Upload 11 files
Browse files- README.md +202 -0
- adapter_config.json +34 -0
- adapter_model.safetensors +3 -0
- optimizer.pt +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +23 -0
- tokenizer.json +0 -0
- tokenizer_config.json +2064 -0
- trainer_state.json +2313 -0
- training_args.bin +3 -0
README.md
ADDED
|
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: Delta-Vector/Control-8B
|
| 3 |
+
library_name: peft
|
| 4 |
+
---
|
| 5 |
+
|
| 6 |
+
# Model Card for Model ID
|
| 7 |
+
|
| 8 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
| 9 |
+
|
| 10 |
+
|
| 11 |
+
|
| 12 |
+
## Model Details
|
| 13 |
+
|
| 14 |
+
### Model Description
|
| 15 |
+
|
| 16 |
+
<!-- Provide a longer summary of what this model is. -->
|
| 17 |
+
|
| 18 |
+
|
| 19 |
+
|
| 20 |
+
- **Developed by:** [More Information Needed]
|
| 21 |
+
- **Funded by [optional]:** [More Information Needed]
|
| 22 |
+
- **Shared by [optional]:** [More Information Needed]
|
| 23 |
+
- **Model type:** [More Information Needed]
|
| 24 |
+
- **Language(s) (NLP):** [More Information Needed]
|
| 25 |
+
- **License:** [More Information Needed]
|
| 26 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
| 27 |
+
|
| 28 |
+
### Model Sources [optional]
|
| 29 |
+
|
| 30 |
+
<!-- Provide the basic links for the model. -->
|
| 31 |
+
|
| 32 |
+
- **Repository:** [More Information Needed]
|
| 33 |
+
- **Paper [optional]:** [More Information Needed]
|
| 34 |
+
- **Demo [optional]:** [More Information Needed]
|
| 35 |
+
|
| 36 |
+
## Uses
|
| 37 |
+
|
| 38 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
| 39 |
+
|
| 40 |
+
### Direct Use
|
| 41 |
+
|
| 42 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
| 43 |
+
|
| 44 |
+
[More Information Needed]
|
| 45 |
+
|
| 46 |
+
### Downstream Use [optional]
|
| 47 |
+
|
| 48 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
| 49 |
+
|
| 50 |
+
[More Information Needed]
|
| 51 |
+
|
| 52 |
+
### Out-of-Scope Use
|
| 53 |
+
|
| 54 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
| 55 |
+
|
| 56 |
+
[More Information Needed]
|
| 57 |
+
|
| 58 |
+
## Bias, Risks, and Limitations
|
| 59 |
+
|
| 60 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
| 61 |
+
|
| 62 |
+
[More Information Needed]
|
| 63 |
+
|
| 64 |
+
### Recommendations
|
| 65 |
+
|
| 66 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
| 67 |
+
|
| 68 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
| 69 |
+
|
| 70 |
+
## How to Get Started with the Model
|
| 71 |
+
|
| 72 |
+
Use the code below to get started with the model.
|
| 73 |
+
|
| 74 |
+
[More Information Needed]
|
| 75 |
+
|
| 76 |
+
## Training Details
|
| 77 |
+
|
| 78 |
+
### Training Data
|
| 79 |
+
|
| 80 |
+
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
| 81 |
+
|
| 82 |
+
[More Information Needed]
|
| 83 |
+
|
| 84 |
+
### Training Procedure
|
| 85 |
+
|
| 86 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
| 87 |
+
|
| 88 |
+
#### Preprocessing [optional]
|
| 89 |
+
|
| 90 |
+
[More Information Needed]
|
| 91 |
+
|
| 92 |
+
|
| 93 |
+
#### Training Hyperparameters
|
| 94 |
+
|
| 95 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
| 96 |
+
|
| 97 |
+
#### Speeds, Sizes, Times [optional]
|
| 98 |
+
|
| 99 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
| 100 |
+
|
| 101 |
+
[More Information Needed]
|
| 102 |
+
|
| 103 |
+
## Evaluation
|
| 104 |
+
|
| 105 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
| 106 |
+
|
| 107 |
+
### Testing Data, Factors & Metrics
|
| 108 |
+
|
| 109 |
+
#### Testing Data
|
| 110 |
+
|
| 111 |
+
<!-- This should link to a Dataset Card if possible. -->
|
| 112 |
+
|
| 113 |
+
[More Information Needed]
|
| 114 |
+
|
| 115 |
+
#### Factors
|
| 116 |
+
|
| 117 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
| 118 |
+
|
| 119 |
+
[More Information Needed]
|
| 120 |
+
|
| 121 |
+
#### Metrics
|
| 122 |
+
|
| 123 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
| 124 |
+
|
| 125 |
+
[More Information Needed]
|
| 126 |
+
|
| 127 |
+
### Results
|
| 128 |
+
|
| 129 |
+
[More Information Needed]
|
| 130 |
+
|
| 131 |
+
#### Summary
|
| 132 |
+
|
| 133 |
+
|
| 134 |
+
|
| 135 |
+
## Model Examination [optional]
|
| 136 |
+
|
| 137 |
+
<!-- Relevant interpretability work for the model goes here -->
|
| 138 |
+
|
| 139 |
+
[More Information Needed]
|
| 140 |
+
|
| 141 |
+
## Environmental Impact
|
| 142 |
+
|
| 143 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
| 144 |
+
|
| 145 |
+
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
| 146 |
+
|
| 147 |
+
- **Hardware Type:** [More Information Needed]
|
| 148 |
+
- **Hours used:** [More Information Needed]
|
| 149 |
+
- **Cloud Provider:** [More Information Needed]
|
| 150 |
+
- **Compute Region:** [More Information Needed]
|
| 151 |
+
- **Carbon Emitted:** [More Information Needed]
|
| 152 |
+
|
| 153 |
+
## Technical Specifications [optional]
|
| 154 |
+
|
| 155 |
+
### Model Architecture and Objective
|
| 156 |
+
|
| 157 |
+
[More Information Needed]
|
| 158 |
+
|
| 159 |
+
### Compute Infrastructure
|
| 160 |
+
|
| 161 |
+
[More Information Needed]
|
| 162 |
+
|
| 163 |
+
#### Hardware
|
| 164 |
+
|
| 165 |
+
[More Information Needed]
|
| 166 |
+
|
| 167 |
+
#### Software
|
| 168 |
+
|
| 169 |
+
[More Information Needed]
|
| 170 |
+
|
| 171 |
+
## Citation [optional]
|
| 172 |
+
|
| 173 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
| 174 |
+
|
| 175 |
+
**BibTeX:**
|
| 176 |
+
|
| 177 |
+
[More Information Needed]
|
| 178 |
+
|
| 179 |
+
**APA:**
|
| 180 |
+
|
| 181 |
+
[More Information Needed]
|
| 182 |
+
|
| 183 |
+
## Glossary [optional]
|
| 184 |
+
|
| 185 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
| 186 |
+
|
| 187 |
+
[More Information Needed]
|
| 188 |
+
|
| 189 |
+
## More Information [optional]
|
| 190 |
+
|
| 191 |
+
[More Information Needed]
|
| 192 |
+
|
| 193 |
+
## Model Card Authors [optional]
|
| 194 |
+
|
| 195 |
+
[More Information Needed]
|
| 196 |
+
|
| 197 |
+
## Model Card Contact
|
| 198 |
+
|
| 199 |
+
[More Information Needed]
|
| 200 |
+
### Framework versions
|
| 201 |
+
|
| 202 |
+
- PEFT 0.13.2
|
adapter_config.json
ADDED
|
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "Delta-Vector/Control-8B",
|
| 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": 64,
|
| 14 |
+
"lora_dropout": 0,
|
| 15 |
+
"megatron_config": null,
|
| 16 |
+
"megatron_core": "megatron.core",
|
| 17 |
+
"modules_to_save": null,
|
| 18 |
+
"peft_type": "LORA",
|
| 19 |
+
"r": 64,
|
| 20 |
+
"rank_pattern": {},
|
| 21 |
+
"revision": null,
|
| 22 |
+
"target_modules": [
|
| 23 |
+
"down_proj",
|
| 24 |
+
"o_proj",
|
| 25 |
+
"up_proj",
|
| 26 |
+
"gate_proj",
|
| 27 |
+
"k_proj",
|
| 28 |
+
"v_proj",
|
| 29 |
+
"q_proj"
|
| 30 |
+
],
|
| 31 |
+
"task_type": "CAUSAL_LM",
|
| 32 |
+
"use_dora": false,
|
| 33 |
+
"use_rslora": true
|
| 34 |
+
}
|
adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d5cfe3747d9c980787a8c79190a32cf9ed558f581ef96e144337156073ee2647
|
| 3 |
+
size 671149168
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:58286acca5773d2e7c51dcafc8a86ba940537a8742f2c627cd1d1832a78bd8a2
|
| 3 |
+
size 341314196
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1ff264f99d31b522cc7e2a4eac9d38606d0c58a34c0adc74d71e0ca8b371dc36
|
| 3 |
+
size 14244
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:de40ffc0bbc293cc5e26c89be2c2b14865af66d168dc4b4b3ada76d003c13718
|
| 3 |
+
size 1064
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<|begin_of_text|>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "<|eot_id|>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": {
|
| 17 |
+
"content": "<|finetune_right_pad_id|>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
}
|
| 23 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,2064 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"128000": {
|
| 4 |
+
"content": "<|begin_of_text|>",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"128001": {
|
| 12 |
+
"content": "<|end_of_text|>",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"128002": {
|
| 20 |
+
"content": "<|reserved_special_token_0|>",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"128003": {
|
| 28 |
+
"content": "<|reserved_special_token_1|>",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"128004": {
|
| 36 |
+
"content": "<|finetune_right_pad_id|>",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
},
|
| 43 |
+
"128005": {
|
| 44 |
+
"content": "<|reserved_special_token_2|>",
|
| 45 |
+
"lstrip": false,
|
| 46 |
+
"normalized": false,
|
| 47 |
+
"rstrip": false,
|
| 48 |
+
"single_word": false,
|
| 49 |
+
"special": true
|
| 50 |
+
},
|
| 51 |
+
"128006": {
|
| 52 |
+
"content": "<|start_header_id|>",
|
| 53 |
+
"lstrip": false,
|
| 54 |
+
"normalized": false,
|
| 55 |
+
"rstrip": false,
|
| 56 |
+
"single_word": false,
|
| 57 |
+
"special": true
|
| 58 |
+
},
|
| 59 |
+
"128007": {
|
| 60 |
+
"content": "<|end_header_id|>",
|
| 61 |
+
"lstrip": false,
|
| 62 |
+
"normalized": false,
|
| 63 |
+
"rstrip": false,
|
| 64 |
+
"single_word": false,
|
| 65 |
+
"special": true
|
| 66 |
+
},
|
| 67 |
+
"128008": {
|
| 68 |
+
"content": "<|eom_id|>",
|
| 69 |
+
"lstrip": false,
|
| 70 |
+
"normalized": false,
|
| 71 |
+
"rstrip": false,
|
| 72 |
+
"single_word": false,
|
| 73 |
+
"special": true
|
| 74 |
+
},
|
| 75 |
+
"128009": {
|
| 76 |
+
"content": "<|eot_id|>",
|
| 77 |
+
"lstrip": false,
|
| 78 |
+
"normalized": false,
|
| 79 |
+
"rstrip": false,
|
| 80 |
+
"single_word": false,
|
| 81 |
+
"special": true
|
| 82 |
+
},
|
| 83 |
+
"128010": {
|
| 84 |
+
"content": "<|python_tag|>",
|
| 85 |
+
"lstrip": false,
|
| 86 |
+
"normalized": false,
|
| 87 |
+
"rstrip": false,
|
| 88 |
+
"single_word": false,
|
| 89 |
+
"special": true
|
| 90 |
+
},
|
| 91 |
+
"128011": {
|
| 92 |
+
"content": "<|reserved_special_token_3|>",
|
| 93 |
+
"lstrip": false,
|
| 94 |
+
"normalized": false,
|
| 95 |
+
"rstrip": false,
|
| 96 |
+
"single_word": false,
|
| 97 |
+
"special": true
|
| 98 |
+
},
|
| 99 |
+
"128012": {
|
| 100 |
+
"content": "<|reserved_special_token_4|>",
|
| 101 |
+
"lstrip": false,
|
| 102 |
+
"normalized": false,
|
| 103 |
+
"rstrip": false,
|
| 104 |
+
"single_word": false,
|
| 105 |
+
"special": true
|
| 106 |
+
},
|
| 107 |
+
"128013": {
|
| 108 |
+
"content": "<|reserved_special_token_5|>",
|
| 109 |
+
"lstrip": false,
|
| 110 |
+
"normalized": false,
|
| 111 |
+
"rstrip": false,
|
| 112 |
+
"single_word": false,
|
| 113 |
+
"special": true
|
| 114 |
+
},
|
| 115 |
+
"128014": {
|
| 116 |
+
"content": "<|reserved_special_token_6|>",
|
| 117 |
+
"lstrip": false,
|
| 118 |
+
"normalized": false,
|
| 119 |
+
"rstrip": false,
|
| 120 |
+
"single_word": false,
|
| 121 |
+
"special": true
|
| 122 |
+
},
|
| 123 |
+
"128015": {
|
| 124 |
+
"content": "<|reserved_special_token_7|>",
|
| 125 |
+
"lstrip": false,
|
| 126 |
+
"normalized": false,
|
| 127 |
+
"rstrip": false,
|
| 128 |
+
"single_word": false,
|
| 129 |
+
"special": true
|
| 130 |
+
},
|
| 131 |
+
"128016": {
|
| 132 |
+
"content": "<|reserved_special_token_8|>",
|
| 133 |
+
"lstrip": false,
|
| 134 |
+
"normalized": false,
|
| 135 |
+
"rstrip": false,
|
| 136 |
+
"single_word": false,
|
| 137 |
+
"special": true
|
| 138 |
+
},
|
| 139 |
+
"128017": {
|
| 140 |
+
"content": "<|reserved_special_token_9|>",
|
| 141 |
+
"lstrip": false,
|
| 142 |
+
"normalized": false,
|
| 143 |
+
"rstrip": false,
|
| 144 |
+
"single_word": false,
|
| 145 |
+
"special": true
|
| 146 |
+
},
|
| 147 |
+
"128018": {
|
| 148 |
+
"content": "<|reserved_special_token_10|>",
|
| 149 |
+
"lstrip": false,
|
| 150 |
+
"normalized": false,
|
| 151 |
+
"rstrip": false,
|
| 152 |
+
"single_word": false,
|
| 153 |
+
"special": true
|
| 154 |
+
},
|
| 155 |
+
"128019": {
|
| 156 |
+
"content": "<|reserved_special_token_11|>",
|
| 157 |
+
"lstrip": false,
|
| 158 |
+
"normalized": false,
|
| 159 |
+
"rstrip": false,
|
| 160 |
+
"single_word": false,
|
| 161 |
+
"special": true
|
| 162 |
+
},
|
| 163 |
+
"128020": {
|
| 164 |
+
"content": "<|reserved_special_token_12|>",
|
| 165 |
+
"lstrip": false,
|
| 166 |
+
"normalized": false,
|
| 167 |
+
"rstrip": false,
|
| 168 |
+
"single_word": false,
|
| 169 |
+
"special": true
|
| 170 |
+
},
|
| 171 |
+
"128021": {
|
| 172 |
+
"content": "<|reserved_special_token_13|>",
|
| 173 |
+
"lstrip": false,
|
| 174 |
+
"normalized": false,
|
| 175 |
+
"rstrip": false,
|
| 176 |
+
"single_word": false,
|
| 177 |
+
"special": true
|
| 178 |
+
},
|
| 179 |
+
"128022": {
|
| 180 |
+
"content": "<|reserved_special_token_14|>",
|
| 181 |
+
"lstrip": false,
|
| 182 |
+
"normalized": false,
|
| 183 |
+
"rstrip": false,
|
| 184 |
+
"single_word": false,
|
| 185 |
+
"special": true
|
| 186 |
+
},
|
| 187 |
+
"128023": {
|
| 188 |
+
"content": "<|reserved_special_token_15|>",
|
| 189 |
+
"lstrip": false,
|
| 190 |
+
"normalized": false,
|
| 191 |
+
"rstrip": false,
|
| 192 |
+
"single_word": false,
|
| 193 |
+
"special": true
|
| 194 |
+
},
|
| 195 |
+
"128024": {
|
| 196 |
+
"content": "<|reserved_special_token_16|>",
|
| 197 |
+
"lstrip": false,
|
| 198 |
+
"normalized": false,
|
| 199 |
+
"rstrip": false,
|
| 200 |
+
"single_word": false,
|
| 201 |
+
"special": true
|
| 202 |
+
},
|
| 203 |
+
"128025": {
|
| 204 |
+
"content": "<|reserved_special_token_17|>",
|
| 205 |
+
"lstrip": false,
|
| 206 |
+
"normalized": false,
|
| 207 |
+
"rstrip": false,
|
| 208 |
+
"single_word": false,
|
| 209 |
+
"special": true
|
| 210 |
+
},
|
| 211 |
+
"128026": {
|
| 212 |
+
"content": "<|reserved_special_token_18|>",
|
| 213 |
+
"lstrip": false,
|
| 214 |
+
"normalized": false,
|
| 215 |
+
"rstrip": false,
|
| 216 |
+
"single_word": false,
|
| 217 |
+
"special": true
|
| 218 |
+
},
|
| 219 |
+
"128027": {
|
| 220 |
+
"content": "<|reserved_special_token_19|>",
|
| 221 |
+
"lstrip": false,
|
| 222 |
+
"normalized": false,
|
| 223 |
+
"rstrip": false,
|
| 224 |
+
"single_word": false,
|
| 225 |
+
"special": true
|
| 226 |
+
},
|
| 227 |
+
"128028": {
|
| 228 |
+
"content": "<|reserved_special_token_20|>",
|
| 229 |
+
"lstrip": false,
|
| 230 |
+
"normalized": false,
|
| 231 |
+
"rstrip": false,
|
| 232 |
+
"single_word": false,
|
| 233 |
+
"special": true
|
| 234 |
+
},
|
| 235 |
+
"128029": {
|
| 236 |
+
"content": "<|reserved_special_token_21|>",
|
| 237 |
+
"lstrip": false,
|
| 238 |
+
"normalized": false,
|
| 239 |
+
"rstrip": false,
|
| 240 |
+
"single_word": false,
|
| 241 |
+
"special": true
|
| 242 |
+
},
|
| 243 |
+
"128030": {
|
| 244 |
+
"content": "<|reserved_special_token_22|>",
|
| 245 |
+
"lstrip": false,
|
| 246 |
+
"normalized": false,
|
| 247 |
+
"rstrip": false,
|
| 248 |
+
"single_word": false,
|
| 249 |
+
"special": true
|
| 250 |
+
},
|
| 251 |
+
"128031": {
|
| 252 |
+
"content": "<|reserved_special_token_23|>",
|
| 253 |
+
"lstrip": false,
|
| 254 |
+
"normalized": false,
|
| 255 |
+
"rstrip": false,
|
| 256 |
+
"single_word": false,
|
| 257 |
+
"special": true
|
| 258 |
+
},
|
| 259 |
+
"128032": {
|
| 260 |
+
"content": "<|reserved_special_token_24|>",
|
| 261 |
+
"lstrip": false,
|
| 262 |
+
"normalized": false,
|
| 263 |
+
"rstrip": false,
|
| 264 |
+
"single_word": false,
|
| 265 |
+
"special": true
|
| 266 |
+
},
|
| 267 |
+
"128033": {
|
| 268 |
+
"content": "<|reserved_special_token_25|>",
|
| 269 |
+
"lstrip": false,
|
| 270 |
+
"normalized": false,
|
| 271 |
+
"rstrip": false,
|
| 272 |
+
"single_word": false,
|
| 273 |
+
"special": true
|
| 274 |
+
},
|
| 275 |
+
"128034": {
|
| 276 |
+
"content": "<|reserved_special_token_26|>",
|
| 277 |
+
"lstrip": false,
|
| 278 |
+
"normalized": false,
|
| 279 |
+
"rstrip": false,
|
| 280 |
+
"single_word": false,
|
| 281 |
+
"special": true
|
| 282 |
+
},
|
| 283 |
+
"128035": {
|
| 284 |
+
"content": "<|reserved_special_token_27|>",
|
| 285 |
+
"lstrip": false,
|
| 286 |
+
"normalized": false,
|
| 287 |
+
"rstrip": false,
|
| 288 |
+
"single_word": false,
|
| 289 |
+
"special": true
|
| 290 |
+
},
|
| 291 |
+
"128036": {
|
| 292 |
+
"content": "<|reserved_special_token_28|>",
|
| 293 |
+
"lstrip": false,
|
| 294 |
+
"normalized": false,
|
| 295 |
+
"rstrip": false,
|
| 296 |
+
"single_word": false,
|
| 297 |
+
"special": true
|
| 298 |
+
},
|
| 299 |
+
"128037": {
|
| 300 |
+
"content": "<|reserved_special_token_29|>",
|
| 301 |
+
"lstrip": false,
|
| 302 |
+
"normalized": false,
|
| 303 |
+
"rstrip": false,
|
| 304 |
+
"single_word": false,
|
| 305 |
+
"special": true
|
| 306 |
+
},
|
| 307 |
+
"128038": {
|
| 308 |
+
"content": "<|reserved_special_token_30|>",
|
| 309 |
+
"lstrip": false,
|
| 310 |
+
"normalized": false,
|
| 311 |
+
"rstrip": false,
|
| 312 |
+
"single_word": false,
|
| 313 |
+
"special": true
|
| 314 |
+
},
|
| 315 |
+
"128039": {
|
| 316 |
+
"content": "<|reserved_special_token_31|>",
|
| 317 |
+
"lstrip": false,
|
| 318 |
+
"normalized": false,
|
| 319 |
+
"rstrip": false,
|
| 320 |
+
"single_word": false,
|
| 321 |
+
"special": true
|
| 322 |
+
},
|
| 323 |
+
"128040": {
|
| 324 |
+
"content": "<|reserved_special_token_32|>",
|
| 325 |
+
"lstrip": false,
|
| 326 |
+
"normalized": false,
|
| 327 |
+
"rstrip": false,
|
| 328 |
+
"single_word": false,
|
| 329 |
+
"special": true
|
| 330 |
+
},
|
| 331 |
+
"128041": {
|
| 332 |
+
"content": "<|reserved_special_token_33|>",
|
| 333 |
+
"lstrip": false,
|
| 334 |
+
"normalized": false,
|
| 335 |
+
"rstrip": false,
|
| 336 |
+
"single_word": false,
|
| 337 |
+
"special": true
|
| 338 |
+
},
|
| 339 |
+
"128042": {
|
| 340 |
+
"content": "<|reserved_special_token_34|>",
|
| 341 |
+
"lstrip": false,
|
| 342 |
+
"normalized": false,
|
| 343 |
+
"rstrip": false,
|
| 344 |
+
"single_word": false,
|
| 345 |
+
"special": true
|
| 346 |
+
},
|
| 347 |
+
"128043": {
|
| 348 |
+
"content": "<|reserved_special_token_35|>",
|
| 349 |
+
"lstrip": false,
|
| 350 |
+
"normalized": false,
|
| 351 |
+
"rstrip": false,
|
| 352 |
+
"single_word": false,
|
| 353 |
+
"special": true
|
| 354 |
+
},
|
| 355 |
+
"128044": {
|
| 356 |
+
"content": "<|reserved_special_token_36|>",
|
| 357 |
+
"lstrip": false,
|
| 358 |
+
"normalized": false,
|
| 359 |
+
"rstrip": false,
|
| 360 |
+
"single_word": false,
|
| 361 |
+
"special": true
|
| 362 |
+
},
|
| 363 |
+
"128045": {
|
| 364 |
+
"content": "<|reserved_special_token_37|>",
|
| 365 |
+
"lstrip": false,
|
| 366 |
+
"normalized": false,
|
| 367 |
+
"rstrip": false,
|
| 368 |
+
"single_word": false,
|
| 369 |
+
"special": true
|
| 370 |
+
},
|
| 371 |
+
"128046": {
|
| 372 |
+
"content": "<|reserved_special_token_38|>",
|
| 373 |
+
"lstrip": false,
|
| 374 |
+
"normalized": false,
|
| 375 |
+
"rstrip": false,
|
| 376 |
+
"single_word": false,
|
| 377 |
+
"special": true
|
| 378 |
+
},
|
| 379 |
+
"128047": {
|
| 380 |
+
"content": "<|reserved_special_token_39|>",
|
| 381 |
+
"lstrip": false,
|
| 382 |
+
"normalized": false,
|
| 383 |
+
"rstrip": false,
|
| 384 |
+
"single_word": false,
|
| 385 |
+
"special": true
|
| 386 |
+
},
|
| 387 |
+
"128048": {
|
| 388 |
+
"content": "<|reserved_special_token_40|>",
|
| 389 |
+
"lstrip": false,
|
| 390 |
+
"normalized": false,
|
| 391 |
+
"rstrip": false,
|
| 392 |
+
"single_word": false,
|
| 393 |
+
"special": true
|
| 394 |
+
},
|
| 395 |
+
"128049": {
|
| 396 |
+
"content": "<|reserved_special_token_41|>",
|
| 397 |
+
"lstrip": false,
|
| 398 |
+
"normalized": false,
|
| 399 |
+
"rstrip": false,
|
| 400 |
+
"single_word": false,
|
| 401 |
+
"special": true
|
| 402 |
+
},
|
| 403 |
+
"128050": {
|
| 404 |
+
"content": "<|reserved_special_token_42|>",
|
| 405 |
+
"lstrip": false,
|
| 406 |
+
"normalized": false,
|
| 407 |
+
"rstrip": false,
|
| 408 |
+
"single_word": false,
|
| 409 |
+
"special": true
|
| 410 |
+
},
|
| 411 |
+
"128051": {
|
| 412 |
+
"content": "<|reserved_special_token_43|>",
|
| 413 |
+
"lstrip": false,
|
| 414 |
+
"normalized": false,
|
| 415 |
+
"rstrip": false,
|
| 416 |
+
"single_word": false,
|
| 417 |
+
"special": true
|
| 418 |
+
},
|
| 419 |
+
"128052": {
|
| 420 |
+
"content": "<|reserved_special_token_44|>",
|
| 421 |
+
"lstrip": false,
|
| 422 |
+
"normalized": false,
|
| 423 |
+
"rstrip": false,
|
| 424 |
+
"single_word": false,
|
| 425 |
+
"special": true
|
| 426 |
+
},
|
| 427 |
+
"128053": {
|
| 428 |
+
"content": "<|reserved_special_token_45|>",
|
| 429 |
+
"lstrip": false,
|
| 430 |
+
"normalized": false,
|
| 431 |
+
"rstrip": false,
|
| 432 |
+
"single_word": false,
|
| 433 |
+
"special": true
|
| 434 |
+
},
|
| 435 |
+
"128054": {
|
| 436 |
+
"content": "<|reserved_special_token_46|>",
|
| 437 |
+
"lstrip": false,
|
| 438 |
+
"normalized": false,
|
| 439 |
+
"rstrip": false,
|
| 440 |
+
"single_word": false,
|
| 441 |
+
"special": true
|
| 442 |
+
},
|
| 443 |
+
"128055": {
|
| 444 |
+
"content": "<|reserved_special_token_47|>",
|
| 445 |
+
"lstrip": false,
|
| 446 |
+
"normalized": false,
|
| 447 |
+
"rstrip": false,
|
| 448 |
+
"single_word": false,
|
| 449 |
+
"special": true
|
| 450 |
+
},
|
| 451 |
+
"128056": {
|
| 452 |
+
"content": "<|reserved_special_token_48|>",
|
| 453 |
+
"lstrip": false,
|
| 454 |
+
"normalized": false,
|
| 455 |
+
"rstrip": false,
|
| 456 |
+
"single_word": false,
|
| 457 |
+
"special": true
|
| 458 |
+
},
|
| 459 |
+
"128057": {
|
| 460 |
+
"content": "<|reserved_special_token_49|>",
|
| 461 |
+
"lstrip": false,
|
| 462 |
+
"normalized": false,
|
| 463 |
+
"rstrip": false,
|
| 464 |
+
"single_word": false,
|
| 465 |
+
"special": true
|
| 466 |
+
},
|
| 467 |
+
"128058": {
|
| 468 |
+
"content": "<|reserved_special_token_50|>",
|
| 469 |
+
"lstrip": false,
|
| 470 |
+
"normalized": false,
|
| 471 |
+
"rstrip": false,
|
| 472 |
+
"single_word": false,
|
| 473 |
+
"special": true
|
| 474 |
+
},
|
| 475 |
+
"128059": {
|
| 476 |
+
"content": "<|reserved_special_token_51|>",
|
| 477 |
+
"lstrip": false,
|
| 478 |
+
"normalized": false,
|
| 479 |
+
"rstrip": false,
|
| 480 |
+
"single_word": false,
|
| 481 |
+
"special": true
|
| 482 |
+
},
|
| 483 |
+
"128060": {
|
| 484 |
+
"content": "<|reserved_special_token_52|>",
|
| 485 |
+
"lstrip": false,
|
| 486 |
+
"normalized": false,
|
| 487 |
+
"rstrip": false,
|
| 488 |
+
"single_word": false,
|
| 489 |
+
"special": true
|
| 490 |
+
},
|
| 491 |
+
"128061": {
|
| 492 |
+
"content": "<|reserved_special_token_53|>",
|
| 493 |
+
"lstrip": false,
|
| 494 |
+
"normalized": false,
|
| 495 |
+
"rstrip": false,
|
| 496 |
+
"single_word": false,
|
| 497 |
+
"special": true
|
| 498 |
+
},
|
| 499 |
+
"128062": {
|
| 500 |
+
"content": "<|reserved_special_token_54|>",
|
| 501 |
+
"lstrip": false,
|
| 502 |
+
"normalized": false,
|
| 503 |
+
"rstrip": false,
|
| 504 |
+
"single_word": false,
|
| 505 |
+
"special": true
|
| 506 |
+
},
|
| 507 |
+
"128063": {
|
| 508 |
+
"content": "<|reserved_special_token_55|>",
|
| 509 |
+
"lstrip": false,
|
| 510 |
+
"normalized": false,
|
| 511 |
+
"rstrip": false,
|
| 512 |
+
"single_word": false,
|
| 513 |
+
"special": true
|
| 514 |
+
},
|
| 515 |
+
"128064": {
|
| 516 |
+
"content": "<|reserved_special_token_56|>",
|
| 517 |
+
"lstrip": false,
|
| 518 |
+
"normalized": false,
|
| 519 |
+
"rstrip": false,
|
| 520 |
+
"single_word": false,
|
| 521 |
+
"special": true
|
| 522 |
+
},
|
| 523 |
+
"128065": {
|
| 524 |
+
"content": "<|reserved_special_token_57|>",
|
| 525 |
+
"lstrip": false,
|
| 526 |
+
"normalized": false,
|
| 527 |
+
"rstrip": false,
|
| 528 |
+
"single_word": false,
|
| 529 |
+
"special": true
|
| 530 |
+
},
|
| 531 |
+
"128066": {
|
| 532 |
+
"content": "<|reserved_special_token_58|>",
|
| 533 |
+
"lstrip": false,
|
| 534 |
+
"normalized": false,
|
| 535 |
+
"rstrip": false,
|
| 536 |
+
"single_word": false,
|
| 537 |
+
"special": true
|
| 538 |
+
},
|
| 539 |
+
"128067": {
|
| 540 |
+
"content": "<|reserved_special_token_59|>",
|
| 541 |
+
"lstrip": false,
|
| 542 |
+
"normalized": false,
|
| 543 |
+
"rstrip": false,
|
| 544 |
+
"single_word": false,
|
| 545 |
+
"special": true
|
| 546 |
+
},
|
| 547 |
+
"128068": {
|
| 548 |
+
"content": "<|reserved_special_token_60|>",
|
| 549 |
+
"lstrip": false,
|
| 550 |
+
"normalized": false,
|
| 551 |
+
"rstrip": false,
|
| 552 |
+
"single_word": false,
|
| 553 |
+
"special": true
|
| 554 |
+
},
|
| 555 |
+
"128069": {
|
| 556 |
+
"content": "<|reserved_special_token_61|>",
|
| 557 |
+
"lstrip": false,
|
| 558 |
+
"normalized": false,
|
| 559 |
+
"rstrip": false,
|
| 560 |
+
"single_word": false,
|
| 561 |
+
"special": true
|
| 562 |
+
},
|
| 563 |
+
"128070": {
|
| 564 |
+
"content": "<|reserved_special_token_62|>",
|
| 565 |
+
"lstrip": false,
|
| 566 |
+
"normalized": false,
|
| 567 |
+
"rstrip": false,
|
| 568 |
+
"single_word": false,
|
| 569 |
+
"special": true
|
| 570 |
+
},
|
| 571 |
+
"128071": {
|
| 572 |
+
"content": "<|reserved_special_token_63|>",
|
| 573 |
+
"lstrip": false,
|
| 574 |
+
"normalized": false,
|
| 575 |
+
"rstrip": false,
|
| 576 |
+
"single_word": false,
|
| 577 |
+
"special": true
|
| 578 |
+
},
|
| 579 |
+
"128072": {
|
| 580 |
+
"content": "<|reserved_special_token_64|>",
|
| 581 |
+
"lstrip": false,
|
| 582 |
+
"normalized": false,
|
| 583 |
+
"rstrip": false,
|
| 584 |
+
"single_word": false,
|
| 585 |
+
"special": true
|
| 586 |
+
},
|
| 587 |
+
"128073": {
|
| 588 |
+
"content": "<|reserved_special_token_65|>",
|
| 589 |
+
"lstrip": false,
|
| 590 |
+
"normalized": false,
|
| 591 |
+
"rstrip": false,
|
| 592 |
+
"single_word": false,
|
| 593 |
+
"special": true
|
| 594 |
+
},
|
| 595 |
+
"128074": {
|
| 596 |
+
"content": "<|reserved_special_token_66|>",
|
| 597 |
+
"lstrip": false,
|
| 598 |
+
"normalized": false,
|
| 599 |
+
"rstrip": false,
|
| 600 |
+
"single_word": false,
|
| 601 |
+
"special": true
|
| 602 |
+
},
|
| 603 |
+
"128075": {
|
| 604 |
+
"content": "<|reserved_special_token_67|>",
|
| 605 |
+
"lstrip": false,
|
| 606 |
+
"normalized": false,
|
| 607 |
+
"rstrip": false,
|
| 608 |
+
"single_word": false,
|
| 609 |
+
"special": true
|
| 610 |
+
},
|
| 611 |
+
"128076": {
|
| 612 |
+
"content": "<|reserved_special_token_68|>",
|
| 613 |
+
"lstrip": false,
|
| 614 |
+
"normalized": false,
|
| 615 |
+
"rstrip": false,
|
| 616 |
+
"single_word": false,
|
| 617 |
+
"special": true
|
| 618 |
+
},
|
| 619 |
+
"128077": {
|
| 620 |
+
"content": "<|reserved_special_token_69|>",
|
| 621 |
+
"lstrip": false,
|
| 622 |
+
"normalized": false,
|
| 623 |
+
"rstrip": false,
|
| 624 |
+
"single_word": false,
|
| 625 |
+
"special": true
|
| 626 |
+
},
|
| 627 |
+
"128078": {
|
| 628 |
+
"content": "<|reserved_special_token_70|>",
|
| 629 |
+
"lstrip": false,
|
| 630 |
+
"normalized": false,
|
| 631 |
+
"rstrip": false,
|
| 632 |
+
"single_word": false,
|
| 633 |
+
"special": true
|
| 634 |
+
},
|
| 635 |
+
"128079": {
|
| 636 |
+
"content": "<|reserved_special_token_71|>",
|
| 637 |
+
"lstrip": false,
|
| 638 |
+
"normalized": false,
|
| 639 |
+
"rstrip": false,
|
| 640 |
+
"single_word": false,
|
| 641 |
+
"special": true
|
| 642 |
+
},
|
| 643 |
+
"128080": {
|
| 644 |
+
"content": "<|reserved_special_token_72|>",
|
| 645 |
+
"lstrip": false,
|
| 646 |
+
"normalized": false,
|
| 647 |
+
"rstrip": false,
|
| 648 |
+
"single_word": false,
|
| 649 |
+
"special": true
|
| 650 |
+
},
|
| 651 |
+
"128081": {
|
| 652 |
+
"content": "<|reserved_special_token_73|>",
|
| 653 |
+
"lstrip": false,
|
| 654 |
+
"normalized": false,
|
| 655 |
+
"rstrip": false,
|
| 656 |
+
"single_word": false,
|
| 657 |
+
"special": true
|
| 658 |
+
},
|
| 659 |
+
"128082": {
|
| 660 |
+
"content": "<|reserved_special_token_74|>",
|
| 661 |
+
"lstrip": false,
|
| 662 |
+
"normalized": false,
|
| 663 |
+
"rstrip": false,
|
| 664 |
+
"single_word": false,
|
| 665 |
+
"special": true
|
| 666 |
+
},
|
| 667 |
+
"128083": {
|
| 668 |
+
"content": "<|reserved_special_token_75|>",
|
| 669 |
+
"lstrip": false,
|
| 670 |
+
"normalized": false,
|
| 671 |
+
"rstrip": false,
|
| 672 |
+
"single_word": false,
|
| 673 |
+
"special": true
|
| 674 |
+
},
|
| 675 |
+
"128084": {
|
| 676 |
+
"content": "<|reserved_special_token_76|>",
|
| 677 |
+
"lstrip": false,
|
| 678 |
+
"normalized": false,
|
| 679 |
+
"rstrip": false,
|
| 680 |
+
"single_word": false,
|
| 681 |
+
"special": true
|
| 682 |
+
},
|
| 683 |
+
"128085": {
|
| 684 |
+
"content": "<|reserved_special_token_77|>",
|
| 685 |
+
"lstrip": false,
|
| 686 |
+
"normalized": false,
|
| 687 |
+
"rstrip": false,
|
| 688 |
+
"single_word": false,
|
| 689 |
+
"special": true
|
| 690 |
+
},
|
| 691 |
+
"128086": {
|
| 692 |
+
"content": "<|reserved_special_token_78|>",
|
| 693 |
+
"lstrip": false,
|
| 694 |
+
"normalized": false,
|
| 695 |
+
"rstrip": false,
|
| 696 |
+
"single_word": false,
|
| 697 |
+
"special": true
|
| 698 |
+
},
|
| 699 |
+
"128087": {
|
| 700 |
+
"content": "<|reserved_special_token_79|>",
|
| 701 |
+
"lstrip": false,
|
| 702 |
+
"normalized": false,
|
| 703 |
+
"rstrip": false,
|
| 704 |
+
"single_word": false,
|
| 705 |
+
"special": true
|
| 706 |
+
},
|
| 707 |
+
"128088": {
|
| 708 |
+
"content": "<|reserved_special_token_80|>",
|
| 709 |
+
"lstrip": false,
|
| 710 |
+
"normalized": false,
|
| 711 |
+
"rstrip": false,
|
| 712 |
+
"single_word": false,
|
| 713 |
+
"special": true
|
| 714 |
+
},
|
| 715 |
+
"128089": {
|
| 716 |
+
"content": "<|reserved_special_token_81|>",
|
| 717 |
+
"lstrip": false,
|
| 718 |
+
"normalized": false,
|
| 719 |
+
"rstrip": false,
|
| 720 |
+
"single_word": false,
|
| 721 |
+
"special": true
|
| 722 |
+
},
|
| 723 |
+
"128090": {
|
| 724 |
+
"content": "<|reserved_special_token_82|>",
|
| 725 |
+
"lstrip": false,
|
| 726 |
+
"normalized": false,
|
| 727 |
+
"rstrip": false,
|
| 728 |
+
"single_word": false,
|
| 729 |
+
"special": true
|
| 730 |
+
},
|
| 731 |
+
"128091": {
|
| 732 |
+
"content": "<|reserved_special_token_83|>",
|
| 733 |
+
"lstrip": false,
|
| 734 |
+
"normalized": false,
|
| 735 |
+
"rstrip": false,
|
| 736 |
+
"single_word": false,
|
| 737 |
+
"special": true
|
| 738 |
+
},
|
| 739 |
+
"128092": {
|
| 740 |
+
"content": "<|reserved_special_token_84|>",
|
| 741 |
+
"lstrip": false,
|
| 742 |
+
"normalized": false,
|
| 743 |
+
"rstrip": false,
|
| 744 |
+
"single_word": false,
|
| 745 |
+
"special": true
|
| 746 |
+
},
|
| 747 |
+
"128093": {
|
| 748 |
+
"content": "<|reserved_special_token_85|>",
|
| 749 |
+
"lstrip": false,
|
| 750 |
+
"normalized": false,
|
| 751 |
+
"rstrip": false,
|
| 752 |
+
"single_word": false,
|
| 753 |
+
"special": true
|
| 754 |
+
},
|
| 755 |
+
"128094": {
|
| 756 |
+
"content": "<|reserved_special_token_86|>",
|
| 757 |
+
"lstrip": false,
|
| 758 |
+
"normalized": false,
|
| 759 |
+
"rstrip": false,
|
| 760 |
+
"single_word": false,
|
| 761 |
+
"special": true
|
| 762 |
+
},
|
| 763 |
+
"128095": {
|
| 764 |
+
"content": "<|reserved_special_token_87|>",
|
| 765 |
+
"lstrip": false,
|
| 766 |
+
"normalized": false,
|
| 767 |
+
"rstrip": false,
|
| 768 |
+
"single_word": false,
|
| 769 |
+
"special": true
|
| 770 |
+
},
|
| 771 |
+
"128096": {
|
| 772 |
+
"content": "<|reserved_special_token_88|>",
|
| 773 |
+
"lstrip": false,
|
| 774 |
+
"normalized": false,
|
| 775 |
+
"rstrip": false,
|
| 776 |
+
"single_word": false,
|
| 777 |
+
"special": true
|
| 778 |
+
},
|
| 779 |
+
"128097": {
|
| 780 |
+
"content": "<|reserved_special_token_89|>",
|
| 781 |
+
"lstrip": false,
|
| 782 |
+
"normalized": false,
|
| 783 |
+
"rstrip": false,
|
| 784 |
+
"single_word": false,
|
| 785 |
+
"special": true
|
| 786 |
+
},
|
| 787 |
+
"128098": {
|
| 788 |
+
"content": "<|reserved_special_token_90|>",
|
| 789 |
+
"lstrip": false,
|
| 790 |
+
"normalized": false,
|
| 791 |
+
"rstrip": false,
|
| 792 |
+
"single_word": false,
|
| 793 |
+
"special": true
|
| 794 |
+
},
|
| 795 |
+
"128099": {
|
| 796 |
+
"content": "<|reserved_special_token_91|>",
|
| 797 |
+
"lstrip": false,
|
| 798 |
+
"normalized": false,
|
| 799 |
+
"rstrip": false,
|
| 800 |
+
"single_word": false,
|
| 801 |
+
"special": true
|
| 802 |
+
},
|
| 803 |
+
"128100": {
|
| 804 |
+
"content": "<|reserved_special_token_92|>",
|
| 805 |
+
"lstrip": false,
|
| 806 |
+
"normalized": false,
|
| 807 |
+
"rstrip": false,
|
| 808 |
+
"single_word": false,
|
| 809 |
+
"special": true
|
| 810 |
+
},
|
| 811 |
+
"128101": {
|
| 812 |
+
"content": "<|reserved_special_token_93|>",
|
| 813 |
+
"lstrip": false,
|
| 814 |
+
"normalized": false,
|
| 815 |
+
"rstrip": false,
|
| 816 |
+
"single_word": false,
|
| 817 |
+
"special": true
|
| 818 |
+
},
|
| 819 |
+
"128102": {
|
| 820 |
+
"content": "<|reserved_special_token_94|>",
|
| 821 |
+
"lstrip": false,
|
| 822 |
+
"normalized": false,
|
| 823 |
+
"rstrip": false,
|
| 824 |
+
"single_word": false,
|
| 825 |
+
"special": true
|
| 826 |
+
},
|
| 827 |
+
"128103": {
|
| 828 |
+
"content": "<|reserved_special_token_95|>",
|
| 829 |
+
"lstrip": false,
|
| 830 |
+
"normalized": false,
|
| 831 |
+
"rstrip": false,
|
| 832 |
+
"single_word": false,
|
| 833 |
+
"special": true
|
| 834 |
+
},
|
| 835 |
+
"128104": {
|
| 836 |
+
"content": "<|reserved_special_token_96|>",
|
| 837 |
+
"lstrip": false,
|
| 838 |
+
"normalized": false,
|
| 839 |
+
"rstrip": false,
|
| 840 |
+
"single_word": false,
|
| 841 |
+
"special": true
|
| 842 |
+
},
|
| 843 |
+
"128105": {
|
| 844 |
+
"content": "<|reserved_special_token_97|>",
|
| 845 |
+
"lstrip": false,
|
| 846 |
+
"normalized": false,
|
| 847 |
+
"rstrip": false,
|
| 848 |
+
"single_word": false,
|
| 849 |
+
"special": true
|
| 850 |
+
},
|
| 851 |
+
"128106": {
|
| 852 |
+
"content": "<|reserved_special_token_98|>",
|
| 853 |
+
"lstrip": false,
|
| 854 |
+
"normalized": false,
|
| 855 |
+
"rstrip": false,
|
| 856 |
+
"single_word": false,
|
| 857 |
+
"special": true
|
| 858 |
+
},
|
| 859 |
+
"128107": {
|
| 860 |
+
"content": "<|reserved_special_token_99|>",
|
| 861 |
+
"lstrip": false,
|
| 862 |
+
"normalized": false,
|
| 863 |
+
"rstrip": false,
|
| 864 |
+
"single_word": false,
|
| 865 |
+
"special": true
|
| 866 |
+
},
|
| 867 |
+
"128108": {
|
| 868 |
+
"content": "<|reserved_special_token_100|>",
|
| 869 |
+
"lstrip": false,
|
| 870 |
+
"normalized": false,
|
| 871 |
+
"rstrip": false,
|
| 872 |
+
"single_word": false,
|
| 873 |
+
"special": true
|
| 874 |
+
},
|
| 875 |
+
"128109": {
|
| 876 |
+
"content": "<|reserved_special_token_101|>",
|
| 877 |
+
"lstrip": false,
|
| 878 |
+
"normalized": false,
|
| 879 |
+
"rstrip": false,
|
| 880 |
+
"single_word": false,
|
| 881 |
+
"special": true
|
| 882 |
+
},
|
| 883 |
+
"128110": {
|
| 884 |
+
"content": "<|reserved_special_token_102|>",
|
| 885 |
+
"lstrip": false,
|
| 886 |
+
"normalized": false,
|
| 887 |
+
"rstrip": false,
|
| 888 |
+
"single_word": false,
|
| 889 |
+
"special": true
|
| 890 |
+
},
|
| 891 |
+
"128111": {
|
| 892 |
+
"content": "<|reserved_special_token_103|>",
|
| 893 |
+
"lstrip": false,
|
| 894 |
+
"normalized": false,
|
| 895 |
+
"rstrip": false,
|
| 896 |
+
"single_word": false,
|
| 897 |
+
"special": true
|
| 898 |
+
},
|
| 899 |
+
"128112": {
|
| 900 |
+
"content": "<|reserved_special_token_104|>",
|
| 901 |
+
"lstrip": false,
|
| 902 |
+
"normalized": false,
|
| 903 |
+
"rstrip": false,
|
| 904 |
+
"single_word": false,
|
| 905 |
+
"special": true
|
| 906 |
+
},
|
| 907 |
+
"128113": {
|
| 908 |
+
"content": "<|reserved_special_token_105|>",
|
| 909 |
+
"lstrip": false,
|
| 910 |
+
"normalized": false,
|
| 911 |
+
"rstrip": false,
|
| 912 |
+
"single_word": false,
|
| 913 |
+
"special": true
|
| 914 |
+
},
|
| 915 |
+
"128114": {
|
| 916 |
+
"content": "<|reserved_special_token_106|>",
|
| 917 |
+
"lstrip": false,
|
| 918 |
+
"normalized": false,
|
| 919 |
+
"rstrip": false,
|
| 920 |
+
"single_word": false,
|
| 921 |
+
"special": true
|
| 922 |
+
},
|
| 923 |
+
"128115": {
|
| 924 |
+
"content": "<|reserved_special_token_107|>",
|
| 925 |
+
"lstrip": false,
|
| 926 |
+
"normalized": false,
|
| 927 |
+
"rstrip": false,
|
| 928 |
+
"single_word": false,
|
| 929 |
+
"special": true
|
| 930 |
+
},
|
| 931 |
+
"128116": {
|
| 932 |
+
"content": "<|reserved_special_token_108|>",
|
| 933 |
+
"lstrip": false,
|
| 934 |
+
"normalized": false,
|
| 935 |
+
"rstrip": false,
|
| 936 |
+
"single_word": false,
|
| 937 |
+
"special": true
|
| 938 |
+
},
|
| 939 |
+
"128117": {
|
| 940 |
+
"content": "<|reserved_special_token_109|>",
|
| 941 |
+
"lstrip": false,
|
| 942 |
+
"normalized": false,
|
| 943 |
+
"rstrip": false,
|
| 944 |
+
"single_word": false,
|
| 945 |
+
"special": true
|
| 946 |
+
},
|
| 947 |
+
"128118": {
|
| 948 |
+
"content": "<|reserved_special_token_110|>",
|
| 949 |
+
"lstrip": false,
|
| 950 |
+
"normalized": false,
|
| 951 |
+
"rstrip": false,
|
| 952 |
+
"single_word": false,
|
| 953 |
+
"special": true
|
| 954 |
+
},
|
| 955 |
+
"128119": {
|
| 956 |
+
"content": "<|reserved_special_token_111|>",
|
| 957 |
+
"lstrip": false,
|
| 958 |
+
"normalized": false,
|
| 959 |
+
"rstrip": false,
|
| 960 |
+
"single_word": false,
|
| 961 |
+
"special": true
|
| 962 |
+
},
|
| 963 |
+
"128120": {
|
| 964 |
+
"content": "<|reserved_special_token_112|>",
|
| 965 |
+
"lstrip": false,
|
| 966 |
+
"normalized": false,
|
| 967 |
+
"rstrip": false,
|
| 968 |
+
"single_word": false,
|
| 969 |
+
"special": true
|
| 970 |
+
},
|
| 971 |
+
"128121": {
|
| 972 |
+
"content": "<|reserved_special_token_113|>",
|
| 973 |
+
"lstrip": false,
|
| 974 |
+
"normalized": false,
|
| 975 |
+
"rstrip": false,
|
| 976 |
+
"single_word": false,
|
| 977 |
+
"special": true
|
| 978 |
+
},
|
| 979 |
+
"128122": {
|
| 980 |
+
"content": "<|reserved_special_token_114|>",
|
| 981 |
+
"lstrip": false,
|
| 982 |
+
"normalized": false,
|
| 983 |
+
"rstrip": false,
|
| 984 |
+
"single_word": false,
|
| 985 |
+
"special": true
|
| 986 |
+
},
|
| 987 |
+
"128123": {
|
| 988 |
+
"content": "<|reserved_special_token_115|>",
|
| 989 |
+
"lstrip": false,
|
| 990 |
+
"normalized": false,
|
| 991 |
+
"rstrip": false,
|
| 992 |
+
"single_word": false,
|
| 993 |
+
"special": true
|
| 994 |
+
},
|
| 995 |
+
"128124": {
|
| 996 |
+
"content": "<|reserved_special_token_116|>",
|
| 997 |
+
"lstrip": false,
|
| 998 |
+
"normalized": false,
|
| 999 |
+
"rstrip": false,
|
| 1000 |
+
"single_word": false,
|
| 1001 |
+
"special": true
|
| 1002 |
+
},
|
| 1003 |
+
"128125": {
|
| 1004 |
+
"content": "<|reserved_special_token_117|>",
|
| 1005 |
+
"lstrip": false,
|
| 1006 |
+
"normalized": false,
|
| 1007 |
+
"rstrip": false,
|
| 1008 |
+
"single_word": false,
|
| 1009 |
+
"special": true
|
| 1010 |
+
},
|
| 1011 |
+
"128126": {
|
| 1012 |
+
"content": "<|reserved_special_token_118|>",
|
| 1013 |
+
"lstrip": false,
|
| 1014 |
+
"normalized": false,
|
| 1015 |
+
"rstrip": false,
|
| 1016 |
+
"single_word": false,
|
| 1017 |
+
"special": true
|
| 1018 |
+
},
|
| 1019 |
+
"128127": {
|
| 1020 |
+
"content": "<|reserved_special_token_119|>",
|
| 1021 |
+
"lstrip": false,
|
| 1022 |
+
"normalized": false,
|
| 1023 |
+
"rstrip": false,
|
| 1024 |
+
"single_word": false,
|
| 1025 |
+
"special": true
|
| 1026 |
+
},
|
| 1027 |
+
"128128": {
|
| 1028 |
+
"content": "<|reserved_special_token_120|>",
|
| 1029 |
+
"lstrip": false,
|
| 1030 |
+
"normalized": false,
|
| 1031 |
+
"rstrip": false,
|
| 1032 |
+
"single_word": false,
|
| 1033 |
+
"special": true
|
| 1034 |
+
},
|
| 1035 |
+
"128129": {
|
| 1036 |
+
"content": "<|reserved_special_token_121|>",
|
| 1037 |
+
"lstrip": false,
|
| 1038 |
+
"normalized": false,
|
| 1039 |
+
"rstrip": false,
|
| 1040 |
+
"single_word": false,
|
| 1041 |
+
"special": true
|
| 1042 |
+
},
|
| 1043 |
+
"128130": {
|
| 1044 |
+
"content": "<|reserved_special_token_122|>",
|
| 1045 |
+
"lstrip": false,
|
| 1046 |
+
"normalized": false,
|
| 1047 |
+
"rstrip": false,
|
| 1048 |
+
"single_word": false,
|
| 1049 |
+
"special": true
|
| 1050 |
+
},
|
| 1051 |
+
"128131": {
|
| 1052 |
+
"content": "<|reserved_special_token_123|>",
|
| 1053 |
+
"lstrip": false,
|
| 1054 |
+
"normalized": false,
|
| 1055 |
+
"rstrip": false,
|
| 1056 |
+
"single_word": false,
|
| 1057 |
+
"special": true
|
| 1058 |
+
},
|
| 1059 |
+
"128132": {
|
| 1060 |
+
"content": "<|reserved_special_token_124|>",
|
| 1061 |
+
"lstrip": false,
|
| 1062 |
+
"normalized": false,
|
| 1063 |
+
"rstrip": false,
|
| 1064 |
+
"single_word": false,
|
| 1065 |
+
"special": true
|
| 1066 |
+
},
|
| 1067 |
+
"128133": {
|
| 1068 |
+
"content": "<|reserved_special_token_125|>",
|
| 1069 |
+
"lstrip": false,
|
| 1070 |
+
"normalized": false,
|
| 1071 |
+
"rstrip": false,
|
| 1072 |
+
"single_word": false,
|
| 1073 |
+
"special": true
|
| 1074 |
+
},
|
| 1075 |
+
"128134": {
|
| 1076 |
+
"content": "<|reserved_special_token_126|>",
|
| 1077 |
+
"lstrip": false,
|
| 1078 |
+
"normalized": false,
|
| 1079 |
+
"rstrip": false,
|
| 1080 |
+
"single_word": false,
|
| 1081 |
+
"special": true
|
| 1082 |
+
},
|
| 1083 |
+
"128135": {
|
| 1084 |
+
"content": "<|reserved_special_token_127|>",
|
| 1085 |
+
"lstrip": false,
|
| 1086 |
+
"normalized": false,
|
| 1087 |
+
"rstrip": false,
|
| 1088 |
+
"single_word": false,
|
| 1089 |
+
"special": true
|
| 1090 |
+
},
|
| 1091 |
+
"128136": {
|
| 1092 |
+
"content": "<|reserved_special_token_128|>",
|
| 1093 |
+
"lstrip": false,
|
| 1094 |
+
"normalized": false,
|
| 1095 |
+
"rstrip": false,
|
| 1096 |
+
"single_word": false,
|
| 1097 |
+
"special": true
|
| 1098 |
+
},
|
| 1099 |
+
"128137": {
|
| 1100 |
+
"content": "<|reserved_special_token_129|>",
|
| 1101 |
+
"lstrip": false,
|
| 1102 |
+
"normalized": false,
|
| 1103 |
+
"rstrip": false,
|
| 1104 |
+
"single_word": false,
|
| 1105 |
+
"special": true
|
| 1106 |
+
},
|
| 1107 |
+
"128138": {
|
| 1108 |
+
"content": "<|reserved_special_token_130|>",
|
| 1109 |
+
"lstrip": false,
|
| 1110 |
+
"normalized": false,
|
| 1111 |
+
"rstrip": false,
|
| 1112 |
+
"single_word": false,
|
| 1113 |
+
"special": true
|
| 1114 |
+
},
|
| 1115 |
+
"128139": {
|
| 1116 |
+
"content": "<|reserved_special_token_131|>",
|
| 1117 |
+
"lstrip": false,
|
| 1118 |
+
"normalized": false,
|
| 1119 |
+
"rstrip": false,
|
| 1120 |
+
"single_word": false,
|
| 1121 |
+
"special": true
|
| 1122 |
+
},
|
| 1123 |
+
"128140": {
|
| 1124 |
+
"content": "<|reserved_special_token_132|>",
|
| 1125 |
+
"lstrip": false,
|
| 1126 |
+
"normalized": false,
|
| 1127 |
+
"rstrip": false,
|
| 1128 |
+
"single_word": false,
|
| 1129 |
+
"special": true
|
| 1130 |
+
},
|
| 1131 |
+
"128141": {
|
| 1132 |
+
"content": "<|reserved_special_token_133|>",
|
| 1133 |
+
"lstrip": false,
|
| 1134 |
+
"normalized": false,
|
| 1135 |
+
"rstrip": false,
|
| 1136 |
+
"single_word": false,
|
| 1137 |
+
"special": true
|
| 1138 |
+
},
|
| 1139 |
+
"128142": {
|
| 1140 |
+
"content": "<|reserved_special_token_134|>",
|
| 1141 |
+
"lstrip": false,
|
| 1142 |
+
"normalized": false,
|
| 1143 |
+
"rstrip": false,
|
| 1144 |
+
"single_word": false,
|
| 1145 |
+
"special": true
|
| 1146 |
+
},
|
| 1147 |
+
"128143": {
|
| 1148 |
+
"content": "<|reserved_special_token_135|>",
|
| 1149 |
+
"lstrip": false,
|
| 1150 |
+
"normalized": false,
|
| 1151 |
+
"rstrip": false,
|
| 1152 |
+
"single_word": false,
|
| 1153 |
+
"special": true
|
| 1154 |
+
},
|
| 1155 |
+
"128144": {
|
| 1156 |
+
"content": "<|reserved_special_token_136|>",
|
| 1157 |
+
"lstrip": false,
|
| 1158 |
+
"normalized": false,
|
| 1159 |
+
"rstrip": false,
|
| 1160 |
+
"single_word": false,
|
| 1161 |
+
"special": true
|
| 1162 |
+
},
|
| 1163 |
+
"128145": {
|
| 1164 |
+
"content": "<|reserved_special_token_137|>",
|
| 1165 |
+
"lstrip": false,
|
| 1166 |
+
"normalized": false,
|
| 1167 |
+
"rstrip": false,
|
| 1168 |
+
"single_word": false,
|
| 1169 |
+
"special": true
|
| 1170 |
+
},
|
| 1171 |
+
"128146": {
|
| 1172 |
+
"content": "<|reserved_special_token_138|>",
|
| 1173 |
+
"lstrip": false,
|
| 1174 |
+
"normalized": false,
|
| 1175 |
+
"rstrip": false,
|
| 1176 |
+
"single_word": false,
|
| 1177 |
+
"special": true
|
| 1178 |
+
},
|
| 1179 |
+
"128147": {
|
| 1180 |
+
"content": "<|reserved_special_token_139|>",
|
| 1181 |
+
"lstrip": false,
|
| 1182 |
+
"normalized": false,
|
| 1183 |
+
"rstrip": false,
|
| 1184 |
+
"single_word": false,
|
| 1185 |
+
"special": true
|
| 1186 |
+
},
|
| 1187 |
+
"128148": {
|
| 1188 |
+
"content": "<|reserved_special_token_140|>",
|
| 1189 |
+
"lstrip": false,
|
| 1190 |
+
"normalized": false,
|
| 1191 |
+
"rstrip": false,
|
| 1192 |
+
"single_word": false,
|
| 1193 |
+
"special": true
|
| 1194 |
+
},
|
| 1195 |
+
"128149": {
|
| 1196 |
+
"content": "<|reserved_special_token_141|>",
|
| 1197 |
+
"lstrip": false,
|
| 1198 |
+
"normalized": false,
|
| 1199 |
+
"rstrip": false,
|
| 1200 |
+
"single_word": false,
|
| 1201 |
+
"special": true
|
| 1202 |
+
},
|
| 1203 |
+
"128150": {
|
| 1204 |
+
"content": "<|reserved_special_token_142|>",
|
| 1205 |
+
"lstrip": false,
|
| 1206 |
+
"normalized": false,
|
| 1207 |
+
"rstrip": false,
|
| 1208 |
+
"single_word": false,
|
| 1209 |
+
"special": true
|
| 1210 |
+
},
|
| 1211 |
+
"128151": {
|
| 1212 |
+
"content": "<|reserved_special_token_143|>",
|
| 1213 |
+
"lstrip": false,
|
| 1214 |
+
"normalized": false,
|
| 1215 |
+
"rstrip": false,
|
| 1216 |
+
"single_word": false,
|
| 1217 |
+
"special": true
|
| 1218 |
+
},
|
| 1219 |
+
"128152": {
|
| 1220 |
+
"content": "<|reserved_special_token_144|>",
|
| 1221 |
+
"lstrip": false,
|
| 1222 |
+
"normalized": false,
|
| 1223 |
+
"rstrip": false,
|
| 1224 |
+
"single_word": false,
|
| 1225 |
+
"special": true
|
| 1226 |
+
},
|
| 1227 |
+
"128153": {
|
| 1228 |
+
"content": "<|reserved_special_token_145|>",
|
| 1229 |
+
"lstrip": false,
|
| 1230 |
+
"normalized": false,
|
| 1231 |
+
"rstrip": false,
|
| 1232 |
+
"single_word": false,
|
| 1233 |
+
"special": true
|
| 1234 |
+
},
|
| 1235 |
+
"128154": {
|
| 1236 |
+
"content": "<|reserved_special_token_146|>",
|
| 1237 |
+
"lstrip": false,
|
| 1238 |
+
"normalized": false,
|
| 1239 |
+
"rstrip": false,
|
| 1240 |
+
"single_word": false,
|
| 1241 |
+
"special": true
|
| 1242 |
+
},
|
| 1243 |
+
"128155": {
|
| 1244 |
+
"content": "<|reserved_special_token_147|>",
|
| 1245 |
+
"lstrip": false,
|
| 1246 |
+
"normalized": false,
|
| 1247 |
+
"rstrip": false,
|
| 1248 |
+
"single_word": false,
|
| 1249 |
+
"special": true
|
| 1250 |
+
},
|
| 1251 |
+
"128156": {
|
| 1252 |
+
"content": "<|reserved_special_token_148|>",
|
| 1253 |
+
"lstrip": false,
|
| 1254 |
+
"normalized": false,
|
| 1255 |
+
"rstrip": false,
|
| 1256 |
+
"single_word": false,
|
| 1257 |
+
"special": true
|
| 1258 |
+
},
|
| 1259 |
+
"128157": {
|
| 1260 |
+
"content": "<|reserved_special_token_149|>",
|
| 1261 |
+
"lstrip": false,
|
| 1262 |
+
"normalized": false,
|
| 1263 |
+
"rstrip": false,
|
| 1264 |
+
"single_word": false,
|
| 1265 |
+
"special": true
|
| 1266 |
+
},
|
| 1267 |
+
"128158": {
|
| 1268 |
+
"content": "<|reserved_special_token_150|>",
|
| 1269 |
+
"lstrip": false,
|
| 1270 |
+
"normalized": false,
|
| 1271 |
+
"rstrip": false,
|
| 1272 |
+
"single_word": false,
|
| 1273 |
+
"special": true
|
| 1274 |
+
},
|
| 1275 |
+
"128159": {
|
| 1276 |
+
"content": "<|reserved_special_token_151|>",
|
| 1277 |
+
"lstrip": false,
|
| 1278 |
+
"normalized": false,
|
| 1279 |
+
"rstrip": false,
|
| 1280 |
+
"single_word": false,
|
| 1281 |
+
"special": true
|
| 1282 |
+
},
|
| 1283 |
+
"128160": {
|
| 1284 |
+
"content": "<|reserved_special_token_152|>",
|
| 1285 |
+
"lstrip": false,
|
| 1286 |
+
"normalized": false,
|
| 1287 |
+
"rstrip": false,
|
| 1288 |
+
"single_word": false,
|
| 1289 |
+
"special": true
|
| 1290 |
+
},
|
| 1291 |
+
"128161": {
|
| 1292 |
+
"content": "<|reserved_special_token_153|>",
|
| 1293 |
+
"lstrip": false,
|
| 1294 |
+
"normalized": false,
|
| 1295 |
+
"rstrip": false,
|
| 1296 |
+
"single_word": false,
|
| 1297 |
+
"special": true
|
| 1298 |
+
},
|
| 1299 |
+
"128162": {
|
| 1300 |
+
"content": "<|reserved_special_token_154|>",
|
| 1301 |
+
"lstrip": false,
|
| 1302 |
+
"normalized": false,
|
| 1303 |
+
"rstrip": false,
|
| 1304 |
+
"single_word": false,
|
| 1305 |
+
"special": true
|
| 1306 |
+
},
|
| 1307 |
+
"128163": {
|
| 1308 |
+
"content": "<|reserved_special_token_155|>",
|
| 1309 |
+
"lstrip": false,
|
| 1310 |
+
"normalized": false,
|
| 1311 |
+
"rstrip": false,
|
| 1312 |
+
"single_word": false,
|
| 1313 |
+
"special": true
|
| 1314 |
+
},
|
| 1315 |
+
"128164": {
|
| 1316 |
+
"content": "<|reserved_special_token_156|>",
|
| 1317 |
+
"lstrip": false,
|
| 1318 |
+
"normalized": false,
|
| 1319 |
+
"rstrip": false,
|
| 1320 |
+
"single_word": false,
|
| 1321 |
+
"special": true
|
| 1322 |
+
},
|
| 1323 |
+
"128165": {
|
| 1324 |
+
"content": "<|reserved_special_token_157|>",
|
| 1325 |
+
"lstrip": false,
|
| 1326 |
+
"normalized": false,
|
| 1327 |
+
"rstrip": false,
|
| 1328 |
+
"single_word": false,
|
| 1329 |
+
"special": true
|
| 1330 |
+
},
|
| 1331 |
+
"128166": {
|
| 1332 |
+
"content": "<|reserved_special_token_158|>",
|
| 1333 |
+
"lstrip": false,
|
| 1334 |
+
"normalized": false,
|
| 1335 |
+
"rstrip": false,
|
| 1336 |
+
"single_word": false,
|
| 1337 |
+
"special": true
|
| 1338 |
+
},
|
| 1339 |
+
"128167": {
|
| 1340 |
+
"content": "<|reserved_special_token_159|>",
|
| 1341 |
+
"lstrip": false,
|
| 1342 |
+
"normalized": false,
|
| 1343 |
+
"rstrip": false,
|
| 1344 |
+
"single_word": false,
|
| 1345 |
+
"special": true
|
| 1346 |
+
},
|
| 1347 |
+
"128168": {
|
| 1348 |
+
"content": "<|reserved_special_token_160|>",
|
| 1349 |
+
"lstrip": false,
|
| 1350 |
+
"normalized": false,
|
| 1351 |
+
"rstrip": false,
|
| 1352 |
+
"single_word": false,
|
| 1353 |
+
"special": true
|
| 1354 |
+
},
|
| 1355 |
+
"128169": {
|
| 1356 |
+
"content": "<|reserved_special_token_161|>",
|
| 1357 |
+
"lstrip": false,
|
| 1358 |
+
"normalized": false,
|
| 1359 |
+
"rstrip": false,
|
| 1360 |
+
"single_word": false,
|
| 1361 |
+
"special": true
|
| 1362 |
+
},
|
| 1363 |
+
"128170": {
|
| 1364 |
+
"content": "<|reserved_special_token_162|>",
|
| 1365 |
+
"lstrip": false,
|
| 1366 |
+
"normalized": false,
|
| 1367 |
+
"rstrip": false,
|
| 1368 |
+
"single_word": false,
|
| 1369 |
+
"special": true
|
| 1370 |
+
},
|
| 1371 |
+
"128171": {
|
| 1372 |
+
"content": "<|reserved_special_token_163|>",
|
| 1373 |
+
"lstrip": false,
|
| 1374 |
+
"normalized": false,
|
| 1375 |
+
"rstrip": false,
|
| 1376 |
+
"single_word": false,
|
| 1377 |
+
"special": true
|
| 1378 |
+
},
|
| 1379 |
+
"128172": {
|
| 1380 |
+
"content": "<|reserved_special_token_164|>",
|
| 1381 |
+
"lstrip": false,
|
| 1382 |
+
"normalized": false,
|
| 1383 |
+
"rstrip": false,
|
| 1384 |
+
"single_word": false,
|
| 1385 |
+
"special": true
|
| 1386 |
+
},
|
| 1387 |
+
"128173": {
|
| 1388 |
+
"content": "<|reserved_special_token_165|>",
|
| 1389 |
+
"lstrip": false,
|
| 1390 |
+
"normalized": false,
|
| 1391 |
+
"rstrip": false,
|
| 1392 |
+
"single_word": false,
|
| 1393 |
+
"special": true
|
| 1394 |
+
},
|
| 1395 |
+
"128174": {
|
| 1396 |
+
"content": "<|reserved_special_token_166|>",
|
| 1397 |
+
"lstrip": false,
|
| 1398 |
+
"normalized": false,
|
| 1399 |
+
"rstrip": false,
|
| 1400 |
+
"single_word": false,
|
| 1401 |
+
"special": true
|
| 1402 |
+
},
|
| 1403 |
+
"128175": {
|
| 1404 |
+
"content": "<|reserved_special_token_167|>",
|
| 1405 |
+
"lstrip": false,
|
| 1406 |
+
"normalized": false,
|
| 1407 |
+
"rstrip": false,
|
| 1408 |
+
"single_word": false,
|
| 1409 |
+
"special": true
|
| 1410 |
+
},
|
| 1411 |
+
"128176": {
|
| 1412 |
+
"content": "<|reserved_special_token_168|>",
|
| 1413 |
+
"lstrip": false,
|
| 1414 |
+
"normalized": false,
|
| 1415 |
+
"rstrip": false,
|
| 1416 |
+
"single_word": false,
|
| 1417 |
+
"special": true
|
| 1418 |
+
},
|
| 1419 |
+
"128177": {
|
| 1420 |
+
"content": "<|reserved_special_token_169|>",
|
| 1421 |
+
"lstrip": false,
|
| 1422 |
+
"normalized": false,
|
| 1423 |
+
"rstrip": false,
|
| 1424 |
+
"single_word": false,
|
| 1425 |
+
"special": true
|
| 1426 |
+
},
|
| 1427 |
+
"128178": {
|
| 1428 |
+
"content": "<|reserved_special_token_170|>",
|
| 1429 |
+
"lstrip": false,
|
| 1430 |
+
"normalized": false,
|
| 1431 |
+
"rstrip": false,
|
| 1432 |
+
"single_word": false,
|
| 1433 |
+
"special": true
|
| 1434 |
+
},
|
| 1435 |
+
"128179": {
|
| 1436 |
+
"content": "<|reserved_special_token_171|>",
|
| 1437 |
+
"lstrip": false,
|
| 1438 |
+
"normalized": false,
|
| 1439 |
+
"rstrip": false,
|
| 1440 |
+
"single_word": false,
|
| 1441 |
+
"special": true
|
| 1442 |
+
},
|
| 1443 |
+
"128180": {
|
| 1444 |
+
"content": "<|reserved_special_token_172|>",
|
| 1445 |
+
"lstrip": false,
|
| 1446 |
+
"normalized": false,
|
| 1447 |
+
"rstrip": false,
|
| 1448 |
+
"single_word": false,
|
| 1449 |
+
"special": true
|
| 1450 |
+
},
|
| 1451 |
+
"128181": {
|
| 1452 |
+
"content": "<|reserved_special_token_173|>",
|
| 1453 |
+
"lstrip": false,
|
| 1454 |
+
"normalized": false,
|
| 1455 |
+
"rstrip": false,
|
| 1456 |
+
"single_word": false,
|
| 1457 |
+
"special": true
|
| 1458 |
+
},
|
| 1459 |
+
"128182": {
|
| 1460 |
+
"content": "<|reserved_special_token_174|>",
|
| 1461 |
+
"lstrip": false,
|
| 1462 |
+
"normalized": false,
|
| 1463 |
+
"rstrip": false,
|
| 1464 |
+
"single_word": false,
|
| 1465 |
+
"special": true
|
| 1466 |
+
},
|
| 1467 |
+
"128183": {
|
| 1468 |
+
"content": "<|reserved_special_token_175|>",
|
| 1469 |
+
"lstrip": false,
|
| 1470 |
+
"normalized": false,
|
| 1471 |
+
"rstrip": false,
|
| 1472 |
+
"single_word": false,
|
| 1473 |
+
"special": true
|
| 1474 |
+
},
|
| 1475 |
+
"128184": {
|
| 1476 |
+
"content": "<|reserved_special_token_176|>",
|
| 1477 |
+
"lstrip": false,
|
| 1478 |
+
"normalized": false,
|
| 1479 |
+
"rstrip": false,
|
| 1480 |
+
"single_word": false,
|
| 1481 |
+
"special": true
|
| 1482 |
+
},
|
| 1483 |
+
"128185": {
|
| 1484 |
+
"content": "<|reserved_special_token_177|>",
|
| 1485 |
+
"lstrip": false,
|
| 1486 |
+
"normalized": false,
|
| 1487 |
+
"rstrip": false,
|
| 1488 |
+
"single_word": false,
|
| 1489 |
+
"special": true
|
| 1490 |
+
},
|
| 1491 |
+
"128186": {
|
| 1492 |
+
"content": "<|reserved_special_token_178|>",
|
| 1493 |
+
"lstrip": false,
|
| 1494 |
+
"normalized": false,
|
| 1495 |
+
"rstrip": false,
|
| 1496 |
+
"single_word": false,
|
| 1497 |
+
"special": true
|
| 1498 |
+
},
|
| 1499 |
+
"128187": {
|
| 1500 |
+
"content": "<|reserved_special_token_179|>",
|
| 1501 |
+
"lstrip": false,
|
| 1502 |
+
"normalized": false,
|
| 1503 |
+
"rstrip": false,
|
| 1504 |
+
"single_word": false,
|
| 1505 |
+
"special": true
|
| 1506 |
+
},
|
| 1507 |
+
"128188": {
|
| 1508 |
+
"content": "<|reserved_special_token_180|>",
|
| 1509 |
+
"lstrip": false,
|
| 1510 |
+
"normalized": false,
|
| 1511 |
+
"rstrip": false,
|
| 1512 |
+
"single_word": false,
|
| 1513 |
+
"special": true
|
| 1514 |
+
},
|
| 1515 |
+
"128189": {
|
| 1516 |
+
"content": "<|reserved_special_token_181|>",
|
| 1517 |
+
"lstrip": false,
|
| 1518 |
+
"normalized": false,
|
| 1519 |
+
"rstrip": false,
|
| 1520 |
+
"single_word": false,
|
| 1521 |
+
"special": true
|
| 1522 |
+
},
|
| 1523 |
+
"128190": {
|
| 1524 |
+
"content": "<|reserved_special_token_182|>",
|
| 1525 |
+
"lstrip": false,
|
| 1526 |
+
"normalized": false,
|
| 1527 |
+
"rstrip": false,
|
| 1528 |
+
"single_word": false,
|
| 1529 |
+
"special": true
|
| 1530 |
+
},
|
| 1531 |
+
"128191": {
|
| 1532 |
+
"content": "<|reserved_special_token_183|>",
|
| 1533 |
+
"lstrip": false,
|
| 1534 |
+
"normalized": false,
|
| 1535 |
+
"rstrip": false,
|
| 1536 |
+
"single_word": false,
|
| 1537 |
+
"special": true
|
| 1538 |
+
},
|
| 1539 |
+
"128192": {
|
| 1540 |
+
"content": "<|reserved_special_token_184|>",
|
| 1541 |
+
"lstrip": false,
|
| 1542 |
+
"normalized": false,
|
| 1543 |
+
"rstrip": false,
|
| 1544 |
+
"single_word": false,
|
| 1545 |
+
"special": true
|
| 1546 |
+
},
|
| 1547 |
+
"128193": {
|
| 1548 |
+
"content": "<|reserved_special_token_185|>",
|
| 1549 |
+
"lstrip": false,
|
| 1550 |
+
"normalized": false,
|
| 1551 |
+
"rstrip": false,
|
| 1552 |
+
"single_word": false,
|
| 1553 |
+
"special": true
|
| 1554 |
+
},
|
| 1555 |
+
"128194": {
|
| 1556 |
+
"content": "<|reserved_special_token_186|>",
|
| 1557 |
+
"lstrip": false,
|
| 1558 |
+
"normalized": false,
|
| 1559 |
+
"rstrip": false,
|
| 1560 |
+
"single_word": false,
|
| 1561 |
+
"special": true
|
| 1562 |
+
},
|
| 1563 |
+
"128195": {
|
| 1564 |
+
"content": "<|reserved_special_token_187|>",
|
| 1565 |
+
"lstrip": false,
|
| 1566 |
+
"normalized": false,
|
| 1567 |
+
"rstrip": false,
|
| 1568 |
+
"single_word": false,
|
| 1569 |
+
"special": true
|
| 1570 |
+
},
|
| 1571 |
+
"128196": {
|
| 1572 |
+
"content": "<|reserved_special_token_188|>",
|
| 1573 |
+
"lstrip": false,
|
| 1574 |
+
"normalized": false,
|
| 1575 |
+
"rstrip": false,
|
| 1576 |
+
"single_word": false,
|
| 1577 |
+
"special": true
|
| 1578 |
+
},
|
| 1579 |
+
"128197": {
|
| 1580 |
+
"content": "<|reserved_special_token_189|>",
|
| 1581 |
+
"lstrip": false,
|
| 1582 |
+
"normalized": false,
|
| 1583 |
+
"rstrip": false,
|
| 1584 |
+
"single_word": false,
|
| 1585 |
+
"special": true
|
| 1586 |
+
},
|
| 1587 |
+
"128198": {
|
| 1588 |
+
"content": "<|reserved_special_token_190|>",
|
| 1589 |
+
"lstrip": false,
|
| 1590 |
+
"normalized": false,
|
| 1591 |
+
"rstrip": false,
|
| 1592 |
+
"single_word": false,
|
| 1593 |
+
"special": true
|
| 1594 |
+
},
|
| 1595 |
+
"128199": {
|
| 1596 |
+
"content": "<|reserved_special_token_191|>",
|
| 1597 |
+
"lstrip": false,
|
| 1598 |
+
"normalized": false,
|
| 1599 |
+
"rstrip": false,
|
| 1600 |
+
"single_word": false,
|
| 1601 |
+
"special": true
|
| 1602 |
+
},
|
| 1603 |
+
"128200": {
|
| 1604 |
+
"content": "<|reserved_special_token_192|>",
|
| 1605 |
+
"lstrip": false,
|
| 1606 |
+
"normalized": false,
|
| 1607 |
+
"rstrip": false,
|
| 1608 |
+
"single_word": false,
|
| 1609 |
+
"special": true
|
| 1610 |
+
},
|
| 1611 |
+
"128201": {
|
| 1612 |
+
"content": "<|reserved_special_token_193|>",
|
| 1613 |
+
"lstrip": false,
|
| 1614 |
+
"normalized": false,
|
| 1615 |
+
"rstrip": false,
|
| 1616 |
+
"single_word": false,
|
| 1617 |
+
"special": true
|
| 1618 |
+
},
|
| 1619 |
+
"128202": {
|
| 1620 |
+
"content": "<|reserved_special_token_194|>",
|
| 1621 |
+
"lstrip": false,
|
| 1622 |
+
"normalized": false,
|
| 1623 |
+
"rstrip": false,
|
| 1624 |
+
"single_word": false,
|
| 1625 |
+
"special": true
|
| 1626 |
+
},
|
| 1627 |
+
"128203": {
|
| 1628 |
+
"content": "<|reserved_special_token_195|>",
|
| 1629 |
+
"lstrip": false,
|
| 1630 |
+
"normalized": false,
|
| 1631 |
+
"rstrip": false,
|
| 1632 |
+
"single_word": false,
|
| 1633 |
+
"special": true
|
| 1634 |
+
},
|
| 1635 |
+
"128204": {
|
| 1636 |
+
"content": "<|reserved_special_token_196|>",
|
| 1637 |
+
"lstrip": false,
|
| 1638 |
+
"normalized": false,
|
| 1639 |
+
"rstrip": false,
|
| 1640 |
+
"single_word": false,
|
| 1641 |
+
"special": true
|
| 1642 |
+
},
|
| 1643 |
+
"128205": {
|
| 1644 |
+
"content": "<|reserved_special_token_197|>",
|
| 1645 |
+
"lstrip": false,
|
| 1646 |
+
"normalized": false,
|
| 1647 |
+
"rstrip": false,
|
| 1648 |
+
"single_word": false,
|
| 1649 |
+
"special": true
|
| 1650 |
+
},
|
| 1651 |
+
"128206": {
|
| 1652 |
+
"content": "<|reserved_special_token_198|>",
|
| 1653 |
+
"lstrip": false,
|
| 1654 |
+
"normalized": false,
|
| 1655 |
+
"rstrip": false,
|
| 1656 |
+
"single_word": false,
|
| 1657 |
+
"special": true
|
| 1658 |
+
},
|
| 1659 |
+
"128207": {
|
| 1660 |
+
"content": "<|reserved_special_token_199|>",
|
| 1661 |
+
"lstrip": false,
|
| 1662 |
+
"normalized": false,
|
| 1663 |
+
"rstrip": false,
|
| 1664 |
+
"single_word": false,
|
| 1665 |
+
"special": true
|
| 1666 |
+
},
|
| 1667 |
+
"128208": {
|
| 1668 |
+
"content": "<|reserved_special_token_200|>",
|
| 1669 |
+
"lstrip": false,
|
| 1670 |
+
"normalized": false,
|
| 1671 |
+
"rstrip": false,
|
| 1672 |
+
"single_word": false,
|
| 1673 |
+
"special": true
|
| 1674 |
+
},
|
| 1675 |
+
"128209": {
|
| 1676 |
+
"content": "<|reserved_special_token_201|>",
|
| 1677 |
+
"lstrip": false,
|
| 1678 |
+
"normalized": false,
|
| 1679 |
+
"rstrip": false,
|
| 1680 |
+
"single_word": false,
|
| 1681 |
+
"special": true
|
| 1682 |
+
},
|
| 1683 |
+
"128210": {
|
| 1684 |
+
"content": "<|reserved_special_token_202|>",
|
| 1685 |
+
"lstrip": false,
|
| 1686 |
+
"normalized": false,
|
| 1687 |
+
"rstrip": false,
|
| 1688 |
+
"single_word": false,
|
| 1689 |
+
"special": true
|
| 1690 |
+
},
|
| 1691 |
+
"128211": {
|
| 1692 |
+
"content": "<|reserved_special_token_203|>",
|
| 1693 |
+
"lstrip": false,
|
| 1694 |
+
"normalized": false,
|
| 1695 |
+
"rstrip": false,
|
| 1696 |
+
"single_word": false,
|
| 1697 |
+
"special": true
|
| 1698 |
+
},
|
| 1699 |
+
"128212": {
|
| 1700 |
+
"content": "<|reserved_special_token_204|>",
|
| 1701 |
+
"lstrip": false,
|
| 1702 |
+
"normalized": false,
|
| 1703 |
+
"rstrip": false,
|
| 1704 |
+
"single_word": false,
|
| 1705 |
+
"special": true
|
| 1706 |
+
},
|
| 1707 |
+
"128213": {
|
| 1708 |
+
"content": "<|reserved_special_token_205|>",
|
| 1709 |
+
"lstrip": false,
|
| 1710 |
+
"normalized": false,
|
| 1711 |
+
"rstrip": false,
|
| 1712 |
+
"single_word": false,
|
| 1713 |
+
"special": true
|
| 1714 |
+
},
|
| 1715 |
+
"128214": {
|
| 1716 |
+
"content": "<|reserved_special_token_206|>",
|
| 1717 |
+
"lstrip": false,
|
| 1718 |
+
"normalized": false,
|
| 1719 |
+
"rstrip": false,
|
| 1720 |
+
"single_word": false,
|
| 1721 |
+
"special": true
|
| 1722 |
+
},
|
| 1723 |
+
"128215": {
|
| 1724 |
+
"content": "<|reserved_special_token_207|>",
|
| 1725 |
+
"lstrip": false,
|
| 1726 |
+
"normalized": false,
|
| 1727 |
+
"rstrip": false,
|
| 1728 |
+
"single_word": false,
|
| 1729 |
+
"special": true
|
| 1730 |
+
},
|
| 1731 |
+
"128216": {
|
| 1732 |
+
"content": "<|reserved_special_token_208|>",
|
| 1733 |
+
"lstrip": false,
|
| 1734 |
+
"normalized": false,
|
| 1735 |
+
"rstrip": false,
|
| 1736 |
+
"single_word": false,
|
| 1737 |
+
"special": true
|
| 1738 |
+
},
|
| 1739 |
+
"128217": {
|
| 1740 |
+
"content": "<|reserved_special_token_209|>",
|
| 1741 |
+
"lstrip": false,
|
| 1742 |
+
"normalized": false,
|
| 1743 |
+
"rstrip": false,
|
| 1744 |
+
"single_word": false,
|
| 1745 |
+
"special": true
|
| 1746 |
+
},
|
| 1747 |
+
"128218": {
|
| 1748 |
+
"content": "<|reserved_special_token_210|>",
|
| 1749 |
+
"lstrip": false,
|
| 1750 |
+
"normalized": false,
|
| 1751 |
+
"rstrip": false,
|
| 1752 |
+
"single_word": false,
|
| 1753 |
+
"special": true
|
| 1754 |
+
},
|
| 1755 |
+
"128219": {
|
| 1756 |
+
"content": "<|reserved_special_token_211|>",
|
| 1757 |
+
"lstrip": false,
|
| 1758 |
+
"normalized": false,
|
| 1759 |
+
"rstrip": false,
|
| 1760 |
+
"single_word": false,
|
| 1761 |
+
"special": true
|
| 1762 |
+
},
|
| 1763 |
+
"128220": {
|
| 1764 |
+
"content": "<|reserved_special_token_212|>",
|
| 1765 |
+
"lstrip": false,
|
| 1766 |
+
"normalized": false,
|
| 1767 |
+
"rstrip": false,
|
| 1768 |
+
"single_word": false,
|
| 1769 |
+
"special": true
|
| 1770 |
+
},
|
| 1771 |
+
"128221": {
|
| 1772 |
+
"content": "<|reserved_special_token_213|>",
|
| 1773 |
+
"lstrip": false,
|
| 1774 |
+
"normalized": false,
|
| 1775 |
+
"rstrip": false,
|
| 1776 |
+
"single_word": false,
|
| 1777 |
+
"special": true
|
| 1778 |
+
},
|
| 1779 |
+
"128222": {
|
| 1780 |
+
"content": "<|reserved_special_token_214|>",
|
| 1781 |
+
"lstrip": false,
|
| 1782 |
+
"normalized": false,
|
| 1783 |
+
"rstrip": false,
|
| 1784 |
+
"single_word": false,
|
| 1785 |
+
"special": true
|
| 1786 |
+
},
|
| 1787 |
+
"128223": {
|
| 1788 |
+
"content": "<|reserved_special_token_215|>",
|
| 1789 |
+
"lstrip": false,
|
| 1790 |
+
"normalized": false,
|
| 1791 |
+
"rstrip": false,
|
| 1792 |
+
"single_word": false,
|
| 1793 |
+
"special": true
|
| 1794 |
+
},
|
| 1795 |
+
"128224": {
|
| 1796 |
+
"content": "<|reserved_special_token_216|>",
|
| 1797 |
+
"lstrip": false,
|
| 1798 |
+
"normalized": false,
|
| 1799 |
+
"rstrip": false,
|
| 1800 |
+
"single_word": false,
|
| 1801 |
+
"special": true
|
| 1802 |
+
},
|
| 1803 |
+
"128225": {
|
| 1804 |
+
"content": "<|reserved_special_token_217|>",
|
| 1805 |
+
"lstrip": false,
|
| 1806 |
+
"normalized": false,
|
| 1807 |
+
"rstrip": false,
|
| 1808 |
+
"single_word": false,
|
| 1809 |
+
"special": true
|
| 1810 |
+
},
|
| 1811 |
+
"128226": {
|
| 1812 |
+
"content": "<|reserved_special_token_218|>",
|
| 1813 |
+
"lstrip": false,
|
| 1814 |
+
"normalized": false,
|
| 1815 |
+
"rstrip": false,
|
| 1816 |
+
"single_word": false,
|
| 1817 |
+
"special": true
|
| 1818 |
+
},
|
| 1819 |
+
"128227": {
|
| 1820 |
+
"content": "<|reserved_special_token_219|>",
|
| 1821 |
+
"lstrip": false,
|
| 1822 |
+
"normalized": false,
|
| 1823 |
+
"rstrip": false,
|
| 1824 |
+
"single_word": false,
|
| 1825 |
+
"special": true
|
| 1826 |
+
},
|
| 1827 |
+
"128228": {
|
| 1828 |
+
"content": "<|reserved_special_token_220|>",
|
| 1829 |
+
"lstrip": false,
|
| 1830 |
+
"normalized": false,
|
| 1831 |
+
"rstrip": false,
|
| 1832 |
+
"single_word": false,
|
| 1833 |
+
"special": true
|
| 1834 |
+
},
|
| 1835 |
+
"128229": {
|
| 1836 |
+
"content": "<|reserved_special_token_221|>",
|
| 1837 |
+
"lstrip": false,
|
| 1838 |
+
"normalized": false,
|
| 1839 |
+
"rstrip": false,
|
| 1840 |
+
"single_word": false,
|
| 1841 |
+
"special": true
|
| 1842 |
+
},
|
| 1843 |
+
"128230": {
|
| 1844 |
+
"content": "<|reserved_special_token_222|>",
|
| 1845 |
+
"lstrip": false,
|
| 1846 |
+
"normalized": false,
|
| 1847 |
+
"rstrip": false,
|
| 1848 |
+
"single_word": false,
|
| 1849 |
+
"special": true
|
| 1850 |
+
},
|
| 1851 |
+
"128231": {
|
| 1852 |
+
"content": "<|reserved_special_token_223|>",
|
| 1853 |
+
"lstrip": false,
|
| 1854 |
+
"normalized": false,
|
| 1855 |
+
"rstrip": false,
|
| 1856 |
+
"single_word": false,
|
| 1857 |
+
"special": true
|
| 1858 |
+
},
|
| 1859 |
+
"128232": {
|
| 1860 |
+
"content": "<|reserved_special_token_224|>",
|
| 1861 |
+
"lstrip": false,
|
| 1862 |
+
"normalized": false,
|
| 1863 |
+
"rstrip": false,
|
| 1864 |
+
"single_word": false,
|
| 1865 |
+
"special": true
|
| 1866 |
+
},
|
| 1867 |
+
"128233": {
|
| 1868 |
+
"content": "<|reserved_special_token_225|>",
|
| 1869 |
+
"lstrip": false,
|
| 1870 |
+
"normalized": false,
|
| 1871 |
+
"rstrip": false,
|
| 1872 |
+
"single_word": false,
|
| 1873 |
+
"special": true
|
| 1874 |
+
},
|
| 1875 |
+
"128234": {
|
| 1876 |
+
"content": "<|reserved_special_token_226|>",
|
| 1877 |
+
"lstrip": false,
|
| 1878 |
+
"normalized": false,
|
| 1879 |
+
"rstrip": false,
|
| 1880 |
+
"single_word": false,
|
| 1881 |
+
"special": true
|
| 1882 |
+
},
|
| 1883 |
+
"128235": {
|
| 1884 |
+
"content": "<|reserved_special_token_227|>",
|
| 1885 |
+
"lstrip": false,
|
| 1886 |
+
"normalized": false,
|
| 1887 |
+
"rstrip": false,
|
| 1888 |
+
"single_word": false,
|
| 1889 |
+
"special": true
|
| 1890 |
+
},
|
| 1891 |
+
"128236": {
|
| 1892 |
+
"content": "<|reserved_special_token_228|>",
|
| 1893 |
+
"lstrip": false,
|
| 1894 |
+
"normalized": false,
|
| 1895 |
+
"rstrip": false,
|
| 1896 |
+
"single_word": false,
|
| 1897 |
+
"special": true
|
| 1898 |
+
},
|
| 1899 |
+
"128237": {
|
| 1900 |
+
"content": "<|reserved_special_token_229|>",
|
| 1901 |
+
"lstrip": false,
|
| 1902 |
+
"normalized": false,
|
| 1903 |
+
"rstrip": false,
|
| 1904 |
+
"single_word": false,
|
| 1905 |
+
"special": true
|
| 1906 |
+
},
|
| 1907 |
+
"128238": {
|
| 1908 |
+
"content": "<|reserved_special_token_230|>",
|
| 1909 |
+
"lstrip": false,
|
| 1910 |
+
"normalized": false,
|
| 1911 |
+
"rstrip": false,
|
| 1912 |
+
"single_word": false,
|
| 1913 |
+
"special": true
|
| 1914 |
+
},
|
| 1915 |
+
"128239": {
|
| 1916 |
+
"content": "<|reserved_special_token_231|>",
|
| 1917 |
+
"lstrip": false,
|
| 1918 |
+
"normalized": false,
|
| 1919 |
+
"rstrip": false,
|
| 1920 |
+
"single_word": false,
|
| 1921 |
+
"special": true
|
| 1922 |
+
},
|
| 1923 |
+
"128240": {
|
| 1924 |
+
"content": "<|reserved_special_token_232|>",
|
| 1925 |
+
"lstrip": false,
|
| 1926 |
+
"normalized": false,
|
| 1927 |
+
"rstrip": false,
|
| 1928 |
+
"single_word": false,
|
| 1929 |
+
"special": true
|
| 1930 |
+
},
|
| 1931 |
+
"128241": {
|
| 1932 |
+
"content": "<|reserved_special_token_233|>",
|
| 1933 |
+
"lstrip": false,
|
| 1934 |
+
"normalized": false,
|
| 1935 |
+
"rstrip": false,
|
| 1936 |
+
"single_word": false,
|
| 1937 |
+
"special": true
|
| 1938 |
+
},
|
| 1939 |
+
"128242": {
|
| 1940 |
+
"content": "<|reserved_special_token_234|>",
|
| 1941 |
+
"lstrip": false,
|
| 1942 |
+
"normalized": false,
|
| 1943 |
+
"rstrip": false,
|
| 1944 |
+
"single_word": false,
|
| 1945 |
+
"special": true
|
| 1946 |
+
},
|
| 1947 |
+
"128243": {
|
| 1948 |
+
"content": "<|reserved_special_token_235|>",
|
| 1949 |
+
"lstrip": false,
|
| 1950 |
+
"normalized": false,
|
| 1951 |
+
"rstrip": false,
|
| 1952 |
+
"single_word": false,
|
| 1953 |
+
"special": true
|
| 1954 |
+
},
|
| 1955 |
+
"128244": {
|
| 1956 |
+
"content": "<|reserved_special_token_236|>",
|
| 1957 |
+
"lstrip": false,
|
| 1958 |
+
"normalized": false,
|
| 1959 |
+
"rstrip": false,
|
| 1960 |
+
"single_word": false,
|
| 1961 |
+
"special": true
|
| 1962 |
+
},
|
| 1963 |
+
"128245": {
|
| 1964 |
+
"content": "<|reserved_special_token_237|>",
|
| 1965 |
+
"lstrip": false,
|
| 1966 |
+
"normalized": false,
|
| 1967 |
+
"rstrip": false,
|
| 1968 |
+
"single_word": false,
|
| 1969 |
+
"special": true
|
| 1970 |
+
},
|
| 1971 |
+
"128246": {
|
| 1972 |
+
"content": "<|reserved_special_token_238|>",
|
| 1973 |
+
"lstrip": false,
|
| 1974 |
+
"normalized": false,
|
| 1975 |
+
"rstrip": false,
|
| 1976 |
+
"single_word": false,
|
| 1977 |
+
"special": true
|
| 1978 |
+
},
|
| 1979 |
+
"128247": {
|
| 1980 |
+
"content": "<|reserved_special_token_239|>",
|
| 1981 |
+
"lstrip": false,
|
| 1982 |
+
"normalized": false,
|
| 1983 |
+
"rstrip": false,
|
| 1984 |
+
"single_word": false,
|
| 1985 |
+
"special": true
|
| 1986 |
+
},
|
| 1987 |
+
"128248": {
|
| 1988 |
+
"content": "<|reserved_special_token_240|>",
|
| 1989 |
+
"lstrip": false,
|
| 1990 |
+
"normalized": false,
|
| 1991 |
+
"rstrip": false,
|
| 1992 |
+
"single_word": false,
|
| 1993 |
+
"special": true
|
| 1994 |
+
},
|
| 1995 |
+
"128249": {
|
| 1996 |
+
"content": "<|reserved_special_token_241|>",
|
| 1997 |
+
"lstrip": false,
|
| 1998 |
+
"normalized": false,
|
| 1999 |
+
"rstrip": false,
|
| 2000 |
+
"single_word": false,
|
| 2001 |
+
"special": true
|
| 2002 |
+
},
|
| 2003 |
+
"128250": {
|
| 2004 |
+
"content": "<|reserved_special_token_242|>",
|
| 2005 |
+
"lstrip": false,
|
| 2006 |
+
"normalized": false,
|
| 2007 |
+
"rstrip": false,
|
| 2008 |
+
"single_word": false,
|
| 2009 |
+
"special": true
|
| 2010 |
+
},
|
| 2011 |
+
"128251": {
|
| 2012 |
+
"content": "<|reserved_special_token_243|>",
|
| 2013 |
+
"lstrip": false,
|
| 2014 |
+
"normalized": false,
|
| 2015 |
+
"rstrip": false,
|
| 2016 |
+
"single_word": false,
|
| 2017 |
+
"special": true
|
| 2018 |
+
},
|
| 2019 |
+
"128252": {
|
| 2020 |
+
"content": "<|reserved_special_token_244|>",
|
| 2021 |
+
"lstrip": false,
|
| 2022 |
+
"normalized": false,
|
| 2023 |
+
"rstrip": false,
|
| 2024 |
+
"single_word": false,
|
| 2025 |
+
"special": true
|
| 2026 |
+
},
|
| 2027 |
+
"128253": {
|
| 2028 |
+
"content": "<|reserved_special_token_245|>",
|
| 2029 |
+
"lstrip": false,
|
| 2030 |
+
"normalized": false,
|
| 2031 |
+
"rstrip": false,
|
| 2032 |
+
"single_word": false,
|
| 2033 |
+
"special": true
|
| 2034 |
+
},
|
| 2035 |
+
"128254": {
|
| 2036 |
+
"content": "<|reserved_special_token_246|>",
|
| 2037 |
+
"lstrip": false,
|
| 2038 |
+
"normalized": false,
|
| 2039 |
+
"rstrip": false,
|
| 2040 |
+
"single_word": false,
|
| 2041 |
+
"special": true
|
| 2042 |
+
},
|
| 2043 |
+
"128255": {
|
| 2044 |
+
"content": "<|reserved_special_token_247|>",
|
| 2045 |
+
"lstrip": false,
|
| 2046 |
+
"normalized": false,
|
| 2047 |
+
"rstrip": false,
|
| 2048 |
+
"single_word": false,
|
| 2049 |
+
"special": true
|
| 2050 |
+
}
|
| 2051 |
+
},
|
| 2052 |
+
"bos_token": "<|begin_of_text|>",
|
| 2053 |
+
"chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{% endif %}",
|
| 2054 |
+
"clean_up_tokenization_spaces": true,
|
| 2055 |
+
"eos_token": "<|eot_id|>",
|
| 2056 |
+
"model_input_names": [
|
| 2057 |
+
"input_ids",
|
| 2058 |
+
"attention_mask"
|
| 2059 |
+
],
|
| 2060 |
+
"model_max_length": 131072,
|
| 2061 |
+
"pad_token": "<|finetune_right_pad_id|>",
|
| 2062 |
+
"padding_side": "right",
|
| 2063 |
+
"tokenizer_class": "PreTrainedTokenizerFast"
|
| 2064 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,2313 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 1.9934426229508198,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 152,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.013114754098360656,
|
| 13 |
+
"grad_norm": NaN,
|
| 14 |
+
"learning_rate": 0.0,
|
| 15 |
+
"logits/chosen": -0.7201688289642334,
|
| 16 |
+
"logits/rejected": -0.25958356261253357,
|
| 17 |
+
"logps/chosen": -235.22982788085938,
|
| 18 |
+
"logps/rejected": -110.77284240722656,
|
| 19 |
+
"loss": 0.6931,
|
| 20 |
+
"rewards/accuracies": 0.0,
|
| 21 |
+
"rewards/chosen": 0.0,
|
| 22 |
+
"rewards/margins": 0.0,
|
| 23 |
+
"rewards/rejected": 0.0,
|
| 24 |
+
"step": 1
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.02622950819672131,
|
| 28 |
+
"grad_norm": NaN,
|
| 29 |
+
"learning_rate": 0.0,
|
| 30 |
+
"logits/chosen": -0.6440946459770203,
|
| 31 |
+
"logits/rejected": -0.8803070783615112,
|
| 32 |
+
"logps/chosen": -233.35064697265625,
|
| 33 |
+
"logps/rejected": -270.211669921875,
|
| 34 |
+
"loss": 0.6931,
|
| 35 |
+
"rewards/accuracies": 0.0,
|
| 36 |
+
"rewards/chosen": 0.0,
|
| 37 |
+
"rewards/margins": 0.0,
|
| 38 |
+
"rewards/rejected": 0.0,
|
| 39 |
+
"step": 2
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.03934426229508197,
|
| 43 |
+
"grad_norm": Infinity,
|
| 44 |
+
"learning_rate": 0.0,
|
| 45 |
+
"logits/chosen": -0.3529421091079712,
|
| 46 |
+
"logits/rejected": -0.46579116582870483,
|
| 47 |
+
"logps/chosen": -283.93499755859375,
|
| 48 |
+
"logps/rejected": -236.17298889160156,
|
| 49 |
+
"loss": 0.6931,
|
| 50 |
+
"rewards/accuracies": 0.0,
|
| 51 |
+
"rewards/chosen": 0.0,
|
| 52 |
+
"rewards/margins": 0.0,
|
| 53 |
+
"rewards/rejected": 0.0,
|
| 54 |
+
"step": 3
|
| 55 |
+
},
|
| 56 |
+
{
|
| 57 |
+
"epoch": 0.05245901639344262,
|
| 58 |
+
"grad_norm": 116.6382827758789,
|
| 59 |
+
"learning_rate": 3.125e-07,
|
| 60 |
+
"logits/chosen": -0.6149371862411499,
|
| 61 |
+
"logits/rejected": -0.6765552163124084,
|
| 62 |
+
"logps/chosen": -330.7442321777344,
|
| 63 |
+
"logps/rejected": -333.74853515625,
|
| 64 |
+
"loss": 0.6931,
|
| 65 |
+
"rewards/accuracies": 0.0,
|
| 66 |
+
"rewards/chosen": 0.0,
|
| 67 |
+
"rewards/margins": 0.0,
|
| 68 |
+
"rewards/rejected": 0.0,
|
| 69 |
+
"step": 4
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 0.06557377049180328,
|
| 73 |
+
"grad_norm": 96.14250946044922,
|
| 74 |
+
"learning_rate": 6.25e-07,
|
| 75 |
+
"logits/chosen": -0.48342880606651306,
|
| 76 |
+
"logits/rejected": -0.552554190158844,
|
| 77 |
+
"logps/chosen": -224.43968200683594,
|
| 78 |
+
"logps/rejected": -243.84121704101562,
|
| 79 |
+
"loss": 0.6931,
|
| 80 |
+
"rewards/accuracies": 0.0,
|
| 81 |
+
"rewards/chosen": 0.0,
|
| 82 |
+
"rewards/margins": 0.0,
|
| 83 |
+
"rewards/rejected": 0.0,
|
| 84 |
+
"step": 5
|
| 85 |
+
},
|
| 86 |
+
{
|
| 87 |
+
"epoch": 0.07868852459016394,
|
| 88 |
+
"grad_norm": 119.71466064453125,
|
| 89 |
+
"learning_rate": 9.375000000000001e-07,
|
| 90 |
+
"logits/chosen": -0.4438214600086212,
|
| 91 |
+
"logits/rejected": -0.41411423683166504,
|
| 92 |
+
"logps/chosen": -509.1705322265625,
|
| 93 |
+
"logps/rejected": -331.69927978515625,
|
| 94 |
+
"loss": 0.6942,
|
| 95 |
+
"rewards/accuracies": 0.5,
|
| 96 |
+
"rewards/chosen": -0.005420684814453125,
|
| 97 |
+
"rewards/margins": -0.0020191192161291838,
|
| 98 |
+
"rewards/rejected": -0.0034015655983239412,
|
| 99 |
+
"step": 6
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 0.09180327868852459,
|
| 103 |
+
"grad_norm": 89.92263793945312,
|
| 104 |
+
"learning_rate": 1.25e-06,
|
| 105 |
+
"logits/chosen": -0.5990754961967468,
|
| 106 |
+
"logits/rejected": -0.5052899718284607,
|
| 107 |
+
"logps/chosen": -353.8023376464844,
|
| 108 |
+
"logps/rejected": -293.9719543457031,
|
| 109 |
+
"loss": 0.6924,
|
| 110 |
+
"rewards/accuracies": 0.75,
|
| 111 |
+
"rewards/chosen": 0.0021602632477879524,
|
| 112 |
+
"rewards/margins": 0.001445007394067943,
|
| 113 |
+
"rewards/rejected": 0.0007152557955123484,
|
| 114 |
+
"step": 7
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.10491803278688525,
|
| 118 |
+
"grad_norm": 91.0330810546875,
|
| 119 |
+
"learning_rate": 1.5625e-06,
|
| 120 |
+
"logits/chosen": -0.7285553216934204,
|
| 121 |
+
"logits/rejected": -0.8203944563865662,
|
| 122 |
+
"logps/chosen": -201.29092407226562,
|
| 123 |
+
"logps/rejected": -310.0835876464844,
|
| 124 |
+
"loss": 0.6923,
|
| 125 |
+
"rewards/accuracies": 0.75,
|
| 126 |
+
"rewards/chosen": -0.0027733801398426294,
|
| 127 |
+
"rewards/margins": 0.00168361677788198,
|
| 128 |
+
"rewards/rejected": -0.004456996917724609,
|
| 129 |
+
"step": 8
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.1180327868852459,
|
| 133 |
+
"grad_norm": 115.72259521484375,
|
| 134 |
+
"learning_rate": 1.8750000000000003e-06,
|
| 135 |
+
"logits/chosen": -0.6387780904769897,
|
| 136 |
+
"logits/rejected": -0.4966055750846863,
|
| 137 |
+
"logps/chosen": -286.18316650390625,
|
| 138 |
+
"logps/rejected": -174.62039184570312,
|
| 139 |
+
"loss": 0.6924,
|
| 140 |
+
"rewards/accuracies": 0.75,
|
| 141 |
+
"rewards/chosen": -0.008039474487304688,
|
| 142 |
+
"rewards/margins": 0.0014192580711096525,
|
| 143 |
+
"rewards/rejected": -0.009458731859922409,
|
| 144 |
+
"step": 9
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 0.13114754098360656,
|
| 148 |
+
"grad_norm": 81.71347045898438,
|
| 149 |
+
"learning_rate": 2.1875000000000002e-06,
|
| 150 |
+
"logits/chosen": -0.43023377656936646,
|
| 151 |
+
"logits/rejected": -0.4917900860309601,
|
| 152 |
+
"logps/chosen": -123.80950164794922,
|
| 153 |
+
"logps/rejected": -231.78781127929688,
|
| 154 |
+
"loss": 0.6922,
|
| 155 |
+
"rewards/accuracies": 0.25,
|
| 156 |
+
"rewards/chosen": -0.013120556250214577,
|
| 157 |
+
"rewards/margins": 0.001862620934844017,
|
| 158 |
+
"rewards/rejected": -0.014983177185058594,
|
| 159 |
+
"step": 10
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 0.14426229508196722,
|
| 163 |
+
"grad_norm": 126.95443725585938,
|
| 164 |
+
"learning_rate": 2.5e-06,
|
| 165 |
+
"logits/chosen": -0.5431928634643555,
|
| 166 |
+
"logits/rejected": -0.6928932666778564,
|
| 167 |
+
"logps/chosen": -466.6590881347656,
|
| 168 |
+
"logps/rejected": -450.839111328125,
|
| 169 |
+
"loss": 0.6835,
|
| 170 |
+
"rewards/accuracies": 0.75,
|
| 171 |
+
"rewards/chosen": 0.003947257064282894,
|
| 172 |
+
"rewards/margins": 0.01957416534423828,
|
| 173 |
+
"rewards/rejected": -0.015626907348632812,
|
| 174 |
+
"step": 11
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 0.15737704918032788,
|
| 178 |
+
"grad_norm": 106.9858169555664,
|
| 179 |
+
"learning_rate": 2.8125e-06,
|
| 180 |
+
"logits/chosen": -0.8515354990959167,
|
| 181 |
+
"logits/rejected": -0.8400233387947083,
|
| 182 |
+
"logps/chosen": -496.6812438964844,
|
| 183 |
+
"logps/rejected": -367.9149169921875,
|
| 184 |
+
"loss": 0.6932,
|
| 185 |
+
"rewards/accuracies": 0.5,
|
| 186 |
+
"rewards/chosen": -0.013410568237304688,
|
| 187 |
+
"rewards/margins": 0.0008895890787243843,
|
| 188 |
+
"rewards/rejected": -0.014300156384706497,
|
| 189 |
+
"step": 12
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 0.17049180327868851,
|
| 193 |
+
"grad_norm": 94.6556167602539,
|
| 194 |
+
"learning_rate": 3.125e-06,
|
| 195 |
+
"logits/chosen": -0.8845179080963135,
|
| 196 |
+
"logits/rejected": -0.8273138403892517,
|
| 197 |
+
"logps/chosen": -332.0273742675781,
|
| 198 |
+
"logps/rejected": -263.0736389160156,
|
| 199 |
+
"loss": 0.6739,
|
| 200 |
+
"rewards/accuracies": 0.75,
|
| 201 |
+
"rewards/chosen": -0.0007216455414891243,
|
| 202 |
+
"rewards/margins": 0.03937549516558647,
|
| 203 |
+
"rewards/rejected": -0.04009714350104332,
|
| 204 |
+
"step": 13
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 0.18360655737704917,
|
| 208 |
+
"grad_norm": 110.63664245605469,
|
| 209 |
+
"learning_rate": 3.4375e-06,
|
| 210 |
+
"logits/chosen": -0.49672091007232666,
|
| 211 |
+
"logits/rejected": -0.7252901792526245,
|
| 212 |
+
"logps/chosen": -182.361572265625,
|
| 213 |
+
"logps/rejected": -378.4778747558594,
|
| 214 |
+
"loss": 0.6764,
|
| 215 |
+
"rewards/accuracies": 0.5,
|
| 216 |
+
"rewards/chosen": -0.03787527605891228,
|
| 217 |
+
"rewards/margins": 0.0358370766043663,
|
| 218 |
+
"rewards/rejected": -0.07371234893798828,
|
| 219 |
+
"step": 14
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.19672131147540983,
|
| 223 |
+
"grad_norm": 76.27680969238281,
|
| 224 |
+
"learning_rate": 3.7500000000000005e-06,
|
| 225 |
+
"logits/chosen": -0.5162211656570435,
|
| 226 |
+
"logits/rejected": -0.4975786507129669,
|
| 227 |
+
"logps/chosen": -179.30902099609375,
|
| 228 |
+
"logps/rejected": -132.12823486328125,
|
| 229 |
+
"loss": 0.6905,
|
| 230 |
+
"rewards/accuracies": 0.75,
|
| 231 |
+
"rewards/chosen": -0.037923429161310196,
|
| 232 |
+
"rewards/margins": 0.005405997391790152,
|
| 233 |
+
"rewards/rejected": -0.04332943260669708,
|
| 234 |
+
"step": 15
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.2098360655737705,
|
| 238 |
+
"grad_norm": 91.94597625732422,
|
| 239 |
+
"learning_rate": 4.0625000000000005e-06,
|
| 240 |
+
"logits/chosen": -0.3636321425437927,
|
| 241 |
+
"logits/rejected": -0.6324741840362549,
|
| 242 |
+
"logps/chosen": -153.548828125,
|
| 243 |
+
"logps/rejected": -371.84765625,
|
| 244 |
+
"loss": 0.713,
|
| 245 |
+
"rewards/accuracies": 0.25,
|
| 246 |
+
"rewards/chosen": -0.06001920625567436,
|
| 247 |
+
"rewards/margins": -0.038457777351140976,
|
| 248 |
+
"rewards/rejected": -0.021561432629823685,
|
| 249 |
+
"step": 16
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 0.22295081967213115,
|
| 253 |
+
"grad_norm": 75.85398864746094,
|
| 254 |
+
"learning_rate": 4.3750000000000005e-06,
|
| 255 |
+
"logits/chosen": -0.5712193250656128,
|
| 256 |
+
"logits/rejected": -0.3860137164592743,
|
| 257 |
+
"logps/chosen": -267.605224609375,
|
| 258 |
+
"logps/rejected": -104.8357162475586,
|
| 259 |
+
"loss": 0.6921,
|
| 260 |
+
"rewards/accuracies": 0.5,
|
| 261 |
+
"rewards/chosen": -0.022034931927919388,
|
| 262 |
+
"rewards/margins": 0.0022784238681197166,
|
| 263 |
+
"rewards/rejected": -0.02431335672736168,
|
| 264 |
+
"step": 17
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 0.2360655737704918,
|
| 268 |
+
"grad_norm": 117.28124237060547,
|
| 269 |
+
"learning_rate": 4.6875000000000004e-06,
|
| 270 |
+
"logits/chosen": -0.5285807251930237,
|
| 271 |
+
"logits/rejected": -0.3493229150772095,
|
| 272 |
+
"logps/chosen": -380.4576416015625,
|
| 273 |
+
"logps/rejected": -311.0014343261719,
|
| 274 |
+
"loss": 0.7359,
|
| 275 |
+
"rewards/accuracies": 0.5,
|
| 276 |
+
"rewards/chosen": -0.16734714806079865,
|
| 277 |
+
"rewards/margins": -0.07893352955579758,
|
| 278 |
+
"rewards/rejected": -0.08841361850500107,
|
| 279 |
+
"step": 18
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 0.24918032786885247,
|
| 283 |
+
"grad_norm": 90.01153564453125,
|
| 284 |
+
"learning_rate": 5e-06,
|
| 285 |
+
"logits/chosen": -0.6711679697036743,
|
| 286 |
+
"logits/rejected": -0.2690754532814026,
|
| 287 |
+
"logps/chosen": -462.41973876953125,
|
| 288 |
+
"logps/rejected": -297.78363037109375,
|
| 289 |
+
"loss": 0.6435,
|
| 290 |
+
"rewards/accuracies": 0.75,
|
| 291 |
+
"rewards/chosen": -0.0683719664812088,
|
| 292 |
+
"rewards/margins": 0.10821684449911118,
|
| 293 |
+
"rewards/rejected": -0.17658883333206177,
|
| 294 |
+
"step": 19
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 0.26229508196721313,
|
| 298 |
+
"grad_norm": 73.38824462890625,
|
| 299 |
+
"learning_rate": 4.9632352941176475e-06,
|
| 300 |
+
"logits/chosen": -0.6787087917327881,
|
| 301 |
+
"logits/rejected": -0.6652618050575256,
|
| 302 |
+
"logps/chosen": -361.91131591796875,
|
| 303 |
+
"logps/rejected": -243.35589599609375,
|
| 304 |
+
"loss": 0.6319,
|
| 305 |
+
"rewards/accuracies": 1.0,
|
| 306 |
+
"rewards/chosen": 0.04816999286413193,
|
| 307 |
+
"rewards/margins": 0.12730780243873596,
|
| 308 |
+
"rewards/rejected": -0.07913780957460403,
|
| 309 |
+
"step": 20
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 0.2754098360655738,
|
| 313 |
+
"grad_norm": 115.89125061035156,
|
| 314 |
+
"learning_rate": 4.9264705882352945e-06,
|
| 315 |
+
"logits/chosen": -0.3588840365409851,
|
| 316 |
+
"logits/rejected": -0.2116285115480423,
|
| 317 |
+
"logps/chosen": -400.4305419921875,
|
| 318 |
+
"logps/rejected": -362.8456726074219,
|
| 319 |
+
"loss": 0.6087,
|
| 320 |
+
"rewards/accuracies": 1.0,
|
| 321 |
+
"rewards/chosen": 0.10708275437355042,
|
| 322 |
+
"rewards/margins": 0.1842678040266037,
|
| 323 |
+
"rewards/rejected": -0.07718505710363388,
|
| 324 |
+
"step": 21
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.28852459016393445,
|
| 328 |
+
"grad_norm": 78.77503204345703,
|
| 329 |
+
"learning_rate": 4.889705882352942e-06,
|
| 330 |
+
"logits/chosen": -0.8203290700912476,
|
| 331 |
+
"logits/rejected": -0.8240777254104614,
|
| 332 |
+
"logps/chosen": -166.8377685546875,
|
| 333 |
+
"logps/rejected": -170.83688354492188,
|
| 334 |
+
"loss": 0.7257,
|
| 335 |
+
"rewards/accuracies": 0.5,
|
| 336 |
+
"rewards/chosen": -0.06841621547937393,
|
| 337 |
+
"rewards/margins": -0.061698053032159805,
|
| 338 |
+
"rewards/rejected": -0.0067181577906012535,
|
| 339 |
+
"step": 22
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.3016393442622951,
|
| 343 |
+
"grad_norm": 121.3331527709961,
|
| 344 |
+
"learning_rate": 4.852941176470589e-06,
|
| 345 |
+
"logits/chosen": -0.2023768126964569,
|
| 346 |
+
"logits/rejected": 0.14346128702163696,
|
| 347 |
+
"logps/chosen": -404.2669677734375,
|
| 348 |
+
"logps/rejected": -286.7450256347656,
|
| 349 |
+
"loss": 0.6238,
|
| 350 |
+
"rewards/accuracies": 0.75,
|
| 351 |
+
"rewards/chosen": 0.12858295440673828,
|
| 352 |
+
"rewards/margins": 0.14947663247585297,
|
| 353 |
+
"rewards/rejected": -0.020893670618534088,
|
| 354 |
+
"step": 23
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 0.31475409836065577,
|
| 358 |
+
"grad_norm": 103.55362701416016,
|
| 359 |
+
"learning_rate": 4.816176470588236e-06,
|
| 360 |
+
"logits/chosen": -0.5769512057304382,
|
| 361 |
+
"logits/rejected": -0.7388426661491394,
|
| 362 |
+
"logps/chosen": -483.7005310058594,
|
| 363 |
+
"logps/rejected": -367.4910583496094,
|
| 364 |
+
"loss": 0.5843,
|
| 365 |
+
"rewards/accuracies": 1.0,
|
| 366 |
+
"rewards/chosen": 0.05827799811959267,
|
| 367 |
+
"rewards/margins": 0.27695170044898987,
|
| 368 |
+
"rewards/rejected": -0.2186737060546875,
|
| 369 |
+
"step": 24
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 0.32786885245901637,
|
| 373 |
+
"grad_norm": 72.6626205444336,
|
| 374 |
+
"learning_rate": 4.779411764705883e-06,
|
| 375 |
+
"logits/chosen": -0.7255613803863525,
|
| 376 |
+
"logits/rejected": -0.884934663772583,
|
| 377 |
+
"logps/chosen": -183.0727081298828,
|
| 378 |
+
"logps/rejected": -202.55877685546875,
|
| 379 |
+
"loss": 0.6588,
|
| 380 |
+
"rewards/accuracies": 0.75,
|
| 381 |
+
"rewards/chosen": 0.0200653113424778,
|
| 382 |
+
"rewards/margins": 0.09606742858886719,
|
| 383 |
+
"rewards/rejected": -0.07600211352109909,
|
| 384 |
+
"step": 25
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 0.34098360655737703,
|
| 388 |
+
"grad_norm": 88.45654296875,
|
| 389 |
+
"learning_rate": 4.74264705882353e-06,
|
| 390 |
+
"logits/chosen": -0.5392031073570251,
|
| 391 |
+
"logits/rejected": -0.7600653171539307,
|
| 392 |
+
"logps/chosen": -405.0447998046875,
|
| 393 |
+
"logps/rejected": -448.3751220703125,
|
| 394 |
+
"loss": 0.5453,
|
| 395 |
+
"rewards/accuracies": 1.0,
|
| 396 |
+
"rewards/chosen": 0.170909121632576,
|
| 397 |
+
"rewards/margins": 0.33048784732818604,
|
| 398 |
+
"rewards/rejected": -0.15957871079444885,
|
| 399 |
+
"step": 26
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 0.3540983606557377,
|
| 403 |
+
"grad_norm": 72.38986206054688,
|
| 404 |
+
"learning_rate": 4.705882352941177e-06,
|
| 405 |
+
"logits/chosen": -0.8080704212188721,
|
| 406 |
+
"logits/rejected": -0.4376976788043976,
|
| 407 |
+
"logps/chosen": -242.55665588378906,
|
| 408 |
+
"logps/rejected": -131.02154541015625,
|
| 409 |
+
"loss": 0.7378,
|
| 410 |
+
"rewards/accuracies": 0.75,
|
| 411 |
+
"rewards/chosen": -0.07056399434804916,
|
| 412 |
+
"rewards/margins": -0.06801767647266388,
|
| 413 |
+
"rewards/rejected": -0.0025463104248046875,
|
| 414 |
+
"step": 27
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"epoch": 0.36721311475409835,
|
| 418 |
+
"grad_norm": 89.0915298461914,
|
| 419 |
+
"learning_rate": 4.669117647058824e-06,
|
| 420 |
+
"logits/chosen": -0.7039719820022583,
|
| 421 |
+
"logits/rejected": -0.45313090085983276,
|
| 422 |
+
"logps/chosen": -357.1167297363281,
|
| 423 |
+
"logps/rejected": -254.34747314453125,
|
| 424 |
+
"loss": 0.6511,
|
| 425 |
+
"rewards/accuracies": 0.5,
|
| 426 |
+
"rewards/chosen": 0.1653575897216797,
|
| 427 |
+
"rewards/margins": 0.11446285247802734,
|
| 428 |
+
"rewards/rejected": 0.050894737243652344,
|
| 429 |
+
"step": 28
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.380327868852459,
|
| 433 |
+
"grad_norm": 72.88048553466797,
|
| 434 |
+
"learning_rate": 4.632352941176471e-06,
|
| 435 |
+
"logits/chosen": -0.4176654815673828,
|
| 436 |
+
"logits/rejected": -0.8021068572998047,
|
| 437 |
+
"logps/chosen": -118.46458435058594,
|
| 438 |
+
"logps/rejected": -266.1793518066406,
|
| 439 |
+
"loss": 0.6207,
|
| 440 |
+
"rewards/accuracies": 0.5,
|
| 441 |
+
"rewards/chosen": -0.03454189747571945,
|
| 442 |
+
"rewards/margins": 0.17219945788383484,
|
| 443 |
+
"rewards/rejected": -0.2067413479089737,
|
| 444 |
+
"step": 29
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 0.39344262295081966,
|
| 448 |
+
"grad_norm": 112.41997528076172,
|
| 449 |
+
"learning_rate": 4.595588235294118e-06,
|
| 450 |
+
"logits/chosen": -0.5515627264976501,
|
| 451 |
+
"logits/rejected": -0.3022332489490509,
|
| 452 |
+
"logps/chosen": -383.1882629394531,
|
| 453 |
+
"logps/rejected": -355.9986877441406,
|
| 454 |
+
"loss": 0.7112,
|
| 455 |
+
"rewards/accuracies": 0.25,
|
| 456 |
+
"rewards/chosen": 0.12149354070425034,
|
| 457 |
+
"rewards/margins": 0.018218979239463806,
|
| 458 |
+
"rewards/rejected": 0.10327454656362534,
|
| 459 |
+
"step": 30
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 0.4065573770491803,
|
| 463 |
+
"grad_norm": 99.6341781616211,
|
| 464 |
+
"learning_rate": 4.558823529411765e-06,
|
| 465 |
+
"logits/chosen": -0.32010310888290405,
|
| 466 |
+
"logits/rejected": -0.34287354350090027,
|
| 467 |
+
"logps/chosen": -433.3697509765625,
|
| 468 |
+
"logps/rejected": -427.46868896484375,
|
| 469 |
+
"loss": 0.5341,
|
| 470 |
+
"rewards/accuracies": 1.0,
|
| 471 |
+
"rewards/chosen": 0.1381477415561676,
|
| 472 |
+
"rewards/margins": 0.3722812533378601,
|
| 473 |
+
"rewards/rejected": -0.2341335415840149,
|
| 474 |
+
"step": 31
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 0.419672131147541,
|
| 478 |
+
"grad_norm": 141.9149932861328,
|
| 479 |
+
"learning_rate": 4.522058823529412e-06,
|
| 480 |
+
"logits/chosen": -0.3783895969390869,
|
| 481 |
+
"logits/rejected": -0.22028671205043793,
|
| 482 |
+
"logps/chosen": -438.865478515625,
|
| 483 |
+
"logps/rejected": -378.45306396484375,
|
| 484 |
+
"loss": 0.7389,
|
| 485 |
+
"rewards/accuracies": 0.75,
|
| 486 |
+
"rewards/chosen": -0.20297011733055115,
|
| 487 |
+
"rewards/margins": -0.03645037114620209,
|
| 488 |
+
"rewards/rejected": -0.16651973128318787,
|
| 489 |
+
"step": 32
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 0.43278688524590164,
|
| 493 |
+
"grad_norm": 83.45268249511719,
|
| 494 |
+
"learning_rate": 4.485294117647059e-06,
|
| 495 |
+
"logits/chosen": -0.4643877446651459,
|
| 496 |
+
"logits/rejected": -0.23612239956855774,
|
| 497 |
+
"logps/chosen": -323.2715148925781,
|
| 498 |
+
"logps/rejected": -257.071533203125,
|
| 499 |
+
"loss": 0.6477,
|
| 500 |
+
"rewards/accuracies": 0.5,
|
| 501 |
+
"rewards/chosen": 0.06585502624511719,
|
| 502 |
+
"rewards/margins": 0.09959708154201508,
|
| 503 |
+
"rewards/rejected": -0.03374204784631729,
|
| 504 |
+
"step": 33
|
| 505 |
+
},
|
| 506 |
+
{
|
| 507 |
+
"epoch": 0.4459016393442623,
|
| 508 |
+
"grad_norm": 123.2249526977539,
|
| 509 |
+
"learning_rate": 4.448529411764706e-06,
|
| 510 |
+
"logits/chosen": -0.7680925130844116,
|
| 511 |
+
"logits/rejected": -0.6171376705169678,
|
| 512 |
+
"logps/chosen": -480.37481689453125,
|
| 513 |
+
"logps/rejected": -430.70379638671875,
|
| 514 |
+
"loss": 0.7551,
|
| 515 |
+
"rewards/accuracies": 0.5,
|
| 516 |
+
"rewards/chosen": -0.217463880777359,
|
| 517 |
+
"rewards/margins": -0.08437519520521164,
|
| 518 |
+
"rewards/rejected": -0.13308867812156677,
|
| 519 |
+
"step": 34
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 0.45901639344262296,
|
| 523 |
+
"grad_norm": NaN,
|
| 524 |
+
"learning_rate": 4.448529411764706e-06,
|
| 525 |
+
"logits/chosen": -0.9053277969360352,
|
| 526 |
+
"logits/rejected": -0.691852331161499,
|
| 527 |
+
"logps/chosen": -409.5699462890625,
|
| 528 |
+
"logps/rejected": -475.8656005859375,
|
| 529 |
+
"loss": 0.8483,
|
| 530 |
+
"rewards/accuracies": 0.25,
|
| 531 |
+
"rewards/chosen": -0.18217086791992188,
|
| 532 |
+
"rewards/margins": -0.2824680209159851,
|
| 533 |
+
"rewards/rejected": 0.10029716044664383,
|
| 534 |
+
"step": 35
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 0.4721311475409836,
|
| 538 |
+
"grad_norm": 105.83935546875,
|
| 539 |
+
"learning_rate": 4.411764705882353e-06,
|
| 540 |
+
"logits/chosen": -0.28655514121055603,
|
| 541 |
+
"logits/rejected": -0.05234713852405548,
|
| 542 |
+
"logps/chosen": -563.8226318359375,
|
| 543 |
+
"logps/rejected": -375.774658203125,
|
| 544 |
+
"loss": 0.6024,
|
| 545 |
+
"rewards/accuracies": 0.75,
|
| 546 |
+
"rewards/chosen": 0.048460379242897034,
|
| 547 |
+
"rewards/margins": 0.28112107515335083,
|
| 548 |
+
"rewards/rejected": -0.2326606810092926,
|
| 549 |
+
"step": 36
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 0.4852459016393443,
|
| 553 |
+
"grad_norm": 68.51673126220703,
|
| 554 |
+
"learning_rate": 4.3750000000000005e-06,
|
| 555 |
+
"logits/chosen": -0.7692010402679443,
|
| 556 |
+
"logits/rejected": -0.9052639007568359,
|
| 557 |
+
"logps/chosen": -262.10467529296875,
|
| 558 |
+
"logps/rejected": -209.62413024902344,
|
| 559 |
+
"loss": 0.5991,
|
| 560 |
+
"rewards/accuracies": 1.0,
|
| 561 |
+
"rewards/chosen": 0.09292706847190857,
|
| 562 |
+
"rewards/margins": 0.20516462624073029,
|
| 563 |
+
"rewards/rejected": -0.11223754286766052,
|
| 564 |
+
"step": 37
|
| 565 |
+
},
|
| 566 |
+
{
|
| 567 |
+
"epoch": 0.49836065573770494,
|
| 568 |
+
"grad_norm": 152.35870361328125,
|
| 569 |
+
"learning_rate": 4.3382352941176475e-06,
|
| 570 |
+
"logits/chosen": -0.4434085190296173,
|
| 571 |
+
"logits/rejected": -0.5462446212768555,
|
| 572 |
+
"logps/chosen": -325.6352844238281,
|
| 573 |
+
"logps/rejected": -386.6681823730469,
|
| 574 |
+
"loss": 1.048,
|
| 575 |
+
"rewards/accuracies": 0.5,
|
| 576 |
+
"rewards/chosen": -0.2829402983188629,
|
| 577 |
+
"rewards/margins": -0.5018165707588196,
|
| 578 |
+
"rewards/rejected": 0.21887625753879547,
|
| 579 |
+
"step": 38
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 0.5114754098360655,
|
| 583 |
+
"grad_norm": 128.87644958496094,
|
| 584 |
+
"learning_rate": 4.301470588235295e-06,
|
| 585 |
+
"logits/chosen": -0.32321175932884216,
|
| 586 |
+
"logits/rejected": -0.6219479441642761,
|
| 587 |
+
"logps/chosen": -220.80865478515625,
|
| 588 |
+
"logps/rejected": -679.1721801757812,
|
| 589 |
+
"loss": 0.6471,
|
| 590 |
+
"rewards/accuracies": 0.75,
|
| 591 |
+
"rewards/chosen": -0.08989439904689789,
|
| 592 |
+
"rewards/margins": 0.1783585399389267,
|
| 593 |
+
"rewards/rejected": -0.268252968788147,
|
| 594 |
+
"step": 39
|
| 595 |
+
},
|
| 596 |
+
{
|
| 597 |
+
"epoch": 0.5245901639344263,
|
| 598 |
+
"grad_norm": 164.9374542236328,
|
| 599 |
+
"learning_rate": 4.264705882352942e-06,
|
| 600 |
+
"logits/chosen": -0.41436851024627686,
|
| 601 |
+
"logits/rejected": -0.3371754288673401,
|
| 602 |
+
"logps/chosen": -453.7709045410156,
|
| 603 |
+
"logps/rejected": -186.964599609375,
|
| 604 |
+
"loss": 0.7023,
|
| 605 |
+
"rewards/accuracies": 0.5,
|
| 606 |
+
"rewards/chosen": -0.012208174914121628,
|
| 607 |
+
"rewards/margins": 0.0052278414368629456,
|
| 608 |
+
"rewards/rejected": -0.01743602193892002,
|
| 609 |
+
"step": 40
|
| 610 |
+
},
|
| 611 |
+
{
|
| 612 |
+
"epoch": 0.5377049180327869,
|
| 613 |
+
"grad_norm": 85.42108917236328,
|
| 614 |
+
"learning_rate": 4.227941176470589e-06,
|
| 615 |
+
"logits/chosen": -0.3417915403842926,
|
| 616 |
+
"logits/rejected": -0.6106492280960083,
|
| 617 |
+
"logps/chosen": -410.3317565917969,
|
| 618 |
+
"logps/rejected": -356.129638671875,
|
| 619 |
+
"loss": 0.5101,
|
| 620 |
+
"rewards/accuracies": 0.75,
|
| 621 |
+
"rewards/chosen": 0.12232876569032669,
|
| 622 |
+
"rewards/margins": 0.4886293411254883,
|
| 623 |
+
"rewards/rejected": -0.3663005828857422,
|
| 624 |
+
"step": 41
|
| 625 |
+
},
|
| 626 |
+
{
|
| 627 |
+
"epoch": 0.5508196721311476,
|
| 628 |
+
"grad_norm": 92.59017181396484,
|
| 629 |
+
"learning_rate": 4.191176470588236e-06,
|
| 630 |
+
"logits/chosen": -0.3282807171344757,
|
| 631 |
+
"logits/rejected": -0.6609268188476562,
|
| 632 |
+
"logps/chosen": -273.1469421386719,
|
| 633 |
+
"logps/rejected": -394.88787841796875,
|
| 634 |
+
"loss": 0.5399,
|
| 635 |
+
"rewards/accuracies": 1.0,
|
| 636 |
+
"rewards/chosen": 0.09656943380832672,
|
| 637 |
+
"rewards/margins": 0.3409425616264343,
|
| 638 |
+
"rewards/rejected": -0.2443731427192688,
|
| 639 |
+
"step": 42
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 0.5639344262295082,
|
| 643 |
+
"grad_norm": 113.27176666259766,
|
| 644 |
+
"learning_rate": 4.154411764705883e-06,
|
| 645 |
+
"logits/chosen": -0.6696023941040039,
|
| 646 |
+
"logits/rejected": -0.4758712649345398,
|
| 647 |
+
"logps/chosen": -259.9328918457031,
|
| 648 |
+
"logps/rejected": -257.8404846191406,
|
| 649 |
+
"loss": 0.7035,
|
| 650 |
+
"rewards/accuracies": 0.5,
|
| 651 |
+
"rewards/chosen": -0.07427978515625,
|
| 652 |
+
"rewards/margins": 0.009069837629795074,
|
| 653 |
+
"rewards/rejected": -0.08334961533546448,
|
| 654 |
+
"step": 43
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 0.5770491803278689,
|
| 658 |
+
"grad_norm": 115.66248321533203,
|
| 659 |
+
"learning_rate": 4.11764705882353e-06,
|
| 660 |
+
"logits/chosen": -0.5908689498901367,
|
| 661 |
+
"logits/rejected": -0.6039953231811523,
|
| 662 |
+
"logps/chosen": -264.3017578125,
|
| 663 |
+
"logps/rejected": -345.41534423828125,
|
| 664 |
+
"loss": 0.758,
|
| 665 |
+
"rewards/accuracies": 0.5,
|
| 666 |
+
"rewards/chosen": -0.16783800721168518,
|
| 667 |
+
"rewards/margins": -0.07998895645141602,
|
| 668 |
+
"rewards/rejected": -0.08784904330968857,
|
| 669 |
+
"step": 44
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 0.5901639344262295,
|
| 673 |
+
"grad_norm": 114.06060028076172,
|
| 674 |
+
"learning_rate": 4.080882352941177e-06,
|
| 675 |
+
"logits/chosen": -0.4014369249343872,
|
| 676 |
+
"logits/rejected": -0.31871065497398376,
|
| 677 |
+
"logps/chosen": -365.35687255859375,
|
| 678 |
+
"logps/rejected": -380.46661376953125,
|
| 679 |
+
"loss": 0.7162,
|
| 680 |
+
"rewards/accuracies": 0.75,
|
| 681 |
+
"rewards/chosen": 0.09307613968849182,
|
| 682 |
+
"rewards/margins": -0.03436946123838425,
|
| 683 |
+
"rewards/rejected": 0.12744559347629547,
|
| 684 |
+
"step": 45
|
| 685 |
+
},
|
| 686 |
+
{
|
| 687 |
+
"epoch": 0.6032786885245902,
|
| 688 |
+
"grad_norm": 138.62567138671875,
|
| 689 |
+
"learning_rate": 4.044117647058824e-06,
|
| 690 |
+
"logits/chosen": -0.638996958732605,
|
| 691 |
+
"logits/rejected": -0.39604443311691284,
|
| 692 |
+
"logps/chosen": -286.7137451171875,
|
| 693 |
+
"logps/rejected": -220.05154418945312,
|
| 694 |
+
"loss": 0.8332,
|
| 695 |
+
"rewards/accuracies": 0.5,
|
| 696 |
+
"rewards/chosen": -0.1774437129497528,
|
| 697 |
+
"rewards/margins": -0.23038703203201294,
|
| 698 |
+
"rewards/rejected": 0.05294332653284073,
|
| 699 |
+
"step": 46
|
| 700 |
+
},
|
| 701 |
+
{
|
| 702 |
+
"epoch": 0.6163934426229508,
|
| 703 |
+
"grad_norm": 57.410499572753906,
|
| 704 |
+
"learning_rate": 4.007352941176471e-06,
|
| 705 |
+
"logits/chosen": -0.6090636253356934,
|
| 706 |
+
"logits/rejected": -0.5290719866752625,
|
| 707 |
+
"logps/chosen": -137.49166870117188,
|
| 708 |
+
"logps/rejected": -139.84095764160156,
|
| 709 |
+
"loss": 0.5675,
|
| 710 |
+
"rewards/accuracies": 1.0,
|
| 711 |
+
"rewards/chosen": 0.006125451996922493,
|
| 712 |
+
"rewards/margins": 0.29940930008888245,
|
| 713 |
+
"rewards/rejected": -0.2932838499546051,
|
| 714 |
+
"step": 47
|
| 715 |
+
},
|
| 716 |
+
{
|
| 717 |
+
"epoch": 0.6295081967213115,
|
| 718 |
+
"grad_norm": 74.56676483154297,
|
| 719 |
+
"learning_rate": 3.970588235294118e-06,
|
| 720 |
+
"logits/chosen": -0.7181419134140015,
|
| 721 |
+
"logits/rejected": -0.4697718024253845,
|
| 722 |
+
"logps/chosen": -189.2108154296875,
|
| 723 |
+
"logps/rejected": -129.29373168945312,
|
| 724 |
+
"loss": 0.6282,
|
| 725 |
+
"rewards/accuracies": 0.75,
|
| 726 |
+
"rewards/chosen": -0.16447561979293823,
|
| 727 |
+
"rewards/margins": 0.13910141587257385,
|
| 728 |
+
"rewards/rejected": -0.3035770356655121,
|
| 729 |
+
"step": 48
|
| 730 |
+
},
|
| 731 |
+
{
|
| 732 |
+
"epoch": 0.6426229508196721,
|
| 733 |
+
"grad_norm": 71.27189636230469,
|
| 734 |
+
"learning_rate": 3.933823529411765e-06,
|
| 735 |
+
"logits/chosen": -0.5085806846618652,
|
| 736 |
+
"logits/rejected": -0.44473588466644287,
|
| 737 |
+
"logps/chosen": -442.37554931640625,
|
| 738 |
+
"logps/rejected": -340.0184326171875,
|
| 739 |
+
"loss": 0.4663,
|
| 740 |
+
"rewards/accuracies": 1.0,
|
| 741 |
+
"rewards/chosen": 0.27928200364112854,
|
| 742 |
+
"rewards/margins": 0.581198513507843,
|
| 743 |
+
"rewards/rejected": -0.3019165098667145,
|
| 744 |
+
"step": 49
|
| 745 |
+
},
|
| 746 |
+
{
|
| 747 |
+
"epoch": 0.6557377049180327,
|
| 748 |
+
"grad_norm": 94.27779388427734,
|
| 749 |
+
"learning_rate": 3.897058823529412e-06,
|
| 750 |
+
"logits/chosen": -0.43181851506233215,
|
| 751 |
+
"logits/rejected": -0.2016599327325821,
|
| 752 |
+
"logps/chosen": -412.7520446777344,
|
| 753 |
+
"logps/rejected": -255.32366943359375,
|
| 754 |
+
"loss": 0.5602,
|
| 755 |
+
"rewards/accuracies": 0.75,
|
| 756 |
+
"rewards/chosen": 0.15803948044776917,
|
| 757 |
+
"rewards/margins": 0.30720824003219604,
|
| 758 |
+
"rewards/rejected": -0.14916877448558807,
|
| 759 |
+
"step": 50
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 0.6688524590163935,
|
| 763 |
+
"grad_norm": 105.73281860351562,
|
| 764 |
+
"learning_rate": 3.860294117647059e-06,
|
| 765 |
+
"logits/chosen": -0.8714503645896912,
|
| 766 |
+
"logits/rejected": -0.8866394758224487,
|
| 767 |
+
"logps/chosen": -234.35894775390625,
|
| 768 |
+
"logps/rejected": -381.7604064941406,
|
| 769 |
+
"loss": 0.679,
|
| 770 |
+
"rewards/accuracies": 0.5,
|
| 771 |
+
"rewards/chosen": 0.20015183091163635,
|
| 772 |
+
"rewards/margins": 0.0683051347732544,
|
| 773 |
+
"rewards/rejected": 0.13184669613838196,
|
| 774 |
+
"step": 51
|
| 775 |
+
},
|
| 776 |
+
{
|
| 777 |
+
"epoch": 0.6819672131147541,
|
| 778 |
+
"grad_norm": 114.59404754638672,
|
| 779 |
+
"learning_rate": 3.8235294117647055e-06,
|
| 780 |
+
"logits/chosen": -0.3797226846218109,
|
| 781 |
+
"logits/rejected": -0.28768518567085266,
|
| 782 |
+
"logps/chosen": -527.8758544921875,
|
| 783 |
+
"logps/rejected": -398.22833251953125,
|
| 784 |
+
"loss": 0.5557,
|
| 785 |
+
"rewards/accuracies": 0.75,
|
| 786 |
+
"rewards/chosen": 0.1556282937526703,
|
| 787 |
+
"rewards/margins": 0.3929787576198578,
|
| 788 |
+
"rewards/rejected": -0.2373504638671875,
|
| 789 |
+
"step": 52
|
| 790 |
+
},
|
| 791 |
+
{
|
| 792 |
+
"epoch": 0.6950819672131148,
|
| 793 |
+
"grad_norm": 79.82359313964844,
|
| 794 |
+
"learning_rate": 3.786764705882353e-06,
|
| 795 |
+
"logits/chosen": -0.36424490809440613,
|
| 796 |
+
"logits/rejected": -0.4016554355621338,
|
| 797 |
+
"logps/chosen": -264.1070556640625,
|
| 798 |
+
"logps/rejected": -228.17445373535156,
|
| 799 |
+
"loss": 0.5864,
|
| 800 |
+
"rewards/accuracies": 0.75,
|
| 801 |
+
"rewards/chosen": 0.08102244883775711,
|
| 802 |
+
"rewards/margins": 0.2558790147304535,
|
| 803 |
+
"rewards/rejected": -0.17485657334327698,
|
| 804 |
+
"step": 53
|
| 805 |
+
},
|
| 806 |
+
{
|
| 807 |
+
"epoch": 0.7081967213114754,
|
| 808 |
+
"grad_norm": 96.55302429199219,
|
| 809 |
+
"learning_rate": 3.7500000000000005e-06,
|
| 810 |
+
"logits/chosen": -0.2944083511829376,
|
| 811 |
+
"logits/rejected": -0.1153193861246109,
|
| 812 |
+
"logps/chosen": -548.8867797851562,
|
| 813 |
+
"logps/rejected": -476.7703857421875,
|
| 814 |
+
"loss": 0.4772,
|
| 815 |
+
"rewards/accuracies": 1.0,
|
| 816 |
+
"rewards/chosen": 0.578123152256012,
|
| 817 |
+
"rewards/margins": 0.5144607424736023,
|
| 818 |
+
"rewards/rejected": 0.0636623352766037,
|
| 819 |
+
"step": 54
|
| 820 |
+
},
|
| 821 |
+
{
|
| 822 |
+
"epoch": 0.7213114754098361,
|
| 823 |
+
"grad_norm": 99.41586303710938,
|
| 824 |
+
"learning_rate": 3.7132352941176476e-06,
|
| 825 |
+
"logits/chosen": -0.28071513772010803,
|
| 826 |
+
"logits/rejected": -0.3517005443572998,
|
| 827 |
+
"logps/chosen": -269.35107421875,
|
| 828 |
+
"logps/rejected": -245.49374389648438,
|
| 829 |
+
"loss": 0.6535,
|
| 830 |
+
"rewards/accuracies": 0.75,
|
| 831 |
+
"rewards/chosen": -0.32255783677101135,
|
| 832 |
+
"rewards/margins": 0.18369215726852417,
|
| 833 |
+
"rewards/rejected": -0.5062500238418579,
|
| 834 |
+
"step": 55
|
| 835 |
+
},
|
| 836 |
+
{
|
| 837 |
+
"epoch": 0.7344262295081967,
|
| 838 |
+
"grad_norm": 102.873046875,
|
| 839 |
+
"learning_rate": 3.6764705882352946e-06,
|
| 840 |
+
"logits/chosen": -0.5045206546783447,
|
| 841 |
+
"logits/rejected": -0.33617326617240906,
|
| 842 |
+
"logps/chosen": -446.717529296875,
|
| 843 |
+
"logps/rejected": -354.23199462890625,
|
| 844 |
+
"loss": 0.5308,
|
| 845 |
+
"rewards/accuracies": 1.0,
|
| 846 |
+
"rewards/chosen": 0.11581029742956161,
|
| 847 |
+
"rewards/margins": 0.36529916524887085,
|
| 848 |
+
"rewards/rejected": -0.24948886036872864,
|
| 849 |
+
"step": 56
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 0.7475409836065574,
|
| 853 |
+
"grad_norm": 107.32563018798828,
|
| 854 |
+
"learning_rate": 3.6397058823529413e-06,
|
| 855 |
+
"logits/chosen": -0.7487730979919434,
|
| 856 |
+
"logits/rejected": -0.5132504105567932,
|
| 857 |
+
"logps/chosen": -297.9276428222656,
|
| 858 |
+
"logps/rejected": -272.4541015625,
|
| 859 |
+
"loss": 0.6717,
|
| 860 |
+
"rewards/accuracies": 0.75,
|
| 861 |
+
"rewards/chosen": 0.00452117994427681,
|
| 862 |
+
"rewards/margins": 0.049825482070446014,
|
| 863 |
+
"rewards/rejected": -0.045304298400878906,
|
| 864 |
+
"step": 57
|
| 865 |
+
},
|
| 866 |
+
{
|
| 867 |
+
"epoch": 0.760655737704918,
|
| 868 |
+
"grad_norm": 197.63619995117188,
|
| 869 |
+
"learning_rate": 3.6029411764705883e-06,
|
| 870 |
+
"logits/chosen": -0.3516054153442383,
|
| 871 |
+
"logits/rejected": -0.4525684714317322,
|
| 872 |
+
"logps/chosen": -527.5667724609375,
|
| 873 |
+
"logps/rejected": -721.8489990234375,
|
| 874 |
+
"loss": 0.9658,
|
| 875 |
+
"rewards/accuracies": 0.5,
|
| 876 |
+
"rewards/chosen": -0.026310719549655914,
|
| 877 |
+
"rewards/margins": -0.28759005665779114,
|
| 878 |
+
"rewards/rejected": 0.26127931475639343,
|
| 879 |
+
"step": 58
|
| 880 |
+
},
|
| 881 |
+
{
|
| 882 |
+
"epoch": 0.7737704918032787,
|
| 883 |
+
"grad_norm": 58.864341735839844,
|
| 884 |
+
"learning_rate": 3.566176470588236e-06,
|
| 885 |
+
"logits/chosen": -0.8907312750816345,
|
| 886 |
+
"logits/rejected": -0.5560203194618225,
|
| 887 |
+
"logps/chosen": -356.2855224609375,
|
| 888 |
+
"logps/rejected": -259.6497802734375,
|
| 889 |
+
"loss": 0.5038,
|
| 890 |
+
"rewards/accuracies": 0.75,
|
| 891 |
+
"rewards/chosen": 0.31428688764572144,
|
| 892 |
+
"rewards/margins": 0.4714818000793457,
|
| 893 |
+
"rewards/rejected": -0.15719491243362427,
|
| 894 |
+
"step": 59
|
| 895 |
+
},
|
| 896 |
+
{
|
| 897 |
+
"epoch": 0.7868852459016393,
|
| 898 |
+
"grad_norm": 77.59774017333984,
|
| 899 |
+
"learning_rate": 3.529411764705883e-06,
|
| 900 |
+
"logits/chosen": -0.5632966160774231,
|
| 901 |
+
"logits/rejected": -0.6254044771194458,
|
| 902 |
+
"logps/chosen": -523.7625732421875,
|
| 903 |
+
"logps/rejected": -410.9280700683594,
|
| 904 |
+
"loss": 0.3917,
|
| 905 |
+
"rewards/accuracies": 0.75,
|
| 906 |
+
"rewards/chosen": 0.16903266310691833,
|
| 907 |
+
"rewards/margins": 0.9428247213363647,
|
| 908 |
+
"rewards/rejected": -0.7737920880317688,
|
| 909 |
+
"step": 60
|
| 910 |
+
},
|
| 911 |
+
{
|
| 912 |
+
"epoch": 0.8,
|
| 913 |
+
"grad_norm": 125.0260009765625,
|
| 914 |
+
"learning_rate": 3.4926470588235295e-06,
|
| 915 |
+
"logits/chosen": -0.7440542578697205,
|
| 916 |
+
"logits/rejected": -0.703271210193634,
|
| 917 |
+
"logps/chosen": -259.8118591308594,
|
| 918 |
+
"logps/rejected": -273.839599609375,
|
| 919 |
+
"loss": 0.8524,
|
| 920 |
+
"rewards/accuracies": 0.25,
|
| 921 |
+
"rewards/chosen": -0.13262319564819336,
|
| 922 |
+
"rewards/margins": -0.27512502670288086,
|
| 923 |
+
"rewards/rejected": 0.1425018012523651,
|
| 924 |
+
"step": 61
|
| 925 |
+
},
|
| 926 |
+
{
|
| 927 |
+
"epoch": 0.8131147540983606,
|
| 928 |
+
"grad_norm": 76.26204681396484,
|
| 929 |
+
"learning_rate": 3.4558823529411766e-06,
|
| 930 |
+
"logits/chosen": -0.7221469283103943,
|
| 931 |
+
"logits/rejected": -0.7659784555435181,
|
| 932 |
+
"logps/chosen": -184.25143432617188,
|
| 933 |
+
"logps/rejected": -179.50430297851562,
|
| 934 |
+
"loss": 0.6865,
|
| 935 |
+
"rewards/accuracies": 0.5,
|
| 936 |
+
"rewards/chosen": 0.0025919005274772644,
|
| 937 |
+
"rewards/margins": 0.019242577254772186,
|
| 938 |
+
"rewards/rejected": -0.016650676727294922,
|
| 939 |
+
"step": 62
|
| 940 |
+
},
|
| 941 |
+
{
|
| 942 |
+
"epoch": 0.8262295081967214,
|
| 943 |
+
"grad_norm": 98.49539184570312,
|
| 944 |
+
"learning_rate": 3.419117647058824e-06,
|
| 945 |
+
"logits/chosen": -0.39552026987075806,
|
| 946 |
+
"logits/rejected": -0.5626529455184937,
|
| 947 |
+
"logps/chosen": -299.3195495605469,
|
| 948 |
+
"logps/rejected": -409.58978271484375,
|
| 949 |
+
"loss": 0.6728,
|
| 950 |
+
"rewards/accuracies": 0.75,
|
| 951 |
+
"rewards/chosen": -0.10388422012329102,
|
| 952 |
+
"rewards/margins": 0.0691218301653862,
|
| 953 |
+
"rewards/rejected": -0.1730060577392578,
|
| 954 |
+
"step": 63
|
| 955 |
+
},
|
| 956 |
+
{
|
| 957 |
+
"epoch": 0.839344262295082,
|
| 958 |
+
"grad_norm": 121.93528747558594,
|
| 959 |
+
"learning_rate": 3.382352941176471e-06,
|
| 960 |
+
"logits/chosen": -0.3543356955051422,
|
| 961 |
+
"logits/rejected": -0.23809625208377838,
|
| 962 |
+
"logps/chosen": -189.68069458007812,
|
| 963 |
+
"logps/rejected": -349.9007263183594,
|
| 964 |
+
"loss": 0.8636,
|
| 965 |
+
"rewards/accuracies": 0.25,
|
| 966 |
+
"rewards/chosen": -0.3187013864517212,
|
| 967 |
+
"rewards/margins": -0.2557255029678345,
|
| 968 |
+
"rewards/rejected": -0.06297589093446732,
|
| 969 |
+
"step": 64
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 0.8524590163934426,
|
| 973 |
+
"grad_norm": 35.53516387939453,
|
| 974 |
+
"learning_rate": 3.3455882352941178e-06,
|
| 975 |
+
"logits/chosen": -0.9258323311805725,
|
| 976 |
+
"logits/rejected": -0.8565582036972046,
|
| 977 |
+
"logps/chosen": -272.64453125,
|
| 978 |
+
"logps/rejected": -173.0827178955078,
|
| 979 |
+
"loss": 0.5008,
|
| 980 |
+
"rewards/accuracies": 0.5,
|
| 981 |
+
"rewards/chosen": 0.3930124044418335,
|
| 982 |
+
"rewards/margins": 0.5905007123947144,
|
| 983 |
+
"rewards/rejected": -0.19748830795288086,
|
| 984 |
+
"step": 65
|
| 985 |
+
},
|
| 986 |
+
{
|
| 987 |
+
"epoch": 0.8655737704918033,
|
| 988 |
+
"grad_norm": 162.02955627441406,
|
| 989 |
+
"learning_rate": 3.308823529411765e-06,
|
| 990 |
+
"logits/chosen": -0.7951459288597107,
|
| 991 |
+
"logits/rejected": -0.9009961485862732,
|
| 992 |
+
"logps/chosen": -322.9057312011719,
|
| 993 |
+
"logps/rejected": -461.6522216796875,
|
| 994 |
+
"loss": 0.9941,
|
| 995 |
+
"rewards/accuracies": 0.25,
|
| 996 |
+
"rewards/chosen": -0.22350434958934784,
|
| 997 |
+
"rewards/margins": -0.43997135758399963,
|
| 998 |
+
"rewards/rejected": 0.2164669930934906,
|
| 999 |
+
"step": 66
|
| 1000 |
+
},
|
| 1001 |
+
{
|
| 1002 |
+
"epoch": 0.8786885245901639,
|
| 1003 |
+
"grad_norm": 49.46587371826172,
|
| 1004 |
+
"learning_rate": 3.272058823529412e-06,
|
| 1005 |
+
"logits/chosen": -0.8077062368392944,
|
| 1006 |
+
"logits/rejected": -0.7711391448974609,
|
| 1007 |
+
"logps/chosen": -334.55621337890625,
|
| 1008 |
+
"logps/rejected": -304.2231750488281,
|
| 1009 |
+
"loss": 0.4265,
|
| 1010 |
+
"rewards/accuracies": 1.0,
|
| 1011 |
+
"rewards/chosen": 0.5165804028511047,
|
| 1012 |
+
"rewards/margins": 0.7691186666488647,
|
| 1013 |
+
"rewards/rejected": -0.2525383234024048,
|
| 1014 |
+
"step": 67
|
| 1015 |
+
},
|
| 1016 |
+
{
|
| 1017 |
+
"epoch": 0.8918032786885246,
|
| 1018 |
+
"grad_norm": 113.88951110839844,
|
| 1019 |
+
"learning_rate": 3.2352941176470594e-06,
|
| 1020 |
+
"logits/chosen": -0.48406150937080383,
|
| 1021 |
+
"logits/rejected": -0.550665020942688,
|
| 1022 |
+
"logps/chosen": -252.42161560058594,
|
| 1023 |
+
"logps/rejected": -426.91375732421875,
|
| 1024 |
+
"loss": 0.7502,
|
| 1025 |
+
"rewards/accuracies": 0.5,
|
| 1026 |
+
"rewards/chosen": -0.13350410759449005,
|
| 1027 |
+
"rewards/margins": -0.05722009390592575,
|
| 1028 |
+
"rewards/rejected": -0.07628403604030609,
|
| 1029 |
+
"step": 68
|
| 1030 |
+
},
|
| 1031 |
+
{
|
| 1032 |
+
"epoch": 0.9049180327868852,
|
| 1033 |
+
"grad_norm": 82.540771484375,
|
| 1034 |
+
"learning_rate": 3.198529411764706e-06,
|
| 1035 |
+
"logits/chosen": -0.6168251633644104,
|
| 1036 |
+
"logits/rejected": -0.5766561031341553,
|
| 1037 |
+
"logps/chosen": -355.02587890625,
|
| 1038 |
+
"logps/rejected": -185.5700225830078,
|
| 1039 |
+
"loss": 0.5665,
|
| 1040 |
+
"rewards/accuracies": 1.0,
|
| 1041 |
+
"rewards/chosen": -0.07997532188892365,
|
| 1042 |
+
"rewards/margins": 0.31432589888572693,
|
| 1043 |
+
"rewards/rejected": -0.3943012058734894,
|
| 1044 |
+
"step": 69
|
| 1045 |
+
},
|
| 1046 |
+
{
|
| 1047 |
+
"epoch": 0.9180327868852459,
|
| 1048 |
+
"grad_norm": 80.47476196289062,
|
| 1049 |
+
"learning_rate": 3.161764705882353e-06,
|
| 1050 |
+
"logits/chosen": -0.44328969717025757,
|
| 1051 |
+
"logits/rejected": -0.23468244075775146,
|
| 1052 |
+
"logps/chosen": -298.8565673828125,
|
| 1053 |
+
"logps/rejected": -271.02874755859375,
|
| 1054 |
+
"loss": 0.5233,
|
| 1055 |
+
"rewards/accuracies": 1.0,
|
| 1056 |
+
"rewards/chosen": 0.3650921881198883,
|
| 1057 |
+
"rewards/margins": 0.4301413893699646,
|
| 1058 |
+
"rewards/rejected": -0.0650491714477539,
|
| 1059 |
+
"step": 70
|
| 1060 |
+
},
|
| 1061 |
+
{
|
| 1062 |
+
"epoch": 0.9311475409836065,
|
| 1063 |
+
"grad_norm": 183.71018981933594,
|
| 1064 |
+
"learning_rate": 3.125e-06,
|
| 1065 |
+
"logits/chosen": -0.7024189233779907,
|
| 1066 |
+
"logits/rejected": -0.3720092177391052,
|
| 1067 |
+
"logps/chosen": -663.25341796875,
|
| 1068 |
+
"logps/rejected": -509.05072021484375,
|
| 1069 |
+
"loss": 0.6182,
|
| 1070 |
+
"rewards/accuracies": 0.5,
|
| 1071 |
+
"rewards/chosen": 0.02078094333410263,
|
| 1072 |
+
"rewards/margins": 0.3649251461029053,
|
| 1073 |
+
"rewards/rejected": -0.3441442549228668,
|
| 1074 |
+
"step": 71
|
| 1075 |
+
},
|
| 1076 |
+
{
|
| 1077 |
+
"epoch": 0.9442622950819672,
|
| 1078 |
+
"grad_norm": 73.77120971679688,
|
| 1079 |
+
"learning_rate": 3.0882352941176476e-06,
|
| 1080 |
+
"logits/chosen": -0.7303851842880249,
|
| 1081 |
+
"logits/rejected": -0.5275728702545166,
|
| 1082 |
+
"logps/chosen": -273.287353515625,
|
| 1083 |
+
"logps/rejected": -248.97366333007812,
|
| 1084 |
+
"loss": 0.5902,
|
| 1085 |
+
"rewards/accuracies": 1.0,
|
| 1086 |
+
"rewards/chosen": 0.15096759796142578,
|
| 1087 |
+
"rewards/margins": 0.22571565210819244,
|
| 1088 |
+
"rewards/rejected": -0.07474804669618607,
|
| 1089 |
+
"step": 72
|
| 1090 |
+
},
|
| 1091 |
+
{
|
| 1092 |
+
"epoch": 0.9573770491803278,
|
| 1093 |
+
"grad_norm": 119.30152893066406,
|
| 1094 |
+
"learning_rate": 3.0514705882352947e-06,
|
| 1095 |
+
"logits/chosen": -0.7145899534225464,
|
| 1096 |
+
"logits/rejected": -0.6755335330963135,
|
| 1097 |
+
"logps/chosen": -358.4460144042969,
|
| 1098 |
+
"logps/rejected": -413.93402099609375,
|
| 1099 |
+
"loss": 0.715,
|
| 1100 |
+
"rewards/accuracies": 0.75,
|
| 1101 |
+
"rewards/chosen": -0.5442755818367004,
|
| 1102 |
+
"rewards/margins": -0.015435710549354553,
|
| 1103 |
+
"rewards/rejected": -0.5288398861885071,
|
| 1104 |
+
"step": 73
|
| 1105 |
+
},
|
| 1106 |
+
{
|
| 1107 |
+
"epoch": 0.9704918032786886,
|
| 1108 |
+
"grad_norm": Infinity,
|
| 1109 |
+
"learning_rate": 3.0514705882352947e-06,
|
| 1110 |
+
"logits/chosen": -0.37683844566345215,
|
| 1111 |
+
"logits/rejected": -0.19479577243328094,
|
| 1112 |
+
"logps/chosen": -191.80364990234375,
|
| 1113 |
+
"logps/rejected": -239.4271240234375,
|
| 1114 |
+
"loss": 0.6901,
|
| 1115 |
+
"rewards/accuracies": 0.5,
|
| 1116 |
+
"rewards/chosen": -0.12151336669921875,
|
| 1117 |
+
"rewards/margins": 0.011674299836158752,
|
| 1118 |
+
"rewards/rejected": -0.1331876814365387,
|
| 1119 |
+
"step": 74
|
| 1120 |
+
},
|
| 1121 |
+
{
|
| 1122 |
+
"epoch": 0.9836065573770492,
|
| 1123 |
+
"grad_norm": 37.73300552368164,
|
| 1124 |
+
"learning_rate": 3.0147058823529413e-06,
|
| 1125 |
+
"logits/chosen": -0.7108013033866882,
|
| 1126 |
+
"logits/rejected": -0.8427099585533142,
|
| 1127 |
+
"logps/chosen": -237.83132934570312,
|
| 1128 |
+
"logps/rejected": -235.86509704589844,
|
| 1129 |
+
"loss": 0.5368,
|
| 1130 |
+
"rewards/accuracies": 0.5,
|
| 1131 |
+
"rewards/chosen": 0.3780634105205536,
|
| 1132 |
+
"rewards/margins": 0.5749028921127319,
|
| 1133 |
+
"rewards/rejected": -0.19683943688869476,
|
| 1134 |
+
"step": 75
|
| 1135 |
+
},
|
| 1136 |
+
{
|
| 1137 |
+
"epoch": 0.9967213114754099,
|
| 1138 |
+
"grad_norm": 50.56627655029297,
|
| 1139 |
+
"learning_rate": 2.9779411764705884e-06,
|
| 1140 |
+
"logits/chosen": -0.3920336663722992,
|
| 1141 |
+
"logits/rejected": -0.5925789475440979,
|
| 1142 |
+
"logps/chosen": -352.024658203125,
|
| 1143 |
+
"logps/rejected": -319.0198669433594,
|
| 1144 |
+
"loss": 0.3911,
|
| 1145 |
+
"rewards/accuracies": 0.75,
|
| 1146 |
+
"rewards/chosen": 0.4176803529262543,
|
| 1147 |
+
"rewards/margins": 0.8605508804321289,
|
| 1148 |
+
"rewards/rejected": -0.44287049770355225,
|
| 1149 |
+
"step": 76
|
| 1150 |
+
},
|
| 1151 |
+
{
|
| 1152 |
+
"epoch": 1.0098360655737706,
|
| 1153 |
+
"grad_norm": 31.756732940673828,
|
| 1154 |
+
"learning_rate": 2.9411764705882355e-06,
|
| 1155 |
+
"logits/chosen": -0.9694571495056152,
|
| 1156 |
+
"logits/rejected": -0.7683681845664978,
|
| 1157 |
+
"logps/chosen": -397.28277587890625,
|
| 1158 |
+
"logps/rejected": -506.4493103027344,
|
| 1159 |
+
"loss": 0.2859,
|
| 1160 |
+
"rewards/accuracies": 1.0,
|
| 1161 |
+
"rewards/chosen": 3.0198912620544434,
|
| 1162 |
+
"rewards/margins": 6.584094524383545,
|
| 1163 |
+
"rewards/rejected": -3.5642035007476807,
|
| 1164 |
+
"step": 77
|
| 1165 |
+
},
|
| 1166 |
+
{
|
| 1167 |
+
"epoch": 1.022950819672131,
|
| 1168 |
+
"grad_norm": 15.996756553649902,
|
| 1169 |
+
"learning_rate": 2.904411764705883e-06,
|
| 1170 |
+
"logits/chosen": -0.4139990210533142,
|
| 1171 |
+
"logits/rejected": -0.5289357900619507,
|
| 1172 |
+
"logps/chosen": -157.25994873046875,
|
| 1173 |
+
"logps/rejected": -292.02252197265625,
|
| 1174 |
+
"loss": 0.0868,
|
| 1175 |
+
"rewards/accuracies": 1.0,
|
| 1176 |
+
"rewards/chosen": 0.7793710827827454,
|
| 1177 |
+
"rewards/margins": 3.51633358001709,
|
| 1178 |
+
"rewards/rejected": -2.73696231842041,
|
| 1179 |
+
"step": 78
|
| 1180 |
+
},
|
| 1181 |
+
{
|
| 1182 |
+
"epoch": 1.0360655737704918,
|
| 1183 |
+
"grad_norm": 4.163623809814453,
|
| 1184 |
+
"learning_rate": 2.8676470588235296e-06,
|
| 1185 |
+
"logits/chosen": -0.8043258190155029,
|
| 1186 |
+
"logits/rejected": -0.7802602052688599,
|
| 1187 |
+
"logps/chosen": -419.2426452636719,
|
| 1188 |
+
"logps/rejected": -306.1612548828125,
|
| 1189 |
+
"loss": 0.0156,
|
| 1190 |
+
"rewards/accuracies": 1.0,
|
| 1191 |
+
"rewards/chosen": 2.816192626953125,
|
| 1192 |
+
"rewards/margins": 5.203756332397461,
|
| 1193 |
+
"rewards/rejected": -2.3875632286071777,
|
| 1194 |
+
"step": 79
|
| 1195 |
+
},
|
| 1196 |
+
{
|
| 1197 |
+
"epoch": 1.0491803278688525,
|
| 1198 |
+
"grad_norm": 13.230965614318848,
|
| 1199 |
+
"learning_rate": 2.8308823529411766e-06,
|
| 1200 |
+
"logits/chosen": -0.6542176008224487,
|
| 1201 |
+
"logits/rejected": -0.3940190374851227,
|
| 1202 |
+
"logps/chosen": -421.56170654296875,
|
| 1203 |
+
"logps/rejected": -406.03619384765625,
|
| 1204 |
+
"loss": 0.1049,
|
| 1205 |
+
"rewards/accuracies": 1.0,
|
| 1206 |
+
"rewards/chosen": 3.0519039630889893,
|
| 1207 |
+
"rewards/margins": 5.3741607666015625,
|
| 1208 |
+
"rewards/rejected": -2.322256565093994,
|
| 1209 |
+
"step": 80
|
| 1210 |
+
},
|
| 1211 |
+
{
|
| 1212 |
+
"epoch": 1.0622950819672132,
|
| 1213 |
+
"grad_norm": 31.09598731994629,
|
| 1214 |
+
"learning_rate": 2.7941176470588237e-06,
|
| 1215 |
+
"logits/chosen": -0.7882400751113892,
|
| 1216 |
+
"logits/rejected": -0.755602240562439,
|
| 1217 |
+
"logps/chosen": -143.84951782226562,
|
| 1218 |
+
"logps/rejected": -207.64418029785156,
|
| 1219 |
+
"loss": 0.3054,
|
| 1220 |
+
"rewards/accuracies": 1.0,
|
| 1221 |
+
"rewards/chosen": 0.5518492460250854,
|
| 1222 |
+
"rewards/margins": 1.3898382186889648,
|
| 1223 |
+
"rewards/rejected": -0.8379888534545898,
|
| 1224 |
+
"step": 81
|
| 1225 |
+
},
|
| 1226 |
+
{
|
| 1227 |
+
"epoch": 1.0754098360655737,
|
| 1228 |
+
"grad_norm": 7.787254810333252,
|
| 1229 |
+
"learning_rate": 2.757352941176471e-06,
|
| 1230 |
+
"logits/chosen": -0.347468763589859,
|
| 1231 |
+
"logits/rejected": -0.34622734785079956,
|
| 1232 |
+
"logps/chosen": -263.9562072753906,
|
| 1233 |
+
"logps/rejected": -390.29901123046875,
|
| 1234 |
+
"loss": 0.0387,
|
| 1235 |
+
"rewards/accuracies": 1.0,
|
| 1236 |
+
"rewards/chosen": 2.743457555770874,
|
| 1237 |
+
"rewards/margins": 6.276088714599609,
|
| 1238 |
+
"rewards/rejected": -3.5326313972473145,
|
| 1239 |
+
"step": 82
|
| 1240 |
+
},
|
| 1241 |
+
{
|
| 1242 |
+
"epoch": 1.0885245901639344,
|
| 1243 |
+
"grad_norm": 12.739912986755371,
|
| 1244 |
+
"learning_rate": 2.720588235294118e-06,
|
| 1245 |
+
"logits/chosen": -0.5520642399787903,
|
| 1246 |
+
"logits/rejected": -0.632639467716217,
|
| 1247 |
+
"logps/chosen": -542.7330322265625,
|
| 1248 |
+
"logps/rejected": -477.4020080566406,
|
| 1249 |
+
"loss": 0.0857,
|
| 1250 |
+
"rewards/accuracies": 1.0,
|
| 1251 |
+
"rewards/chosen": 3.9007229804992676,
|
| 1252 |
+
"rewards/margins": 8.109764099121094,
|
| 1253 |
+
"rewards/rejected": -4.209041595458984,
|
| 1254 |
+
"step": 83
|
| 1255 |
+
},
|
| 1256 |
+
{
|
| 1257 |
+
"epoch": 1.1016393442622952,
|
| 1258 |
+
"grad_norm": 39.59391784667969,
|
| 1259 |
+
"learning_rate": 2.683823529411765e-06,
|
| 1260 |
+
"logits/chosen": -0.5291910767555237,
|
| 1261 |
+
"logits/rejected": -0.47945737838745117,
|
| 1262 |
+
"logps/chosen": -385.80242919921875,
|
| 1263 |
+
"logps/rejected": -362.5047912597656,
|
| 1264 |
+
"loss": 0.1411,
|
| 1265 |
+
"rewards/accuracies": 1.0,
|
| 1266 |
+
"rewards/chosen": 1.6711763143539429,
|
| 1267 |
+
"rewards/margins": 3.675436496734619,
|
| 1268 |
+
"rewards/rejected": -2.004260301589966,
|
| 1269 |
+
"step": 84
|
| 1270 |
+
},
|
| 1271 |
+
{
|
| 1272 |
+
"epoch": 1.1147540983606556,
|
| 1273 |
+
"grad_norm": 34.75082015991211,
|
| 1274 |
+
"learning_rate": 2.647058823529412e-06,
|
| 1275 |
+
"logits/chosen": -0.8582125902175903,
|
| 1276 |
+
"logits/rejected": -0.961124837398529,
|
| 1277 |
+
"logps/chosen": -127.2431640625,
|
| 1278 |
+
"logps/rejected": -181.58657836914062,
|
| 1279 |
+
"loss": 0.3015,
|
| 1280 |
+
"rewards/accuracies": 1.0,
|
| 1281 |
+
"rewards/chosen": 1.1156275272369385,
|
| 1282 |
+
"rewards/margins": 2.283085346221924,
|
| 1283 |
+
"rewards/rejected": -1.1674578189849854,
|
| 1284 |
+
"step": 85
|
| 1285 |
+
},
|
| 1286 |
+
{
|
| 1287 |
+
"epoch": 1.1278688524590164,
|
| 1288 |
+
"grad_norm": 18.05373191833496,
|
| 1289 |
+
"learning_rate": 2.610294117647059e-06,
|
| 1290 |
+
"logits/chosen": -0.8542808890342712,
|
| 1291 |
+
"logits/rejected": -0.6588492393493652,
|
| 1292 |
+
"logps/chosen": -249.22372436523438,
|
| 1293 |
+
"logps/rejected": -176.06527709960938,
|
| 1294 |
+
"loss": 0.1498,
|
| 1295 |
+
"rewards/accuracies": 1.0,
|
| 1296 |
+
"rewards/chosen": 1.803849697113037,
|
| 1297 |
+
"rewards/margins": 2.9191579818725586,
|
| 1298 |
+
"rewards/rejected": -1.115308165550232,
|
| 1299 |
+
"step": 86
|
| 1300 |
+
},
|
| 1301 |
+
{
|
| 1302 |
+
"epoch": 1.140983606557377,
|
| 1303 |
+
"grad_norm": 5.507705211639404,
|
| 1304 |
+
"learning_rate": 2.5735294117647057e-06,
|
| 1305 |
+
"logits/chosen": -0.4963078498840332,
|
| 1306 |
+
"logits/rejected": -0.8181336522102356,
|
| 1307 |
+
"logps/chosen": -108.07630920410156,
|
| 1308 |
+
"logps/rejected": -320.96392822265625,
|
| 1309 |
+
"loss": 0.0256,
|
| 1310 |
+
"rewards/accuracies": 1.0,
|
| 1311 |
+
"rewards/chosen": 1.0501946210861206,
|
| 1312 |
+
"rewards/margins": 4.599462032318115,
|
| 1313 |
+
"rewards/rejected": -3.549267292022705,
|
| 1314 |
+
"step": 87
|
| 1315 |
+
},
|
| 1316 |
+
{
|
| 1317 |
+
"epoch": 1.1540983606557378,
|
| 1318 |
+
"grad_norm": 12.978127479553223,
|
| 1319 |
+
"learning_rate": 2.536764705882353e-06,
|
| 1320 |
+
"logits/chosen": -0.8022123575210571,
|
| 1321 |
+
"logits/rejected": -0.8916893005371094,
|
| 1322 |
+
"logps/chosen": -98.68746948242188,
|
| 1323 |
+
"logps/rejected": -129.98577880859375,
|
| 1324 |
+
"loss": 0.2735,
|
| 1325 |
+
"rewards/accuracies": 1.0,
|
| 1326 |
+
"rewards/chosen": 0.5756351947784424,
|
| 1327 |
+
"rewards/margins": 1.4945859909057617,
|
| 1328 |
+
"rewards/rejected": -0.9189507961273193,
|
| 1329 |
+
"step": 88
|
| 1330 |
+
},
|
| 1331 |
+
{
|
| 1332 |
+
"epoch": 1.1672131147540983,
|
| 1333 |
+
"grad_norm": 8.445465087890625,
|
| 1334 |
+
"learning_rate": 2.5e-06,
|
| 1335 |
+
"logits/chosen": -0.238316610455513,
|
| 1336 |
+
"logits/rejected": -0.21277102828025818,
|
| 1337 |
+
"logps/chosen": -355.0726318359375,
|
| 1338 |
+
"logps/rejected": -468.03424072265625,
|
| 1339 |
+
"loss": 0.0439,
|
| 1340 |
+
"rewards/accuracies": 1.0,
|
| 1341 |
+
"rewards/chosen": 3.785343885421753,
|
| 1342 |
+
"rewards/margins": 8.177167892456055,
|
| 1343 |
+
"rewards/rejected": -4.391823768615723,
|
| 1344 |
+
"step": 89
|
| 1345 |
+
},
|
| 1346 |
+
{
|
| 1347 |
+
"epoch": 1.180327868852459,
|
| 1348 |
+
"grad_norm": 119.01290130615234,
|
| 1349 |
+
"learning_rate": 2.4632352941176473e-06,
|
| 1350 |
+
"logits/chosen": -0.38539862632751465,
|
| 1351 |
+
"logits/rejected": -0.2583141326904297,
|
| 1352 |
+
"logps/chosen": -479.6025695800781,
|
| 1353 |
+
"logps/rejected": -433.03045654296875,
|
| 1354 |
+
"loss": 0.2972,
|
| 1355 |
+
"rewards/accuracies": 0.75,
|
| 1356 |
+
"rewards/chosen": 2.800222873687744,
|
| 1357 |
+
"rewards/margins": 6.087710380554199,
|
| 1358 |
+
"rewards/rejected": -3.287487506866455,
|
| 1359 |
+
"step": 90
|
| 1360 |
+
},
|
| 1361 |
+
{
|
| 1362 |
+
"epoch": 1.1934426229508197,
|
| 1363 |
+
"grad_norm": 31.620267868041992,
|
| 1364 |
+
"learning_rate": 2.4264705882352943e-06,
|
| 1365 |
+
"logits/chosen": -0.5990991592407227,
|
| 1366 |
+
"logits/rejected": -0.4338776469230652,
|
| 1367 |
+
"logps/chosen": -287.31878662109375,
|
| 1368 |
+
"logps/rejected": -425.55963134765625,
|
| 1369 |
+
"loss": 0.2764,
|
| 1370 |
+
"rewards/accuracies": 1.0,
|
| 1371 |
+
"rewards/chosen": 1.9531813859939575,
|
| 1372 |
+
"rewards/margins": 4.420433044433594,
|
| 1373 |
+
"rewards/rejected": -2.4672515392303467,
|
| 1374 |
+
"step": 91
|
| 1375 |
+
},
|
| 1376 |
+
{
|
| 1377 |
+
"epoch": 1.2065573770491804,
|
| 1378 |
+
"grad_norm": 5.715668201446533,
|
| 1379 |
+
"learning_rate": 2.3897058823529414e-06,
|
| 1380 |
+
"logits/chosen": -0.5918264389038086,
|
| 1381 |
+
"logits/rejected": -0.34481585025787354,
|
| 1382 |
+
"logps/chosen": -462.36181640625,
|
| 1383 |
+
"logps/rejected": -291.8490295410156,
|
| 1384 |
+
"loss": 0.0246,
|
| 1385 |
+
"rewards/accuracies": 1.0,
|
| 1386 |
+
"rewards/chosen": 4.236080169677734,
|
| 1387 |
+
"rewards/margins": 6.656676292419434,
|
| 1388 |
+
"rewards/rejected": -2.420595645904541,
|
| 1389 |
+
"step": 92
|
| 1390 |
+
},
|
| 1391 |
+
{
|
| 1392 |
+
"epoch": 1.219672131147541,
|
| 1393 |
+
"grad_norm": 10.8475923538208,
|
| 1394 |
+
"learning_rate": 2.3529411764705885e-06,
|
| 1395 |
+
"logits/chosen": -0.48867395520210266,
|
| 1396 |
+
"logits/rejected": -0.2037501335144043,
|
| 1397 |
+
"logps/chosen": -248.76011657714844,
|
| 1398 |
+
"logps/rejected": -278.86505126953125,
|
| 1399 |
+
"loss": 0.0703,
|
| 1400 |
+
"rewards/accuracies": 1.0,
|
| 1401 |
+
"rewards/chosen": 2.4005353450775146,
|
| 1402 |
+
"rewards/margins": 3.532731056213379,
|
| 1403 |
+
"rewards/rejected": -1.1321957111358643,
|
| 1404 |
+
"step": 93
|
| 1405 |
+
},
|
| 1406 |
+
{
|
| 1407 |
+
"epoch": 1.2327868852459016,
|
| 1408 |
+
"grad_norm": 17.5373477935791,
|
| 1409 |
+
"learning_rate": 2.3161764705882355e-06,
|
| 1410 |
+
"logits/chosen": -0.800743043422699,
|
| 1411 |
+
"logits/rejected": -0.3216054141521454,
|
| 1412 |
+
"logps/chosen": -332.1054382324219,
|
| 1413 |
+
"logps/rejected": -262.9385070800781,
|
| 1414 |
+
"loss": 0.0781,
|
| 1415 |
+
"rewards/accuracies": 1.0,
|
| 1416 |
+
"rewards/chosen": 3.3670170307159424,
|
| 1417 |
+
"rewards/margins": 5.165108680725098,
|
| 1418 |
+
"rewards/rejected": -1.7980915307998657,
|
| 1419 |
+
"step": 94
|
| 1420 |
+
},
|
| 1421 |
+
{
|
| 1422 |
+
"epoch": 1.2459016393442623,
|
| 1423 |
+
"grad_norm": 17.166118621826172,
|
| 1424 |
+
"learning_rate": 2.2794117647058826e-06,
|
| 1425 |
+
"logits/chosen": -0.5876657366752625,
|
| 1426 |
+
"logits/rejected": -0.30134695768356323,
|
| 1427 |
+
"logps/chosen": -438.53070068359375,
|
| 1428 |
+
"logps/rejected": -283.11053466796875,
|
| 1429 |
+
"loss": 0.0878,
|
| 1430 |
+
"rewards/accuracies": 1.0,
|
| 1431 |
+
"rewards/chosen": 5.845110893249512,
|
| 1432 |
+
"rewards/margins": 7.538168430328369,
|
| 1433 |
+
"rewards/rejected": -1.6930572986602783,
|
| 1434 |
+
"step": 95
|
| 1435 |
+
},
|
| 1436 |
+
{
|
| 1437 |
+
"epoch": 1.2590163934426228,
|
| 1438 |
+
"grad_norm": 23.068361282348633,
|
| 1439 |
+
"learning_rate": 2.2426470588235296e-06,
|
| 1440 |
+
"logits/chosen": -0.6558918356895447,
|
| 1441 |
+
"logits/rejected": -0.3275706171989441,
|
| 1442 |
+
"logps/chosen": -370.03094482421875,
|
| 1443 |
+
"logps/rejected": -453.90203857421875,
|
| 1444 |
+
"loss": 0.1287,
|
| 1445 |
+
"rewards/accuracies": 1.0,
|
| 1446 |
+
"rewards/chosen": 2.0850746631622314,
|
| 1447 |
+
"rewards/margins": 4.879607677459717,
|
| 1448 |
+
"rewards/rejected": -2.7945332527160645,
|
| 1449 |
+
"step": 96
|
| 1450 |
+
},
|
| 1451 |
+
{
|
| 1452 |
+
"epoch": 1.2721311475409836,
|
| 1453 |
+
"grad_norm": 5.994075298309326,
|
| 1454 |
+
"learning_rate": 2.2058823529411767e-06,
|
| 1455 |
+
"logits/chosen": -0.6101892590522766,
|
| 1456 |
+
"logits/rejected": -0.5373432040214539,
|
| 1457 |
+
"logps/chosen": -347.5174560546875,
|
| 1458 |
+
"logps/rejected": -322.55023193359375,
|
| 1459 |
+
"loss": 0.0318,
|
| 1460 |
+
"rewards/accuracies": 1.0,
|
| 1461 |
+
"rewards/chosen": 2.3236427307128906,
|
| 1462 |
+
"rewards/margins": 4.85604190826416,
|
| 1463 |
+
"rewards/rejected": -2.5323991775512695,
|
| 1464 |
+
"step": 97
|
| 1465 |
+
},
|
| 1466 |
+
{
|
| 1467 |
+
"epoch": 1.2852459016393443,
|
| 1468 |
+
"grad_norm": 14.375985145568848,
|
| 1469 |
+
"learning_rate": 2.1691176470588238e-06,
|
| 1470 |
+
"logits/chosen": -0.6097806692123413,
|
| 1471 |
+
"logits/rejected": -0.5758112072944641,
|
| 1472 |
+
"logps/chosen": -341.9951477050781,
|
| 1473 |
+
"logps/rejected": -290.09136962890625,
|
| 1474 |
+
"loss": 0.1422,
|
| 1475 |
+
"rewards/accuracies": 1.0,
|
| 1476 |
+
"rewards/chosen": 2.372694253921509,
|
| 1477 |
+
"rewards/margins": 5.112575531005859,
|
| 1478 |
+
"rewards/rejected": -2.7398810386657715,
|
| 1479 |
+
"step": 98
|
| 1480 |
+
},
|
| 1481 |
+
{
|
| 1482 |
+
"epoch": 1.298360655737705,
|
| 1483 |
+
"grad_norm": 10.561140060424805,
|
| 1484 |
+
"learning_rate": 2.132352941176471e-06,
|
| 1485 |
+
"logits/chosen": -0.7798110842704773,
|
| 1486 |
+
"logits/rejected": -0.5334391593933105,
|
| 1487 |
+
"logps/chosen": -122.71707916259766,
|
| 1488 |
+
"logps/rejected": -138.75685119628906,
|
| 1489 |
+
"loss": 0.224,
|
| 1490 |
+
"rewards/accuracies": 0.75,
|
| 1491 |
+
"rewards/chosen": 0.45279568433761597,
|
| 1492 |
+
"rewards/margins": 2.1160295009613037,
|
| 1493 |
+
"rewards/rejected": -1.6632338762283325,
|
| 1494 |
+
"step": 99
|
| 1495 |
+
},
|
| 1496 |
+
{
|
| 1497 |
+
"epoch": 1.3114754098360657,
|
| 1498 |
+
"grad_norm": 8.718037605285645,
|
| 1499 |
+
"learning_rate": 2.095588235294118e-06,
|
| 1500 |
+
"logits/chosen": -0.5125188827514648,
|
| 1501 |
+
"logits/rejected": -0.35307127237319946,
|
| 1502 |
+
"logps/chosen": -180.09408569335938,
|
| 1503 |
+
"logps/rejected": -273.54046630859375,
|
| 1504 |
+
"loss": 0.0465,
|
| 1505 |
+
"rewards/accuracies": 1.0,
|
| 1506 |
+
"rewards/chosen": 1.8067989349365234,
|
| 1507 |
+
"rewards/margins": 5.022237777709961,
|
| 1508 |
+
"rewards/rejected": -3.2154390811920166,
|
| 1509 |
+
"step": 100
|
| 1510 |
+
},
|
| 1511 |
+
{
|
| 1512 |
+
"epoch": 1.3245901639344262,
|
| 1513 |
+
"grad_norm": 11.257354736328125,
|
| 1514 |
+
"learning_rate": 2.058823529411765e-06,
|
| 1515 |
+
"logits/chosen": -0.48480626940727234,
|
| 1516 |
+
"logits/rejected": -0.4184003174304962,
|
| 1517 |
+
"logps/chosen": -349.5723876953125,
|
| 1518 |
+
"logps/rejected": -458.3537902832031,
|
| 1519 |
+
"loss": 0.0341,
|
| 1520 |
+
"rewards/accuracies": 1.0,
|
| 1521 |
+
"rewards/chosen": 2.9435834884643555,
|
| 1522 |
+
"rewards/margins": 6.52362060546875,
|
| 1523 |
+
"rewards/rejected": -3.5800368785858154,
|
| 1524 |
+
"step": 101
|
| 1525 |
+
},
|
| 1526 |
+
{
|
| 1527 |
+
"epoch": 1.337704918032787,
|
| 1528 |
+
"grad_norm": 8.118950843811035,
|
| 1529 |
+
"learning_rate": 2.022058823529412e-06,
|
| 1530 |
+
"logits/chosen": -0.6667636632919312,
|
| 1531 |
+
"logits/rejected": -0.3804593086242676,
|
| 1532 |
+
"logps/chosen": -331.16015625,
|
| 1533 |
+
"logps/rejected": -266.6229248046875,
|
| 1534 |
+
"loss": 0.1422,
|
| 1535 |
+
"rewards/accuracies": 1.0,
|
| 1536 |
+
"rewards/chosen": 4.118168830871582,
|
| 1537 |
+
"rewards/margins": 5.915567398071289,
|
| 1538 |
+
"rewards/rejected": -1.797398328781128,
|
| 1539 |
+
"step": 102
|
| 1540 |
+
},
|
| 1541 |
+
{
|
| 1542 |
+
"epoch": 1.3508196721311476,
|
| 1543 |
+
"grad_norm": 14.03177547454834,
|
| 1544 |
+
"learning_rate": 1.985294117647059e-06,
|
| 1545 |
+
"logits/chosen": -0.34312984347343445,
|
| 1546 |
+
"logits/rejected": -0.5378394722938538,
|
| 1547 |
+
"logps/chosen": -205.9506378173828,
|
| 1548 |
+
"logps/rejected": -219.46360778808594,
|
| 1549 |
+
"loss": 0.113,
|
| 1550 |
+
"rewards/accuracies": 1.0,
|
| 1551 |
+
"rewards/chosen": 2.023257255554199,
|
| 1552 |
+
"rewards/margins": 3.4092535972595215,
|
| 1553 |
+
"rewards/rejected": -1.3859964609146118,
|
| 1554 |
+
"step": 103
|
| 1555 |
+
},
|
| 1556 |
+
{
|
| 1557 |
+
"epoch": 1.3639344262295081,
|
| 1558 |
+
"grad_norm": 2.7447023391723633,
|
| 1559 |
+
"learning_rate": 1.948529411764706e-06,
|
| 1560 |
+
"logits/chosen": -0.3522460162639618,
|
| 1561 |
+
"logits/rejected": -0.4929681122303009,
|
| 1562 |
+
"logps/chosen": -295.0723571777344,
|
| 1563 |
+
"logps/rejected": -344.48834228515625,
|
| 1564 |
+
"loss": 0.0114,
|
| 1565 |
+
"rewards/accuracies": 1.0,
|
| 1566 |
+
"rewards/chosen": 2.613781690597534,
|
| 1567 |
+
"rewards/margins": 6.21614408493042,
|
| 1568 |
+
"rewards/rejected": -3.602362871170044,
|
| 1569 |
+
"step": 104
|
| 1570 |
+
},
|
| 1571 |
+
{
|
| 1572 |
+
"epoch": 1.3770491803278688,
|
| 1573 |
+
"grad_norm": 3.9517393112182617,
|
| 1574 |
+
"learning_rate": 1.9117647058823528e-06,
|
| 1575 |
+
"logits/chosen": -0.5514786243438721,
|
| 1576 |
+
"logits/rejected": -0.515537440776825,
|
| 1577 |
+
"logps/chosen": -283.73504638671875,
|
| 1578 |
+
"logps/rejected": -354.9101257324219,
|
| 1579 |
+
"loss": 0.0147,
|
| 1580 |
+
"rewards/accuracies": 1.0,
|
| 1581 |
+
"rewards/chosen": 3.183412551879883,
|
| 1582 |
+
"rewards/margins": 6.139578819274902,
|
| 1583 |
+
"rewards/rejected": -2.9561657905578613,
|
| 1584 |
+
"step": 105
|
| 1585 |
+
},
|
| 1586 |
+
{
|
| 1587 |
+
"epoch": 1.3901639344262295,
|
| 1588 |
+
"grad_norm": 32.080848693847656,
|
| 1589 |
+
"learning_rate": 1.8750000000000003e-06,
|
| 1590 |
+
"logits/chosen": -0.34524667263031006,
|
| 1591 |
+
"logits/rejected": -0.2804412245750427,
|
| 1592 |
+
"logps/chosen": -487.1918029785156,
|
| 1593 |
+
"logps/rejected": -459.1595764160156,
|
| 1594 |
+
"loss": 0.1497,
|
| 1595 |
+
"rewards/accuracies": 1.0,
|
| 1596 |
+
"rewards/chosen": 3.4442732334136963,
|
| 1597 |
+
"rewards/margins": 6.211602210998535,
|
| 1598 |
+
"rewards/rejected": -2.767328977584839,
|
| 1599 |
+
"step": 106
|
| 1600 |
+
},
|
| 1601 |
+
{
|
| 1602 |
+
"epoch": 1.40327868852459,
|
| 1603 |
+
"grad_norm": 6.278583526611328,
|
| 1604 |
+
"learning_rate": 1.8382352941176473e-06,
|
| 1605 |
+
"logits/chosen": -1.0492626428604126,
|
| 1606 |
+
"logits/rejected": -0.637208878993988,
|
| 1607 |
+
"logps/chosen": -508.1822509765625,
|
| 1608 |
+
"logps/rejected": -264.3661804199219,
|
| 1609 |
+
"loss": 0.0256,
|
| 1610 |
+
"rewards/accuracies": 1.0,
|
| 1611 |
+
"rewards/chosen": 3.434685230255127,
|
| 1612 |
+
"rewards/margins": 5.93399715423584,
|
| 1613 |
+
"rewards/rejected": -2.4993114471435547,
|
| 1614 |
+
"step": 107
|
| 1615 |
+
},
|
| 1616 |
+
{
|
| 1617 |
+
"epoch": 1.4163934426229507,
|
| 1618 |
+
"grad_norm": 3.8192379474639893,
|
| 1619 |
+
"learning_rate": 1.8014705882352942e-06,
|
| 1620 |
+
"logits/chosen": -0.49397462606430054,
|
| 1621 |
+
"logits/rejected": -0.39174699783325195,
|
| 1622 |
+
"logps/chosen": -250.099853515625,
|
| 1623 |
+
"logps/rejected": -342.03033447265625,
|
| 1624 |
+
"loss": 0.0194,
|
| 1625 |
+
"rewards/accuracies": 1.0,
|
| 1626 |
+
"rewards/chosen": 1.3859384059906006,
|
| 1627 |
+
"rewards/margins": 4.495996475219727,
|
| 1628 |
+
"rewards/rejected": -3.110058307647705,
|
| 1629 |
+
"step": 108
|
| 1630 |
+
},
|
| 1631 |
+
{
|
| 1632 |
+
"epoch": 1.4295081967213115,
|
| 1633 |
+
"grad_norm": 5.807373523712158,
|
| 1634 |
+
"learning_rate": 1.7647058823529414e-06,
|
| 1635 |
+
"logits/chosen": -0.584580659866333,
|
| 1636 |
+
"logits/rejected": -0.15329986810684204,
|
| 1637 |
+
"logps/chosen": -442.9632873535156,
|
| 1638 |
+
"logps/rejected": -318.378173828125,
|
| 1639 |
+
"loss": 0.0165,
|
| 1640 |
+
"rewards/accuracies": 1.0,
|
| 1641 |
+
"rewards/chosen": 2.1344716548919678,
|
| 1642 |
+
"rewards/margins": 5.192463397979736,
|
| 1643 |
+
"rewards/rejected": -3.0579919815063477,
|
| 1644 |
+
"step": 109
|
| 1645 |
+
},
|
| 1646 |
+
{
|
| 1647 |
+
"epoch": 1.4426229508196722,
|
| 1648 |
+
"grad_norm": 3.5901246070861816,
|
| 1649 |
+
"learning_rate": 1.7279411764705883e-06,
|
| 1650 |
+
"logits/chosen": -0.5349779725074768,
|
| 1651 |
+
"logits/rejected": -0.2637510299682617,
|
| 1652 |
+
"logps/chosen": -414.6310729980469,
|
| 1653 |
+
"logps/rejected": -428.139404296875,
|
| 1654 |
+
"loss": 0.0136,
|
| 1655 |
+
"rewards/accuracies": 1.0,
|
| 1656 |
+
"rewards/chosen": 2.6161444187164307,
|
| 1657 |
+
"rewards/margins": 7.400443077087402,
|
| 1658 |
+
"rewards/rejected": -4.784298896789551,
|
| 1659 |
+
"step": 110
|
| 1660 |
+
},
|
| 1661 |
+
{
|
| 1662 |
+
"epoch": 1.455737704918033,
|
| 1663 |
+
"grad_norm": 17.46812629699707,
|
| 1664 |
+
"learning_rate": 1.6911764705882356e-06,
|
| 1665 |
+
"logits/chosen": -0.6205960512161255,
|
| 1666 |
+
"logits/rejected": -0.6515633463859558,
|
| 1667 |
+
"logps/chosen": -233.56886291503906,
|
| 1668 |
+
"logps/rejected": -327.51611328125,
|
| 1669 |
+
"loss": 0.1822,
|
| 1670 |
+
"rewards/accuracies": 1.0,
|
| 1671 |
+
"rewards/chosen": 1.1055248975753784,
|
| 1672 |
+
"rewards/margins": 4.226891994476318,
|
| 1673 |
+
"rewards/rejected": -3.1213672161102295,
|
| 1674 |
+
"step": 111
|
| 1675 |
+
},
|
| 1676 |
+
{
|
| 1677 |
+
"epoch": 1.4688524590163934,
|
| 1678 |
+
"grad_norm": 11.27214241027832,
|
| 1679 |
+
"learning_rate": 1.6544117647058824e-06,
|
| 1680 |
+
"logits/chosen": -0.3313244581222534,
|
| 1681 |
+
"logits/rejected": -0.22155167162418365,
|
| 1682 |
+
"logps/chosen": -391.53466796875,
|
| 1683 |
+
"logps/rejected": -230.6190643310547,
|
| 1684 |
+
"loss": 0.1142,
|
| 1685 |
+
"rewards/accuracies": 1.0,
|
| 1686 |
+
"rewards/chosen": 2.988477945327759,
|
| 1687 |
+
"rewards/margins": 5.188130855560303,
|
| 1688 |
+
"rewards/rejected": -2.199653148651123,
|
| 1689 |
+
"step": 112
|
| 1690 |
+
},
|
| 1691 |
+
{
|
| 1692 |
+
"epoch": 1.481967213114754,
|
| 1693 |
+
"grad_norm": 9.786858558654785,
|
| 1694 |
+
"learning_rate": 1.6176470588235297e-06,
|
| 1695 |
+
"logits/chosen": -0.5634331703186035,
|
| 1696 |
+
"logits/rejected": -0.4348165690898895,
|
| 1697 |
+
"logps/chosen": -252.67152404785156,
|
| 1698 |
+
"logps/rejected": -352.4822998046875,
|
| 1699 |
+
"loss": 0.0467,
|
| 1700 |
+
"rewards/accuracies": 1.0,
|
| 1701 |
+
"rewards/chosen": 1.8047726154327393,
|
| 1702 |
+
"rewards/margins": 6.142679691314697,
|
| 1703 |
+
"rewards/rejected": -4.337907314300537,
|
| 1704 |
+
"step": 113
|
| 1705 |
+
},
|
| 1706 |
+
{
|
| 1707 |
+
"epoch": 1.4950819672131148,
|
| 1708 |
+
"grad_norm": 4.376170635223389,
|
| 1709 |
+
"learning_rate": 1.5808823529411765e-06,
|
| 1710 |
+
"logits/chosen": -0.15515179932117462,
|
| 1711 |
+
"logits/rejected": -0.1870616376399994,
|
| 1712 |
+
"logps/chosen": -289.219970703125,
|
| 1713 |
+
"logps/rejected": -400.1667175292969,
|
| 1714 |
+
"loss": 0.0207,
|
| 1715 |
+
"rewards/accuracies": 1.0,
|
| 1716 |
+
"rewards/chosen": 2.1680092811584473,
|
| 1717 |
+
"rewards/margins": 4.854602336883545,
|
| 1718 |
+
"rewards/rejected": -2.6865930557250977,
|
| 1719 |
+
"step": 114
|
| 1720 |
+
},
|
| 1721 |
+
{
|
| 1722 |
+
"epoch": 1.5081967213114753,
|
| 1723 |
+
"grad_norm": 3.8763139247894287,
|
| 1724 |
+
"learning_rate": 1.5441176470588238e-06,
|
| 1725 |
+
"logits/chosen": -0.2717803716659546,
|
| 1726 |
+
"logits/rejected": -0.17628008127212524,
|
| 1727 |
+
"logps/chosen": -546.1766357421875,
|
| 1728 |
+
"logps/rejected": -451.3502502441406,
|
| 1729 |
+
"loss": 0.0166,
|
| 1730 |
+
"rewards/accuracies": 1.0,
|
| 1731 |
+
"rewards/chosen": 2.681325912475586,
|
| 1732 |
+
"rewards/margins": 5.725113868713379,
|
| 1733 |
+
"rewards/rejected": -3.0437874794006348,
|
| 1734 |
+
"step": 115
|
| 1735 |
+
},
|
| 1736 |
+
{
|
| 1737 |
+
"epoch": 1.521311475409836,
|
| 1738 |
+
"grad_norm": 30.37358283996582,
|
| 1739 |
+
"learning_rate": 1.5073529411764707e-06,
|
| 1740 |
+
"logits/chosen": -0.9199023246765137,
|
| 1741 |
+
"logits/rejected": -0.8192650079727173,
|
| 1742 |
+
"logps/chosen": -247.5410919189453,
|
| 1743 |
+
"logps/rejected": -390.4881896972656,
|
| 1744 |
+
"loss": 0.1679,
|
| 1745 |
+
"rewards/accuracies": 1.0,
|
| 1746 |
+
"rewards/chosen": 1.817814588546753,
|
| 1747 |
+
"rewards/margins": 4.526091575622559,
|
| 1748 |
+
"rewards/rejected": -2.7082767486572266,
|
| 1749 |
+
"step": 116
|
| 1750 |
+
},
|
| 1751 |
+
{
|
| 1752 |
+
"epoch": 1.5344262295081967,
|
| 1753 |
+
"grad_norm": 17.32929229736328,
|
| 1754 |
+
"learning_rate": 1.4705882352941177e-06,
|
| 1755 |
+
"logits/chosen": -0.4218984842300415,
|
| 1756 |
+
"logits/rejected": -0.411405086517334,
|
| 1757 |
+
"logps/chosen": -202.14004516601562,
|
| 1758 |
+
"logps/rejected": -220.29254150390625,
|
| 1759 |
+
"loss": 0.1733,
|
| 1760 |
+
"rewards/accuracies": 1.0,
|
| 1761 |
+
"rewards/chosen": 1.8182326555252075,
|
| 1762 |
+
"rewards/margins": 3.9761695861816406,
|
| 1763 |
+
"rewards/rejected": -2.1579370498657227,
|
| 1764 |
+
"step": 117
|
| 1765 |
+
},
|
| 1766 |
+
{
|
| 1767 |
+
"epoch": 1.5475409836065572,
|
| 1768 |
+
"grad_norm": 15.47387981414795,
|
| 1769 |
+
"learning_rate": 1.4338235294117648e-06,
|
| 1770 |
+
"logits/chosen": -0.6655436754226685,
|
| 1771 |
+
"logits/rejected": -0.9528688192367554,
|
| 1772 |
+
"logps/chosen": -110.75199890136719,
|
| 1773 |
+
"logps/rejected": -216.50701904296875,
|
| 1774 |
+
"loss": 0.0995,
|
| 1775 |
+
"rewards/accuracies": 1.0,
|
| 1776 |
+
"rewards/chosen": 0.448855996131897,
|
| 1777 |
+
"rewards/margins": 2.9766037464141846,
|
| 1778 |
+
"rewards/rejected": -2.5277481079101562,
|
| 1779 |
+
"step": 118
|
| 1780 |
+
},
|
| 1781 |
+
{
|
| 1782 |
+
"epoch": 1.5606557377049182,
|
| 1783 |
+
"grad_norm": 56.997802734375,
|
| 1784 |
+
"learning_rate": 1.3970588235294119e-06,
|
| 1785 |
+
"logits/chosen": -0.3543809652328491,
|
| 1786 |
+
"logits/rejected": -0.5634450912475586,
|
| 1787 |
+
"logps/chosen": -307.3863525390625,
|
| 1788 |
+
"logps/rejected": -422.4675598144531,
|
| 1789 |
+
"loss": 0.19,
|
| 1790 |
+
"rewards/accuracies": 0.75,
|
| 1791 |
+
"rewards/chosen": 1.821000337600708,
|
| 1792 |
+
"rewards/margins": 5.365086555480957,
|
| 1793 |
+
"rewards/rejected": -3.5440866947174072,
|
| 1794 |
+
"step": 119
|
| 1795 |
+
},
|
| 1796 |
+
{
|
| 1797 |
+
"epoch": 1.5737704918032787,
|
| 1798 |
+
"grad_norm": 5.717536926269531,
|
| 1799 |
+
"learning_rate": 1.360294117647059e-06,
|
| 1800 |
+
"logits/chosen": -0.394744873046875,
|
| 1801 |
+
"logits/rejected": -0.46669620275497437,
|
| 1802 |
+
"logps/chosen": -162.78341674804688,
|
| 1803 |
+
"logps/rejected": -354.51654052734375,
|
| 1804 |
+
"loss": 0.0251,
|
| 1805 |
+
"rewards/accuracies": 1.0,
|
| 1806 |
+
"rewards/chosen": 1.3121498823165894,
|
| 1807 |
+
"rewards/margins": 5.8546037673950195,
|
| 1808 |
+
"rewards/rejected": -4.542453765869141,
|
| 1809 |
+
"step": 120
|
| 1810 |
+
},
|
| 1811 |
+
{
|
| 1812 |
+
"epoch": 1.5868852459016394,
|
| 1813 |
+
"grad_norm": 102.92301177978516,
|
| 1814 |
+
"learning_rate": 1.323529411764706e-06,
|
| 1815 |
+
"logits/chosen": -0.8797488212585449,
|
| 1816 |
+
"logits/rejected": -0.5256719589233398,
|
| 1817 |
+
"logps/chosen": -400.2969055175781,
|
| 1818 |
+
"logps/rejected": -228.6015625,
|
| 1819 |
+
"loss": 0.3735,
|
| 1820 |
+
"rewards/accuracies": 0.75,
|
| 1821 |
+
"rewards/chosen": 1.3958312273025513,
|
| 1822 |
+
"rewards/margins": 2.500825881958008,
|
| 1823 |
+
"rewards/rejected": -1.1049946546554565,
|
| 1824 |
+
"step": 121
|
| 1825 |
+
},
|
| 1826 |
+
{
|
| 1827 |
+
"epoch": 1.6,
|
| 1828 |
+
"grad_norm": 12.96183967590332,
|
| 1829 |
+
"learning_rate": 1.2867647058823528e-06,
|
| 1830 |
+
"logits/chosen": -0.1941753625869751,
|
| 1831 |
+
"logits/rejected": -0.2740371525287628,
|
| 1832 |
+
"logps/chosen": -146.65438842773438,
|
| 1833 |
+
"logps/rejected": -286.4040832519531,
|
| 1834 |
+
"loss": 0.0833,
|
| 1835 |
+
"rewards/accuracies": 1.0,
|
| 1836 |
+
"rewards/chosen": 1.6577894687652588,
|
| 1837 |
+
"rewards/margins": 5.093594074249268,
|
| 1838 |
+
"rewards/rejected": -3.4358043670654297,
|
| 1839 |
+
"step": 122
|
| 1840 |
+
},
|
| 1841 |
+
{
|
| 1842 |
+
"epoch": 1.6131147540983606,
|
| 1843 |
+
"grad_norm": 1.308056354522705,
|
| 1844 |
+
"learning_rate": 1.25e-06,
|
| 1845 |
+
"logits/chosen": -0.2991219460964203,
|
| 1846 |
+
"logits/rejected": -0.608604371547699,
|
| 1847 |
+
"logps/chosen": -332.8055419921875,
|
| 1848 |
+
"logps/rejected": -501.82794189453125,
|
| 1849 |
+
"loss": 0.0056,
|
| 1850 |
+
"rewards/accuracies": 1.0,
|
| 1851 |
+
"rewards/chosen": 1.9228206872940063,
|
| 1852 |
+
"rewards/margins": 6.52579927444458,
|
| 1853 |
+
"rewards/rejected": -4.602978706359863,
|
| 1854 |
+
"step": 123
|
| 1855 |
+
},
|
| 1856 |
+
{
|
| 1857 |
+
"epoch": 1.6262295081967213,
|
| 1858 |
+
"grad_norm": 6.536846160888672,
|
| 1859 |
+
"learning_rate": 1.2132352941176472e-06,
|
| 1860 |
+
"logits/chosen": -0.5168918371200562,
|
| 1861 |
+
"logits/rejected": -0.8077197670936584,
|
| 1862 |
+
"logps/chosen": -200.44891357421875,
|
| 1863 |
+
"logps/rejected": -283.05535888671875,
|
| 1864 |
+
"loss": 0.0305,
|
| 1865 |
+
"rewards/accuracies": 1.0,
|
| 1866 |
+
"rewards/chosen": 1.2009633779525757,
|
| 1867 |
+
"rewards/margins": 4.113708019256592,
|
| 1868 |
+
"rewards/rejected": -2.9127449989318848,
|
| 1869 |
+
"step": 124
|
| 1870 |
+
},
|
| 1871 |
+
{
|
| 1872 |
+
"epoch": 1.639344262295082,
|
| 1873 |
+
"grad_norm": 14.031917572021484,
|
| 1874 |
+
"learning_rate": 1.1764705882352942e-06,
|
| 1875 |
+
"logits/chosen": -0.2985928952693939,
|
| 1876 |
+
"logits/rejected": -0.5871812701225281,
|
| 1877 |
+
"logps/chosen": -203.19163513183594,
|
| 1878 |
+
"logps/rejected": -404.0279846191406,
|
| 1879 |
+
"loss": 0.1122,
|
| 1880 |
+
"rewards/accuracies": 1.0,
|
| 1881 |
+
"rewards/chosen": 1.369646668434143,
|
| 1882 |
+
"rewards/margins": 5.168557643890381,
|
| 1883 |
+
"rewards/rejected": -3.7989113330841064,
|
| 1884 |
+
"step": 125
|
| 1885 |
+
},
|
| 1886 |
+
{
|
| 1887 |
+
"epoch": 1.6524590163934425,
|
| 1888 |
+
"grad_norm": 1.0998114347457886,
|
| 1889 |
+
"learning_rate": 1.1397058823529413e-06,
|
| 1890 |
+
"logits/chosen": -0.9684606790542603,
|
| 1891 |
+
"logits/rejected": -0.8049026727676392,
|
| 1892 |
+
"logps/chosen": -247.9980010986328,
|
| 1893 |
+
"logps/rejected": -212.36807250976562,
|
| 1894 |
+
"loss": 0.178,
|
| 1895 |
+
"rewards/accuracies": 0.75,
|
| 1896 |
+
"rewards/chosen": 2.4171135425567627,
|
| 1897 |
+
"rewards/margins": 5.950634002685547,
|
| 1898 |
+
"rewards/rejected": -3.533520460128784,
|
| 1899 |
+
"step": 126
|
| 1900 |
+
},
|
| 1901 |
+
{
|
| 1902 |
+
"epoch": 1.6655737704918034,
|
| 1903 |
+
"grad_norm": 1.8453718423843384,
|
| 1904 |
+
"learning_rate": 1.1029411764705884e-06,
|
| 1905 |
+
"logits/chosen": -0.4717595875263214,
|
| 1906 |
+
"logits/rejected": -0.13389728963375092,
|
| 1907 |
+
"logps/chosen": -400.8570251464844,
|
| 1908 |
+
"logps/rejected": -322.6037902832031,
|
| 1909 |
+
"loss": 0.0069,
|
| 1910 |
+
"rewards/accuracies": 1.0,
|
| 1911 |
+
"rewards/chosen": 3.168325901031494,
|
| 1912 |
+
"rewards/margins": 6.738244533538818,
|
| 1913 |
+
"rewards/rejected": -3.569918155670166,
|
| 1914 |
+
"step": 127
|
| 1915 |
+
},
|
| 1916 |
+
{
|
| 1917 |
+
"epoch": 1.678688524590164,
|
| 1918 |
+
"grad_norm": 9.327398300170898,
|
| 1919 |
+
"learning_rate": 1.0661764705882354e-06,
|
| 1920 |
+
"logits/chosen": -0.45057347416877747,
|
| 1921 |
+
"logits/rejected": -0.22152967751026154,
|
| 1922 |
+
"logps/chosen": -261.6713562011719,
|
| 1923 |
+
"logps/rejected": -318.07391357421875,
|
| 1924 |
+
"loss": 0.0558,
|
| 1925 |
+
"rewards/accuracies": 1.0,
|
| 1926 |
+
"rewards/chosen": 2.15228271484375,
|
| 1927 |
+
"rewards/margins": 5.979676723480225,
|
| 1928 |
+
"rewards/rejected": -3.8273940086364746,
|
| 1929 |
+
"step": 128
|
| 1930 |
+
},
|
| 1931 |
+
{
|
| 1932 |
+
"epoch": 1.6918032786885244,
|
| 1933 |
+
"grad_norm": 21.2039737701416,
|
| 1934 |
+
"learning_rate": 1.0294117647058825e-06,
|
| 1935 |
+
"logits/chosen": -0.5791776180267334,
|
| 1936 |
+
"logits/rejected": -0.8412386178970337,
|
| 1937 |
+
"logps/chosen": -132.2311553955078,
|
| 1938 |
+
"logps/rejected": -418.17657470703125,
|
| 1939 |
+
"loss": 0.1523,
|
| 1940 |
+
"rewards/accuracies": 1.0,
|
| 1941 |
+
"rewards/chosen": 0.6422145962715149,
|
| 1942 |
+
"rewards/margins": 6.080798625946045,
|
| 1943 |
+
"rewards/rejected": -5.438583850860596,
|
| 1944 |
+
"step": 129
|
| 1945 |
+
},
|
| 1946 |
+
{
|
| 1947 |
+
"epoch": 1.7049180327868854,
|
| 1948 |
+
"grad_norm": 0.3313053250312805,
|
| 1949 |
+
"learning_rate": 9.926470588235295e-07,
|
| 1950 |
+
"logits/chosen": -0.7310227155685425,
|
| 1951 |
+
"logits/rejected": -0.6085512638092041,
|
| 1952 |
+
"logps/chosen": -517.57373046875,
|
| 1953 |
+
"logps/rejected": -645.620849609375,
|
| 1954 |
+
"loss": 0.001,
|
| 1955 |
+
"rewards/accuracies": 1.0,
|
| 1956 |
+
"rewards/chosen": 3.5617308616638184,
|
| 1957 |
+
"rewards/margins": 8.085519790649414,
|
| 1958 |
+
"rewards/rejected": -4.5237884521484375,
|
| 1959 |
+
"step": 130
|
| 1960 |
+
},
|
| 1961 |
+
{
|
| 1962 |
+
"epoch": 1.7180327868852459,
|
| 1963 |
+
"grad_norm": 71.060546875,
|
| 1964 |
+
"learning_rate": 9.558823529411764e-07,
|
| 1965 |
+
"logits/chosen": -0.6338833570480347,
|
| 1966 |
+
"logits/rejected": -0.897128701210022,
|
| 1967 |
+
"logps/chosen": -193.55189514160156,
|
| 1968 |
+
"logps/rejected": -340.1580810546875,
|
| 1969 |
+
"loss": 0.3464,
|
| 1970 |
+
"rewards/accuracies": 0.75,
|
| 1971 |
+
"rewards/chosen": 0.23160991072654724,
|
| 1972 |
+
"rewards/margins": 1.533915400505066,
|
| 1973 |
+
"rewards/rejected": -1.3023054599761963,
|
| 1974 |
+
"step": 131
|
| 1975 |
+
},
|
| 1976 |
+
{
|
| 1977 |
+
"epoch": 1.7311475409836066,
|
| 1978 |
+
"grad_norm": 11.899687767028809,
|
| 1979 |
+
"learning_rate": 9.191176470588237e-07,
|
| 1980 |
+
"logits/chosen": -0.8149244785308838,
|
| 1981 |
+
"logits/rejected": -0.5785297155380249,
|
| 1982 |
+
"logps/chosen": -213.12173461914062,
|
| 1983 |
+
"logps/rejected": -237.8140411376953,
|
| 1984 |
+
"loss": 0.0893,
|
| 1985 |
+
"rewards/accuracies": 1.0,
|
| 1986 |
+
"rewards/chosen": 1.6387001276016235,
|
| 1987 |
+
"rewards/margins": 3.045469284057617,
|
| 1988 |
+
"rewards/rejected": -1.4067691564559937,
|
| 1989 |
+
"step": 132
|
| 1990 |
+
},
|
| 1991 |
+
{
|
| 1992 |
+
"epoch": 1.7442622950819673,
|
| 1993 |
+
"grad_norm": 1.8859055042266846,
|
| 1994 |
+
"learning_rate": 8.823529411764707e-07,
|
| 1995 |
+
"logits/chosen": -0.40556299686431885,
|
| 1996 |
+
"logits/rejected": -0.577975332736969,
|
| 1997 |
+
"logps/chosen": -514.1160888671875,
|
| 1998 |
+
"logps/rejected": -692.885009765625,
|
| 1999 |
+
"loss": 0.0032,
|
| 2000 |
+
"rewards/accuracies": 1.0,
|
| 2001 |
+
"rewards/chosen": 2.4865522384643555,
|
| 2002 |
+
"rewards/margins": 9.726764678955078,
|
| 2003 |
+
"rewards/rejected": -7.240212440490723,
|
| 2004 |
+
"step": 133
|
| 2005 |
+
},
|
| 2006 |
+
{
|
| 2007 |
+
"epoch": 1.7573770491803278,
|
| 2008 |
+
"grad_norm": 15.04454517364502,
|
| 2009 |
+
"learning_rate": 8.455882352941178e-07,
|
| 2010 |
+
"logits/chosen": -0.7795289754867554,
|
| 2011 |
+
"logits/rejected": -0.8595843315124512,
|
| 2012 |
+
"logps/chosen": -117.66368103027344,
|
| 2013 |
+
"logps/rejected": -155.0380859375,
|
| 2014 |
+
"loss": 0.1567,
|
| 2015 |
+
"rewards/accuracies": 1.0,
|
| 2016 |
+
"rewards/chosen": 1.0589184761047363,
|
| 2017 |
+
"rewards/margins": 2.530170440673828,
|
| 2018 |
+
"rewards/rejected": -1.4712518453598022,
|
| 2019 |
+
"step": 134
|
| 2020 |
+
},
|
| 2021 |
+
{
|
| 2022 |
+
"epoch": 1.7704918032786885,
|
| 2023 |
+
"grad_norm": 79.06763458251953,
|
| 2024 |
+
"learning_rate": 8.088235294117648e-07,
|
| 2025 |
+
"logits/chosen": -0.7521681189537048,
|
| 2026 |
+
"logits/rejected": -0.5849143862724304,
|
| 2027 |
+
"logps/chosen": -370.17303466796875,
|
| 2028 |
+
"logps/rejected": -297.7393493652344,
|
| 2029 |
+
"loss": 0.3304,
|
| 2030 |
+
"rewards/accuracies": 0.75,
|
| 2031 |
+
"rewards/chosen": 1.5731346607208252,
|
| 2032 |
+
"rewards/margins": 4.559065341949463,
|
| 2033 |
+
"rewards/rejected": -2.9859304428100586,
|
| 2034 |
+
"step": 135
|
| 2035 |
+
},
|
| 2036 |
+
{
|
| 2037 |
+
"epoch": 1.7836065573770492,
|
| 2038 |
+
"grad_norm": 75.73023223876953,
|
| 2039 |
+
"learning_rate": 7.720588235294119e-07,
|
| 2040 |
+
"logits/chosen": -0.24577771127223969,
|
| 2041 |
+
"logits/rejected": -0.2834129333496094,
|
| 2042 |
+
"logps/chosen": -169.0641632080078,
|
| 2043 |
+
"logps/rejected": -227.2678985595703,
|
| 2044 |
+
"loss": 0.1953,
|
| 2045 |
+
"rewards/accuracies": 1.0,
|
| 2046 |
+
"rewards/chosen": 0.9874727725982666,
|
| 2047 |
+
"rewards/margins": 2.466601848602295,
|
| 2048 |
+
"rewards/rejected": -1.4791290760040283,
|
| 2049 |
+
"step": 136
|
| 2050 |
+
},
|
| 2051 |
+
{
|
| 2052 |
+
"epoch": 1.7967213114754097,
|
| 2053 |
+
"grad_norm": 13.235738754272461,
|
| 2054 |
+
"learning_rate": 7.352941176470589e-07,
|
| 2055 |
+
"logits/chosen": -0.8364167213439941,
|
| 2056 |
+
"logits/rejected": -0.7191005349159241,
|
| 2057 |
+
"logps/chosen": -281.6129150390625,
|
| 2058 |
+
"logps/rejected": -327.17169189453125,
|
| 2059 |
+
"loss": 0.0731,
|
| 2060 |
+
"rewards/accuracies": 1.0,
|
| 2061 |
+
"rewards/chosen": 2.5926880836486816,
|
| 2062 |
+
"rewards/margins": 5.672669410705566,
|
| 2063 |
+
"rewards/rejected": -3.0799813270568848,
|
| 2064 |
+
"step": 137
|
| 2065 |
+
},
|
| 2066 |
+
{
|
| 2067 |
+
"epoch": 1.8098360655737706,
|
| 2068 |
+
"grad_norm": 5.092410087585449,
|
| 2069 |
+
"learning_rate": 6.985294117647059e-07,
|
| 2070 |
+
"logits/chosen": -0.6490945219993591,
|
| 2071 |
+
"logits/rejected": -0.9161443710327148,
|
| 2072 |
+
"logps/chosen": -366.2134704589844,
|
| 2073 |
+
"logps/rejected": -429.5161437988281,
|
| 2074 |
+
"loss": 0.0178,
|
| 2075 |
+
"rewards/accuracies": 1.0,
|
| 2076 |
+
"rewards/chosen": 1.8624721765518188,
|
| 2077 |
+
"rewards/margins": 6.365274906158447,
|
| 2078 |
+
"rewards/rejected": -4.50280237197876,
|
| 2079 |
+
"step": 138
|
| 2080 |
+
},
|
| 2081 |
+
{
|
| 2082 |
+
"epoch": 1.8229508196721311,
|
| 2083 |
+
"grad_norm": 3.215587615966797,
|
| 2084 |
+
"learning_rate": 6.61764705882353e-07,
|
| 2085 |
+
"logits/chosen": -0.7531751990318298,
|
| 2086 |
+
"logits/rejected": -0.30548983812332153,
|
| 2087 |
+
"logps/chosen": -386.60504150390625,
|
| 2088 |
+
"logps/rejected": -275.23779296875,
|
| 2089 |
+
"loss": 0.0127,
|
| 2090 |
+
"rewards/accuracies": 1.0,
|
| 2091 |
+
"rewards/chosen": 3.7106332778930664,
|
| 2092 |
+
"rewards/margins": 6.189945220947266,
|
| 2093 |
+
"rewards/rejected": -2.4793121814727783,
|
| 2094 |
+
"step": 139
|
| 2095 |
+
},
|
| 2096 |
+
{
|
| 2097 |
+
"epoch": 1.8360655737704918,
|
| 2098 |
+
"grad_norm": 0.22684346139431,
|
| 2099 |
+
"learning_rate": 6.25e-07,
|
| 2100 |
+
"logits/chosen": -0.38512834906578064,
|
| 2101 |
+
"logits/rejected": -0.39937111735343933,
|
| 2102 |
+
"logps/chosen": -506.0502624511719,
|
| 2103 |
+
"logps/rejected": -478.14990234375,
|
| 2104 |
+
"loss": 0.0006,
|
| 2105 |
+
"rewards/accuracies": 1.0,
|
| 2106 |
+
"rewards/chosen": 4.004444599151611,
|
| 2107 |
+
"rewards/margins": 9.403310775756836,
|
| 2108 |
+
"rewards/rejected": -5.398866653442383,
|
| 2109 |
+
"step": 140
|
| 2110 |
+
},
|
| 2111 |
+
{
|
| 2112 |
+
"epoch": 1.8491803278688526,
|
| 2113 |
+
"grad_norm": 8.121055603027344,
|
| 2114 |
+
"learning_rate": 5.882352941176471e-07,
|
| 2115 |
+
"logits/chosen": -0.5020557045936584,
|
| 2116 |
+
"logits/rejected": -0.6416282653808594,
|
| 2117 |
+
"logps/chosen": -369.1741027832031,
|
| 2118 |
+
"logps/rejected": -440.558837890625,
|
| 2119 |
+
"loss": 0.0314,
|
| 2120 |
+
"rewards/accuracies": 1.0,
|
| 2121 |
+
"rewards/chosen": 3.697706699371338,
|
| 2122 |
+
"rewards/margins": 7.363080024719238,
|
| 2123 |
+
"rewards/rejected": -3.6653730869293213,
|
| 2124 |
+
"step": 141
|
| 2125 |
+
},
|
| 2126 |
+
{
|
| 2127 |
+
"epoch": 1.862295081967213,
|
| 2128 |
+
"grad_norm": 25.55944061279297,
|
| 2129 |
+
"learning_rate": 5.514705882352942e-07,
|
| 2130 |
+
"logits/chosen": -0.6144732236862183,
|
| 2131 |
+
"logits/rejected": -0.5314571857452393,
|
| 2132 |
+
"logps/chosen": -412.43310546875,
|
| 2133 |
+
"logps/rejected": -425.11572265625,
|
| 2134 |
+
"loss": 0.0594,
|
| 2135 |
+
"rewards/accuracies": 1.0,
|
| 2136 |
+
"rewards/chosen": 2.2833995819091797,
|
| 2137 |
+
"rewards/margins": 5.651876926422119,
|
| 2138 |
+
"rewards/rejected": -3.3684768676757812,
|
| 2139 |
+
"step": 142
|
| 2140 |
+
},
|
| 2141 |
+
{
|
| 2142 |
+
"epoch": 1.8754098360655738,
|
| 2143 |
+
"grad_norm": 2.3017585277557373,
|
| 2144 |
+
"learning_rate": 5.147058823529412e-07,
|
| 2145 |
+
"logits/chosen": -0.7556811571121216,
|
| 2146 |
+
"logits/rejected": -0.8270020484924316,
|
| 2147 |
+
"logps/chosen": -401.3725280761719,
|
| 2148 |
+
"logps/rejected": -348.38067626953125,
|
| 2149 |
+
"loss": 0.181,
|
| 2150 |
+
"rewards/accuracies": 0.75,
|
| 2151 |
+
"rewards/chosen": 2.7437126636505127,
|
| 2152 |
+
"rewards/margins": 7.136537551879883,
|
| 2153 |
+
"rewards/rejected": -4.392825126647949,
|
| 2154 |
+
"step": 143
|
| 2155 |
+
},
|
| 2156 |
+
{
|
| 2157 |
+
"epoch": 1.8885245901639345,
|
| 2158 |
+
"grad_norm": 1.4070271253585815,
|
| 2159 |
+
"learning_rate": 4.779411764705882e-07,
|
| 2160 |
+
"logits/chosen": -0.24664568901062012,
|
| 2161 |
+
"logits/rejected": -0.640694797039032,
|
| 2162 |
+
"logps/chosen": -327.0250549316406,
|
| 2163 |
+
"logps/rejected": -863.6223754882812,
|
| 2164 |
+
"loss": 0.0034,
|
| 2165 |
+
"rewards/accuracies": 1.0,
|
| 2166 |
+
"rewards/chosen": 1.61453115940094,
|
| 2167 |
+
"rewards/margins": 6.990232467651367,
|
| 2168 |
+
"rewards/rejected": -5.375700950622559,
|
| 2169 |
+
"step": 144
|
| 2170 |
+
},
|
| 2171 |
+
{
|
| 2172 |
+
"epoch": 1.901639344262295,
|
| 2173 |
+
"grad_norm": 37.87571334838867,
|
| 2174 |
+
"learning_rate": 4.4117647058823536e-07,
|
| 2175 |
+
"logits/chosen": -0.7307272553443909,
|
| 2176 |
+
"logits/rejected": -0.5720311403274536,
|
| 2177 |
+
"logps/chosen": -393.85491943359375,
|
| 2178 |
+
"logps/rejected": -344.6254577636719,
|
| 2179 |
+
"loss": 0.352,
|
| 2180 |
+
"rewards/accuracies": 0.75,
|
| 2181 |
+
"rewards/chosen": 1.1627728939056396,
|
| 2182 |
+
"rewards/margins": 3.641770124435425,
|
| 2183 |
+
"rewards/rejected": -2.478997230529785,
|
| 2184 |
+
"step": 145
|
| 2185 |
+
},
|
| 2186 |
+
{
|
| 2187 |
+
"epoch": 1.9147540983606557,
|
| 2188 |
+
"grad_norm": 15.04370403289795,
|
| 2189 |
+
"learning_rate": 4.044117647058824e-07,
|
| 2190 |
+
"logits/chosen": -0.842681884765625,
|
| 2191 |
+
"logits/rejected": -0.4292832314968109,
|
| 2192 |
+
"logps/chosen": -297.94207763671875,
|
| 2193 |
+
"logps/rejected": -240.36907958984375,
|
| 2194 |
+
"loss": 0.0534,
|
| 2195 |
+
"rewards/accuracies": 1.0,
|
| 2196 |
+
"rewards/chosen": 3.2723472118377686,
|
| 2197 |
+
"rewards/margins": 5.443933963775635,
|
| 2198 |
+
"rewards/rejected": -2.171586751937866,
|
| 2199 |
+
"step": 146
|
| 2200 |
+
},
|
| 2201 |
+
{
|
| 2202 |
+
"epoch": 1.9278688524590164,
|
| 2203 |
+
"grad_norm": 15.202438354492188,
|
| 2204 |
+
"learning_rate": 3.6764705882352943e-07,
|
| 2205 |
+
"logits/chosen": -0.6476624011993408,
|
| 2206 |
+
"logits/rejected": -0.49806222319602966,
|
| 2207 |
+
"logps/chosen": -224.61077880859375,
|
| 2208 |
+
"logps/rejected": -169.60565185546875,
|
| 2209 |
+
"loss": 0.1546,
|
| 2210 |
+
"rewards/accuracies": 1.0,
|
| 2211 |
+
"rewards/chosen": 0.8692402839660645,
|
| 2212 |
+
"rewards/margins": 2.598930597305298,
|
| 2213 |
+
"rewards/rejected": -1.7296903133392334,
|
| 2214 |
+
"step": 147
|
| 2215 |
+
},
|
| 2216 |
+
{
|
| 2217 |
+
"epoch": 1.940983606557377,
|
| 2218 |
+
"grad_norm": 7.096276760101318,
|
| 2219 |
+
"learning_rate": 3.308823529411765e-07,
|
| 2220 |
+
"logits/chosen": -0.7730454802513123,
|
| 2221 |
+
"logits/rejected": -0.4797229766845703,
|
| 2222 |
+
"logps/chosen": -321.5426025390625,
|
| 2223 |
+
"logps/rejected": -219.32769775390625,
|
| 2224 |
+
"loss": 0.0219,
|
| 2225 |
+
"rewards/accuracies": 1.0,
|
| 2226 |
+
"rewards/chosen": 2.728835344314575,
|
| 2227 |
+
"rewards/margins": 5.427863597869873,
|
| 2228 |
+
"rewards/rejected": -2.699028253555298,
|
| 2229 |
+
"step": 148
|
| 2230 |
+
},
|
| 2231 |
+
{
|
| 2232 |
+
"epoch": 1.9540983606557378,
|
| 2233 |
+
"grad_norm": 66.5175552368164,
|
| 2234 |
+
"learning_rate": 2.9411764705882356e-07,
|
| 2235 |
+
"logits/chosen": -0.31179729104042053,
|
| 2236 |
+
"logits/rejected": -0.28874772787094116,
|
| 2237 |
+
"logps/chosen": -279.7017822265625,
|
| 2238 |
+
"logps/rejected": -289.318115234375,
|
| 2239 |
+
"loss": 0.2663,
|
| 2240 |
+
"rewards/accuracies": 0.75,
|
| 2241 |
+
"rewards/chosen": 1.061594009399414,
|
| 2242 |
+
"rewards/margins": 3.8362441062927246,
|
| 2243 |
+
"rewards/rejected": -2.7746498584747314,
|
| 2244 |
+
"step": 149
|
| 2245 |
+
},
|
| 2246 |
+
{
|
| 2247 |
+
"epoch": 1.9672131147540983,
|
| 2248 |
+
"grad_norm": 32.35987091064453,
|
| 2249 |
+
"learning_rate": 2.573529411764706e-07,
|
| 2250 |
+
"logits/chosen": -0.6153096556663513,
|
| 2251 |
+
"logits/rejected": -0.725881814956665,
|
| 2252 |
+
"logps/chosen": -301.1914367675781,
|
| 2253 |
+
"logps/rejected": -272.52825927734375,
|
| 2254 |
+
"loss": 0.233,
|
| 2255 |
+
"rewards/accuracies": 1.0,
|
| 2256 |
+
"rewards/chosen": 1.4337717294692993,
|
| 2257 |
+
"rewards/margins": 3.663452625274658,
|
| 2258 |
+
"rewards/rejected": -2.2296810150146484,
|
| 2259 |
+
"step": 150
|
| 2260 |
+
},
|
| 2261 |
+
{
|
| 2262 |
+
"epoch": 1.980327868852459,
|
| 2263 |
+
"grad_norm": 0.4960515797138214,
|
| 2264 |
+
"learning_rate": 2.2058823529411768e-07,
|
| 2265 |
+
"logits/chosen": -0.30176612734794617,
|
| 2266 |
+
"logits/rejected": 0.019010625779628754,
|
| 2267 |
+
"logps/chosen": -270.0059814453125,
|
| 2268 |
+
"logps/rejected": -376.6888732910156,
|
| 2269 |
+
"loss": 0.0017,
|
| 2270 |
+
"rewards/accuracies": 1.0,
|
| 2271 |
+
"rewards/chosen": 1.2527967691421509,
|
| 2272 |
+
"rewards/margins": 7.02215576171875,
|
| 2273 |
+
"rewards/rejected": -5.7693586349487305,
|
| 2274 |
+
"step": 151
|
| 2275 |
+
},
|
| 2276 |
+
{
|
| 2277 |
+
"epoch": 1.9934426229508198,
|
| 2278 |
+
"grad_norm": 29.579833984375,
|
| 2279 |
+
"learning_rate": 1.8382352941176472e-07,
|
| 2280 |
+
"logits/chosen": -0.753585696220398,
|
| 2281 |
+
"logits/rejected": -0.5951805114746094,
|
| 2282 |
+
"logps/chosen": -178.24880981445312,
|
| 2283 |
+
"logps/rejected": -202.90585327148438,
|
| 2284 |
+
"loss": 0.1476,
|
| 2285 |
+
"rewards/accuracies": 1.0,
|
| 2286 |
+
"rewards/chosen": 1.0991493463516235,
|
| 2287 |
+
"rewards/margins": 2.3130767345428467,
|
| 2288 |
+
"rewards/rejected": -1.2139275074005127,
|
| 2289 |
+
"step": 152
|
| 2290 |
+
}
|
| 2291 |
+
],
|
| 2292 |
+
"logging_steps": 1,
|
| 2293 |
+
"max_steps": 152,
|
| 2294 |
+
"num_input_tokens_seen": 0,
|
| 2295 |
+
"num_train_epochs": 2,
|
| 2296 |
+
"save_steps": 500,
|
| 2297 |
+
"stateful_callbacks": {
|
| 2298 |
+
"TrainerControl": {
|
| 2299 |
+
"args": {
|
| 2300 |
+
"should_epoch_stop": false,
|
| 2301 |
+
"should_evaluate": false,
|
| 2302 |
+
"should_log": false,
|
| 2303 |
+
"should_save": true,
|
| 2304 |
+
"should_training_stop": true
|
| 2305 |
+
},
|
| 2306 |
+
"attributes": {}
|
| 2307 |
+
}
|
| 2308 |
+
},
|
| 2309 |
+
"total_flos": 0.0,
|
| 2310 |
+
"train_batch_size": 1,
|
| 2311 |
+
"trial_name": null,
|
| 2312 |
+
"trial_params": null
|
| 2313 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f08cf1af37eda7ad810f974896d5632aead7cd186400d413fab5415033be4b7e
|
| 3 |
+
size 5944
|