Upload folder using huggingface_hub
Browse files- checkpoint-400/README.md +202 -0
- checkpoint-400/adapter_config.json +34 -0
- checkpoint-400/adapter_model.safetensors +3 -0
- checkpoint-400/optimizer.pt +3 -0
- checkpoint-400/rng_state.pth +3 -0
- checkpoint-400/scheduler.pt +3 -0
- checkpoint-400/special_tokens_map.json +17 -0
- checkpoint-400/tokenizer.json +3 -0
- checkpoint-400/tokenizer_config.json +2065 -0
- checkpoint-400/trainer_state.json +2970 -0
- checkpoint-400/training_args.bin +3 -0
- trainer_log.jsonl +0 -0
checkpoint-400/README.md
ADDED
|
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: unsloth/Llama-3.2-3B-Instruct
|
| 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 0.12.0
|
checkpoint-400/adapter_config.json
ADDED
|
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "unsloth/Llama-3.2-3B-Instruct",
|
| 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": 256,
|
| 14 |
+
"lora_dropout": 0.0,
|
| 15 |
+
"megatron_config": null,
|
| 16 |
+
"megatron_core": "megatron.core",
|
| 17 |
+
"modules_to_save": null,
|
| 18 |
+
"peft_type": "LORA",
|
| 19 |
+
"r": 256,
|
| 20 |
+
"rank_pattern": {},
|
| 21 |
+
"revision": null,
|
| 22 |
+
"target_modules": [
|
| 23 |
+
"k_proj",
|
| 24 |
+
"down_proj",
|
| 25 |
+
"v_proj",
|
| 26 |
+
"up_proj",
|
| 27 |
+
"gate_proj",
|
| 28 |
+
"o_proj",
|
| 29 |
+
"q_proj"
|
| 30 |
+
],
|
| 31 |
+
"task_type": "CAUSAL_LM",
|
| 32 |
+
"use_dora": false,
|
| 33 |
+
"use_rslora": false
|
| 34 |
+
}
|
checkpoint-400/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4398d7137b9af3ba21001ba69ba86319010ddfae7a0ce4d5d645048f3b68b69a
|
| 3 |
+
size 1556140392
|
checkpoint-400/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0d770a259776647cfe0b64a821b7e899c1e1769c48c72d1911a3d290e1fe1e35
|
| 3 |
+
size 3112505578
|
checkpoint-400/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0aaaf5f5f027d7ebfe653319ee1309e9d3af38cf7bf9f33eddc5b0c461c3ca40
|
| 3 |
+
size 14308
|
checkpoint-400/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ae2b61bc73ee258f2bd09d4b7a417228ca55ebfa321a85081f32bf2e67e230a6
|
| 3 |
+
size 1064
|
checkpoint-400/special_tokens_map.json
ADDED
|
@@ -0,0 +1,17 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": "<|eot_id|>"
|
| 17 |
+
}
|
checkpoint-400/tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
|
| 3 |
+
size 17209920
|
checkpoint-400/tokenizer_config.json
ADDED
|
@@ -0,0 +1,2065 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 = \"\" %}\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": "<|eot_id|>",
|
| 2062 |
+
"padding_side": "right",
|
| 2063 |
+
"split_special_tokens": false,
|
| 2064 |
+
"tokenizer_class": "PreTrainedTokenizerFast"
|
| 2065 |
+
}
|
checkpoint-400/trainer_state.json
ADDED
|
@@ -0,0 +1,2970 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.046045903116464615,
|
| 3 |
+
"best_model_checkpoint": "/home/paperspace/Data/models/gommt/llm3br256/checkpoint-400",
|
| 4 |
+
"epoch": 2.5806451612903225,
|
| 5 |
+
"eval_steps": 25,
|
| 6 |
+
"global_step": 400,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.0064516129032258064,
|
| 13 |
+
"grad_norm": 0.5787440538406372,
|
| 14 |
+
"learning_rate": 2.577319587628866e-07,
|
| 15 |
+
"loss": 0.2947,
|
| 16 |
+
"step": 1
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.012903225806451613,
|
| 20 |
+
"grad_norm": 0.5514878630638123,
|
| 21 |
+
"learning_rate": 5.154639175257732e-07,
|
| 22 |
+
"loss": 0.2774,
|
| 23 |
+
"step": 2
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.01935483870967742,
|
| 27 |
+
"grad_norm": 0.5519412159919739,
|
| 28 |
+
"learning_rate": 7.731958762886599e-07,
|
| 29 |
+
"loss": 0.301,
|
| 30 |
+
"step": 3
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.025806451612903226,
|
| 34 |
+
"grad_norm": 0.5313215851783752,
|
| 35 |
+
"learning_rate": 1.0309278350515464e-06,
|
| 36 |
+
"loss": 0.2792,
|
| 37 |
+
"step": 4
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.03225806451612903,
|
| 41 |
+
"grad_norm": 0.5504052639007568,
|
| 42 |
+
"learning_rate": 1.288659793814433e-06,
|
| 43 |
+
"loss": 0.2918,
|
| 44 |
+
"step": 5
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.03870967741935484,
|
| 48 |
+
"grad_norm": 0.5057755708694458,
|
| 49 |
+
"learning_rate": 1.5463917525773197e-06,
|
| 50 |
+
"loss": 0.2731,
|
| 51 |
+
"step": 6
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.04516129032258064,
|
| 55 |
+
"grad_norm": 0.5207090377807617,
|
| 56 |
+
"learning_rate": 1.804123711340206e-06,
|
| 57 |
+
"loss": 0.3004,
|
| 58 |
+
"step": 7
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.05161290322580645,
|
| 62 |
+
"grad_norm": 0.5149654746055603,
|
| 63 |
+
"learning_rate": 2.061855670103093e-06,
|
| 64 |
+
"loss": 0.2605,
|
| 65 |
+
"step": 8
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.05806451612903226,
|
| 69 |
+
"grad_norm": 0.5021620988845825,
|
| 70 |
+
"learning_rate": 2.3195876288659796e-06,
|
| 71 |
+
"loss": 0.2932,
|
| 72 |
+
"step": 9
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.06451612903225806,
|
| 76 |
+
"grad_norm": 0.5057784914970398,
|
| 77 |
+
"learning_rate": 2.577319587628866e-06,
|
| 78 |
+
"loss": 0.2761,
|
| 79 |
+
"step": 10
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.07096774193548387,
|
| 83 |
+
"grad_norm": 0.49885252118110657,
|
| 84 |
+
"learning_rate": 2.8350515463917527e-06,
|
| 85 |
+
"loss": 0.2779,
|
| 86 |
+
"step": 11
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.07741935483870968,
|
| 90 |
+
"grad_norm": 0.5161502957344055,
|
| 91 |
+
"learning_rate": 3.0927835051546395e-06,
|
| 92 |
+
"loss": 0.2666,
|
| 93 |
+
"step": 12
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.08387096774193549,
|
| 97 |
+
"grad_norm": 0.4862574338912964,
|
| 98 |
+
"learning_rate": 3.350515463917526e-06,
|
| 99 |
+
"loss": 0.2891,
|
| 100 |
+
"step": 13
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.09032258064516129,
|
| 104 |
+
"grad_norm": 0.42886313796043396,
|
| 105 |
+
"learning_rate": 3.608247422680412e-06,
|
| 106 |
+
"loss": 0.2605,
|
| 107 |
+
"step": 14
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.0967741935483871,
|
| 111 |
+
"grad_norm": 0.41169312596321106,
|
| 112 |
+
"learning_rate": 3.865979381443299e-06,
|
| 113 |
+
"loss": 0.2515,
|
| 114 |
+
"step": 15
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.1032258064516129,
|
| 118 |
+
"grad_norm": 0.39097175002098083,
|
| 119 |
+
"learning_rate": 4.123711340206186e-06,
|
| 120 |
+
"loss": 0.2676,
|
| 121 |
+
"step": 16
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.10967741935483871,
|
| 125 |
+
"grad_norm": 0.3687884211540222,
|
| 126 |
+
"learning_rate": 4.381443298969072e-06,
|
| 127 |
+
"loss": 0.2564,
|
| 128 |
+
"step": 17
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.11612903225806452,
|
| 132 |
+
"grad_norm": 0.36199015378952026,
|
| 133 |
+
"learning_rate": 4.639175257731959e-06,
|
| 134 |
+
"loss": 0.2631,
|
| 135 |
+
"step": 18
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.12258064516129032,
|
| 139 |
+
"grad_norm": 0.33205243945121765,
|
| 140 |
+
"learning_rate": 4.8969072164948455e-06,
|
| 141 |
+
"loss": 0.2598,
|
| 142 |
+
"step": 19
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.12903225806451613,
|
| 146 |
+
"grad_norm": 0.2873350977897644,
|
| 147 |
+
"learning_rate": 5.154639175257732e-06,
|
| 148 |
+
"loss": 0.2445,
|
| 149 |
+
"step": 20
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.13548387096774195,
|
| 153 |
+
"grad_norm": 0.27828869223594666,
|
| 154 |
+
"learning_rate": 5.412371134020619e-06,
|
| 155 |
+
"loss": 0.2312,
|
| 156 |
+
"step": 21
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.14193548387096774,
|
| 160 |
+
"grad_norm": 0.2796691358089447,
|
| 161 |
+
"learning_rate": 5.670103092783505e-06,
|
| 162 |
+
"loss": 0.2373,
|
| 163 |
+
"step": 22
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.14838709677419354,
|
| 167 |
+
"grad_norm": 0.2518955171108246,
|
| 168 |
+
"learning_rate": 5.927835051546392e-06,
|
| 169 |
+
"loss": 0.2147,
|
| 170 |
+
"step": 23
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.15483870967741936,
|
| 174 |
+
"grad_norm": 0.24648350477218628,
|
| 175 |
+
"learning_rate": 6.185567010309279e-06,
|
| 176 |
+
"loss": 0.209,
|
| 177 |
+
"step": 24
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.16129032258064516,
|
| 181 |
+
"grad_norm": 0.24219118058681488,
|
| 182 |
+
"learning_rate": 6.443298969072164e-06,
|
| 183 |
+
"loss": 0.232,
|
| 184 |
+
"step": 25
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.16129032258064516,
|
| 188 |
+
"eval_loss": 0.2192624807357788,
|
| 189 |
+
"eval_runtime": 21.7174,
|
| 190 |
+
"eval_samples_per_second": 4.605,
|
| 191 |
+
"eval_steps_per_second": 0.092,
|
| 192 |
+
"step": 25
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.16774193548387098,
|
| 196 |
+
"grad_norm": 0.23314689099788666,
|
| 197 |
+
"learning_rate": 6.701030927835052e-06,
|
| 198 |
+
"loss": 0.2115,
|
| 199 |
+
"step": 26
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 0.17419354838709677,
|
| 203 |
+
"grad_norm": 0.2250155806541443,
|
| 204 |
+
"learning_rate": 6.958762886597939e-06,
|
| 205 |
+
"loss": 0.2171,
|
| 206 |
+
"step": 27
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.18064516129032257,
|
| 210 |
+
"grad_norm": 0.21403469145298004,
|
| 211 |
+
"learning_rate": 7.216494845360824e-06,
|
| 212 |
+
"loss": 0.1991,
|
| 213 |
+
"step": 28
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.1870967741935484,
|
| 217 |
+
"grad_norm": 0.2005668729543686,
|
| 218 |
+
"learning_rate": 7.4742268041237115e-06,
|
| 219 |
+
"loss": 0.2015,
|
| 220 |
+
"step": 29
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 0.1935483870967742,
|
| 224 |
+
"grad_norm": 0.2055639624595642,
|
| 225 |
+
"learning_rate": 7.731958762886599e-06,
|
| 226 |
+
"loss": 0.1995,
|
| 227 |
+
"step": 30
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 0.2,
|
| 231 |
+
"grad_norm": 0.20002567768096924,
|
| 232 |
+
"learning_rate": 7.989690721649484e-06,
|
| 233 |
+
"loss": 0.1987,
|
| 234 |
+
"step": 31
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.2064516129032258,
|
| 238 |
+
"grad_norm": 0.19098369777202606,
|
| 239 |
+
"learning_rate": 8.247422680412371e-06,
|
| 240 |
+
"loss": 0.1842,
|
| 241 |
+
"step": 32
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 0.2129032258064516,
|
| 245 |
+
"grad_norm": 0.17131243646144867,
|
| 246 |
+
"learning_rate": 8.505154639175259e-06,
|
| 247 |
+
"loss": 0.1934,
|
| 248 |
+
"step": 33
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.21935483870967742,
|
| 252 |
+
"grad_norm": 0.19705425202846527,
|
| 253 |
+
"learning_rate": 8.762886597938144e-06,
|
| 254 |
+
"loss": 0.1983,
|
| 255 |
+
"step": 34
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.22580645161290322,
|
| 259 |
+
"grad_norm": 0.1701938658952713,
|
| 260 |
+
"learning_rate": 9.020618556701031e-06,
|
| 261 |
+
"loss": 0.1854,
|
| 262 |
+
"step": 35
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 0.23225806451612904,
|
| 266 |
+
"grad_norm": 0.16887512803077698,
|
| 267 |
+
"learning_rate": 9.278350515463918e-06,
|
| 268 |
+
"loss": 0.1883,
|
| 269 |
+
"step": 36
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 0.23870967741935484,
|
| 273 |
+
"grad_norm": 0.16543127596378326,
|
| 274 |
+
"learning_rate": 9.536082474226804e-06,
|
| 275 |
+
"loss": 0.159,
|
| 276 |
+
"step": 37
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 0.24516129032258063,
|
| 280 |
+
"grad_norm": 0.16382737457752228,
|
| 281 |
+
"learning_rate": 9.793814432989691e-06,
|
| 282 |
+
"loss": 0.1893,
|
| 283 |
+
"step": 38
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 0.25161290322580643,
|
| 287 |
+
"grad_norm": 0.16113704442977905,
|
| 288 |
+
"learning_rate": 1.0051546391752578e-05,
|
| 289 |
+
"loss": 0.1746,
|
| 290 |
+
"step": 39
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.25806451612903225,
|
| 294 |
+
"grad_norm": 0.15014876425266266,
|
| 295 |
+
"learning_rate": 1.0309278350515464e-05,
|
| 296 |
+
"loss": 0.1712,
|
| 297 |
+
"step": 40
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.2645161290322581,
|
| 301 |
+
"grad_norm": 0.16049867868423462,
|
| 302 |
+
"learning_rate": 1.0567010309278351e-05,
|
| 303 |
+
"loss": 0.1589,
|
| 304 |
+
"step": 41
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 0.2709677419354839,
|
| 308 |
+
"grad_norm": 0.13896311819553375,
|
| 309 |
+
"learning_rate": 1.0824742268041238e-05,
|
| 310 |
+
"loss": 0.1621,
|
| 311 |
+
"step": 42
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 0.27741935483870966,
|
| 315 |
+
"grad_norm": 0.14771641790866852,
|
| 316 |
+
"learning_rate": 1.1082474226804124e-05,
|
| 317 |
+
"loss": 0.1783,
|
| 318 |
+
"step": 43
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 0.2838709677419355,
|
| 322 |
+
"grad_norm": 0.14235621690750122,
|
| 323 |
+
"learning_rate": 1.134020618556701e-05,
|
| 324 |
+
"loss": 0.1637,
|
| 325 |
+
"step": 44
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 0.2903225806451613,
|
| 329 |
+
"grad_norm": 0.13013780117034912,
|
| 330 |
+
"learning_rate": 1.1597938144329898e-05,
|
| 331 |
+
"loss": 0.1537,
|
| 332 |
+
"step": 45
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 0.2967741935483871,
|
| 336 |
+
"grad_norm": 0.13013966381549835,
|
| 337 |
+
"learning_rate": 1.1855670103092783e-05,
|
| 338 |
+
"loss": 0.1574,
|
| 339 |
+
"step": 46
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.3032258064516129,
|
| 343 |
+
"grad_norm": 0.1356808990240097,
|
| 344 |
+
"learning_rate": 1.211340206185567e-05,
|
| 345 |
+
"loss": 0.1585,
|
| 346 |
+
"step": 47
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.3096774193548387,
|
| 350 |
+
"grad_norm": 0.1297629475593567,
|
| 351 |
+
"learning_rate": 1.2371134020618558e-05,
|
| 352 |
+
"loss": 0.1554,
|
| 353 |
+
"step": 48
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 0.3161290322580645,
|
| 357 |
+
"grad_norm": 0.13573496043682098,
|
| 358 |
+
"learning_rate": 1.2628865979381443e-05,
|
| 359 |
+
"loss": 0.1584,
|
| 360 |
+
"step": 49
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 0.3225806451612903,
|
| 364 |
+
"grad_norm": 0.14283044636249542,
|
| 365 |
+
"learning_rate": 1.2886597938144329e-05,
|
| 366 |
+
"loss": 0.1524,
|
| 367 |
+
"step": 50
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 0.3225806451612903,
|
| 371 |
+
"eval_loss": 0.15066054463386536,
|
| 372 |
+
"eval_runtime": 20.6503,
|
| 373 |
+
"eval_samples_per_second": 4.843,
|
| 374 |
+
"eval_steps_per_second": 0.097,
|
| 375 |
+
"step": 50
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 0.32903225806451614,
|
| 379 |
+
"grad_norm": 0.1236417219042778,
|
| 380 |
+
"learning_rate": 1.3144329896907218e-05,
|
| 381 |
+
"loss": 0.1459,
|
| 382 |
+
"step": 51
|
| 383 |
+
},
|
| 384 |
+
{
|
| 385 |
+
"epoch": 0.33548387096774196,
|
| 386 |
+
"grad_norm": 0.12115009129047394,
|
| 387 |
+
"learning_rate": 1.3402061855670103e-05,
|
| 388 |
+
"loss": 0.1408,
|
| 389 |
+
"step": 52
|
| 390 |
+
},
|
| 391 |
+
{
|
| 392 |
+
"epoch": 0.3419354838709677,
|
| 393 |
+
"grad_norm": 0.1199135035276413,
|
| 394 |
+
"learning_rate": 1.3659793814432989e-05,
|
| 395 |
+
"loss": 0.1444,
|
| 396 |
+
"step": 53
|
| 397 |
+
},
|
| 398 |
+
{
|
| 399 |
+
"epoch": 0.34838709677419355,
|
| 400 |
+
"grad_norm": 0.1241321787238121,
|
| 401 |
+
"learning_rate": 1.3917525773195878e-05,
|
| 402 |
+
"loss": 0.1416,
|
| 403 |
+
"step": 54
|
| 404 |
+
},
|
| 405 |
+
{
|
| 406 |
+
"epoch": 0.3548387096774194,
|
| 407 |
+
"grad_norm": 0.11240442097187042,
|
| 408 |
+
"learning_rate": 1.4175257731958763e-05,
|
| 409 |
+
"loss": 0.1229,
|
| 410 |
+
"step": 55
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 0.36129032258064514,
|
| 414 |
+
"grad_norm": 0.11829587817192078,
|
| 415 |
+
"learning_rate": 1.4432989690721649e-05,
|
| 416 |
+
"loss": 0.1387,
|
| 417 |
+
"step": 56
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 0.36774193548387096,
|
| 421 |
+
"grad_norm": 0.1287028193473816,
|
| 422 |
+
"learning_rate": 1.4690721649484537e-05,
|
| 423 |
+
"loss": 0.1481,
|
| 424 |
+
"step": 57
|
| 425 |
+
},
|
| 426 |
+
{
|
| 427 |
+
"epoch": 0.3741935483870968,
|
| 428 |
+
"grad_norm": 0.11497591435909271,
|
| 429 |
+
"learning_rate": 1.4948453608247423e-05,
|
| 430 |
+
"loss": 0.1259,
|
| 431 |
+
"step": 58
|
| 432 |
+
},
|
| 433 |
+
{
|
| 434 |
+
"epoch": 0.38064516129032255,
|
| 435 |
+
"grad_norm": 0.11566972732543945,
|
| 436 |
+
"learning_rate": 1.5206185567010308e-05,
|
| 437 |
+
"loss": 0.1193,
|
| 438 |
+
"step": 59
|
| 439 |
+
},
|
| 440 |
+
{
|
| 441 |
+
"epoch": 0.3870967741935484,
|
| 442 |
+
"grad_norm": 0.1135919988155365,
|
| 443 |
+
"learning_rate": 1.5463917525773197e-05,
|
| 444 |
+
"loss": 0.1215,
|
| 445 |
+
"step": 60
|
| 446 |
+
},
|
| 447 |
+
{
|
| 448 |
+
"epoch": 0.3935483870967742,
|
| 449 |
+
"grad_norm": 0.1099628284573555,
|
| 450 |
+
"learning_rate": 1.5721649484536083e-05,
|
| 451 |
+
"loss": 0.1331,
|
| 452 |
+
"step": 61
|
| 453 |
+
},
|
| 454 |
+
{
|
| 455 |
+
"epoch": 0.4,
|
| 456 |
+
"grad_norm": 0.10907468944787979,
|
| 457 |
+
"learning_rate": 1.5979381443298968e-05,
|
| 458 |
+
"loss": 0.117,
|
| 459 |
+
"step": 62
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 0.4064516129032258,
|
| 463 |
+
"grad_norm": 0.11619539558887482,
|
| 464 |
+
"learning_rate": 1.6237113402061857e-05,
|
| 465 |
+
"loss": 0.1126,
|
| 466 |
+
"step": 63
|
| 467 |
+
},
|
| 468 |
+
{
|
| 469 |
+
"epoch": 0.4129032258064516,
|
| 470 |
+
"grad_norm": 0.109222911298275,
|
| 471 |
+
"learning_rate": 1.6494845360824743e-05,
|
| 472 |
+
"loss": 0.1192,
|
| 473 |
+
"step": 64
|
| 474 |
+
},
|
| 475 |
+
{
|
| 476 |
+
"epoch": 0.41935483870967744,
|
| 477 |
+
"grad_norm": 0.12224064767360687,
|
| 478 |
+
"learning_rate": 1.6752577319587628e-05,
|
| 479 |
+
"loss": 0.1245,
|
| 480 |
+
"step": 65
|
| 481 |
+
},
|
| 482 |
+
{
|
| 483 |
+
"epoch": 0.4258064516129032,
|
| 484 |
+
"grad_norm": 0.12005683034658432,
|
| 485 |
+
"learning_rate": 1.7010309278350517e-05,
|
| 486 |
+
"loss": 0.1111,
|
| 487 |
+
"step": 66
|
| 488 |
+
},
|
| 489 |
+
{
|
| 490 |
+
"epoch": 0.432258064516129,
|
| 491 |
+
"grad_norm": 0.11314112693071365,
|
| 492 |
+
"learning_rate": 1.7268041237113403e-05,
|
| 493 |
+
"loss": 0.1109,
|
| 494 |
+
"step": 67
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 0.43870967741935485,
|
| 498 |
+
"grad_norm": 0.11626581847667694,
|
| 499 |
+
"learning_rate": 1.7525773195876288e-05,
|
| 500 |
+
"loss": 0.1224,
|
| 501 |
+
"step": 68
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 0.44516129032258067,
|
| 505 |
+
"grad_norm": 0.11105289310216904,
|
| 506 |
+
"learning_rate": 1.7783505154639177e-05,
|
| 507 |
+
"loss": 0.1142,
|
| 508 |
+
"step": 69
|
| 509 |
+
},
|
| 510 |
+
{
|
| 511 |
+
"epoch": 0.45161290322580644,
|
| 512 |
+
"grad_norm": 0.12696442008018494,
|
| 513 |
+
"learning_rate": 1.8041237113402062e-05,
|
| 514 |
+
"loss": 0.1077,
|
| 515 |
+
"step": 70
|
| 516 |
+
},
|
| 517 |
+
{
|
| 518 |
+
"epoch": 0.45806451612903226,
|
| 519 |
+
"grad_norm": 0.11383359134197235,
|
| 520 |
+
"learning_rate": 1.8298969072164948e-05,
|
| 521 |
+
"loss": 0.1076,
|
| 522 |
+
"step": 71
|
| 523 |
+
},
|
| 524 |
+
{
|
| 525 |
+
"epoch": 0.4645161290322581,
|
| 526 |
+
"grad_norm": 0.11222764849662781,
|
| 527 |
+
"learning_rate": 1.8556701030927837e-05,
|
| 528 |
+
"loss": 0.1212,
|
| 529 |
+
"step": 72
|
| 530 |
+
},
|
| 531 |
+
{
|
| 532 |
+
"epoch": 0.47096774193548385,
|
| 533 |
+
"grad_norm": 0.12386021018028259,
|
| 534 |
+
"learning_rate": 1.8814432989690722e-05,
|
| 535 |
+
"loss": 0.1203,
|
| 536 |
+
"step": 73
|
| 537 |
+
},
|
| 538 |
+
{
|
| 539 |
+
"epoch": 0.4774193548387097,
|
| 540 |
+
"grad_norm": 0.10532196611166,
|
| 541 |
+
"learning_rate": 1.9072164948453608e-05,
|
| 542 |
+
"loss": 0.1079,
|
| 543 |
+
"step": 74
|
| 544 |
+
},
|
| 545 |
+
{
|
| 546 |
+
"epoch": 0.4838709677419355,
|
| 547 |
+
"grad_norm": 0.1084241271018982,
|
| 548 |
+
"learning_rate": 1.9329896907216497e-05,
|
| 549 |
+
"loss": 0.115,
|
| 550 |
+
"step": 75
|
| 551 |
+
},
|
| 552 |
+
{
|
| 553 |
+
"epoch": 0.4838709677419355,
|
| 554 |
+
"eval_loss": 0.11645982414484024,
|
| 555 |
+
"eval_runtime": 20.6021,
|
| 556 |
+
"eval_samples_per_second": 4.854,
|
| 557 |
+
"eval_steps_per_second": 0.097,
|
| 558 |
+
"step": 75
|
| 559 |
+
},
|
| 560 |
+
{
|
| 561 |
+
"epoch": 0.49032258064516127,
|
| 562 |
+
"grad_norm": 0.12820391356945038,
|
| 563 |
+
"learning_rate": 1.9587628865979382e-05,
|
| 564 |
+
"loss": 0.1091,
|
| 565 |
+
"step": 76
|
| 566 |
+
},
|
| 567 |
+
{
|
| 568 |
+
"epoch": 0.4967741935483871,
|
| 569 |
+
"grad_norm": 0.1124340295791626,
|
| 570 |
+
"learning_rate": 1.9845360824742268e-05,
|
| 571 |
+
"loss": 0.1129,
|
| 572 |
+
"step": 77
|
| 573 |
+
},
|
| 574 |
+
{
|
| 575 |
+
"epoch": 0.5032258064516129,
|
| 576 |
+
"grad_norm": 0.10982845723628998,
|
| 577 |
+
"learning_rate": 2.0103092783505157e-05,
|
| 578 |
+
"loss": 0.126,
|
| 579 |
+
"step": 78
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 0.5096774193548387,
|
| 583 |
+
"grad_norm": 0.1185258999466896,
|
| 584 |
+
"learning_rate": 2.0360824742268042e-05,
|
| 585 |
+
"loss": 0.1094,
|
| 586 |
+
"step": 79
|
| 587 |
+
},
|
| 588 |
+
{
|
| 589 |
+
"epoch": 0.5161290322580645,
|
| 590 |
+
"grad_norm": 0.0972081646323204,
|
| 591 |
+
"learning_rate": 2.0618556701030927e-05,
|
| 592 |
+
"loss": 0.103,
|
| 593 |
+
"step": 80
|
| 594 |
+
},
|
| 595 |
+
{
|
| 596 |
+
"epoch": 0.5225806451612903,
|
| 597 |
+
"grad_norm": 0.10331461578607559,
|
| 598 |
+
"learning_rate": 2.0876288659793816e-05,
|
| 599 |
+
"loss": 0.1107,
|
| 600 |
+
"step": 81
|
| 601 |
+
},
|
| 602 |
+
{
|
| 603 |
+
"epoch": 0.5290322580645161,
|
| 604 |
+
"grad_norm": 0.11630548536777496,
|
| 605 |
+
"learning_rate": 2.1134020618556702e-05,
|
| 606 |
+
"loss": 0.1184,
|
| 607 |
+
"step": 82
|
| 608 |
+
},
|
| 609 |
+
{
|
| 610 |
+
"epoch": 0.535483870967742,
|
| 611 |
+
"grad_norm": 0.10714004188776016,
|
| 612 |
+
"learning_rate": 2.1391752577319587e-05,
|
| 613 |
+
"loss": 0.1059,
|
| 614 |
+
"step": 83
|
| 615 |
+
},
|
| 616 |
+
{
|
| 617 |
+
"epoch": 0.5419354838709678,
|
| 618 |
+
"grad_norm": 0.10682078450918198,
|
| 619 |
+
"learning_rate": 2.1649484536082476e-05,
|
| 620 |
+
"loss": 0.1047,
|
| 621 |
+
"step": 84
|
| 622 |
+
},
|
| 623 |
+
{
|
| 624 |
+
"epoch": 0.5483870967741935,
|
| 625 |
+
"grad_norm": 0.10373492538928986,
|
| 626 |
+
"learning_rate": 2.1907216494845362e-05,
|
| 627 |
+
"loss": 0.0906,
|
| 628 |
+
"step": 85
|
| 629 |
+
},
|
| 630 |
+
{
|
| 631 |
+
"epoch": 0.5548387096774193,
|
| 632 |
+
"grad_norm": 0.10939467698335648,
|
| 633 |
+
"learning_rate": 2.2164948453608247e-05,
|
| 634 |
+
"loss": 0.105,
|
| 635 |
+
"step": 86
|
| 636 |
+
},
|
| 637 |
+
{
|
| 638 |
+
"epoch": 0.5612903225806452,
|
| 639 |
+
"grad_norm": 0.1066933274269104,
|
| 640 |
+
"learning_rate": 2.2422680412371136e-05,
|
| 641 |
+
"loss": 0.1046,
|
| 642 |
+
"step": 87
|
| 643 |
+
},
|
| 644 |
+
{
|
| 645 |
+
"epoch": 0.567741935483871,
|
| 646 |
+
"grad_norm": 0.11235528439283371,
|
| 647 |
+
"learning_rate": 2.268041237113402e-05,
|
| 648 |
+
"loss": 0.1183,
|
| 649 |
+
"step": 88
|
| 650 |
+
},
|
| 651 |
+
{
|
| 652 |
+
"epoch": 0.5741935483870968,
|
| 653 |
+
"grad_norm": 0.11120587587356567,
|
| 654 |
+
"learning_rate": 2.2938144329896907e-05,
|
| 655 |
+
"loss": 0.1012,
|
| 656 |
+
"step": 89
|
| 657 |
+
},
|
| 658 |
+
{
|
| 659 |
+
"epoch": 0.5806451612903226,
|
| 660 |
+
"grad_norm": 0.11943212896585464,
|
| 661 |
+
"learning_rate": 2.3195876288659796e-05,
|
| 662 |
+
"loss": 0.1081,
|
| 663 |
+
"step": 90
|
| 664 |
+
},
|
| 665 |
+
{
|
| 666 |
+
"epoch": 0.5870967741935483,
|
| 667 |
+
"grad_norm": 0.11067789793014526,
|
| 668 |
+
"learning_rate": 2.345360824742268e-05,
|
| 669 |
+
"loss": 0.106,
|
| 670 |
+
"step": 91
|
| 671 |
+
},
|
| 672 |
+
{
|
| 673 |
+
"epoch": 0.5935483870967742,
|
| 674 |
+
"grad_norm": 0.10897871106863022,
|
| 675 |
+
"learning_rate": 2.3711340206185567e-05,
|
| 676 |
+
"loss": 0.1017,
|
| 677 |
+
"step": 92
|
| 678 |
+
},
|
| 679 |
+
{
|
| 680 |
+
"epoch": 0.6,
|
| 681 |
+
"grad_norm": 0.10811934620141983,
|
| 682 |
+
"learning_rate": 2.3969072164948456e-05,
|
| 683 |
+
"loss": 0.1043,
|
| 684 |
+
"step": 93
|
| 685 |
+
},
|
| 686 |
+
{
|
| 687 |
+
"epoch": 0.6064516129032258,
|
| 688 |
+
"grad_norm": 0.12143644690513611,
|
| 689 |
+
"learning_rate": 2.422680412371134e-05,
|
| 690 |
+
"loss": 0.0906,
|
| 691 |
+
"step": 94
|
| 692 |
+
},
|
| 693 |
+
{
|
| 694 |
+
"epoch": 0.6129032258064516,
|
| 695 |
+
"grad_norm": 0.11472067981958389,
|
| 696 |
+
"learning_rate": 2.4484536082474227e-05,
|
| 697 |
+
"loss": 0.1064,
|
| 698 |
+
"step": 95
|
| 699 |
+
},
|
| 700 |
+
{
|
| 701 |
+
"epoch": 0.6193548387096774,
|
| 702 |
+
"grad_norm": 0.11486558616161346,
|
| 703 |
+
"learning_rate": 2.4742268041237116e-05,
|
| 704 |
+
"loss": 0.1076,
|
| 705 |
+
"step": 96
|
| 706 |
+
},
|
| 707 |
+
{
|
| 708 |
+
"epoch": 0.6258064516129033,
|
| 709 |
+
"grad_norm": 0.11682534962892532,
|
| 710 |
+
"learning_rate": 2.5e-05,
|
| 711 |
+
"loss": 0.1015,
|
| 712 |
+
"step": 97
|
| 713 |
+
},
|
| 714 |
+
{
|
| 715 |
+
"epoch": 0.632258064516129,
|
| 716 |
+
"grad_norm": 0.10343407839536667,
|
| 717 |
+
"learning_rate": 2.5257731958762887e-05,
|
| 718 |
+
"loss": 0.0951,
|
| 719 |
+
"step": 98
|
| 720 |
+
},
|
| 721 |
+
{
|
| 722 |
+
"epoch": 0.6387096774193548,
|
| 723 |
+
"grad_norm": 0.13064107298851013,
|
| 724 |
+
"learning_rate": 2.5515463917525772e-05,
|
| 725 |
+
"loss": 0.0952,
|
| 726 |
+
"step": 99
|
| 727 |
+
},
|
| 728 |
+
{
|
| 729 |
+
"epoch": 0.6451612903225806,
|
| 730 |
+
"grad_norm": 0.11045321077108383,
|
| 731 |
+
"learning_rate": 2.5773195876288658e-05,
|
| 732 |
+
"loss": 0.0875,
|
| 733 |
+
"step": 100
|
| 734 |
+
},
|
| 735 |
+
{
|
| 736 |
+
"epoch": 0.6451612903225806,
|
| 737 |
+
"eval_loss": 0.1003575325012207,
|
| 738 |
+
"eval_runtime": 20.6227,
|
| 739 |
+
"eval_samples_per_second": 4.849,
|
| 740 |
+
"eval_steps_per_second": 0.097,
|
| 741 |
+
"step": 100
|
| 742 |
+
},
|
| 743 |
+
{
|
| 744 |
+
"epoch": 0.6516129032258065,
|
| 745 |
+
"grad_norm": 0.10884646326303482,
|
| 746 |
+
"learning_rate": 2.603092783505155e-05,
|
| 747 |
+
"loss": 0.1082,
|
| 748 |
+
"step": 101
|
| 749 |
+
},
|
| 750 |
+
{
|
| 751 |
+
"epoch": 0.6580645161290323,
|
| 752 |
+
"grad_norm": 0.12365655601024628,
|
| 753 |
+
"learning_rate": 2.6288659793814435e-05,
|
| 754 |
+
"loss": 0.1079,
|
| 755 |
+
"step": 102
|
| 756 |
+
},
|
| 757 |
+
{
|
| 758 |
+
"epoch": 0.6645161290322581,
|
| 759 |
+
"grad_norm": 0.12333594262599945,
|
| 760 |
+
"learning_rate": 2.654639175257732e-05,
|
| 761 |
+
"loss": 0.0987,
|
| 762 |
+
"step": 103
|
| 763 |
+
},
|
| 764 |
+
{
|
| 765 |
+
"epoch": 0.6709677419354839,
|
| 766 |
+
"grad_norm": 0.12649482488632202,
|
| 767 |
+
"learning_rate": 2.6804123711340206e-05,
|
| 768 |
+
"loss": 0.1008,
|
| 769 |
+
"step": 104
|
| 770 |
+
},
|
| 771 |
+
{
|
| 772 |
+
"epoch": 0.6774193548387096,
|
| 773 |
+
"grad_norm": 0.12309876084327698,
|
| 774 |
+
"learning_rate": 2.7061855670103092e-05,
|
| 775 |
+
"loss": 0.0865,
|
| 776 |
+
"step": 105
|
| 777 |
+
},
|
| 778 |
+
{
|
| 779 |
+
"epoch": 0.6838709677419355,
|
| 780 |
+
"grad_norm": 0.11590270698070526,
|
| 781 |
+
"learning_rate": 2.7319587628865977e-05,
|
| 782 |
+
"loss": 0.0943,
|
| 783 |
+
"step": 106
|
| 784 |
+
},
|
| 785 |
+
{
|
| 786 |
+
"epoch": 0.6903225806451613,
|
| 787 |
+
"grad_norm": 0.13238589465618134,
|
| 788 |
+
"learning_rate": 2.757731958762887e-05,
|
| 789 |
+
"loss": 0.1092,
|
| 790 |
+
"step": 107
|
| 791 |
+
},
|
| 792 |
+
{
|
| 793 |
+
"epoch": 0.6967741935483871,
|
| 794 |
+
"grad_norm": 0.10838130116462708,
|
| 795 |
+
"learning_rate": 2.7835051546391755e-05,
|
| 796 |
+
"loss": 0.0972,
|
| 797 |
+
"step": 108
|
| 798 |
+
},
|
| 799 |
+
{
|
| 800 |
+
"epoch": 0.7032258064516129,
|
| 801 |
+
"grad_norm": 0.11450201272964478,
|
| 802 |
+
"learning_rate": 2.809278350515464e-05,
|
| 803 |
+
"loss": 0.0886,
|
| 804 |
+
"step": 109
|
| 805 |
+
},
|
| 806 |
+
{
|
| 807 |
+
"epoch": 0.7096774193548387,
|
| 808 |
+
"grad_norm": 0.11476748436689377,
|
| 809 |
+
"learning_rate": 2.8350515463917526e-05,
|
| 810 |
+
"loss": 0.0934,
|
| 811 |
+
"step": 110
|
| 812 |
+
},
|
| 813 |
+
{
|
| 814 |
+
"epoch": 0.7161290322580646,
|
| 815 |
+
"grad_norm": 0.1416608691215515,
|
| 816 |
+
"learning_rate": 2.860824742268041e-05,
|
| 817 |
+
"loss": 0.1044,
|
| 818 |
+
"step": 111
|
| 819 |
+
},
|
| 820 |
+
{
|
| 821 |
+
"epoch": 0.7225806451612903,
|
| 822 |
+
"grad_norm": 0.11946123838424683,
|
| 823 |
+
"learning_rate": 2.8865979381443297e-05,
|
| 824 |
+
"loss": 0.1001,
|
| 825 |
+
"step": 112
|
| 826 |
+
},
|
| 827 |
+
{
|
| 828 |
+
"epoch": 0.7290322580645161,
|
| 829 |
+
"grad_norm": 0.10268019139766693,
|
| 830 |
+
"learning_rate": 2.912371134020619e-05,
|
| 831 |
+
"loss": 0.0879,
|
| 832 |
+
"step": 113
|
| 833 |
+
},
|
| 834 |
+
{
|
| 835 |
+
"epoch": 0.7354838709677419,
|
| 836 |
+
"grad_norm": 0.12969037890434265,
|
| 837 |
+
"learning_rate": 2.9381443298969075e-05,
|
| 838 |
+
"loss": 0.1046,
|
| 839 |
+
"step": 114
|
| 840 |
+
},
|
| 841 |
+
{
|
| 842 |
+
"epoch": 0.7419354838709677,
|
| 843 |
+
"grad_norm": 0.112672358751297,
|
| 844 |
+
"learning_rate": 2.963917525773196e-05,
|
| 845 |
+
"loss": 0.0979,
|
| 846 |
+
"step": 115
|
| 847 |
+
},
|
| 848 |
+
{
|
| 849 |
+
"epoch": 0.7483870967741936,
|
| 850 |
+
"grad_norm": 0.11950547248125076,
|
| 851 |
+
"learning_rate": 2.9896907216494846e-05,
|
| 852 |
+
"loss": 0.0983,
|
| 853 |
+
"step": 116
|
| 854 |
+
},
|
| 855 |
+
{
|
| 856 |
+
"epoch": 0.7548387096774194,
|
| 857 |
+
"grad_norm": 0.11480306833982468,
|
| 858 |
+
"learning_rate": 3.015463917525773e-05,
|
| 859 |
+
"loss": 0.0772,
|
| 860 |
+
"step": 117
|
| 861 |
+
},
|
| 862 |
+
{
|
| 863 |
+
"epoch": 0.7612903225806451,
|
| 864 |
+
"grad_norm": 0.11258739978075027,
|
| 865 |
+
"learning_rate": 3.0412371134020617e-05,
|
| 866 |
+
"loss": 0.0855,
|
| 867 |
+
"step": 118
|
| 868 |
+
},
|
| 869 |
+
{
|
| 870 |
+
"epoch": 0.7677419354838709,
|
| 871 |
+
"grad_norm": 0.11581332236528397,
|
| 872 |
+
"learning_rate": 3.0670103092783506e-05,
|
| 873 |
+
"loss": 0.0864,
|
| 874 |
+
"step": 119
|
| 875 |
+
},
|
| 876 |
+
{
|
| 877 |
+
"epoch": 0.7741935483870968,
|
| 878 |
+
"grad_norm": 0.13305814564228058,
|
| 879 |
+
"learning_rate": 3.0927835051546395e-05,
|
| 880 |
+
"loss": 0.0917,
|
| 881 |
+
"step": 120
|
| 882 |
+
},
|
| 883 |
+
{
|
| 884 |
+
"epoch": 0.7806451612903226,
|
| 885 |
+
"grad_norm": 0.11415888369083405,
|
| 886 |
+
"learning_rate": 3.118556701030928e-05,
|
| 887 |
+
"loss": 0.0948,
|
| 888 |
+
"step": 121
|
| 889 |
+
},
|
| 890 |
+
{
|
| 891 |
+
"epoch": 0.7870967741935484,
|
| 892 |
+
"grad_norm": 0.12214888632297516,
|
| 893 |
+
"learning_rate": 3.1443298969072166e-05,
|
| 894 |
+
"loss": 0.0931,
|
| 895 |
+
"step": 122
|
| 896 |
+
},
|
| 897 |
+
{
|
| 898 |
+
"epoch": 0.7935483870967742,
|
| 899 |
+
"grad_norm": 0.13365623354911804,
|
| 900 |
+
"learning_rate": 3.1701030927835054e-05,
|
| 901 |
+
"loss": 0.0816,
|
| 902 |
+
"step": 123
|
| 903 |
+
},
|
| 904 |
+
{
|
| 905 |
+
"epoch": 0.8,
|
| 906 |
+
"grad_norm": 0.12570084631443024,
|
| 907 |
+
"learning_rate": 3.1958762886597937e-05,
|
| 908 |
+
"loss": 0.0859,
|
| 909 |
+
"step": 124
|
| 910 |
+
},
|
| 911 |
+
{
|
| 912 |
+
"epoch": 0.8064516129032258,
|
| 913 |
+
"grad_norm": 0.11142268776893616,
|
| 914 |
+
"learning_rate": 3.2216494845360825e-05,
|
| 915 |
+
"loss": 0.092,
|
| 916 |
+
"step": 125
|
| 917 |
+
},
|
| 918 |
+
{
|
| 919 |
+
"epoch": 0.8064516129032258,
|
| 920 |
+
"eval_loss": 0.09087119251489639,
|
| 921 |
+
"eval_runtime": 20.6603,
|
| 922 |
+
"eval_samples_per_second": 4.84,
|
| 923 |
+
"eval_steps_per_second": 0.097,
|
| 924 |
+
"step": 125
|
| 925 |
+
},
|
| 926 |
+
{
|
| 927 |
+
"epoch": 0.8129032258064516,
|
| 928 |
+
"grad_norm": 0.13126152753829956,
|
| 929 |
+
"learning_rate": 3.2474226804123714e-05,
|
| 930 |
+
"loss": 0.085,
|
| 931 |
+
"step": 126
|
| 932 |
+
},
|
| 933 |
+
{
|
| 934 |
+
"epoch": 0.8193548387096774,
|
| 935 |
+
"grad_norm": 0.12571650743484497,
|
| 936 |
+
"learning_rate": 3.2731958762886596e-05,
|
| 937 |
+
"loss": 0.092,
|
| 938 |
+
"step": 127
|
| 939 |
+
},
|
| 940 |
+
{
|
| 941 |
+
"epoch": 0.8258064516129032,
|
| 942 |
+
"grad_norm": 0.11935378611087799,
|
| 943 |
+
"learning_rate": 3.2989690721649485e-05,
|
| 944 |
+
"loss": 0.0923,
|
| 945 |
+
"step": 128
|
| 946 |
+
},
|
| 947 |
+
{
|
| 948 |
+
"epoch": 0.832258064516129,
|
| 949 |
+
"grad_norm": 0.1310584396123886,
|
| 950 |
+
"learning_rate": 3.3247422680412374e-05,
|
| 951 |
+
"loss": 0.0854,
|
| 952 |
+
"step": 129
|
| 953 |
+
},
|
| 954 |
+
{
|
| 955 |
+
"epoch": 0.8387096774193549,
|
| 956 |
+
"grad_norm": 0.12715069949626923,
|
| 957 |
+
"learning_rate": 3.3505154639175256e-05,
|
| 958 |
+
"loss": 0.0917,
|
| 959 |
+
"step": 130
|
| 960 |
+
},
|
| 961 |
+
{
|
| 962 |
+
"epoch": 0.8451612903225807,
|
| 963 |
+
"grad_norm": 0.13257332146167755,
|
| 964 |
+
"learning_rate": 3.3762886597938145e-05,
|
| 965 |
+
"loss": 0.083,
|
| 966 |
+
"step": 131
|
| 967 |
+
},
|
| 968 |
+
{
|
| 969 |
+
"epoch": 0.8516129032258064,
|
| 970 |
+
"grad_norm": 0.11446800082921982,
|
| 971 |
+
"learning_rate": 3.4020618556701034e-05,
|
| 972 |
+
"loss": 0.0901,
|
| 973 |
+
"step": 132
|
| 974 |
+
},
|
| 975 |
+
{
|
| 976 |
+
"epoch": 0.8580645161290322,
|
| 977 |
+
"grad_norm": 0.10843442380428314,
|
| 978 |
+
"learning_rate": 3.4278350515463916e-05,
|
| 979 |
+
"loss": 0.0892,
|
| 980 |
+
"step": 133
|
| 981 |
+
},
|
| 982 |
+
{
|
| 983 |
+
"epoch": 0.864516129032258,
|
| 984 |
+
"grad_norm": 0.13865868747234344,
|
| 985 |
+
"learning_rate": 3.4536082474226805e-05,
|
| 986 |
+
"loss": 0.0843,
|
| 987 |
+
"step": 134
|
| 988 |
+
},
|
| 989 |
+
{
|
| 990 |
+
"epoch": 0.8709677419354839,
|
| 991 |
+
"grad_norm": 0.11984317004680634,
|
| 992 |
+
"learning_rate": 3.4793814432989694e-05,
|
| 993 |
+
"loss": 0.0909,
|
| 994 |
+
"step": 135
|
| 995 |
+
},
|
| 996 |
+
{
|
| 997 |
+
"epoch": 0.8774193548387097,
|
| 998 |
+
"grad_norm": 0.12147698551416397,
|
| 999 |
+
"learning_rate": 3.5051546391752576e-05,
|
| 1000 |
+
"loss": 0.0818,
|
| 1001 |
+
"step": 136
|
| 1002 |
+
},
|
| 1003 |
+
{
|
| 1004 |
+
"epoch": 0.8838709677419355,
|
| 1005 |
+
"grad_norm": 0.14456403255462646,
|
| 1006 |
+
"learning_rate": 3.5309278350515465e-05,
|
| 1007 |
+
"loss": 0.0829,
|
| 1008 |
+
"step": 137
|
| 1009 |
+
},
|
| 1010 |
+
{
|
| 1011 |
+
"epoch": 0.8903225806451613,
|
| 1012 |
+
"grad_norm": 0.11969202756881714,
|
| 1013 |
+
"learning_rate": 3.5567010309278354e-05,
|
| 1014 |
+
"loss": 0.0846,
|
| 1015 |
+
"step": 138
|
| 1016 |
+
},
|
| 1017 |
+
{
|
| 1018 |
+
"epoch": 0.896774193548387,
|
| 1019 |
+
"grad_norm": 0.12115851789712906,
|
| 1020 |
+
"learning_rate": 3.5824742268041236e-05,
|
| 1021 |
+
"loss": 0.0736,
|
| 1022 |
+
"step": 139
|
| 1023 |
+
},
|
| 1024 |
+
{
|
| 1025 |
+
"epoch": 0.9032258064516129,
|
| 1026 |
+
"grad_norm": 0.1291874796152115,
|
| 1027 |
+
"learning_rate": 3.6082474226804125e-05,
|
| 1028 |
+
"loss": 0.0888,
|
| 1029 |
+
"step": 140
|
| 1030 |
+
},
|
| 1031 |
+
{
|
| 1032 |
+
"epoch": 0.9096774193548387,
|
| 1033 |
+
"grad_norm": 0.11851019412279129,
|
| 1034 |
+
"learning_rate": 3.6340206185567014e-05,
|
| 1035 |
+
"loss": 0.0847,
|
| 1036 |
+
"step": 141
|
| 1037 |
+
},
|
| 1038 |
+
{
|
| 1039 |
+
"epoch": 0.9161290322580645,
|
| 1040 |
+
"grad_norm": 0.12146991491317749,
|
| 1041 |
+
"learning_rate": 3.6597938144329896e-05,
|
| 1042 |
+
"loss": 0.0813,
|
| 1043 |
+
"step": 142
|
| 1044 |
+
},
|
| 1045 |
+
{
|
| 1046 |
+
"epoch": 0.9225806451612903,
|
| 1047 |
+
"grad_norm": 1.0139228105545044,
|
| 1048 |
+
"learning_rate": 3.6855670103092785e-05,
|
| 1049 |
+
"loss": 0.1059,
|
| 1050 |
+
"step": 143
|
| 1051 |
+
},
|
| 1052 |
+
{
|
| 1053 |
+
"epoch": 0.9290322580645162,
|
| 1054 |
+
"grad_norm": 0.21279872953891754,
|
| 1055 |
+
"learning_rate": 3.7113402061855674e-05,
|
| 1056 |
+
"loss": 0.0966,
|
| 1057 |
+
"step": 144
|
| 1058 |
+
},
|
| 1059 |
+
{
|
| 1060 |
+
"epoch": 0.9354838709677419,
|
| 1061 |
+
"grad_norm": 0.16659015417099,
|
| 1062 |
+
"learning_rate": 3.7371134020618556e-05,
|
| 1063 |
+
"loss": 0.0963,
|
| 1064 |
+
"step": 145
|
| 1065 |
+
},
|
| 1066 |
+
{
|
| 1067 |
+
"epoch": 0.9419354838709677,
|
| 1068 |
+
"grad_norm": 0.1789676696062088,
|
| 1069 |
+
"learning_rate": 3.7628865979381445e-05,
|
| 1070 |
+
"loss": 0.099,
|
| 1071 |
+
"step": 146
|
| 1072 |
+
},
|
| 1073 |
+
{
|
| 1074 |
+
"epoch": 0.9483870967741935,
|
| 1075 |
+
"grad_norm": 0.1633814126253128,
|
| 1076 |
+
"learning_rate": 3.7886597938144333e-05,
|
| 1077 |
+
"loss": 0.0958,
|
| 1078 |
+
"step": 147
|
| 1079 |
+
},
|
| 1080 |
+
{
|
| 1081 |
+
"epoch": 0.9548387096774194,
|
| 1082 |
+
"grad_norm": 0.1775261014699936,
|
| 1083 |
+
"learning_rate": 3.8144329896907216e-05,
|
| 1084 |
+
"loss": 0.1017,
|
| 1085 |
+
"step": 148
|
| 1086 |
+
},
|
| 1087 |
+
{
|
| 1088 |
+
"epoch": 0.9612903225806452,
|
| 1089 |
+
"grad_norm": 0.11921869218349457,
|
| 1090 |
+
"learning_rate": 3.8402061855670104e-05,
|
| 1091 |
+
"loss": 0.0945,
|
| 1092 |
+
"step": 149
|
| 1093 |
+
},
|
| 1094 |
+
{
|
| 1095 |
+
"epoch": 0.967741935483871,
|
| 1096 |
+
"grad_norm": 0.14354467391967773,
|
| 1097 |
+
"learning_rate": 3.865979381443299e-05,
|
| 1098 |
+
"loss": 0.1077,
|
| 1099 |
+
"step": 150
|
| 1100 |
+
},
|
| 1101 |
+
{
|
| 1102 |
+
"epoch": 0.967741935483871,
|
| 1103 |
+
"eval_loss": 0.08996601402759552,
|
| 1104 |
+
"eval_runtime": 20.6312,
|
| 1105 |
+
"eval_samples_per_second": 4.847,
|
| 1106 |
+
"eval_steps_per_second": 0.097,
|
| 1107 |
+
"step": 150
|
| 1108 |
+
},
|
| 1109 |
+
{
|
| 1110 |
+
"epoch": 0.9741935483870968,
|
| 1111 |
+
"grad_norm": 0.13735030591487885,
|
| 1112 |
+
"learning_rate": 3.8917525773195875e-05,
|
| 1113 |
+
"loss": 0.099,
|
| 1114 |
+
"step": 151
|
| 1115 |
+
},
|
| 1116 |
+
{
|
| 1117 |
+
"epoch": 0.9806451612903225,
|
| 1118 |
+
"grad_norm": 0.10479952394962311,
|
| 1119 |
+
"learning_rate": 3.9175257731958764e-05,
|
| 1120 |
+
"loss": 0.0775,
|
| 1121 |
+
"step": 152
|
| 1122 |
+
},
|
| 1123 |
+
{
|
| 1124 |
+
"epoch": 0.9870967741935484,
|
| 1125 |
+
"grad_norm": 0.1122341901063919,
|
| 1126 |
+
"learning_rate": 3.943298969072165e-05,
|
| 1127 |
+
"loss": 0.0723,
|
| 1128 |
+
"step": 153
|
| 1129 |
+
},
|
| 1130 |
+
{
|
| 1131 |
+
"epoch": 0.9935483870967742,
|
| 1132 |
+
"grad_norm": 0.1230883076786995,
|
| 1133 |
+
"learning_rate": 3.9690721649484535e-05,
|
| 1134 |
+
"loss": 0.0721,
|
| 1135 |
+
"step": 154
|
| 1136 |
+
},
|
| 1137 |
+
{
|
| 1138 |
+
"epoch": 1.0,
|
| 1139 |
+
"grad_norm": 0.14200343191623688,
|
| 1140 |
+
"learning_rate": 3.9948453608247424e-05,
|
| 1141 |
+
"loss": 0.0826,
|
| 1142 |
+
"step": 155
|
| 1143 |
+
},
|
| 1144 |
+
{
|
| 1145 |
+
"epoch": 1.0064516129032257,
|
| 1146 |
+
"grad_norm": 0.1111890971660614,
|
| 1147 |
+
"learning_rate": 4.020618556701031e-05,
|
| 1148 |
+
"loss": 0.0801,
|
| 1149 |
+
"step": 156
|
| 1150 |
+
},
|
| 1151 |
+
{
|
| 1152 |
+
"epoch": 1.0129032258064516,
|
| 1153 |
+
"grad_norm": 0.12783704698085785,
|
| 1154 |
+
"learning_rate": 4.0463917525773195e-05,
|
| 1155 |
+
"loss": 0.0947,
|
| 1156 |
+
"step": 157
|
| 1157 |
+
},
|
| 1158 |
+
{
|
| 1159 |
+
"epoch": 1.0193548387096774,
|
| 1160 |
+
"grad_norm": 0.12492270022630692,
|
| 1161 |
+
"learning_rate": 4.0721649484536084e-05,
|
| 1162 |
+
"loss": 0.0865,
|
| 1163 |
+
"step": 158
|
| 1164 |
+
},
|
| 1165 |
+
{
|
| 1166 |
+
"epoch": 1.0258064516129033,
|
| 1167 |
+
"grad_norm": 0.1070851981639862,
|
| 1168 |
+
"learning_rate": 4.097938144329897e-05,
|
| 1169 |
+
"loss": 0.0748,
|
| 1170 |
+
"step": 159
|
| 1171 |
+
},
|
| 1172 |
+
{
|
| 1173 |
+
"epoch": 1.032258064516129,
|
| 1174 |
+
"grad_norm": 0.1142066940665245,
|
| 1175 |
+
"learning_rate": 4.1237113402061855e-05,
|
| 1176 |
+
"loss": 0.0773,
|
| 1177 |
+
"step": 160
|
| 1178 |
+
},
|
| 1179 |
+
{
|
| 1180 |
+
"epoch": 1.038709677419355,
|
| 1181 |
+
"grad_norm": 0.13485798239707947,
|
| 1182 |
+
"learning_rate": 4.1494845360824744e-05,
|
| 1183 |
+
"loss": 0.0886,
|
| 1184 |
+
"step": 161
|
| 1185 |
+
},
|
| 1186 |
+
{
|
| 1187 |
+
"epoch": 1.0451612903225806,
|
| 1188 |
+
"grad_norm": 0.11550623178482056,
|
| 1189 |
+
"learning_rate": 4.175257731958763e-05,
|
| 1190 |
+
"loss": 0.0795,
|
| 1191 |
+
"step": 162
|
| 1192 |
+
},
|
| 1193 |
+
{
|
| 1194 |
+
"epoch": 1.0516129032258064,
|
| 1195 |
+
"grad_norm": 0.1292477399110794,
|
| 1196 |
+
"learning_rate": 4.2010309278350515e-05,
|
| 1197 |
+
"loss": 0.0721,
|
| 1198 |
+
"step": 163
|
| 1199 |
+
},
|
| 1200 |
+
{
|
| 1201 |
+
"epoch": 1.0580645161290323,
|
| 1202 |
+
"grad_norm": 0.1202891618013382,
|
| 1203 |
+
"learning_rate": 4.2268041237113404e-05,
|
| 1204 |
+
"loss": 0.0713,
|
| 1205 |
+
"step": 164
|
| 1206 |
+
},
|
| 1207 |
+
{
|
| 1208 |
+
"epoch": 1.064516129032258,
|
| 1209 |
+
"grad_norm": 0.1149148941040039,
|
| 1210 |
+
"learning_rate": 4.252577319587629e-05,
|
| 1211 |
+
"loss": 0.0776,
|
| 1212 |
+
"step": 165
|
| 1213 |
+
},
|
| 1214 |
+
{
|
| 1215 |
+
"epoch": 1.070967741935484,
|
| 1216 |
+
"grad_norm": 0.12351440638303757,
|
| 1217 |
+
"learning_rate": 4.2783505154639175e-05,
|
| 1218 |
+
"loss": 0.0802,
|
| 1219 |
+
"step": 166
|
| 1220 |
+
},
|
| 1221 |
+
{
|
| 1222 |
+
"epoch": 1.0774193548387097,
|
| 1223 |
+
"grad_norm": 0.1218574196100235,
|
| 1224 |
+
"learning_rate": 4.3041237113402064e-05,
|
| 1225 |
+
"loss": 0.0791,
|
| 1226 |
+
"step": 167
|
| 1227 |
+
},
|
| 1228 |
+
{
|
| 1229 |
+
"epoch": 1.0838709677419356,
|
| 1230 |
+
"grad_norm": 0.1170034110546112,
|
| 1231 |
+
"learning_rate": 4.329896907216495e-05,
|
| 1232 |
+
"loss": 0.0834,
|
| 1233 |
+
"step": 168
|
| 1234 |
+
},
|
| 1235 |
+
{
|
| 1236 |
+
"epoch": 1.0903225806451613,
|
| 1237 |
+
"grad_norm": 0.10807105898857117,
|
| 1238 |
+
"learning_rate": 4.3556701030927835e-05,
|
| 1239 |
+
"loss": 0.074,
|
| 1240 |
+
"step": 169
|
| 1241 |
+
},
|
| 1242 |
+
{
|
| 1243 |
+
"epoch": 1.096774193548387,
|
| 1244 |
+
"grad_norm": 0.14144091308116913,
|
| 1245 |
+
"learning_rate": 4.3814432989690723e-05,
|
| 1246 |
+
"loss": 0.0867,
|
| 1247 |
+
"step": 170
|
| 1248 |
+
},
|
| 1249 |
+
{
|
| 1250 |
+
"epoch": 1.103225806451613,
|
| 1251 |
+
"grad_norm": 0.11608368158340454,
|
| 1252 |
+
"learning_rate": 4.407216494845361e-05,
|
| 1253 |
+
"loss": 0.0702,
|
| 1254 |
+
"step": 171
|
| 1255 |
+
},
|
| 1256 |
+
{
|
| 1257 |
+
"epoch": 1.1096774193548387,
|
| 1258 |
+
"grad_norm": 0.11372846364974976,
|
| 1259 |
+
"learning_rate": 4.4329896907216494e-05,
|
| 1260 |
+
"loss": 0.0768,
|
| 1261 |
+
"step": 172
|
| 1262 |
+
},
|
| 1263 |
+
{
|
| 1264 |
+
"epoch": 1.1161290322580646,
|
| 1265 |
+
"grad_norm": 0.13371770083904266,
|
| 1266 |
+
"learning_rate": 4.458762886597938e-05,
|
| 1267 |
+
"loss": 0.0754,
|
| 1268 |
+
"step": 173
|
| 1269 |
+
},
|
| 1270 |
+
{
|
| 1271 |
+
"epoch": 1.1225806451612903,
|
| 1272 |
+
"grad_norm": 0.10914810746908188,
|
| 1273 |
+
"learning_rate": 4.484536082474227e-05,
|
| 1274 |
+
"loss": 0.0781,
|
| 1275 |
+
"step": 174
|
| 1276 |
+
},
|
| 1277 |
+
{
|
| 1278 |
+
"epoch": 1.129032258064516,
|
| 1279 |
+
"grad_norm": 0.1071656197309494,
|
| 1280 |
+
"learning_rate": 4.5103092783505154e-05,
|
| 1281 |
+
"loss": 0.0688,
|
| 1282 |
+
"step": 175
|
| 1283 |
+
},
|
| 1284 |
+
{
|
| 1285 |
+
"epoch": 1.129032258064516,
|
| 1286 |
+
"eval_loss": 0.07778502255678177,
|
| 1287 |
+
"eval_runtime": 20.6276,
|
| 1288 |
+
"eval_samples_per_second": 4.848,
|
| 1289 |
+
"eval_steps_per_second": 0.097,
|
| 1290 |
+
"step": 175
|
| 1291 |
+
},
|
| 1292 |
+
{
|
| 1293 |
+
"epoch": 1.135483870967742,
|
| 1294 |
+
"grad_norm": 0.11929682642221451,
|
| 1295 |
+
"learning_rate": 4.536082474226804e-05,
|
| 1296 |
+
"loss": 0.0865,
|
| 1297 |
+
"step": 176
|
| 1298 |
+
},
|
| 1299 |
+
{
|
| 1300 |
+
"epoch": 1.1419354838709677,
|
| 1301 |
+
"grad_norm": 0.11669743806123734,
|
| 1302 |
+
"learning_rate": 4.561855670103093e-05,
|
| 1303 |
+
"loss": 0.0656,
|
| 1304 |
+
"step": 177
|
| 1305 |
+
},
|
| 1306 |
+
{
|
| 1307 |
+
"epoch": 1.1483870967741936,
|
| 1308 |
+
"grad_norm": 0.11047486960887909,
|
| 1309 |
+
"learning_rate": 4.5876288659793814e-05,
|
| 1310 |
+
"loss": 0.0745,
|
| 1311 |
+
"step": 178
|
| 1312 |
+
},
|
| 1313 |
+
{
|
| 1314 |
+
"epoch": 1.1548387096774193,
|
| 1315 |
+
"grad_norm": 0.10313151776790619,
|
| 1316 |
+
"learning_rate": 4.61340206185567e-05,
|
| 1317 |
+
"loss": 0.0695,
|
| 1318 |
+
"step": 179
|
| 1319 |
+
},
|
| 1320 |
+
{
|
| 1321 |
+
"epoch": 1.1612903225806452,
|
| 1322 |
+
"grad_norm": 0.10674114525318146,
|
| 1323 |
+
"learning_rate": 4.639175257731959e-05,
|
| 1324 |
+
"loss": 0.0802,
|
| 1325 |
+
"step": 180
|
| 1326 |
+
},
|
| 1327 |
+
{
|
| 1328 |
+
"epoch": 1.167741935483871,
|
| 1329 |
+
"grad_norm": 0.12059634923934937,
|
| 1330 |
+
"learning_rate": 4.6649484536082474e-05,
|
| 1331 |
+
"loss": 0.0733,
|
| 1332 |
+
"step": 181
|
| 1333 |
+
},
|
| 1334 |
+
{
|
| 1335 |
+
"epoch": 1.1741935483870969,
|
| 1336 |
+
"grad_norm": 0.13753844797611237,
|
| 1337 |
+
"learning_rate": 4.690721649484536e-05,
|
| 1338 |
+
"loss": 0.0778,
|
| 1339 |
+
"step": 182
|
| 1340 |
+
},
|
| 1341 |
+
{
|
| 1342 |
+
"epoch": 1.1806451612903226,
|
| 1343 |
+
"grad_norm": 0.12316151708364487,
|
| 1344 |
+
"learning_rate": 4.716494845360825e-05,
|
| 1345 |
+
"loss": 0.0732,
|
| 1346 |
+
"step": 183
|
| 1347 |
+
},
|
| 1348 |
+
{
|
| 1349 |
+
"epoch": 1.1870967741935483,
|
| 1350 |
+
"grad_norm": 0.1259049028158188,
|
| 1351 |
+
"learning_rate": 4.7422680412371134e-05,
|
| 1352 |
+
"loss": 0.0768,
|
| 1353 |
+
"step": 184
|
| 1354 |
+
},
|
| 1355 |
+
{
|
| 1356 |
+
"epoch": 1.1935483870967742,
|
| 1357 |
+
"grad_norm": 0.12398969382047653,
|
| 1358 |
+
"learning_rate": 4.768041237113402e-05,
|
| 1359 |
+
"loss": 0.0784,
|
| 1360 |
+
"step": 185
|
| 1361 |
+
},
|
| 1362 |
+
{
|
| 1363 |
+
"epoch": 1.2,
|
| 1364 |
+
"grad_norm": 0.11158449947834015,
|
| 1365 |
+
"learning_rate": 4.793814432989691e-05,
|
| 1366 |
+
"loss": 0.063,
|
| 1367 |
+
"step": 186
|
| 1368 |
+
},
|
| 1369 |
+
{
|
| 1370 |
+
"epoch": 1.206451612903226,
|
| 1371 |
+
"grad_norm": 0.1099303588271141,
|
| 1372 |
+
"learning_rate": 4.8195876288659794e-05,
|
| 1373 |
+
"loss": 0.0715,
|
| 1374 |
+
"step": 187
|
| 1375 |
+
},
|
| 1376 |
+
{
|
| 1377 |
+
"epoch": 1.2129032258064516,
|
| 1378 |
+
"grad_norm": 0.12735599279403687,
|
| 1379 |
+
"learning_rate": 4.845360824742268e-05,
|
| 1380 |
+
"loss": 0.0727,
|
| 1381 |
+
"step": 188
|
| 1382 |
+
},
|
| 1383 |
+
{
|
| 1384 |
+
"epoch": 1.2193548387096773,
|
| 1385 |
+
"grad_norm": 0.12002066522836685,
|
| 1386 |
+
"learning_rate": 4.871134020618557e-05,
|
| 1387 |
+
"loss": 0.0662,
|
| 1388 |
+
"step": 189
|
| 1389 |
+
},
|
| 1390 |
+
{
|
| 1391 |
+
"epoch": 1.2258064516129032,
|
| 1392 |
+
"grad_norm": 0.11072317510843277,
|
| 1393 |
+
"learning_rate": 4.8969072164948454e-05,
|
| 1394 |
+
"loss": 0.0632,
|
| 1395 |
+
"step": 190
|
| 1396 |
+
},
|
| 1397 |
+
{
|
| 1398 |
+
"epoch": 1.232258064516129,
|
| 1399 |
+
"grad_norm": 0.11942410469055176,
|
| 1400 |
+
"learning_rate": 4.922680412371134e-05,
|
| 1401 |
+
"loss": 0.0787,
|
| 1402 |
+
"step": 191
|
| 1403 |
+
},
|
| 1404 |
+
{
|
| 1405 |
+
"epoch": 1.238709677419355,
|
| 1406 |
+
"grad_norm": 0.12091650813817978,
|
| 1407 |
+
"learning_rate": 4.948453608247423e-05,
|
| 1408 |
+
"loss": 0.068,
|
| 1409 |
+
"step": 192
|
| 1410 |
+
},
|
| 1411 |
+
{
|
| 1412 |
+
"epoch": 1.2451612903225806,
|
| 1413 |
+
"grad_norm": 0.12011866271495819,
|
| 1414 |
+
"learning_rate": 4.9742268041237114e-05,
|
| 1415 |
+
"loss": 0.0718,
|
| 1416 |
+
"step": 193
|
| 1417 |
+
},
|
| 1418 |
+
{
|
| 1419 |
+
"epoch": 1.2516129032258063,
|
| 1420 |
+
"grad_norm": 0.1052054762840271,
|
| 1421 |
+
"learning_rate": 5e-05,
|
| 1422 |
+
"loss": 0.0684,
|
| 1423 |
+
"step": 194
|
| 1424 |
+
},
|
| 1425 |
+
{
|
| 1426 |
+
"epoch": 1.2580645161290323,
|
| 1427 |
+
"grad_norm": 0.14064306020736694,
|
| 1428 |
+
"learning_rate": 5.025773195876289e-05,
|
| 1429 |
+
"loss": 0.1004,
|
| 1430 |
+
"step": 195
|
| 1431 |
+
},
|
| 1432 |
+
{
|
| 1433 |
+
"epoch": 1.2645161290322582,
|
| 1434 |
+
"grad_norm": 0.11315371841192245,
|
| 1435 |
+
"learning_rate": 5.051546391752577e-05,
|
| 1436 |
+
"loss": 0.0723,
|
| 1437 |
+
"step": 196
|
| 1438 |
+
},
|
| 1439 |
+
{
|
| 1440 |
+
"epoch": 1.270967741935484,
|
| 1441 |
+
"grad_norm": 0.10275565087795258,
|
| 1442 |
+
"learning_rate": 5.077319587628866e-05,
|
| 1443 |
+
"loss": 0.0624,
|
| 1444 |
+
"step": 197
|
| 1445 |
+
},
|
| 1446 |
+
{
|
| 1447 |
+
"epoch": 1.2774193548387096,
|
| 1448 |
+
"grad_norm": 0.10500184446573257,
|
| 1449 |
+
"learning_rate": 5.1030927835051544e-05,
|
| 1450 |
+
"loss": 0.0654,
|
| 1451 |
+
"step": 198
|
| 1452 |
+
},
|
| 1453 |
+
{
|
| 1454 |
+
"epoch": 1.2838709677419355,
|
| 1455 |
+
"grad_norm": 0.11868240684270859,
|
| 1456 |
+
"learning_rate": 5.128865979381443e-05,
|
| 1457 |
+
"loss": 0.0682,
|
| 1458 |
+
"step": 199
|
| 1459 |
+
},
|
| 1460 |
+
{
|
| 1461 |
+
"epoch": 1.2903225806451613,
|
| 1462 |
+
"grad_norm": 0.12519873678684235,
|
| 1463 |
+
"learning_rate": 5.1546391752577315e-05,
|
| 1464 |
+
"loss": 0.0682,
|
| 1465 |
+
"step": 200
|
| 1466 |
+
},
|
| 1467 |
+
{
|
| 1468 |
+
"epoch": 1.2903225806451613,
|
| 1469 |
+
"eval_loss": 0.07227456569671631,
|
| 1470 |
+
"eval_runtime": 21.4152,
|
| 1471 |
+
"eval_samples_per_second": 4.67,
|
| 1472 |
+
"eval_steps_per_second": 0.093,
|
| 1473 |
+
"step": 200
|
| 1474 |
+
},
|
| 1475 |
+
{
|
| 1476 |
+
"epoch": 1.2967741935483872,
|
| 1477 |
+
"grad_norm": 0.11801688373088837,
|
| 1478 |
+
"learning_rate": 5.180412371134021e-05,
|
| 1479 |
+
"loss": 0.0661,
|
| 1480 |
+
"step": 201
|
| 1481 |
+
},
|
| 1482 |
+
{
|
| 1483 |
+
"epoch": 1.303225806451613,
|
| 1484 |
+
"grad_norm": 0.12295070290565491,
|
| 1485 |
+
"learning_rate": 5.20618556701031e-05,
|
| 1486 |
+
"loss": 0.0572,
|
| 1487 |
+
"step": 202
|
| 1488 |
+
},
|
| 1489 |
+
{
|
| 1490 |
+
"epoch": 1.3096774193548386,
|
| 1491 |
+
"grad_norm": 0.11511899530887604,
|
| 1492 |
+
"learning_rate": 5.231958762886598e-05,
|
| 1493 |
+
"loss": 0.0687,
|
| 1494 |
+
"step": 203
|
| 1495 |
+
},
|
| 1496 |
+
{
|
| 1497 |
+
"epoch": 1.3161290322580645,
|
| 1498 |
+
"grad_norm": 0.10693535953760147,
|
| 1499 |
+
"learning_rate": 5.257731958762887e-05,
|
| 1500 |
+
"loss": 0.0606,
|
| 1501 |
+
"step": 204
|
| 1502 |
+
},
|
| 1503 |
+
{
|
| 1504 |
+
"epoch": 1.3225806451612903,
|
| 1505 |
+
"grad_norm": 0.11811978369951248,
|
| 1506 |
+
"learning_rate": 5.283505154639175e-05,
|
| 1507 |
+
"loss": 0.0692,
|
| 1508 |
+
"step": 205
|
| 1509 |
+
},
|
| 1510 |
+
{
|
| 1511 |
+
"epoch": 1.3290322580645162,
|
| 1512 |
+
"grad_norm": 0.11573677510023117,
|
| 1513 |
+
"learning_rate": 5.309278350515464e-05,
|
| 1514 |
+
"loss": 0.0778,
|
| 1515 |
+
"step": 206
|
| 1516 |
+
},
|
| 1517 |
+
{
|
| 1518 |
+
"epoch": 1.335483870967742,
|
| 1519 |
+
"grad_norm": 0.1057257205247879,
|
| 1520 |
+
"learning_rate": 5.335051546391753e-05,
|
| 1521 |
+
"loss": 0.0537,
|
| 1522 |
+
"step": 207
|
| 1523 |
+
},
|
| 1524 |
+
{
|
| 1525 |
+
"epoch": 1.3419354838709676,
|
| 1526 |
+
"grad_norm": 0.11804960668087006,
|
| 1527 |
+
"learning_rate": 5.360824742268041e-05,
|
| 1528 |
+
"loss": 0.0637,
|
| 1529 |
+
"step": 208
|
| 1530 |
+
},
|
| 1531 |
+
{
|
| 1532 |
+
"epoch": 1.3483870967741935,
|
| 1533 |
+
"grad_norm": 0.10735280811786652,
|
| 1534 |
+
"learning_rate": 5.38659793814433e-05,
|
| 1535 |
+
"loss": 0.0694,
|
| 1536 |
+
"step": 209
|
| 1537 |
+
},
|
| 1538 |
+
{
|
| 1539 |
+
"epoch": 1.3548387096774195,
|
| 1540 |
+
"grad_norm": 0.10669250041246414,
|
| 1541 |
+
"learning_rate": 5.4123711340206184e-05,
|
| 1542 |
+
"loss": 0.0581,
|
| 1543 |
+
"step": 210
|
| 1544 |
+
},
|
| 1545 |
+
{
|
| 1546 |
+
"epoch": 1.3612903225806452,
|
| 1547 |
+
"grad_norm": 0.12118824571371078,
|
| 1548 |
+
"learning_rate": 5.438144329896907e-05,
|
| 1549 |
+
"loss": 0.0711,
|
| 1550 |
+
"step": 211
|
| 1551 |
+
},
|
| 1552 |
+
{
|
| 1553 |
+
"epoch": 1.367741935483871,
|
| 1554 |
+
"grad_norm": 0.10448060184717178,
|
| 1555 |
+
"learning_rate": 5.4639175257731955e-05,
|
| 1556 |
+
"loss": 0.0641,
|
| 1557 |
+
"step": 212
|
| 1558 |
+
},
|
| 1559 |
+
{
|
| 1560 |
+
"epoch": 1.3741935483870968,
|
| 1561 |
+
"grad_norm": 0.11256902664899826,
|
| 1562 |
+
"learning_rate": 5.489690721649485e-05,
|
| 1563 |
+
"loss": 0.0617,
|
| 1564 |
+
"step": 213
|
| 1565 |
+
},
|
| 1566 |
+
{
|
| 1567 |
+
"epoch": 1.3806451612903226,
|
| 1568 |
+
"grad_norm": 0.12368633598089218,
|
| 1569 |
+
"learning_rate": 5.515463917525774e-05,
|
| 1570 |
+
"loss": 0.0698,
|
| 1571 |
+
"step": 214
|
| 1572 |
+
},
|
| 1573 |
+
{
|
| 1574 |
+
"epoch": 1.3870967741935485,
|
| 1575 |
+
"grad_norm": 0.1177687793970108,
|
| 1576 |
+
"learning_rate": 5.541237113402062e-05,
|
| 1577 |
+
"loss": 0.0748,
|
| 1578 |
+
"step": 215
|
| 1579 |
+
},
|
| 1580 |
+
{
|
| 1581 |
+
"epoch": 1.3935483870967742,
|
| 1582 |
+
"grad_norm": 0.11173977702856064,
|
| 1583 |
+
"learning_rate": 5.567010309278351e-05,
|
| 1584 |
+
"loss": 0.058,
|
| 1585 |
+
"step": 216
|
| 1586 |
+
},
|
| 1587 |
+
{
|
| 1588 |
+
"epoch": 1.4,
|
| 1589 |
+
"grad_norm": 0.10333617776632309,
|
| 1590 |
+
"learning_rate": 5.592783505154639e-05,
|
| 1591 |
+
"loss": 0.0544,
|
| 1592 |
+
"step": 217
|
| 1593 |
+
},
|
| 1594 |
+
{
|
| 1595 |
+
"epoch": 1.4064516129032258,
|
| 1596 |
+
"grad_norm": 0.12021996080875397,
|
| 1597 |
+
"learning_rate": 5.618556701030928e-05,
|
| 1598 |
+
"loss": 0.0654,
|
| 1599 |
+
"step": 218
|
| 1600 |
+
},
|
| 1601 |
+
{
|
| 1602 |
+
"epoch": 1.4129032258064516,
|
| 1603 |
+
"grad_norm": 0.10966646671295166,
|
| 1604 |
+
"learning_rate": 5.644329896907217e-05,
|
| 1605 |
+
"loss": 0.0654,
|
| 1606 |
+
"step": 219
|
| 1607 |
+
},
|
| 1608 |
+
{
|
| 1609 |
+
"epoch": 1.4193548387096775,
|
| 1610 |
+
"grad_norm": 0.1111980453133583,
|
| 1611 |
+
"learning_rate": 5.670103092783505e-05,
|
| 1612 |
+
"loss": 0.0683,
|
| 1613 |
+
"step": 220
|
| 1614 |
+
},
|
| 1615 |
+
{
|
| 1616 |
+
"epoch": 1.4258064516129032,
|
| 1617 |
+
"grad_norm": 0.10386307537555695,
|
| 1618 |
+
"learning_rate": 5.695876288659794e-05,
|
| 1619 |
+
"loss": 0.0514,
|
| 1620 |
+
"step": 221
|
| 1621 |
+
},
|
| 1622 |
+
{
|
| 1623 |
+
"epoch": 1.432258064516129,
|
| 1624 |
+
"grad_norm": 0.12473642826080322,
|
| 1625 |
+
"learning_rate": 5.721649484536082e-05,
|
| 1626 |
+
"loss": 0.0728,
|
| 1627 |
+
"step": 222
|
| 1628 |
+
},
|
| 1629 |
+
{
|
| 1630 |
+
"epoch": 1.4387096774193548,
|
| 1631 |
+
"grad_norm": 0.12365364283323288,
|
| 1632 |
+
"learning_rate": 5.747422680412371e-05,
|
| 1633 |
+
"loss": 0.0719,
|
| 1634 |
+
"step": 223
|
| 1635 |
+
},
|
| 1636 |
+
{
|
| 1637 |
+
"epoch": 1.4451612903225808,
|
| 1638 |
+
"grad_norm": 0.124308742582798,
|
| 1639 |
+
"learning_rate": 5.7731958762886594e-05,
|
| 1640 |
+
"loss": 0.0668,
|
| 1641 |
+
"step": 224
|
| 1642 |
+
},
|
| 1643 |
+
{
|
| 1644 |
+
"epoch": 1.4516129032258065,
|
| 1645 |
+
"grad_norm": 0.10575917363166809,
|
| 1646 |
+
"learning_rate": 5.798969072164949e-05,
|
| 1647 |
+
"loss": 0.0621,
|
| 1648 |
+
"step": 225
|
| 1649 |
+
},
|
| 1650 |
+
{
|
| 1651 |
+
"epoch": 1.4516129032258065,
|
| 1652 |
+
"eval_loss": 0.06675011664628983,
|
| 1653 |
+
"eval_runtime": 20.6214,
|
| 1654 |
+
"eval_samples_per_second": 4.849,
|
| 1655 |
+
"eval_steps_per_second": 0.097,
|
| 1656 |
+
"step": 225
|
| 1657 |
+
},
|
| 1658 |
+
{
|
| 1659 |
+
"epoch": 1.4580645161290322,
|
| 1660 |
+
"grad_norm": 0.11430371552705765,
|
| 1661 |
+
"learning_rate": 5.824742268041238e-05,
|
| 1662 |
+
"loss": 0.0544,
|
| 1663 |
+
"step": 226
|
| 1664 |
+
},
|
| 1665 |
+
{
|
| 1666 |
+
"epoch": 1.4645161290322581,
|
| 1667 |
+
"grad_norm": 0.11742933839559555,
|
| 1668 |
+
"learning_rate": 5.850515463917526e-05,
|
| 1669 |
+
"loss": 0.0628,
|
| 1670 |
+
"step": 227
|
| 1671 |
+
},
|
| 1672 |
+
{
|
| 1673 |
+
"epoch": 1.4709677419354839,
|
| 1674 |
+
"grad_norm": 0.11245157569646835,
|
| 1675 |
+
"learning_rate": 5.876288659793815e-05,
|
| 1676 |
+
"loss": 0.0601,
|
| 1677 |
+
"step": 228
|
| 1678 |
+
},
|
| 1679 |
+
{
|
| 1680 |
+
"epoch": 1.4774193548387098,
|
| 1681 |
+
"grad_norm": 0.11818389594554901,
|
| 1682 |
+
"learning_rate": 5.902061855670103e-05,
|
| 1683 |
+
"loss": 0.061,
|
| 1684 |
+
"step": 229
|
| 1685 |
+
},
|
| 1686 |
+
{
|
| 1687 |
+
"epoch": 1.4838709677419355,
|
| 1688 |
+
"grad_norm": 0.11650433391332626,
|
| 1689 |
+
"learning_rate": 5.927835051546392e-05,
|
| 1690 |
+
"loss": 0.0618,
|
| 1691 |
+
"step": 230
|
| 1692 |
+
},
|
| 1693 |
+
{
|
| 1694 |
+
"epoch": 1.4903225806451612,
|
| 1695 |
+
"grad_norm": 0.12074518948793411,
|
| 1696 |
+
"learning_rate": 5.953608247422681e-05,
|
| 1697 |
+
"loss": 0.0638,
|
| 1698 |
+
"step": 231
|
| 1699 |
+
},
|
| 1700 |
+
{
|
| 1701 |
+
"epoch": 1.4967741935483871,
|
| 1702 |
+
"grad_norm": 0.10723990947008133,
|
| 1703 |
+
"learning_rate": 5.979381443298969e-05,
|
| 1704 |
+
"loss": 0.0645,
|
| 1705 |
+
"step": 232
|
| 1706 |
+
},
|
| 1707 |
+
{
|
| 1708 |
+
"epoch": 1.5032258064516129,
|
| 1709 |
+
"grad_norm": 0.11135580390691757,
|
| 1710 |
+
"learning_rate": 6.005154639175258e-05,
|
| 1711 |
+
"loss": 0.0623,
|
| 1712 |
+
"step": 233
|
| 1713 |
+
},
|
| 1714 |
+
{
|
| 1715 |
+
"epoch": 1.5096774193548388,
|
| 1716 |
+
"grad_norm": 0.12259957939386368,
|
| 1717 |
+
"learning_rate": 6.030927835051546e-05,
|
| 1718 |
+
"loss": 0.0735,
|
| 1719 |
+
"step": 234
|
| 1720 |
+
},
|
| 1721 |
+
{
|
| 1722 |
+
"epoch": 1.5161290322580645,
|
| 1723 |
+
"grad_norm": 0.09547890722751617,
|
| 1724 |
+
"learning_rate": 6.056701030927835e-05,
|
| 1725 |
+
"loss": 0.0564,
|
| 1726 |
+
"step": 235
|
| 1727 |
+
},
|
| 1728 |
+
{
|
| 1729 |
+
"epoch": 1.5225806451612902,
|
| 1730 |
+
"grad_norm": 0.10515465587377548,
|
| 1731 |
+
"learning_rate": 6.0824742268041234e-05,
|
| 1732 |
+
"loss": 0.062,
|
| 1733 |
+
"step": 236
|
| 1734 |
+
},
|
| 1735 |
+
{
|
| 1736 |
+
"epoch": 1.5290322580645161,
|
| 1737 |
+
"grad_norm": 0.1125471293926239,
|
| 1738 |
+
"learning_rate": 6.108247422680413e-05,
|
| 1739 |
+
"loss": 0.0563,
|
| 1740 |
+
"step": 237
|
| 1741 |
+
},
|
| 1742 |
+
{
|
| 1743 |
+
"epoch": 1.535483870967742,
|
| 1744 |
+
"grad_norm": 0.11628098785877228,
|
| 1745 |
+
"learning_rate": 6.134020618556701e-05,
|
| 1746 |
+
"loss": 0.0649,
|
| 1747 |
+
"step": 238
|
| 1748 |
+
},
|
| 1749 |
+
{
|
| 1750 |
+
"epoch": 1.5419354838709678,
|
| 1751 |
+
"grad_norm": 0.1112600564956665,
|
| 1752 |
+
"learning_rate": 6.159793814432991e-05,
|
| 1753 |
+
"loss": 0.0539,
|
| 1754 |
+
"step": 239
|
| 1755 |
+
},
|
| 1756 |
+
{
|
| 1757 |
+
"epoch": 1.5483870967741935,
|
| 1758 |
+
"grad_norm": 0.13200533390045166,
|
| 1759 |
+
"learning_rate": 6.185567010309279e-05,
|
| 1760 |
+
"loss": 0.0713,
|
| 1761 |
+
"step": 240
|
| 1762 |
+
},
|
| 1763 |
+
{
|
| 1764 |
+
"epoch": 1.5548387096774192,
|
| 1765 |
+
"grad_norm": 0.11476446688175201,
|
| 1766 |
+
"learning_rate": 6.211340206185567e-05,
|
| 1767 |
+
"loss": 0.0626,
|
| 1768 |
+
"step": 241
|
| 1769 |
+
},
|
| 1770 |
+
{
|
| 1771 |
+
"epoch": 1.5612903225806452,
|
| 1772 |
+
"grad_norm": 0.13394683599472046,
|
| 1773 |
+
"learning_rate": 6.237113402061855e-05,
|
| 1774 |
+
"loss": 0.0672,
|
| 1775 |
+
"step": 242
|
| 1776 |
+
},
|
| 1777 |
+
{
|
| 1778 |
+
"epoch": 1.567741935483871,
|
| 1779 |
+
"grad_norm": 0.1322658658027649,
|
| 1780 |
+
"learning_rate": 6.262886597938145e-05,
|
| 1781 |
+
"loss": 0.0687,
|
| 1782 |
+
"step": 243
|
| 1783 |
+
},
|
| 1784 |
+
{
|
| 1785 |
+
"epoch": 1.5741935483870968,
|
| 1786 |
+
"grad_norm": 0.10362022370100021,
|
| 1787 |
+
"learning_rate": 6.288659793814433e-05,
|
| 1788 |
+
"loss": 0.057,
|
| 1789 |
+
"step": 244
|
| 1790 |
+
},
|
| 1791 |
+
{
|
| 1792 |
+
"epoch": 1.5806451612903225,
|
| 1793 |
+
"grad_norm": 0.1106092780828476,
|
| 1794 |
+
"learning_rate": 6.314432989690721e-05,
|
| 1795 |
+
"loss": 0.0541,
|
| 1796 |
+
"step": 245
|
| 1797 |
+
},
|
| 1798 |
+
{
|
| 1799 |
+
"epoch": 1.5870967741935482,
|
| 1800 |
+
"grad_norm": 0.12139949202537537,
|
| 1801 |
+
"learning_rate": 6.340206185567011e-05,
|
| 1802 |
+
"loss": 0.0641,
|
| 1803 |
+
"step": 246
|
| 1804 |
+
},
|
| 1805 |
+
{
|
| 1806 |
+
"epoch": 1.5935483870967742,
|
| 1807 |
+
"grad_norm": 0.09728733450174332,
|
| 1808 |
+
"learning_rate": 6.365979381443299e-05,
|
| 1809 |
+
"loss": 0.0491,
|
| 1810 |
+
"step": 247
|
| 1811 |
+
},
|
| 1812 |
+
{
|
| 1813 |
+
"epoch": 1.6,
|
| 1814 |
+
"grad_norm": 0.10788699984550476,
|
| 1815 |
+
"learning_rate": 6.391752577319587e-05,
|
| 1816 |
+
"loss": 0.0545,
|
| 1817 |
+
"step": 248
|
| 1818 |
+
},
|
| 1819 |
+
{
|
| 1820 |
+
"epoch": 1.6064516129032258,
|
| 1821 |
+
"grad_norm": 0.11605466157197952,
|
| 1822 |
+
"learning_rate": 6.417525773195877e-05,
|
| 1823 |
+
"loss": 0.0528,
|
| 1824 |
+
"step": 249
|
| 1825 |
+
},
|
| 1826 |
+
{
|
| 1827 |
+
"epoch": 1.6129032258064515,
|
| 1828 |
+
"grad_norm": 0.10914571583271027,
|
| 1829 |
+
"learning_rate": 6.443298969072165e-05,
|
| 1830 |
+
"loss": 0.0668,
|
| 1831 |
+
"step": 250
|
| 1832 |
+
},
|
| 1833 |
+
{
|
| 1834 |
+
"epoch": 1.6129032258064515,
|
| 1835 |
+
"eval_loss": 0.06458242982625961,
|
| 1836 |
+
"eval_runtime": 20.6082,
|
| 1837 |
+
"eval_samples_per_second": 4.852,
|
| 1838 |
+
"eval_steps_per_second": 0.097,
|
| 1839 |
+
"step": 250
|
| 1840 |
+
},
|
| 1841 |
+
{
|
| 1842 |
+
"epoch": 1.6193548387096774,
|
| 1843 |
+
"grad_norm": 0.10836615413427353,
|
| 1844 |
+
"learning_rate": 6.469072164948455e-05,
|
| 1845 |
+
"loss": 0.0647,
|
| 1846 |
+
"step": 251
|
| 1847 |
+
},
|
| 1848 |
+
{
|
| 1849 |
+
"epoch": 1.6258064516129034,
|
| 1850 |
+
"grad_norm": 0.09761244803667068,
|
| 1851 |
+
"learning_rate": 6.494845360824743e-05,
|
| 1852 |
+
"loss": 0.0545,
|
| 1853 |
+
"step": 252
|
| 1854 |
+
},
|
| 1855 |
+
{
|
| 1856 |
+
"epoch": 1.632258064516129,
|
| 1857 |
+
"grad_norm": 0.10434439033269882,
|
| 1858 |
+
"learning_rate": 6.520618556701031e-05,
|
| 1859 |
+
"loss": 0.058,
|
| 1860 |
+
"step": 253
|
| 1861 |
+
},
|
| 1862 |
+
{
|
| 1863 |
+
"epoch": 1.6387096774193548,
|
| 1864 |
+
"grad_norm": 0.10498231649398804,
|
| 1865 |
+
"learning_rate": 6.546391752577319e-05,
|
| 1866 |
+
"loss": 0.0613,
|
| 1867 |
+
"step": 254
|
| 1868 |
+
},
|
| 1869 |
+
{
|
| 1870 |
+
"epoch": 1.6451612903225805,
|
| 1871 |
+
"grad_norm": 0.09180215001106262,
|
| 1872 |
+
"learning_rate": 6.572164948453609e-05,
|
| 1873 |
+
"loss": 0.0499,
|
| 1874 |
+
"step": 255
|
| 1875 |
+
},
|
| 1876 |
+
{
|
| 1877 |
+
"epoch": 1.6516129032258065,
|
| 1878 |
+
"grad_norm": 0.10550273954868317,
|
| 1879 |
+
"learning_rate": 6.597938144329897e-05,
|
| 1880 |
+
"loss": 0.0546,
|
| 1881 |
+
"step": 256
|
| 1882 |
+
},
|
| 1883 |
+
{
|
| 1884 |
+
"epoch": 1.6580645161290324,
|
| 1885 |
+
"grad_norm": 0.11006518453359604,
|
| 1886 |
+
"learning_rate": 6.623711340206185e-05,
|
| 1887 |
+
"loss": 0.0573,
|
| 1888 |
+
"step": 257
|
| 1889 |
+
},
|
| 1890 |
+
{
|
| 1891 |
+
"epoch": 1.664516129032258,
|
| 1892 |
+
"grad_norm": 0.09517877548933029,
|
| 1893 |
+
"learning_rate": 6.649484536082475e-05,
|
| 1894 |
+
"loss": 0.0571,
|
| 1895 |
+
"step": 258
|
| 1896 |
+
},
|
| 1897 |
+
{
|
| 1898 |
+
"epoch": 1.6709677419354838,
|
| 1899 |
+
"grad_norm": 0.10255111753940582,
|
| 1900 |
+
"learning_rate": 6.675257731958763e-05,
|
| 1901 |
+
"loss": 0.067,
|
| 1902 |
+
"step": 259
|
| 1903 |
+
},
|
| 1904 |
+
{
|
| 1905 |
+
"epoch": 1.6774193548387095,
|
| 1906 |
+
"grad_norm": 0.10252523422241211,
|
| 1907 |
+
"learning_rate": 6.701030927835051e-05,
|
| 1908 |
+
"loss": 0.0547,
|
| 1909 |
+
"step": 260
|
| 1910 |
+
},
|
| 1911 |
+
{
|
| 1912 |
+
"epoch": 1.6838709677419355,
|
| 1913 |
+
"grad_norm": 0.10796947032213211,
|
| 1914 |
+
"learning_rate": 6.726804123711341e-05,
|
| 1915 |
+
"loss": 0.0555,
|
| 1916 |
+
"step": 261
|
| 1917 |
+
},
|
| 1918 |
+
{
|
| 1919 |
+
"epoch": 1.6903225806451614,
|
| 1920 |
+
"grad_norm": 0.09685982763767242,
|
| 1921 |
+
"learning_rate": 6.752577319587629e-05,
|
| 1922 |
+
"loss": 0.056,
|
| 1923 |
+
"step": 262
|
| 1924 |
+
},
|
| 1925 |
+
{
|
| 1926 |
+
"epoch": 1.696774193548387,
|
| 1927 |
+
"grad_norm": 0.10517261922359467,
|
| 1928 |
+
"learning_rate": 6.778350515463919e-05,
|
| 1929 |
+
"loss": 0.0721,
|
| 1930 |
+
"step": 263
|
| 1931 |
+
},
|
| 1932 |
+
{
|
| 1933 |
+
"epoch": 1.7032258064516128,
|
| 1934 |
+
"grad_norm": 0.10260171443223953,
|
| 1935 |
+
"learning_rate": 6.804123711340207e-05,
|
| 1936 |
+
"loss": 0.063,
|
| 1937 |
+
"step": 264
|
| 1938 |
+
},
|
| 1939 |
+
{
|
| 1940 |
+
"epoch": 1.7096774193548387,
|
| 1941 |
+
"grad_norm": 0.11811640858650208,
|
| 1942 |
+
"learning_rate": 6.829896907216495e-05,
|
| 1943 |
+
"loss": 0.0695,
|
| 1944 |
+
"step": 265
|
| 1945 |
+
},
|
| 1946 |
+
{
|
| 1947 |
+
"epoch": 1.7161290322580647,
|
| 1948 |
+
"grad_norm": 0.11343566328287125,
|
| 1949 |
+
"learning_rate": 6.855670103092783e-05,
|
| 1950 |
+
"loss": 0.0644,
|
| 1951 |
+
"step": 266
|
| 1952 |
+
},
|
| 1953 |
+
{
|
| 1954 |
+
"epoch": 1.7225806451612904,
|
| 1955 |
+
"grad_norm": 0.10600105673074722,
|
| 1956 |
+
"learning_rate": 6.881443298969073e-05,
|
| 1957 |
+
"loss": 0.058,
|
| 1958 |
+
"step": 267
|
| 1959 |
+
},
|
| 1960 |
+
{
|
| 1961 |
+
"epoch": 1.729032258064516,
|
| 1962 |
+
"grad_norm": 0.11247742176055908,
|
| 1963 |
+
"learning_rate": 6.907216494845361e-05,
|
| 1964 |
+
"loss": 0.0585,
|
| 1965 |
+
"step": 268
|
| 1966 |
+
},
|
| 1967 |
+
{
|
| 1968 |
+
"epoch": 1.7354838709677418,
|
| 1969 |
+
"grad_norm": 0.10289078205823898,
|
| 1970 |
+
"learning_rate": 6.932989690721649e-05,
|
| 1971 |
+
"loss": 0.06,
|
| 1972 |
+
"step": 269
|
| 1973 |
+
},
|
| 1974 |
+
{
|
| 1975 |
+
"epoch": 1.7419354838709677,
|
| 1976 |
+
"grad_norm": 0.11505839973688126,
|
| 1977 |
+
"learning_rate": 6.958762886597939e-05,
|
| 1978 |
+
"loss": 0.0622,
|
| 1979 |
+
"step": 270
|
| 1980 |
+
},
|
| 1981 |
+
{
|
| 1982 |
+
"epoch": 1.7483870967741937,
|
| 1983 |
+
"grad_norm": 0.10896378755569458,
|
| 1984 |
+
"learning_rate": 6.984536082474227e-05,
|
| 1985 |
+
"loss": 0.0564,
|
| 1986 |
+
"step": 271
|
| 1987 |
+
},
|
| 1988 |
+
{
|
| 1989 |
+
"epoch": 1.7548387096774194,
|
| 1990 |
+
"grad_norm": 0.10462034493684769,
|
| 1991 |
+
"learning_rate": 7.010309278350515e-05,
|
| 1992 |
+
"loss": 0.0478,
|
| 1993 |
+
"step": 272
|
| 1994 |
+
},
|
| 1995 |
+
{
|
| 1996 |
+
"epoch": 1.761290322580645,
|
| 1997 |
+
"grad_norm": 0.0960521250963211,
|
| 1998 |
+
"learning_rate": 7.036082474226805e-05,
|
| 1999 |
+
"loss": 0.0501,
|
| 2000 |
+
"step": 273
|
| 2001 |
+
},
|
| 2002 |
+
{
|
| 2003 |
+
"epoch": 1.7677419354838708,
|
| 2004 |
+
"grad_norm": 0.113226018846035,
|
| 2005 |
+
"learning_rate": 7.061855670103093e-05,
|
| 2006 |
+
"loss": 0.0487,
|
| 2007 |
+
"step": 274
|
| 2008 |
+
},
|
| 2009 |
+
{
|
| 2010 |
+
"epoch": 1.7741935483870968,
|
| 2011 |
+
"grad_norm": 0.12256605923175812,
|
| 2012 |
+
"learning_rate": 7.087628865979383e-05,
|
| 2013 |
+
"loss": 0.0672,
|
| 2014 |
+
"step": 275
|
| 2015 |
+
},
|
| 2016 |
+
{
|
| 2017 |
+
"epoch": 1.7741935483870968,
|
| 2018 |
+
"eval_loss": 0.0586564727127552,
|
| 2019 |
+
"eval_runtime": 20.6122,
|
| 2020 |
+
"eval_samples_per_second": 4.851,
|
| 2021 |
+
"eval_steps_per_second": 0.097,
|
| 2022 |
+
"step": 275
|
| 2023 |
+
},
|
| 2024 |
+
{
|
| 2025 |
+
"epoch": 1.7806451612903227,
|
| 2026 |
+
"grad_norm": 0.11341353505849838,
|
| 2027 |
+
"learning_rate": 7.113402061855671e-05,
|
| 2028 |
+
"loss": 0.0605,
|
| 2029 |
+
"step": 276
|
| 2030 |
+
},
|
| 2031 |
+
{
|
| 2032 |
+
"epoch": 1.7870967741935484,
|
| 2033 |
+
"grad_norm": 0.10689063370227814,
|
| 2034 |
+
"learning_rate": 7.139175257731959e-05,
|
| 2035 |
+
"loss": 0.0557,
|
| 2036 |
+
"step": 277
|
| 2037 |
+
},
|
| 2038 |
+
{
|
| 2039 |
+
"epoch": 1.793548387096774,
|
| 2040 |
+
"grad_norm": 0.10520404577255249,
|
| 2041 |
+
"learning_rate": 7.164948453608247e-05,
|
| 2042 |
+
"loss": 0.0587,
|
| 2043 |
+
"step": 278
|
| 2044 |
+
},
|
| 2045 |
+
{
|
| 2046 |
+
"epoch": 1.8,
|
| 2047 |
+
"grad_norm": 0.12727777659893036,
|
| 2048 |
+
"learning_rate": 7.190721649484537e-05,
|
| 2049 |
+
"loss": 0.0581,
|
| 2050 |
+
"step": 279
|
| 2051 |
+
},
|
| 2052 |
+
{
|
| 2053 |
+
"epoch": 1.8064516129032258,
|
| 2054 |
+
"grad_norm": 0.11627282202243805,
|
| 2055 |
+
"learning_rate": 7.216494845360825e-05,
|
| 2056 |
+
"loss": 0.0561,
|
| 2057 |
+
"step": 280
|
| 2058 |
+
},
|
| 2059 |
+
{
|
| 2060 |
+
"epoch": 1.8129032258064517,
|
| 2061 |
+
"grad_norm": 0.09967481344938278,
|
| 2062 |
+
"learning_rate": 7.242268041237113e-05,
|
| 2063 |
+
"loss": 0.0489,
|
| 2064 |
+
"step": 281
|
| 2065 |
+
},
|
| 2066 |
+
{
|
| 2067 |
+
"epoch": 1.8193548387096774,
|
| 2068 |
+
"grad_norm": 0.09930626302957535,
|
| 2069 |
+
"learning_rate": 7.268041237113403e-05,
|
| 2070 |
+
"loss": 0.054,
|
| 2071 |
+
"step": 282
|
| 2072 |
+
},
|
| 2073 |
+
{
|
| 2074 |
+
"epoch": 1.8258064516129031,
|
| 2075 |
+
"grad_norm": 0.09552939981222153,
|
| 2076 |
+
"learning_rate": 7.293814432989691e-05,
|
| 2077 |
+
"loss": 0.0555,
|
| 2078 |
+
"step": 283
|
| 2079 |
+
},
|
| 2080 |
+
{
|
| 2081 |
+
"epoch": 1.832258064516129,
|
| 2082 |
+
"grad_norm": 0.11425229907035828,
|
| 2083 |
+
"learning_rate": 7.319587628865979e-05,
|
| 2084 |
+
"loss": 0.0636,
|
| 2085 |
+
"step": 284
|
| 2086 |
+
},
|
| 2087 |
+
{
|
| 2088 |
+
"epoch": 1.838709677419355,
|
| 2089 |
+
"grad_norm": 0.1075424998998642,
|
| 2090 |
+
"learning_rate": 7.345360824742269e-05,
|
| 2091 |
+
"loss": 0.0533,
|
| 2092 |
+
"step": 285
|
| 2093 |
+
},
|
| 2094 |
+
{
|
| 2095 |
+
"epoch": 1.8451612903225807,
|
| 2096 |
+
"grad_norm": 0.09101930260658264,
|
| 2097 |
+
"learning_rate": 7.371134020618557e-05,
|
| 2098 |
+
"loss": 0.0393,
|
| 2099 |
+
"step": 286
|
| 2100 |
+
},
|
| 2101 |
+
{
|
| 2102 |
+
"epoch": 1.8516129032258064,
|
| 2103 |
+
"grad_norm": 0.11300979554653168,
|
| 2104 |
+
"learning_rate": 7.396907216494847e-05,
|
| 2105 |
+
"loss": 0.0512,
|
| 2106 |
+
"step": 287
|
| 2107 |
+
},
|
| 2108 |
+
{
|
| 2109 |
+
"epoch": 1.8580645161290321,
|
| 2110 |
+
"grad_norm": 0.12898088991641998,
|
| 2111 |
+
"learning_rate": 7.422680412371135e-05,
|
| 2112 |
+
"loss": 0.0657,
|
| 2113 |
+
"step": 288
|
| 2114 |
+
},
|
| 2115 |
+
{
|
| 2116 |
+
"epoch": 1.864516129032258,
|
| 2117 |
+
"grad_norm": 0.10775969177484512,
|
| 2118 |
+
"learning_rate": 7.448453608247423e-05,
|
| 2119 |
+
"loss": 0.0633,
|
| 2120 |
+
"step": 289
|
| 2121 |
+
},
|
| 2122 |
+
{
|
| 2123 |
+
"epoch": 1.870967741935484,
|
| 2124 |
+
"grad_norm": 0.12368246912956238,
|
| 2125 |
+
"learning_rate": 7.474226804123711e-05,
|
| 2126 |
+
"loss": 0.0639,
|
| 2127 |
+
"step": 290
|
| 2128 |
+
},
|
| 2129 |
+
{
|
| 2130 |
+
"epoch": 1.8774193548387097,
|
| 2131 |
+
"grad_norm": 0.11313799023628235,
|
| 2132 |
+
"learning_rate": 7.500000000000001e-05,
|
| 2133 |
+
"loss": 0.059,
|
| 2134 |
+
"step": 291
|
| 2135 |
+
},
|
| 2136 |
+
{
|
| 2137 |
+
"epoch": 1.8838709677419354,
|
| 2138 |
+
"grad_norm": 0.10701242834329605,
|
| 2139 |
+
"learning_rate": 7.525773195876289e-05,
|
| 2140 |
+
"loss": 0.0473,
|
| 2141 |
+
"step": 292
|
| 2142 |
+
},
|
| 2143 |
+
{
|
| 2144 |
+
"epoch": 1.8903225806451613,
|
| 2145 |
+
"grad_norm": 0.09166759997606277,
|
| 2146 |
+
"learning_rate": 7.551546391752577e-05,
|
| 2147 |
+
"loss": 0.0438,
|
| 2148 |
+
"step": 293
|
| 2149 |
+
},
|
| 2150 |
+
{
|
| 2151 |
+
"epoch": 1.896774193548387,
|
| 2152 |
+
"grad_norm": 0.1073215901851654,
|
| 2153 |
+
"learning_rate": 7.577319587628867e-05,
|
| 2154 |
+
"loss": 0.0618,
|
| 2155 |
+
"step": 294
|
| 2156 |
+
},
|
| 2157 |
+
{
|
| 2158 |
+
"epoch": 1.903225806451613,
|
| 2159 |
+
"grad_norm": 0.11972848325967789,
|
| 2160 |
+
"learning_rate": 7.603092783505155e-05,
|
| 2161 |
+
"loss": 0.06,
|
| 2162 |
+
"step": 295
|
| 2163 |
+
},
|
| 2164 |
+
{
|
| 2165 |
+
"epoch": 1.9096774193548387,
|
| 2166 |
+
"grad_norm": 0.10502435266971588,
|
| 2167 |
+
"learning_rate": 7.628865979381443e-05,
|
| 2168 |
+
"loss": 0.0517,
|
| 2169 |
+
"step": 296
|
| 2170 |
+
},
|
| 2171 |
+
{
|
| 2172 |
+
"epoch": 1.9161290322580644,
|
| 2173 |
+
"grad_norm": 0.10517352819442749,
|
| 2174 |
+
"learning_rate": 7.654639175257731e-05,
|
| 2175 |
+
"loss": 0.0499,
|
| 2176 |
+
"step": 297
|
| 2177 |
+
},
|
| 2178 |
+
{
|
| 2179 |
+
"epoch": 1.9225806451612903,
|
| 2180 |
+
"grad_norm": 0.08997687697410583,
|
| 2181 |
+
"learning_rate": 7.680412371134021e-05,
|
| 2182 |
+
"loss": 0.0426,
|
| 2183 |
+
"step": 298
|
| 2184 |
+
},
|
| 2185 |
+
{
|
| 2186 |
+
"epoch": 1.9290322580645163,
|
| 2187 |
+
"grad_norm": 0.10763172805309296,
|
| 2188 |
+
"learning_rate": 7.70618556701031e-05,
|
| 2189 |
+
"loss": 0.0624,
|
| 2190 |
+
"step": 299
|
| 2191 |
+
},
|
| 2192 |
+
{
|
| 2193 |
+
"epoch": 1.935483870967742,
|
| 2194 |
+
"grad_norm": 0.09808403253555298,
|
| 2195 |
+
"learning_rate": 7.731958762886599e-05,
|
| 2196 |
+
"loss": 0.0484,
|
| 2197 |
+
"step": 300
|
| 2198 |
+
},
|
| 2199 |
+
{
|
| 2200 |
+
"epoch": 1.935483870967742,
|
| 2201 |
+
"eval_loss": 0.05441552773118019,
|
| 2202 |
+
"eval_runtime": 20.6185,
|
| 2203 |
+
"eval_samples_per_second": 4.85,
|
| 2204 |
+
"eval_steps_per_second": 0.097,
|
| 2205 |
+
"step": 300
|
| 2206 |
+
},
|
| 2207 |
+
{
|
| 2208 |
+
"epoch": 1.9419354838709677,
|
| 2209 |
+
"grad_norm": 0.09616626799106598,
|
| 2210 |
+
"learning_rate": 7.757731958762887e-05,
|
| 2211 |
+
"loss": 0.0454,
|
| 2212 |
+
"step": 301
|
| 2213 |
+
},
|
| 2214 |
+
{
|
| 2215 |
+
"epoch": 1.9483870967741934,
|
| 2216 |
+
"grad_norm": 0.12124036252498627,
|
| 2217 |
+
"learning_rate": 7.783505154639175e-05,
|
| 2218 |
+
"loss": 0.0551,
|
| 2219 |
+
"step": 302
|
| 2220 |
+
},
|
| 2221 |
+
{
|
| 2222 |
+
"epoch": 1.9548387096774194,
|
| 2223 |
+
"grad_norm": 0.09645543247461319,
|
| 2224 |
+
"learning_rate": 7.809278350515465e-05,
|
| 2225 |
+
"loss": 0.0484,
|
| 2226 |
+
"step": 303
|
| 2227 |
+
},
|
| 2228 |
+
{
|
| 2229 |
+
"epoch": 1.9612903225806453,
|
| 2230 |
+
"grad_norm": 0.1068158969283104,
|
| 2231 |
+
"learning_rate": 7.835051546391753e-05,
|
| 2232 |
+
"loss": 0.0606,
|
| 2233 |
+
"step": 304
|
| 2234 |
+
},
|
| 2235 |
+
{
|
| 2236 |
+
"epoch": 1.967741935483871,
|
| 2237 |
+
"grad_norm": 0.09896648675203323,
|
| 2238 |
+
"learning_rate": 7.860824742268041e-05,
|
| 2239 |
+
"loss": 0.0437,
|
| 2240 |
+
"step": 305
|
| 2241 |
+
},
|
| 2242 |
+
{
|
| 2243 |
+
"epoch": 1.9741935483870967,
|
| 2244 |
+
"grad_norm": 0.11050526052713394,
|
| 2245 |
+
"learning_rate": 7.88659793814433e-05,
|
| 2246 |
+
"loss": 0.0593,
|
| 2247 |
+
"step": 306
|
| 2248 |
+
},
|
| 2249 |
+
{
|
| 2250 |
+
"epoch": 1.9806451612903224,
|
| 2251 |
+
"grad_norm": 0.10204251855611801,
|
| 2252 |
+
"learning_rate": 7.912371134020619e-05,
|
| 2253 |
+
"loss": 0.061,
|
| 2254 |
+
"step": 307
|
| 2255 |
+
},
|
| 2256 |
+
{
|
| 2257 |
+
"epoch": 1.9870967741935484,
|
| 2258 |
+
"grad_norm": 0.10084798187017441,
|
| 2259 |
+
"learning_rate": 7.938144329896907e-05,
|
| 2260 |
+
"loss": 0.0473,
|
| 2261 |
+
"step": 308
|
| 2262 |
+
},
|
| 2263 |
+
{
|
| 2264 |
+
"epoch": 1.9935483870967743,
|
| 2265 |
+
"grad_norm": 0.1033916026353836,
|
| 2266 |
+
"learning_rate": 7.963917525773195e-05,
|
| 2267 |
+
"loss": 0.0455,
|
| 2268 |
+
"step": 309
|
| 2269 |
+
},
|
| 2270 |
+
{
|
| 2271 |
+
"epoch": 2.0,
|
| 2272 |
+
"grad_norm": 0.16185474395751953,
|
| 2273 |
+
"learning_rate": 7.989690721649485e-05,
|
| 2274 |
+
"loss": 0.0757,
|
| 2275 |
+
"step": 310
|
| 2276 |
+
},
|
| 2277 |
+
{
|
| 2278 |
+
"epoch": 2.0064516129032257,
|
| 2279 |
+
"grad_norm": 0.09380825608968735,
|
| 2280 |
+
"learning_rate": 8.015463917525774e-05,
|
| 2281 |
+
"loss": 0.0454,
|
| 2282 |
+
"step": 311
|
| 2283 |
+
},
|
| 2284 |
+
{
|
| 2285 |
+
"epoch": 2.0129032258064514,
|
| 2286 |
+
"grad_norm": 0.08151062577962875,
|
| 2287 |
+
"learning_rate": 8.041237113402063e-05,
|
| 2288 |
+
"loss": 0.0312,
|
| 2289 |
+
"step": 312
|
| 2290 |
+
},
|
| 2291 |
+
{
|
| 2292 |
+
"epoch": 2.0193548387096776,
|
| 2293 |
+
"grad_norm": 0.08947654813528061,
|
| 2294 |
+
"learning_rate": 8.067010309278351e-05,
|
| 2295 |
+
"loss": 0.0428,
|
| 2296 |
+
"step": 313
|
| 2297 |
+
},
|
| 2298 |
+
{
|
| 2299 |
+
"epoch": 2.0258064516129033,
|
| 2300 |
+
"grad_norm": 0.10064241290092468,
|
| 2301 |
+
"learning_rate": 8.092783505154639e-05,
|
| 2302 |
+
"loss": 0.0375,
|
| 2303 |
+
"step": 314
|
| 2304 |
+
},
|
| 2305 |
+
{
|
| 2306 |
+
"epoch": 2.032258064516129,
|
| 2307 |
+
"grad_norm": 0.10445793718099594,
|
| 2308 |
+
"learning_rate": 8.118556701030929e-05,
|
| 2309 |
+
"loss": 0.0437,
|
| 2310 |
+
"step": 315
|
| 2311 |
+
},
|
| 2312 |
+
{
|
| 2313 |
+
"epoch": 2.0387096774193547,
|
| 2314 |
+
"grad_norm": 0.08970332890748978,
|
| 2315 |
+
"learning_rate": 8.144329896907217e-05,
|
| 2316 |
+
"loss": 0.0345,
|
| 2317 |
+
"step": 316
|
| 2318 |
+
},
|
| 2319 |
+
{
|
| 2320 |
+
"epoch": 2.0451612903225804,
|
| 2321 |
+
"grad_norm": 0.12089475244283676,
|
| 2322 |
+
"learning_rate": 8.170103092783505e-05,
|
| 2323 |
+
"loss": 0.0477,
|
| 2324 |
+
"step": 317
|
| 2325 |
+
},
|
| 2326 |
+
{
|
| 2327 |
+
"epoch": 2.0516129032258066,
|
| 2328 |
+
"grad_norm": 0.12545561790466309,
|
| 2329 |
+
"learning_rate": 8.195876288659795e-05,
|
| 2330 |
+
"loss": 0.0632,
|
| 2331 |
+
"step": 318
|
| 2332 |
+
},
|
| 2333 |
+
{
|
| 2334 |
+
"epoch": 2.0580645161290323,
|
| 2335 |
+
"grad_norm": 0.15998150408267975,
|
| 2336 |
+
"learning_rate": 8.221649484536083e-05,
|
| 2337 |
+
"loss": 0.0478,
|
| 2338 |
+
"step": 319
|
| 2339 |
+
},
|
| 2340 |
+
{
|
| 2341 |
+
"epoch": 2.064516129032258,
|
| 2342 |
+
"grad_norm": 0.09755123406648636,
|
| 2343 |
+
"learning_rate": 8.247422680412371e-05,
|
| 2344 |
+
"loss": 0.0395,
|
| 2345 |
+
"step": 320
|
| 2346 |
+
},
|
| 2347 |
+
{
|
| 2348 |
+
"epoch": 2.0709677419354837,
|
| 2349 |
+
"grad_norm": 0.10251940786838531,
|
| 2350 |
+
"learning_rate": 8.273195876288659e-05,
|
| 2351 |
+
"loss": 0.0474,
|
| 2352 |
+
"step": 321
|
| 2353 |
+
},
|
| 2354 |
+
{
|
| 2355 |
+
"epoch": 2.07741935483871,
|
| 2356 |
+
"grad_norm": 0.09739600867033005,
|
| 2357 |
+
"learning_rate": 8.298969072164949e-05,
|
| 2358 |
+
"loss": 0.0443,
|
| 2359 |
+
"step": 322
|
| 2360 |
+
},
|
| 2361 |
+
{
|
| 2362 |
+
"epoch": 2.0838709677419356,
|
| 2363 |
+
"grad_norm": 0.11511006206274033,
|
| 2364 |
+
"learning_rate": 8.324742268041238e-05,
|
| 2365 |
+
"loss": 0.0458,
|
| 2366 |
+
"step": 323
|
| 2367 |
+
},
|
| 2368 |
+
{
|
| 2369 |
+
"epoch": 2.0903225806451613,
|
| 2370 |
+
"grad_norm": 0.09681696444749832,
|
| 2371 |
+
"learning_rate": 8.350515463917527e-05,
|
| 2372 |
+
"loss": 0.0396,
|
| 2373 |
+
"step": 324
|
| 2374 |
+
},
|
| 2375 |
+
{
|
| 2376 |
+
"epoch": 2.096774193548387,
|
| 2377 |
+
"grad_norm": 0.1090191900730133,
|
| 2378 |
+
"learning_rate": 8.376288659793815e-05,
|
| 2379 |
+
"loss": 0.0468,
|
| 2380 |
+
"step": 325
|
| 2381 |
+
},
|
| 2382 |
+
{
|
| 2383 |
+
"epoch": 2.096774193548387,
|
| 2384 |
+
"eval_loss": 0.05155442655086517,
|
| 2385 |
+
"eval_runtime": 20.6145,
|
| 2386 |
+
"eval_samples_per_second": 4.851,
|
| 2387 |
+
"eval_steps_per_second": 0.097,
|
| 2388 |
+
"step": 325
|
| 2389 |
+
},
|
| 2390 |
+
{
|
| 2391 |
+
"epoch": 2.1032258064516127,
|
| 2392 |
+
"grad_norm": 0.10617301613092422,
|
| 2393 |
+
"learning_rate": 8.402061855670103e-05,
|
| 2394 |
+
"loss": 0.0437,
|
| 2395 |
+
"step": 326
|
| 2396 |
+
},
|
| 2397 |
+
{
|
| 2398 |
+
"epoch": 2.109677419354839,
|
| 2399 |
+
"grad_norm": 0.11813998222351074,
|
| 2400 |
+
"learning_rate": 8.427835051546393e-05,
|
| 2401 |
+
"loss": 0.0458,
|
| 2402 |
+
"step": 327
|
| 2403 |
+
},
|
| 2404 |
+
{
|
| 2405 |
+
"epoch": 2.1161290322580646,
|
| 2406 |
+
"grad_norm": 0.09822124242782593,
|
| 2407 |
+
"learning_rate": 8.453608247422681e-05,
|
| 2408 |
+
"loss": 0.0414,
|
| 2409 |
+
"step": 328
|
| 2410 |
+
},
|
| 2411 |
+
{
|
| 2412 |
+
"epoch": 2.1225806451612903,
|
| 2413 |
+
"grad_norm": 0.0994827002286911,
|
| 2414 |
+
"learning_rate": 8.479381443298969e-05,
|
| 2415 |
+
"loss": 0.0505,
|
| 2416 |
+
"step": 329
|
| 2417 |
+
},
|
| 2418 |
+
{
|
| 2419 |
+
"epoch": 2.129032258064516,
|
| 2420 |
+
"grad_norm": 0.10852402448654175,
|
| 2421 |
+
"learning_rate": 8.505154639175259e-05,
|
| 2422 |
+
"loss": 0.0401,
|
| 2423 |
+
"step": 330
|
| 2424 |
+
},
|
| 2425 |
+
{
|
| 2426 |
+
"epoch": 2.135483870967742,
|
| 2427 |
+
"grad_norm": 0.0973113551735878,
|
| 2428 |
+
"learning_rate": 8.530927835051547e-05,
|
| 2429 |
+
"loss": 0.0468,
|
| 2430 |
+
"step": 331
|
| 2431 |
+
},
|
| 2432 |
+
{
|
| 2433 |
+
"epoch": 2.141935483870968,
|
| 2434 |
+
"grad_norm": 0.10243872553110123,
|
| 2435 |
+
"learning_rate": 8.556701030927835e-05,
|
| 2436 |
+
"loss": 0.0457,
|
| 2437 |
+
"step": 332
|
| 2438 |
+
},
|
| 2439 |
+
{
|
| 2440 |
+
"epoch": 2.1483870967741936,
|
| 2441 |
+
"grad_norm": 0.11962252110242844,
|
| 2442 |
+
"learning_rate": 8.582474226804123e-05,
|
| 2443 |
+
"loss": 0.0548,
|
| 2444 |
+
"step": 333
|
| 2445 |
+
},
|
| 2446 |
+
{
|
| 2447 |
+
"epoch": 2.1548387096774193,
|
| 2448 |
+
"grad_norm": 0.10123623162508011,
|
| 2449 |
+
"learning_rate": 8.608247422680413e-05,
|
| 2450 |
+
"loss": 0.0369,
|
| 2451 |
+
"step": 334
|
| 2452 |
+
},
|
| 2453 |
+
{
|
| 2454 |
+
"epoch": 2.161290322580645,
|
| 2455 |
+
"grad_norm": 0.09829887747764587,
|
| 2456 |
+
"learning_rate": 8.634020618556702e-05,
|
| 2457 |
+
"loss": 0.0372,
|
| 2458 |
+
"step": 335
|
| 2459 |
+
},
|
| 2460 |
+
{
|
| 2461 |
+
"epoch": 2.167741935483871,
|
| 2462 |
+
"grad_norm": 0.09360591322183609,
|
| 2463 |
+
"learning_rate": 8.65979381443299e-05,
|
| 2464 |
+
"loss": 0.0479,
|
| 2465 |
+
"step": 336
|
| 2466 |
+
},
|
| 2467 |
+
{
|
| 2468 |
+
"epoch": 2.174193548387097,
|
| 2469 |
+
"grad_norm": 0.10151084512472153,
|
| 2470 |
+
"learning_rate": 8.685567010309279e-05,
|
| 2471 |
+
"loss": 0.0367,
|
| 2472 |
+
"step": 337
|
| 2473 |
+
},
|
| 2474 |
+
{
|
| 2475 |
+
"epoch": 2.1806451612903226,
|
| 2476 |
+
"grad_norm": 0.12664125859737396,
|
| 2477 |
+
"learning_rate": 8.711340206185567e-05,
|
| 2478 |
+
"loss": 0.043,
|
| 2479 |
+
"step": 338
|
| 2480 |
+
},
|
| 2481 |
+
{
|
| 2482 |
+
"epoch": 2.1870967741935483,
|
| 2483 |
+
"grad_norm": 0.11126257479190826,
|
| 2484 |
+
"learning_rate": 8.737113402061856e-05,
|
| 2485 |
+
"loss": 0.0393,
|
| 2486 |
+
"step": 339
|
| 2487 |
+
},
|
| 2488 |
+
{
|
| 2489 |
+
"epoch": 2.193548387096774,
|
| 2490 |
+
"grad_norm": 0.09164562076330185,
|
| 2491 |
+
"learning_rate": 8.762886597938145e-05,
|
| 2492 |
+
"loss": 0.0436,
|
| 2493 |
+
"step": 340
|
| 2494 |
+
},
|
| 2495 |
+
{
|
| 2496 |
+
"epoch": 2.2,
|
| 2497 |
+
"grad_norm": 0.10741306096315384,
|
| 2498 |
+
"learning_rate": 8.788659793814433e-05,
|
| 2499 |
+
"loss": 0.0463,
|
| 2500 |
+
"step": 341
|
| 2501 |
+
},
|
| 2502 |
+
{
|
| 2503 |
+
"epoch": 2.206451612903226,
|
| 2504 |
+
"grad_norm": 0.09051238000392914,
|
| 2505 |
+
"learning_rate": 8.814432989690722e-05,
|
| 2506 |
+
"loss": 0.043,
|
| 2507 |
+
"step": 342
|
| 2508 |
+
},
|
| 2509 |
+
{
|
| 2510 |
+
"epoch": 2.2129032258064516,
|
| 2511 |
+
"grad_norm": 0.07722020149230957,
|
| 2512 |
+
"learning_rate": 8.840206185567011e-05,
|
| 2513 |
+
"loss": 0.0354,
|
| 2514 |
+
"step": 343
|
| 2515 |
+
},
|
| 2516 |
+
{
|
| 2517 |
+
"epoch": 2.2193548387096773,
|
| 2518 |
+
"grad_norm": 0.08493324369192123,
|
| 2519 |
+
"learning_rate": 8.865979381443299e-05,
|
| 2520 |
+
"loss": 0.0525,
|
| 2521 |
+
"step": 344
|
| 2522 |
+
},
|
| 2523 |
+
{
|
| 2524 |
+
"epoch": 2.225806451612903,
|
| 2525 |
+
"grad_norm": 0.09371798485517502,
|
| 2526 |
+
"learning_rate": 8.891752577319587e-05,
|
| 2527 |
+
"loss": 0.0424,
|
| 2528 |
+
"step": 345
|
| 2529 |
+
},
|
| 2530 |
+
{
|
| 2531 |
+
"epoch": 2.232258064516129,
|
| 2532 |
+
"grad_norm": 0.10090696066617966,
|
| 2533 |
+
"learning_rate": 8.917525773195877e-05,
|
| 2534 |
+
"loss": 0.0469,
|
| 2535 |
+
"step": 346
|
| 2536 |
+
},
|
| 2537 |
+
{
|
| 2538 |
+
"epoch": 2.238709677419355,
|
| 2539 |
+
"grad_norm": 0.08301045000553131,
|
| 2540 |
+
"learning_rate": 8.943298969072166e-05,
|
| 2541 |
+
"loss": 0.0404,
|
| 2542 |
+
"step": 347
|
| 2543 |
+
},
|
| 2544 |
+
{
|
| 2545 |
+
"epoch": 2.2451612903225806,
|
| 2546 |
+
"grad_norm": 0.0968640148639679,
|
| 2547 |
+
"learning_rate": 8.969072164948454e-05,
|
| 2548 |
+
"loss": 0.0534,
|
| 2549 |
+
"step": 348
|
| 2550 |
+
},
|
| 2551 |
+
{
|
| 2552 |
+
"epoch": 2.2516129032258063,
|
| 2553 |
+
"grad_norm": 0.10685165971517563,
|
| 2554 |
+
"learning_rate": 8.994845360824743e-05,
|
| 2555 |
+
"loss": 0.0391,
|
| 2556 |
+
"step": 349
|
| 2557 |
+
},
|
| 2558 |
+
{
|
| 2559 |
+
"epoch": 2.258064516129032,
|
| 2560 |
+
"grad_norm": 0.09006287902593613,
|
| 2561 |
+
"learning_rate": 9.020618556701031e-05,
|
| 2562 |
+
"loss": 0.0438,
|
| 2563 |
+
"step": 350
|
| 2564 |
+
},
|
| 2565 |
+
{
|
| 2566 |
+
"epoch": 2.258064516129032,
|
| 2567 |
+
"eval_loss": 0.05031716451048851,
|
| 2568 |
+
"eval_runtime": 20.609,
|
| 2569 |
+
"eval_samples_per_second": 4.852,
|
| 2570 |
+
"eval_steps_per_second": 0.097,
|
| 2571 |
+
"step": 350
|
| 2572 |
+
},
|
| 2573 |
+
{
|
| 2574 |
+
"epoch": 2.264516129032258,
|
| 2575 |
+
"grad_norm": 0.10811453312635422,
|
| 2576 |
+
"learning_rate": 9.04639175257732e-05,
|
| 2577 |
+
"loss": 0.0488,
|
| 2578 |
+
"step": 351
|
| 2579 |
+
},
|
| 2580 |
+
{
|
| 2581 |
+
"epoch": 2.270967741935484,
|
| 2582 |
+
"grad_norm": 0.10823424160480499,
|
| 2583 |
+
"learning_rate": 9.072164948453609e-05,
|
| 2584 |
+
"loss": 0.0456,
|
| 2585 |
+
"step": 352
|
| 2586 |
+
},
|
| 2587 |
+
{
|
| 2588 |
+
"epoch": 2.2774193548387096,
|
| 2589 |
+
"grad_norm": 0.08600781857967377,
|
| 2590 |
+
"learning_rate": 9.097938144329897e-05,
|
| 2591 |
+
"loss": 0.0398,
|
| 2592 |
+
"step": 353
|
| 2593 |
+
},
|
| 2594 |
+
{
|
| 2595 |
+
"epoch": 2.2838709677419353,
|
| 2596 |
+
"grad_norm": 0.10172222554683685,
|
| 2597 |
+
"learning_rate": 9.123711340206186e-05,
|
| 2598 |
+
"loss": 0.0427,
|
| 2599 |
+
"step": 354
|
| 2600 |
+
},
|
| 2601 |
+
{
|
| 2602 |
+
"epoch": 2.2903225806451615,
|
| 2603 |
+
"grad_norm": 0.09986208379268646,
|
| 2604 |
+
"learning_rate": 9.149484536082475e-05,
|
| 2605 |
+
"loss": 0.0387,
|
| 2606 |
+
"step": 355
|
| 2607 |
+
},
|
| 2608 |
+
{
|
| 2609 |
+
"epoch": 2.296774193548387,
|
| 2610 |
+
"grad_norm": 0.10122333467006683,
|
| 2611 |
+
"learning_rate": 9.175257731958763e-05,
|
| 2612 |
+
"loss": 0.0442,
|
| 2613 |
+
"step": 356
|
| 2614 |
+
},
|
| 2615 |
+
{
|
| 2616 |
+
"epoch": 2.303225806451613,
|
| 2617 |
+
"grad_norm": 0.09510695189237595,
|
| 2618 |
+
"learning_rate": 9.201030927835051e-05,
|
| 2619 |
+
"loss": 0.0447,
|
| 2620 |
+
"step": 357
|
| 2621 |
+
},
|
| 2622 |
+
{
|
| 2623 |
+
"epoch": 2.3096774193548386,
|
| 2624 |
+
"grad_norm": 0.09774709492921829,
|
| 2625 |
+
"learning_rate": 9.22680412371134e-05,
|
| 2626 |
+
"loss": 0.0344,
|
| 2627 |
+
"step": 358
|
| 2628 |
+
},
|
| 2629 |
+
{
|
| 2630 |
+
"epoch": 2.3161290322580643,
|
| 2631 |
+
"grad_norm": 0.0921277180314064,
|
| 2632 |
+
"learning_rate": 9.25257731958763e-05,
|
| 2633 |
+
"loss": 0.0411,
|
| 2634 |
+
"step": 359
|
| 2635 |
+
},
|
| 2636 |
+
{
|
| 2637 |
+
"epoch": 2.3225806451612905,
|
| 2638 |
+
"grad_norm": 0.10613450407981873,
|
| 2639 |
+
"learning_rate": 9.278350515463918e-05,
|
| 2640 |
+
"loss": 0.0443,
|
| 2641 |
+
"step": 360
|
| 2642 |
+
},
|
| 2643 |
+
{
|
| 2644 |
+
"epoch": 2.329032258064516,
|
| 2645 |
+
"grad_norm": 0.10701876133680344,
|
| 2646 |
+
"learning_rate": 9.304123711340207e-05,
|
| 2647 |
+
"loss": 0.039,
|
| 2648 |
+
"step": 361
|
| 2649 |
+
},
|
| 2650 |
+
{
|
| 2651 |
+
"epoch": 2.335483870967742,
|
| 2652 |
+
"grad_norm": 0.09017759561538696,
|
| 2653 |
+
"learning_rate": 9.329896907216495e-05,
|
| 2654 |
+
"loss": 0.0369,
|
| 2655 |
+
"step": 362
|
| 2656 |
+
},
|
| 2657 |
+
{
|
| 2658 |
+
"epoch": 2.3419354838709676,
|
| 2659 |
+
"grad_norm": 0.10165076702833176,
|
| 2660 |
+
"learning_rate": 9.355670103092784e-05,
|
| 2661 |
+
"loss": 0.041,
|
| 2662 |
+
"step": 363
|
| 2663 |
+
},
|
| 2664 |
+
{
|
| 2665 |
+
"epoch": 2.3483870967741938,
|
| 2666 |
+
"grad_norm": 0.09364940971136093,
|
| 2667 |
+
"learning_rate": 9.381443298969073e-05,
|
| 2668 |
+
"loss": 0.0463,
|
| 2669 |
+
"step": 364
|
| 2670 |
+
},
|
| 2671 |
+
{
|
| 2672 |
+
"epoch": 2.3548387096774195,
|
| 2673 |
+
"grad_norm": 0.08863069862127304,
|
| 2674 |
+
"learning_rate": 9.407216494845361e-05,
|
| 2675 |
+
"loss": 0.0363,
|
| 2676 |
+
"step": 365
|
| 2677 |
+
},
|
| 2678 |
+
{
|
| 2679 |
+
"epoch": 2.361290322580645,
|
| 2680 |
+
"grad_norm": 0.10201136022806168,
|
| 2681 |
+
"learning_rate": 9.43298969072165e-05,
|
| 2682 |
+
"loss": 0.0384,
|
| 2683 |
+
"step": 366
|
| 2684 |
+
},
|
| 2685 |
+
{
|
| 2686 |
+
"epoch": 2.367741935483871,
|
| 2687 |
+
"grad_norm": 0.09771512448787689,
|
| 2688 |
+
"learning_rate": 9.458762886597939e-05,
|
| 2689 |
+
"loss": 0.0386,
|
| 2690 |
+
"step": 367
|
| 2691 |
+
},
|
| 2692 |
+
{
|
| 2693 |
+
"epoch": 2.3741935483870966,
|
| 2694 |
+
"grad_norm": 0.09068713337182999,
|
| 2695 |
+
"learning_rate": 9.484536082474227e-05,
|
| 2696 |
+
"loss": 0.0389,
|
| 2697 |
+
"step": 368
|
| 2698 |
+
},
|
| 2699 |
+
{
|
| 2700 |
+
"epoch": 2.3806451612903228,
|
| 2701 |
+
"grad_norm": 0.10729826241731644,
|
| 2702 |
+
"learning_rate": 9.510309278350515e-05,
|
| 2703 |
+
"loss": 0.0419,
|
| 2704 |
+
"step": 369
|
| 2705 |
+
},
|
| 2706 |
+
{
|
| 2707 |
+
"epoch": 2.3870967741935485,
|
| 2708 |
+
"grad_norm": 0.10047543793916702,
|
| 2709 |
+
"learning_rate": 9.536082474226805e-05,
|
| 2710 |
+
"loss": 0.046,
|
| 2711 |
+
"step": 370
|
| 2712 |
+
},
|
| 2713 |
+
{
|
| 2714 |
+
"epoch": 2.393548387096774,
|
| 2715 |
+
"grad_norm": 0.08138115704059601,
|
| 2716 |
+
"learning_rate": 9.561855670103094e-05,
|
| 2717 |
+
"loss": 0.03,
|
| 2718 |
+
"step": 371
|
| 2719 |
+
},
|
| 2720 |
+
{
|
| 2721 |
+
"epoch": 2.4,
|
| 2722 |
+
"grad_norm": 0.08465878665447235,
|
| 2723 |
+
"learning_rate": 9.587628865979382e-05,
|
| 2724 |
+
"loss": 0.0383,
|
| 2725 |
+
"step": 372
|
| 2726 |
+
},
|
| 2727 |
+
{
|
| 2728 |
+
"epoch": 2.4064516129032256,
|
| 2729 |
+
"grad_norm": 0.10496239364147186,
|
| 2730 |
+
"learning_rate": 9.61340206185567e-05,
|
| 2731 |
+
"loss": 0.0423,
|
| 2732 |
+
"step": 373
|
| 2733 |
+
},
|
| 2734 |
+
{
|
| 2735 |
+
"epoch": 2.412903225806452,
|
| 2736 |
+
"grad_norm": 0.09935601055622101,
|
| 2737 |
+
"learning_rate": 9.639175257731959e-05,
|
| 2738 |
+
"loss": 0.043,
|
| 2739 |
+
"step": 374
|
| 2740 |
+
},
|
| 2741 |
+
{
|
| 2742 |
+
"epoch": 2.4193548387096775,
|
| 2743 |
+
"grad_norm": 0.0851937010884285,
|
| 2744 |
+
"learning_rate": 9.664948453608248e-05,
|
| 2745 |
+
"loss": 0.0364,
|
| 2746 |
+
"step": 375
|
| 2747 |
+
},
|
| 2748 |
+
{
|
| 2749 |
+
"epoch": 2.4193548387096775,
|
| 2750 |
+
"eval_loss": 0.04934929683804512,
|
| 2751 |
+
"eval_runtime": 20.6137,
|
| 2752 |
+
"eval_samples_per_second": 4.851,
|
| 2753 |
+
"eval_steps_per_second": 0.097,
|
| 2754 |
+
"step": 375
|
| 2755 |
+
},
|
| 2756 |
+
{
|
| 2757 |
+
"epoch": 2.425806451612903,
|
| 2758 |
+
"grad_norm": 0.07887910306453705,
|
| 2759 |
+
"learning_rate": 9.690721649484537e-05,
|
| 2760 |
+
"loss": 0.0307,
|
| 2761 |
+
"step": 376
|
| 2762 |
+
},
|
| 2763 |
+
{
|
| 2764 |
+
"epoch": 2.432258064516129,
|
| 2765 |
+
"grad_norm": 0.10647827386856079,
|
| 2766 |
+
"learning_rate": 9.716494845360825e-05,
|
| 2767 |
+
"loss": 0.0455,
|
| 2768 |
+
"step": 377
|
| 2769 |
+
},
|
| 2770 |
+
{
|
| 2771 |
+
"epoch": 2.4387096774193546,
|
| 2772 |
+
"grad_norm": 0.09436062723398209,
|
| 2773 |
+
"learning_rate": 9.742268041237114e-05,
|
| 2774 |
+
"loss": 0.0476,
|
| 2775 |
+
"step": 378
|
| 2776 |
+
},
|
| 2777 |
+
{
|
| 2778 |
+
"epoch": 2.445161290322581,
|
| 2779 |
+
"grad_norm": 0.10967639833688736,
|
| 2780 |
+
"learning_rate": 9.768041237113403e-05,
|
| 2781 |
+
"loss": 0.0368,
|
| 2782 |
+
"step": 379
|
| 2783 |
+
},
|
| 2784 |
+
{
|
| 2785 |
+
"epoch": 2.4516129032258065,
|
| 2786 |
+
"grad_norm": 0.0899633839726448,
|
| 2787 |
+
"learning_rate": 9.793814432989691e-05,
|
| 2788 |
+
"loss": 0.0291,
|
| 2789 |
+
"step": 380
|
| 2790 |
+
},
|
| 2791 |
+
{
|
| 2792 |
+
"epoch": 2.458064516129032,
|
| 2793 |
+
"grad_norm": 0.10881899297237396,
|
| 2794 |
+
"learning_rate": 9.819587628865979e-05,
|
| 2795 |
+
"loss": 0.0452,
|
| 2796 |
+
"step": 381
|
| 2797 |
+
},
|
| 2798 |
+
{
|
| 2799 |
+
"epoch": 2.464516129032258,
|
| 2800 |
+
"grad_norm": 0.09735005348920822,
|
| 2801 |
+
"learning_rate": 9.845360824742269e-05,
|
| 2802 |
+
"loss": 0.0329,
|
| 2803 |
+
"step": 382
|
| 2804 |
+
},
|
| 2805 |
+
{
|
| 2806 |
+
"epoch": 2.4709677419354836,
|
| 2807 |
+
"grad_norm": 0.10843765735626221,
|
| 2808 |
+
"learning_rate": 9.871134020618558e-05,
|
| 2809 |
+
"loss": 0.0379,
|
| 2810 |
+
"step": 383
|
| 2811 |
+
},
|
| 2812 |
+
{
|
| 2813 |
+
"epoch": 2.47741935483871,
|
| 2814 |
+
"grad_norm": 0.09915640950202942,
|
| 2815 |
+
"learning_rate": 9.896907216494846e-05,
|
| 2816 |
+
"loss": 0.0416,
|
| 2817 |
+
"step": 384
|
| 2818 |
+
},
|
| 2819 |
+
{
|
| 2820 |
+
"epoch": 2.4838709677419355,
|
| 2821 |
+
"grad_norm": 0.08816944807767868,
|
| 2822 |
+
"learning_rate": 9.922680412371134e-05,
|
| 2823 |
+
"loss": 0.035,
|
| 2824 |
+
"step": 385
|
| 2825 |
+
},
|
| 2826 |
+
{
|
| 2827 |
+
"epoch": 2.490322580645161,
|
| 2828 |
+
"grad_norm": 0.08104445785284042,
|
| 2829 |
+
"learning_rate": 9.948453608247423e-05,
|
| 2830 |
+
"loss": 0.0356,
|
| 2831 |
+
"step": 386
|
| 2832 |
+
},
|
| 2833 |
+
{
|
| 2834 |
+
"epoch": 2.496774193548387,
|
| 2835 |
+
"grad_norm": 0.10272940993309021,
|
| 2836 |
+
"learning_rate": 9.974226804123712e-05,
|
| 2837 |
+
"loss": 0.0404,
|
| 2838 |
+
"step": 387
|
| 2839 |
+
},
|
| 2840 |
+
{
|
| 2841 |
+
"epoch": 2.5032258064516126,
|
| 2842 |
+
"grad_norm": 0.08973879367113113,
|
| 2843 |
+
"learning_rate": 0.0001,
|
| 2844 |
+
"loss": 0.0305,
|
| 2845 |
+
"step": 388
|
| 2846 |
+
},
|
| 2847 |
+
{
|
| 2848 |
+
"epoch": 2.509677419354839,
|
| 2849 |
+
"grad_norm": 0.1103263571858406,
|
| 2850 |
+
"learning_rate": 9.999997970748714e-05,
|
| 2851 |
+
"loss": 0.0459,
|
| 2852 |
+
"step": 389
|
| 2853 |
+
},
|
| 2854 |
+
{
|
| 2855 |
+
"epoch": 2.5161290322580645,
|
| 2856 |
+
"grad_norm": 0.09237506985664368,
|
| 2857 |
+
"learning_rate": 9.999991882996502e-05,
|
| 2858 |
+
"loss": 0.0363,
|
| 2859 |
+
"step": 390
|
| 2860 |
+
},
|
| 2861 |
+
{
|
| 2862 |
+
"epoch": 2.52258064516129,
|
| 2863 |
+
"grad_norm": 0.08599911630153656,
|
| 2864 |
+
"learning_rate": 9.999981736748307e-05,
|
| 2865 |
+
"loss": 0.0377,
|
| 2866 |
+
"step": 391
|
| 2867 |
+
},
|
| 2868 |
+
{
|
| 2869 |
+
"epoch": 2.5290322580645164,
|
| 2870 |
+
"grad_norm": 0.08956660330295563,
|
| 2871 |
+
"learning_rate": 9.999967532012362e-05,
|
| 2872 |
+
"loss": 0.0355,
|
| 2873 |
+
"step": 392
|
| 2874 |
+
},
|
| 2875 |
+
{
|
| 2876 |
+
"epoch": 2.535483870967742,
|
| 2877 |
+
"grad_norm": 0.08925971388816833,
|
| 2878 |
+
"learning_rate": 9.9999492688002e-05,
|
| 2879 |
+
"loss": 0.038,
|
| 2880 |
+
"step": 393
|
| 2881 |
+
},
|
| 2882 |
+
{
|
| 2883 |
+
"epoch": 2.541935483870968,
|
| 2884 |
+
"grad_norm": 0.08915024995803833,
|
| 2885 |
+
"learning_rate": 9.999926947126643e-05,
|
| 2886 |
+
"loss": 0.0376,
|
| 2887 |
+
"step": 394
|
| 2888 |
+
},
|
| 2889 |
+
{
|
| 2890 |
+
"epoch": 2.5483870967741935,
|
| 2891 |
+
"grad_norm": 0.09460075944662094,
|
| 2892 |
+
"learning_rate": 9.999900567009811e-05,
|
| 2893 |
+
"loss": 0.0367,
|
| 2894 |
+
"step": 395
|
| 2895 |
+
},
|
| 2896 |
+
{
|
| 2897 |
+
"epoch": 2.554838709677419,
|
| 2898 |
+
"grad_norm": 0.0868026539683342,
|
| 2899 |
+
"learning_rate": 9.999870128471116e-05,
|
| 2900 |
+
"loss": 0.0356,
|
| 2901 |
+
"step": 396
|
| 2902 |
+
},
|
| 2903 |
+
{
|
| 2904 |
+
"epoch": 2.5612903225806454,
|
| 2905 |
+
"grad_norm": 0.09221860021352768,
|
| 2906 |
+
"learning_rate": 9.999835631535266e-05,
|
| 2907 |
+
"loss": 0.0441,
|
| 2908 |
+
"step": 397
|
| 2909 |
+
},
|
| 2910 |
+
{
|
| 2911 |
+
"epoch": 2.567741935483871,
|
| 2912 |
+
"grad_norm": 0.1023736447095871,
|
| 2913 |
+
"learning_rate": 9.99979707623026e-05,
|
| 2914 |
+
"loss": 0.0451,
|
| 2915 |
+
"step": 398
|
| 2916 |
+
},
|
| 2917 |
+
{
|
| 2918 |
+
"epoch": 2.574193548387097,
|
| 2919 |
+
"grad_norm": 0.08648494631052017,
|
| 2920 |
+
"learning_rate": 9.999754462587395e-05,
|
| 2921 |
+
"loss": 0.0375,
|
| 2922 |
+
"step": 399
|
| 2923 |
+
},
|
| 2924 |
+
{
|
| 2925 |
+
"epoch": 2.5806451612903225,
|
| 2926 |
+
"grad_norm": 0.08478187024593353,
|
| 2927 |
+
"learning_rate": 9.99970779064126e-05,
|
| 2928 |
+
"loss": 0.0365,
|
| 2929 |
+
"step": 400
|
| 2930 |
+
},
|
| 2931 |
+
{
|
| 2932 |
+
"epoch": 2.5806451612903225,
|
| 2933 |
+
"eval_loss": 0.046045903116464615,
|
| 2934 |
+
"eval_runtime": 20.63,
|
| 2935 |
+
"eval_samples_per_second": 4.847,
|
| 2936 |
+
"eval_steps_per_second": 0.097,
|
| 2937 |
+
"step": 400
|
| 2938 |
+
}
|
| 2939 |
+
],
|
| 2940 |
+
"logging_steps": 1,
|
| 2941 |
+
"max_steps": 3875,
|
| 2942 |
+
"num_input_tokens_seen": 0,
|
| 2943 |
+
"num_train_epochs": 25,
|
| 2944 |
+
"save_steps": 100,
|
| 2945 |
+
"stateful_callbacks": {
|
| 2946 |
+
"EarlyStoppingCallback": {
|
| 2947 |
+
"args": {
|
| 2948 |
+
"early_stopping_patience": 5,
|
| 2949 |
+
"early_stopping_threshold": 0.0
|
| 2950 |
+
},
|
| 2951 |
+
"attributes": {
|
| 2952 |
+
"early_stopping_patience_counter": 0
|
| 2953 |
+
}
|
| 2954 |
+
},
|
| 2955 |
+
"TrainerControl": {
|
| 2956 |
+
"args": {
|
| 2957 |
+
"should_epoch_stop": false,
|
| 2958 |
+
"should_evaluate": false,
|
| 2959 |
+
"should_log": false,
|
| 2960 |
+
"should_save": true,
|
| 2961 |
+
"should_training_stop": false
|
| 2962 |
+
},
|
| 2963 |
+
"attributes": {}
|
| 2964 |
+
}
|
| 2965 |
+
},
|
| 2966 |
+
"total_flos": 2.0150004422069453e+18,
|
| 2967 |
+
"train_batch_size": 64,
|
| 2968 |
+
"trial_name": null,
|
| 2969 |
+
"trial_params": null
|
| 2970 |
+
}
|
checkpoint-400/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:796918ce9b3604fd3e7d43822e561dbfe1830533da791f9a30c6e44202f010e0
|
| 3 |
+
size 5432
|
trainer_log.jsonl
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|