [More Information Needed]
|
| 21 |
+
- **Funded by [optional]:** [More Information Needed]
|
| 22 |
+
- **Shared by [optional]:** [More Information Needed]
|
| 23 |
+
- **Model type:** [More Information Needed]
|
| 24 |
+
- **Language(s) (NLP):** [More Information Needed]
|
| 25 |
+
- **License:** [More Information Needed]
|
| 26 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
| 27 |
+
|
| 28 |
+
### Model Sources [optional]
|
| 29 |
+
|
| 30 |
+
<!-- Provide the basic links for the model. -->
|
| 31 |
+
|
| 32 |
+
- **Repository:** [More Information Needed]
|
| 33 |
+
- **Paper [optional]:** [More Information Needed]
|
| 34 |
+
- **Demo [optional]:** [More Information Needed]
|
| 35 |
+
|
| 36 |
+
## Uses
|
| 37 |
+
|
| 38 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
| 39 |
+
|
| 40 |
+
### Direct Use
|
| 41 |
+
|
| 42 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
| 43 |
+
|
| 44 |
+
[More Information Needed]
|
| 45 |
+
|
| 46 |
+
### Downstream Use [optional]
|
| 47 |
+
|
| 48 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
| 49 |
+
|
| 50 |
+
[More Information Needed]
|
| 51 |
+
|
| 52 |
+
### Out-of-Scope Use
|
| 53 |
+
|
| 54 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
| 55 |
+
|
| 56 |
+
[More Information Needed]
|
| 57 |
+
|
| 58 |
+
## Bias, Risks, and Limitations
|
| 59 |
+
|
| 60 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
| 61 |
+
|
| 62 |
+
[More Information Needed]
|
| 63 |
+
|
| 64 |
+
### Recommendations
|
| 65 |
+
|
| 66 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
| 67 |
+
|
| 68 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
| 69 |
+
|
| 70 |
+
## How to Get Started with the Model
|
| 71 |
+
|
| 72 |
+
Use the code below to get started with the model.
|
| 73 |
+
|
| 74 |
+
[More Information Needed]
|
| 75 |
+
|
| 76 |
+
## Training Details
|
| 77 |
+
|
| 78 |
+
### Training Data
|
| 79 |
+
|
| 80 |
+
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
| 81 |
+
|
| 82 |
+
[More Information Needed]
|
| 83 |
+
|
| 84 |
+
### Training Procedure
|
| 85 |
+
|
| 86 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
| 87 |
+
|
| 88 |
+
#### Preprocessing [optional]
|
| 89 |
+
|
| 90 |
+
[More Information Needed]
|
| 91 |
+
|
| 92 |
+
|
| 93 |
+
#### Training Hyperparameters
|
| 94 |
+
|
| 95 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
| 96 |
+
|
| 97 |
+
#### Speeds, Sizes, Times [optional]
|
| 98 |
+
|
| 99 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
| 100 |
+
|
| 101 |
+
[More Information Needed]
|
| 102 |
+
|
| 103 |
+
## Evaluation
|
| 104 |
+
|
| 105 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
| 106 |
+
|
| 107 |
+
### Testing Data, Factors & Metrics
|
| 108 |
+
|
| 109 |
+
#### Testing Data
|
| 110 |
+
|
| 111 |
+
<!-- This should link to a Dataset Card if possible. -->
|
| 112 |
+
|
| 113 |
+
[More Information Needed]
|
| 114 |
+
|
| 115 |
+
#### Factors
|
| 116 |
+
|
| 117 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
| 118 |
+
|
| 119 |
+
[More Information Needed]
|
| 120 |
+
|
| 121 |
+
#### Metrics
|
| 122 |
+
|
| 123 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
| 124 |
+
|
| 125 |
+
[More Information Needed]
|
| 126 |
+
|
| 127 |
+
### Results
|
| 128 |
+
|
| 129 |
+
[More Information Needed]
|
| 130 |
+
|
| 131 |
+
#### Summary
|
| 132 |
+
|
| 133 |
+
|
| 134 |
+
|
| 135 |
+
## Model Examination [optional]
|
| 136 |
+
|
| 137 |
+
<!-- Relevant interpretability work for the model goes here -->
|
| 138 |
+
|
| 139 |
+
[More Information Needed]
|
| 140 |
+
|
| 141 |
+
## Environmental Impact
|
| 142 |
+
|
| 143 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
| 144 |
+
|
| 145 |
+
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
| 146 |
+
|
| 147 |
+
- **Hardware Type:** [More Information Needed]
|
| 148 |
+
- **Hours used:** [More Information Needed]
|
| 149 |
+
- **Cloud Provider:** [More Information Needed]
|
| 150 |
+
- **Compute Region:** [More Information Needed]
|
| 151 |
+
- **Carbon Emitted:** [More Information Needed]
|
| 152 |
+
|
| 153 |
+
## Technical Specifications [optional]
|
| 154 |
+
|
| 155 |
+
### Model Architecture and Objective
|
| 156 |
+
|
| 157 |
+
[More Information Needed]
|
| 158 |
+
|
| 159 |
+
### Compute Infrastructure
|
| 160 |
+
|
| 161 |
+
[More Information Needed]
|
| 162 |
+
|
| 163 |
+
#### Hardware
|
| 164 |
+
|
| 165 |
+
[More Information Needed]
|
| 166 |
+
|
| 167 |
+
#### Software
|
| 168 |
+
|
| 169 |
+
[More Information Needed]
|
| 170 |
+
|
| 171 |
+
## Citation [optional]
|
| 172 |
+
|
| 173 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
| 174 |
+
|
| 175 |
+
**BibTeX:**
|
| 176 |
+
|
| 177 |
+
[More Information Needed]
|
| 178 |
+
|
| 179 |
+
**APA:**
|
| 180 |
+
|
| 181 |
+
[More Information Needed]
|
| 182 |
+
|
| 183 |
+
## Glossary [optional]
|
| 184 |
+
|
| 185 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
| 186 |
+
|
| 187 |
+
[More Information Needed]
|
| 188 |
+
|
| 189 |
+
## More Information [optional]
|
| 190 |
+
|
| 191 |
+
[More Information Needed]
|
| 192 |
+
|
| 193 |
+
## Model Card Authors [optional]
|
| 194 |
+
|
| 195 |
+
[More Information Needed]
|
| 196 |
+
|
| 197 |
+
## Model Card Contact
|
| 198 |
+
|
| 199 |
+
[More Information Needed]
|
| 200 |
+
### Framework versions
|
| 201 |
+
|
| 202 |
+
- PEFT 0.13.2
|
adapter_config.json
ADDED
|
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "Bllossom/llama-3.2-Korean-Bllossom-3B",
|
| 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": 0.01,
|
| 15 |
+
"megatron_config": null,
|
| 16 |
+
"megatron_core": "megatron.core",
|
| 17 |
+
"modules_to_save": null,
|
| 18 |
+
"peft_type": "LORA",
|
| 19 |
+
"r": 16,
|
| 20 |
+
"rank_pattern": {},
|
| 21 |
+
"revision": null,
|
| 22 |
+
"target_modules": [
|
| 23 |
+
"k_proj",
|
| 24 |
+
"down_proj",
|
| 25 |
+
"up_proj",
|
| 26 |
+
"o_proj",
|
| 27 |
+
"v_proj",
|
| 28 |
+
"q_proj",
|
| 29 |
+
"gate_proj"
|
| 30 |
+
],
|
| 31 |
+
"task_type": "CAUSAL_LM",
|
| 32 |
+
"use_dora": false,
|
| 33 |
+
"use_rslora": false
|
| 34 |
+
}
|
adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a5530238ac558c839f6e6c2ce0906251dcc88d9f30be93f894b89eabae9f3610
|
| 3 |
+
size 97307544
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:31420505e3828246029dd520394ac421c66fbe4c19fe17f4da2f0b6b3167fc82
|
| 3 |
+
size 50866370
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:32d74856addbb0f31519362aede5f27c41fcda8f1786140fea6b679deb55e2b6
|
| 3 |
+
size 14308
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3399402f4e824e5b414391ee6cb879da4b54c720a0413863c0a42d307961263a
|
| 3 |
+
size 1064
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<|begin_of_text|>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "<|eot_id|>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": {
|
| 17 |
+
"content": "<|finetune_right_pad_id|>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
}
|
| 23 |
+
}
|
tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
|
| 3 |
+
size 17209920
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,2064 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"128000": {
|
| 4 |
+
"content": "<|begin_of_text|>",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"128001": {
|
| 12 |
+
"content": "<|end_of_text|>",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"128002": {
|
| 20 |
+
"content": "<|reserved_special_token_0|>",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"128003": {
|
| 28 |
+
"content": "<|reserved_special_token_1|>",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"128004": {
|
| 36 |
+
"content": "<|finetune_right_pad_id|>",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
},
|
| 43 |
+
"128005": {
|
| 44 |
+
"content": "<|reserved_special_token_2|>",
|
| 45 |
+
"lstrip": false,
|
| 46 |
+
"normalized": false,
|
| 47 |
+
"rstrip": false,
|
| 48 |
+
"single_word": false,
|
| 49 |
+
"special": true
|
| 50 |
+
},
|
| 51 |
+
"128006": {
|
| 52 |
+
"content": "<|start_header_id|>",
|
| 53 |
+
"lstrip": false,
|
| 54 |
+
"normalized": false,
|
| 55 |
+
"rstrip": false,
|
| 56 |
+
"single_word": false,
|
| 57 |
+
"special": true
|
| 58 |
+
},
|
| 59 |
+
"128007": {
|
| 60 |
+
"content": "<|end_header_id|>",
|
| 61 |
+
"lstrip": false,
|
| 62 |
+
"normalized": false,
|
| 63 |
+
"rstrip": false,
|
| 64 |
+
"single_word": false,
|
| 65 |
+
"special": true
|
| 66 |
+
},
|
| 67 |
+
"128008": {
|
| 68 |
+
"content": "<|eom_id|>",
|
| 69 |
+
"lstrip": false,
|
| 70 |
+
"normalized": false,
|
| 71 |
+
"rstrip": false,
|
| 72 |
+
"single_word": false,
|
| 73 |
+
"special": true
|
| 74 |
+
},
|
| 75 |
+
"128009": {
|
| 76 |
+
"content": "<|eot_id|>",
|
| 77 |
+
"lstrip": false,
|
| 78 |
+
"normalized": false,
|
| 79 |
+
"rstrip": false,
|
| 80 |
+
"single_word": false,
|
| 81 |
+
"special": true
|
| 82 |
+
},
|
| 83 |
+
"128010": {
|
| 84 |
+
"content": "<|python_tag|>",
|
| 85 |
+
"lstrip": false,
|
| 86 |
+
"normalized": false,
|
| 87 |
+
"rstrip": false,
|
| 88 |
+
"single_word": false,
|
| 89 |
+
"special": true
|
| 90 |
+
},
|
| 91 |
+
"128011": {
|
| 92 |
+
"content": "<|reserved_special_token_3|>",
|
| 93 |
+
"lstrip": false,
|
| 94 |
+
"normalized": false,
|
| 95 |
+
"rstrip": false,
|
| 96 |
+
"single_word": false,
|
| 97 |
+
"special": true
|
| 98 |
+
},
|
| 99 |
+
"128012": {
|
| 100 |
+
"content": "<|reserved_special_token_4|>",
|
| 101 |
+
"lstrip": false,
|
| 102 |
+
"normalized": false,
|
| 103 |
+
"rstrip": false,
|
| 104 |
+
"single_word": false,
|
| 105 |
+
"special": true
|
| 106 |
+
},
|
| 107 |
+
"128013": {
|
| 108 |
+
"content": "<|reserved_special_token_5|>",
|
| 109 |
+
"lstrip": false,
|
| 110 |
+
"normalized": false,
|
| 111 |
+
"rstrip": false,
|
| 112 |
+
"single_word": false,
|
| 113 |
+
"special": true
|
| 114 |
+
},
|
| 115 |
+
"128014": {
|
| 116 |
+
"content": "<|reserved_special_token_6|>",
|
| 117 |
+
"lstrip": false,
|
| 118 |
+
"normalized": false,
|
| 119 |
+
"rstrip": false,
|
| 120 |
+
"single_word": false,
|
| 121 |
+
"special": true
|
| 122 |
+
},
|
| 123 |
+
"128015": {
|
| 124 |
+
"content": "<|reserved_special_token_7|>",
|
| 125 |
+
"lstrip": false,
|
| 126 |
+
"normalized": false,
|
| 127 |
+
"rstrip": false,
|
| 128 |
+
"single_word": false,
|
| 129 |
+
"special": true
|
| 130 |
+
},
|
| 131 |
+
"128016": {
|
| 132 |
+
"content": "<|reserved_special_token_8|>",
|
| 133 |
+
"lstrip": false,
|
| 134 |
+
"normalized": false,
|
| 135 |
+
"rstrip": false,
|
| 136 |
+
"single_word": false,
|
| 137 |
+
"special": true
|
| 138 |
+
},
|
| 139 |
+
"128017": {
|
| 140 |
+
"content": "<|reserved_special_token_9|>",
|
| 141 |
+
"lstrip": false,
|
| 142 |
+
"normalized": false,
|
| 143 |
+
"rstrip": false,
|
| 144 |
+
"single_word": false,
|
| 145 |
+
"special": true
|
| 146 |
+
},
|
| 147 |
+
"128018": {
|
| 148 |
+
"content": "<|reserved_special_token_10|>",
|
| 149 |
+
"lstrip": false,
|
| 150 |
+
"normalized": false,
|
| 151 |
+
"rstrip": false,
|
| 152 |
+
"single_word": false,
|
| 153 |
+
"special": true
|
| 154 |
+
},
|
| 155 |
+
"128019": {
|
| 156 |
+
"content": "<|reserved_special_token_11|>",
|
| 157 |
+
"lstrip": false,
|
| 158 |
+
"normalized": false,
|
| 159 |
+
"rstrip": false,
|
| 160 |
+
"single_word": false,
|
| 161 |
+
"special": true
|
| 162 |
+
},
|
| 163 |
+
"128020": {
|
| 164 |
+
"content": "<|reserved_special_token_12|>",
|
| 165 |
+
"lstrip": false,
|
| 166 |
+
"normalized": false,
|
| 167 |
+
"rstrip": false,
|
| 168 |
+
"single_word": false,
|
| 169 |
+
"special": true
|
| 170 |
+
},
|
| 171 |
+
"128021": {
|
| 172 |
+
"content": "<|reserved_special_token_13|>",
|
| 173 |
+
"lstrip": false,
|
| 174 |
+
"normalized": false,
|
| 175 |
+
"rstrip": false,
|
| 176 |
+
"single_word": false,
|
| 177 |
+
"special": true
|
| 178 |
+
},
|
| 179 |
+
"128022": {
|
| 180 |
+
"content": "<|reserved_special_token_14|>",
|
| 181 |
+
"lstrip": false,
|
| 182 |
+
"normalized": false,
|
| 183 |
+
"rstrip": false,
|
| 184 |
+
"single_word": false,
|
| 185 |
+
"special": true
|
| 186 |
+
},
|
| 187 |
+
"128023": {
|
| 188 |
+
"content": "<|reserved_special_token_15|>",
|
| 189 |
+
"lstrip": false,
|
| 190 |
+
"normalized": false,
|
| 191 |
+
"rstrip": false,
|
| 192 |
+
"single_word": false,
|
| 193 |
+
"special": true
|
| 194 |
+
},
|
| 195 |
+
"128024": {
|
| 196 |
+
"content": "<|reserved_special_token_16|>",
|
| 197 |
+
"lstrip": false,
|
| 198 |
+
"normalized": false,
|
| 199 |
+
"rstrip": false,
|
| 200 |
+
"single_word": false,
|
| 201 |
+
"special": true
|
| 202 |
+
},
|
| 203 |
+
"128025": {
|
| 204 |
+
"content": "<|reserved_special_token_17|>",
|
| 205 |
+
"lstrip": false,
|
| 206 |
+
"normalized": false,
|
| 207 |
+
"rstrip": false,
|
| 208 |
+
"single_word": false,
|
| 209 |
+
"special": true
|
| 210 |
+
},
|
| 211 |
+
"128026": {
|
| 212 |
+
"content": "<|reserved_special_token_18|>",
|
| 213 |
+
"lstrip": false,
|
| 214 |
+
"normalized": false,
|
| 215 |
+
"rstrip": false,
|
| 216 |
+
"single_word": false,
|
| 217 |
+
"special": true
|
| 218 |
+
},
|
| 219 |
+
"128027": {
|
| 220 |
+
"content": "<|reserved_special_token_19|>",
|
| 221 |
+
"lstrip": false,
|
| 222 |
+
"normalized": false,
|
| 223 |
+
"rstrip": false,
|
| 224 |
+
"single_word": false,
|
| 225 |
+
"special": true
|
| 226 |
+
},
|
| 227 |
+
"128028": {
|
| 228 |
+
"content": "<|reserved_special_token_20|>",
|
| 229 |
+
"lstrip": false,
|
| 230 |
+
"normalized": false,
|
| 231 |
+
"rstrip": false,
|
| 232 |
+
"single_word": false,
|
| 233 |
+
"special": true
|
| 234 |
+
},
|
| 235 |
+
"128029": {
|
| 236 |
+
"content": "<|reserved_special_token_21|>",
|
| 237 |
+
"lstrip": false,
|
| 238 |
+
"normalized": false,
|
| 239 |
+
"rstrip": false,
|
| 240 |
+
"single_word": false,
|
| 241 |
+
"special": true
|
| 242 |
+
},
|
| 243 |
+
"128030": {
|
| 244 |
+
"content": "<|reserved_special_token_22|>",
|
| 245 |
+
"lstrip": false,
|
| 246 |
+
"normalized": false,
|
| 247 |
+
"rstrip": false,
|
| 248 |
+
"single_word": false,
|
| 249 |
+
"special": true
|
| 250 |
+
},
|
| 251 |
+
"128031": {
|
| 252 |
+
"content": "<|reserved_special_token_23|>",
|
| 253 |
+
"lstrip": false,
|
| 254 |
+
"normalized": false,
|
| 255 |
+
"rstrip": false,
|
| 256 |
+
"single_word": false,
|
| 257 |
+
"special": true
|
| 258 |
+
},
|
| 259 |
+
"128032": {
|
| 260 |
+
"content": "<|reserved_special_token_24|>",
|
| 261 |
+
"lstrip": false,
|
| 262 |
+
"normalized": false,
|
| 263 |
+
"rstrip": false,
|
| 264 |
+
"single_word": false,
|
| 265 |
+
"special": true
|
| 266 |
+
},
|
| 267 |
+
"128033": {
|
| 268 |
+
"content": "<|reserved_special_token_25|>",
|
| 269 |
+
"lstrip": false,
|
| 270 |
+
"normalized": false,
|
| 271 |
+
"rstrip": false,
|
| 272 |
+
"single_word": false,
|
| 273 |
+
"special": true
|
| 274 |
+
},
|
| 275 |
+
"128034": {
|
| 276 |
+
"content": "<|reserved_special_token_26|>",
|
| 277 |
+
"lstrip": false,
|
| 278 |
+
"normalized": false,
|
| 279 |
+
"rstrip": false,
|
| 280 |
+
"single_word": false,
|
| 281 |
+
"special": true
|
| 282 |
+
},
|
| 283 |
+
"128035": {
|
| 284 |
+
"content": "<|reserved_special_token_27|>",
|
| 285 |
+
"lstrip": false,
|
| 286 |
+
"normalized": false,
|
| 287 |
+
"rstrip": false,
|
| 288 |
+
"single_word": false,
|
| 289 |
+
"special": true
|
| 290 |
+
},
|
| 291 |
+
"128036": {
|
| 292 |
+
"content": "<|reserved_special_token_28|>",
|
| 293 |
+
"lstrip": false,
|
| 294 |
+
"normalized": false,
|
| 295 |
+
"rstrip": false,
|
| 296 |
+
"single_word": false,
|
| 297 |
+
"special": true
|
| 298 |
+
},
|
| 299 |
+
"128037": {
|
| 300 |
+
"content": "<|reserved_special_token_29|>",
|
| 301 |
+
"lstrip": false,
|
| 302 |
+
"normalized": false,
|
| 303 |
+
"rstrip": false,
|
| 304 |
+
"single_word": false,
|
| 305 |
+
"special": true
|
| 306 |
+
},
|
| 307 |
+
"128038": {
|
| 308 |
+
"content": "<|reserved_special_token_30|>",
|
| 309 |
+
"lstrip": false,
|
| 310 |
+
"normalized": false,
|
| 311 |
+
"rstrip": false,
|
| 312 |
+
"single_word": false,
|
| 313 |
+
"special": true
|
| 314 |
+
},
|
| 315 |
+
"128039": {
|
| 316 |
+
"content": "<|reserved_special_token_31|>",
|
| 317 |
+
"lstrip": false,
|
| 318 |
+
"normalized": false,
|
| 319 |
+
"rstrip": false,
|
| 320 |
+
"single_word": false,
|
| 321 |
+
"special": true
|
| 322 |
+
},
|
| 323 |
+
"128040": {
|
| 324 |
+
"content": "<|reserved_special_token_32|>",
|
| 325 |
+
"lstrip": false,
|
| 326 |
+
"normalized": false,
|
| 327 |
+
"rstrip": false,
|
| 328 |
+
"single_word": false,
|
| 329 |
+
"special": true
|
| 330 |
+
},
|
| 331 |
+
"128041": {
|
| 332 |
+
"content": "<|reserved_special_token_33|>",
|
| 333 |
+
"lstrip": false,
|
| 334 |
+
"normalized": false,
|
| 335 |
+
"rstrip": false,
|
| 336 |
+
"single_word": false,
|
| 337 |
+
"special": true
|
| 338 |
+
},
|
| 339 |
+
"128042": {
|
| 340 |
+
"content": "<|reserved_special_token_34|>",
|
| 341 |
+
"lstrip": false,
|
| 342 |
+
"normalized": false,
|
| 343 |
+
"rstrip": false,
|
| 344 |
+
"single_word": false,
|
| 345 |
+
"special": true
|
| 346 |
+
},
|
| 347 |
+
"128043": {
|
| 348 |
+
"content": "<|reserved_special_token_35|>",
|
| 349 |
+
"lstrip": false,
|
| 350 |
+
"normalized": false,
|
| 351 |
+
"rstrip": false,
|
| 352 |
+
"single_word": false,
|
| 353 |
+
"special": true
|
| 354 |
+
},
|
| 355 |
+
"128044": {
|
| 356 |
+
"content": "<|reserved_special_token_36|>",
|
| 357 |
+
"lstrip": false,
|
| 358 |
+
"normalized": false,
|
| 359 |
+
"rstrip": false,
|
| 360 |
+
"single_word": false,
|
| 361 |
+
"special": true
|
| 362 |
+
},
|
| 363 |
+
"128045": {
|
| 364 |
+
"content": "<|reserved_special_token_37|>",
|
| 365 |
+
"lstrip": false,
|
| 366 |
+
"normalized": false,
|
| 367 |
+
"rstrip": false,
|
| 368 |
+
"single_word": false,
|
| 369 |
+
"special": true
|
| 370 |
+
},
|
| 371 |
+
"128046": {
|
| 372 |
+
"content": "<|reserved_special_token_38|>",
|
| 373 |
+
"lstrip": false,
|
| 374 |
+
"normalized": false,
|
| 375 |
+
"rstrip": false,
|
| 376 |
+
"single_word": false,
|
| 377 |
+
"special": true
|
| 378 |
+
},
|
| 379 |
+
"128047": {
|
| 380 |
+
"content": "<|reserved_special_token_39|>",
|
| 381 |
+
"lstrip": false,
|
| 382 |
+
"normalized": false,
|
| 383 |
+
"rstrip": false,
|
| 384 |
+
"single_word": false,
|
| 385 |
+
"special": true
|
| 386 |
+
},
|
| 387 |
+
"128048": {
|
| 388 |
+
"content": "<|reserved_special_token_40|>",
|
| 389 |
+
"lstrip": false,
|
| 390 |
+
"normalized": false,
|
| 391 |
+
"rstrip": false,
|
| 392 |
+
"single_word": false,
|
| 393 |
+
"special": true
|
| 394 |
+
},
|
| 395 |
+
"128049": {
|
| 396 |
+
"content": "<|reserved_special_token_41|>",
|
| 397 |
+
"lstrip": false,
|
| 398 |
+
"normalized": false,
|
| 399 |
+
"rstrip": false,
|
| 400 |
+
"single_word": false,
|
| 401 |
+
"special": true
|
| 402 |
+
},
|
| 403 |
+
"128050": {
|
| 404 |
+
"content": "<|reserved_special_token_42|>",
|
| 405 |
+
"lstrip": false,
|
| 406 |
+
"normalized": false,
|
| 407 |
+
"rstrip": false,
|
| 408 |
+
"single_word": false,
|
| 409 |
+
"special": true
|
| 410 |
+
},
|
| 411 |
+
"128051": {
|
| 412 |
+
"content": "<|reserved_special_token_43|>",
|
| 413 |
+
"lstrip": false,
|
| 414 |
+
"normalized": false,
|
| 415 |
+
"rstrip": false,
|
| 416 |
+
"single_word": false,
|
| 417 |
+
"special": true
|
| 418 |
+
},
|
| 419 |
+
"128052": {
|
| 420 |
+
"content": "<|reserved_special_token_44|>",
|
| 421 |
+
"lstrip": false,
|
| 422 |
+
"normalized": false,
|
| 423 |
+
"rstrip": false,
|
| 424 |
+
"single_word": false,
|
| 425 |
+
"special": true
|
| 426 |
+
},
|
| 427 |
+
"128053": {
|
| 428 |
+
"content": "<|reserved_special_token_45|>",
|
| 429 |
+
"lstrip": false,
|
| 430 |
+
"normalized": false,
|
| 431 |
+
"rstrip": false,
|
| 432 |
+
"single_word": false,
|
| 433 |
+
"special": true
|
| 434 |
+
},
|
| 435 |
+
"128054": {
|
| 436 |
+
"content": "<|reserved_special_token_46|>",
|
| 437 |
+
"lstrip": false,
|
| 438 |
+
"normalized": false,
|
| 439 |
+
"rstrip": false,
|
| 440 |
+
"single_word": false,
|
| 441 |
+
"special": true
|
| 442 |
+
},
|
| 443 |
+
"128055": {
|
| 444 |
+
"content": "<|reserved_special_token_47|>",
|
| 445 |
+
"lstrip": false,
|
| 446 |
+
"normalized": false,
|
| 447 |
+
"rstrip": false,
|
| 448 |
+
"single_word": false,
|
| 449 |
+
"special": true
|
| 450 |
+
},
|
| 451 |
+
"128056": {
|
| 452 |
+
"content": "<|reserved_special_token_48|>",
|
| 453 |
+
"lstrip": false,
|
| 454 |
+
"normalized": false,
|
| 455 |
+
"rstrip": false,
|
| 456 |
+
"single_word": false,
|
| 457 |
+
"special": true
|
| 458 |
+
},
|
| 459 |
+
"128057": {
|
| 460 |
+
"content": "<|reserved_special_token_49|>",
|
| 461 |
+
"lstrip": false,
|
| 462 |
+
"normalized": false,
|
| 463 |
+
"rstrip": false,
|
| 464 |
+
"single_word": false,
|
| 465 |
+
"special": true
|
| 466 |
+
},
|
| 467 |
+
"128058": {
|
| 468 |
+
"content": "<|reserved_special_token_50|>",
|
| 469 |
+
"lstrip": false,
|
| 470 |
+
"normalized": false,
|
| 471 |
+
"rstrip": false,
|
| 472 |
+
"single_word": false,
|
| 473 |
+
"special": true
|
| 474 |
+
},
|
| 475 |
+
"128059": {
|
| 476 |
+
"content": "<|reserved_special_token_51|>",
|
| 477 |
+
"lstrip": false,
|
| 478 |
+
"normalized": false,
|
| 479 |
+
"rstrip": false,
|
| 480 |
+
"single_word": false,
|
| 481 |
+
"special": true
|
| 482 |
+
},
|
| 483 |
+
"128060": {
|
| 484 |
+
"content": "<|reserved_special_token_52|>",
|
| 485 |
+
"lstrip": false,
|
| 486 |
+
"normalized": false,
|
| 487 |
+
"rstrip": false,
|
| 488 |
+
"single_word": false,
|
| 489 |
+
"special": true
|
| 490 |
+
},
|
| 491 |
+
"128061": {
|
| 492 |
+
"content": "<|reserved_special_token_53|>",
|
| 493 |
+
"lstrip": false,
|
| 494 |
+
"normalized": false,
|
| 495 |
+
"rstrip": false,
|
| 496 |
+
"single_word": false,
|
| 497 |
+
"special": true
|
| 498 |
+
},
|
| 499 |
+
"128062": {
|
| 500 |
+
"content": "<|reserved_special_token_54|>",
|
| 501 |
+
"lstrip": false,
|
| 502 |
+
"normalized": false,
|
| 503 |
+
"rstrip": false,
|
| 504 |
+
"single_word": false,
|
| 505 |
+
"special": true
|
| 506 |
+
},
|
| 507 |
+
"128063": {
|
| 508 |
+
"content": "<|reserved_special_token_55|>",
|
| 509 |
+
"lstrip": false,
|
| 510 |
+
"normalized": false,
|
| 511 |
+
"rstrip": false,
|
| 512 |
+
"single_word": false,
|
| 513 |
+
"special": true
|
| 514 |
+
},
|
| 515 |
+
"128064": {
|
| 516 |
+
"content": "<|reserved_special_token_56|>",
|
| 517 |
+
"lstrip": false,
|
| 518 |
+
"normalized": false,
|
| 519 |
+
"rstrip": false,
|
| 520 |
+
"single_word": false,
|
| 521 |
+
"special": true
|
| 522 |
+
},
|
| 523 |
+
"128065": {
|
| 524 |
+
"content": "<|reserved_special_token_57|>",
|
| 525 |
+
"lstrip": false,
|
| 526 |
+
"normalized": false,
|
| 527 |
+
"rstrip": false,
|
| 528 |
+
"single_word": false,
|
| 529 |
+
"special": true
|
| 530 |
+
},
|
| 531 |
+
"128066": {
|
| 532 |
+
"content": "<|reserved_special_token_58|>",
|
| 533 |
+
"lstrip": false,
|
| 534 |
+
"normalized": false,
|
| 535 |
+
"rstrip": false,
|
| 536 |
+
"single_word": false,
|
| 537 |
+
"special": true
|
| 538 |
+
},
|
| 539 |
+
"128067": {
|
| 540 |
+
"content": "<|reserved_special_token_59|>",
|
| 541 |
+
"lstrip": false,
|
| 542 |
+
"normalized": false,
|
| 543 |
+
"rstrip": false,
|
| 544 |
+
"single_word": false,
|
| 545 |
+
"special": true
|
| 546 |
+
},
|
| 547 |
+
"128068": {
|
| 548 |
+
"content": "<|reserved_special_token_60|>",
|
| 549 |
+
"lstrip": false,
|
| 550 |
+
"normalized": false,
|
| 551 |
+
"rstrip": false,
|
| 552 |
+
"single_word": false,
|
| 553 |
+
"special": true
|
| 554 |
+
},
|
| 555 |
+
"128069": {
|
| 556 |
+
"content": "<|reserved_special_token_61|>",
|
| 557 |
+
"lstrip": false,
|
| 558 |
+
"normalized": false,
|
| 559 |
+
"rstrip": false,
|
| 560 |
+
"single_word": false,
|
| 561 |
+
"special": true
|
| 562 |
+
},
|
| 563 |
+
"128070": {
|
| 564 |
+
"content": "<|reserved_special_token_62|>",
|
| 565 |
+
"lstrip": false,
|
| 566 |
+
"normalized": false,
|
| 567 |
+
"rstrip": false,
|
| 568 |
+
"single_word": false,
|
| 569 |
+
"special": true
|
| 570 |
+
},
|
| 571 |
+
"128071": {
|
| 572 |
+
"content": "<|reserved_special_token_63|>",
|
| 573 |
+
"lstrip": false,
|
| 574 |
+
"normalized": false,
|
| 575 |
+
"rstrip": false,
|
| 576 |
+
"single_word": false,
|
| 577 |
+
"special": true
|
| 578 |
+
},
|
| 579 |
+
"128072": {
|
| 580 |
+
"content": "<|reserved_special_token_64|>",
|
| 581 |
+
"lstrip": false,
|
| 582 |
+
"normalized": false,
|
| 583 |
+
"rstrip": false,
|
| 584 |
+
"single_word": false,
|
| 585 |
+
"special": true
|
| 586 |
+
},
|
| 587 |
+
"128073": {
|
| 588 |
+
"content": "<|reserved_special_token_65|>",
|
| 589 |
+
"lstrip": false,
|
| 590 |
+
"normalized": false,
|
| 591 |
+
"rstrip": false,
|
| 592 |
+
"single_word": false,
|
| 593 |
+
"special": true
|
| 594 |
+
},
|
| 595 |
+
"128074": {
|
| 596 |
+
"content": "<|reserved_special_token_66|>",
|
| 597 |
+
"lstrip": false,
|
| 598 |
+
"normalized": false,
|
| 599 |
+
"rstrip": false,
|
| 600 |
+
"single_word": false,
|
| 601 |
+
"special": true
|
| 602 |
+
},
|
| 603 |
+
"128075": {
|
| 604 |
+
"content": "<|reserved_special_token_67|>",
|
| 605 |
+
"lstrip": false,
|
| 606 |
+
"normalized": false,
|
| 607 |
+
"rstrip": false,
|
| 608 |
+
"single_word": false,
|
| 609 |
+
"special": true
|
| 610 |
+
},
|
| 611 |
+
"128076": {
|
| 612 |
+
"content": "<|reserved_special_token_68|>",
|
| 613 |
+
"lstrip": false,
|
| 614 |
+
"normalized": false,
|
| 615 |
+
"rstrip": false,
|
| 616 |
+
"single_word": false,
|
| 617 |
+
"special": true
|
| 618 |
+
},
|
| 619 |
+
"128077": {
|
| 620 |
+
"content": "<|reserved_special_token_69|>",
|
| 621 |
+
"lstrip": false,
|
| 622 |
+
"normalized": false,
|
| 623 |
+
"rstrip": false,
|
| 624 |
+
"single_word": false,
|
| 625 |
+
"special": true
|
| 626 |
+
},
|
| 627 |
+
"128078": {
|
| 628 |
+
"content": "<|reserved_special_token_70|>",
|
| 629 |
+
"lstrip": false,
|
| 630 |
+
"normalized": false,
|
| 631 |
+
"rstrip": false,
|
| 632 |
+
"single_word": false,
|
| 633 |
+
"special": true
|
| 634 |
+
},
|
| 635 |
+
"128079": {
|
| 636 |
+
"content": "<|reserved_special_token_71|>",
|
| 637 |
+
"lstrip": false,
|
| 638 |
+
"normalized": false,
|
| 639 |
+
"rstrip": false,
|
| 640 |
+
"single_word": false,
|
| 641 |
+
"special": true
|
| 642 |
+
},
|
| 643 |
+
"128080": {
|
| 644 |
+
"content": "<|reserved_special_token_72|>",
|
| 645 |
+
"lstrip": false,
|
| 646 |
+
"normalized": false,
|
| 647 |
+
"rstrip": false,
|
| 648 |
+
"single_word": false,
|
| 649 |
+
"special": true
|
| 650 |
+
},
|
| 651 |
+
"128081": {
|
| 652 |
+
"content": "<|reserved_special_token_73|>",
|
| 653 |
+
"lstrip": false,
|
| 654 |
+
"normalized": false,
|
| 655 |
+
"rstrip": false,
|
| 656 |
+
"single_word": false,
|
| 657 |
+
"special": true
|
| 658 |
+
},
|
| 659 |
+
"128082": {
|
| 660 |
+
"content": "<|reserved_special_token_74|>",
|
| 661 |
+
"lstrip": false,
|
| 662 |
+
"normalized": false,
|
| 663 |
+
"rstrip": false,
|
| 664 |
+
"single_word": false,
|
| 665 |
+
"special": true
|
| 666 |
+
},
|
| 667 |
+
"128083": {
|
| 668 |
+
"content": "<|reserved_special_token_75|>",
|
| 669 |
+
"lstrip": false,
|
| 670 |
+
"normalized": false,
|
| 671 |
+
"rstrip": false,
|
| 672 |
+
"single_word": false,
|
| 673 |
+
"special": true
|
| 674 |
+
},
|
| 675 |
+
"128084": {
|
| 676 |
+
"content": "<|reserved_special_token_76|>",
|
| 677 |
+
"lstrip": false,
|
| 678 |
+
"normalized": false,
|
| 679 |
+
"rstrip": false,
|
| 680 |
+
"single_word": false,
|
| 681 |
+
"special": true
|
| 682 |
+
},
|
| 683 |
+
"128085": {
|
| 684 |
+
"content": "<|reserved_special_token_77|>",
|
| 685 |
+
"lstrip": false,
|
| 686 |
+
"normalized": false,
|
| 687 |
+
"rstrip": false,
|
| 688 |
+
"single_word": false,
|
| 689 |
+
"special": true
|
| 690 |
+
},
|
| 691 |
+
"128086": {
|
| 692 |
+
"content": "<|reserved_special_token_78|>",
|
| 693 |
+
"lstrip": false,
|
| 694 |
+
"normalized": false,
|
| 695 |
+
"rstrip": false,
|
| 696 |
+
"single_word": false,
|
| 697 |
+
"special": true
|
| 698 |
+
},
|
| 699 |
+
"128087": {
|
| 700 |
+
"content": "<|reserved_special_token_79|>",
|
| 701 |
+
"lstrip": false,
|
| 702 |
+
"normalized": false,
|
| 703 |
+
"rstrip": false,
|
| 704 |
+
"single_word": false,
|
| 705 |
+
"special": true
|
| 706 |
+
},
|
| 707 |
+
"128088": {
|
| 708 |
+
"content": "<|reserved_special_token_80|>",
|
| 709 |
+
"lstrip": false,
|
| 710 |
+
"normalized": false,
|
| 711 |
+
"rstrip": false,
|
| 712 |
+
"single_word": false,
|
| 713 |
+
"special": true
|
| 714 |
+
},
|
| 715 |
+
"128089": {
|
| 716 |
+
"content": "<|reserved_special_token_81|>",
|
| 717 |
+
"lstrip": false,
|
| 718 |
+
"normalized": false,
|
| 719 |
+
"rstrip": false,
|
| 720 |
+
"single_word": false,
|
| 721 |
+
"special": true
|
| 722 |
+
},
|
| 723 |
+
"128090": {
|
| 724 |
+
"content": "<|reserved_special_token_82|>",
|
| 725 |
+
"lstrip": false,
|
| 726 |
+
"normalized": false,
|
| 727 |
+
"rstrip": false,
|
| 728 |
+
"single_word": false,
|
| 729 |
+
"special": true
|
| 730 |
+
},
|
| 731 |
+
"128091": {
|
| 732 |
+
"content": "<|reserved_special_token_83|>",
|
| 733 |
+
"lstrip": false,
|
| 734 |
+
"normalized": false,
|
| 735 |
+
"rstrip": false,
|
| 736 |
+
"single_word": false,
|
| 737 |
+
"special": true
|
| 738 |
+
},
|
| 739 |
+
"128092": {
|
| 740 |
+
"content": "<|reserved_special_token_84|>",
|
| 741 |
+
"lstrip": false,
|
| 742 |
+
"normalized": false,
|
| 743 |
+
"rstrip": false,
|
| 744 |
+
"single_word": false,
|
| 745 |
+
"special": true
|
| 746 |
+
},
|
| 747 |
+
"128093": {
|
| 748 |
+
"content": "<|reserved_special_token_85|>",
|
| 749 |
+
"lstrip": false,
|
| 750 |
+
"normalized": false,
|
| 751 |
+
"rstrip": false,
|
| 752 |
+
"single_word": false,
|
| 753 |
+
"special": true
|
| 754 |
+
},
|
| 755 |
+
"128094": {
|
| 756 |
+
"content": "<|reserved_special_token_86|>",
|
| 757 |
+
"lstrip": false,
|
| 758 |
+
"normalized": false,
|
| 759 |
+
"rstrip": false,
|
| 760 |
+
"single_word": false,
|
| 761 |
+
"special": true
|
| 762 |
+
},
|
| 763 |
+
"128095": {
|
| 764 |
+
"content": "<|reserved_special_token_87|>",
|
| 765 |
+
"lstrip": false,
|
| 766 |
+
"normalized": false,
|
| 767 |
+
"rstrip": false,
|
| 768 |
+
"single_word": false,
|
| 769 |
+
"special": true
|
| 770 |
+
},
|
| 771 |
+
"128096": {
|
| 772 |
+
"content": "<|reserved_special_token_88|>",
|
| 773 |
+
"lstrip": false,
|
| 774 |
+
"normalized": false,
|
| 775 |
+
"rstrip": false,
|
| 776 |
+
"single_word": false,
|
| 777 |
+
"special": true
|
| 778 |
+
},
|
| 779 |
+
"128097": {
|
| 780 |
+
"content": "<|reserved_special_token_89|>",
|
| 781 |
+
"lstrip": false,
|
| 782 |
+
"normalized": false,
|
| 783 |
+
"rstrip": false,
|
| 784 |
+
"single_word": false,
|
| 785 |
+
"special": true
|
| 786 |
+
},
|
| 787 |
+
"128098": {
|
| 788 |
+
"content": "<|reserved_special_token_90|>",
|
| 789 |
+
"lstrip": false,
|
| 790 |
+
"normalized": false,
|
| 791 |
+
"rstrip": false,
|
| 792 |
+
"single_word": false,
|
| 793 |
+
"special": true
|
| 794 |
+
},
|
| 795 |
+
"128099": {
|
| 796 |
+
"content": "<|reserved_special_token_91|>",
|
| 797 |
+
"lstrip": false,
|
| 798 |
+
"normalized": false,
|
| 799 |
+
"rstrip": false,
|
| 800 |
+
"single_word": false,
|
| 801 |
+
"special": true
|
| 802 |
+
},
|
| 803 |
+
"128100": {
|
| 804 |
+
"content": "<|reserved_special_token_92|>",
|
| 805 |
+
"lstrip": false,
|
| 806 |
+
"normalized": false,
|
| 807 |
+
"rstrip": false,
|
| 808 |
+
"single_word": false,
|
| 809 |
+
"special": true
|
| 810 |
+
},
|
| 811 |
+
"128101": {
|
| 812 |
+
"content": "<|reserved_special_token_93|>",
|
| 813 |
+
"lstrip": false,
|
| 814 |
+
"normalized": false,
|
| 815 |
+
"rstrip": false,
|
| 816 |
+
"single_word": false,
|
| 817 |
+
"special": true
|
| 818 |
+
},
|
| 819 |
+
"128102": {
|
| 820 |
+
"content": "<|reserved_special_token_94|>",
|
| 821 |
+
"lstrip": false,
|
| 822 |
+
"normalized": false,
|
| 823 |
+
"rstrip": false,
|
| 824 |
+
"single_word": false,
|
| 825 |
+
"special": true
|
| 826 |
+
},
|
| 827 |
+
"128103": {
|
| 828 |
+
"content": "<|reserved_special_token_95|>",
|
| 829 |
+
"lstrip": false,
|
| 830 |
+
"normalized": false,
|
| 831 |
+
"rstrip": false,
|
| 832 |
+
"single_word": false,
|
| 833 |
+
"special": true
|
| 834 |
+
},
|
| 835 |
+
"128104": {
|
| 836 |
+
"content": "<|reserved_special_token_96|>",
|
| 837 |
+
"lstrip": false,
|
| 838 |
+
"normalized": false,
|
| 839 |
+
"rstrip": false,
|
| 840 |
+
"single_word": false,
|
| 841 |
+
"special": true
|
| 842 |
+
},
|
| 843 |
+
"128105": {
|
| 844 |
+
"content": "<|reserved_special_token_97|>",
|
| 845 |
+
"lstrip": false,
|
| 846 |
+
"normalized": false,
|
| 847 |
+
"rstrip": false,
|
| 848 |
+
"single_word": false,
|
| 849 |
+
"special": true
|
| 850 |
+
},
|
| 851 |
+
"128106": {
|
| 852 |
+
"content": "<|reserved_special_token_98|>",
|
| 853 |
+
"lstrip": false,
|
| 854 |
+
"normalized": false,
|
| 855 |
+
"rstrip": false,
|
| 856 |
+
"single_word": false,
|
| 857 |
+
"special": true
|
| 858 |
+
},
|
| 859 |
+
"128107": {
|
| 860 |
+
"content": "<|reserved_special_token_99|>",
|
| 861 |
+
"lstrip": false,
|
| 862 |
+
"normalized": false,
|
| 863 |
+
"rstrip": false,
|
| 864 |
+
"single_word": false,
|
| 865 |
+
"special": true
|
| 866 |
+
},
|
| 867 |
+
"128108": {
|
| 868 |
+
"content": "<|reserved_special_token_100|>",
|
| 869 |
+
"lstrip": false,
|
| 870 |
+
"normalized": false,
|
| 871 |
+
"rstrip": false,
|
| 872 |
+
"single_word": false,
|
| 873 |
+
"special": true
|
| 874 |
+
},
|
| 875 |
+
"128109": {
|
| 876 |
+
"content": "<|reserved_special_token_101|>",
|
| 877 |
+
"lstrip": false,
|
| 878 |
+
"normalized": false,
|
| 879 |
+
"rstrip": false,
|
| 880 |
+
"single_word": false,
|
| 881 |
+
"special": true
|
| 882 |
+
},
|
| 883 |
+
"128110": {
|
| 884 |
+
"content": "<|reserved_special_token_102|>",
|
| 885 |
+
"lstrip": false,
|
| 886 |
+
"normalized": false,
|
| 887 |
+
"rstrip": false,
|
| 888 |
+
"single_word": false,
|
| 889 |
+
"special": true
|
| 890 |
+
},
|
| 891 |
+
"128111": {
|
| 892 |
+
"content": "<|reserved_special_token_103|>",
|
| 893 |
+
"lstrip": false,
|
| 894 |
+
"normalized": false,
|
| 895 |
+
"rstrip": false,
|
| 896 |
+
"single_word": false,
|
| 897 |
+
"special": true
|
| 898 |
+
},
|
| 899 |
+
"128112": {
|
| 900 |
+
"content": "<|reserved_special_token_104|>",
|
| 901 |
+
"lstrip": false,
|
| 902 |
+
"normalized": false,
|
| 903 |
+
"rstrip": false,
|
| 904 |
+
"single_word": false,
|
| 905 |
+
"special": true
|
| 906 |
+
},
|
| 907 |
+
"128113": {
|
| 908 |
+
"content": "<|reserved_special_token_105|>",
|
| 909 |
+
"lstrip": false,
|
| 910 |
+
"normalized": false,
|
| 911 |
+
"rstrip": false,
|
| 912 |
+
"single_word": false,
|
| 913 |
+
"special": true
|
| 914 |
+
},
|
| 915 |
+
"128114": {
|
| 916 |
+
"content": "<|reserved_special_token_106|>",
|
| 917 |
+
"lstrip": false,
|
| 918 |
+
"normalized": false,
|
| 919 |
+
"rstrip": false,
|
| 920 |
+
"single_word": false,
|
| 921 |
+
"special": true
|
| 922 |
+
},
|
| 923 |
+
"128115": {
|
| 924 |
+
"content": "<|reserved_special_token_107|>",
|
| 925 |
+
"lstrip": false,
|
| 926 |
+
"normalized": false,
|
| 927 |
+
"rstrip": false,
|
| 928 |
+
"single_word": false,
|
| 929 |
+
"special": true
|
| 930 |
+
},
|
| 931 |
+
"128116": {
|
| 932 |
+
"content": "<|reserved_special_token_108|>",
|
| 933 |
+
"lstrip": false,
|
| 934 |
+
"normalized": false,
|
| 935 |
+
"rstrip": false,
|
| 936 |
+
"single_word": false,
|
| 937 |
+
"special": true
|
| 938 |
+
},
|
| 939 |
+
"128117": {
|
| 940 |
+
"content": "<|reserved_special_token_109|>",
|
| 941 |
+
"lstrip": false,
|
| 942 |
+
"normalized": false,
|
| 943 |
+
"rstrip": false,
|
| 944 |
+
"single_word": false,
|
| 945 |
+
"special": true
|
| 946 |
+
},
|
| 947 |
+
"128118": {
|
| 948 |
+
"content": "<|reserved_special_token_110|>",
|
| 949 |
+
"lstrip": false,
|
| 950 |
+
"normalized": false,
|
| 951 |
+
"rstrip": false,
|
| 952 |
+
"single_word": false,
|
| 953 |
+
"special": true
|
| 954 |
+
},
|
| 955 |
+
"128119": {
|
| 956 |
+
"content": "<|reserved_special_token_111|>",
|
| 957 |
+
"lstrip": false,
|
| 958 |
+
"normalized": false,
|
| 959 |
+
"rstrip": false,
|
| 960 |
+
"single_word": false,
|
| 961 |
+
"special": true
|
| 962 |
+
},
|
| 963 |
+
"128120": {
|
| 964 |
+
"content": "<|reserved_special_token_112|>",
|
| 965 |
+
"lstrip": false,
|
| 966 |
+
"normalized": false,
|
| 967 |
+
"rstrip": false,
|
| 968 |
+
"single_word": false,
|
| 969 |
+
"special": true
|
| 970 |
+
},
|
| 971 |
+
"128121": {
|
| 972 |
+
"content": "<|reserved_special_token_113|>",
|
| 973 |
+
"lstrip": false,
|
| 974 |
+
"normalized": false,
|
| 975 |
+
"rstrip": false,
|
| 976 |
+
"single_word": false,
|
| 977 |
+
"special": true
|
| 978 |
+
},
|
| 979 |
+
"128122": {
|
| 980 |
+
"content": "<|reserved_special_token_114|>",
|
| 981 |
+
"lstrip": false,
|
| 982 |
+
"normalized": false,
|
| 983 |
+
"rstrip": false,
|
| 984 |
+
"single_word": false,
|
| 985 |
+
"special": true
|
| 986 |
+
},
|
| 987 |
+
"128123": {
|
| 988 |
+
"content": "<|reserved_special_token_115|>",
|
| 989 |
+
"lstrip": false,
|
| 990 |
+
"normalized": false,
|
| 991 |
+
"rstrip": false,
|
| 992 |
+
"single_word": false,
|
| 993 |
+
"special": true
|
| 994 |
+
},
|
| 995 |
+
"128124": {
|
| 996 |
+
"content": "<|reserved_special_token_116|>",
|
| 997 |
+
"lstrip": false,
|
| 998 |
+
"normalized": false,
|
| 999 |
+
"rstrip": false,
|
| 1000 |
+
"single_word": false,
|
| 1001 |
+
"special": true
|
| 1002 |
+
},
|
| 1003 |
+
"128125": {
|
| 1004 |
+
"content": "<|reserved_special_token_117|>",
|
| 1005 |
+
"lstrip": false,
|
| 1006 |
+
"normalized": false,
|
| 1007 |
+
"rstrip": false,
|
| 1008 |
+
"single_word": false,
|
| 1009 |
+
"special": true
|
| 1010 |
+
},
|
| 1011 |
+
"128126": {
|
| 1012 |
+
"content": "<|reserved_special_token_118|>",
|
| 1013 |
+
"lstrip": false,
|
| 1014 |
+
"normalized": false,
|
| 1015 |
+
"rstrip": false,
|
| 1016 |
+
"single_word": false,
|
| 1017 |
+
"special": true
|
| 1018 |
+
},
|
| 1019 |
+
"128127": {
|
| 1020 |
+
"content": "<|reserved_special_token_119|>",
|
| 1021 |
+
"lstrip": false,
|
| 1022 |
+
"normalized": false,
|
| 1023 |
+
"rstrip": false,
|
| 1024 |
+
"single_word": false,
|
| 1025 |
+
"special": true
|
| 1026 |
+
},
|
| 1027 |
+
"128128": {
|
| 1028 |
+
"content": "<|reserved_special_token_120|>",
|
| 1029 |
+
"lstrip": false,
|
| 1030 |
+
"normalized": false,
|
| 1031 |
+
"rstrip": false,
|
| 1032 |
+
"single_word": false,
|
| 1033 |
+
"special": true
|
| 1034 |
+
},
|
| 1035 |
+
"128129": {
|
| 1036 |
+
"content": "<|reserved_special_token_121|>",
|
| 1037 |
+
"lstrip": false,
|
| 1038 |
+
"normalized": false,
|
| 1039 |
+
"rstrip": false,
|
| 1040 |
+
"single_word": false,
|
| 1041 |
+
"special": true
|
| 1042 |
+
},
|
| 1043 |
+
"128130": {
|
| 1044 |
+
"content": "<|reserved_special_token_122|>",
|
| 1045 |
+
"lstrip": false,
|
| 1046 |
+
"normalized": false,
|
| 1047 |
+
"rstrip": false,
|
| 1048 |
+
"single_word": false,
|
| 1049 |
+
"special": true
|
| 1050 |
+
},
|
| 1051 |
+
"128131": {
|
| 1052 |
+
"content": "<|reserved_special_token_123|>",
|
| 1053 |
+
"lstrip": false,
|
| 1054 |
+
"normalized": false,
|
| 1055 |
+
"rstrip": false,
|
| 1056 |
+
"single_word": false,
|
| 1057 |
+
"special": true
|
| 1058 |
+
},
|
| 1059 |
+
"128132": {
|
| 1060 |
+
"content": "<|reserved_special_token_124|>",
|
| 1061 |
+
"lstrip": false,
|
| 1062 |
+
"normalized": false,
|
| 1063 |
+
"rstrip": false,
|
| 1064 |
+
"single_word": false,
|
| 1065 |
+
"special": true
|
| 1066 |
+
},
|
| 1067 |
+
"128133": {
|
| 1068 |
+
"content": "<|reserved_special_token_125|>",
|
| 1069 |
+
"lstrip": false,
|
| 1070 |
+
"normalized": false,
|
| 1071 |
+
"rstrip": false,
|
| 1072 |
+
"single_word": false,
|
| 1073 |
+
"special": true
|
| 1074 |
+
},
|
| 1075 |
+
"128134": {
|
| 1076 |
+
"content": "<|reserved_special_token_126|>",
|
| 1077 |
+
"lstrip": false,
|
| 1078 |
+
"normalized": false,
|
| 1079 |
+
"rstrip": false,
|
| 1080 |
+
"single_word": false,
|
| 1081 |
+
"special": true
|
| 1082 |
+
},
|
| 1083 |
+
"128135": {
|
| 1084 |
+
"content": "<|reserved_special_token_127|>",
|
| 1085 |
+
"lstrip": false,
|
| 1086 |
+
"normalized": false,
|
| 1087 |
+
"rstrip": false,
|
| 1088 |
+
"single_word": false,
|
| 1089 |
+
"special": true
|
| 1090 |
+
},
|
| 1091 |
+
"128136": {
|
| 1092 |
+
"content": "<|reserved_special_token_128|>",
|
| 1093 |
+
"lstrip": false,
|
| 1094 |
+
"normalized": false,
|
| 1095 |
+
"rstrip": false,
|
| 1096 |
+
"single_word": false,
|
| 1097 |
+
"special": true
|
| 1098 |
+
},
|
| 1099 |
+
"128137": {
|
| 1100 |
+
"content": "<|reserved_special_token_129|>",
|
| 1101 |
+
"lstrip": false,
|
| 1102 |
+
"normalized": false,
|
| 1103 |
+
"rstrip": false,
|
| 1104 |
+
"single_word": false,
|
| 1105 |
+
"special": true
|
| 1106 |
+
},
|
| 1107 |
+
"128138": {
|
| 1108 |
+
"content": "<|reserved_special_token_130|>",
|
| 1109 |
+
"lstrip": false,
|
| 1110 |
+
"normalized": false,
|
| 1111 |
+
"rstrip": false,
|
| 1112 |
+
"single_word": false,
|
| 1113 |
+
"special": true
|
| 1114 |
+
},
|
| 1115 |
+
"128139": {
|
| 1116 |
+
"content": "<|reserved_special_token_131|>",
|
| 1117 |
+
"lstrip": false,
|
| 1118 |
+
"normalized": false,
|
| 1119 |
+
"rstrip": false,
|
| 1120 |
+
"single_word": false,
|
| 1121 |
+
"special": true
|
| 1122 |
+
},
|
| 1123 |
+
"128140": {
|
| 1124 |
+
"content": "<|reserved_special_token_132|>",
|
| 1125 |
+
"lstrip": false,
|
| 1126 |
+
"normalized": false,
|
| 1127 |
+
"rstrip": false,
|
| 1128 |
+
"single_word": false,
|
| 1129 |
+
"special": true
|
| 1130 |
+
},
|
| 1131 |
+
"128141": {
|
| 1132 |
+
"content": "<|reserved_special_token_133|>",
|
| 1133 |
+
"lstrip": false,
|
| 1134 |
+
"normalized": false,
|
| 1135 |
+
"rstrip": false,
|
| 1136 |
+
"single_word": false,
|
| 1137 |
+
"special": true
|
| 1138 |
+
},
|
| 1139 |
+
"128142": {
|
| 1140 |
+
"content": "<|reserved_special_token_134|>",
|
| 1141 |
+
"lstrip": false,
|
| 1142 |
+
"normalized": false,
|
| 1143 |
+
"rstrip": false,
|
| 1144 |
+
"single_word": false,
|
| 1145 |
+
"special": true
|
| 1146 |
+
},
|
| 1147 |
+
"128143": {
|
| 1148 |
+
"content": "<|reserved_special_token_135|>",
|
| 1149 |
+
"lstrip": false,
|
| 1150 |
+
"normalized": false,
|
| 1151 |
+
"rstrip": false,
|
| 1152 |
+
"single_word": false,
|
| 1153 |
+
"special": true
|
| 1154 |
+
},
|
| 1155 |
+
"128144": {
|
| 1156 |
+
"content": "<|reserved_special_token_136|>",
|
| 1157 |
+
"lstrip": false,
|
| 1158 |
+
"normalized": false,
|
| 1159 |
+
"rstrip": false,
|
| 1160 |
+
"single_word": false,
|
| 1161 |
+
"special": true
|
| 1162 |
+
},
|
| 1163 |
+
"128145": {
|
| 1164 |
+
"content": "<|reserved_special_token_137|>",
|
| 1165 |
+
"lstrip": false,
|
| 1166 |
+
"normalized": false,
|
| 1167 |
+
"rstrip": false,
|
| 1168 |
+
"single_word": false,
|
| 1169 |
+
"special": true
|
| 1170 |
+
},
|
| 1171 |
+
"128146": {
|
| 1172 |
+
"content": "<|reserved_special_token_138|>",
|
| 1173 |
+
"lstrip": false,
|
| 1174 |
+
"normalized": false,
|
| 1175 |
+
"rstrip": false,
|
| 1176 |
+
"single_word": false,
|
| 1177 |
+
"special": true
|
| 1178 |
+
},
|
| 1179 |
+
"128147": {
|
| 1180 |
+
"content": "<|reserved_special_token_139|>",
|
| 1181 |
+
"lstrip": false,
|
| 1182 |
+
"normalized": false,
|
| 1183 |
+
"rstrip": false,
|
| 1184 |
+
"single_word": false,
|
| 1185 |
+
"special": true
|
| 1186 |
+
},
|
| 1187 |
+
"128148": {
|
| 1188 |
+
"content": "<|reserved_special_token_140|>",
|
| 1189 |
+
"lstrip": false,
|
| 1190 |
+
"normalized": false,
|
| 1191 |
+
"rstrip": false,
|
| 1192 |
+
"single_word": false,
|
| 1193 |
+
"special": true
|
| 1194 |
+
},
|
| 1195 |
+
"128149": {
|
| 1196 |
+
"content": "<|reserved_special_token_141|>",
|
| 1197 |
+
"lstrip": false,
|
| 1198 |
+
"normalized": false,
|
| 1199 |
+
"rstrip": false,
|
| 1200 |
+
"single_word": false,
|
| 1201 |
+
"special": true
|
| 1202 |
+
},
|
| 1203 |
+
"128150": {
|
| 1204 |
+
"content": "<|reserved_special_token_142|>",
|
| 1205 |
+
"lstrip": false,
|
| 1206 |
+
"normalized": false,
|
| 1207 |
+
"rstrip": false,
|
| 1208 |
+
"single_word": false,
|
| 1209 |
+
"special": true
|
| 1210 |
+
},
|
| 1211 |
+
"128151": {
|
| 1212 |
+
"content": "<|reserved_special_token_143|>",
|
| 1213 |
+
"lstrip": false,
|
| 1214 |
+
"normalized": false,
|
| 1215 |
+
"rstrip": false,
|
| 1216 |
+
"single_word": false,
|
| 1217 |
+
"special": true
|
| 1218 |
+
},
|
| 1219 |
+
"128152": {
|
| 1220 |
+
"content": "<|reserved_special_token_144|>",
|
| 1221 |
+
"lstrip": false,
|
| 1222 |
+
"normalized": false,
|
| 1223 |
+
"rstrip": false,
|
| 1224 |
+
"single_word": false,
|
| 1225 |
+
"special": true
|
| 1226 |
+
},
|
| 1227 |
+
"128153": {
|
| 1228 |
+
"content": "<|reserved_special_token_145|>",
|
| 1229 |
+
"lstrip": false,
|
| 1230 |
+
"normalized": false,
|
| 1231 |
+
"rstrip": false,
|
| 1232 |
+
"single_word": false,
|
| 1233 |
+
"special": true
|
| 1234 |
+
},
|
| 1235 |
+
"128154": {
|
| 1236 |
+
"content": "<|reserved_special_token_146|>",
|
| 1237 |
+
"lstrip": false,
|
| 1238 |
+
"normalized": false,
|
| 1239 |
+
"rstrip": false,
|
| 1240 |
+
"single_word": false,
|
| 1241 |
+
"special": true
|
| 1242 |
+
},
|
| 1243 |
+
"128155": {
|
| 1244 |
+
"content": "<|reserved_special_token_147|>",
|
| 1245 |
+
"lstrip": false,
|
| 1246 |
+
"normalized": false,
|
| 1247 |
+
"rstrip": false,
|
| 1248 |
+
"single_word": false,
|
| 1249 |
+
"special": true
|
| 1250 |
+
},
|
| 1251 |
+
"128156": {
|
| 1252 |
+
"content": "<|reserved_special_token_148|>",
|
| 1253 |
+
"lstrip": false,
|
| 1254 |
+
"normalized": false,
|
| 1255 |
+
"rstrip": false,
|
| 1256 |
+
"single_word": false,
|
| 1257 |
+
"special": true
|
| 1258 |
+
},
|
| 1259 |
+
"128157": {
|
| 1260 |
+
"content": "<|reserved_special_token_149|>",
|
| 1261 |
+
"lstrip": false,
|
| 1262 |
+
"normalized": false,
|
| 1263 |
+
"rstrip": false,
|
| 1264 |
+
"single_word": false,
|
| 1265 |
+
"special": true
|
| 1266 |
+
},
|
| 1267 |
+
"128158": {
|
| 1268 |
+
"content": "<|reserved_special_token_150|>",
|
| 1269 |
+
"lstrip": false,
|
| 1270 |
+
"normalized": false,
|
| 1271 |
+
"rstrip": false,
|
| 1272 |
+
"single_word": false,
|
| 1273 |
+
"special": true
|
| 1274 |
+
},
|
| 1275 |
+
"128159": {
|
| 1276 |
+
"content": "<|reserved_special_token_151|>",
|
| 1277 |
+
"lstrip": false,
|
| 1278 |
+
"normalized": false,
|
| 1279 |
+
"rstrip": false,
|
| 1280 |
+
"single_word": false,
|
| 1281 |
+
"special": true
|
| 1282 |
+
},
|
| 1283 |
+
"128160": {
|
| 1284 |
+
"content": "<|reserved_special_token_152|>",
|
| 1285 |
+
"lstrip": false,
|
| 1286 |
+
"normalized": false,
|
| 1287 |
+
"rstrip": false,
|
| 1288 |
+
"single_word": false,
|
| 1289 |
+
"special": true
|
| 1290 |
+
},
|
| 1291 |
+
"128161": {
|
| 1292 |
+
"content": "<|reserved_special_token_153|>",
|
| 1293 |
+
"lstrip": false,
|
| 1294 |
+
"normalized": false,
|
| 1295 |
+
"rstrip": false,
|
| 1296 |
+
"single_word": false,
|
| 1297 |
+
"special": true
|
| 1298 |
+
},
|
| 1299 |
+
"128162": {
|
| 1300 |
+
"content": "<|reserved_special_token_154|>",
|
| 1301 |
+
"lstrip": false,
|
| 1302 |
+
"normalized": false,
|
| 1303 |
+
"rstrip": false,
|
| 1304 |
+
"single_word": false,
|
| 1305 |
+
"special": true
|
| 1306 |
+
},
|
| 1307 |
+
"128163": {
|
| 1308 |
+
"content": "<|reserved_special_token_155|>",
|
| 1309 |
+
"lstrip": false,
|
| 1310 |
+
"normalized": false,
|
| 1311 |
+
"rstrip": false,
|
| 1312 |
+
"single_word": false,
|
| 1313 |
+
"special": true
|
| 1314 |
+
},
|
| 1315 |
+
"128164": {
|
| 1316 |
+
"content": "<|reserved_special_token_156|>",
|
| 1317 |
+
"lstrip": false,
|
| 1318 |
+
"normalized": false,
|
| 1319 |
+
"rstrip": false,
|
| 1320 |
+
"single_word": false,
|
| 1321 |
+
"special": true
|
| 1322 |
+
},
|
| 1323 |
+
"128165": {
|
| 1324 |
+
"content": "<|reserved_special_token_157|>",
|
| 1325 |
+
"lstrip": false,
|
| 1326 |
+
"normalized": false,
|
| 1327 |
+
"rstrip": false,
|
| 1328 |
+
"single_word": false,
|
| 1329 |
+
"special": true
|
| 1330 |
+
},
|
| 1331 |
+
"128166": {
|
| 1332 |
+
"content": "<|reserved_special_token_158|>",
|
| 1333 |
+
"lstrip": false,
|
| 1334 |
+
"normalized": false,
|
| 1335 |
+
"rstrip": false,
|
| 1336 |
+
"single_word": false,
|
| 1337 |
+
"special": true
|
| 1338 |
+
},
|
| 1339 |
+
"128167": {
|
| 1340 |
+
"content": "<|reserved_special_token_159|>",
|
| 1341 |
+
"lstrip": false,
|
| 1342 |
+
"normalized": false,
|
| 1343 |
+
"rstrip": false,
|
| 1344 |
+
"single_word": false,
|
| 1345 |
+
"special": true
|
| 1346 |
+
},
|
| 1347 |
+
"128168": {
|
| 1348 |
+
"content": "<|reserved_special_token_160|>",
|
| 1349 |
+
"lstrip": false,
|
| 1350 |
+
"normalized": false,
|
| 1351 |
+
"rstrip": false,
|
| 1352 |
+
"single_word": false,
|
| 1353 |
+
"special": true
|
| 1354 |
+
},
|
| 1355 |
+
"128169": {
|
| 1356 |
+
"content": "<|reserved_special_token_161|>",
|
| 1357 |
+
"lstrip": false,
|
| 1358 |
+
"normalized": false,
|
| 1359 |
+
"rstrip": false,
|
| 1360 |
+
"single_word": false,
|
| 1361 |
+
"special": true
|
| 1362 |
+
},
|
| 1363 |
+
"128170": {
|
| 1364 |
+
"content": "<|reserved_special_token_162|>",
|
| 1365 |
+
"lstrip": false,
|
| 1366 |
+
"normalized": false,
|
| 1367 |
+
"rstrip": false,
|
| 1368 |
+
"single_word": false,
|
| 1369 |
+
"special": true
|
| 1370 |
+
},
|
| 1371 |
+
"128171": {
|
| 1372 |
+
"content": "<|reserved_special_token_163|>",
|
| 1373 |
+
"lstrip": false,
|
| 1374 |
+
"normalized": false,
|
| 1375 |
+
"rstrip": false,
|
| 1376 |
+
"single_word": false,
|
| 1377 |
+
"special": true
|
| 1378 |
+
},
|
| 1379 |
+
"128172": {
|
| 1380 |
+
"content": "<|reserved_special_token_164|>",
|
| 1381 |
+
"lstrip": false,
|
| 1382 |
+
"normalized": false,
|
| 1383 |
+
"rstrip": false,
|
| 1384 |
+
"single_word": false,
|
| 1385 |
+
"special": true
|
| 1386 |
+
},
|
| 1387 |
+
"128173": {
|
| 1388 |
+
"content": "<|reserved_special_token_165|>",
|
| 1389 |
+
"lstrip": false,
|
| 1390 |
+
"normalized": false,
|
| 1391 |
+
"rstrip": false,
|
| 1392 |
+
"single_word": false,
|
| 1393 |
+
"special": true
|
| 1394 |
+
},
|
| 1395 |
+
"128174": {
|
| 1396 |
+
"content": "<|reserved_special_token_166|>",
|
| 1397 |
+
"lstrip": false,
|
| 1398 |
+
"normalized": false,
|
| 1399 |
+
"rstrip": false,
|
| 1400 |
+
"single_word": false,
|
| 1401 |
+
"special": true
|
| 1402 |
+
},
|
| 1403 |
+
"128175": {
|
| 1404 |
+
"content": "<|reserved_special_token_167|>",
|
| 1405 |
+
"lstrip": false,
|
| 1406 |
+
"normalized": false,
|
| 1407 |
+
"rstrip": false,
|
| 1408 |
+
"single_word": false,
|
| 1409 |
+
"special": true
|
| 1410 |
+
},
|
| 1411 |
+
"128176": {
|
| 1412 |
+
"content": "<|reserved_special_token_168|>",
|
| 1413 |
+
"lstrip": false,
|
| 1414 |
+
"normalized": false,
|
| 1415 |
+
"rstrip": false,
|
| 1416 |
+
"single_word": false,
|
| 1417 |
+
"special": true
|
| 1418 |
+
},
|
| 1419 |
+
"128177": {
|
| 1420 |
+
"content": "<|reserved_special_token_169|>",
|
| 1421 |
+
"lstrip": false,
|
| 1422 |
+
"normalized": false,
|
| 1423 |
+
"rstrip": false,
|
| 1424 |
+
"single_word": false,
|
| 1425 |
+
"special": true
|
| 1426 |
+
},
|
| 1427 |
+
"128178": {
|
| 1428 |
+
"content": "<|reserved_special_token_170|>",
|
| 1429 |
+
"lstrip": false,
|
| 1430 |
+
"normalized": false,
|
| 1431 |
+
"rstrip": false,
|
| 1432 |
+
"single_word": false,
|
| 1433 |
+
"special": true
|
| 1434 |
+
},
|
| 1435 |
+
"128179": {
|
| 1436 |
+
"content": "<|reserved_special_token_171|>",
|
| 1437 |
+
"lstrip": false,
|
| 1438 |
+
"normalized": false,
|
| 1439 |
+
"rstrip": false,
|
| 1440 |
+
"single_word": false,
|
| 1441 |
+
"special": true
|
| 1442 |
+
},
|
| 1443 |
+
"128180": {
|
| 1444 |
+
"content": "<|reserved_special_token_172|>",
|
| 1445 |
+
"lstrip": false,
|
| 1446 |
+
"normalized": false,
|
| 1447 |
+
"rstrip": false,
|
| 1448 |
+
"single_word": false,
|
| 1449 |
+
"special": true
|
| 1450 |
+
},
|
| 1451 |
+
"128181": {
|
| 1452 |
+
"content": "<|reserved_special_token_173|>",
|
| 1453 |
+
"lstrip": false,
|
| 1454 |
+
"normalized": false,
|
| 1455 |
+
"rstrip": false,
|
| 1456 |
+
"single_word": false,
|
| 1457 |
+
"special": true
|
| 1458 |
+
},
|
| 1459 |
+
"128182": {
|
| 1460 |
+
"content": "<|reserved_special_token_174|>",
|
| 1461 |
+
"lstrip": false,
|
| 1462 |
+
"normalized": false,
|
| 1463 |
+
"rstrip": false,
|
| 1464 |
+
"single_word": false,
|
| 1465 |
+
"special": true
|
| 1466 |
+
},
|
| 1467 |
+
"128183": {
|
| 1468 |
+
"content": "<|reserved_special_token_175|>",
|
| 1469 |
+
"lstrip": false,
|
| 1470 |
+
"normalized": false,
|
| 1471 |
+
"rstrip": false,
|
| 1472 |
+
"single_word": false,
|
| 1473 |
+
"special": true
|
| 1474 |
+
},
|
| 1475 |
+
"128184": {
|
| 1476 |
+
"content": "<|reserved_special_token_176|>",
|
| 1477 |
+
"lstrip": false,
|
| 1478 |
+
"normalized": false,
|
| 1479 |
+
"rstrip": false,
|
| 1480 |
+
"single_word": false,
|
| 1481 |
+
"special": true
|
| 1482 |
+
},
|
| 1483 |
+
"128185": {
|
| 1484 |
+
"content": "<|reserved_special_token_177|>",
|
| 1485 |
+
"lstrip": false,
|
| 1486 |
+
"normalized": false,
|
| 1487 |
+
"rstrip": false,
|
| 1488 |
+
"single_word": false,
|
| 1489 |
+
"special": true
|
| 1490 |
+
},
|
| 1491 |
+
"128186": {
|
| 1492 |
+
"content": "<|reserved_special_token_178|>",
|
| 1493 |
+
"lstrip": false,
|
| 1494 |
+
"normalized": false,
|
| 1495 |
+
"rstrip": false,
|
| 1496 |
+
"single_word": false,
|
| 1497 |
+
"special": true
|
| 1498 |
+
},
|
| 1499 |
+
"128187": {
|
| 1500 |
+
"content": "<|reserved_special_token_179|>",
|
| 1501 |
+
"lstrip": false,
|
| 1502 |
+
"normalized": false,
|
| 1503 |
+
"rstrip": false,
|
| 1504 |
+
"single_word": false,
|
| 1505 |
+
"special": true
|
| 1506 |
+
},
|
| 1507 |
+
"128188": {
|
| 1508 |
+
"content": "<|reserved_special_token_180|>",
|
| 1509 |
+
"lstrip": false,
|
| 1510 |
+
"normalized": false,
|
| 1511 |
+
"rstrip": false,
|
| 1512 |
+
"single_word": false,
|
| 1513 |
+
"special": true
|
| 1514 |
+
},
|
| 1515 |
+
"128189": {
|
| 1516 |
+
"content": "<|reserved_special_token_181|>",
|
| 1517 |
+
"lstrip": false,
|
| 1518 |
+
"normalized": false,
|
| 1519 |
+
"rstrip": false,
|
| 1520 |
+
"single_word": false,
|
| 1521 |
+
"special": true
|
| 1522 |
+
},
|
| 1523 |
+
"128190": {
|
| 1524 |
+
"content": "<|reserved_special_token_182|>",
|
| 1525 |
+
"lstrip": false,
|
| 1526 |
+
"normalized": false,
|
| 1527 |
+
"rstrip": false,
|
| 1528 |
+
"single_word": false,
|
| 1529 |
+
"special": true
|
| 1530 |
+
},
|
| 1531 |
+
"128191": {
|
| 1532 |
+
"content": "<|reserved_special_token_183|>",
|
| 1533 |
+
"lstrip": false,
|
| 1534 |
+
"normalized": false,
|
| 1535 |
+
"rstrip": false,
|
| 1536 |
+
"single_word": false,
|
| 1537 |
+
"special": true
|
| 1538 |
+
},
|
| 1539 |
+
"128192": {
|
| 1540 |
+
"content": "<|reserved_special_token_184|>",
|
| 1541 |
+
"lstrip": false,
|
| 1542 |
+
"normalized": false,
|
| 1543 |
+
"rstrip": false,
|
| 1544 |
+
"single_word": false,
|
| 1545 |
+
"special": true
|
| 1546 |
+
},
|
| 1547 |
+
"128193": {
|
| 1548 |
+
"content": "<|reserved_special_token_185|>",
|
| 1549 |
+
"lstrip": false,
|
| 1550 |
+
"normalized": false,
|
| 1551 |
+
"rstrip": false,
|
| 1552 |
+
"single_word": false,
|
| 1553 |
+
"special": true
|
| 1554 |
+
},
|
| 1555 |
+
"128194": {
|
| 1556 |
+
"content": "<|reserved_special_token_186|>",
|
| 1557 |
+
"lstrip": false,
|
| 1558 |
+
"normalized": false,
|
| 1559 |
+
"rstrip": false,
|
| 1560 |
+
"single_word": false,
|
| 1561 |
+
"special": true
|
| 1562 |
+
},
|
| 1563 |
+
"128195": {
|
| 1564 |
+
"content": "<|reserved_special_token_187|>",
|
| 1565 |
+
"lstrip": false,
|
| 1566 |
+
"normalized": false,
|
| 1567 |
+
"rstrip": false,
|
| 1568 |
+
"single_word": false,
|
| 1569 |
+
"special": true
|
| 1570 |
+
},
|
| 1571 |
+
"128196": {
|
| 1572 |
+
"content": "<|reserved_special_token_188|>",
|
| 1573 |
+
"lstrip": false,
|
| 1574 |
+
"normalized": false,
|
| 1575 |
+
"rstrip": false,
|
| 1576 |
+
"single_word": false,
|
| 1577 |
+
"special": true
|
| 1578 |
+
},
|
| 1579 |
+
"128197": {
|
| 1580 |
+
"content": "<|reserved_special_token_189|>",
|
| 1581 |
+
"lstrip": false,
|
| 1582 |
+
"normalized": false,
|
| 1583 |
+
"rstrip": false,
|
| 1584 |
+
"single_word": false,
|
| 1585 |
+
"special": true
|
| 1586 |
+
},
|
| 1587 |
+
"128198": {
|
| 1588 |
+
"content": "<|reserved_special_token_190|>",
|
| 1589 |
+
"lstrip": false,
|
| 1590 |
+
"normalized": false,
|
| 1591 |
+
"rstrip": false,
|
| 1592 |
+
"single_word": false,
|
| 1593 |
+
"special": true
|
| 1594 |
+
},
|
| 1595 |
+
"128199": {
|
| 1596 |
+
"content": "<|reserved_special_token_191|>",
|
| 1597 |
+
"lstrip": false,
|
| 1598 |
+
"normalized": false,
|
| 1599 |
+
"rstrip": false,
|
| 1600 |
+
"single_word": false,
|
| 1601 |
+
"special": true
|
| 1602 |
+
},
|
| 1603 |
+
"128200": {
|
| 1604 |
+
"content": "<|reserved_special_token_192|>",
|
| 1605 |
+
"lstrip": false,
|
| 1606 |
+
"normalized": false,
|
| 1607 |
+
"rstrip": false,
|
| 1608 |
+
"single_word": false,
|
| 1609 |
+
"special": true
|
| 1610 |
+
},
|
| 1611 |
+
"128201": {
|
| 1612 |
+
"content": "<|reserved_special_token_193|>",
|
| 1613 |
+
"lstrip": false,
|
| 1614 |
+
"normalized": false,
|
| 1615 |
+
"rstrip": false,
|
| 1616 |
+
"single_word": false,
|
| 1617 |
+
"special": true
|
| 1618 |
+
},
|
| 1619 |
+
"128202": {
|
| 1620 |
+
"content": "<|reserved_special_token_194|>",
|
| 1621 |
+
"lstrip": false,
|
| 1622 |
+
"normalized": false,
|
| 1623 |
+
"rstrip": false,
|
| 1624 |
+
"single_word": false,
|
| 1625 |
+
"special": true
|
| 1626 |
+
},
|
| 1627 |
+
"128203": {
|
| 1628 |
+
"content": "<|reserved_special_token_195|>",
|
| 1629 |
+
"lstrip": false,
|
| 1630 |
+
"normalized": false,
|
| 1631 |
+
"rstrip": false,
|
| 1632 |
+
"single_word": false,
|
| 1633 |
+
"special": true
|
| 1634 |
+
},
|
| 1635 |
+
"128204": {
|
| 1636 |
+
"content": "<|reserved_special_token_196|>",
|
| 1637 |
+
"lstrip": false,
|
| 1638 |
+
"normalized": false,
|
| 1639 |
+
"rstrip": false,
|
| 1640 |
+
"single_word": false,
|
| 1641 |
+
"special": true
|
| 1642 |
+
},
|
| 1643 |
+
"128205": {
|
| 1644 |
+
"content": "<|reserved_special_token_197|>",
|
| 1645 |
+
"lstrip": false,
|
| 1646 |
+
"normalized": false,
|
| 1647 |
+
"rstrip": false,
|
| 1648 |
+
"single_word": false,
|
| 1649 |
+
"special": true
|
| 1650 |
+
},
|
| 1651 |
+
"128206": {
|
| 1652 |
+
"content": "<|reserved_special_token_198|>",
|
| 1653 |
+
"lstrip": false,
|
| 1654 |
+
"normalized": false,
|
| 1655 |
+
"rstrip": false,
|
| 1656 |
+
"single_word": false,
|
| 1657 |
+
"special": true
|
| 1658 |
+
},
|
| 1659 |
+
"128207": {
|
| 1660 |
+
"content": "<|reserved_special_token_199|>",
|
| 1661 |
+
"lstrip": false,
|
| 1662 |
+
"normalized": false,
|
| 1663 |
+
"rstrip": false,
|
| 1664 |
+
"single_word": false,
|
| 1665 |
+
"special": true
|
| 1666 |
+
},
|
| 1667 |
+
"128208": {
|
| 1668 |
+
"content": "<|reserved_special_token_200|>",
|
| 1669 |
+
"lstrip": false,
|
| 1670 |
+
"normalized": false,
|
| 1671 |
+
"rstrip": false,
|
| 1672 |
+
"single_word": false,
|
| 1673 |
+
"special": true
|
| 1674 |
+
},
|
| 1675 |
+
"128209": {
|
| 1676 |
+
"content": "<|reserved_special_token_201|>",
|
| 1677 |
+
"lstrip": false,
|
| 1678 |
+
"normalized": false,
|
| 1679 |
+
"rstrip": false,
|
| 1680 |
+
"single_word": false,
|
| 1681 |
+
"special": true
|
| 1682 |
+
},
|
| 1683 |
+
"128210": {
|
| 1684 |
+
"content": "<|reserved_special_token_202|>",
|
| 1685 |
+
"lstrip": false,
|
| 1686 |
+
"normalized": false,
|
| 1687 |
+
"rstrip": false,
|
| 1688 |
+
"single_word": false,
|
| 1689 |
+
"special": true
|
| 1690 |
+
},
|
| 1691 |
+
"128211": {
|
| 1692 |
+
"content": "<|reserved_special_token_203|>",
|
| 1693 |
+
"lstrip": false,
|
| 1694 |
+
"normalized": false,
|
| 1695 |
+
"rstrip": false,
|
| 1696 |
+
"single_word": false,
|
| 1697 |
+
"special": true
|
| 1698 |
+
},
|
| 1699 |
+
"128212": {
|
| 1700 |
+
"content": "<|reserved_special_token_204|>",
|
| 1701 |
+
"lstrip": false,
|
| 1702 |
+
"normalized": false,
|
| 1703 |
+
"rstrip": false,
|
| 1704 |
+
"single_word": false,
|
| 1705 |
+
"special": true
|
| 1706 |
+
},
|
| 1707 |
+
"128213": {
|
| 1708 |
+
"content": "<|reserved_special_token_205|>",
|
| 1709 |
+
"lstrip": false,
|
| 1710 |
+
"normalized": false,
|
| 1711 |
+
"rstrip": false,
|
| 1712 |
+
"single_word": false,
|
| 1713 |
+
"special": true
|
| 1714 |
+
},
|
| 1715 |
+
"128214": {
|
| 1716 |
+
"content": "<|reserved_special_token_206|>",
|
| 1717 |
+
"lstrip": false,
|
| 1718 |
+
"normalized": false,
|
| 1719 |
+
"rstrip": false,
|
| 1720 |
+
"single_word": false,
|
| 1721 |
+
"special": true
|
| 1722 |
+
},
|
| 1723 |
+
"128215": {
|
| 1724 |
+
"content": "<|reserved_special_token_207|>",
|
| 1725 |
+
"lstrip": false,
|
| 1726 |
+
"normalized": false,
|
| 1727 |
+
"rstrip": false,
|
| 1728 |
+
"single_word": false,
|
| 1729 |
+
"special": true
|
| 1730 |
+
},
|
| 1731 |
+
"128216": {
|
| 1732 |
+
"content": "<|reserved_special_token_208|>",
|
| 1733 |
+
"lstrip": false,
|
| 1734 |
+
"normalized": false,
|
| 1735 |
+
"rstrip": false,
|
| 1736 |
+
"single_word": false,
|
| 1737 |
+
"special": true
|
| 1738 |
+
},
|
| 1739 |
+
"128217": {
|
| 1740 |
+
"content": "<|reserved_special_token_209|>",
|
| 1741 |
+
"lstrip": false,
|
| 1742 |
+
"normalized": false,
|
| 1743 |
+
"rstrip": false,
|
| 1744 |
+
"single_word": false,
|
| 1745 |
+
"special": true
|
| 1746 |
+
},
|
| 1747 |
+
"128218": {
|
| 1748 |
+
"content": "<|reserved_special_token_210|>",
|
| 1749 |
+
"lstrip": false,
|
| 1750 |
+
"normalized": false,
|
| 1751 |
+
"rstrip": false,
|
| 1752 |
+
"single_word": false,
|
| 1753 |
+
"special": true
|
| 1754 |
+
},
|
| 1755 |
+
"128219": {
|
| 1756 |
+
"content": "<|reserved_special_token_211|>",
|
| 1757 |
+
"lstrip": false,
|
| 1758 |
+
"normalized": false,
|
| 1759 |
+
"rstrip": false,
|
| 1760 |
+
"single_word": false,
|
| 1761 |
+
"special": true
|
| 1762 |
+
},
|
| 1763 |
+
"128220": {
|
| 1764 |
+
"content": "<|reserved_special_token_212|>",
|
| 1765 |
+
"lstrip": false,
|
| 1766 |
+
"normalized": false,
|
| 1767 |
+
"rstrip": false,
|
| 1768 |
+
"single_word": false,
|
| 1769 |
+
"special": true
|
| 1770 |
+
},
|
| 1771 |
+
"128221": {
|
| 1772 |
+
"content": "<|reserved_special_token_213|>",
|
| 1773 |
+
"lstrip": false,
|
| 1774 |
+
"normalized": false,
|
| 1775 |
+
"rstrip": false,
|
| 1776 |
+
"single_word": false,
|
| 1777 |
+
"special": true
|
| 1778 |
+
},
|
| 1779 |
+
"128222": {
|
| 1780 |
+
"content": "<|reserved_special_token_214|>",
|
| 1781 |
+
"lstrip": false,
|
| 1782 |
+
"normalized": false,
|
| 1783 |
+
"rstrip": false,
|
| 1784 |
+
"single_word": false,
|
| 1785 |
+
"special": true
|
| 1786 |
+
},
|
| 1787 |
+
"128223": {
|
| 1788 |
+
"content": "<|reserved_special_token_215|>",
|
| 1789 |
+
"lstrip": false,
|
| 1790 |
+
"normalized": false,
|
| 1791 |
+
"rstrip": false,
|
| 1792 |
+
"single_word": false,
|
| 1793 |
+
"special": true
|
| 1794 |
+
},
|
| 1795 |
+
"128224": {
|
| 1796 |
+
"content": "<|reserved_special_token_216|>",
|
| 1797 |
+
"lstrip": false,
|
| 1798 |
+
"normalized": false,
|
| 1799 |
+
"rstrip": false,
|
| 1800 |
+
"single_word": false,
|
| 1801 |
+
"special": true
|
| 1802 |
+
},
|
| 1803 |
+
"128225": {
|
| 1804 |
+
"content": "<|reserved_special_token_217|>",
|
| 1805 |
+
"lstrip": false,
|
| 1806 |
+
"normalized": false,
|
| 1807 |
+
"rstrip": false,
|
| 1808 |
+
"single_word": false,
|
| 1809 |
+
"special": true
|
| 1810 |
+
},
|
| 1811 |
+
"128226": {
|
| 1812 |
+
"content": "<|reserved_special_token_218|>",
|
| 1813 |
+
"lstrip": false,
|
| 1814 |
+
"normalized": false,
|
| 1815 |
+
"rstrip": false,
|
| 1816 |
+
"single_word": false,
|
| 1817 |
+
"special": true
|
| 1818 |
+
},
|
| 1819 |
+
"128227": {
|
| 1820 |
+
"content": "<|reserved_special_token_219|>",
|
| 1821 |
+
"lstrip": false,
|
| 1822 |
+
"normalized": false,
|
| 1823 |
+
"rstrip": false,
|
| 1824 |
+
"single_word": false,
|
| 1825 |
+
"special": true
|
| 1826 |
+
},
|
| 1827 |
+
"128228": {
|
| 1828 |
+
"content": "<|reserved_special_token_220|>",
|
| 1829 |
+
"lstrip": false,
|
| 1830 |
+
"normalized": false,
|
| 1831 |
+
"rstrip": false,
|
| 1832 |
+
"single_word": false,
|
| 1833 |
+
"special": true
|
| 1834 |
+
},
|
| 1835 |
+
"128229": {
|
| 1836 |
+
"content": "<|reserved_special_token_221|>",
|
| 1837 |
+
"lstrip": false,
|
| 1838 |
+
"normalized": false,
|
| 1839 |
+
"rstrip": false,
|
| 1840 |
+
"single_word": false,
|
| 1841 |
+
"special": true
|
| 1842 |
+
},
|
| 1843 |
+
"128230": {
|
| 1844 |
+
"content": "<|reserved_special_token_222|>",
|
| 1845 |
+
"lstrip": false,
|
| 1846 |
+
"normalized": false,
|
| 1847 |
+
"rstrip": false,
|
| 1848 |
+
"single_word": false,
|
| 1849 |
+
"special": true
|
| 1850 |
+
},
|
| 1851 |
+
"128231": {
|
| 1852 |
+
"content": "<|reserved_special_token_223|>",
|
| 1853 |
+
"lstrip": false,
|
| 1854 |
+
"normalized": false,
|
| 1855 |
+
"rstrip": false,
|
| 1856 |
+
"single_word": false,
|
| 1857 |
+
"special": true
|
| 1858 |
+
},
|
| 1859 |
+
"128232": {
|
| 1860 |
+
"content": "<|reserved_special_token_224|>",
|
| 1861 |
+
"lstrip": false,
|
| 1862 |
+
"normalized": false,
|
| 1863 |
+
"rstrip": false,
|
| 1864 |
+
"single_word": false,
|
| 1865 |
+
"special": true
|
| 1866 |
+
},
|
| 1867 |
+
"128233": {
|
| 1868 |
+
"content": "<|reserved_special_token_225|>",
|
| 1869 |
+
"lstrip": false,
|
| 1870 |
+
"normalized": false,
|
| 1871 |
+
"rstrip": false,
|
| 1872 |
+
"single_word": false,
|
| 1873 |
+
"special": true
|
| 1874 |
+
},
|
| 1875 |
+
"128234": {
|
| 1876 |
+
"content": "<|reserved_special_token_226|>",
|
| 1877 |
+
"lstrip": false,
|
| 1878 |
+
"normalized": false,
|
| 1879 |
+
"rstrip": false,
|
| 1880 |
+
"single_word": false,
|
| 1881 |
+
"special": true
|
| 1882 |
+
},
|
| 1883 |
+
"128235": {
|
| 1884 |
+
"content": "<|reserved_special_token_227|>",
|
| 1885 |
+
"lstrip": false,
|
| 1886 |
+
"normalized": false,
|
| 1887 |
+
"rstrip": false,
|
| 1888 |
+
"single_word": false,
|
| 1889 |
+
"special": true
|
| 1890 |
+
},
|
| 1891 |
+
"128236": {
|
| 1892 |
+
"content": "<|reserved_special_token_228|>",
|
| 1893 |
+
"lstrip": false,
|
| 1894 |
+
"normalized": false,
|
| 1895 |
+
"rstrip": false,
|
| 1896 |
+
"single_word": false,
|
| 1897 |
+
"special": true
|
| 1898 |
+
},
|
| 1899 |
+
"128237": {
|
| 1900 |
+
"content": "<|reserved_special_token_229|>",
|
| 1901 |
+
"lstrip": false,
|
| 1902 |
+
"normalized": false,
|
| 1903 |
+
"rstrip": false,
|
| 1904 |
+
"single_word": false,
|
| 1905 |
+
"special": true
|
| 1906 |
+
},
|
| 1907 |
+
"128238": {
|
| 1908 |
+
"content": "<|reserved_special_token_230|>",
|
| 1909 |
+
"lstrip": false,
|
| 1910 |
+
"normalized": false,
|
| 1911 |
+
"rstrip": false,
|
| 1912 |
+
"single_word": false,
|
| 1913 |
+
"special": true
|
| 1914 |
+
},
|
| 1915 |
+
"128239": {
|
| 1916 |
+
"content": "<|reserved_special_token_231|>",
|
| 1917 |
+
"lstrip": false,
|
| 1918 |
+
"normalized": false,
|
| 1919 |
+
"rstrip": false,
|
| 1920 |
+
"single_word": false,
|
| 1921 |
+
"special": true
|
| 1922 |
+
},
|
| 1923 |
+
"128240": {
|
| 1924 |
+
"content": "<|reserved_special_token_232|>",
|
| 1925 |
+
"lstrip": false,
|
| 1926 |
+
"normalized": false,
|
| 1927 |
+
"rstrip": false,
|
| 1928 |
+
"single_word": false,
|
| 1929 |
+
"special": true
|
| 1930 |
+
},
|
| 1931 |
+
"128241": {
|
| 1932 |
+
"content": "<|reserved_special_token_233|>",
|
| 1933 |
+
"lstrip": false,
|
| 1934 |
+
"normalized": false,
|
| 1935 |
+
"rstrip": false,
|
| 1936 |
+
"single_word": false,
|
| 1937 |
+
"special": true
|
| 1938 |
+
},
|
| 1939 |
+
"128242": {
|
| 1940 |
+
"content": "<|reserved_special_token_234|>",
|
| 1941 |
+
"lstrip": false,
|
| 1942 |
+
"normalized": false,
|
| 1943 |
+
"rstrip": false,
|
| 1944 |
+
"single_word": false,
|
| 1945 |
+
"special": true
|
| 1946 |
+
},
|
| 1947 |
+
"128243": {
|
| 1948 |
+
"content": "<|reserved_special_token_235|>",
|
| 1949 |
+
"lstrip": false,
|
| 1950 |
+
"normalized": false,
|
| 1951 |
+
"rstrip": false,
|
| 1952 |
+
"single_word": false,
|
| 1953 |
+
"special": true
|
| 1954 |
+
},
|
| 1955 |
+
"128244": {
|
| 1956 |
+
"content": "<|reserved_special_token_236|>",
|
| 1957 |
+
"lstrip": false,
|
| 1958 |
+
"normalized": false,
|
| 1959 |
+
"rstrip": false,
|
| 1960 |
+
"single_word": false,
|
| 1961 |
+
"special": true
|
| 1962 |
+
},
|
| 1963 |
+
"128245": {
|
| 1964 |
+
"content": "<|reserved_special_token_237|>",
|
| 1965 |
+
"lstrip": false,
|
| 1966 |
+
"normalized": false,
|
| 1967 |
+
"rstrip": false,
|
| 1968 |
+
"single_word": false,
|
| 1969 |
+
"special": true
|
| 1970 |
+
},
|
| 1971 |
+
"128246": {
|
| 1972 |
+
"content": "<|reserved_special_token_238|>",
|
| 1973 |
+
"lstrip": false,
|
| 1974 |
+
"normalized": false,
|
| 1975 |
+
"rstrip": false,
|
| 1976 |
+
"single_word": false,
|
| 1977 |
+
"special": true
|
| 1978 |
+
},
|
| 1979 |
+
"128247": {
|
| 1980 |
+
"content": "<|reserved_special_token_239|>",
|
| 1981 |
+
"lstrip": false,
|
| 1982 |
+
"normalized": false,
|
| 1983 |
+
"rstrip": false,
|
| 1984 |
+
"single_word": false,
|
| 1985 |
+
"special": true
|
| 1986 |
+
},
|
| 1987 |
+
"128248": {
|
| 1988 |
+
"content": "<|reserved_special_token_240|>",
|
| 1989 |
+
"lstrip": false,
|
| 1990 |
+
"normalized": false,
|
| 1991 |
+
"rstrip": false,
|
| 1992 |
+
"single_word": false,
|
| 1993 |
+
"special": true
|
| 1994 |
+
},
|
| 1995 |
+
"128249": {
|
| 1996 |
+
"content": "<|reserved_special_token_241|>",
|
| 1997 |
+
"lstrip": false,
|
| 1998 |
+
"normalized": false,
|
| 1999 |
+
"rstrip": false,
|
| 2000 |
+
"single_word": false,
|
| 2001 |
+
"special": true
|
| 2002 |
+
},
|
| 2003 |
+
"128250": {
|
| 2004 |
+
"content": "<|reserved_special_token_242|>",
|
| 2005 |
+
"lstrip": false,
|
| 2006 |
+
"normalized": false,
|
| 2007 |
+
"rstrip": false,
|
| 2008 |
+
"single_word": false,
|
| 2009 |
+
"special": true
|
| 2010 |
+
},
|
| 2011 |
+
"128251": {
|
| 2012 |
+
"content": "<|reserved_special_token_243|>",
|
| 2013 |
+
"lstrip": false,
|
| 2014 |
+
"normalized": false,
|
| 2015 |
+
"rstrip": false,
|
| 2016 |
+
"single_word": false,
|
| 2017 |
+
"special": true
|
| 2018 |
+
},
|
| 2019 |
+
"128252": {
|
| 2020 |
+
"content": "<|reserved_special_token_244|>",
|
| 2021 |
+
"lstrip": false,
|
| 2022 |
+
"normalized": false,
|
| 2023 |
+
"rstrip": false,
|
| 2024 |
+
"single_word": false,
|
| 2025 |
+
"special": true
|
| 2026 |
+
},
|
| 2027 |
+
"128253": {
|
| 2028 |
+
"content": "<|reserved_special_token_245|>",
|
| 2029 |
+
"lstrip": false,
|
| 2030 |
+
"normalized": false,
|
| 2031 |
+
"rstrip": false,
|
| 2032 |
+
"single_word": false,
|
| 2033 |
+
"special": true
|
| 2034 |
+
},
|
| 2035 |
+
"128254": {
|
| 2036 |
+
"content": "<|reserved_special_token_246|>",
|
| 2037 |
+
"lstrip": false,
|
| 2038 |
+
"normalized": false,
|
| 2039 |
+
"rstrip": false,
|
| 2040 |
+
"single_word": false,
|
| 2041 |
+
"special": true
|
| 2042 |
+
},
|
| 2043 |
+
"128255": {
|
| 2044 |
+
"content": "<|reserved_special_token_247|>",
|
| 2045 |
+
"lstrip": false,
|
| 2046 |
+
"normalized": false,
|
| 2047 |
+
"rstrip": false,
|
| 2048 |
+
"single_word": false,
|
| 2049 |
+
"special": true
|
| 2050 |
+
}
|
| 2051 |
+
},
|
| 2052 |
+
"bos_token": "<|begin_of_text|>",
|
| 2053 |
+
"chat_template": "{{- bos_token }}\n{%- if custom_tools is defined %}\n {%- set tools = custom_tools %}\n{%- endif %}\n{%- if not tools_in_user_message is defined %}\n {%- set tools_in_user_message = true %}\n{%- endif %}\n{%- if not date_string is defined %}\n {%- if strftime_now is defined %}\n {%- set date_string = strftime_now(\"%d %b %Y\") %}\n {%- else %}\n {%- set date_string = \"26 Jul 2024\" %}\n {%- endif %}\n{%- endif %}\n{%- if not tools is defined %}\n {%- set tools = none %}\n{%- endif %}\n\n{#- This block extracts the system message, so we can slot it into the right place. #}\n{%- if messages[0]['role'] == 'system' %}\n {%- set system_message = messages[0]['content']|trim %}\n {%- set messages = messages[1:] %}\n{%- else %}\n {%- set system_message = \"You are a helpful AI assistant. Please answer the user's questions kindly. 당신은 유능한 AI 어시스턴트 입니다. 사용자의 질문에 대해 친절하게 답변해주세요.\" %}\n{%- endif %}\n\n{#- System message #}\n{{- \"<|start_header_id|>system<|end_header_id|>\\n\\n\" }}\n{%- if tools is not none %}\n {{- \"Environment: ipython\\n\" }}\n{%- endif %}\n{{- \"Cutting Knowledge Date: December 2023\\n\" }}\n{{- \"Today Date: \" + date_string + \"\\n\\n\" }}\n{%- if tools is not none and not tools_in_user_message %}\n {{- \"You have access to the following functions. To call a function, please respond with JSON for a function call.\" }}\n {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n {{- \"Do not use variables.\\n\\n\" }}\n {%- for t in tools %}\n {{- t | tojson(indent=4) }}\n {{- \"\\n\\n\" }}\n {%- endfor %}\n{%- endif %}\n{{- system_message }}\n{{- \"<|eot_id|>\" }}\n\n{#- Custom tools are passed in a user message with some extra guidance #}\n{%- if tools_in_user_message and not tools is none %}\n {#- Extract the first user message so we can plug it in here #}\n {%- if messages | length != 0 %}\n {%- set first_user_message = messages[0]['content']|trim %}\n {%- set messages = messages[1:] %}\n {%- else %}\n {{- raise_exception(\"Cannot put tools in the first user message when there's no first user message!\") }}\n{%- endif %}\n {{- '<|start_header_id|>user<|end_header_id|>\\n\\n' -}}\n {{- \"Given the following functions, please respond with a JSON for a function call \" }}\n {{- \"with its proper arguments that best answers the given prompt.\\n\\n\" }}\n {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n {{- \"Do not use variables.\\n\\n\" }}\n {%- for t in tools %}\n {{- t | tojson(indent=4) }}\n {{- \"\\n\\n\" }}\n {%- endfor %}\n {{- first_user_message + \"<|eot_id|>\"}}\n{%- endif %}\n\n{%- for message in messages %}\n {%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %}\n {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\\n\\n'+ message['content'] | trim + '<|eot_id|>' }}\n {%- elif 'tool_calls' in message %}\n {%- if not message.tool_calls|length == 1 %}\n {{- raise_exception(\"This model only supports single tool-calls at once!\") }}\n {%- endif %}\n {%- set tool_call = message.tool_calls[0].function %}\n {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' -}}\n {{- '{\"name\": \"' + tool_call.name + '\", ' }}\n {{- '\"parameters\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- \"}\" }}\n {{- \"<|eot_id|>\" }}\n {%- elif message.role == \"tool\" or message.role == \"ipython\" %}\n {{- \"<|start_header_id|>ipython<|end_header_id|>\\n\\n\" }}\n {%- if message.content is mapping or message.content is iterable %}\n {{- message.content | tojson }}\n {%- else %}\n {{- message.content }}\n {%- endif %}\n {{- \"<|eot_id|>\" }}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' }}\n{%- endif %}\n",
|
| 2054 |
+
"clean_up_tokenization_spaces": true,
|
| 2055 |
+
"eos_token": "<|eot_id|>",
|
| 2056 |
+
"model_input_names": [
|
| 2057 |
+
"input_ids",
|
| 2058 |
+
"attention_mask"
|
| 2059 |
+
],
|
| 2060 |
+
"model_max_length": 131072,
|
| 2061 |
+
"pad_token": "<|finetune_right_pad_id|>",
|
| 2062 |
+
"padding_side": "right",
|
| 2063 |
+
"tokenizer_class": "PreTrainedTokenizerFast"
|
| 2064 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,2958 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.20996317267417908,
|
| 3 |
+
"best_model_checkpoint": "./model_outputs/checkpoint-9750",
|
| 4 |
+
"epoch": 1.9240878505041734,
|
| 5 |
+
"eval_steps": 50,
|
| 6 |
+
"global_step": 9750,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.009866408824516053,
|
| 13 |
+
"grad_norm": 0.5440589189529419,
|
| 14 |
+
"learning_rate": 8.333333333333334e-06,
|
| 15 |
+
"loss": 1.8768,
|
| 16 |
+
"step": 50
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.009866408824516053,
|
| 20 |
+
"eval_loss": 1.8065277338027954,
|
| 21 |
+
"eval_runtime": 0.199,
|
| 22 |
+
"eval_samples_per_second": 25.12,
|
| 23 |
+
"eval_steps_per_second": 5.024,
|
| 24 |
+
"step": 50
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.019732817649032106,
|
| 28 |
+
"grad_norm": 0.5126028656959534,
|
| 29 |
+
"learning_rate": 1.6666666666666667e-05,
|
| 30 |
+
"loss": 1.6013,
|
| 31 |
+
"step": 100
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.019732817649032106,
|
| 35 |
+
"eval_loss": 1.4184890985488892,
|
| 36 |
+
"eval_runtime": 0.1842,
|
| 37 |
+
"eval_samples_per_second": 27.145,
|
| 38 |
+
"eval_steps_per_second": 5.429,
|
| 39 |
+
"step": 100
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.02959922647354816,
|
| 43 |
+
"grad_norm": 0.8953598141670227,
|
| 44 |
+
"learning_rate": 2.5e-05,
|
| 45 |
+
"loss": 1.3394,
|
| 46 |
+
"step": 150
|
| 47 |
+
},
|
| 48 |
+
{
|
| 49 |
+
"epoch": 0.02959922647354816,
|
| 50 |
+
"eval_loss": 1.2211127281188965,
|
| 51 |
+
"eval_runtime": 0.1845,
|
| 52 |
+
"eval_samples_per_second": 27.095,
|
| 53 |
+
"eval_steps_per_second": 5.419,
|
| 54 |
+
"step": 150
|
| 55 |
+
},
|
| 56 |
+
{
|
| 57 |
+
"epoch": 0.03946563529806421,
|
| 58 |
+
"grad_norm": 1.0633267164230347,
|
| 59 |
+
"learning_rate": 3.3333333333333335e-05,
|
| 60 |
+
"loss": 1.2225,
|
| 61 |
+
"step": 200
|
| 62 |
+
},
|
| 63 |
+
{
|
| 64 |
+
"epoch": 0.03946563529806421,
|
| 65 |
+
"eval_loss": 1.1311841011047363,
|
| 66 |
+
"eval_runtime": 0.1844,
|
| 67 |
+
"eval_samples_per_second": 27.117,
|
| 68 |
+
"eval_steps_per_second": 5.423,
|
| 69 |
+
"step": 200
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 0.049332044122580264,
|
| 73 |
+
"grad_norm": 1.340325951576233,
|
| 74 |
+
"learning_rate": 4.166666666666667e-05,
|
| 75 |
+
"loss": 1.1527,
|
| 76 |
+
"step": 250
|
| 77 |
+
},
|
| 78 |
+
{
|
| 79 |
+
"epoch": 0.049332044122580264,
|
| 80 |
+
"eval_loss": 1.0357060432434082,
|
| 81 |
+
"eval_runtime": 0.1844,
|
| 82 |
+
"eval_samples_per_second": 27.116,
|
| 83 |
+
"eval_steps_per_second": 5.423,
|
| 84 |
+
"step": 250
|
| 85 |
+
},
|
| 86 |
+
{
|
| 87 |
+
"epoch": 0.05919845294709632,
|
| 88 |
+
"grad_norm": 1.1488324403762817,
|
| 89 |
+
"learning_rate": 5e-05,
|
| 90 |
+
"loss": 1.098,
|
| 91 |
+
"step": 300
|
| 92 |
+
},
|
| 93 |
+
{
|
| 94 |
+
"epoch": 0.05919845294709632,
|
| 95 |
+
"eval_loss": 0.9791008830070496,
|
| 96 |
+
"eval_runtime": 0.1852,
|
| 97 |
+
"eval_samples_per_second": 27.002,
|
| 98 |
+
"eval_steps_per_second": 5.4,
|
| 99 |
+
"step": 300
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 0.06906486177161236,
|
| 103 |
+
"grad_norm": 1.3122004270553589,
|
| 104 |
+
"learning_rate": 5.833333333333334e-05,
|
| 105 |
+
"loss": 1.0511,
|
| 106 |
+
"step": 350
|
| 107 |
+
},
|
| 108 |
+
{
|
| 109 |
+
"epoch": 0.06906486177161236,
|
| 110 |
+
"eval_loss": 0.9438408017158508,
|
| 111 |
+
"eval_runtime": 0.1844,
|
| 112 |
+
"eval_samples_per_second": 27.119,
|
| 113 |
+
"eval_steps_per_second": 5.424,
|
| 114 |
+
"step": 350
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.07893127059612842,
|
| 118 |
+
"grad_norm": 1.4071924686431885,
|
| 119 |
+
"learning_rate": 6.666666666666667e-05,
|
| 120 |
+
"loss": 1.0327,
|
| 121 |
+
"step": 400
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.07893127059612842,
|
| 125 |
+
"eval_loss": 0.9280341863632202,
|
| 126 |
+
"eval_runtime": 0.1839,
|
| 127 |
+
"eval_samples_per_second": 27.193,
|
| 128 |
+
"eval_steps_per_second": 5.439,
|
| 129 |
+
"step": 400
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.08879767942064447,
|
| 133 |
+
"grad_norm": 1.447715163230896,
|
| 134 |
+
"learning_rate": 7.500000000000001e-05,
|
| 135 |
+
"loss": 0.9924,
|
| 136 |
+
"step": 450
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.08879767942064447,
|
| 140 |
+
"eval_loss": 0.9004782438278198,
|
| 141 |
+
"eval_runtime": 0.1846,
|
| 142 |
+
"eval_samples_per_second": 27.09,
|
| 143 |
+
"eval_steps_per_second": 5.418,
|
| 144 |
+
"step": 450
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 0.09866408824516053,
|
| 148 |
+
"grad_norm": 1.6754121780395508,
|
| 149 |
+
"learning_rate": 8.333333333333334e-05,
|
| 150 |
+
"loss": 0.9313,
|
| 151 |
+
"step": 500
|
| 152 |
+
},
|
| 153 |
+
{
|
| 154 |
+
"epoch": 0.09866408824516053,
|
| 155 |
+
"eval_loss": 0.7985298037528992,
|
| 156 |
+
"eval_runtime": 0.1849,
|
| 157 |
+
"eval_samples_per_second": 27.04,
|
| 158 |
+
"eval_steps_per_second": 5.408,
|
| 159 |
+
"step": 500
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 0.10853049706967657,
|
| 163 |
+
"grad_norm": 1.7146815061569214,
|
| 164 |
+
"learning_rate": 9.166666666666667e-05,
|
| 165 |
+
"loss": 0.7311,
|
| 166 |
+
"step": 550
|
| 167 |
+
},
|
| 168 |
+
{
|
| 169 |
+
"epoch": 0.10853049706967657,
|
| 170 |
+
"eval_loss": 0.5294134020805359,
|
| 171 |
+
"eval_runtime": 0.1845,
|
| 172 |
+
"eval_samples_per_second": 27.107,
|
| 173 |
+
"eval_steps_per_second": 5.421,
|
| 174 |
+
"step": 550
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 0.11839690589419263,
|
| 178 |
+
"grad_norm": 1.3303102254867554,
|
| 179 |
+
"learning_rate": 0.0001,
|
| 180 |
+
"loss": 0.5309,
|
| 181 |
+
"step": 600
|
| 182 |
+
},
|
| 183 |
+
{
|
| 184 |
+
"epoch": 0.11839690589419263,
|
| 185 |
+
"eval_loss": 0.42509689927101135,
|
| 186 |
+
"eval_runtime": 0.1847,
|
| 187 |
+
"eval_samples_per_second": 27.075,
|
| 188 |
+
"eval_steps_per_second": 5.415,
|
| 189 |
+
"step": 600
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 0.1282633147187087,
|
| 193 |
+
"grad_norm": 0.9372690320014954,
|
| 194 |
+
"learning_rate": 0.00010833333333333333,
|
| 195 |
+
"loss": 0.4645,
|
| 196 |
+
"step": 650
|
| 197 |
+
},
|
| 198 |
+
{
|
| 199 |
+
"epoch": 0.1282633147187087,
|
| 200 |
+
"eval_loss": 0.37647953629493713,
|
| 201 |
+
"eval_runtime": 0.1851,
|
| 202 |
+
"eval_samples_per_second": 27.009,
|
| 203 |
+
"eval_steps_per_second": 5.402,
|
| 204 |
+
"step": 650
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 0.13812972354322473,
|
| 208 |
+
"grad_norm": 0.9396585822105408,
|
| 209 |
+
"learning_rate": 0.00011666666666666668,
|
| 210 |
+
"loss": 0.4258,
|
| 211 |
+
"step": 700
|
| 212 |
+
},
|
| 213 |
+
{
|
| 214 |
+
"epoch": 0.13812972354322473,
|
| 215 |
+
"eval_loss": 0.3551653325557709,
|
| 216 |
+
"eval_runtime": 0.1853,
|
| 217 |
+
"eval_samples_per_second": 26.982,
|
| 218 |
+
"eval_steps_per_second": 5.396,
|
| 219 |
+
"step": 700
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.14799613236774078,
|
| 223 |
+
"grad_norm": 0.6549014449119568,
|
| 224 |
+
"learning_rate": 0.000125,
|
| 225 |
+
"loss": 0.4101,
|
| 226 |
+
"step": 750
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.14799613236774078,
|
| 230 |
+
"eval_loss": 0.3371706008911133,
|
| 231 |
+
"eval_runtime": 0.1856,
|
| 232 |
+
"eval_samples_per_second": 26.941,
|
| 233 |
+
"eval_steps_per_second": 5.388,
|
| 234 |
+
"step": 750
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.15786254119225684,
|
| 238 |
+
"grad_norm": 0.5201817750930786,
|
| 239 |
+
"learning_rate": 0.00013333333333333334,
|
| 240 |
+
"loss": 0.3877,
|
| 241 |
+
"step": 800
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 0.15786254119225684,
|
| 245 |
+
"eval_loss": 0.3209473192691803,
|
| 246 |
+
"eval_runtime": 0.1844,
|
| 247 |
+
"eval_samples_per_second": 27.12,
|
| 248 |
+
"eval_steps_per_second": 5.424,
|
| 249 |
+
"step": 800
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 0.1677289500167729,
|
| 253 |
+
"grad_norm": 0.44689691066741943,
|
| 254 |
+
"learning_rate": 0.00014166666666666668,
|
| 255 |
+
"loss": 0.3856,
|
| 256 |
+
"step": 850
|
| 257 |
+
},
|
| 258 |
+
{
|
| 259 |
+
"epoch": 0.1677289500167729,
|
| 260 |
+
"eval_loss": 0.3198350965976715,
|
| 261 |
+
"eval_runtime": 0.1841,
|
| 262 |
+
"eval_samples_per_second": 27.157,
|
| 263 |
+
"eval_steps_per_second": 5.431,
|
| 264 |
+
"step": 850
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 0.17759535884128894,
|
| 268 |
+
"grad_norm": 0.4665811359882355,
|
| 269 |
+
"learning_rate": 0.00015000000000000001,
|
| 270 |
+
"loss": 0.3815,
|
| 271 |
+
"step": 900
|
| 272 |
+
},
|
| 273 |
+
{
|
| 274 |
+
"epoch": 0.17759535884128894,
|
| 275 |
+
"eval_loss": 0.31239432096481323,
|
| 276 |
+
"eval_runtime": 0.1858,
|
| 277 |
+
"eval_samples_per_second": 26.91,
|
| 278 |
+
"eval_steps_per_second": 5.382,
|
| 279 |
+
"step": 900
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 0.187461767665805,
|
| 283 |
+
"grad_norm": 0.40847715735435486,
|
| 284 |
+
"learning_rate": 0.00015833333333333332,
|
| 285 |
+
"loss": 0.3678,
|
| 286 |
+
"step": 950
|
| 287 |
+
},
|
| 288 |
+
{
|
| 289 |
+
"epoch": 0.187461767665805,
|
| 290 |
+
"eval_loss": 0.31479328870773315,
|
| 291 |
+
"eval_runtime": 0.1847,
|
| 292 |
+
"eval_samples_per_second": 27.067,
|
| 293 |
+
"eval_steps_per_second": 5.413,
|
| 294 |
+
"step": 950
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 0.19732817649032106,
|
| 298 |
+
"grad_norm": 0.4807054400444031,
|
| 299 |
+
"learning_rate": 0.0001666666666666667,
|
| 300 |
+
"loss": 0.3663,
|
| 301 |
+
"step": 1000
|
| 302 |
+
},
|
| 303 |
+
{
|
| 304 |
+
"epoch": 0.19732817649032106,
|
| 305 |
+
"eval_loss": 0.317302405834198,
|
| 306 |
+
"eval_runtime": 0.1849,
|
| 307 |
+
"eval_samples_per_second": 27.036,
|
| 308 |
+
"eval_steps_per_second": 5.407,
|
| 309 |
+
"step": 1000
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 0.20719458531483712,
|
| 313 |
+
"grad_norm": 0.40431880950927734,
|
| 314 |
+
"learning_rate": 0.000175,
|
| 315 |
+
"loss": 0.3618,
|
| 316 |
+
"step": 1050
|
| 317 |
+
},
|
| 318 |
+
{
|
| 319 |
+
"epoch": 0.20719458531483712,
|
| 320 |
+
"eval_loss": 0.30631712079048157,
|
| 321 |
+
"eval_runtime": 0.1843,
|
| 322 |
+
"eval_samples_per_second": 27.129,
|
| 323 |
+
"eval_steps_per_second": 5.426,
|
| 324 |
+
"step": 1050
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.21706099413935315,
|
| 328 |
+
"grad_norm": 0.3184848725795746,
|
| 329 |
+
"learning_rate": 0.00018333333333333334,
|
| 330 |
+
"loss": 0.3585,
|
| 331 |
+
"step": 1100
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.21706099413935315,
|
| 335 |
+
"eval_loss": 0.3047851026058197,
|
| 336 |
+
"eval_runtime": 0.1842,
|
| 337 |
+
"eval_samples_per_second": 27.139,
|
| 338 |
+
"eval_steps_per_second": 5.428,
|
| 339 |
+
"step": 1100
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.2269274029638692,
|
| 343 |
+
"grad_norm": 0.29751336574554443,
|
| 344 |
+
"learning_rate": 0.00019166666666666667,
|
| 345 |
+
"loss": 0.3545,
|
| 346 |
+
"step": 1150
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.2269274029638692,
|
| 350 |
+
"eval_loss": 0.30102381110191345,
|
| 351 |
+
"eval_runtime": 0.1859,
|
| 352 |
+
"eval_samples_per_second": 26.901,
|
| 353 |
+
"eval_steps_per_second": 5.38,
|
| 354 |
+
"step": 1150
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 0.23679381178838527,
|
| 358 |
+
"grad_norm": 0.3572952449321747,
|
| 359 |
+
"learning_rate": 0.0002,
|
| 360 |
+
"loss": 0.354,
|
| 361 |
+
"step": 1200
|
| 362 |
+
},
|
| 363 |
+
{
|
| 364 |
+
"epoch": 0.23679381178838527,
|
| 365 |
+
"eval_loss": 0.2969129979610443,
|
| 366 |
+
"eval_runtime": 0.185,
|
| 367 |
+
"eval_samples_per_second": 27.03,
|
| 368 |
+
"eval_steps_per_second": 5.406,
|
| 369 |
+
"step": 1200
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 0.24666022061290133,
|
| 373 |
+
"grad_norm": 0.397197961807251,
|
| 374 |
+
"learning_rate": 0.00019998454365958754,
|
| 375 |
+
"loss": 0.3505,
|
| 376 |
+
"step": 1250
|
| 377 |
+
},
|
| 378 |
+
{
|
| 379 |
+
"epoch": 0.24666022061290133,
|
| 380 |
+
"eval_loss": 0.2986981272697449,
|
| 381 |
+
"eval_runtime": 0.1868,
|
| 382 |
+
"eval_samples_per_second": 26.768,
|
| 383 |
+
"eval_steps_per_second": 5.354,
|
| 384 |
+
"step": 1250
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 0.2565266294374174,
|
| 388 |
+
"grad_norm": 0.31810271739959717,
|
| 389 |
+
"learning_rate": 0.00019993817941631932,
|
| 390 |
+
"loss": 0.3469,
|
| 391 |
+
"step": 1300
|
| 392 |
+
},
|
| 393 |
+
{
|
| 394 |
+
"epoch": 0.2565266294374174,
|
| 395 |
+
"eval_loss": 0.2904866635799408,
|
| 396 |
+
"eval_runtime": 0.361,
|
| 397 |
+
"eval_samples_per_second": 13.851,
|
| 398 |
+
"eval_steps_per_second": 2.77,
|
| 399 |
+
"step": 1300
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 0.26639303826193345,
|
| 403 |
+
"grad_norm": 0.3378036618232727,
|
| 404 |
+
"learning_rate": 0.00019986092160262587,
|
| 405 |
+
"loss": 0.3465,
|
| 406 |
+
"step": 1350
|
| 407 |
+
},
|
| 408 |
+
{
|
| 409 |
+
"epoch": 0.26639303826193345,
|
| 410 |
+
"eval_loss": 0.29250431060791016,
|
| 411 |
+
"eval_runtime": 0.1881,
|
| 412 |
+
"eval_samples_per_second": 26.582,
|
| 413 |
+
"eval_steps_per_second": 5.316,
|
| 414 |
+
"step": 1350
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"epoch": 0.27625944708644945,
|
| 418 |
+
"grad_norm": 0.25885072350502014,
|
| 419 |
+
"learning_rate": 0.00019975279410096856,
|
| 420 |
+
"loss": 0.3427,
|
| 421 |
+
"step": 1400
|
| 422 |
+
},
|
| 423 |
+
{
|
| 424 |
+
"epoch": 0.27625944708644945,
|
| 425 |
+
"eval_loss": 0.2970002293586731,
|
| 426 |
+
"eval_runtime": 0.1858,
|
| 427 |
+
"eval_samples_per_second": 26.911,
|
| 428 |
+
"eval_steps_per_second": 5.382,
|
| 429 |
+
"step": 1400
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.2861258559109655,
|
| 433 |
+
"grad_norm": 0.37681177258491516,
|
| 434 |
+
"learning_rate": 0.00019961383033645683,
|
| 435 |
+
"loss": 0.3423,
|
| 436 |
+
"step": 1450
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 0.2861258559109655,
|
| 440 |
+
"eval_loss": 0.28687533736228943,
|
| 441 |
+
"eval_runtime": 0.1869,
|
| 442 |
+
"eval_samples_per_second": 26.751,
|
| 443 |
+
"eval_steps_per_second": 5.35,
|
| 444 |
+
"step": 1450
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 0.29599226473548157,
|
| 448 |
+
"grad_norm": 0.33231380581855774,
|
| 449 |
+
"learning_rate": 0.00019944407326651575,
|
| 450 |
+
"loss": 0.3388,
|
| 451 |
+
"step": 1500
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 0.29599226473548157,
|
| 455 |
+
"eval_loss": 0.28474920988082886,
|
| 456 |
+
"eval_runtime": 0.1871,
|
| 457 |
+
"eval_samples_per_second": 26.718,
|
| 458 |
+
"eval_steps_per_second": 5.344,
|
| 459 |
+
"step": 1500
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 0.30585867355999763,
|
| 463 |
+
"grad_norm": 0.3391518294811249,
|
| 464 |
+
"learning_rate": 0.00019924357536760644,
|
| 465 |
+
"loss": 0.3316,
|
| 466 |
+
"step": 1550
|
| 467 |
+
},
|
| 468 |
+
{
|
| 469 |
+
"epoch": 0.30585867355999763,
|
| 470 |
+
"eval_loss": 0.27619096636772156,
|
| 471 |
+
"eval_runtime": 0.2,
|
| 472 |
+
"eval_samples_per_second": 25.0,
|
| 473 |
+
"eval_steps_per_second": 5.0,
|
| 474 |
+
"step": 1550
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 0.3157250823845137,
|
| 478 |
+
"grad_norm": 0.3423280715942383,
|
| 479 |
+
"learning_rate": 0.0001990123986190045,
|
| 480 |
+
"loss": 0.3376,
|
| 481 |
+
"step": 1600
|
| 482 |
+
},
|
| 483 |
+
{
|
| 484 |
+
"epoch": 0.3157250823845137,
|
| 485 |
+
"eval_loss": 0.2841600179672241,
|
| 486 |
+
"eval_runtime": 0.1876,
|
| 487 |
+
"eval_samples_per_second": 26.647,
|
| 488 |
+
"eval_steps_per_second": 5.329,
|
| 489 |
+
"step": 1600
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 0.32559149120902975,
|
| 493 |
+
"grad_norm": 0.37309399247169495,
|
| 494 |
+
"learning_rate": 0.00019875061448364033,
|
| 495 |
+
"loss": 0.3357,
|
| 496 |
+
"step": 1650
|
| 497 |
+
},
|
| 498 |
+
{
|
| 499 |
+
"epoch": 0.32559149120902975,
|
| 500 |
+
"eval_loss": 0.2811121344566345,
|
| 501 |
+
"eval_runtime": 0.1875,
|
| 502 |
+
"eval_samples_per_second": 26.669,
|
| 503 |
+
"eval_steps_per_second": 5.334,
|
| 504 |
+
"step": 1650
|
| 505 |
+
},
|
| 506 |
+
{
|
| 507 |
+
"epoch": 0.3354579000335458,
|
| 508 |
+
"grad_norm": 0.33649030327796936,
|
| 509 |
+
"learning_rate": 0.00019845830388600822,
|
| 510 |
+
"loss": 0.3294,
|
| 511 |
+
"step": 1700
|
| 512 |
+
},
|
| 513 |
+
{
|
| 514 |
+
"epoch": 0.3354579000335458,
|
| 515 |
+
"eval_loss": 0.27847614884376526,
|
| 516 |
+
"eval_runtime": 0.1869,
|
| 517 |
+
"eval_samples_per_second": 26.754,
|
| 518 |
+
"eval_steps_per_second": 5.351,
|
| 519 |
+
"step": 1700
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 0.34532430885806187,
|
| 523 |
+
"grad_norm": 0.38383936882019043,
|
| 524 |
+
"learning_rate": 0.00019813555718715012,
|
| 525 |
+
"loss": 0.334,
|
| 526 |
+
"step": 1750
|
| 527 |
+
},
|
| 528 |
+
{
|
| 529 |
+
"epoch": 0.34532430885806187,
|
| 530 |
+
"eval_loss": 0.2873836159706116,
|
| 531 |
+
"eval_runtime": 0.1865,
|
| 532 |
+
"eval_samples_per_second": 26.806,
|
| 533 |
+
"eval_steps_per_second": 5.361,
|
| 534 |
+
"step": 1750
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 0.3551907176825779,
|
| 538 |
+
"grad_norm": 0.3089899718761444,
|
| 539 |
+
"learning_rate": 0.000197782474156723,
|
| 540 |
+
"loss": 0.3275,
|
| 541 |
+
"step": 1800
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 0.3551907176825779,
|
| 545 |
+
"eval_loss": 0.2808569669723511,
|
| 546 |
+
"eval_runtime": 0.1864,
|
| 547 |
+
"eval_samples_per_second": 26.824,
|
| 548 |
+
"eval_steps_per_second": 5.365,
|
| 549 |
+
"step": 1800
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 0.36505712650709393,
|
| 553 |
+
"grad_norm": 0.3028016686439514,
|
| 554 |
+
"learning_rate": 0.0001973991639421571,
|
| 555 |
+
"loss": 0.3303,
|
| 556 |
+
"step": 1850
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 0.36505712650709393,
|
| 560 |
+
"eval_loss": 0.27654123306274414,
|
| 561 |
+
"eval_runtime": 0.1859,
|
| 562 |
+
"eval_samples_per_second": 26.894,
|
| 563 |
+
"eval_steps_per_second": 5.379,
|
| 564 |
+
"step": 1850
|
| 565 |
+
},
|
| 566 |
+
{
|
| 567 |
+
"epoch": 0.37492353533161,
|
| 568 |
+
"grad_norm": 0.2978042960166931,
|
| 569 |
+
"learning_rate": 0.0001969857450349156,
|
| 570 |
+
"loss": 0.3304,
|
| 571 |
+
"step": 1900
|
| 572 |
+
},
|
| 573 |
+
{
|
| 574 |
+
"epoch": 0.37492353533161,
|
| 575 |
+
"eval_loss": 0.270946741104126,
|
| 576 |
+
"eval_runtime": 0.1856,
|
| 577 |
+
"eval_samples_per_second": 26.941,
|
| 578 |
+
"eval_steps_per_second": 5.388,
|
| 579 |
+
"step": 1900
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 0.38478994415612605,
|
| 583 |
+
"grad_norm": 0.3676602244377136,
|
| 584 |
+
"learning_rate": 0.00019654234523386576,
|
| 585 |
+
"loss": 0.3319,
|
| 586 |
+
"step": 1950
|
| 587 |
+
},
|
| 588 |
+
{
|
| 589 |
+
"epoch": 0.38478994415612605,
|
| 590 |
+
"eval_loss": 0.26677393913269043,
|
| 591 |
+
"eval_runtime": 0.1857,
|
| 592 |
+
"eval_samples_per_second": 26.927,
|
| 593 |
+
"eval_steps_per_second": 5.385,
|
| 594 |
+
"step": 1950
|
| 595 |
+
},
|
| 596 |
+
{
|
| 597 |
+
"epoch": 0.3946563529806421,
|
| 598 |
+
"grad_norm": 0.243007093667984,
|
| 599 |
+
"learning_rate": 0.00019606910160577286,
|
| 600 |
+
"loss": 0.3253,
|
| 601 |
+
"step": 2000
|
| 602 |
+
},
|
| 603 |
+
{
|
| 604 |
+
"epoch": 0.3946563529806421,
|
| 605 |
+
"eval_loss": 0.26983901858329773,
|
| 606 |
+
"eval_runtime": 0.186,
|
| 607 |
+
"eval_samples_per_second": 26.888,
|
| 608 |
+
"eval_steps_per_second": 5.378,
|
| 609 |
+
"step": 2000
|
| 610 |
+
},
|
| 611 |
+
{
|
| 612 |
+
"epoch": 0.40452276180515817,
|
| 613 |
+
"grad_norm": 0.2672829329967499,
|
| 614 |
+
"learning_rate": 0.00019556616044292917,
|
| 615 |
+
"loss": 0.3269,
|
| 616 |
+
"step": 2050
|
| 617 |
+
},
|
| 618 |
+
{
|
| 619 |
+
"epoch": 0.40452276180515817,
|
| 620 |
+
"eval_loss": 0.2751110792160034,
|
| 621 |
+
"eval_runtime": 0.187,
|
| 622 |
+
"eval_samples_per_second": 26.74,
|
| 623 |
+
"eval_steps_per_second": 5.348,
|
| 624 |
+
"step": 2050
|
| 625 |
+
},
|
| 626 |
+
{
|
| 627 |
+
"epoch": 0.41438917062967423,
|
| 628 |
+
"grad_norm": 0.26455241441726685,
|
| 629 |
+
"learning_rate": 0.00019503367721793112,
|
| 630 |
+
"loss": 0.3269,
|
| 631 |
+
"step": 2100
|
| 632 |
+
},
|
| 633 |
+
{
|
| 634 |
+
"epoch": 0.41438917062967423,
|
| 635 |
+
"eval_loss": 0.2611739933490753,
|
| 636 |
+
"eval_runtime": 0.1862,
|
| 637 |
+
"eval_samples_per_second": 26.854,
|
| 638 |
+
"eval_steps_per_second": 5.371,
|
| 639 |
+
"step": 2100
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 0.4242555794541903,
|
| 643 |
+
"grad_norm": 0.260708749294281,
|
| 644 |
+
"learning_rate": 0.00019447181653561851,
|
| 645 |
+
"loss": 0.3264,
|
| 646 |
+
"step": 2150
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 0.4242555794541903,
|
| 650 |
+
"eval_loss": 0.25694364309310913,
|
| 651 |
+
"eval_runtime": 0.1866,
|
| 652 |
+
"eval_samples_per_second": 26.801,
|
| 653 |
+
"eval_steps_per_second": 5.36,
|
| 654 |
+
"step": 2150
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 0.4341219882787063,
|
| 658 |
+
"grad_norm": 0.3702332079410553,
|
| 659 |
+
"learning_rate": 0.00019388075208219072,
|
| 660 |
+
"loss": 0.3205,
|
| 661 |
+
"step": 2200
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 0.4341219882787063,
|
| 665 |
+
"eval_loss": 0.2542697489261627,
|
| 666 |
+
"eval_runtime": 0.1859,
|
| 667 |
+
"eval_samples_per_second": 26.897,
|
| 668 |
+
"eval_steps_per_second": 5.379,
|
| 669 |
+
"step": 2200
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 0.44398839710322235,
|
| 673 |
+
"grad_norm": 0.2797427177429199,
|
| 674 |
+
"learning_rate": 0.00019326066657151568,
|
| 675 |
+
"loss": 0.3251,
|
| 676 |
+
"step": 2250
|
| 677 |
+
},
|
| 678 |
+
{
|
| 679 |
+
"epoch": 0.44398839710322235,
|
| 680 |
+
"eval_loss": 0.2655983865261078,
|
| 681 |
+
"eval_runtime": 0.186,
|
| 682 |
+
"eval_samples_per_second": 26.886,
|
| 683 |
+
"eval_steps_per_second": 5.377,
|
| 684 |
+
"step": 2250
|
| 685 |
+
},
|
| 686 |
+
{
|
| 687 |
+
"epoch": 0.4538548059277384,
|
| 688 |
+
"grad_norm": 0.27329573035240173,
|
| 689 |
+
"learning_rate": 0.00019261175168864823,
|
| 690 |
+
"loss": 0.3203,
|
| 691 |
+
"step": 2300
|
| 692 |
+
},
|
| 693 |
+
{
|
| 694 |
+
"epoch": 0.4538548059277384,
|
| 695 |
+
"eval_loss": 0.2548620402812958,
|
| 696 |
+
"eval_runtime": 0.1859,
|
| 697 |
+
"eval_samples_per_second": 26.897,
|
| 698 |
+
"eval_steps_per_second": 5.379,
|
| 699 |
+
"step": 2300
|
| 700 |
+
},
|
| 701 |
+
{
|
| 702 |
+
"epoch": 0.4637212147522545,
|
| 703 |
+
"grad_norm": 0.2299811691045761,
|
| 704 |
+
"learning_rate": 0.00019193420803057483,
|
| 705 |
+
"loss": 0.3171,
|
| 706 |
+
"step": 2350
|
| 707 |
+
},
|
| 708 |
+
{
|
| 709 |
+
"epoch": 0.4637212147522545,
|
| 710 |
+
"eval_loss": 0.25404179096221924,
|
| 711 |
+
"eval_runtime": 0.1869,
|
| 712 |
+
"eval_samples_per_second": 26.755,
|
| 713 |
+
"eval_steps_per_second": 5.351,
|
| 714 |
+
"step": 2350
|
| 715 |
+
},
|
| 716 |
+
{
|
| 717 |
+
"epoch": 0.47358762357677053,
|
| 718 |
+
"grad_norm": 0.43620172142982483,
|
| 719 |
+
"learning_rate": 0.00019122824504420402,
|
| 720 |
+
"loss": 0.3192,
|
| 721 |
+
"step": 2400
|
| 722 |
+
},
|
| 723 |
+
{
|
| 724 |
+
"epoch": 0.47358762357677053,
|
| 725 |
+
"eval_loss": 0.2546399235725403,
|
| 726 |
+
"eval_runtime": 0.1862,
|
| 727 |
+
"eval_samples_per_second": 26.85,
|
| 728 |
+
"eval_steps_per_second": 5.37,
|
| 729 |
+
"step": 2400
|
| 730 |
+
},
|
| 731 |
+
{
|
| 732 |
+
"epoch": 0.4834540324012866,
|
| 733 |
+
"grad_norm": 0.2562660574913025,
|
| 734 |
+
"learning_rate": 0.0001904940809616205,
|
| 735 |
+
"loss": 0.3204,
|
| 736 |
+
"step": 2450
|
| 737 |
+
},
|
| 738 |
+
{
|
| 739 |
+
"epoch": 0.4834540324012866,
|
| 740 |
+
"eval_loss": 0.25131484866142273,
|
| 741 |
+
"eval_runtime": 0.1861,
|
| 742 |
+
"eval_samples_per_second": 26.861,
|
| 743 |
+
"eval_steps_per_second": 5.372,
|
| 744 |
+
"step": 2450
|
| 745 |
+
},
|
| 746 |
+
{
|
| 747 |
+
"epoch": 0.49332044122580265,
|
| 748 |
+
"grad_norm": 0.21843916177749634,
|
| 749 |
+
"learning_rate": 0.0001897319427326239,
|
| 750 |
+
"loss": 0.3211,
|
| 751 |
+
"step": 2500
|
| 752 |
+
},
|
| 753 |
+
{
|
| 754 |
+
"epoch": 0.49332044122580265,
|
| 755 |
+
"eval_loss": 0.2540796399116516,
|
| 756 |
+
"eval_runtime": 0.1862,
|
| 757 |
+
"eval_samples_per_second": 26.851,
|
| 758 |
+
"eval_steps_per_second": 5.37,
|
| 759 |
+
"step": 2500
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 0.5031868500503187,
|
| 763 |
+
"grad_norm": 0.2513650059700012,
|
| 764 |
+
"learning_rate": 0.00018894206595457228,
|
| 765 |
+
"loss": 0.3172,
|
| 766 |
+
"step": 2550
|
| 767 |
+
},
|
| 768 |
+
{
|
| 769 |
+
"epoch": 0.5031868500503187,
|
| 770 |
+
"eval_loss": 0.254707932472229,
|
| 771 |
+
"eval_runtime": 0.1862,
|
| 772 |
+
"eval_samples_per_second": 26.851,
|
| 773 |
+
"eval_steps_per_second": 5.37,
|
| 774 |
+
"step": 2550
|
| 775 |
+
},
|
| 776 |
+
{
|
| 777 |
+
"epoch": 0.5130532588748348,
|
| 778 |
+
"grad_norm": 0.2910959720611572,
|
| 779 |
+
"learning_rate": 0.00018812469479955306,
|
| 780 |
+
"loss": 0.319,
|
| 781 |
+
"step": 2600
|
| 782 |
+
},
|
| 783 |
+
{
|
| 784 |
+
"epoch": 0.5130532588748348,
|
| 785 |
+
"eval_loss": 0.2549395263195038,
|
| 786 |
+
"eval_runtime": 0.186,
|
| 787 |
+
"eval_samples_per_second": 26.877,
|
| 788 |
+
"eval_steps_per_second": 5.375,
|
| 789 |
+
"step": 2600
|
| 790 |
+
},
|
| 791 |
+
{
|
| 792 |
+
"epoch": 0.5229196676993508,
|
| 793 |
+
"grad_norm": 0.36300212144851685,
|
| 794 |
+
"learning_rate": 0.00018728008193890248,
|
| 795 |
+
"loss": 0.3141,
|
| 796 |
+
"step": 2650
|
| 797 |
+
},
|
| 798 |
+
{
|
| 799 |
+
"epoch": 0.5229196676993508,
|
| 800 |
+
"eval_loss": 0.25633907318115234,
|
| 801 |
+
"eval_runtime": 0.1866,
|
| 802 |
+
"eval_samples_per_second": 26.789,
|
| 803 |
+
"eval_steps_per_second": 5.358,
|
| 804 |
+
"step": 2650
|
| 805 |
+
},
|
| 806 |
+
{
|
| 807 |
+
"epoch": 0.5327860765238669,
|
| 808 |
+
"grad_norm": 0.27469244599342346,
|
| 809 |
+
"learning_rate": 0.00018640848846509836,
|
| 810 |
+
"loss": 0.3165,
|
| 811 |
+
"step": 2700
|
| 812 |
+
},
|
| 813 |
+
{
|
| 814 |
+
"epoch": 0.5327860765238669,
|
| 815 |
+
"eval_loss": 0.25254935026168823,
|
| 816 |
+
"eval_runtime": 0.1868,
|
| 817 |
+
"eval_samples_per_second": 26.772,
|
| 818 |
+
"eval_steps_per_second": 5.354,
|
| 819 |
+
"step": 2700
|
| 820 |
+
},
|
| 821 |
+
{
|
| 822 |
+
"epoch": 0.5426524853483828,
|
| 823 |
+
"grad_norm": 0.24992810189723969,
|
| 824 |
+
"learning_rate": 0.00018551018381104942,
|
| 825 |
+
"loss": 0.3148,
|
| 826 |
+
"step": 2750
|
| 827 |
+
},
|
| 828 |
+
{
|
| 829 |
+
"epoch": 0.5426524853483828,
|
| 830 |
+
"eval_loss": 0.2522678077220917,
|
| 831 |
+
"eval_runtime": 0.187,
|
| 832 |
+
"eval_samples_per_second": 26.739,
|
| 833 |
+
"eval_steps_per_second": 5.348,
|
| 834 |
+
"step": 2750
|
| 835 |
+
},
|
| 836 |
+
{
|
| 837 |
+
"epoch": 0.5525188941728989,
|
| 838 |
+
"grad_norm": 0.22494597733020782,
|
| 839 |
+
"learning_rate": 0.00018458544566680613,
|
| 840 |
+
"loss": 0.3178,
|
| 841 |
+
"step": 2800
|
| 842 |
+
},
|
| 843 |
+
{
|
| 844 |
+
"epoch": 0.5525188941728989,
|
| 845 |
+
"eval_loss": 0.2535417973995209,
|
| 846 |
+
"eval_runtime": 0.1861,
|
| 847 |
+
"eval_samples_per_second": 26.866,
|
| 848 |
+
"eval_steps_per_second": 5.373,
|
| 849 |
+
"step": 2800
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 0.562385302997415,
|
| 853 |
+
"grad_norm": 0.2611429989337921,
|
| 854 |
+
"learning_rate": 0.0001836345598937195,
|
| 855 |
+
"loss": 0.3151,
|
| 856 |
+
"step": 2850
|
| 857 |
+
},
|
| 858 |
+
{
|
| 859 |
+
"epoch": 0.562385302997415,
|
| 860 |
+
"eval_loss": 0.2576417326927185,
|
| 861 |
+
"eval_runtime": 0.1858,
|
| 862 |
+
"eval_samples_per_second": 26.917,
|
| 863 |
+
"eval_steps_per_second": 5.383,
|
| 864 |
+
"step": 2850
|
| 865 |
+
},
|
| 866 |
+
{
|
| 867 |
+
"epoch": 0.572251711821931,
|
| 868 |
+
"grad_norm": 0.2593046724796295,
|
| 869 |
+
"learning_rate": 0.00018265782043607362,
|
| 870 |
+
"loss": 0.3155,
|
| 871 |
+
"step": 2900
|
| 872 |
+
},
|
| 873 |
+
{
|
| 874 |
+
"epoch": 0.572251711821931,
|
| 875 |
+
"eval_loss": 0.24795055389404297,
|
| 876 |
+
"eval_runtime": 0.1873,
|
| 877 |
+
"eval_samples_per_second": 26.699,
|
| 878 |
+
"eval_steps_per_second": 5.34,
|
| 879 |
+
"step": 2900
|
| 880 |
+
},
|
| 881 |
+
{
|
| 882 |
+
"epoch": 0.5821181206464471,
|
| 883 |
+
"grad_norm": 0.2805608808994293,
|
| 884 |
+
"learning_rate": 0.00018165552923021946,
|
| 885 |
+
"loss": 0.3084,
|
| 886 |
+
"step": 2950
|
| 887 |
+
},
|
| 888 |
+
{
|
| 889 |
+
"epoch": 0.5821181206464471,
|
| 890 |
+
"eval_loss": 0.2520078122615814,
|
| 891 |
+
"eval_runtime": 0.186,
|
| 892 |
+
"eval_samples_per_second": 26.883,
|
| 893 |
+
"eval_steps_per_second": 5.377,
|
| 894 |
+
"step": 2950
|
| 895 |
+
},
|
| 896 |
+
{
|
| 897 |
+
"epoch": 0.5919845294709631,
|
| 898 |
+
"grad_norm": 0.2355504184961319,
|
| 899 |
+
"learning_rate": 0.00018062799611123843,
|
| 900 |
+
"loss": 0.3135,
|
| 901 |
+
"step": 3000
|
| 902 |
+
},
|
| 903 |
+
{
|
| 904 |
+
"epoch": 0.5919845294709631,
|
| 905 |
+
"eval_loss": 0.2500859797000885,
|
| 906 |
+
"eval_runtime": 0.1863,
|
| 907 |
+
"eval_samples_per_second": 26.834,
|
| 908 |
+
"eval_steps_per_second": 5.367,
|
| 909 |
+
"step": 3000
|
| 910 |
+
},
|
| 911 |
+
{
|
| 912 |
+
"epoch": 0.6018509382954792,
|
| 913 |
+
"grad_norm": 0.23624199628829956,
|
| 914 |
+
"learning_rate": 0.00017957553871716405,
|
| 915 |
+
"loss": 0.3063,
|
| 916 |
+
"step": 3050
|
| 917 |
+
},
|
| 918 |
+
{
|
| 919 |
+
"epoch": 0.6018509382954792,
|
| 920 |
+
"eval_loss": 0.24056918919086456,
|
| 921 |
+
"eval_runtime": 0.1859,
|
| 922 |
+
"eval_samples_per_second": 26.894,
|
| 923 |
+
"eval_steps_per_second": 5.379,
|
| 924 |
+
"step": 3050
|
| 925 |
+
},
|
| 926 |
+
{
|
| 927 |
+
"epoch": 0.6117173471199953,
|
| 928 |
+
"grad_norm": 0.2305937111377716,
|
| 929 |
+
"learning_rate": 0.00017849848239079126,
|
| 930 |
+
"loss": 0.3076,
|
| 931 |
+
"step": 3100
|
| 932 |
+
},
|
| 933 |
+
{
|
| 934 |
+
"epoch": 0.6117173471199953,
|
| 935 |
+
"eval_loss": 0.2453293353319168,
|
| 936 |
+
"eval_runtime": 0.1852,
|
| 937 |
+
"eval_samples_per_second": 26.996,
|
| 938 |
+
"eval_steps_per_second": 5.399,
|
| 939 |
+
"step": 3100
|
| 940 |
+
},
|
| 941 |
+
{
|
| 942 |
+
"epoch": 0.6215837559445113,
|
| 943 |
+
"grad_norm": 0.28438571095466614,
|
| 944 |
+
"learning_rate": 0.00017739716007910458,
|
| 945 |
+
"loss": 0.309,
|
| 946 |
+
"step": 3150
|
| 947 |
+
},
|
| 948 |
+
{
|
| 949 |
+
"epoch": 0.6215837559445113,
|
| 950 |
+
"eval_loss": 0.241606667637825,
|
| 951 |
+
"eval_runtime": 0.1859,
|
| 952 |
+
"eval_samples_per_second": 26.891,
|
| 953 |
+
"eval_steps_per_second": 5.378,
|
| 954 |
+
"step": 3150
|
| 955 |
+
},
|
| 956 |
+
{
|
| 957 |
+
"epoch": 0.6314501647690274,
|
| 958 |
+
"grad_norm": 0.31287047266960144,
|
| 959 |
+
"learning_rate": 0.00017627191223035512,
|
| 960 |
+
"loss": 0.3123,
|
| 961 |
+
"step": 3200
|
| 962 |
+
},
|
| 963 |
+
{
|
| 964 |
+
"epoch": 0.6314501647690274,
|
| 965 |
+
"eval_loss": 0.24313075840473175,
|
| 966 |
+
"eval_runtime": 0.1856,
|
| 967 |
+
"eval_samples_per_second": 26.939,
|
| 968 |
+
"eval_steps_per_second": 5.388,
|
| 969 |
+
"step": 3200
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 0.6413165735935434,
|
| 973 |
+
"grad_norm": 0.2634814381599426,
|
| 974 |
+
"learning_rate": 0.00017512308668881876,
|
| 975 |
+
"loss": 0.3093,
|
| 976 |
+
"step": 3250
|
| 977 |
+
},
|
| 978 |
+
{
|
| 979 |
+
"epoch": 0.6413165735935434,
|
| 980 |
+
"eval_loss": 0.24376794695854187,
|
| 981 |
+
"eval_runtime": 0.1861,
|
| 982 |
+
"eval_samples_per_second": 26.872,
|
| 983 |
+
"eval_steps_per_second": 5.374,
|
| 984 |
+
"step": 3250
|
| 985 |
+
},
|
| 986 |
+
{
|
| 987 |
+
"epoch": 0.6511829824180595,
|
| 988 |
+
"grad_norm": 0.22829458117485046,
|
| 989 |
+
"learning_rate": 0.00017395103858726846,
|
| 990 |
+
"loss": 0.3093,
|
| 991 |
+
"step": 3300
|
| 992 |
+
},
|
| 993 |
+
{
|
| 994 |
+
"epoch": 0.6511829824180595,
|
| 995 |
+
"eval_loss": 0.2428242713212967,
|
| 996 |
+
"eval_runtime": 0.1881,
|
| 997 |
+
"eval_samples_per_second": 26.589,
|
| 998 |
+
"eval_steps_per_second": 5.318,
|
| 999 |
+
"step": 3300
|
| 1000 |
+
},
|
| 1001 |
+
{
|
| 1002 |
+
"epoch": 0.6610493912425756,
|
| 1003 |
+
"grad_norm": 0.26152193546295166,
|
| 1004 |
+
"learning_rate": 0.00017275613023719298,
|
| 1005 |
+
"loss": 0.3113,
|
| 1006 |
+
"step": 3350
|
| 1007 |
+
},
|
| 1008 |
+
{
|
| 1009 |
+
"epoch": 0.6610493912425756,
|
| 1010 |
+
"eval_loss": 0.24297213554382324,
|
| 1011 |
+
"eval_runtime": 0.1864,
|
| 1012 |
+
"eval_samples_per_second": 26.821,
|
| 1013 |
+
"eval_steps_per_second": 5.364,
|
| 1014 |
+
"step": 3350
|
| 1015 |
+
},
|
| 1016 |
+
{
|
| 1017 |
+
"epoch": 0.6709158000670916,
|
| 1018 |
+
"grad_norm": 0.21779882907867432,
|
| 1019 |
+
"learning_rate": 0.00017153873101679668,
|
| 1020 |
+
"loss": 0.3085,
|
| 1021 |
+
"step": 3400
|
| 1022 |
+
},
|
| 1023 |
+
{
|
| 1024 |
+
"epoch": 0.6709158000670916,
|
| 1025 |
+
"eval_loss": 0.24597088992595673,
|
| 1026 |
+
"eval_runtime": 0.1862,
|
| 1027 |
+
"eval_samples_per_second": 26.854,
|
| 1028 |
+
"eval_steps_per_second": 5.371,
|
| 1029 |
+
"step": 3400
|
| 1030 |
+
},
|
| 1031 |
+
{
|
| 1032 |
+
"epoch": 0.6807822088916077,
|
| 1033 |
+
"grad_norm": 0.21129541099071503,
|
| 1034 |
+
"learning_rate": 0.00017029921725681492,
|
| 1035 |
+
"loss": 0.3045,
|
| 1036 |
+
"step": 3450
|
| 1037 |
+
},
|
| 1038 |
+
{
|
| 1039 |
+
"epoch": 0.6807822088916077,
|
| 1040 |
+
"eval_loss": 0.23454919457435608,
|
| 1041 |
+
"eval_runtime": 0.1867,
|
| 1042 |
+
"eval_samples_per_second": 26.786,
|
| 1043 |
+
"eval_steps_per_second": 5.357,
|
| 1044 |
+
"step": 3450
|
| 1045 |
+
},
|
| 1046 |
+
{
|
| 1047 |
+
"epoch": 0.6906486177161237,
|
| 1048 |
+
"grad_norm": 0.19822391867637634,
|
| 1049 |
+
"learning_rate": 0.00016903797212418015,
|
| 1050 |
+
"loss": 0.3049,
|
| 1051 |
+
"step": 3500
|
| 1052 |
+
},
|
| 1053 |
+
{
|
| 1054 |
+
"epoch": 0.6906486177161237,
|
| 1055 |
+
"eval_loss": 0.23835961520671844,
|
| 1056 |
+
"eval_runtime": 0.1872,
|
| 1057 |
+
"eval_samples_per_second": 26.708,
|
| 1058 |
+
"eval_steps_per_second": 5.342,
|
| 1059 |
+
"step": 3500
|
| 1060 |
+
},
|
| 1061 |
+
{
|
| 1062 |
+
"epoch": 0.7005150265406397,
|
| 1063 |
+
"grad_norm": 0.2132054716348648,
|
| 1064 |
+
"learning_rate": 0.00016775538550357463,
|
| 1065 |
+
"loss": 0.3058,
|
| 1066 |
+
"step": 3550
|
| 1067 |
+
},
|
| 1068 |
+
{
|
| 1069 |
+
"epoch": 0.7005150265406397,
|
| 1070 |
+
"eval_loss": 0.2351282387971878,
|
| 1071 |
+
"eval_runtime": 0.1862,
|
| 1072 |
+
"eval_samples_per_second": 26.857,
|
| 1073 |
+
"eval_steps_per_second": 5.371,
|
| 1074 |
+
"step": 3550
|
| 1075 |
+
},
|
| 1076 |
+
{
|
| 1077 |
+
"epoch": 0.7103814353651557,
|
| 1078 |
+
"grad_norm": 0.23732738196849823,
|
| 1079 |
+
"learning_rate": 0.0001664518538769067,
|
| 1080 |
+
"loss": 0.3021,
|
| 1081 |
+
"step": 3600
|
| 1082 |
+
},
|
| 1083 |
+
{
|
| 1084 |
+
"epoch": 0.7103814353651557,
|
| 1085 |
+
"eval_loss": 0.23832817375659943,
|
| 1086 |
+
"eval_runtime": 0.1857,
|
| 1087 |
+
"eval_samples_per_second": 26.93,
|
| 1088 |
+
"eval_steps_per_second": 5.386,
|
| 1089 |
+
"step": 3600
|
| 1090 |
+
},
|
| 1091 |
+
{
|
| 1092 |
+
"epoch": 0.7202478441896718,
|
| 1093 |
+
"grad_norm": 0.3427148759365082,
|
| 1094 |
+
"learning_rate": 0.00016512778020074753,
|
| 1095 |
+
"loss": 0.3044,
|
| 1096 |
+
"step": 3650
|
| 1097 |
+
},
|
| 1098 |
+
{
|
| 1099 |
+
"epoch": 0.7202478441896718,
|
| 1100 |
+
"eval_loss": 0.24248237907886505,
|
| 1101 |
+
"eval_runtime": 0.1861,
|
| 1102 |
+
"eval_samples_per_second": 26.863,
|
| 1103 |
+
"eval_steps_per_second": 5.373,
|
| 1104 |
+
"step": 3650
|
| 1105 |
+
},
|
| 1106 |
+
{
|
| 1107 |
+
"epoch": 0.7301142530141879,
|
| 1108 |
+
"grad_norm": 0.33537736535072327,
|
| 1109 |
+
"learning_rate": 0.00016378357378176654,
|
| 1110 |
+
"loss": 0.3004,
|
| 1111 |
+
"step": 3700
|
| 1112 |
+
},
|
| 1113 |
+
{
|
| 1114 |
+
"epoch": 0.7301142530141879,
|
| 1115 |
+
"eval_loss": 0.23529915511608124,
|
| 1116 |
+
"eval_runtime": 0.185,
|
| 1117 |
+
"eval_samples_per_second": 27.026,
|
| 1118 |
+
"eval_steps_per_second": 5.405,
|
| 1119 |
+
"step": 3700
|
| 1120 |
+
},
|
| 1121 |
+
{
|
| 1122 |
+
"epoch": 0.7399806618387039,
|
| 1123 |
+
"grad_norm": 0.236049085855484,
|
| 1124 |
+
"learning_rate": 0.00016241965015020363,
|
| 1125 |
+
"loss": 0.3047,
|
| 1126 |
+
"step": 3750
|
| 1127 |
+
},
|
| 1128 |
+
{
|
| 1129 |
+
"epoch": 0.7399806618387039,
|
| 1130 |
+
"eval_loss": 0.23639431595802307,
|
| 1131 |
+
"eval_runtime": 0.1858,
|
| 1132 |
+
"eval_samples_per_second": 26.914,
|
| 1133 |
+
"eval_steps_per_second": 5.383,
|
| 1134 |
+
"step": 3750
|
| 1135 |
+
},
|
| 1136 |
+
{
|
| 1137 |
+
"epoch": 0.74984707066322,
|
| 1138 |
+
"grad_norm": 0.23827500641345978,
|
| 1139 |
+
"learning_rate": 0.0001610364309314178,
|
| 1140 |
+
"loss": 0.2991,
|
| 1141 |
+
"step": 3800
|
| 1142 |
+
},
|
| 1143 |
+
{
|
| 1144 |
+
"epoch": 0.74984707066322,
|
| 1145 |
+
"eval_loss": 0.23711517453193665,
|
| 1146 |
+
"eval_runtime": 0.1845,
|
| 1147 |
+
"eval_samples_per_second": 27.098,
|
| 1148 |
+
"eval_steps_per_second": 5.42,
|
| 1149 |
+
"step": 3800
|
| 1150 |
+
},
|
| 1151 |
+
{
|
| 1152 |
+
"epoch": 0.759713479487736,
|
| 1153 |
+
"grad_norm": 0.24710151553153992,
|
| 1154 |
+
"learning_rate": 0.00015963434371555116,
|
| 1155 |
+
"loss": 0.2993,
|
| 1156 |
+
"step": 3850
|
| 1157 |
+
},
|
| 1158 |
+
{
|
| 1159 |
+
"epoch": 0.759713479487736,
|
| 1160 |
+
"eval_loss": 0.2302863895893097,
|
| 1161 |
+
"eval_runtime": 0.1857,
|
| 1162 |
+
"eval_samples_per_second": 26.929,
|
| 1163 |
+
"eval_steps_per_second": 5.386,
|
| 1164 |
+
"step": 3850
|
| 1165 |
+
},
|
| 1166 |
+
{
|
| 1167 |
+
"epoch": 0.7695798883122521,
|
| 1168 |
+
"grad_norm": 0.18992306292057037,
|
| 1169 |
+
"learning_rate": 0.00015821382192534968,
|
| 1170 |
+
"loss": 0.3022,
|
| 1171 |
+
"step": 3900
|
| 1172 |
+
},
|
| 1173 |
+
{
|
| 1174 |
+
"epoch": 0.7695798883122521,
|
| 1175 |
+
"eval_loss": 0.23323240876197815,
|
| 1176 |
+
"eval_runtime": 0.1847,
|
| 1177 |
+
"eval_samples_per_second": 27.071,
|
| 1178 |
+
"eval_steps_per_second": 5.414,
|
| 1179 |
+
"step": 3900
|
| 1180 |
+
},
|
| 1181 |
+
{
|
| 1182 |
+
"epoch": 0.7794462971367682,
|
| 1183 |
+
"grad_norm": 0.2224888652563095,
|
| 1184 |
+
"learning_rate": 0.00015677530468218045,
|
| 1185 |
+
"loss": 0.3028,
|
| 1186 |
+
"step": 3950
|
| 1187 |
+
},
|
| 1188 |
+
{
|
| 1189 |
+
"epoch": 0.7794462971367682,
|
| 1190 |
+
"eval_loss": 0.2351154088973999,
|
| 1191 |
+
"eval_runtime": 0.1846,
|
| 1192 |
+
"eval_samples_per_second": 27.091,
|
| 1193 |
+
"eval_steps_per_second": 5.418,
|
| 1194 |
+
"step": 3950
|
| 1195 |
+
},
|
| 1196 |
+
{
|
| 1197 |
+
"epoch": 0.7893127059612842,
|
| 1198 |
+
"grad_norm": 0.2259168177843094,
|
| 1199 |
+
"learning_rate": 0.0001553192366702874,
|
| 1200 |
+
"loss": 0.3019,
|
| 1201 |
+
"step": 4000
|
| 1202 |
+
},
|
| 1203 |
+
{
|
| 1204 |
+
"epoch": 0.7893127059612842,
|
| 1205 |
+
"eval_loss": 0.227354496717453,
|
| 1206 |
+
"eval_runtime": 0.1846,
|
| 1207 |
+
"eval_samples_per_second": 27.09,
|
| 1208 |
+
"eval_steps_per_second": 5.418,
|
| 1209 |
+
"step": 4000
|
| 1210 |
+
},
|
| 1211 |
+
{
|
| 1212 |
+
"epoch": 0.7991791147858003,
|
| 1213 |
+
"grad_norm": 0.291294127702713,
|
| 1214 |
+
"learning_rate": 0.0001538460679993277,
|
| 1215 |
+
"loss": 0.2989,
|
| 1216 |
+
"step": 4050
|
| 1217 |
+
},
|
| 1218 |
+
{
|
| 1219 |
+
"epoch": 0.7991791147858003,
|
| 1220 |
+
"eval_loss": 0.24032792448997498,
|
| 1221 |
+
"eval_runtime": 0.185,
|
| 1222 |
+
"eval_samples_per_second": 27.022,
|
| 1223 |
+
"eval_steps_per_second": 5.404,
|
| 1224 |
+
"step": 4050
|
| 1225 |
+
},
|
| 1226 |
+
{
|
| 1227 |
+
"epoch": 0.8090455236103163,
|
| 1228 |
+
"grad_norm": 0.23510493338108063,
|
| 1229 |
+
"learning_rate": 0.00015235625406523058,
|
| 1230 |
+
"loss": 0.3004,
|
| 1231 |
+
"step": 4100
|
| 1232 |
+
},
|
| 1233 |
+
{
|
| 1234 |
+
"epoch": 0.8090455236103163,
|
| 1235 |
+
"eval_loss": 0.2415897101163864,
|
| 1236 |
+
"eval_runtime": 0.1848,
|
| 1237 |
+
"eval_samples_per_second": 27.05,
|
| 1238 |
+
"eval_steps_per_second": 5.41,
|
| 1239 |
+
"step": 4100
|
| 1240 |
+
},
|
| 1241 |
+
{
|
| 1242 |
+
"epoch": 0.8189119324348324,
|
| 1243 |
+
"grad_norm": 0.21880796551704407,
|
| 1244 |
+
"learning_rate": 0.00015085025540942238,
|
| 1245 |
+
"loss": 0.3,
|
| 1246 |
+
"step": 4150
|
| 1247 |
+
},
|
| 1248 |
+
{
|
| 1249 |
+
"epoch": 0.8189119324348324,
|
| 1250 |
+
"eval_loss": 0.24045029282569885,
|
| 1251 |
+
"eval_runtime": 0.1849,
|
| 1252 |
+
"eval_samples_per_second": 27.045,
|
| 1253 |
+
"eval_steps_per_second": 5.409,
|
| 1254 |
+
"step": 4150
|
| 1255 |
+
},
|
| 1256 |
+
{
|
| 1257 |
+
"epoch": 0.8287783412593485,
|
| 1258 |
+
"grad_norm": 0.24291107058525085,
|
| 1259 |
+
"learning_rate": 0.0001493285375764608,
|
| 1260 |
+
"loss": 0.2976,
|
| 1261 |
+
"step": 4200
|
| 1262 |
+
},
|
| 1263 |
+
{
|
| 1264 |
+
"epoch": 0.8287783412593485,
|
| 1265 |
+
"eval_loss": 0.24324026703834534,
|
| 1266 |
+
"eval_runtime": 0.1847,
|
| 1267 |
+
"eval_samples_per_second": 27.067,
|
| 1268 |
+
"eval_steps_per_second": 5.413,
|
| 1269 |
+
"step": 4200
|
| 1270 |
+
},
|
| 1271 |
+
{
|
| 1272 |
+
"epoch": 0.8386447500838645,
|
| 1273 |
+
"grad_norm": 0.2263229787349701,
|
| 1274 |
+
"learning_rate": 0.0001477915709701226,
|
| 1275 |
+
"loss": 0.298,
|
| 1276 |
+
"step": 4250
|
| 1277 |
+
},
|
| 1278 |
+
{
|
| 1279 |
+
"epoch": 0.8386447500838645,
|
| 1280 |
+
"eval_loss": 0.2447391003370285,
|
| 1281 |
+
"eval_runtime": 0.1847,
|
| 1282 |
+
"eval_samples_per_second": 27.068,
|
| 1283 |
+
"eval_steps_per_second": 5.414,
|
| 1284 |
+
"step": 4250
|
| 1285 |
+
},
|
| 1286 |
+
{
|
| 1287 |
+
"epoch": 0.8485111589083806,
|
| 1288 |
+
"grad_norm": 0.20994020998477936,
|
| 1289 |
+
"learning_rate": 0.00014623983070798918,
|
| 1290 |
+
"loss": 0.297,
|
| 1291 |
+
"step": 4300
|
| 1292 |
+
},
|
| 1293 |
+
{
|
| 1294 |
+
"epoch": 0.8485111589083806,
|
| 1295 |
+
"eval_loss": 0.24018962681293488,
|
| 1296 |
+
"eval_runtime": 0.1843,
|
| 1297 |
+
"eval_samples_per_second": 27.127,
|
| 1298 |
+
"eval_steps_per_second": 5.425,
|
| 1299 |
+
"step": 4300
|
| 1300 |
+
},
|
| 1301 |
+
{
|
| 1302 |
+
"epoch": 0.8583775677328965,
|
| 1303 |
+
"grad_norm": 0.19051186740398407,
|
| 1304 |
+
"learning_rate": 0.000144673796474575,
|
| 1305 |
+
"loss": 0.2929,
|
| 1306 |
+
"step": 4350
|
| 1307 |
+
},
|
| 1308 |
+
{
|
| 1309 |
+
"epoch": 0.8583775677328965,
|
| 1310 |
+
"eval_loss": 0.23791976273059845,
|
| 1311 |
+
"eval_runtime": 0.1849,
|
| 1312 |
+
"eval_samples_per_second": 27.037,
|
| 1313 |
+
"eval_steps_per_second": 5.407,
|
| 1314 |
+
"step": 4350
|
| 1315 |
+
},
|
| 1316 |
+
{
|
| 1317 |
+
"epoch": 0.8682439765574126,
|
| 1318 |
+
"grad_norm": 0.23745004832744598,
|
| 1319 |
+
"learning_rate": 0.00014309395237304426,
|
| 1320 |
+
"loss": 0.2989,
|
| 1321 |
+
"step": 4400
|
| 1322 |
+
},
|
| 1323 |
+
{
|
| 1324 |
+
"epoch": 0.8682439765574126,
|
| 1325 |
+
"eval_loss": 0.23674488067626953,
|
| 1326 |
+
"eval_runtime": 0.1858,
|
| 1327 |
+
"eval_samples_per_second": 26.904,
|
| 1328 |
+
"eval_steps_per_second": 5.381,
|
| 1329 |
+
"step": 4400
|
| 1330 |
+
},
|
| 1331 |
+
{
|
| 1332 |
+
"epoch": 0.8781103853819286,
|
| 1333 |
+
"grad_norm": 0.19539549946784973,
|
| 1334 |
+
"learning_rate": 0.0001415007867755616,
|
| 1335 |
+
"loss": 0.2972,
|
| 1336 |
+
"step": 4450
|
| 1337 |
+
},
|
| 1338 |
+
{
|
| 1339 |
+
"epoch": 0.8781103853819286,
|
| 1340 |
+
"eval_loss": 0.23721548914909363,
|
| 1341 |
+
"eval_runtime": 0.1843,
|
| 1342 |
+
"eval_samples_per_second": 27.128,
|
| 1343 |
+
"eval_steps_per_second": 5.426,
|
| 1344 |
+
"step": 4450
|
| 1345 |
+
},
|
| 1346 |
+
{
|
| 1347 |
+
"epoch": 0.8879767942064447,
|
| 1348 |
+
"grad_norm": 0.26372581720352173,
|
| 1349 |
+
"learning_rate": 0.00013989479217232315,
|
| 1350 |
+
"loss": 0.2989,
|
| 1351 |
+
"step": 4500
|
| 1352 |
+
},
|
| 1353 |
+
{
|
| 1354 |
+
"epoch": 0.8879767942064447,
|
| 1355 |
+
"eval_loss": 0.2338230162858963,
|
| 1356 |
+
"eval_runtime": 0.1851,
|
| 1357 |
+
"eval_samples_per_second": 27.014,
|
| 1358 |
+
"eval_steps_per_second": 5.403,
|
| 1359 |
+
"step": 4500
|
| 1360 |
+
},
|
| 1361 |
+
{
|
| 1362 |
+
"epoch": 0.8978432030309608,
|
| 1363 |
+
"grad_norm": 0.2618955373764038,
|
| 1364 |
+
"learning_rate": 0.00013827646501931472,
|
| 1365 |
+
"loss": 0.2896,
|
| 1366 |
+
"step": 4550
|
| 1367 |
+
},
|
| 1368 |
+
{
|
| 1369 |
+
"epoch": 0.8978432030309608,
|
| 1370 |
+
"eval_loss": 0.23268970847129822,
|
| 1371 |
+
"eval_runtime": 0.1842,
|
| 1372 |
+
"eval_samples_per_second": 27.148,
|
| 1373 |
+
"eval_steps_per_second": 5.43,
|
| 1374 |
+
"step": 4550
|
| 1375 |
+
},
|
| 1376 |
+
{
|
| 1377 |
+
"epoch": 0.9077096118554768,
|
| 1378 |
+
"grad_norm": 0.2664230167865753,
|
| 1379 |
+
"learning_rate": 0.00013664630558484379,
|
| 1380 |
+
"loss": 0.2889,
|
| 1381 |
+
"step": 4600
|
| 1382 |
+
},
|
| 1383 |
+
{
|
| 1384 |
+
"epoch": 0.9077096118554768,
|
| 1385 |
+
"eval_loss": 0.22873499989509583,
|
| 1386 |
+
"eval_runtime": 0.1845,
|
| 1387 |
+
"eval_samples_per_second": 27.094,
|
| 1388 |
+
"eval_steps_per_second": 5.419,
|
| 1389 |
+
"step": 4600
|
| 1390 |
+
},
|
| 1391 |
+
{
|
| 1392 |
+
"epoch": 0.9175760206799929,
|
| 1393 |
+
"grad_norm": 0.21087364852428436,
|
| 1394 |
+
"learning_rate": 0.00013500481779489326,
|
| 1395 |
+
"loss": 0.2958,
|
| 1396 |
+
"step": 4650
|
| 1397 |
+
},
|
| 1398 |
+
{
|
| 1399 |
+
"epoch": 0.9175760206799929,
|
| 1400 |
+
"eval_loss": 0.23380012810230255,
|
| 1401 |
+
"eval_runtime": 0.1848,
|
| 1402 |
+
"eval_samples_per_second": 27.061,
|
| 1403 |
+
"eval_steps_per_second": 5.412,
|
| 1404 |
+
"step": 4650
|
| 1405 |
+
},
|
| 1406 |
+
{
|
| 1407 |
+
"epoch": 0.927442429504509,
|
| 1408 |
+
"grad_norm": 0.21377532184123993,
|
| 1409 |
+
"learning_rate": 0.00013335250907734448,
|
| 1410 |
+
"loss": 0.296,
|
| 1411 |
+
"step": 4700
|
| 1412 |
+
},
|
| 1413 |
+
{
|
| 1414 |
+
"epoch": 0.927442429504509,
|
| 1415 |
+
"eval_loss": 0.23471400141716003,
|
| 1416 |
+
"eval_runtime": 0.1847,
|
| 1417 |
+
"eval_samples_per_second": 27.075,
|
| 1418 |
+
"eval_steps_per_second": 5.415,
|
| 1419 |
+
"step": 4700
|
| 1420 |
+
},
|
| 1421 |
+
{
|
| 1422 |
+
"epoch": 0.937308838329025,
|
| 1423 |
+
"grad_norm": 0.2032233327627182,
|
| 1424 |
+
"learning_rate": 0.0001316898902051175,
|
| 1425 |
+
"loss": 0.2927,
|
| 1426 |
+
"step": 4750
|
| 1427 |
+
},
|
| 1428 |
+
{
|
| 1429 |
+
"epoch": 0.937308838329025,
|
| 1430 |
+
"eval_loss": 0.23120686411857605,
|
| 1431 |
+
"eval_runtime": 0.185,
|
| 1432 |
+
"eval_samples_per_second": 27.026,
|
| 1433 |
+
"eval_steps_per_second": 5.405,
|
| 1434 |
+
"step": 4750
|
| 1435 |
+
},
|
| 1436 |
+
{
|
| 1437 |
+
"epoch": 0.9471752471535411,
|
| 1438 |
+
"grad_norm": 0.22421005368232727,
|
| 1439 |
+
"learning_rate": 0.00013001747513827764,
|
| 1440 |
+
"loss": 0.2956,
|
| 1441 |
+
"step": 4800
|
| 1442 |
+
},
|
| 1443 |
+
{
|
| 1444 |
+
"epoch": 0.9471752471535411,
|
| 1445 |
+
"eval_loss": 0.23076245188713074,
|
| 1446 |
+
"eval_runtime": 0.1846,
|
| 1447 |
+
"eval_samples_per_second": 27.079,
|
| 1448 |
+
"eval_steps_per_second": 5.416,
|
| 1449 |
+
"step": 4800
|
| 1450 |
+
},
|
| 1451 |
+
{
|
| 1452 |
+
"epoch": 0.9570416559780571,
|
| 1453 |
+
"grad_norm": 0.2466699182987213,
|
| 1454 |
+
"learning_rate": 0.0001283357808651566,
|
| 1455 |
+
"loss": 0.2907,
|
| 1456 |
+
"step": 4850
|
| 1457 |
+
},
|
| 1458 |
+
{
|
| 1459 |
+
"epoch": 0.9570416559780571,
|
| 1460 |
+
"eval_loss": 0.22873035073280334,
|
| 1461 |
+
"eval_runtime": 0.1843,
|
| 1462 |
+
"eval_samples_per_second": 27.128,
|
| 1463 |
+
"eval_steps_per_second": 5.426,
|
| 1464 |
+
"step": 4850
|
| 1465 |
+
},
|
| 1466 |
+
{
|
| 1467 |
+
"epoch": 0.9669080648025732,
|
| 1468 |
+
"grad_norm": 0.20787620544433594,
|
| 1469 |
+
"learning_rate": 0.00012664532724253745,
|
| 1470 |
+
"loss": 0.2954,
|
| 1471 |
+
"step": 4900
|
| 1472 |
+
},
|
| 1473 |
+
{
|
| 1474 |
+
"epoch": 0.9669080648025732,
|
| 1475 |
+
"eval_loss": 0.22716188430786133,
|
| 1476 |
+
"eval_runtime": 0.1847,
|
| 1477 |
+
"eval_samples_per_second": 27.076,
|
| 1478 |
+
"eval_steps_per_second": 5.415,
|
| 1479 |
+
"step": 4900
|
| 1480 |
+
},
|
| 1481 |
+
{
|
| 1482 |
+
"epoch": 0.9767744736270892,
|
| 1483 |
+
"grad_norm": 0.22663253545761108,
|
| 1484 |
+
"learning_rate": 0.00012494663683495304,
|
| 1485 |
+
"loss": 0.2897,
|
| 1486 |
+
"step": 4950
|
| 1487 |
+
},
|
| 1488 |
+
{
|
| 1489 |
+
"epoch": 0.9767744736270892,
|
| 1490 |
+
"eval_loss": 0.2276424914598465,
|
| 1491 |
+
"eval_runtime": 0.1848,
|
| 1492 |
+
"eval_samples_per_second": 27.05,
|
| 1493 |
+
"eval_steps_per_second": 5.41,
|
| 1494 |
+
"step": 4950
|
| 1495 |
+
},
|
| 1496 |
+
{
|
| 1497 |
+
"epoch": 0.9866408824516053,
|
| 1498 |
+
"grad_norm": 0.20295187830924988,
|
| 1499 |
+
"learning_rate": 0.00012324023475314725,
|
| 1500 |
+
"loss": 0.2958,
|
| 1501 |
+
"step": 5000
|
| 1502 |
+
},
|
| 1503 |
+
{
|
| 1504 |
+
"epoch": 0.9866408824516053,
|
| 1505 |
+
"eval_loss": 0.23117908835411072,
|
| 1506 |
+
"eval_runtime": 0.185,
|
| 1507 |
+
"eval_samples_per_second": 27.024,
|
| 1508 |
+
"eval_steps_per_second": 5.405,
|
| 1509 |
+
"step": 5000
|
| 1510 |
+
},
|
| 1511 |
+
{
|
| 1512 |
+
"epoch": 0.9965072912761214,
|
| 1513 |
+
"grad_norm": 0.2138393521308899,
|
| 1514 |
+
"learning_rate": 0.0001215266484917493,
|
| 1515 |
+
"loss": 0.2876,
|
| 1516 |
+
"step": 5050
|
| 1517 |
+
},
|
| 1518 |
+
{
|
| 1519 |
+
"epoch": 0.9965072912761214,
|
| 1520 |
+
"eval_loss": 0.22664275765419006,
|
| 1521 |
+
"eval_runtime": 0.1852,
|
| 1522 |
+
"eval_samples_per_second": 27.002,
|
| 1523 |
+
"eval_steps_per_second": 5.4,
|
| 1524 |
+
"step": 5050
|
| 1525 |
+
},
|
| 1526 |
+
{
|
| 1527 |
+
"epoch": 1.0063737001006374,
|
| 1528 |
+
"grad_norm": 0.1731952726840973,
|
| 1529 |
+
"learning_rate": 0.00011980640776621077,
|
| 1530 |
+
"loss": 0.2843,
|
| 1531 |
+
"step": 5100
|
| 1532 |
+
},
|
| 1533 |
+
{
|
| 1534 |
+
"epoch": 1.0063737001006374,
|
| 1535 |
+
"eval_loss": 0.22769823670387268,
|
| 1536 |
+
"eval_runtime": 0.185,
|
| 1537 |
+
"eval_samples_per_second": 27.027,
|
| 1538 |
+
"eval_steps_per_second": 5.405,
|
| 1539 |
+
"step": 5100
|
| 1540 |
+
},
|
| 1541 |
+
{
|
| 1542 |
+
"epoch": 1.0162401089251534,
|
| 1543 |
+
"grad_norm": 0.21639849245548248,
|
| 1544 |
+
"learning_rate": 0.0001180800443490566,
|
| 1545 |
+
"loss": 0.2744,
|
| 1546 |
+
"step": 5150
|
| 1547 |
+
},
|
| 1548 |
+
{
|
| 1549 |
+
"epoch": 1.0162401089251534,
|
| 1550 |
+
"eval_loss": 0.23013372719287872,
|
| 1551 |
+
"eval_runtime": 0.1844,
|
| 1552 |
+
"eval_samples_per_second": 27.117,
|
| 1553 |
+
"eval_steps_per_second": 5.423,
|
| 1554 |
+
"step": 5150
|
| 1555 |
+
},
|
| 1556 |
+
{
|
| 1557 |
+
"epoch": 1.0261065177496695,
|
| 1558 |
+
"grad_norm": 0.2546159625053406,
|
| 1559 |
+
"learning_rate": 0.0001163480919054998,
|
| 1560 |
+
"loss": 0.2745,
|
| 1561 |
+
"step": 5200
|
| 1562 |
+
},
|
| 1563 |
+
{
|
| 1564 |
+
"epoch": 1.0261065177496695,
|
| 1565 |
+
"eval_loss": 0.22475233674049377,
|
| 1566 |
+
"eval_runtime": 0.1858,
|
| 1567 |
+
"eval_samples_per_second": 26.911,
|
| 1568 |
+
"eval_steps_per_second": 5.382,
|
| 1569 |
+
"step": 5200
|
| 1570 |
+
},
|
| 1571 |
+
{
|
| 1572 |
+
"epoch": 1.0359729265741855,
|
| 1573 |
+
"grad_norm": 0.21476522088050842,
|
| 1574 |
+
"learning_rate": 0.00011461108582847126,
|
| 1575 |
+
"loss": 0.2734,
|
| 1576 |
+
"step": 5250
|
| 1577 |
+
},
|
| 1578 |
+
{
|
| 1579 |
+
"epoch": 1.0359729265741855,
|
| 1580 |
+
"eval_loss": 0.22389909625053406,
|
| 1581 |
+
"eval_runtime": 0.1847,
|
| 1582 |
+
"eval_samples_per_second": 27.07,
|
| 1583 |
+
"eval_steps_per_second": 5.414,
|
| 1584 |
+
"step": 5250
|
| 1585 |
+
},
|
| 1586 |
+
{
|
| 1587 |
+
"epoch": 1.0458393353987017,
|
| 1588 |
+
"grad_norm": 0.21301063895225525,
|
| 1589 |
+
"learning_rate": 0.00011286956307311555,
|
| 1590 |
+
"loss": 0.2703,
|
| 1591 |
+
"step": 5300
|
| 1592 |
+
},
|
| 1593 |
+
{
|
| 1594 |
+
"epoch": 1.0458393353987017,
|
| 1595 |
+
"eval_loss": 0.2267945110797882,
|
| 1596 |
+
"eval_runtime": 0.1843,
|
| 1597 |
+
"eval_samples_per_second": 27.135,
|
| 1598 |
+
"eval_steps_per_second": 5.427,
|
| 1599 |
+
"step": 5300
|
| 1600 |
+
},
|
| 1601 |
+
{
|
| 1602 |
+
"epoch": 1.0557057442232176,
|
| 1603 |
+
"grad_norm": 0.221356600522995,
|
| 1604 |
+
"learning_rate": 0.00011112406199080346,
|
| 1605 |
+
"loss": 0.2717,
|
| 1606 |
+
"step": 5350
|
| 1607 |
+
},
|
| 1608 |
+
{
|
| 1609 |
+
"epoch": 1.0557057442232176,
|
| 1610 |
+
"eval_loss": 0.2249325066804886,
|
| 1611 |
+
"eval_runtime": 0.1846,
|
| 1612 |
+
"eval_samples_per_second": 27.078,
|
| 1613 |
+
"eval_steps_per_second": 5.416,
|
| 1614 |
+
"step": 5350
|
| 1615 |
+
},
|
| 1616 |
+
{
|
| 1617 |
+
"epoch": 1.0655721530477338,
|
| 1618 |
+
"grad_norm": 0.22443543374538422,
|
| 1619 |
+
"learning_rate": 0.00010937512216271338,
|
| 1620 |
+
"loss": 0.2705,
|
| 1621 |
+
"step": 5400
|
| 1622 |
+
},
|
| 1623 |
+
{
|
| 1624 |
+
"epoch": 1.0655721530477338,
|
| 1625 |
+
"eval_loss": 0.2256511151790619,
|
| 1626 |
+
"eval_runtime": 0.1845,
|
| 1627 |
+
"eval_samples_per_second": 27.097,
|
| 1628 |
+
"eval_steps_per_second": 5.419,
|
| 1629 |
+
"step": 5400
|
| 1630 |
+
},
|
| 1631 |
+
{
|
| 1632 |
+
"epoch": 1.0754385618722497,
|
| 1633 |
+
"grad_norm": 0.20267891883850098,
|
| 1634 |
+
"learning_rate": 0.00010762328423303218,
|
| 1635 |
+
"loss": 0.2735,
|
| 1636 |
+
"step": 5450
|
| 1637 |
+
},
|
| 1638 |
+
{
|
| 1639 |
+
"epoch": 1.0754385618722497,
|
| 1640 |
+
"eval_loss": 0.22567923367023468,
|
| 1641 |
+
"eval_runtime": 0.1846,
|
| 1642 |
+
"eval_samples_per_second": 27.086,
|
| 1643 |
+
"eval_steps_per_second": 5.417,
|
| 1644 |
+
"step": 5450
|
| 1645 |
+
},
|
| 1646 |
+
{
|
| 1647 |
+
"epoch": 1.085304970696766,
|
| 1648 |
+
"grad_norm": 0.21884013712406158,
|
| 1649 |
+
"learning_rate": 0.00010586908974182767,
|
| 1650 |
+
"loss": 0.2756,
|
| 1651 |
+
"step": 5500
|
| 1652 |
+
},
|
| 1653 |
+
{
|
| 1654 |
+
"epoch": 1.085304970696766,
|
| 1655 |
+
"eval_loss": 0.22433491051197052,
|
| 1656 |
+
"eval_runtime": 0.1847,
|
| 1657 |
+
"eval_samples_per_second": 27.077,
|
| 1658 |
+
"eval_steps_per_second": 5.415,
|
| 1659 |
+
"step": 5500
|
| 1660 |
+
},
|
| 1661 |
+
{
|
| 1662 |
+
"epoch": 1.0951713795212819,
|
| 1663 |
+
"grad_norm": 0.21301575005054474,
|
| 1664 |
+
"learning_rate": 0.00010411308095764393,
|
| 1665 |
+
"loss": 0.2714,
|
| 1666 |
+
"step": 5550
|
| 1667 |
+
},
|
| 1668 |
+
{
|
| 1669 |
+
"epoch": 1.0951713795212819,
|
| 1670 |
+
"eval_loss": 0.22806711494922638,
|
| 1671 |
+
"eval_runtime": 0.1844,
|
| 1672 |
+
"eval_samples_per_second": 27.113,
|
| 1673 |
+
"eval_steps_per_second": 5.423,
|
| 1674 |
+
"step": 5550
|
| 1675 |
+
},
|
| 1676 |
+
{
|
| 1677 |
+
"epoch": 1.1050377883457978,
|
| 1678 |
+
"grad_norm": 0.3255505859851837,
|
| 1679 |
+
"learning_rate": 0.0001023558007098717,
|
| 1680 |
+
"loss": 0.2715,
|
| 1681 |
+
"step": 5600
|
| 1682 |
+
},
|
| 1683 |
+
{
|
| 1684 |
+
"epoch": 1.1050377883457978,
|
| 1685 |
+
"eval_loss": 0.22649523615837097,
|
| 1686 |
+
"eval_runtime": 0.1848,
|
| 1687 |
+
"eval_samples_per_second": 27.059,
|
| 1688 |
+
"eval_steps_per_second": 5.412,
|
| 1689 |
+
"step": 5600
|
| 1690 |
+
},
|
| 1691 |
+
{
|
| 1692 |
+
"epoch": 1.114904197170314,
|
| 1693 |
+
"grad_norm": 0.30551499128341675,
|
| 1694 |
+
"learning_rate": 0.00010059779222094512,
|
| 1695 |
+
"loss": 0.2737,
|
| 1696 |
+
"step": 5650
|
| 1697 |
+
},
|
| 1698 |
+
{
|
| 1699 |
+
"epoch": 1.114904197170314,
|
| 1700 |
+
"eval_loss": 0.2232808619737625,
|
| 1701 |
+
"eval_runtime": 0.1871,
|
| 1702 |
+
"eval_samples_per_second": 26.725,
|
| 1703 |
+
"eval_steps_per_second": 5.345,
|
| 1704 |
+
"step": 5650
|
| 1705 |
+
},
|
| 1706 |
+
{
|
| 1707 |
+
"epoch": 1.12477060599483,
|
| 1708 |
+
"grad_norm": 0.23381146788597107,
|
| 1709 |
+
"learning_rate": 9.88395989384173e-05,
|
| 1710 |
+
"loss": 0.2709,
|
| 1711 |
+
"step": 5700
|
| 1712 |
+
},
|
| 1713 |
+
{
|
| 1714 |
+
"epoch": 1.12477060599483,
|
| 1715 |
+
"eval_loss": 0.22571022808551788,
|
| 1716 |
+
"eval_runtime": 0.1849,
|
| 1717 |
+
"eval_samples_per_second": 27.039,
|
| 1718 |
+
"eval_steps_per_second": 5.408,
|
| 1719 |
+
"step": 5700
|
| 1720 |
+
},
|
| 1721 |
+
{
|
| 1722 |
+
"epoch": 1.134637014819346,
|
| 1723 |
+
"grad_norm": 0.20602265000343323,
|
| 1724 |
+
"learning_rate": 9.708176436696595e-05,
|
| 1725 |
+
"loss": 0.2721,
|
| 1726 |
+
"step": 5750
|
| 1727 |
+
},
|
| 1728 |
+
{
|
| 1729 |
+
"epoch": 1.134637014819346,
|
| 1730 |
+
"eval_loss": 0.2223341017961502,
|
| 1731 |
+
"eval_runtime": 0.1843,
|
| 1732 |
+
"eval_samples_per_second": 27.136,
|
| 1733 |
+
"eval_steps_per_second": 5.427,
|
| 1734 |
+
"step": 5750
|
| 1735 |
+
},
|
| 1736 |
+
{
|
| 1737 |
+
"epoch": 1.144503423643862,
|
| 1738 |
+
"grad_norm": 0.210631862282753,
|
| 1739 |
+
"learning_rate": 9.532483190038153e-05,
|
| 1740 |
+
"loss": 0.2679,
|
| 1741 |
+
"step": 5800
|
| 1742 |
+
},
|
| 1743 |
+
{
|
| 1744 |
+
"epoch": 1.144503423643862,
|
| 1745 |
+
"eval_loss": 0.2227615863084793,
|
| 1746 |
+
"eval_runtime": 0.185,
|
| 1747 |
+
"eval_samples_per_second": 27.02,
|
| 1748 |
+
"eval_steps_per_second": 5.404,
|
| 1749 |
+
"step": 5800
|
| 1750 |
+
},
|
| 1751 |
+
{
|
| 1752 |
+
"epoch": 1.1543698324683782,
|
| 1753 |
+
"grad_norm": 0.2317020148038864,
|
| 1754 |
+
"learning_rate": 9.356934465358979e-05,
|
| 1755 |
+
"loss": 0.272,
|
| 1756 |
+
"step": 5850
|
| 1757 |
+
},
|
| 1758 |
+
{
|
| 1759 |
+
"epoch": 1.1543698324683782,
|
| 1760 |
+
"eval_loss": 0.2202722728252411,
|
| 1761 |
+
"eval_runtime": 0.1846,
|
| 1762 |
+
"eval_samples_per_second": 27.087,
|
| 1763 |
+
"eval_steps_per_second": 5.417,
|
| 1764 |
+
"step": 5850
|
| 1765 |
+
},
|
| 1766 |
+
{
|
| 1767 |
+
"epoch": 1.1642362412928942,
|
| 1768 |
+
"grad_norm": 0.2153208702802658,
|
| 1769 |
+
"learning_rate": 9.181584529476025e-05,
|
| 1770 |
+
"loss": 0.2705,
|
| 1771 |
+
"step": 5900
|
| 1772 |
+
},
|
| 1773 |
+
{
|
| 1774 |
+
"epoch": 1.1642362412928942,
|
| 1775 |
+
"eval_loss": 0.2222643345594406,
|
| 1776 |
+
"eval_runtime": 0.1845,
|
| 1777 |
+
"eval_samples_per_second": 27.105,
|
| 1778 |
+
"eval_steps_per_second": 5.421,
|
| 1779 |
+
"step": 5900
|
| 1780 |
+
},
|
| 1781 |
+
{
|
| 1782 |
+
"epoch": 1.1741026501174103,
|
| 1783 |
+
"grad_norm": 0.26965272426605225,
|
| 1784 |
+
"learning_rate": 9.006487587755295e-05,
|
| 1785 |
+
"loss": 0.2699,
|
| 1786 |
+
"step": 5950
|
| 1787 |
+
},
|
| 1788 |
+
{
|
| 1789 |
+
"epoch": 1.1741026501174103,
|
| 1790 |
+
"eval_loss": 0.218417689204216,
|
| 1791 |
+
"eval_runtime": 0.1846,
|
| 1792 |
+
"eval_samples_per_second": 27.091,
|
| 1793 |
+
"eval_steps_per_second": 5.418,
|
| 1794 |
+
"step": 5950
|
| 1795 |
+
},
|
| 1796 |
+
{
|
| 1797 |
+
"epoch": 1.1839690589419263,
|
| 1798 |
+
"grad_norm": 0.21898072957992554,
|
| 1799 |
+
"learning_rate": 8.831697767355519e-05,
|
| 1800 |
+
"loss": 0.2698,
|
| 1801 |
+
"step": 6000
|
| 1802 |
+
},
|
| 1803 |
+
{
|
| 1804 |
+
"epoch": 1.1839690589419263,
|
| 1805 |
+
"eval_loss": 0.22147616744041443,
|
| 1806 |
+
"eval_runtime": 0.1855,
|
| 1807 |
+
"eval_samples_per_second": 26.955,
|
| 1808 |
+
"eval_steps_per_second": 5.391,
|
| 1809 |
+
"step": 6000
|
| 1810 |
+
},
|
| 1811 |
+
{
|
| 1812 |
+
"epoch": 1.1938354677664424,
|
| 1813 |
+
"grad_norm": 0.19538186490535736,
|
| 1814 |
+
"learning_rate": 8.65726910049599e-05,
|
| 1815 |
+
"loss": 0.2683,
|
| 1816 |
+
"step": 6050
|
| 1817 |
+
},
|
| 1818 |
+
{
|
| 1819 |
+
"epoch": 1.1938354677664424,
|
| 1820 |
+
"eval_loss": 0.21991392970085144,
|
| 1821 |
+
"eval_runtime": 0.1851,
|
| 1822 |
+
"eval_samples_per_second": 27.012,
|
| 1823 |
+
"eval_steps_per_second": 5.402,
|
| 1824 |
+
"step": 6050
|
| 1825 |
+
},
|
| 1826 |
+
{
|
| 1827 |
+
"epoch": 1.2037018765909584,
|
| 1828 |
+
"grad_norm": 0.21497651934623718,
|
| 1829 |
+
"learning_rate": 8.483255507753762e-05,
|
| 1830 |
+
"loss": 0.2696,
|
| 1831 |
+
"step": 6100
|
| 1832 |
+
},
|
| 1833 |
+
{
|
| 1834 |
+
"epoch": 1.2037018765909584,
|
| 1835 |
+
"eval_loss": 0.22209680080413818,
|
| 1836 |
+
"eval_runtime": 0.1849,
|
| 1837 |
+
"eval_samples_per_second": 27.037,
|
| 1838 |
+
"eval_steps_per_second": 5.407,
|
| 1839 |
+
"step": 6100
|
| 1840 |
+
},
|
| 1841 |
+
{
|
| 1842 |
+
"epoch": 1.2135682854154746,
|
| 1843 |
+
"grad_norm": 0.2190115749835968,
|
| 1844 |
+
"learning_rate": 8.309710781395356e-05,
|
| 1845 |
+
"loss": 0.2676,
|
| 1846 |
+
"step": 6150
|
| 1847 |
+
},
|
| 1848 |
+
{
|
| 1849 |
+
"epoch": 1.2135682854154746,
|
| 1850 |
+
"eval_loss": 0.22349147498607635,
|
| 1851 |
+
"eval_runtime": 0.1845,
|
| 1852 |
+
"eval_samples_per_second": 27.1,
|
| 1853 |
+
"eval_steps_per_second": 5.42,
|
| 1854 |
+
"step": 6150
|
| 1855 |
+
},
|
| 1856 |
+
{
|
| 1857 |
+
"epoch": 1.2234346942399905,
|
| 1858 |
+
"grad_norm": 0.18856999278068542,
|
| 1859 |
+
"learning_rate": 8.136688568748113e-05,
|
| 1860 |
+
"loss": 0.2642,
|
| 1861 |
+
"step": 6200
|
| 1862 |
+
},
|
| 1863 |
+
{
|
| 1864 |
+
"epoch": 1.2234346942399905,
|
| 1865 |
+
"eval_loss": 0.2215404212474823,
|
| 1866 |
+
"eval_runtime": 0.1844,
|
| 1867 |
+
"eval_samples_per_second": 27.115,
|
| 1868 |
+
"eval_steps_per_second": 5.423,
|
| 1869 |
+
"step": 6200
|
| 1870 |
+
},
|
| 1871 |
+
{
|
| 1872 |
+
"epoch": 1.2333011030645067,
|
| 1873 |
+
"grad_norm": 0.2113649994134903,
|
| 1874 |
+
"learning_rate": 7.964242355616385e-05,
|
| 1875 |
+
"loss": 0.2702,
|
| 1876 |
+
"step": 6250
|
| 1877 |
+
},
|
| 1878 |
+
{
|
| 1879 |
+
"epoch": 1.2333011030645067,
|
| 1880 |
+
"eval_loss": 0.22224430739879608,
|
| 1881 |
+
"eval_runtime": 0.1851,
|
| 1882 |
+
"eval_samples_per_second": 27.018,
|
| 1883 |
+
"eval_steps_per_second": 5.404,
|
| 1884 |
+
"step": 6250
|
| 1885 |
+
},
|
| 1886 |
+
{
|
| 1887 |
+
"epoch": 1.2433056416125658,
|
| 1888 |
+
"grad_norm": 0.23301884531974792,
|
| 1889 |
+
"learning_rate": 7.792425449747635e-05,
|
| 1890 |
+
"loss": 0.2701,
|
| 1891 |
+
"step": 6300
|
| 1892 |
+
},
|
| 1893 |
+
{
|
| 1894 |
+
"epoch": 1.2433056416125658,
|
| 1895 |
+
"eval_loss": 0.22047898173332214,
|
| 1896 |
+
"eval_runtime": 0.1979,
|
| 1897 |
+
"eval_samples_per_second": 25.262,
|
| 1898 |
+
"eval_steps_per_second": 5.052,
|
| 1899 |
+
"step": 6300
|
| 1900 |
+
},
|
| 1901 |
+
{
|
| 1902 |
+
"epoch": 1.2531720504370818,
|
| 1903 |
+
"grad_norm": 0.211432546377182,
|
| 1904 |
+
"learning_rate": 7.621290964353581e-05,
|
| 1905 |
+
"loss": 0.2696,
|
| 1906 |
+
"step": 6350
|
| 1907 |
+
},
|
| 1908 |
+
{
|
| 1909 |
+
"epoch": 1.2531720504370818,
|
| 1910 |
+
"eval_loss": 0.22401615977287292,
|
| 1911 |
+
"eval_runtime": 0.1846,
|
| 1912 |
+
"eval_samples_per_second": 27.079,
|
| 1913 |
+
"eval_steps_per_second": 5.416,
|
| 1914 |
+
"step": 6350
|
| 1915 |
+
},
|
| 1916 |
+
{
|
| 1917 |
+
"epoch": 1.263038459261598,
|
| 1918 |
+
"grad_norm": 0.2142704576253891,
|
| 1919 |
+
"learning_rate": 7.450891801691468e-05,
|
| 1920 |
+
"loss": 0.2671,
|
| 1921 |
+
"step": 6400
|
| 1922 |
+
},
|
| 1923 |
+
{
|
| 1924 |
+
"epoch": 1.263038459261598,
|
| 1925 |
+
"eval_loss": 0.2236458957195282,
|
| 1926 |
+
"eval_runtime": 0.1853,
|
| 1927 |
+
"eval_samples_per_second": 26.977,
|
| 1928 |
+
"eval_steps_per_second": 5.395,
|
| 1929 |
+
"step": 6400
|
| 1930 |
+
},
|
| 1931 |
+
{
|
| 1932 |
+
"epoch": 1.2729048680861141,
|
| 1933 |
+
"grad_norm": 0.1931128203868866,
|
| 1934 |
+
"learning_rate": 7.281280636710576e-05,
|
| 1935 |
+
"loss": 0.269,
|
| 1936 |
+
"step": 6450
|
| 1937 |
+
},
|
| 1938 |
+
{
|
| 1939 |
+
"epoch": 1.2729048680861141,
|
| 1940 |
+
"eval_loss": 0.22148045897483826,
|
| 1941 |
+
"eval_runtime": 0.1846,
|
| 1942 |
+
"eval_samples_per_second": 27.085,
|
| 1943 |
+
"eval_steps_per_second": 5.417,
|
| 1944 |
+
"step": 6450
|
| 1945 |
+
},
|
| 1946 |
+
{
|
| 1947 |
+
"epoch": 1.28277127691063,
|
| 1948 |
+
"grad_norm": 0.2120596170425415,
|
| 1949 |
+
"learning_rate": 7.112509900768989e-05,
|
| 1950 |
+
"loss": 0.2692,
|
| 1951 |
+
"step": 6500
|
| 1952 |
+
},
|
| 1953 |
+
{
|
| 1954 |
+
"epoch": 1.28277127691063,
|
| 1955 |
+
"eval_loss": 0.2202589511871338,
|
| 1956 |
+
"eval_runtime": 0.1852,
|
| 1957 |
+
"eval_samples_per_second": 27.003,
|
| 1958 |
+
"eval_steps_per_second": 5.401,
|
| 1959 |
+
"step": 6500
|
| 1960 |
+
},
|
| 1961 |
+
{
|
| 1962 |
+
"epoch": 1.292637685735146,
|
| 1963 |
+
"grad_norm": 0.20692607760429382,
|
| 1964 |
+
"learning_rate": 6.944631765425629e-05,
|
| 1965 |
+
"loss": 0.2647,
|
| 1966 |
+
"step": 6550
|
| 1967 |
+
},
|
| 1968 |
+
{
|
| 1969 |
+
"epoch": 1.292637685735146,
|
| 1970 |
+
"eval_loss": 0.2197343409061432,
|
| 1971 |
+
"eval_runtime": 0.185,
|
| 1972 |
+
"eval_samples_per_second": 27.031,
|
| 1973 |
+
"eval_steps_per_second": 5.406,
|
| 1974 |
+
"step": 6550
|
| 1975 |
+
},
|
| 1976 |
+
{
|
| 1977 |
+
"epoch": 1.3025040945596622,
|
| 1978 |
+
"grad_norm": 0.2301376610994339,
|
| 1979 |
+
"learning_rate": 6.777698126312647e-05,
|
| 1980 |
+
"loss": 0.2647,
|
| 1981 |
+
"step": 6600
|
| 1982 |
+
},
|
| 1983 |
+
{
|
| 1984 |
+
"epoch": 1.3025040945596622,
|
| 1985 |
+
"eval_loss": 0.2176646739244461,
|
| 1986 |
+
"eval_runtime": 0.1857,
|
| 1987 |
+
"eval_samples_per_second": 26.923,
|
| 1988 |
+
"eval_steps_per_second": 5.385,
|
| 1989 |
+
"step": 6600
|
| 1990 |
+
},
|
| 1991 |
+
{
|
| 1992 |
+
"epoch": 1.3123705033841782,
|
| 1993 |
+
"grad_norm": 0.2805488705635071,
|
| 1994 |
+
"learning_rate": 6.611760587093094e-05,
|
| 1995 |
+
"loss": 0.2635,
|
| 1996 |
+
"step": 6650
|
| 1997 |
+
},
|
| 1998 |
+
{
|
| 1999 |
+
"epoch": 1.3123705033841782,
|
| 2000 |
+
"eval_loss": 0.21856221556663513,
|
| 2001 |
+
"eval_runtime": 0.185,
|
| 2002 |
+
"eval_samples_per_second": 27.033,
|
| 2003 |
+
"eval_steps_per_second": 5.407,
|
| 2004 |
+
"step": 6650
|
| 2005 |
+
},
|
| 2006 |
+
{
|
| 2007 |
+
"epoch": 1.3222369122086943,
|
| 2008 |
+
"grad_norm": 0.2176360934972763,
|
| 2009 |
+
"learning_rate": 6.446870443508839e-05,
|
| 2010 |
+
"loss": 0.2628,
|
| 2011 |
+
"step": 6700
|
| 2012 |
+
},
|
| 2013 |
+
{
|
| 2014 |
+
"epoch": 1.3222369122086943,
|
| 2015 |
+
"eval_loss": 0.2163912057876587,
|
| 2016 |
+
"eval_runtime": 0.1848,
|
| 2017 |
+
"eval_samples_per_second": 27.054,
|
| 2018 |
+
"eval_steps_per_second": 5.411,
|
| 2019 |
+
"step": 6700
|
| 2020 |
+
},
|
| 2021 |
+
{
|
| 2022 |
+
"epoch": 1.3321033210332103,
|
| 2023 |
+
"grad_norm": 0.20765335857868195,
|
| 2024 |
+
"learning_rate": 6.283078667523681e-05,
|
| 2025 |
+
"loss": 0.2678,
|
| 2026 |
+
"step": 6750
|
| 2027 |
+
},
|
| 2028 |
+
{
|
| 2029 |
+
"epoch": 1.3321033210332103,
|
| 2030 |
+
"eval_loss": 0.2164166420698166,
|
| 2031 |
+
"eval_runtime": 0.1851,
|
| 2032 |
+
"eval_samples_per_second": 27.017,
|
| 2033 |
+
"eval_steps_per_second": 5.403,
|
| 2034 |
+
"step": 6750
|
| 2035 |
+
},
|
| 2036 |
+
{
|
| 2037 |
+
"epoch": 1.3419697298577264,
|
| 2038 |
+
"grad_norm": 0.2131153792142868,
|
| 2039 |
+
"learning_rate": 6.120435891566542e-05,
|
| 2040 |
+
"loss": 0.266,
|
| 2041 |
+
"step": 6800
|
| 2042 |
+
},
|
| 2043 |
+
{
|
| 2044 |
+
"epoch": 1.3419697298577264,
|
| 2045 |
+
"eval_loss": 0.21605464816093445,
|
| 2046 |
+
"eval_runtime": 0.1847,
|
| 2047 |
+
"eval_samples_per_second": 27.077,
|
| 2048 |
+
"eval_steps_per_second": 5.415,
|
| 2049 |
+
"step": 6800
|
| 2050 |
+
},
|
| 2051 |
+
{
|
| 2052 |
+
"epoch": 1.3518361386822424,
|
| 2053 |
+
"grad_norm": 0.20908519625663757,
|
| 2054 |
+
"learning_rate": 5.9589923928796434e-05,
|
| 2055 |
+
"loss": 0.2646,
|
| 2056 |
+
"step": 6850
|
| 2057 |
+
},
|
| 2058 |
+
{
|
| 2059 |
+
"epoch": 1.3518361386822424,
|
| 2060 |
+
"eval_loss": 0.21923890709877014,
|
| 2061 |
+
"eval_runtime": 0.1847,
|
| 2062 |
+
"eval_samples_per_second": 27.068,
|
| 2063 |
+
"eval_steps_per_second": 5.414,
|
| 2064 |
+
"step": 6850
|
| 2065 |
+
},
|
| 2066 |
+
{
|
| 2067 |
+
"epoch": 1.3617025475067586,
|
| 2068 |
+
"grad_norm": 0.20536689460277557,
|
| 2069 |
+
"learning_rate": 5.7987980779764463e-05,
|
| 2070 |
+
"loss": 0.2631,
|
| 2071 |
+
"step": 6900
|
| 2072 |
+
},
|
| 2073 |
+
{
|
| 2074 |
+
"epoch": 1.3617025475067586,
|
| 2075 |
+
"eval_loss": 0.2201545685529709,
|
| 2076 |
+
"eval_runtime": 0.1848,
|
| 2077 |
+
"eval_samples_per_second": 27.055,
|
| 2078 |
+
"eval_steps_per_second": 5.411,
|
| 2079 |
+
"step": 6900
|
| 2080 |
+
},
|
| 2081 |
+
{
|
| 2082 |
+
"epoch": 1.3715689563312745,
|
| 2083 |
+
"grad_norm": 0.21380028128623962,
|
| 2084 |
+
"learning_rate": 5.639902467214212e-05,
|
| 2085 |
+
"loss": 0.2651,
|
| 2086 |
+
"step": 6950
|
| 2087 |
+
},
|
| 2088 |
+
{
|
| 2089 |
+
"epoch": 1.3715689563312745,
|
| 2090 |
+
"eval_loss": 0.2177874594926834,
|
| 2091 |
+
"eval_runtime": 0.1847,
|
| 2092 |
+
"eval_samples_per_second": 27.069,
|
| 2093 |
+
"eval_steps_per_second": 5.414,
|
| 2094 |
+
"step": 6950
|
| 2095 |
+
},
|
| 2096 |
+
{
|
| 2097 |
+
"epoch": 1.3814353651557907,
|
| 2098 |
+
"grad_norm": 0.2062164545059204,
|
| 2099 |
+
"learning_rate": 5.482354679485948e-05,
|
| 2100 |
+
"loss": 0.2715,
|
| 2101 |
+
"step": 7000
|
| 2102 |
+
},
|
| 2103 |
+
{
|
| 2104 |
+
"epoch": 1.3814353651557907,
|
| 2105 |
+
"eval_loss": 0.21779461205005646,
|
| 2106 |
+
"eval_runtime": 0.1846,
|
| 2107 |
+
"eval_samples_per_second": 27.086,
|
| 2108 |
+
"eval_steps_per_second": 5.417,
|
| 2109 |
+
"step": 7000
|
| 2110 |
+
},
|
| 2111 |
+
{
|
| 2112 |
+
"epoch": 1.3913017739803066,
|
| 2113 |
+
"grad_norm": 0.22111141681671143,
|
| 2114 |
+
"learning_rate": 5.326203417036413e-05,
|
| 2115 |
+
"loss": 0.2601,
|
| 2116 |
+
"step": 7050
|
| 2117 |
+
},
|
| 2118 |
+
{
|
| 2119 |
+
"epoch": 1.3913017739803066,
|
| 2120 |
+
"eval_loss": 0.2183108627796173,
|
| 2121 |
+
"eval_runtime": 0.1845,
|
| 2122 |
+
"eval_samples_per_second": 27.097,
|
| 2123 |
+
"eval_steps_per_second": 5.419,
|
| 2124 |
+
"step": 7050
|
| 2125 |
+
},
|
| 2126 |
+
{
|
| 2127 |
+
"epoch": 1.4011681828048226,
|
| 2128 |
+
"grad_norm": 0.2018529623746872,
|
| 2129 |
+
"learning_rate": 5.17149695040698e-05,
|
| 2130 |
+
"loss": 0.2658,
|
| 2131 |
+
"step": 7100
|
| 2132 |
+
},
|
| 2133 |
+
{
|
| 2134 |
+
"epoch": 1.4011681828048226,
|
| 2135 |
+
"eval_loss": 0.2196209877729416,
|
| 2136 |
+
"eval_runtime": 0.1848,
|
| 2137 |
+
"eval_samples_per_second": 27.049,
|
| 2138 |
+
"eval_steps_per_second": 5.41,
|
| 2139 |
+
"step": 7100
|
| 2140 |
+
},
|
| 2141 |
+
{
|
| 2142 |
+
"epoch": 1.4110345916293388,
|
| 2143 |
+
"grad_norm": 0.2138175666332245,
|
| 2144 |
+
"learning_rate": 5.01828310351389e-05,
|
| 2145 |
+
"loss": 0.2647,
|
| 2146 |
+
"step": 7150
|
| 2147 |
+
},
|
| 2148 |
+
{
|
| 2149 |
+
"epoch": 1.4110345916293388,
|
| 2150 |
+
"eval_loss": 0.21882668137550354,
|
| 2151 |
+
"eval_runtime": 0.1844,
|
| 2152 |
+
"eval_samples_per_second": 27.118,
|
| 2153 |
+
"eval_steps_per_second": 5.424,
|
| 2154 |
+
"step": 7150
|
| 2155 |
+
},
|
| 2156 |
+
{
|
| 2157 |
+
"epoch": 1.420901000453855,
|
| 2158 |
+
"grad_norm": 0.21395103633403778,
|
| 2159 |
+
"learning_rate": 4.866609238864609e-05,
|
| 2160 |
+
"loss": 0.2614,
|
| 2161 |
+
"step": 7200
|
| 2162 |
+
},
|
| 2163 |
+
{
|
| 2164 |
+
"epoch": 1.420901000453855,
|
| 2165 |
+
"eval_loss": 0.21599645912647247,
|
| 2166 |
+
"eval_runtime": 0.1865,
|
| 2167 |
+
"eval_samples_per_second": 26.812,
|
| 2168 |
+
"eval_steps_per_second": 5.362,
|
| 2169 |
+
"step": 7200
|
| 2170 |
+
},
|
| 2171 |
+
{
|
| 2172 |
+
"epoch": 1.4307674092783709,
|
| 2173 |
+
"grad_norm": 0.19431644678115845,
|
| 2174 |
+
"learning_rate": 4.7165222429168156e-05,
|
| 2175 |
+
"loss": 0.2631,
|
| 2176 |
+
"step": 7250
|
| 2177 |
+
},
|
| 2178 |
+
{
|
| 2179 |
+
"epoch": 1.4307674092783709,
|
| 2180 |
+
"eval_loss": 0.21445360779762268,
|
| 2181 |
+
"eval_runtime": 0.1853,
|
| 2182 |
+
"eval_samples_per_second": 26.984,
|
| 2183 |
+
"eval_steps_per_second": 5.397,
|
| 2184 |
+
"step": 7250
|
| 2185 |
+
},
|
| 2186 |
+
{
|
| 2187 |
+
"epoch": 1.4406338181028868,
|
| 2188 |
+
"grad_norm": 0.2003539353609085,
|
| 2189 |
+
"learning_rate": 4.568068511584529e-05,
|
| 2190 |
+
"loss": 0.2619,
|
| 2191 |
+
"step": 7300
|
| 2192 |
+
},
|
| 2193 |
+
{
|
| 2194 |
+
"epoch": 1.4406338181028868,
|
| 2195 |
+
"eval_loss": 0.21582575142383575,
|
| 2196 |
+
"eval_runtime": 0.1846,
|
| 2197 |
+
"eval_samples_per_second": 27.092,
|
| 2198 |
+
"eval_steps_per_second": 5.418,
|
| 2199 |
+
"step": 7300
|
| 2200 |
+
},
|
| 2201 |
+
{
|
| 2202 |
+
"epoch": 1.450500226927403,
|
| 2203 |
+
"grad_norm": 0.2108386605978012,
|
| 2204 |
+
"learning_rate": 4.421293935895882e-05,
|
| 2205 |
+
"loss": 0.2618,
|
| 2206 |
+
"step": 7350
|
| 2207 |
+
},
|
| 2208 |
+
{
|
| 2209 |
+
"epoch": 1.450500226927403,
|
| 2210 |
+
"eval_loss": 0.21553893387317657,
|
| 2211 |
+
"eval_runtime": 0.1856,
|
| 2212 |
+
"eval_samples_per_second": 26.942,
|
| 2213 |
+
"eval_steps_per_second": 5.388,
|
| 2214 |
+
"step": 7350
|
| 2215 |
+
},
|
| 2216 |
+
{
|
| 2217 |
+
"epoch": 1.460366635751919,
|
| 2218 |
+
"grad_norm": 0.2119232714176178,
|
| 2219 |
+
"learning_rate": 4.2762438878069955e-05,
|
| 2220 |
+
"loss": 0.2667,
|
| 2221 |
+
"step": 7400
|
| 2222 |
+
},
|
| 2223 |
+
{
|
| 2224 |
+
"epoch": 1.460366635751919,
|
| 2225 |
+
"eval_loss": 0.21502795815467834,
|
| 2226 |
+
"eval_runtime": 0.1851,
|
| 2227 |
+
"eval_samples_per_second": 27.012,
|
| 2228 |
+
"eval_steps_per_second": 5.402,
|
| 2229 |
+
"step": 7400
|
| 2230 |
+
},
|
| 2231 |
+
{
|
| 2232 |
+
"epoch": 1.470233044576435,
|
| 2233 |
+
"grad_norm": 0.2125096172094345,
|
| 2234 |
+
"learning_rate": 4.13296320617627e-05,
|
| 2235 |
+
"loss": 0.2625,
|
| 2236 |
+
"step": 7450
|
| 2237 |
+
},
|
| 2238 |
+
{
|
| 2239 |
+
"epoch": 1.470233044576435,
|
| 2240 |
+
"eval_loss": 0.2130458652973175,
|
| 2241 |
+
"eval_runtime": 0.1857,
|
| 2242 |
+
"eval_samples_per_second": 26.926,
|
| 2243 |
+
"eval_steps_per_second": 5.385,
|
| 2244 |
+
"step": 7450
|
| 2245 |
+
},
|
| 2246 |
+
{
|
| 2247 |
+
"epoch": 1.480099453400951,
|
| 2248 |
+
"grad_norm": 0.20715288817882538,
|
| 2249 |
+
"learning_rate": 3.991496182903498e-05,
|
| 2250 |
+
"loss": 0.2607,
|
| 2251 |
+
"step": 7500
|
| 2252 |
+
},
|
| 2253 |
+
{
|
| 2254 |
+
"epoch": 1.480099453400951,
|
| 2255 |
+
"eval_loss": 0.2125515192747116,
|
| 2256 |
+
"eval_runtime": 0.1855,
|
| 2257 |
+
"eval_samples_per_second": 26.953,
|
| 2258 |
+
"eval_steps_per_second": 5.391,
|
| 2259 |
+
"step": 7500
|
| 2260 |
+
},
|
| 2261 |
+
{
|
| 2262 |
+
"epoch": 1.4899658622254672,
|
| 2263 |
+
"grad_norm": 0.19759340584278107,
|
| 2264 |
+
"learning_rate": 3.851886549238062e-05,
|
| 2265 |
+
"loss": 0.2596,
|
| 2266 |
+
"step": 7550
|
| 2267 |
+
},
|
| 2268 |
+
{
|
| 2269 |
+
"epoch": 1.4899658622254672,
|
| 2270 |
+
"eval_loss": 0.2126692235469818,
|
| 2271 |
+
"eval_runtime": 0.1848,
|
| 2272 |
+
"eval_samples_per_second": 27.05,
|
| 2273 |
+
"eval_steps_per_second": 5.41,
|
| 2274 |
+
"step": 7550
|
| 2275 |
+
},
|
| 2276 |
+
{
|
| 2277 |
+
"epoch": 1.4998322710499832,
|
| 2278 |
+
"grad_norm": 0.1995980143547058,
|
| 2279 |
+
"learning_rate": 3.714177462260412e-05,
|
| 2280 |
+
"loss": 0.263,
|
| 2281 |
+
"step": 7600
|
| 2282 |
+
},
|
| 2283 |
+
{
|
| 2284 |
+
"epoch": 1.4998322710499832,
|
| 2285 |
+
"eval_loss": 0.2116161286830902,
|
| 2286 |
+
"eval_runtime": 0.1846,
|
| 2287 |
+
"eval_samples_per_second": 27.091,
|
| 2288 |
+
"eval_steps_per_second": 5.418,
|
| 2289 |
+
"step": 7600
|
| 2290 |
+
},
|
| 2291 |
+
{
|
| 2292 |
+
"epoch": 1.5096986798744991,
|
| 2293 |
+
"grad_norm": 0.23178283870220184,
|
| 2294 |
+
"learning_rate": 3.578411491541079e-05,
|
| 2295 |
+
"loss": 0.2623,
|
| 2296 |
+
"step": 7650
|
| 2297 |
+
},
|
| 2298 |
+
{
|
| 2299 |
+
"epoch": 1.5096986798744991,
|
| 2300 |
+
"eval_loss": 0.21194568276405334,
|
| 2301 |
+
"eval_runtime": 0.1847,
|
| 2302 |
+
"eval_samples_per_second": 27.075,
|
| 2303 |
+
"eval_steps_per_second": 5.415,
|
| 2304 |
+
"step": 7650
|
| 2305 |
+
},
|
| 2306 |
+
{
|
| 2307 |
+
"epoch": 1.5195650886990153,
|
| 2308 |
+
"grad_norm": 0.2182031124830246,
|
| 2309 |
+
"learning_rate": 3.444630605981256e-05,
|
| 2310 |
+
"loss": 0.2558,
|
| 2311 |
+
"step": 7700
|
| 2312 |
+
},
|
| 2313 |
+
{
|
| 2314 |
+
"epoch": 1.5195650886990153,
|
| 2315 |
+
"eval_loss": 0.21379950642585754,
|
| 2316 |
+
"eval_runtime": 0.1846,
|
| 2317 |
+
"eval_samples_per_second": 27.079,
|
| 2318 |
+
"eval_steps_per_second": 5.416,
|
| 2319 |
+
"step": 7700
|
| 2320 |
+
},
|
| 2321 |
+
{
|
| 2322 |
+
"epoch": 1.5294314975235315,
|
| 2323 |
+
"grad_norm": 0.2095683068037033,
|
| 2324 |
+
"learning_rate": 3.312876160839099e-05,
|
| 2325 |
+
"loss": 0.261,
|
| 2326 |
+
"step": 7750
|
| 2327 |
+
},
|
| 2328 |
+
{
|
| 2329 |
+
"epoch": 1.5294314975235315,
|
| 2330 |
+
"eval_loss": 0.21340413391590118,
|
| 2331 |
+
"eval_runtime": 0.1852,
|
| 2332 |
+
"eval_samples_per_second": 26.992,
|
| 2333 |
+
"eval_steps_per_second": 5.398,
|
| 2334 |
+
"step": 7750
|
| 2335 |
+
},
|
| 2336 |
+
{
|
| 2337 |
+
"epoch": 1.5392979063480474,
|
| 2338 |
+
"grad_norm": 0.2217652052640915,
|
| 2339 |
+
"learning_rate": 3.183188884945714e-05,
|
| 2340 |
+
"loss": 0.2615,
|
| 2341 |
+
"step": 7800
|
| 2342 |
+
},
|
| 2343 |
+
{
|
| 2344 |
+
"epoch": 1.5392979063480474,
|
| 2345 |
+
"eval_loss": 0.21244795620441437,
|
| 2346 |
+
"eval_runtime": 0.1841,
|
| 2347 |
+
"eval_samples_per_second": 27.163,
|
| 2348 |
+
"eval_steps_per_second": 5.433,
|
| 2349 |
+
"step": 7800
|
| 2350 |
+
},
|
| 2351 |
+
{
|
| 2352 |
+
"epoch": 1.5491643151725634,
|
| 2353 |
+
"grad_norm": 0.21375681459903717,
|
| 2354 |
+
"learning_rate": 3.055608868114761e-05,
|
| 2355 |
+
"loss": 0.2571,
|
| 2356 |
+
"step": 7850
|
| 2357 |
+
},
|
| 2358 |
+
{
|
| 2359 |
+
"epoch": 1.5491643151725634,
|
| 2360 |
+
"eval_loss": 0.21376018226146698,
|
| 2361 |
+
"eval_runtime": 0.1845,
|
| 2362 |
+
"eval_samples_per_second": 27.101,
|
| 2363 |
+
"eval_steps_per_second": 5.42,
|
| 2364 |
+
"step": 7850
|
| 2365 |
+
},
|
| 2366 |
+
{
|
| 2367 |
+
"epoch": 1.5590307239970795,
|
| 2368 |
+
"grad_norm": 0.22278694808483124,
|
| 2369 |
+
"learning_rate": 2.930175548749645e-05,
|
| 2370 |
+
"loss": 0.2614,
|
| 2371 |
+
"step": 7900
|
| 2372 |
+
},
|
| 2373 |
+
{
|
| 2374 |
+
"epoch": 1.5590307239970795,
|
| 2375 |
+
"eval_loss": 0.21383312344551086,
|
| 2376 |
+
"eval_runtime": 0.1851,
|
| 2377 |
+
"eval_samples_per_second": 27.013,
|
| 2378 |
+
"eval_steps_per_second": 5.403,
|
| 2379 |
+
"step": 7900
|
| 2380 |
+
},
|
| 2381 |
+
{
|
| 2382 |
+
"epoch": 1.5688971328215957,
|
| 2383 |
+
"grad_norm": 0.2054503709077835,
|
| 2384 |
+
"learning_rate": 2.806927701652029e-05,
|
| 2385 |
+
"loss": 0.2628,
|
| 2386 |
+
"step": 7950
|
| 2387 |
+
},
|
| 2388 |
+
{
|
| 2389 |
+
"epoch": 1.5688971328215957,
|
| 2390 |
+
"eval_loss": 0.21245412528514862,
|
| 2391 |
+
"eval_runtime": 0.1849,
|
| 2392 |
+
"eval_samples_per_second": 27.044,
|
| 2393 |
+
"eval_steps_per_second": 5.409,
|
| 2394 |
+
"step": 7950
|
| 2395 |
+
},
|
| 2396 |
+
{
|
| 2397 |
+
"epoch": 1.5787635416461117,
|
| 2398 |
+
"grad_norm": 0.20330142974853516,
|
| 2399 |
+
"learning_rate": 2.6859034260355042e-05,
|
| 2400 |
+
"loss": 0.2587,
|
| 2401 |
+
"step": 8000
|
| 2402 |
+
},
|
| 2403 |
+
{
|
| 2404 |
+
"epoch": 1.5787635416461117,
|
| 2405 |
+
"eval_loss": 0.21231678128242493,
|
| 2406 |
+
"eval_runtime": 0.1841,
|
| 2407 |
+
"eval_samples_per_second": 27.158,
|
| 2408 |
+
"eval_steps_per_second": 5.432,
|
| 2409 |
+
"step": 8000
|
| 2410 |
+
},
|
| 2411 |
+
{
|
| 2412 |
+
"epoch": 1.5886299504706276,
|
| 2413 |
+
"grad_norm": 0.20486824214458466,
|
| 2414 |
+
"learning_rate": 2.567140133748118e-05,
|
| 2415 |
+
"loss": 0.2584,
|
| 2416 |
+
"step": 8050
|
| 2417 |
+
},
|
| 2418 |
+
{
|
| 2419 |
+
"epoch": 1.5886299504706276,
|
| 2420 |
+
"eval_loss": 0.2128223478794098,
|
| 2421 |
+
"eval_runtime": 0.2002,
|
| 2422 |
+
"eval_samples_per_second": 24.971,
|
| 2423 |
+
"eval_steps_per_second": 4.994,
|
| 2424 |
+
"step": 8050
|
| 2425 |
+
},
|
| 2426 |
+
{
|
| 2427 |
+
"epoch": 1.5984963592951438,
|
| 2428 |
+
"grad_norm": 0.21578329801559448,
|
| 2429 |
+
"learning_rate": 2.4506745377073535e-05,
|
| 2430 |
+
"loss": 0.2581,
|
| 2431 |
+
"step": 8100
|
| 2432 |
+
},
|
| 2433 |
+
{
|
| 2434 |
+
"epoch": 1.5984963592951438,
|
| 2435 |
+
"eval_loss": 0.2118312120437622,
|
| 2436 |
+
"eval_runtime": 0.1883,
|
| 2437 |
+
"eval_samples_per_second": 26.558,
|
| 2438 |
+
"eval_steps_per_second": 5.312,
|
| 2439 |
+
"step": 8100
|
| 2440 |
+
},
|
| 2441 |
+
{
|
| 2442 |
+
"epoch": 1.60836276811966,
|
| 2443 |
+
"grad_norm": 0.21013592183589935,
|
| 2444 |
+
"learning_rate": 2.3365426405511802e-05,
|
| 2445 |
+
"loss": 0.2613,
|
| 2446 |
+
"step": 8150
|
| 2447 |
+
},
|
| 2448 |
+
{
|
| 2449 |
+
"epoch": 1.60836276811966,
|
| 2450 |
+
"eval_loss": 0.21296799182891846,
|
| 2451 |
+
"eval_runtime": 0.1872,
|
| 2452 |
+
"eval_samples_per_second": 26.709,
|
| 2453 |
+
"eval_steps_per_second": 5.342,
|
| 2454 |
+
"step": 8150
|
| 2455 |
+
},
|
| 2456 |
+
{
|
| 2457 |
+
"epoch": 1.618229176944176,
|
| 2458 |
+
"grad_norm": 0.22792735695838928,
|
| 2459 |
+
"learning_rate": 2.224779723508692e-05,
|
| 2460 |
+
"loss": 0.2592,
|
| 2461 |
+
"step": 8200
|
| 2462 |
+
},
|
| 2463 |
+
{
|
| 2464 |
+
"epoch": 1.618229176944176,
|
| 2465 |
+
"eval_loss": 0.2124718874692917,
|
| 2466 |
+
"eval_runtime": 0.1884,
|
| 2467 |
+
"eval_samples_per_second": 26.537,
|
| 2468 |
+
"eval_steps_per_second": 5.307,
|
| 2469 |
+
"step": 8200
|
| 2470 |
+
},
|
| 2471 |
+
{
|
| 2472 |
+
"epoch": 1.6280955857686918,
|
| 2473 |
+
"grad_norm": 0.2071530818939209,
|
| 2474 |
+
"learning_rate": 2.1154203354937074e-05,
|
| 2475 |
+
"loss": 0.2589,
|
| 2476 |
+
"step": 8250
|
| 2477 |
+
},
|
| 2478 |
+
{
|
| 2479 |
+
"epoch": 1.6280955857686918,
|
| 2480 |
+
"eval_loss": 0.21143141388893127,
|
| 2481 |
+
"eval_runtime": 0.1867,
|
| 2482 |
+
"eval_samples_per_second": 26.788,
|
| 2483 |
+
"eval_steps_per_second": 5.358,
|
| 2484 |
+
"step": 8250
|
| 2485 |
+
},
|
| 2486 |
+
{
|
| 2487 |
+
"epoch": 1.637961994593208,
|
| 2488 |
+
"grad_norm": 0.2163563370704651,
|
| 2489 |
+
"learning_rate": 2.0084982824248034e-05,
|
| 2490 |
+
"loss": 0.2591,
|
| 2491 |
+
"step": 8300
|
| 2492 |
+
},
|
| 2493 |
+
{
|
| 2494 |
+
"epoch": 1.637961994593208,
|
| 2495 |
+
"eval_loss": 0.2110225409269333,
|
| 2496 |
+
"eval_runtime": 0.188,
|
| 2497 |
+
"eval_samples_per_second": 26.59,
|
| 2498 |
+
"eval_steps_per_second": 5.318,
|
| 2499 |
+
"step": 8300
|
| 2500 |
+
},
|
| 2501 |
+
{
|
| 2502 |
+
"epoch": 1.647828403417724,
|
| 2503 |
+
"grad_norm": 0.1936330944299698,
|
| 2504 |
+
"learning_rate": 1.9040466167749727e-05,
|
| 2505 |
+
"loss": 0.2574,
|
| 2506 |
+
"step": 8350
|
| 2507 |
+
},
|
| 2508 |
+
{
|
| 2509 |
+
"epoch": 1.647828403417724,
|
| 2510 |
+
"eval_loss": 0.21078595519065857,
|
| 2511 |
+
"eval_runtime": 0.1871,
|
| 2512 |
+
"eval_samples_per_second": 26.723,
|
| 2513 |
+
"eval_steps_per_second": 5.345,
|
| 2514 |
+
"step": 8350
|
| 2515 |
+
},
|
| 2516 |
+
{
|
| 2517 |
+
"epoch": 1.65769481224224,
|
| 2518 |
+
"grad_norm": 0.20487622916698456,
|
| 2519 |
+
"learning_rate": 1.802097627354231e-05,
|
| 2520 |
+
"loss": 0.2602,
|
| 2521 |
+
"step": 8400
|
| 2522 |
+
},
|
| 2523 |
+
{
|
| 2524 |
+
"epoch": 1.65769481224224,
|
| 2525 |
+
"eval_loss": 0.21095280349254608,
|
| 2526 |
+
"eval_runtime": 0.1863,
|
| 2527 |
+
"eval_samples_per_second": 26.838,
|
| 2528 |
+
"eval_steps_per_second": 5.368,
|
| 2529 |
+
"step": 8400
|
| 2530 |
+
},
|
| 2531 |
+
{
|
| 2532 |
+
"epoch": 1.667561221066756,
|
| 2533 |
+
"grad_norm": 0.20645365118980408,
|
| 2534 |
+
"learning_rate": 1.7026828293282892e-05,
|
| 2535 |
+
"loss": 0.2607,
|
| 2536 |
+
"step": 8450
|
| 2537 |
+
},
|
| 2538 |
+
{
|
| 2539 |
+
"epoch": 1.667561221066756,
|
| 2540 |
+
"eval_loss": 0.2102348506450653,
|
| 2541 |
+
"eval_runtime": 0.187,
|
| 2542 |
+
"eval_samples_per_second": 26.732,
|
| 2543 |
+
"eval_steps_per_second": 5.346,
|
| 2544 |
+
"step": 8450
|
| 2545 |
+
},
|
| 2546 |
+
{
|
| 2547 |
+
"epoch": 1.6774276298912723,
|
| 2548 |
+
"grad_norm": 0.21055789291858673,
|
| 2549 |
+
"learning_rate": 1.605832954476346e-05,
|
| 2550 |
+
"loss": 0.2567,
|
| 2551 |
+
"step": 8500
|
| 2552 |
+
},
|
| 2553 |
+
{
|
| 2554 |
+
"epoch": 1.6774276298912723,
|
| 2555 |
+
"eval_loss": 0.2107050120830536,
|
| 2556 |
+
"eval_runtime": 0.1878,
|
| 2557 |
+
"eval_samples_per_second": 26.618,
|
| 2558 |
+
"eval_steps_per_second": 5.324,
|
| 2559 |
+
"step": 8500
|
| 2560 |
+
},
|
| 2561 |
+
{
|
| 2562 |
+
"epoch": 1.6872940387157882,
|
| 2563 |
+
"grad_norm": 0.1864519864320755,
|
| 2564 |
+
"learning_rate": 1.5115779416911014e-05,
|
| 2565 |
+
"loss": 0.2568,
|
| 2566 |
+
"step": 8550
|
| 2567 |
+
},
|
| 2568 |
+
{
|
| 2569 |
+
"epoch": 1.6872940387157882,
|
| 2570 |
+
"eval_loss": 0.21016505360603333,
|
| 2571 |
+
"eval_runtime": 0.1867,
|
| 2572 |
+
"eval_samples_per_second": 26.788,
|
| 2573 |
+
"eval_steps_per_second": 5.358,
|
| 2574 |
+
"step": 8550
|
| 2575 |
+
},
|
| 2576 |
+
{
|
| 2577 |
+
"epoch": 1.6971604475403042,
|
| 2578 |
+
"grad_norm": 0.2051512748003006,
|
| 2579 |
+
"learning_rate": 1.4199469277238143e-05,
|
| 2580 |
+
"loss": 0.2614,
|
| 2581 |
+
"step": 8600
|
| 2582 |
+
},
|
| 2583 |
+
{
|
| 2584 |
+
"epoch": 1.6971604475403042,
|
| 2585 |
+
"eval_loss": 0.21043357253074646,
|
| 2586 |
+
"eval_runtime": 0.1874,
|
| 2587 |
+
"eval_samples_per_second": 26.678,
|
| 2588 |
+
"eval_steps_per_second": 5.336,
|
| 2589 |
+
"step": 8600
|
| 2590 |
+
},
|
| 2591 |
+
{
|
| 2592 |
+
"epoch": 1.7070268563648203,
|
| 2593 |
+
"grad_norm": 0.21571016311645508,
|
| 2594 |
+
"learning_rate": 1.330968238177368e-05,
|
| 2595 |
+
"loss": 0.2563,
|
| 2596 |
+
"step": 8650
|
| 2597 |
+
},
|
| 2598 |
+
{
|
| 2599 |
+
"epoch": 1.7070268563648203,
|
| 2600 |
+
"eval_loss": 0.21016483008861542,
|
| 2601 |
+
"eval_runtime": 0.187,
|
| 2602 |
+
"eval_samples_per_second": 26.739,
|
| 2603 |
+
"eval_steps_per_second": 5.348,
|
| 2604 |
+
"step": 8650
|
| 2605 |
+
},
|
| 2606 |
+
{
|
| 2607 |
+
"epoch": 1.7168932651893365,
|
| 2608 |
+
"grad_norm": 0.2853296399116516,
|
| 2609 |
+
"learning_rate": 1.2446693787500697e-05,
|
| 2610 |
+
"loss": 0.2589,
|
| 2611 |
+
"step": 8700
|
| 2612 |
+
},
|
| 2613 |
+
{
|
| 2614 |
+
"epoch": 1.7168932651893365,
|
| 2615 |
+
"eval_loss": 0.21085257828235626,
|
| 2616 |
+
"eval_runtime": 0.1856,
|
| 2617 |
+
"eval_samples_per_second": 26.945,
|
| 2618 |
+
"eval_steps_per_second": 5.389,
|
| 2619 |
+
"step": 8700
|
| 2620 |
+
},
|
| 2621 |
+
{
|
| 2622 |
+
"epoch": 1.7267596740138524,
|
| 2623 |
+
"grad_norm": 0.19415363669395447,
|
| 2624 |
+
"learning_rate": 1.1610770267328852e-05,
|
| 2625 |
+
"loss": 0.2613,
|
| 2626 |
+
"step": 8750
|
| 2627 |
+
},
|
| 2628 |
+
{
|
| 2629 |
+
"epoch": 1.7267596740138524,
|
| 2630 |
+
"eval_loss": 0.21094462275505066,
|
| 2631 |
+
"eval_runtime": 0.1866,
|
| 2632 |
+
"eval_samples_per_second": 26.798,
|
| 2633 |
+
"eval_steps_per_second": 5.36,
|
| 2634 |
+
"step": 8750
|
| 2635 |
+
},
|
| 2636 |
+
{
|
| 2637 |
+
"epoch": 1.7366260828383684,
|
| 2638 |
+
"grad_norm": 0.20800048112869263,
|
| 2639 |
+
"learning_rate": 1.0802170227627873e-05,
|
| 2640 |
+
"loss": 0.2583,
|
| 2641 |
+
"step": 8800
|
| 2642 |
+
},
|
| 2643 |
+
{
|
| 2644 |
+
"epoch": 1.7366260828383684,
|
| 2645 |
+
"eval_loss": 0.21065060794353485,
|
| 2646 |
+
"eval_runtime": 0.187,
|
| 2647 |
+
"eval_samples_per_second": 26.739,
|
| 2648 |
+
"eval_steps_per_second": 5.348,
|
| 2649 |
+
"step": 8800
|
| 2650 |
+
},
|
| 2651 |
+
{
|
| 2652 |
+
"epoch": 1.7464924916628846,
|
| 2653 |
+
"grad_norm": 0.21770550310611725,
|
| 2654 |
+
"learning_rate": 1.0021143628347196e-05,
|
| 2655 |
+
"loss": 0.2634,
|
| 2656 |
+
"step": 8850
|
| 2657 |
+
},
|
| 2658 |
+
{
|
| 2659 |
+
"epoch": 1.7464924916628846,
|
| 2660 |
+
"eval_loss": 0.2107730358839035,
|
| 2661 |
+
"eval_runtime": 0.1872,
|
| 2662 |
+
"eval_samples_per_second": 26.713,
|
| 2663 |
+
"eval_steps_per_second": 5.343,
|
| 2664 |
+
"step": 8850
|
| 2665 |
+
},
|
| 2666 |
+
{
|
| 2667 |
+
"epoch": 1.7563589004874007,
|
| 2668 |
+
"grad_norm": 0.20711322128772736,
|
| 2669 |
+
"learning_rate": 9.26793190574664e-06,
|
| 2670 |
+
"loss": 0.2586,
|
| 2671 |
+
"step": 8900
|
| 2672 |
+
},
|
| 2673 |
+
{
|
| 2674 |
+
"epoch": 1.7563589004874007,
|
| 2675 |
+
"eval_loss": 0.21060581505298615,
|
| 2676 |
+
"eval_runtime": 0.1873,
|
| 2677 |
+
"eval_samples_per_second": 26.696,
|
| 2678 |
+
"eval_steps_per_second": 5.339,
|
| 2679 |
+
"step": 8900
|
| 2680 |
+
},
|
| 2681 |
+
{
|
| 2682 |
+
"epoch": 1.7662253093119167,
|
| 2683 |
+
"grad_norm": 0.1906907856464386,
|
| 2684 |
+
"learning_rate": 8.542767897761917e-06,
|
| 2685 |
+
"loss": 0.2579,
|
| 2686 |
+
"step": 8950
|
| 2687 |
+
},
|
| 2688 |
+
{
|
| 2689 |
+
"epoch": 1.7662253093119167,
|
| 2690 |
+
"eval_loss": 0.21017535030841827,
|
| 2691 |
+
"eval_runtime": 0.1865,
|
| 2692 |
+
"eval_samples_per_second": 26.808,
|
| 2693 |
+
"eval_steps_per_second": 5.362,
|
| 2694 |
+
"step": 8950
|
| 2695 |
+
},
|
| 2696 |
+
{
|
| 2697 |
+
"epoch": 1.7760917181364326,
|
| 2698 |
+
"grad_norm": 0.23783724009990692,
|
| 2699 |
+
"learning_rate": 7.845875772028289e-06,
|
| 2700 |
+
"loss": 0.257,
|
| 2701 |
+
"step": 9000
|
| 2702 |
+
},
|
| 2703 |
+
{
|
| 2704 |
+
"epoch": 1.7760917181364326,
|
| 2705 |
+
"eval_loss": 0.21030497550964355,
|
| 2706 |
+
"eval_runtime": 0.1866,
|
| 2707 |
+
"eval_samples_per_second": 26.796,
|
| 2708 |
+
"eval_steps_per_second": 5.359,
|
| 2709 |
+
"step": 9000
|
| 2710 |
+
},
|
| 2711 |
+
{
|
| 2712 |
+
"epoch": 1.7859581269609488,
|
| 2713 |
+
"grad_norm": 0.20180200040340424,
|
| 2714 |
+
"learning_rate": 7.177470956584253e-06,
|
| 2715 |
+
"loss": 0.2577,
|
| 2716 |
+
"step": 9050
|
| 2717 |
+
},
|
| 2718 |
+
{
|
| 2719 |
+
"epoch": 1.7859581269609488,
|
| 2720 |
+
"eval_loss": 0.21059055626392365,
|
| 2721 |
+
"eval_runtime": 3427.3667,
|
| 2722 |
+
"eval_samples_per_second": 0.001,
|
| 2723 |
+
"eval_steps_per_second": 0.0,
|
| 2724 |
+
"step": 9050
|
| 2725 |
+
},
|
| 2726 |
+
{
|
| 2727 |
+
"epoch": 1.795824535785465,
|
| 2728 |
+
"grad_norm": 0.19345524907112122,
|
| 2729 |
+
"learning_rate": 6.537760073277066e-06,
|
| 2730 |
+
"loss": 0.2569,
|
| 2731 |
+
"step": 9100
|
| 2732 |
+
},
|
| 2733 |
+
{
|
| 2734 |
+
"epoch": 1.795824535785465,
|
| 2735 |
+
"eval_loss": 0.21125975251197815,
|
| 2736 |
+
"eval_runtime": 0.187,
|
| 2737 |
+
"eval_samples_per_second": 26.737,
|
| 2738 |
+
"eval_steps_per_second": 5.347,
|
| 2739 |
+
"step": 9100
|
| 2740 |
+
},
|
| 2741 |
+
{
|
| 2742 |
+
"epoch": 1.8056909446099807,
|
| 2743 |
+
"grad_norm": 0.20590749382972717,
|
| 2744 |
+
"learning_rate": 5.926940873890263e-06,
|
| 2745 |
+
"loss": 0.2575,
|
| 2746 |
+
"step": 9150
|
| 2747 |
+
},
|
| 2748 |
+
{
|
| 2749 |
+
"epoch": 1.8056909446099807,
|
| 2750 |
+
"eval_loss": 0.21117892861366272,
|
| 2751 |
+
"eval_runtime": 0.1868,
|
| 2752 |
+
"eval_samples_per_second": 26.762,
|
| 2753 |
+
"eval_steps_per_second": 5.352,
|
| 2754 |
+
"step": 9150
|
| 2755 |
+
},
|
| 2756 |
+
{
|
| 2757 |
+
"epoch": 1.8155573534344969,
|
| 2758 |
+
"grad_norm": 0.22785334289073944,
|
| 2759 |
+
"learning_rate": 5.345202179013353e-06,
|
| 2760 |
+
"loss": 0.2593,
|
| 2761 |
+
"step": 9200
|
| 2762 |
+
},
|
| 2763 |
+
{
|
| 2764 |
+
"epoch": 1.8155573534344969,
|
| 2765 |
+
"eval_loss": 0.2109127938747406,
|
| 2766 |
+
"eval_runtime": 0.1867,
|
| 2767 |
+
"eval_samples_per_second": 26.785,
|
| 2768 |
+
"eval_steps_per_second": 5.357,
|
| 2769 |
+
"step": 9200
|
| 2770 |
+
},
|
| 2771 |
+
{
|
| 2772 |
+
"epoch": 1.825423762259013,
|
| 2773 |
+
"grad_norm": 0.20013581216335297,
|
| 2774 |
+
"learning_rate": 4.792723819672351e-06,
|
| 2775 |
+
"loss": 0.2564,
|
| 2776 |
+
"step": 9250
|
| 2777 |
+
},
|
| 2778 |
+
{
|
| 2779 |
+
"epoch": 1.825423762259013,
|
| 2780 |
+
"eval_loss": 0.21093535423278809,
|
| 2781 |
+
"eval_runtime": 0.1869,
|
| 2782 |
+
"eval_samples_per_second": 26.753,
|
| 2783 |
+
"eval_steps_per_second": 5.351,
|
| 2784 |
+
"step": 9250
|
| 2785 |
+
},
|
| 2786 |
+
{
|
| 2787 |
+
"epoch": 1.835290171083529,
|
| 2788 |
+
"grad_norm": 0.18782545626163483,
|
| 2789 |
+
"learning_rate": 4.269676581739079e-06,
|
| 2790 |
+
"loss": 0.2592,
|
| 2791 |
+
"step": 9300
|
| 2792 |
+
},
|
| 2793 |
+
{
|
| 2794 |
+
"epoch": 1.835290171083529,
|
| 2795 |
+
"eval_loss": 0.21116788685321808,
|
| 2796 |
+
"eval_runtime": 0.187,
|
| 2797 |
+
"eval_samples_per_second": 26.734,
|
| 2798 |
+
"eval_steps_per_second": 5.347,
|
| 2799 |
+
"step": 9300
|
| 2800 |
+
},
|
| 2801 |
+
{
|
| 2802 |
+
"epoch": 1.845156579908045,
|
| 2803 |
+
"grad_norm": 0.284829318523407,
|
| 2804 |
+
"learning_rate": 3.776222153136788e-06,
|
| 2805 |
+
"loss": 0.2616,
|
| 2806 |
+
"step": 9350
|
| 2807 |
+
},
|
| 2808 |
+
{
|
| 2809 |
+
"epoch": 1.845156579908045,
|
| 2810 |
+
"eval_loss": 0.2108537256717682,
|
| 2811 |
+
"eval_runtime": 0.187,
|
| 2812 |
+
"eval_samples_per_second": 26.739,
|
| 2813 |
+
"eval_steps_per_second": 5.348,
|
| 2814 |
+
"step": 9350
|
| 2815 |
+
},
|
| 2816 |
+
{
|
| 2817 |
+
"epoch": 1.855022988732561,
|
| 2818 |
+
"grad_norm": 0.21778038144111633,
|
| 2819 |
+
"learning_rate": 3.3125130738579922e-06,
|
| 2820 |
+
"loss": 0.2585,
|
| 2821 |
+
"step": 9400
|
| 2822 |
+
},
|
| 2823 |
+
{
|
| 2824 |
+
"epoch": 1.855022988732561,
|
| 2825 |
+
"eval_loss": 0.21062783896923065,
|
| 2826 |
+
"eval_runtime": 0.1869,
|
| 2827 |
+
"eval_samples_per_second": 26.748,
|
| 2828 |
+
"eval_steps_per_second": 5.35,
|
| 2829 |
+
"step": 9400
|
| 2830 |
+
},
|
| 2831 |
+
{
|
| 2832 |
+
"epoch": 1.8648893975570773,
|
| 2833 |
+
"grad_norm": 0.22620098292827606,
|
| 2834 |
+
"learning_rate": 2.878692688810314e-06,
|
| 2835 |
+
"loss": 0.2578,
|
| 2836 |
+
"step": 9450
|
| 2837 |
+
},
|
| 2838 |
+
{
|
| 2839 |
+
"epoch": 1.8648893975570773,
|
| 2840 |
+
"eval_loss": 0.21043607592582703,
|
| 2841 |
+
"eval_runtime": 0.187,
|
| 2842 |
+
"eval_samples_per_second": 26.734,
|
| 2843 |
+
"eval_steps_per_second": 5.347,
|
| 2844 |
+
"step": 9450
|
| 2845 |
+
},
|
| 2846 |
+
{
|
| 2847 |
+
"epoch": 1.8747558063815932,
|
| 2848 |
+
"grad_norm": 0.2136729210615158,
|
| 2849 |
+
"learning_rate": 2.4748951035047596e-06,
|
| 2850 |
+
"loss": 0.2605,
|
| 2851 |
+
"step": 9500
|
| 2852 |
+
},
|
| 2853 |
+
{
|
| 2854 |
+
"epoch": 1.8747558063815932,
|
| 2855 |
+
"eval_loss": 0.21055133640766144,
|
| 2856 |
+
"eval_runtime": 0.1877,
|
| 2857 |
+
"eval_samples_per_second": 26.643,
|
| 2858 |
+
"eval_steps_per_second": 5.329,
|
| 2859 |
+
"step": 9500
|
| 2860 |
+
},
|
| 2861 |
+
{
|
| 2862 |
+
"epoch": 1.8846222152061092,
|
| 2863 |
+
"grad_norm": 0.19579312205314636,
|
| 2864 |
+
"learning_rate": 2.101245142600039e-06,
|
| 2865 |
+
"loss": 0.2592,
|
| 2866 |
+
"step": 9550
|
| 2867 |
+
},
|
| 2868 |
+
{
|
| 2869 |
+
"epoch": 1.8846222152061092,
|
| 2870 |
+
"eval_loss": 0.21009139716625214,
|
| 2871 |
+
"eval_runtime": 0.1864,
|
| 2872 |
+
"eval_samples_per_second": 26.826,
|
| 2873 |
+
"eval_steps_per_second": 5.365,
|
| 2874 |
+
"step": 9550
|
| 2875 |
+
},
|
| 2876 |
+
{
|
| 2877 |
+
"epoch": 1.8944886240306253,
|
| 2878 |
+
"grad_norm": 0.2088346630334854,
|
| 2879 |
+
"learning_rate": 1.7578583113159962e-06,
|
| 2880 |
+
"loss": 0.2575,
|
| 2881 |
+
"step": 9600
|
| 2882 |
+
},
|
| 2883 |
+
{
|
| 2884 |
+
"epoch": 1.8944886240306253,
|
| 2885 |
+
"eval_loss": 0.21053215861320496,
|
| 2886 |
+
"eval_runtime": 0.1864,
|
| 2887 |
+
"eval_samples_per_second": 26.826,
|
| 2888 |
+
"eval_steps_per_second": 5.365,
|
| 2889 |
+
"step": 9600
|
| 2890 |
+
},
|
| 2891 |
+
{
|
| 2892 |
+
"epoch": 1.9043550328551415,
|
| 2893 |
+
"grad_norm": 0.23137839138507843,
|
| 2894 |
+
"learning_rate": 1.4448407597277392e-06,
|
| 2895 |
+
"loss": 0.2606,
|
| 2896 |
+
"step": 9650
|
| 2897 |
+
},
|
| 2898 |
+
{
|
| 2899 |
+
"epoch": 1.9043550328551415,
|
| 2900 |
+
"eval_loss": 0.21052584052085876,
|
| 2901 |
+
"eval_runtime": 0.1872,
|
| 2902 |
+
"eval_samples_per_second": 26.706,
|
| 2903 |
+
"eval_steps_per_second": 5.341,
|
| 2904 |
+
"step": 9650
|
| 2905 |
+
},
|
| 2906 |
+
{
|
| 2907 |
+
"epoch": 1.9142214416796575,
|
| 2908 |
+
"grad_norm": 0.21073339879512787,
|
| 2909 |
+
"learning_rate": 1.1622892499519421e-06,
|
| 2910 |
+
"loss": 0.2558,
|
| 2911 |
+
"step": 9700
|
| 2912 |
+
},
|
| 2913 |
+
{
|
| 2914 |
+
"epoch": 1.9142214416796575,
|
| 2915 |
+
"eval_loss": 0.21001854538917542,
|
| 2916 |
+
"eval_runtime": 0.1866,
|
| 2917 |
+
"eval_samples_per_second": 26.791,
|
| 2918 |
+
"eval_steps_per_second": 5.358,
|
| 2919 |
+
"step": 9700
|
| 2920 |
+
},
|
| 2921 |
+
{
|
| 2922 |
+
"epoch": 1.9240878505041734,
|
| 2923 |
+
"grad_norm": 0.20351086556911469,
|
| 2924 |
+
"learning_rate": 9.102911262349856e-07,
|
| 2925 |
+
"loss": 0.2534,
|
| 2926 |
+
"step": 9750
|
| 2927 |
+
},
|
| 2928 |
+
{
|
| 2929 |
+
"epoch": 1.9240878505041734,
|
| 2930 |
+
"eval_loss": 0.20996317267417908,
|
| 2931 |
+
"eval_runtime": 0.182,
|
| 2932 |
+
"eval_samples_per_second": 27.467,
|
| 2933 |
+
"eval_steps_per_second": 5.493,
|
| 2934 |
+
"step": 9750
|
| 2935 |
+
}
|
| 2936 |
+
],
|
| 2937 |
+
"logging_steps": 50,
|
| 2938 |
+
"max_steps": 10134,
|
| 2939 |
+
"num_input_tokens_seen": 0,
|
| 2940 |
+
"num_train_epochs": 2,
|
| 2941 |
+
"save_steps": 250,
|
| 2942 |
+
"stateful_callbacks": {
|
| 2943 |
+
"TrainerControl": {
|
| 2944 |
+
"args": {
|
| 2945 |
+
"should_epoch_stop": false,
|
| 2946 |
+
"should_evaluate": false,
|
| 2947 |
+
"should_log": false,
|
| 2948 |
+
"should_save": true,
|
| 2949 |
+
"should_training_stop": false
|
| 2950 |
+
},
|
| 2951 |
+
"attributes": {}
|
| 2952 |
+
}
|
| 2953 |
+
},
|
| 2954 |
+
"total_flos": 2.0792506223580856e+18,
|
| 2955 |
+
"train_batch_size": 2,
|
| 2956 |
+
"trial_name": null,
|
| 2957 |
+
"trial_params": null
|
| 2958 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:da4457deca4f83f0dd7752f0f8e7248da2ab1a42fafdd2f09b5eeb11dca4e64b
|
| 3 |
+
size 5496
|