Upload folder using huggingface_hub
Browse files- README.md +206 -0
- adapter_config.json +39 -0
- adapter_model.safetensors +3 -0
- optimizer.pt +3 -0
- preprocessor_config.json +24 -0
- processor_config.json +4 -0
- qformer_tokenizer/added_tokens.json +3 -0
- qformer_tokenizer/special_tokens_map.json +44 -0
- qformer_tokenizer/tokenizer.json +0 -0
- qformer_tokenizer/tokenizer_config.json +66 -0
- qformer_tokenizer/vocab.txt +0 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +125 -0
- tokenizer.json +0 -0
- tokenizer_config.json +958 -0
- trainer_state.json +1245 -0
- training_args.bin +3 -0
README.md
ADDED
|
@@ -0,0 +1,206 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: Salesforce/instructblip-flan-t5-xxl
|
| 3 |
+
library_name: peft
|
| 4 |
+
tags:
|
| 5 |
+
- base_model:adapter:Salesforce/instructblip-flan-t5-xxl
|
| 6 |
+
- lora
|
| 7 |
+
- transformers
|
| 8 |
+
---
|
| 9 |
+
|
| 10 |
+
# Model Card for Model ID
|
| 11 |
+
|
| 12 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
| 13 |
+
|
| 14 |
+
|
| 15 |
+
|
| 16 |
+
## Model Details
|
| 17 |
+
|
| 18 |
+
### Model Description
|
| 19 |
+
|
| 20 |
+
<!-- Provide a longer summary of what this model is. -->
|
| 21 |
+
|
| 22 |
+
|
| 23 |
+
|
| 24 |
+
- **Developed by:** [More Information Needed]
|
| 25 |
+
- **Funded by [optional]:** [More Information Needed]
|
| 26 |
+
- **Shared by [optional]:** [More Information Needed]
|
| 27 |
+
- **Model type:** [More Information Needed]
|
| 28 |
+
- **Language(s) (NLP):** [More Information Needed]
|
| 29 |
+
- **License:** [More Information Needed]
|
| 30 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
| 31 |
+
|
| 32 |
+
### Model Sources [optional]
|
| 33 |
+
|
| 34 |
+
<!-- Provide the basic links for the model. -->
|
| 35 |
+
|
| 36 |
+
- **Repository:** [More Information Needed]
|
| 37 |
+
- **Paper [optional]:** [More Information Needed]
|
| 38 |
+
- **Demo [optional]:** [More Information Needed]
|
| 39 |
+
|
| 40 |
+
## Uses
|
| 41 |
+
|
| 42 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
| 43 |
+
|
| 44 |
+
### Direct Use
|
| 45 |
+
|
| 46 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
| 47 |
+
|
| 48 |
+
[More Information Needed]
|
| 49 |
+
|
| 50 |
+
### Downstream Use [optional]
|
| 51 |
+
|
| 52 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
| 53 |
+
|
| 54 |
+
[More Information Needed]
|
| 55 |
+
|
| 56 |
+
### Out-of-Scope Use
|
| 57 |
+
|
| 58 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
| 59 |
+
|
| 60 |
+
[More Information Needed]
|
| 61 |
+
|
| 62 |
+
## Bias, Risks, and Limitations
|
| 63 |
+
|
| 64 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
| 65 |
+
|
| 66 |
+
[More Information Needed]
|
| 67 |
+
|
| 68 |
+
### Recommendations
|
| 69 |
+
|
| 70 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
| 71 |
+
|
| 72 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
| 73 |
+
|
| 74 |
+
## How to Get Started with the Model
|
| 75 |
+
|
| 76 |
+
Use the code below to get started with the model.
|
| 77 |
+
|
| 78 |
+
[More Information Needed]
|
| 79 |
+
|
| 80 |
+
## Training Details
|
| 81 |
+
|
| 82 |
+
### Training Data
|
| 83 |
+
|
| 84 |
+
<!-- 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. -->
|
| 85 |
+
|
| 86 |
+
[More Information Needed]
|
| 87 |
+
|
| 88 |
+
### Training Procedure
|
| 89 |
+
|
| 90 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
| 91 |
+
|
| 92 |
+
#### Preprocessing [optional]
|
| 93 |
+
|
| 94 |
+
[More Information Needed]
|
| 95 |
+
|
| 96 |
+
|
| 97 |
+
#### Training Hyperparameters
|
| 98 |
+
|
| 99 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
| 100 |
+
|
| 101 |
+
#### Speeds, Sizes, Times [optional]
|
| 102 |
+
|
| 103 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
| 104 |
+
|
| 105 |
+
[More Information Needed]
|
| 106 |
+
|
| 107 |
+
## Evaluation
|
| 108 |
+
|
| 109 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
| 110 |
+
|
| 111 |
+
### Testing Data, Factors & Metrics
|
| 112 |
+
|
| 113 |
+
#### Testing Data
|
| 114 |
+
|
| 115 |
+
<!-- This should link to a Dataset Card if possible. -->
|
| 116 |
+
|
| 117 |
+
[More Information Needed]
|
| 118 |
+
|
| 119 |
+
#### Factors
|
| 120 |
+
|
| 121 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
| 122 |
+
|
| 123 |
+
[More Information Needed]
|
| 124 |
+
|
| 125 |
+
#### Metrics
|
| 126 |
+
|
| 127 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
| 128 |
+
|
| 129 |
+
[More Information Needed]
|
| 130 |
+
|
| 131 |
+
### Results
|
| 132 |
+
|
| 133 |
+
[More Information Needed]
|
| 134 |
+
|
| 135 |
+
#### Summary
|
| 136 |
+
|
| 137 |
+
|
| 138 |
+
|
| 139 |
+
## Model Examination [optional]
|
| 140 |
+
|
| 141 |
+
<!-- Relevant interpretability work for the model goes here -->
|
| 142 |
+
|
| 143 |
+
[More Information Needed]
|
| 144 |
+
|
| 145 |
+
## Environmental Impact
|
| 146 |
+
|
| 147 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
| 148 |
+
|
| 149 |
+
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).
|
| 150 |
+
|
| 151 |
+
- **Hardware Type:** [More Information Needed]
|
| 152 |
+
- **Hours used:** [More Information Needed]
|
| 153 |
+
- **Cloud Provider:** [More Information Needed]
|
| 154 |
+
- **Compute Region:** [More Information Needed]
|
| 155 |
+
- **Carbon Emitted:** [More Information Needed]
|
| 156 |
+
|
| 157 |
+
## Technical Specifications [optional]
|
| 158 |
+
|
| 159 |
+
### Model Architecture and Objective
|
| 160 |
+
|
| 161 |
+
[More Information Needed]
|
| 162 |
+
|
| 163 |
+
### Compute Infrastructure
|
| 164 |
+
|
| 165 |
+
[More Information Needed]
|
| 166 |
+
|
| 167 |
+
#### Hardware
|
| 168 |
+
|
| 169 |
+
[More Information Needed]
|
| 170 |
+
|
| 171 |
+
#### Software
|
| 172 |
+
|
| 173 |
+
[More Information Needed]
|
| 174 |
+
|
| 175 |
+
## Citation [optional]
|
| 176 |
+
|
| 177 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
| 178 |
+
|
| 179 |
+
**BibTeX:**
|
| 180 |
+
|
| 181 |
+
[More Information Needed]
|
| 182 |
+
|
| 183 |
+
**APA:**
|
| 184 |
+
|
| 185 |
+
[More Information Needed]
|
| 186 |
+
|
| 187 |
+
## Glossary [optional]
|
| 188 |
+
|
| 189 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
| 190 |
+
|
| 191 |
+
[More Information Needed]
|
| 192 |
+
|
| 193 |
+
## More Information [optional]
|
| 194 |
+
|
| 195 |
+
[More Information Needed]
|
| 196 |
+
|
| 197 |
+
## Model Card Authors [optional]
|
| 198 |
+
|
| 199 |
+
[More Information Needed]
|
| 200 |
+
|
| 201 |
+
## Model Card Contact
|
| 202 |
+
|
| 203 |
+
[More Information Needed]
|
| 204 |
+
### Framework versions
|
| 205 |
+
|
| 206 |
+
- PEFT 0.17.0
|
adapter_config.json
ADDED
|
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "Salesforce/instructblip-flan-t5-xxl",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"corda_config": null,
|
| 7 |
+
"eva_config": null,
|
| 8 |
+
"exclude_modules": null,
|
| 9 |
+
"fan_in_fan_out": false,
|
| 10 |
+
"inference_mode": true,
|
| 11 |
+
"init_lora_weights": true,
|
| 12 |
+
"layer_replication": null,
|
| 13 |
+
"layers_pattern": null,
|
| 14 |
+
"layers_to_transform": null,
|
| 15 |
+
"loftq_config": {},
|
| 16 |
+
"lora_alpha": 48,
|
| 17 |
+
"lora_bias": false,
|
| 18 |
+
"lora_dropout": 0.01,
|
| 19 |
+
"megatron_config": null,
|
| 20 |
+
"megatron_core": "megatron.core",
|
| 21 |
+
"modules_to_save": null,
|
| 22 |
+
"peft_type": "LORA",
|
| 23 |
+
"qalora_group_size": 16,
|
| 24 |
+
"r": 16,
|
| 25 |
+
"rank_pattern": {},
|
| 26 |
+
"revision": null,
|
| 27 |
+
"target_modules": [
|
| 28 |
+
"k",
|
| 29 |
+
"v",
|
| 30 |
+
"o",
|
| 31 |
+
"q"
|
| 32 |
+
],
|
| 33 |
+
"target_parameters": null,
|
| 34 |
+
"task_type": "SEQ_2_SEQ_LM",
|
| 35 |
+
"trainable_token_indices": null,
|
| 36 |
+
"use_dora": false,
|
| 37 |
+
"use_qalora": false,
|
| 38 |
+
"use_rslora": false
|
| 39 |
+
}
|
adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1c9be41482f0a62915c16fac214840b64998ad4e4963456fb13a51defeb9bc73
|
| 3 |
+
size 151086440
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7d2cd9547fae1ebf985668f0dc3f978ab6cac637ecea25cbe7be4a3500598ddf
|
| 3 |
+
size 302477347
|
preprocessor_config.json
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"do_convert_rgb": true,
|
| 3 |
+
"do_normalize": true,
|
| 4 |
+
"do_rescale": true,
|
| 5 |
+
"do_resize": true,
|
| 6 |
+
"image_mean": [
|
| 7 |
+
0.48145466,
|
| 8 |
+
0.4578275,
|
| 9 |
+
0.40821073
|
| 10 |
+
],
|
| 11 |
+
"image_processor_type": "BlipImageProcessor",
|
| 12 |
+
"image_std": [
|
| 13 |
+
0.26862954,
|
| 14 |
+
0.26130258,
|
| 15 |
+
0.27577711
|
| 16 |
+
],
|
| 17 |
+
"processor_class": "InstructBlipProcessor",
|
| 18 |
+
"resample": 3,
|
| 19 |
+
"rescale_factor": 0.00392156862745098,
|
| 20 |
+
"size": {
|
| 21 |
+
"height": 224,
|
| 22 |
+
"width": 224
|
| 23 |
+
}
|
| 24 |
+
}
|
processor_config.json
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"num_query_tokens": 32,
|
| 3 |
+
"processor_class": "InstructBlipProcessor"
|
| 4 |
+
}
|
qformer_tokenizer/added_tokens.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"[DEC]": 30522
|
| 3 |
+
}
|
qformer_tokenizer/special_tokens_map.json
ADDED
|
@@ -0,0 +1,44 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "[DEC]",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"cls_token": {
|
| 10 |
+
"content": "[CLS]",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"mask_token": {
|
| 17 |
+
"content": "[MASK]",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"pad_token": {
|
| 24 |
+
"content": "[PAD]",
|
| 25 |
+
"lstrip": false,
|
| 26 |
+
"normalized": false,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
},
|
| 30 |
+
"sep_token": {
|
| 31 |
+
"content": "[SEP]",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": false,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false
|
| 36 |
+
},
|
| 37 |
+
"unk_token": {
|
| 38 |
+
"content": "[UNK]",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": false,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false
|
| 43 |
+
}
|
| 44 |
+
}
|
qformer_tokenizer/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
qformer_tokenizer/tokenizer_config.json
ADDED
|
@@ -0,0 +1,66 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "[PAD]",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"100": {
|
| 12 |
+
"content": "[UNK]",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"101": {
|
| 20 |
+
"content": "[CLS]",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"102": {
|
| 28 |
+
"content": "[SEP]",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"103": {
|
| 36 |
+
"content": "[MASK]",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
},
|
| 43 |
+
"30522": {
|
| 44 |
+
"content": "[DEC]",
|
| 45 |
+
"lstrip": false,
|
| 46 |
+
"normalized": false,
|
| 47 |
+
"rstrip": false,
|
| 48 |
+
"single_word": false,
|
| 49 |
+
"special": true
|
| 50 |
+
}
|
| 51 |
+
},
|
| 52 |
+
"bos_token": "[DEC]",
|
| 53 |
+
"clean_up_tokenization_spaces": true,
|
| 54 |
+
"cls_token": "[CLS]",
|
| 55 |
+
"do_lower_case": true,
|
| 56 |
+
"extra_special_tokens": {},
|
| 57 |
+
"mask_token": "[MASK]",
|
| 58 |
+
"model_max_length": 512,
|
| 59 |
+
"pad_token": "[PAD]",
|
| 60 |
+
"sep_token": "[SEP]",
|
| 61 |
+
"strip_accents": null,
|
| 62 |
+
"tokenize_chinese_chars": true,
|
| 63 |
+
"tokenizer_class": "BertTokenizer",
|
| 64 |
+
"truncation_side": "left",
|
| 65 |
+
"unk_token": "[UNK]"
|
| 66 |
+
}
|
qformer_tokenizer/vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f8cd94ba93502a1e3b3dbda1bb885a39125c1c2d94bcd2febfa4955fb9c3624e
|
| 3 |
+
size 14645
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:97f6a9ab565c9d8de5b29c1536f49a6411be870ff0c5894d4016ce822ee32d94
|
| 3 |
+
size 1465
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,125 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<extra_id_0>",
|
| 4 |
+
"<extra_id_1>",
|
| 5 |
+
"<extra_id_2>",
|
| 6 |
+
"<extra_id_3>",
|
| 7 |
+
"<extra_id_4>",
|
| 8 |
+
"<extra_id_5>",
|
| 9 |
+
"<extra_id_6>",
|
| 10 |
+
"<extra_id_7>",
|
| 11 |
+
"<extra_id_8>",
|
| 12 |
+
"<extra_id_9>",
|
| 13 |
+
"<extra_id_10>",
|
| 14 |
+
"<extra_id_11>",
|
| 15 |
+
"<extra_id_12>",
|
| 16 |
+
"<extra_id_13>",
|
| 17 |
+
"<extra_id_14>",
|
| 18 |
+
"<extra_id_15>",
|
| 19 |
+
"<extra_id_16>",
|
| 20 |
+
"<extra_id_17>",
|
| 21 |
+
"<extra_id_18>",
|
| 22 |
+
"<extra_id_19>",
|
| 23 |
+
"<extra_id_20>",
|
| 24 |
+
"<extra_id_21>",
|
| 25 |
+
"<extra_id_22>",
|
| 26 |
+
"<extra_id_23>",
|
| 27 |
+
"<extra_id_24>",
|
| 28 |
+
"<extra_id_25>",
|
| 29 |
+
"<extra_id_26>",
|
| 30 |
+
"<extra_id_27>",
|
| 31 |
+
"<extra_id_28>",
|
| 32 |
+
"<extra_id_29>",
|
| 33 |
+
"<extra_id_30>",
|
| 34 |
+
"<extra_id_31>",
|
| 35 |
+
"<extra_id_32>",
|
| 36 |
+
"<extra_id_33>",
|
| 37 |
+
"<extra_id_34>",
|
| 38 |
+
"<extra_id_35>",
|
| 39 |
+
"<extra_id_36>",
|
| 40 |
+
"<extra_id_37>",
|
| 41 |
+
"<extra_id_38>",
|
| 42 |
+
"<extra_id_39>",
|
| 43 |
+
"<extra_id_40>",
|
| 44 |
+
"<extra_id_41>",
|
| 45 |
+
"<extra_id_42>",
|
| 46 |
+
"<extra_id_43>",
|
| 47 |
+
"<extra_id_44>",
|
| 48 |
+
"<extra_id_45>",
|
| 49 |
+
"<extra_id_46>",
|
| 50 |
+
"<extra_id_47>",
|
| 51 |
+
"<extra_id_48>",
|
| 52 |
+
"<extra_id_49>",
|
| 53 |
+
"<extra_id_50>",
|
| 54 |
+
"<extra_id_51>",
|
| 55 |
+
"<extra_id_52>",
|
| 56 |
+
"<extra_id_53>",
|
| 57 |
+
"<extra_id_54>",
|
| 58 |
+
"<extra_id_55>",
|
| 59 |
+
"<extra_id_56>",
|
| 60 |
+
"<extra_id_57>",
|
| 61 |
+
"<extra_id_58>",
|
| 62 |
+
"<extra_id_59>",
|
| 63 |
+
"<extra_id_60>",
|
| 64 |
+
"<extra_id_61>",
|
| 65 |
+
"<extra_id_62>",
|
| 66 |
+
"<extra_id_63>",
|
| 67 |
+
"<extra_id_64>",
|
| 68 |
+
"<extra_id_65>",
|
| 69 |
+
"<extra_id_66>",
|
| 70 |
+
"<extra_id_67>",
|
| 71 |
+
"<extra_id_68>",
|
| 72 |
+
"<extra_id_69>",
|
| 73 |
+
"<extra_id_70>",
|
| 74 |
+
"<extra_id_71>",
|
| 75 |
+
"<extra_id_72>",
|
| 76 |
+
"<extra_id_73>",
|
| 77 |
+
"<extra_id_74>",
|
| 78 |
+
"<extra_id_75>",
|
| 79 |
+
"<extra_id_76>",
|
| 80 |
+
"<extra_id_77>",
|
| 81 |
+
"<extra_id_78>",
|
| 82 |
+
"<extra_id_79>",
|
| 83 |
+
"<extra_id_80>",
|
| 84 |
+
"<extra_id_81>",
|
| 85 |
+
"<extra_id_82>",
|
| 86 |
+
"<extra_id_83>",
|
| 87 |
+
"<extra_id_84>",
|
| 88 |
+
"<extra_id_85>",
|
| 89 |
+
"<extra_id_86>",
|
| 90 |
+
"<extra_id_87>",
|
| 91 |
+
"<extra_id_88>",
|
| 92 |
+
"<extra_id_89>",
|
| 93 |
+
"<extra_id_90>",
|
| 94 |
+
"<extra_id_91>",
|
| 95 |
+
"<extra_id_92>",
|
| 96 |
+
"<extra_id_93>",
|
| 97 |
+
"<extra_id_94>",
|
| 98 |
+
"<extra_id_95>",
|
| 99 |
+
"<extra_id_96>",
|
| 100 |
+
"<extra_id_97>",
|
| 101 |
+
"<extra_id_98>",
|
| 102 |
+
"<extra_id_99>"
|
| 103 |
+
],
|
| 104 |
+
"eos_token": {
|
| 105 |
+
"content": "</s>",
|
| 106 |
+
"lstrip": false,
|
| 107 |
+
"normalized": false,
|
| 108 |
+
"rstrip": false,
|
| 109 |
+
"single_word": false
|
| 110 |
+
},
|
| 111 |
+
"pad_token": {
|
| 112 |
+
"content": "<pad>",
|
| 113 |
+
"lstrip": false,
|
| 114 |
+
"normalized": false,
|
| 115 |
+
"rstrip": false,
|
| 116 |
+
"single_word": false
|
| 117 |
+
},
|
| 118 |
+
"unk_token": {
|
| 119 |
+
"content": "<unk>",
|
| 120 |
+
"lstrip": false,
|
| 121 |
+
"normalized": false,
|
| 122 |
+
"rstrip": false,
|
| 123 |
+
"single_word": false
|
| 124 |
+
}
|
| 125 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,958 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": null,
|
| 3 |
+
"added_tokens_decoder": {
|
| 4 |
+
"0": {
|
| 5 |
+
"content": "<pad>",
|
| 6 |
+
"lstrip": false,
|
| 7 |
+
"normalized": false,
|
| 8 |
+
"rstrip": false,
|
| 9 |
+
"single_word": false,
|
| 10 |
+
"special": true
|
| 11 |
+
},
|
| 12 |
+
"1": {
|
| 13 |
+
"content": "</s>",
|
| 14 |
+
"lstrip": false,
|
| 15 |
+
"normalized": false,
|
| 16 |
+
"rstrip": false,
|
| 17 |
+
"single_word": false,
|
| 18 |
+
"special": true
|
| 19 |
+
},
|
| 20 |
+
"2": {
|
| 21 |
+
"content": "<unk>",
|
| 22 |
+
"lstrip": false,
|
| 23 |
+
"normalized": false,
|
| 24 |
+
"rstrip": false,
|
| 25 |
+
"single_word": false,
|
| 26 |
+
"special": true
|
| 27 |
+
},
|
| 28 |
+
"32000": {
|
| 29 |
+
"content": "<extra_id_99>",
|
| 30 |
+
"lstrip": false,
|
| 31 |
+
"normalized": false,
|
| 32 |
+
"rstrip": false,
|
| 33 |
+
"single_word": false,
|
| 34 |
+
"special": true
|
| 35 |
+
},
|
| 36 |
+
"32001": {
|
| 37 |
+
"content": "<extra_id_98>",
|
| 38 |
+
"lstrip": false,
|
| 39 |
+
"normalized": false,
|
| 40 |
+
"rstrip": false,
|
| 41 |
+
"single_word": false,
|
| 42 |
+
"special": true
|
| 43 |
+
},
|
| 44 |
+
"32002": {
|
| 45 |
+
"content": "<extra_id_97>",
|
| 46 |
+
"lstrip": false,
|
| 47 |
+
"normalized": false,
|
| 48 |
+
"rstrip": false,
|
| 49 |
+
"single_word": false,
|
| 50 |
+
"special": true
|
| 51 |
+
},
|
| 52 |
+
"32003": {
|
| 53 |
+
"content": "<extra_id_96>",
|
| 54 |
+
"lstrip": false,
|
| 55 |
+
"normalized": false,
|
| 56 |
+
"rstrip": false,
|
| 57 |
+
"single_word": false,
|
| 58 |
+
"special": true
|
| 59 |
+
},
|
| 60 |
+
"32004": {
|
| 61 |
+
"content": "<extra_id_95>",
|
| 62 |
+
"lstrip": false,
|
| 63 |
+
"normalized": false,
|
| 64 |
+
"rstrip": false,
|
| 65 |
+
"single_word": false,
|
| 66 |
+
"special": true
|
| 67 |
+
},
|
| 68 |
+
"32005": {
|
| 69 |
+
"content": "<extra_id_94>",
|
| 70 |
+
"lstrip": false,
|
| 71 |
+
"normalized": false,
|
| 72 |
+
"rstrip": false,
|
| 73 |
+
"single_word": false,
|
| 74 |
+
"special": true
|
| 75 |
+
},
|
| 76 |
+
"32006": {
|
| 77 |
+
"content": "<extra_id_93>",
|
| 78 |
+
"lstrip": false,
|
| 79 |
+
"normalized": false,
|
| 80 |
+
"rstrip": false,
|
| 81 |
+
"single_word": false,
|
| 82 |
+
"special": true
|
| 83 |
+
},
|
| 84 |
+
"32007": {
|
| 85 |
+
"content": "<extra_id_92>",
|
| 86 |
+
"lstrip": false,
|
| 87 |
+
"normalized": false,
|
| 88 |
+
"rstrip": false,
|
| 89 |
+
"single_word": false,
|
| 90 |
+
"special": true
|
| 91 |
+
},
|
| 92 |
+
"32008": {
|
| 93 |
+
"content": "<extra_id_91>",
|
| 94 |
+
"lstrip": false,
|
| 95 |
+
"normalized": false,
|
| 96 |
+
"rstrip": false,
|
| 97 |
+
"single_word": false,
|
| 98 |
+
"special": true
|
| 99 |
+
},
|
| 100 |
+
"32009": {
|
| 101 |
+
"content": "<extra_id_90>",
|
| 102 |
+
"lstrip": false,
|
| 103 |
+
"normalized": false,
|
| 104 |
+
"rstrip": false,
|
| 105 |
+
"single_word": false,
|
| 106 |
+
"special": true
|
| 107 |
+
},
|
| 108 |
+
"32010": {
|
| 109 |
+
"content": "<extra_id_89>",
|
| 110 |
+
"lstrip": false,
|
| 111 |
+
"normalized": false,
|
| 112 |
+
"rstrip": false,
|
| 113 |
+
"single_word": false,
|
| 114 |
+
"special": true
|
| 115 |
+
},
|
| 116 |
+
"32011": {
|
| 117 |
+
"content": "<extra_id_88>",
|
| 118 |
+
"lstrip": false,
|
| 119 |
+
"normalized": false,
|
| 120 |
+
"rstrip": false,
|
| 121 |
+
"single_word": false,
|
| 122 |
+
"special": true
|
| 123 |
+
},
|
| 124 |
+
"32012": {
|
| 125 |
+
"content": "<extra_id_87>",
|
| 126 |
+
"lstrip": false,
|
| 127 |
+
"normalized": false,
|
| 128 |
+
"rstrip": false,
|
| 129 |
+
"single_word": false,
|
| 130 |
+
"special": true
|
| 131 |
+
},
|
| 132 |
+
"32013": {
|
| 133 |
+
"content": "<extra_id_86>",
|
| 134 |
+
"lstrip": false,
|
| 135 |
+
"normalized": false,
|
| 136 |
+
"rstrip": false,
|
| 137 |
+
"single_word": false,
|
| 138 |
+
"special": true
|
| 139 |
+
},
|
| 140 |
+
"32014": {
|
| 141 |
+
"content": "<extra_id_85>",
|
| 142 |
+
"lstrip": false,
|
| 143 |
+
"normalized": false,
|
| 144 |
+
"rstrip": false,
|
| 145 |
+
"single_word": false,
|
| 146 |
+
"special": true
|
| 147 |
+
},
|
| 148 |
+
"32015": {
|
| 149 |
+
"content": "<extra_id_84>",
|
| 150 |
+
"lstrip": false,
|
| 151 |
+
"normalized": false,
|
| 152 |
+
"rstrip": false,
|
| 153 |
+
"single_word": false,
|
| 154 |
+
"special": true
|
| 155 |
+
},
|
| 156 |
+
"32016": {
|
| 157 |
+
"content": "<extra_id_83>",
|
| 158 |
+
"lstrip": false,
|
| 159 |
+
"normalized": false,
|
| 160 |
+
"rstrip": false,
|
| 161 |
+
"single_word": false,
|
| 162 |
+
"special": true
|
| 163 |
+
},
|
| 164 |
+
"32017": {
|
| 165 |
+
"content": "<extra_id_82>",
|
| 166 |
+
"lstrip": false,
|
| 167 |
+
"normalized": false,
|
| 168 |
+
"rstrip": false,
|
| 169 |
+
"single_word": false,
|
| 170 |
+
"special": true
|
| 171 |
+
},
|
| 172 |
+
"32018": {
|
| 173 |
+
"content": "<extra_id_81>",
|
| 174 |
+
"lstrip": false,
|
| 175 |
+
"normalized": false,
|
| 176 |
+
"rstrip": false,
|
| 177 |
+
"single_word": false,
|
| 178 |
+
"special": true
|
| 179 |
+
},
|
| 180 |
+
"32019": {
|
| 181 |
+
"content": "<extra_id_80>",
|
| 182 |
+
"lstrip": false,
|
| 183 |
+
"normalized": false,
|
| 184 |
+
"rstrip": false,
|
| 185 |
+
"single_word": false,
|
| 186 |
+
"special": true
|
| 187 |
+
},
|
| 188 |
+
"32020": {
|
| 189 |
+
"content": "<extra_id_79>",
|
| 190 |
+
"lstrip": false,
|
| 191 |
+
"normalized": false,
|
| 192 |
+
"rstrip": false,
|
| 193 |
+
"single_word": false,
|
| 194 |
+
"special": true
|
| 195 |
+
},
|
| 196 |
+
"32021": {
|
| 197 |
+
"content": "<extra_id_78>",
|
| 198 |
+
"lstrip": false,
|
| 199 |
+
"normalized": false,
|
| 200 |
+
"rstrip": false,
|
| 201 |
+
"single_word": false,
|
| 202 |
+
"special": true
|
| 203 |
+
},
|
| 204 |
+
"32022": {
|
| 205 |
+
"content": "<extra_id_77>",
|
| 206 |
+
"lstrip": false,
|
| 207 |
+
"normalized": false,
|
| 208 |
+
"rstrip": false,
|
| 209 |
+
"single_word": false,
|
| 210 |
+
"special": true
|
| 211 |
+
},
|
| 212 |
+
"32023": {
|
| 213 |
+
"content": "<extra_id_76>",
|
| 214 |
+
"lstrip": false,
|
| 215 |
+
"normalized": false,
|
| 216 |
+
"rstrip": false,
|
| 217 |
+
"single_word": false,
|
| 218 |
+
"special": true
|
| 219 |
+
},
|
| 220 |
+
"32024": {
|
| 221 |
+
"content": "<extra_id_75>",
|
| 222 |
+
"lstrip": false,
|
| 223 |
+
"normalized": false,
|
| 224 |
+
"rstrip": false,
|
| 225 |
+
"single_word": false,
|
| 226 |
+
"special": true
|
| 227 |
+
},
|
| 228 |
+
"32025": {
|
| 229 |
+
"content": "<extra_id_74>",
|
| 230 |
+
"lstrip": false,
|
| 231 |
+
"normalized": false,
|
| 232 |
+
"rstrip": false,
|
| 233 |
+
"single_word": false,
|
| 234 |
+
"special": true
|
| 235 |
+
},
|
| 236 |
+
"32026": {
|
| 237 |
+
"content": "<extra_id_73>",
|
| 238 |
+
"lstrip": false,
|
| 239 |
+
"normalized": false,
|
| 240 |
+
"rstrip": false,
|
| 241 |
+
"single_word": false,
|
| 242 |
+
"special": true
|
| 243 |
+
},
|
| 244 |
+
"32027": {
|
| 245 |
+
"content": "<extra_id_72>",
|
| 246 |
+
"lstrip": false,
|
| 247 |
+
"normalized": false,
|
| 248 |
+
"rstrip": false,
|
| 249 |
+
"single_word": false,
|
| 250 |
+
"special": true
|
| 251 |
+
},
|
| 252 |
+
"32028": {
|
| 253 |
+
"content": "<extra_id_71>",
|
| 254 |
+
"lstrip": false,
|
| 255 |
+
"normalized": false,
|
| 256 |
+
"rstrip": false,
|
| 257 |
+
"single_word": false,
|
| 258 |
+
"special": true
|
| 259 |
+
},
|
| 260 |
+
"32029": {
|
| 261 |
+
"content": "<extra_id_70>",
|
| 262 |
+
"lstrip": false,
|
| 263 |
+
"normalized": false,
|
| 264 |
+
"rstrip": false,
|
| 265 |
+
"single_word": false,
|
| 266 |
+
"special": true
|
| 267 |
+
},
|
| 268 |
+
"32030": {
|
| 269 |
+
"content": "<extra_id_69>",
|
| 270 |
+
"lstrip": false,
|
| 271 |
+
"normalized": false,
|
| 272 |
+
"rstrip": false,
|
| 273 |
+
"single_word": false,
|
| 274 |
+
"special": true
|
| 275 |
+
},
|
| 276 |
+
"32031": {
|
| 277 |
+
"content": "<extra_id_68>",
|
| 278 |
+
"lstrip": false,
|
| 279 |
+
"normalized": false,
|
| 280 |
+
"rstrip": false,
|
| 281 |
+
"single_word": false,
|
| 282 |
+
"special": true
|
| 283 |
+
},
|
| 284 |
+
"32032": {
|
| 285 |
+
"content": "<extra_id_67>",
|
| 286 |
+
"lstrip": false,
|
| 287 |
+
"normalized": false,
|
| 288 |
+
"rstrip": false,
|
| 289 |
+
"single_word": false,
|
| 290 |
+
"special": true
|
| 291 |
+
},
|
| 292 |
+
"32033": {
|
| 293 |
+
"content": "<extra_id_66>",
|
| 294 |
+
"lstrip": false,
|
| 295 |
+
"normalized": false,
|
| 296 |
+
"rstrip": false,
|
| 297 |
+
"single_word": false,
|
| 298 |
+
"special": true
|
| 299 |
+
},
|
| 300 |
+
"32034": {
|
| 301 |
+
"content": "<extra_id_65>",
|
| 302 |
+
"lstrip": false,
|
| 303 |
+
"normalized": false,
|
| 304 |
+
"rstrip": false,
|
| 305 |
+
"single_word": false,
|
| 306 |
+
"special": true
|
| 307 |
+
},
|
| 308 |
+
"32035": {
|
| 309 |
+
"content": "<extra_id_64>",
|
| 310 |
+
"lstrip": false,
|
| 311 |
+
"normalized": false,
|
| 312 |
+
"rstrip": false,
|
| 313 |
+
"single_word": false,
|
| 314 |
+
"special": true
|
| 315 |
+
},
|
| 316 |
+
"32036": {
|
| 317 |
+
"content": "<extra_id_63>",
|
| 318 |
+
"lstrip": false,
|
| 319 |
+
"normalized": false,
|
| 320 |
+
"rstrip": false,
|
| 321 |
+
"single_word": false,
|
| 322 |
+
"special": true
|
| 323 |
+
},
|
| 324 |
+
"32037": {
|
| 325 |
+
"content": "<extra_id_62>",
|
| 326 |
+
"lstrip": false,
|
| 327 |
+
"normalized": false,
|
| 328 |
+
"rstrip": false,
|
| 329 |
+
"single_word": false,
|
| 330 |
+
"special": true
|
| 331 |
+
},
|
| 332 |
+
"32038": {
|
| 333 |
+
"content": "<extra_id_61>",
|
| 334 |
+
"lstrip": false,
|
| 335 |
+
"normalized": false,
|
| 336 |
+
"rstrip": false,
|
| 337 |
+
"single_word": false,
|
| 338 |
+
"special": true
|
| 339 |
+
},
|
| 340 |
+
"32039": {
|
| 341 |
+
"content": "<extra_id_60>",
|
| 342 |
+
"lstrip": false,
|
| 343 |
+
"normalized": false,
|
| 344 |
+
"rstrip": false,
|
| 345 |
+
"single_word": false,
|
| 346 |
+
"special": true
|
| 347 |
+
},
|
| 348 |
+
"32040": {
|
| 349 |
+
"content": "<extra_id_59>",
|
| 350 |
+
"lstrip": false,
|
| 351 |
+
"normalized": false,
|
| 352 |
+
"rstrip": false,
|
| 353 |
+
"single_word": false,
|
| 354 |
+
"special": true
|
| 355 |
+
},
|
| 356 |
+
"32041": {
|
| 357 |
+
"content": "<extra_id_58>",
|
| 358 |
+
"lstrip": false,
|
| 359 |
+
"normalized": false,
|
| 360 |
+
"rstrip": false,
|
| 361 |
+
"single_word": false,
|
| 362 |
+
"special": true
|
| 363 |
+
},
|
| 364 |
+
"32042": {
|
| 365 |
+
"content": "<extra_id_57>",
|
| 366 |
+
"lstrip": false,
|
| 367 |
+
"normalized": false,
|
| 368 |
+
"rstrip": false,
|
| 369 |
+
"single_word": false,
|
| 370 |
+
"special": true
|
| 371 |
+
},
|
| 372 |
+
"32043": {
|
| 373 |
+
"content": "<extra_id_56>",
|
| 374 |
+
"lstrip": false,
|
| 375 |
+
"normalized": false,
|
| 376 |
+
"rstrip": false,
|
| 377 |
+
"single_word": false,
|
| 378 |
+
"special": true
|
| 379 |
+
},
|
| 380 |
+
"32044": {
|
| 381 |
+
"content": "<extra_id_55>",
|
| 382 |
+
"lstrip": false,
|
| 383 |
+
"normalized": false,
|
| 384 |
+
"rstrip": false,
|
| 385 |
+
"single_word": false,
|
| 386 |
+
"special": true
|
| 387 |
+
},
|
| 388 |
+
"32045": {
|
| 389 |
+
"content": "<extra_id_54>",
|
| 390 |
+
"lstrip": false,
|
| 391 |
+
"normalized": false,
|
| 392 |
+
"rstrip": false,
|
| 393 |
+
"single_word": false,
|
| 394 |
+
"special": true
|
| 395 |
+
},
|
| 396 |
+
"32046": {
|
| 397 |
+
"content": "<extra_id_53>",
|
| 398 |
+
"lstrip": false,
|
| 399 |
+
"normalized": false,
|
| 400 |
+
"rstrip": false,
|
| 401 |
+
"single_word": false,
|
| 402 |
+
"special": true
|
| 403 |
+
},
|
| 404 |
+
"32047": {
|
| 405 |
+
"content": "<extra_id_52>",
|
| 406 |
+
"lstrip": false,
|
| 407 |
+
"normalized": false,
|
| 408 |
+
"rstrip": false,
|
| 409 |
+
"single_word": false,
|
| 410 |
+
"special": true
|
| 411 |
+
},
|
| 412 |
+
"32048": {
|
| 413 |
+
"content": "<extra_id_51>",
|
| 414 |
+
"lstrip": false,
|
| 415 |
+
"normalized": false,
|
| 416 |
+
"rstrip": false,
|
| 417 |
+
"single_word": false,
|
| 418 |
+
"special": true
|
| 419 |
+
},
|
| 420 |
+
"32049": {
|
| 421 |
+
"content": "<extra_id_50>",
|
| 422 |
+
"lstrip": false,
|
| 423 |
+
"normalized": false,
|
| 424 |
+
"rstrip": false,
|
| 425 |
+
"single_word": false,
|
| 426 |
+
"special": true
|
| 427 |
+
},
|
| 428 |
+
"32050": {
|
| 429 |
+
"content": "<extra_id_49>",
|
| 430 |
+
"lstrip": false,
|
| 431 |
+
"normalized": false,
|
| 432 |
+
"rstrip": false,
|
| 433 |
+
"single_word": false,
|
| 434 |
+
"special": true
|
| 435 |
+
},
|
| 436 |
+
"32051": {
|
| 437 |
+
"content": "<extra_id_48>",
|
| 438 |
+
"lstrip": false,
|
| 439 |
+
"normalized": false,
|
| 440 |
+
"rstrip": false,
|
| 441 |
+
"single_word": false,
|
| 442 |
+
"special": true
|
| 443 |
+
},
|
| 444 |
+
"32052": {
|
| 445 |
+
"content": "<extra_id_47>",
|
| 446 |
+
"lstrip": false,
|
| 447 |
+
"normalized": false,
|
| 448 |
+
"rstrip": false,
|
| 449 |
+
"single_word": false,
|
| 450 |
+
"special": true
|
| 451 |
+
},
|
| 452 |
+
"32053": {
|
| 453 |
+
"content": "<extra_id_46>",
|
| 454 |
+
"lstrip": false,
|
| 455 |
+
"normalized": false,
|
| 456 |
+
"rstrip": false,
|
| 457 |
+
"single_word": false,
|
| 458 |
+
"special": true
|
| 459 |
+
},
|
| 460 |
+
"32054": {
|
| 461 |
+
"content": "<extra_id_45>",
|
| 462 |
+
"lstrip": false,
|
| 463 |
+
"normalized": false,
|
| 464 |
+
"rstrip": false,
|
| 465 |
+
"single_word": false,
|
| 466 |
+
"special": true
|
| 467 |
+
},
|
| 468 |
+
"32055": {
|
| 469 |
+
"content": "<extra_id_44>",
|
| 470 |
+
"lstrip": false,
|
| 471 |
+
"normalized": false,
|
| 472 |
+
"rstrip": false,
|
| 473 |
+
"single_word": false,
|
| 474 |
+
"special": true
|
| 475 |
+
},
|
| 476 |
+
"32056": {
|
| 477 |
+
"content": "<extra_id_43>",
|
| 478 |
+
"lstrip": false,
|
| 479 |
+
"normalized": false,
|
| 480 |
+
"rstrip": false,
|
| 481 |
+
"single_word": false,
|
| 482 |
+
"special": true
|
| 483 |
+
},
|
| 484 |
+
"32057": {
|
| 485 |
+
"content": "<extra_id_42>",
|
| 486 |
+
"lstrip": false,
|
| 487 |
+
"normalized": false,
|
| 488 |
+
"rstrip": false,
|
| 489 |
+
"single_word": false,
|
| 490 |
+
"special": true
|
| 491 |
+
},
|
| 492 |
+
"32058": {
|
| 493 |
+
"content": "<extra_id_41>",
|
| 494 |
+
"lstrip": false,
|
| 495 |
+
"normalized": false,
|
| 496 |
+
"rstrip": false,
|
| 497 |
+
"single_word": false,
|
| 498 |
+
"special": true
|
| 499 |
+
},
|
| 500 |
+
"32059": {
|
| 501 |
+
"content": "<extra_id_40>",
|
| 502 |
+
"lstrip": false,
|
| 503 |
+
"normalized": false,
|
| 504 |
+
"rstrip": false,
|
| 505 |
+
"single_word": false,
|
| 506 |
+
"special": true
|
| 507 |
+
},
|
| 508 |
+
"32060": {
|
| 509 |
+
"content": "<extra_id_39>",
|
| 510 |
+
"lstrip": false,
|
| 511 |
+
"normalized": false,
|
| 512 |
+
"rstrip": false,
|
| 513 |
+
"single_word": false,
|
| 514 |
+
"special": true
|
| 515 |
+
},
|
| 516 |
+
"32061": {
|
| 517 |
+
"content": "<extra_id_38>",
|
| 518 |
+
"lstrip": false,
|
| 519 |
+
"normalized": false,
|
| 520 |
+
"rstrip": false,
|
| 521 |
+
"single_word": false,
|
| 522 |
+
"special": true
|
| 523 |
+
},
|
| 524 |
+
"32062": {
|
| 525 |
+
"content": "<extra_id_37>",
|
| 526 |
+
"lstrip": false,
|
| 527 |
+
"normalized": false,
|
| 528 |
+
"rstrip": false,
|
| 529 |
+
"single_word": false,
|
| 530 |
+
"special": true
|
| 531 |
+
},
|
| 532 |
+
"32063": {
|
| 533 |
+
"content": "<extra_id_36>",
|
| 534 |
+
"lstrip": false,
|
| 535 |
+
"normalized": false,
|
| 536 |
+
"rstrip": false,
|
| 537 |
+
"single_word": false,
|
| 538 |
+
"special": true
|
| 539 |
+
},
|
| 540 |
+
"32064": {
|
| 541 |
+
"content": "<extra_id_35>",
|
| 542 |
+
"lstrip": false,
|
| 543 |
+
"normalized": false,
|
| 544 |
+
"rstrip": false,
|
| 545 |
+
"single_word": false,
|
| 546 |
+
"special": true
|
| 547 |
+
},
|
| 548 |
+
"32065": {
|
| 549 |
+
"content": "<extra_id_34>",
|
| 550 |
+
"lstrip": false,
|
| 551 |
+
"normalized": false,
|
| 552 |
+
"rstrip": false,
|
| 553 |
+
"single_word": false,
|
| 554 |
+
"special": true
|
| 555 |
+
},
|
| 556 |
+
"32066": {
|
| 557 |
+
"content": "<extra_id_33>",
|
| 558 |
+
"lstrip": false,
|
| 559 |
+
"normalized": false,
|
| 560 |
+
"rstrip": false,
|
| 561 |
+
"single_word": false,
|
| 562 |
+
"special": true
|
| 563 |
+
},
|
| 564 |
+
"32067": {
|
| 565 |
+
"content": "<extra_id_32>",
|
| 566 |
+
"lstrip": false,
|
| 567 |
+
"normalized": false,
|
| 568 |
+
"rstrip": false,
|
| 569 |
+
"single_word": false,
|
| 570 |
+
"special": true
|
| 571 |
+
},
|
| 572 |
+
"32068": {
|
| 573 |
+
"content": "<extra_id_31>",
|
| 574 |
+
"lstrip": false,
|
| 575 |
+
"normalized": false,
|
| 576 |
+
"rstrip": false,
|
| 577 |
+
"single_word": false,
|
| 578 |
+
"special": true
|
| 579 |
+
},
|
| 580 |
+
"32069": {
|
| 581 |
+
"content": "<extra_id_30>",
|
| 582 |
+
"lstrip": false,
|
| 583 |
+
"normalized": false,
|
| 584 |
+
"rstrip": false,
|
| 585 |
+
"single_word": false,
|
| 586 |
+
"special": true
|
| 587 |
+
},
|
| 588 |
+
"32070": {
|
| 589 |
+
"content": "<extra_id_29>",
|
| 590 |
+
"lstrip": false,
|
| 591 |
+
"normalized": false,
|
| 592 |
+
"rstrip": false,
|
| 593 |
+
"single_word": false,
|
| 594 |
+
"special": true
|
| 595 |
+
},
|
| 596 |
+
"32071": {
|
| 597 |
+
"content": "<extra_id_28>",
|
| 598 |
+
"lstrip": false,
|
| 599 |
+
"normalized": false,
|
| 600 |
+
"rstrip": false,
|
| 601 |
+
"single_word": false,
|
| 602 |
+
"special": true
|
| 603 |
+
},
|
| 604 |
+
"32072": {
|
| 605 |
+
"content": "<extra_id_27>",
|
| 606 |
+
"lstrip": false,
|
| 607 |
+
"normalized": false,
|
| 608 |
+
"rstrip": false,
|
| 609 |
+
"single_word": false,
|
| 610 |
+
"special": true
|
| 611 |
+
},
|
| 612 |
+
"32073": {
|
| 613 |
+
"content": "<extra_id_26>",
|
| 614 |
+
"lstrip": false,
|
| 615 |
+
"normalized": false,
|
| 616 |
+
"rstrip": false,
|
| 617 |
+
"single_word": false,
|
| 618 |
+
"special": true
|
| 619 |
+
},
|
| 620 |
+
"32074": {
|
| 621 |
+
"content": "<extra_id_25>",
|
| 622 |
+
"lstrip": false,
|
| 623 |
+
"normalized": false,
|
| 624 |
+
"rstrip": false,
|
| 625 |
+
"single_word": false,
|
| 626 |
+
"special": true
|
| 627 |
+
},
|
| 628 |
+
"32075": {
|
| 629 |
+
"content": "<extra_id_24>",
|
| 630 |
+
"lstrip": false,
|
| 631 |
+
"normalized": false,
|
| 632 |
+
"rstrip": false,
|
| 633 |
+
"single_word": false,
|
| 634 |
+
"special": true
|
| 635 |
+
},
|
| 636 |
+
"32076": {
|
| 637 |
+
"content": "<extra_id_23>",
|
| 638 |
+
"lstrip": false,
|
| 639 |
+
"normalized": false,
|
| 640 |
+
"rstrip": false,
|
| 641 |
+
"single_word": false,
|
| 642 |
+
"special": true
|
| 643 |
+
},
|
| 644 |
+
"32077": {
|
| 645 |
+
"content": "<extra_id_22>",
|
| 646 |
+
"lstrip": false,
|
| 647 |
+
"normalized": false,
|
| 648 |
+
"rstrip": false,
|
| 649 |
+
"single_word": false,
|
| 650 |
+
"special": true
|
| 651 |
+
},
|
| 652 |
+
"32078": {
|
| 653 |
+
"content": "<extra_id_21>",
|
| 654 |
+
"lstrip": false,
|
| 655 |
+
"normalized": false,
|
| 656 |
+
"rstrip": false,
|
| 657 |
+
"single_word": false,
|
| 658 |
+
"special": true
|
| 659 |
+
},
|
| 660 |
+
"32079": {
|
| 661 |
+
"content": "<extra_id_20>",
|
| 662 |
+
"lstrip": false,
|
| 663 |
+
"normalized": false,
|
| 664 |
+
"rstrip": false,
|
| 665 |
+
"single_word": false,
|
| 666 |
+
"special": true
|
| 667 |
+
},
|
| 668 |
+
"32080": {
|
| 669 |
+
"content": "<extra_id_19>",
|
| 670 |
+
"lstrip": false,
|
| 671 |
+
"normalized": false,
|
| 672 |
+
"rstrip": false,
|
| 673 |
+
"single_word": false,
|
| 674 |
+
"special": true
|
| 675 |
+
},
|
| 676 |
+
"32081": {
|
| 677 |
+
"content": "<extra_id_18>",
|
| 678 |
+
"lstrip": false,
|
| 679 |
+
"normalized": false,
|
| 680 |
+
"rstrip": false,
|
| 681 |
+
"single_word": false,
|
| 682 |
+
"special": true
|
| 683 |
+
},
|
| 684 |
+
"32082": {
|
| 685 |
+
"content": "<extra_id_17>",
|
| 686 |
+
"lstrip": false,
|
| 687 |
+
"normalized": false,
|
| 688 |
+
"rstrip": false,
|
| 689 |
+
"single_word": false,
|
| 690 |
+
"special": true
|
| 691 |
+
},
|
| 692 |
+
"32083": {
|
| 693 |
+
"content": "<extra_id_16>",
|
| 694 |
+
"lstrip": false,
|
| 695 |
+
"normalized": false,
|
| 696 |
+
"rstrip": false,
|
| 697 |
+
"single_word": false,
|
| 698 |
+
"special": true
|
| 699 |
+
},
|
| 700 |
+
"32084": {
|
| 701 |
+
"content": "<extra_id_15>",
|
| 702 |
+
"lstrip": false,
|
| 703 |
+
"normalized": false,
|
| 704 |
+
"rstrip": false,
|
| 705 |
+
"single_word": false,
|
| 706 |
+
"special": true
|
| 707 |
+
},
|
| 708 |
+
"32085": {
|
| 709 |
+
"content": "<extra_id_14>",
|
| 710 |
+
"lstrip": false,
|
| 711 |
+
"normalized": false,
|
| 712 |
+
"rstrip": false,
|
| 713 |
+
"single_word": false,
|
| 714 |
+
"special": true
|
| 715 |
+
},
|
| 716 |
+
"32086": {
|
| 717 |
+
"content": "<extra_id_13>",
|
| 718 |
+
"lstrip": false,
|
| 719 |
+
"normalized": false,
|
| 720 |
+
"rstrip": false,
|
| 721 |
+
"single_word": false,
|
| 722 |
+
"special": true
|
| 723 |
+
},
|
| 724 |
+
"32087": {
|
| 725 |
+
"content": "<extra_id_12>",
|
| 726 |
+
"lstrip": false,
|
| 727 |
+
"normalized": false,
|
| 728 |
+
"rstrip": false,
|
| 729 |
+
"single_word": false,
|
| 730 |
+
"special": true
|
| 731 |
+
},
|
| 732 |
+
"32088": {
|
| 733 |
+
"content": "<extra_id_11>",
|
| 734 |
+
"lstrip": false,
|
| 735 |
+
"normalized": false,
|
| 736 |
+
"rstrip": false,
|
| 737 |
+
"single_word": false,
|
| 738 |
+
"special": true
|
| 739 |
+
},
|
| 740 |
+
"32089": {
|
| 741 |
+
"content": "<extra_id_10>",
|
| 742 |
+
"lstrip": false,
|
| 743 |
+
"normalized": false,
|
| 744 |
+
"rstrip": false,
|
| 745 |
+
"single_word": false,
|
| 746 |
+
"special": true
|
| 747 |
+
},
|
| 748 |
+
"32090": {
|
| 749 |
+
"content": "<extra_id_9>",
|
| 750 |
+
"lstrip": false,
|
| 751 |
+
"normalized": false,
|
| 752 |
+
"rstrip": false,
|
| 753 |
+
"single_word": false,
|
| 754 |
+
"special": true
|
| 755 |
+
},
|
| 756 |
+
"32091": {
|
| 757 |
+
"content": "<extra_id_8>",
|
| 758 |
+
"lstrip": false,
|
| 759 |
+
"normalized": false,
|
| 760 |
+
"rstrip": false,
|
| 761 |
+
"single_word": false,
|
| 762 |
+
"special": true
|
| 763 |
+
},
|
| 764 |
+
"32092": {
|
| 765 |
+
"content": "<extra_id_7>",
|
| 766 |
+
"lstrip": false,
|
| 767 |
+
"normalized": false,
|
| 768 |
+
"rstrip": false,
|
| 769 |
+
"single_word": false,
|
| 770 |
+
"special": true
|
| 771 |
+
},
|
| 772 |
+
"32093": {
|
| 773 |
+
"content": "<extra_id_6>",
|
| 774 |
+
"lstrip": false,
|
| 775 |
+
"normalized": false,
|
| 776 |
+
"rstrip": false,
|
| 777 |
+
"single_word": false,
|
| 778 |
+
"special": true
|
| 779 |
+
},
|
| 780 |
+
"32094": {
|
| 781 |
+
"content": "<extra_id_5>",
|
| 782 |
+
"lstrip": false,
|
| 783 |
+
"normalized": false,
|
| 784 |
+
"rstrip": false,
|
| 785 |
+
"single_word": false,
|
| 786 |
+
"special": true
|
| 787 |
+
},
|
| 788 |
+
"32095": {
|
| 789 |
+
"content": "<extra_id_4>",
|
| 790 |
+
"lstrip": false,
|
| 791 |
+
"normalized": false,
|
| 792 |
+
"rstrip": false,
|
| 793 |
+
"single_word": false,
|
| 794 |
+
"special": true
|
| 795 |
+
},
|
| 796 |
+
"32096": {
|
| 797 |
+
"content": "<extra_id_3>",
|
| 798 |
+
"lstrip": false,
|
| 799 |
+
"normalized": false,
|
| 800 |
+
"rstrip": false,
|
| 801 |
+
"single_word": false,
|
| 802 |
+
"special": true
|
| 803 |
+
},
|
| 804 |
+
"32097": {
|
| 805 |
+
"content": "<extra_id_2>",
|
| 806 |
+
"lstrip": false,
|
| 807 |
+
"normalized": false,
|
| 808 |
+
"rstrip": false,
|
| 809 |
+
"single_word": false,
|
| 810 |
+
"special": true
|
| 811 |
+
},
|
| 812 |
+
"32098": {
|
| 813 |
+
"content": "<extra_id_1>",
|
| 814 |
+
"lstrip": false,
|
| 815 |
+
"normalized": false,
|
| 816 |
+
"rstrip": false,
|
| 817 |
+
"single_word": false,
|
| 818 |
+
"special": true
|
| 819 |
+
},
|
| 820 |
+
"32099": {
|
| 821 |
+
"content": "<extra_id_0>",
|
| 822 |
+
"lstrip": false,
|
| 823 |
+
"normalized": false,
|
| 824 |
+
"rstrip": false,
|
| 825 |
+
"single_word": false,
|
| 826 |
+
"special": true
|
| 827 |
+
},
|
| 828 |
+
"32100": {
|
| 829 |
+
"content": "<image>",
|
| 830 |
+
"lstrip": false,
|
| 831 |
+
"normalized": false,
|
| 832 |
+
"rstrip": false,
|
| 833 |
+
"single_word": false,
|
| 834 |
+
"special": true
|
| 835 |
+
},
|
| 836 |
+
"32101": {
|
| 837 |
+
"content": "<video>",
|
| 838 |
+
"lstrip": false,
|
| 839 |
+
"normalized": false,
|
| 840 |
+
"rstrip": false,
|
| 841 |
+
"single_word": false,
|
| 842 |
+
"special": true
|
| 843 |
+
}
|
| 844 |
+
},
|
| 845 |
+
"additional_special_tokens": [
|
| 846 |
+
"<extra_id_0>",
|
| 847 |
+
"<extra_id_1>",
|
| 848 |
+
"<extra_id_2>",
|
| 849 |
+
"<extra_id_3>",
|
| 850 |
+
"<extra_id_4>",
|
| 851 |
+
"<extra_id_5>",
|
| 852 |
+
"<extra_id_6>",
|
| 853 |
+
"<extra_id_7>",
|
| 854 |
+
"<extra_id_8>",
|
| 855 |
+
"<extra_id_9>",
|
| 856 |
+
"<extra_id_10>",
|
| 857 |
+
"<extra_id_11>",
|
| 858 |
+
"<extra_id_12>",
|
| 859 |
+
"<extra_id_13>",
|
| 860 |
+
"<extra_id_14>",
|
| 861 |
+
"<extra_id_15>",
|
| 862 |
+
"<extra_id_16>",
|
| 863 |
+
"<extra_id_17>",
|
| 864 |
+
"<extra_id_18>",
|
| 865 |
+
"<extra_id_19>",
|
| 866 |
+
"<extra_id_20>",
|
| 867 |
+
"<extra_id_21>",
|
| 868 |
+
"<extra_id_22>",
|
| 869 |
+
"<extra_id_23>",
|
| 870 |
+
"<extra_id_24>",
|
| 871 |
+
"<extra_id_25>",
|
| 872 |
+
"<extra_id_26>",
|
| 873 |
+
"<extra_id_27>",
|
| 874 |
+
"<extra_id_28>",
|
| 875 |
+
"<extra_id_29>",
|
| 876 |
+
"<extra_id_30>",
|
| 877 |
+
"<extra_id_31>",
|
| 878 |
+
"<extra_id_32>",
|
| 879 |
+
"<extra_id_33>",
|
| 880 |
+
"<extra_id_34>",
|
| 881 |
+
"<extra_id_35>",
|
| 882 |
+
"<extra_id_36>",
|
| 883 |
+
"<extra_id_37>",
|
| 884 |
+
"<extra_id_38>",
|
| 885 |
+
"<extra_id_39>",
|
| 886 |
+
"<extra_id_40>",
|
| 887 |
+
"<extra_id_41>",
|
| 888 |
+
"<extra_id_42>",
|
| 889 |
+
"<extra_id_43>",
|
| 890 |
+
"<extra_id_44>",
|
| 891 |
+
"<extra_id_45>",
|
| 892 |
+
"<extra_id_46>",
|
| 893 |
+
"<extra_id_47>",
|
| 894 |
+
"<extra_id_48>",
|
| 895 |
+
"<extra_id_49>",
|
| 896 |
+
"<extra_id_50>",
|
| 897 |
+
"<extra_id_51>",
|
| 898 |
+
"<extra_id_52>",
|
| 899 |
+
"<extra_id_53>",
|
| 900 |
+
"<extra_id_54>",
|
| 901 |
+
"<extra_id_55>",
|
| 902 |
+
"<extra_id_56>",
|
| 903 |
+
"<extra_id_57>",
|
| 904 |
+
"<extra_id_58>",
|
| 905 |
+
"<extra_id_59>",
|
| 906 |
+
"<extra_id_60>",
|
| 907 |
+
"<extra_id_61>",
|
| 908 |
+
"<extra_id_62>",
|
| 909 |
+
"<extra_id_63>",
|
| 910 |
+
"<extra_id_64>",
|
| 911 |
+
"<extra_id_65>",
|
| 912 |
+
"<extra_id_66>",
|
| 913 |
+
"<extra_id_67>",
|
| 914 |
+
"<extra_id_68>",
|
| 915 |
+
"<extra_id_69>",
|
| 916 |
+
"<extra_id_70>",
|
| 917 |
+
"<extra_id_71>",
|
| 918 |
+
"<extra_id_72>",
|
| 919 |
+
"<extra_id_73>",
|
| 920 |
+
"<extra_id_74>",
|
| 921 |
+
"<extra_id_75>",
|
| 922 |
+
"<extra_id_76>",
|
| 923 |
+
"<extra_id_77>",
|
| 924 |
+
"<extra_id_78>",
|
| 925 |
+
"<extra_id_79>",
|
| 926 |
+
"<extra_id_80>",
|
| 927 |
+
"<extra_id_81>",
|
| 928 |
+
"<extra_id_82>",
|
| 929 |
+
"<extra_id_83>",
|
| 930 |
+
"<extra_id_84>",
|
| 931 |
+
"<extra_id_85>",
|
| 932 |
+
"<extra_id_86>",
|
| 933 |
+
"<extra_id_87>",
|
| 934 |
+
"<extra_id_88>",
|
| 935 |
+
"<extra_id_89>",
|
| 936 |
+
"<extra_id_90>",
|
| 937 |
+
"<extra_id_91>",
|
| 938 |
+
"<extra_id_92>",
|
| 939 |
+
"<extra_id_93>",
|
| 940 |
+
"<extra_id_94>",
|
| 941 |
+
"<extra_id_95>",
|
| 942 |
+
"<extra_id_96>",
|
| 943 |
+
"<extra_id_97>",
|
| 944 |
+
"<extra_id_98>",
|
| 945 |
+
"<extra_id_99>"
|
| 946 |
+
],
|
| 947 |
+
"clean_up_tokenization_spaces": true,
|
| 948 |
+
"eos_token": "</s>",
|
| 949 |
+
"extra_ids": 100,
|
| 950 |
+
"extra_special_tokens": {},
|
| 951 |
+
"model_max_length": 512,
|
| 952 |
+
"pad_token": "<pad>",
|
| 953 |
+
"processor_class": "InstructBlipProcessor",
|
| 954 |
+
"sp_model_kwargs": {},
|
| 955 |
+
"tokenizer_class": "T5Tokenizer",
|
| 956 |
+
"truncation_side": "left",
|
| 957 |
+
"unk_token": "<unk>"
|
| 958 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1245 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": 0.4038073718547821,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 3.899815440331511,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 14000,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.0002785806316815823,
|
| 14 |
+
"grad_norm": 0.4645193815231323,
|
| 15 |
+
"learning_rate": 0.0,
|
| 16 |
+
"loss": 2.3986,
|
| 17 |
+
"step": 1
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.027858063168158233,
|
| 21 |
+
"grad_norm": 0.3897116482257843,
|
| 22 |
+
"learning_rate": 1.9800000000000004e-05,
|
| 23 |
+
"loss": 2.4541,
|
| 24 |
+
"step": 100
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.055716126336316465,
|
| 28 |
+
"grad_norm": 0.9093355536460876,
|
| 29 |
+
"learning_rate": 3.9800000000000005e-05,
|
| 30 |
+
"loss": 1.4843,
|
| 31 |
+
"step": 200
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.0835741895044747,
|
| 35 |
+
"grad_norm": 1.0977619886398315,
|
| 36 |
+
"learning_rate": 4.9826364280652023e-05,
|
| 37 |
+
"loss": 0.9759,
|
| 38 |
+
"step": 300
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.11143225267263293,
|
| 42 |
+
"grad_norm": 1.0786027908325195,
|
| 43 |
+
"learning_rate": 4.9472005669737774e-05,
|
| 44 |
+
"loss": 0.8439,
|
| 45 |
+
"step": 400
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.13929031584079116,
|
| 49 |
+
"grad_norm": 1.2702925205230713,
|
| 50 |
+
"learning_rate": 4.911764705882353e-05,
|
| 51 |
+
"loss": 0.7883,
|
| 52 |
+
"step": 500
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.13929031584079116,
|
| 56 |
+
"eval_loss": 0.65428227186203,
|
| 57 |
+
"eval_runtime": 591.887,
|
| 58 |
+
"eval_samples_per_second": 48.518,
|
| 59 |
+
"eval_steps_per_second": 3.033,
|
| 60 |
+
"step": 500
|
| 61 |
+
},
|
| 62 |
+
{
|
| 63 |
+
"epoch": 0.1671483790089494,
|
| 64 |
+
"grad_norm": 1.3737353086471558,
|
| 65 |
+
"learning_rate": 4.876328844790929e-05,
|
| 66 |
+
"loss": 0.746,
|
| 67 |
+
"step": 600
|
| 68 |
+
},
|
| 69 |
+
{
|
| 70 |
+
"epoch": 0.19500644217710764,
|
| 71 |
+
"grad_norm": 1.3053338527679443,
|
| 72 |
+
"learning_rate": 4.840892983699504e-05,
|
| 73 |
+
"loss": 0.7122,
|
| 74 |
+
"step": 700
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 0.22286450534526586,
|
| 78 |
+
"grad_norm": 1.814271092414856,
|
| 79 |
+
"learning_rate": 4.80545712260808e-05,
|
| 80 |
+
"loss": 0.6914,
|
| 81 |
+
"step": 800
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 0.2507225685134241,
|
| 85 |
+
"grad_norm": 1.3019365072250366,
|
| 86 |
+
"learning_rate": 4.770021261516655e-05,
|
| 87 |
+
"loss": 0.6831,
|
| 88 |
+
"step": 900
|
| 89 |
+
},
|
| 90 |
+
{
|
| 91 |
+
"epoch": 0.2785806316815823,
|
| 92 |
+
"grad_norm": 1.2910503149032593,
|
| 93 |
+
"learning_rate": 4.7345854004252306e-05,
|
| 94 |
+
"loss": 0.6714,
|
| 95 |
+
"step": 1000
|
| 96 |
+
},
|
| 97 |
+
{
|
| 98 |
+
"epoch": 0.2785806316815823,
|
| 99 |
+
"eval_loss": 0.5705545544624329,
|
| 100 |
+
"eval_runtime": 592.3805,
|
| 101 |
+
"eval_samples_per_second": 48.477,
|
| 102 |
+
"eval_steps_per_second": 3.03,
|
| 103 |
+
"step": 1000
|
| 104 |
+
},
|
| 105 |
+
{
|
| 106 |
+
"epoch": 0.30643869484974057,
|
| 107 |
+
"grad_norm": 1.4649542570114136,
|
| 108 |
+
"learning_rate": 4.699149539333806e-05,
|
| 109 |
+
"loss": 0.6487,
|
| 110 |
+
"step": 1100
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 0.3342967580178988,
|
| 114 |
+
"grad_norm": 1.7467780113220215,
|
| 115 |
+
"learning_rate": 4.6637136782423815e-05,
|
| 116 |
+
"loss": 0.6456,
|
| 117 |
+
"step": 1200
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 0.362154821186057,
|
| 121 |
+
"grad_norm": 1.33451247215271,
|
| 122 |
+
"learning_rate": 4.628277817150957e-05,
|
| 123 |
+
"loss": 0.637,
|
| 124 |
+
"step": 1300
|
| 125 |
+
},
|
| 126 |
+
{
|
| 127 |
+
"epoch": 0.3900128843542153,
|
| 128 |
+
"grad_norm": 1.7314374446868896,
|
| 129 |
+
"learning_rate": 4.592841956059532e-05,
|
| 130 |
+
"loss": 0.6295,
|
| 131 |
+
"step": 1400
|
| 132 |
+
},
|
| 133 |
+
{
|
| 134 |
+
"epoch": 0.4178709475223735,
|
| 135 |
+
"grad_norm": 1.344909906387329,
|
| 136 |
+
"learning_rate": 4.557406094968108e-05,
|
| 137 |
+
"loss": 0.621,
|
| 138 |
+
"step": 1500
|
| 139 |
+
},
|
| 140 |
+
{
|
| 141 |
+
"epoch": 0.4178709475223735,
|
| 142 |
+
"eval_loss": 0.5306675434112549,
|
| 143 |
+
"eval_runtime": 592.5408,
|
| 144 |
+
"eval_samples_per_second": 48.464,
|
| 145 |
+
"eval_steps_per_second": 3.029,
|
| 146 |
+
"step": 1500
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 0.4457290106905317,
|
| 150 |
+
"grad_norm": 1.3075149059295654,
|
| 151 |
+
"learning_rate": 4.521970233876683e-05,
|
| 152 |
+
"loss": 0.6229,
|
| 153 |
+
"step": 1600
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 0.47358707385869,
|
| 157 |
+
"grad_norm": 1.4076815843582153,
|
| 158 |
+
"learning_rate": 4.486534372785259e-05,
|
| 159 |
+
"loss": 0.6109,
|
| 160 |
+
"step": 1700
|
| 161 |
+
},
|
| 162 |
+
{
|
| 163 |
+
"epoch": 0.5014451370268482,
|
| 164 |
+
"grad_norm": 1.3399609327316284,
|
| 165 |
+
"learning_rate": 4.451098511693834e-05,
|
| 166 |
+
"loss": 0.6024,
|
| 167 |
+
"step": 1800
|
| 168 |
+
},
|
| 169 |
+
{
|
| 170 |
+
"epoch": 0.5293032001950064,
|
| 171 |
+
"grad_norm": 1.3271087408065796,
|
| 172 |
+
"learning_rate": 4.41566265060241e-05,
|
| 173 |
+
"loss": 0.5997,
|
| 174 |
+
"step": 1900
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 0.5571612633631646,
|
| 178 |
+
"grad_norm": 1.412111520767212,
|
| 179 |
+
"learning_rate": 4.3802267895109855e-05,
|
| 180 |
+
"loss": 0.5839,
|
| 181 |
+
"step": 2000
|
| 182 |
+
},
|
| 183 |
+
{
|
| 184 |
+
"epoch": 0.5571612633631646,
|
| 185 |
+
"eval_loss": 0.5096445679664612,
|
| 186 |
+
"eval_runtime": 594.5376,
|
| 187 |
+
"eval_samples_per_second": 48.301,
|
| 188 |
+
"eval_steps_per_second": 3.019,
|
| 189 |
+
"step": 2000
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 0.5850193265313229,
|
| 193 |
+
"grad_norm": 1.2040321826934814,
|
| 194 |
+
"learning_rate": 4.3447909284195606e-05,
|
| 195 |
+
"loss": 0.5789,
|
| 196 |
+
"step": 2100
|
| 197 |
+
},
|
| 198 |
+
{
|
| 199 |
+
"epoch": 0.6128773896994811,
|
| 200 |
+
"grad_norm": 1.2207297086715698,
|
| 201 |
+
"learning_rate": 4.3093550673281363e-05,
|
| 202 |
+
"loss": 0.5761,
|
| 203 |
+
"step": 2200
|
| 204 |
+
},
|
| 205 |
+
{
|
| 206 |
+
"epoch": 0.6407354528676393,
|
| 207 |
+
"grad_norm": 1.205450177192688,
|
| 208 |
+
"learning_rate": 4.2739192062367114e-05,
|
| 209 |
+
"loss": 0.5709,
|
| 210 |
+
"step": 2300
|
| 211 |
+
},
|
| 212 |
+
{
|
| 213 |
+
"epoch": 0.6685935160357976,
|
| 214 |
+
"grad_norm": 1.3946952819824219,
|
| 215 |
+
"learning_rate": 4.238483345145287e-05,
|
| 216 |
+
"loss": 0.5696,
|
| 217 |
+
"step": 2400
|
| 218 |
+
},
|
| 219 |
+
{
|
| 220 |
+
"epoch": 0.6964515792039558,
|
| 221 |
+
"grad_norm": 1.1846948862075806,
|
| 222 |
+
"learning_rate": 4.203047484053862e-05,
|
| 223 |
+
"loss": 0.5552,
|
| 224 |
+
"step": 2500
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 0.6964515792039558,
|
| 228 |
+
"eval_loss": 0.4957100749015808,
|
| 229 |
+
"eval_runtime": 593.2402,
|
| 230 |
+
"eval_samples_per_second": 48.407,
|
| 231 |
+
"eval_steps_per_second": 3.026,
|
| 232 |
+
"step": 2500
|
| 233 |
+
},
|
| 234 |
+
{
|
| 235 |
+
"epoch": 0.724309642372114,
|
| 236 |
+
"grad_norm": 1.2646228075027466,
|
| 237 |
+
"learning_rate": 4.167611622962439e-05,
|
| 238 |
+
"loss": 0.5573,
|
| 239 |
+
"step": 2600
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 0.7521677055402723,
|
| 243 |
+
"grad_norm": 1.2027941942214966,
|
| 244 |
+
"learning_rate": 4.132175761871014e-05,
|
| 245 |
+
"loss": 0.5568,
|
| 246 |
+
"step": 2700
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"epoch": 0.7800257687084305,
|
| 250 |
+
"grad_norm": 1.2179590463638306,
|
| 251 |
+
"learning_rate": 4.0967399007795895e-05,
|
| 252 |
+
"loss": 0.5579,
|
| 253 |
+
"step": 2800
|
| 254 |
+
},
|
| 255 |
+
{
|
| 256 |
+
"epoch": 0.8078838318765887,
|
| 257 |
+
"grad_norm": 1.2543010711669922,
|
| 258 |
+
"learning_rate": 4.0613040396881646e-05,
|
| 259 |
+
"loss": 0.5632,
|
| 260 |
+
"step": 2900
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 0.835741895044747,
|
| 264 |
+
"grad_norm": 1.2597264051437378,
|
| 265 |
+
"learning_rate": 4.02586817859674e-05,
|
| 266 |
+
"loss": 0.545,
|
| 267 |
+
"step": 3000
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 0.835741895044747,
|
| 271 |
+
"eval_loss": 0.4792587161064148,
|
| 272 |
+
"eval_runtime": 592.7585,
|
| 273 |
+
"eval_samples_per_second": 48.446,
|
| 274 |
+
"eval_steps_per_second": 3.028,
|
| 275 |
+
"step": 3000
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.8635999582129052,
|
| 279 |
+
"grad_norm": 1.3292843103408813,
|
| 280 |
+
"learning_rate": 3.9904323175053155e-05,
|
| 281 |
+
"loss": 0.5571,
|
| 282 |
+
"step": 3100
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.8914580213810634,
|
| 286 |
+
"grad_norm": 1.3142098188400269,
|
| 287 |
+
"learning_rate": 3.9549964564138906e-05,
|
| 288 |
+
"loss": 0.5397,
|
| 289 |
+
"step": 3200
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.9193160845492218,
|
| 293 |
+
"grad_norm": 1.389565348625183,
|
| 294 |
+
"learning_rate": 3.919560595322467e-05,
|
| 295 |
+
"loss": 0.5478,
|
| 296 |
+
"step": 3300
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.94717414771738,
|
| 300 |
+
"grad_norm": 1.1616095304489136,
|
| 301 |
+
"learning_rate": 3.884124734231042e-05,
|
| 302 |
+
"loss": 0.5396,
|
| 303 |
+
"step": 3400
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.9750322108855382,
|
| 307 |
+
"grad_norm": 1.24950110912323,
|
| 308 |
+
"learning_rate": 3.848688873139618e-05,
|
| 309 |
+
"loss": 0.5337,
|
| 310 |
+
"step": 3500
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 0.9750322108855382,
|
| 314 |
+
"eval_loss": 0.4686237871646881,
|
| 315 |
+
"eval_runtime": 593.0319,
|
| 316 |
+
"eval_samples_per_second": 48.424,
|
| 317 |
+
"eval_steps_per_second": 3.027,
|
| 318 |
+
"step": 3500
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 1.0027858063168158,
|
| 322 |
+
"grad_norm": 1.3192429542541504,
|
| 323 |
+
"learning_rate": 3.813253012048193e-05,
|
| 324 |
+
"loss": 0.5301,
|
| 325 |
+
"step": 3600
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 1.030643869484974,
|
| 329 |
+
"grad_norm": 1.465832233428955,
|
| 330 |
+
"learning_rate": 3.777817150956769e-05,
|
| 331 |
+
"loss": 0.5272,
|
| 332 |
+
"step": 3700
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 1.0585019326531322,
|
| 336 |
+
"grad_norm": 1.4403393268585205,
|
| 337 |
+
"learning_rate": 3.742381289865344e-05,
|
| 338 |
+
"loss": 0.5236,
|
| 339 |
+
"step": 3800
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 1.0863599958212906,
|
| 343 |
+
"grad_norm": 1.3801666498184204,
|
| 344 |
+
"learning_rate": 3.706945428773919e-05,
|
| 345 |
+
"loss": 0.5242,
|
| 346 |
+
"step": 3900
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 1.1142180589894488,
|
| 350 |
+
"grad_norm": 1.076539397239685,
|
| 351 |
+
"learning_rate": 3.671509567682495e-05,
|
| 352 |
+
"loss": 0.5224,
|
| 353 |
+
"step": 4000
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 1.1142180589894488,
|
| 357 |
+
"eval_loss": 0.46663618087768555,
|
| 358 |
+
"eval_runtime": 592.8183,
|
| 359 |
+
"eval_samples_per_second": 48.441,
|
| 360 |
+
"eval_steps_per_second": 3.028,
|
| 361 |
+
"step": 4000
|
| 362 |
+
},
|
| 363 |
+
{
|
| 364 |
+
"epoch": 1.142076122157607,
|
| 365 |
+
"grad_norm": 1.3829838037490845,
|
| 366 |
+
"learning_rate": 3.6360737065910704e-05,
|
| 367 |
+
"loss": 0.5217,
|
| 368 |
+
"step": 4100
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 1.1699341853257652,
|
| 372 |
+
"grad_norm": 1.098763108253479,
|
| 373 |
+
"learning_rate": 3.600637845499646e-05,
|
| 374 |
+
"loss": 0.5169,
|
| 375 |
+
"step": 4200
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 1.1977922484939234,
|
| 379 |
+
"grad_norm": 1.260761022567749,
|
| 380 |
+
"learning_rate": 3.565201984408221e-05,
|
| 381 |
+
"loss": 0.5116,
|
| 382 |
+
"step": 4300
|
| 383 |
+
},
|
| 384 |
+
{
|
| 385 |
+
"epoch": 1.2256503116620816,
|
| 386 |
+
"grad_norm": 1.3205015659332275,
|
| 387 |
+
"learning_rate": 3.529766123316797e-05,
|
| 388 |
+
"loss": 0.518,
|
| 389 |
+
"step": 4400
|
| 390 |
+
},
|
| 391 |
+
{
|
| 392 |
+
"epoch": 1.2535083748302398,
|
| 393 |
+
"grad_norm": 1.3871066570281982,
|
| 394 |
+
"learning_rate": 3.494330262225372e-05,
|
| 395 |
+
"loss": 0.5181,
|
| 396 |
+
"step": 4500
|
| 397 |
+
},
|
| 398 |
+
{
|
| 399 |
+
"epoch": 1.2535083748302398,
|
| 400 |
+
"eval_loss": 0.45501282811164856,
|
| 401 |
+
"eval_runtime": 592.8496,
|
| 402 |
+
"eval_samples_per_second": 48.439,
|
| 403 |
+
"eval_steps_per_second": 3.028,
|
| 404 |
+
"step": 4500
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"epoch": 1.2813664379983982,
|
| 408 |
+
"grad_norm": 1.1054390668869019,
|
| 409 |
+
"learning_rate": 3.458894401133948e-05,
|
| 410 |
+
"loss": 0.5148,
|
| 411 |
+
"step": 4600
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 1.3092245011665564,
|
| 415 |
+
"grad_norm": 1.0034719705581665,
|
| 416 |
+
"learning_rate": 3.4234585400425235e-05,
|
| 417 |
+
"loss": 0.5109,
|
| 418 |
+
"step": 4700
|
| 419 |
+
},
|
| 420 |
+
{
|
| 421 |
+
"epoch": 1.3370825643347146,
|
| 422 |
+
"grad_norm": 1.417938232421875,
|
| 423 |
+
"learning_rate": 3.3880226789510986e-05,
|
| 424 |
+
"loss": 0.5104,
|
| 425 |
+
"step": 4800
|
| 426 |
+
},
|
| 427 |
+
{
|
| 428 |
+
"epoch": 1.3649406275028728,
|
| 429 |
+
"grad_norm": 1.243116855621338,
|
| 430 |
+
"learning_rate": 3.3525868178596744e-05,
|
| 431 |
+
"loss": 0.4988,
|
| 432 |
+
"step": 4900
|
| 433 |
+
},
|
| 434 |
+
{
|
| 435 |
+
"epoch": 1.392798690671031,
|
| 436 |
+
"grad_norm": 1.1632623672485352,
|
| 437 |
+
"learning_rate": 3.3171509567682495e-05,
|
| 438 |
+
"loss": 0.5072,
|
| 439 |
+
"step": 5000
|
| 440 |
+
},
|
| 441 |
+
{
|
| 442 |
+
"epoch": 1.392798690671031,
|
| 443 |
+
"eval_loss": 0.45067891478538513,
|
| 444 |
+
"eval_runtime": 593.6193,
|
| 445 |
+
"eval_samples_per_second": 48.376,
|
| 446 |
+
"eval_steps_per_second": 3.024,
|
| 447 |
+
"step": 5000
|
| 448 |
+
},
|
| 449 |
+
{
|
| 450 |
+
"epoch": 1.4206567538391894,
|
| 451 |
+
"grad_norm": 1.3165979385375977,
|
| 452 |
+
"learning_rate": 3.281715095676825e-05,
|
| 453 |
+
"loss": 0.4934,
|
| 454 |
+
"step": 5100
|
| 455 |
+
},
|
| 456 |
+
{
|
| 457 |
+
"epoch": 1.4485148170073476,
|
| 458 |
+
"grad_norm": 1.3166348934173584,
|
| 459 |
+
"learning_rate": 3.2462792345854e-05,
|
| 460 |
+
"loss": 0.51,
|
| 461 |
+
"step": 5200
|
| 462 |
+
},
|
| 463 |
+
{
|
| 464 |
+
"epoch": 1.4763728801755058,
|
| 465 |
+
"grad_norm": 1.737769365310669,
|
| 466 |
+
"learning_rate": 3.210843373493976e-05,
|
| 467 |
+
"loss": 0.5079,
|
| 468 |
+
"step": 5300
|
| 469 |
+
},
|
| 470 |
+
{
|
| 471 |
+
"epoch": 1.504230943343664,
|
| 472 |
+
"grad_norm": 1.0135122537612915,
|
| 473 |
+
"learning_rate": 3.175407512402552e-05,
|
| 474 |
+
"loss": 0.4915,
|
| 475 |
+
"step": 5400
|
| 476 |
+
},
|
| 477 |
+
{
|
| 478 |
+
"epoch": 1.5320890065118222,
|
| 479 |
+
"grad_norm": 1.161383032798767,
|
| 480 |
+
"learning_rate": 3.139971651311127e-05,
|
| 481 |
+
"loss": 0.4972,
|
| 482 |
+
"step": 5500
|
| 483 |
+
},
|
| 484 |
+
{
|
| 485 |
+
"epoch": 1.5320890065118222,
|
| 486 |
+
"eval_loss": 0.4426087737083435,
|
| 487 |
+
"eval_runtime": 592.4939,
|
| 488 |
+
"eval_samples_per_second": 48.468,
|
| 489 |
+
"eval_steps_per_second": 3.03,
|
| 490 |
+
"step": 5500
|
| 491 |
+
},
|
| 492 |
+
{
|
| 493 |
+
"epoch": 1.5599470696799806,
|
| 494 |
+
"grad_norm": 1.2716448307037354,
|
| 495 |
+
"learning_rate": 3.104535790219703e-05,
|
| 496 |
+
"loss": 0.4904,
|
| 497 |
+
"step": 5600
|
| 498 |
+
},
|
| 499 |
+
{
|
| 500 |
+
"epoch": 1.5878051328481386,
|
| 501 |
+
"grad_norm": 1.2625107765197754,
|
| 502 |
+
"learning_rate": 3.069099929128278e-05,
|
| 503 |
+
"loss": 0.4943,
|
| 504 |
+
"step": 5700
|
| 505 |
+
},
|
| 506 |
+
{
|
| 507 |
+
"epoch": 1.615663196016297,
|
| 508 |
+
"grad_norm": 1.2053842544555664,
|
| 509 |
+
"learning_rate": 3.0336640680368532e-05,
|
| 510 |
+
"loss": 0.5028,
|
| 511 |
+
"step": 5800
|
| 512 |
+
},
|
| 513 |
+
{
|
| 514 |
+
"epoch": 1.6435212591844552,
|
| 515 |
+
"grad_norm": 1.1495795249938965,
|
| 516 |
+
"learning_rate": 2.9982282069454286e-05,
|
| 517 |
+
"loss": 0.4929,
|
| 518 |
+
"step": 5900
|
| 519 |
+
},
|
| 520 |
+
{
|
| 521 |
+
"epoch": 1.6713793223526134,
|
| 522 |
+
"grad_norm": 1.1481202840805054,
|
| 523 |
+
"learning_rate": 2.9627923458540047e-05,
|
| 524 |
+
"loss": 0.4926,
|
| 525 |
+
"step": 6000
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"epoch": 1.6713793223526134,
|
| 529 |
+
"eval_loss": 0.444801926612854,
|
| 530 |
+
"eval_runtime": 592.9633,
|
| 531 |
+
"eval_samples_per_second": 48.43,
|
| 532 |
+
"eval_steps_per_second": 3.027,
|
| 533 |
+
"step": 6000
|
| 534 |
+
},
|
| 535 |
+
{
|
| 536 |
+
"epoch": 1.6992373855207716,
|
| 537 |
+
"grad_norm": 1.3731409311294556,
|
| 538 |
+
"learning_rate": 2.92735648476258e-05,
|
| 539 |
+
"loss": 0.5006,
|
| 540 |
+
"step": 6100
|
| 541 |
+
},
|
| 542 |
+
{
|
| 543 |
+
"epoch": 1.7270954486889298,
|
| 544 |
+
"grad_norm": 1.0181461572647095,
|
| 545 |
+
"learning_rate": 2.8919206236711555e-05,
|
| 546 |
+
"loss": 0.4855,
|
| 547 |
+
"step": 6200
|
| 548 |
+
},
|
| 549 |
+
{
|
| 550 |
+
"epoch": 1.7549535118570883,
|
| 551 |
+
"grad_norm": 1.5491364002227783,
|
| 552 |
+
"learning_rate": 2.856484762579731e-05,
|
| 553 |
+
"loss": 0.4994,
|
| 554 |
+
"step": 6300
|
| 555 |
+
},
|
| 556 |
+
{
|
| 557 |
+
"epoch": 1.7828115750252462,
|
| 558 |
+
"grad_norm": 1.149021029472351,
|
| 559 |
+
"learning_rate": 2.8210489014883064e-05,
|
| 560 |
+
"loss": 0.4918,
|
| 561 |
+
"step": 6400
|
| 562 |
+
},
|
| 563 |
+
{
|
| 564 |
+
"epoch": 1.8106696381934047,
|
| 565 |
+
"grad_norm": 1.0654308795928955,
|
| 566 |
+
"learning_rate": 2.7856130403968818e-05,
|
| 567 |
+
"loss": 0.487,
|
| 568 |
+
"step": 6500
|
| 569 |
+
},
|
| 570 |
+
{
|
| 571 |
+
"epoch": 1.8106696381934047,
|
| 572 |
+
"eval_loss": 0.4356010854244232,
|
| 573 |
+
"eval_runtime": 593.5091,
|
| 574 |
+
"eval_samples_per_second": 48.385,
|
| 575 |
+
"eval_steps_per_second": 3.024,
|
| 576 |
+
"step": 6500
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 1.8385277013615628,
|
| 580 |
+
"grad_norm": 1.2700181007385254,
|
| 581 |
+
"learning_rate": 2.750177179305457e-05,
|
| 582 |
+
"loss": 0.4869,
|
| 583 |
+
"step": 6600
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 1.866385764529721,
|
| 587 |
+
"grad_norm": 1.0347015857696533,
|
| 588 |
+
"learning_rate": 2.714741318214033e-05,
|
| 589 |
+
"loss": 0.4861,
|
| 590 |
+
"step": 6700
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 1.8942438276978795,
|
| 594 |
+
"grad_norm": 1.08585786819458,
|
| 595 |
+
"learning_rate": 2.6793054571226084e-05,
|
| 596 |
+
"loss": 0.4884,
|
| 597 |
+
"step": 6800
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 1.9221018908660374,
|
| 601 |
+
"grad_norm": 1.2477092742919922,
|
| 602 |
+
"learning_rate": 2.6438695960311838e-05,
|
| 603 |
+
"loss": 0.478,
|
| 604 |
+
"step": 6900
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 1.9499599540341959,
|
| 608 |
+
"grad_norm": 1.1088532209396362,
|
| 609 |
+
"learning_rate": 2.6084337349397592e-05,
|
| 610 |
+
"loss": 0.4919,
|
| 611 |
+
"step": 7000
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 1.9499599540341959,
|
| 615 |
+
"eval_loss": 0.43220457434654236,
|
| 616 |
+
"eval_runtime": 593.2416,
|
| 617 |
+
"eval_samples_per_second": 48.407,
|
| 618 |
+
"eval_steps_per_second": 3.026,
|
| 619 |
+
"step": 7000
|
| 620 |
+
},
|
| 621 |
+
{
|
| 622 |
+
"epoch": 1.977818017202354,
|
| 623 |
+
"grad_norm": 1.0134484767913818,
|
| 624 |
+
"learning_rate": 2.5729978738483347e-05,
|
| 625 |
+
"loss": 0.4861,
|
| 626 |
+
"step": 7100
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 2.0055716126336316,
|
| 630 |
+
"grad_norm": 1.185179591178894,
|
| 631 |
+
"learning_rate": 2.53756201275691e-05,
|
| 632 |
+
"loss": 0.4805,
|
| 633 |
+
"step": 7200
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 2.03342967580179,
|
| 637 |
+
"grad_norm": 1.2651209831237793,
|
| 638 |
+
"learning_rate": 2.5021261516654855e-05,
|
| 639 |
+
"loss": 0.4785,
|
| 640 |
+
"step": 7300
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 2.061287738969948,
|
| 644 |
+
"grad_norm": 1.0275731086730957,
|
| 645 |
+
"learning_rate": 2.466690290574061e-05,
|
| 646 |
+
"loss": 0.4767,
|
| 647 |
+
"step": 7400
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 2.0891458021381064,
|
| 651 |
+
"grad_norm": 1.0938606262207031,
|
| 652 |
+
"learning_rate": 2.4312544294826363e-05,
|
| 653 |
+
"loss": 0.4682,
|
| 654 |
+
"step": 7500
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 2.0891458021381064,
|
| 658 |
+
"eval_loss": 0.4292644262313843,
|
| 659 |
+
"eval_runtime": 592.5766,
|
| 660 |
+
"eval_samples_per_second": 48.461,
|
| 661 |
+
"eval_steps_per_second": 3.029,
|
| 662 |
+
"step": 7500
|
| 663 |
+
},
|
| 664 |
+
{
|
| 665 |
+
"epoch": 2.1170038653062644,
|
| 666 |
+
"grad_norm": 1.1097854375839233,
|
| 667 |
+
"learning_rate": 2.395818568391212e-05,
|
| 668 |
+
"loss": 0.4703,
|
| 669 |
+
"step": 7600
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 2.144861928474423,
|
| 673 |
+
"grad_norm": 1.3471382856369019,
|
| 674 |
+
"learning_rate": 2.3603827072997875e-05,
|
| 675 |
+
"loss": 0.4843,
|
| 676 |
+
"step": 7700
|
| 677 |
+
},
|
| 678 |
+
{
|
| 679 |
+
"epoch": 2.1727199916425812,
|
| 680 |
+
"grad_norm": 1.351805329322815,
|
| 681 |
+
"learning_rate": 2.324946846208363e-05,
|
| 682 |
+
"loss": 0.4776,
|
| 683 |
+
"step": 7800
|
| 684 |
+
},
|
| 685 |
+
{
|
| 686 |
+
"epoch": 2.200578054810739,
|
| 687 |
+
"grad_norm": 1.1416364908218384,
|
| 688 |
+
"learning_rate": 2.2895109851169387e-05,
|
| 689 |
+
"loss": 0.4714,
|
| 690 |
+
"step": 7900
|
| 691 |
+
},
|
| 692 |
+
{
|
| 693 |
+
"epoch": 2.2284361179788976,
|
| 694 |
+
"grad_norm": 1.1691741943359375,
|
| 695 |
+
"learning_rate": 2.254075124025514e-05,
|
| 696 |
+
"loss": 0.4734,
|
| 697 |
+
"step": 8000
|
| 698 |
+
},
|
| 699 |
+
{
|
| 700 |
+
"epoch": 2.2284361179788976,
|
| 701 |
+
"eval_loss": 0.4240116477012634,
|
| 702 |
+
"eval_runtime": 594.3246,
|
| 703 |
+
"eval_samples_per_second": 48.319,
|
| 704 |
+
"eval_steps_per_second": 3.02,
|
| 705 |
+
"step": 8000
|
| 706 |
+
},
|
| 707 |
+
{
|
| 708 |
+
"epoch": 2.2562941811470556,
|
| 709 |
+
"grad_norm": 1.0872358083724976,
|
| 710 |
+
"learning_rate": 2.2186392629340892e-05,
|
| 711 |
+
"loss": 0.4711,
|
| 712 |
+
"step": 8100
|
| 713 |
+
},
|
| 714 |
+
{
|
| 715 |
+
"epoch": 2.284152244315214,
|
| 716 |
+
"grad_norm": 1.166755199432373,
|
| 717 |
+
"learning_rate": 2.1832034018426646e-05,
|
| 718 |
+
"loss": 0.4674,
|
| 719 |
+
"step": 8200
|
| 720 |
+
},
|
| 721 |
+
{
|
| 722 |
+
"epoch": 2.312010307483372,
|
| 723 |
+
"grad_norm": 1.397355556488037,
|
| 724 |
+
"learning_rate": 2.1477675407512404e-05,
|
| 725 |
+
"loss": 0.4741,
|
| 726 |
+
"step": 8300
|
| 727 |
+
},
|
| 728 |
+
{
|
| 729 |
+
"epoch": 2.3398683706515304,
|
| 730 |
+
"grad_norm": 1.0663005113601685,
|
| 731 |
+
"learning_rate": 2.1123316796598158e-05,
|
| 732 |
+
"loss": 0.4741,
|
| 733 |
+
"step": 8400
|
| 734 |
+
},
|
| 735 |
+
{
|
| 736 |
+
"epoch": 2.367726433819689,
|
| 737 |
+
"grad_norm": 1.2197699546813965,
|
| 738 |
+
"learning_rate": 2.0768958185683912e-05,
|
| 739 |
+
"loss": 0.4691,
|
| 740 |
+
"step": 8500
|
| 741 |
+
},
|
| 742 |
+
{
|
| 743 |
+
"epoch": 2.367726433819689,
|
| 744 |
+
"eval_loss": 0.4226415753364563,
|
| 745 |
+
"eval_runtime": 592.9032,
|
| 746 |
+
"eval_samples_per_second": 48.435,
|
| 747 |
+
"eval_steps_per_second": 3.027,
|
| 748 |
+
"step": 8500
|
| 749 |
+
},
|
| 750 |
+
{
|
| 751 |
+
"epoch": 2.395584496987847,
|
| 752 |
+
"grad_norm": 1.4034844636917114,
|
| 753 |
+
"learning_rate": 2.041459957476967e-05,
|
| 754 |
+
"loss": 0.4749,
|
| 755 |
+
"step": 8600
|
| 756 |
+
},
|
| 757 |
+
{
|
| 758 |
+
"epoch": 2.4234425601560052,
|
| 759 |
+
"grad_norm": 1.2953102588653564,
|
| 760 |
+
"learning_rate": 2.0060240963855424e-05,
|
| 761 |
+
"loss": 0.4757,
|
| 762 |
+
"step": 8700
|
| 763 |
+
},
|
| 764 |
+
{
|
| 765 |
+
"epoch": 2.451300623324163,
|
| 766 |
+
"grad_norm": 1.3071800470352173,
|
| 767 |
+
"learning_rate": 1.9705882352941178e-05,
|
| 768 |
+
"loss": 0.4668,
|
| 769 |
+
"step": 8800
|
| 770 |
+
},
|
| 771 |
+
{
|
| 772 |
+
"epoch": 2.4791586864923216,
|
| 773 |
+
"grad_norm": 1.1789804697036743,
|
| 774 |
+
"learning_rate": 1.9351523742026932e-05,
|
| 775 |
+
"loss": 0.4729,
|
| 776 |
+
"step": 8900
|
| 777 |
+
},
|
| 778 |
+
{
|
| 779 |
+
"epoch": 2.5070167496604796,
|
| 780 |
+
"grad_norm": 1.2676748037338257,
|
| 781 |
+
"learning_rate": 1.8997165131112687e-05,
|
| 782 |
+
"loss": 0.4679,
|
| 783 |
+
"step": 9000
|
| 784 |
+
},
|
| 785 |
+
{
|
| 786 |
+
"epoch": 2.5070167496604796,
|
| 787 |
+
"eval_loss": 0.4187828004360199,
|
| 788 |
+
"eval_runtime": 592.1014,
|
| 789 |
+
"eval_samples_per_second": 48.5,
|
| 790 |
+
"eval_steps_per_second": 3.032,
|
| 791 |
+
"step": 9000
|
| 792 |
+
},
|
| 793 |
+
{
|
| 794 |
+
"epoch": 2.534874812828638,
|
| 795 |
+
"grad_norm": 1.3900854587554932,
|
| 796 |
+
"learning_rate": 1.864280652019844e-05,
|
| 797 |
+
"loss": 0.4677,
|
| 798 |
+
"step": 9100
|
| 799 |
+
},
|
| 800 |
+
{
|
| 801 |
+
"epoch": 2.5627328759967964,
|
| 802 |
+
"grad_norm": 1.2864222526550293,
|
| 803 |
+
"learning_rate": 1.8288447909284195e-05,
|
| 804 |
+
"loss": 0.4584,
|
| 805 |
+
"step": 9200
|
| 806 |
+
},
|
| 807 |
+
{
|
| 808 |
+
"epoch": 2.5905909391649544,
|
| 809 |
+
"grad_norm": 1.0441097021102905,
|
| 810 |
+
"learning_rate": 1.7934089298369953e-05,
|
| 811 |
+
"loss": 0.4654,
|
| 812 |
+
"step": 9300
|
| 813 |
+
},
|
| 814 |
+
{
|
| 815 |
+
"epoch": 2.618449002333113,
|
| 816 |
+
"grad_norm": 1.1249713897705078,
|
| 817 |
+
"learning_rate": 1.7579730687455707e-05,
|
| 818 |
+
"loss": 0.4674,
|
| 819 |
+
"step": 9400
|
| 820 |
+
},
|
| 821 |
+
{
|
| 822 |
+
"epoch": 2.6463070655012713,
|
| 823 |
+
"grad_norm": 1.2885221242904663,
|
| 824 |
+
"learning_rate": 1.722537207654146e-05,
|
| 825 |
+
"loss": 0.4694,
|
| 826 |
+
"step": 9500
|
| 827 |
+
},
|
| 828 |
+
{
|
| 829 |
+
"epoch": 2.6463070655012713,
|
| 830 |
+
"eval_loss": 0.4162205457687378,
|
| 831 |
+
"eval_runtime": 593.1028,
|
| 832 |
+
"eval_samples_per_second": 48.418,
|
| 833 |
+
"eval_steps_per_second": 3.026,
|
| 834 |
+
"step": 9500
|
| 835 |
+
},
|
| 836 |
+
{
|
| 837 |
+
"epoch": 2.6741651286694292,
|
| 838 |
+
"grad_norm": 1.1028586626052856,
|
| 839 |
+
"learning_rate": 1.6871013465627215e-05,
|
| 840 |
+
"loss": 0.4573,
|
| 841 |
+
"step": 9600
|
| 842 |
+
},
|
| 843 |
+
{
|
| 844 |
+
"epoch": 2.7020231918375877,
|
| 845 |
+
"grad_norm": 1.3248066902160645,
|
| 846 |
+
"learning_rate": 1.651665485471297e-05,
|
| 847 |
+
"loss": 0.4609,
|
| 848 |
+
"step": 9700
|
| 849 |
+
},
|
| 850 |
+
{
|
| 851 |
+
"epoch": 2.7298812550057456,
|
| 852 |
+
"grad_norm": 1.073268175125122,
|
| 853 |
+
"learning_rate": 1.6162296243798724e-05,
|
| 854 |
+
"loss": 0.4543,
|
| 855 |
+
"step": 9800
|
| 856 |
+
},
|
| 857 |
+
{
|
| 858 |
+
"epoch": 2.757739318173904,
|
| 859 |
+
"grad_norm": 1.0753856897354126,
|
| 860 |
+
"learning_rate": 1.5807937632884478e-05,
|
| 861 |
+
"loss": 0.4667,
|
| 862 |
+
"step": 9900
|
| 863 |
+
},
|
| 864 |
+
{
|
| 865 |
+
"epoch": 2.785597381342062,
|
| 866 |
+
"grad_norm": 1.2315281629562378,
|
| 867 |
+
"learning_rate": 1.5453579021970235e-05,
|
| 868 |
+
"loss": 0.4573,
|
| 869 |
+
"step": 10000
|
| 870 |
+
},
|
| 871 |
+
{
|
| 872 |
+
"epoch": 2.785597381342062,
|
| 873 |
+
"eval_loss": 0.41505932807922363,
|
| 874 |
+
"eval_runtime": 592.7426,
|
| 875 |
+
"eval_samples_per_second": 48.448,
|
| 876 |
+
"eval_steps_per_second": 3.028,
|
| 877 |
+
"step": 10000
|
| 878 |
+
},
|
| 879 |
+
{
|
| 880 |
+
"epoch": 2.8134554445102204,
|
| 881 |
+
"grad_norm": 1.1854623556137085,
|
| 882 |
+
"learning_rate": 1.509922041105599e-05,
|
| 883 |
+
"loss": 0.4579,
|
| 884 |
+
"step": 10100
|
| 885 |
+
},
|
| 886 |
+
{
|
| 887 |
+
"epoch": 2.841313507678379,
|
| 888 |
+
"grad_norm": 1.1797943115234375,
|
| 889 |
+
"learning_rate": 1.4744861800141744e-05,
|
| 890 |
+
"loss": 0.4512,
|
| 891 |
+
"step": 10200
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 2.869171570846537,
|
| 895 |
+
"grad_norm": 1.2852693796157837,
|
| 896 |
+
"learning_rate": 1.43905031892275e-05,
|
| 897 |
+
"loss": 0.4657,
|
| 898 |
+
"step": 10300
|
| 899 |
+
},
|
| 900 |
+
{
|
| 901 |
+
"epoch": 2.8970296340146953,
|
| 902 |
+
"grad_norm": 1.4903700351715088,
|
| 903 |
+
"learning_rate": 1.4036144578313254e-05,
|
| 904 |
+
"loss": 0.4565,
|
| 905 |
+
"step": 10400
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"epoch": 2.9248876971828532,
|
| 909 |
+
"grad_norm": 1.1999119520187378,
|
| 910 |
+
"learning_rate": 1.3681785967399008e-05,
|
| 911 |
+
"loss": 0.4505,
|
| 912 |
+
"step": 10500
|
| 913 |
+
},
|
| 914 |
+
{
|
| 915 |
+
"epoch": 2.9248876971828532,
|
| 916 |
+
"eval_loss": 0.41494467854499817,
|
| 917 |
+
"eval_runtime": 594.0624,
|
| 918 |
+
"eval_samples_per_second": 48.34,
|
| 919 |
+
"eval_steps_per_second": 3.022,
|
| 920 |
+
"step": 10500
|
| 921 |
+
},
|
| 922 |
+
{
|
| 923 |
+
"epoch": 2.9527457603510117,
|
| 924 |
+
"grad_norm": 1.1072437763214111,
|
| 925 |
+
"learning_rate": 1.3327427356484764e-05,
|
| 926 |
+
"loss": 0.4636,
|
| 927 |
+
"step": 10600
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"epoch": 2.9806038235191696,
|
| 931 |
+
"grad_norm": 1.0771669149398804,
|
| 932 |
+
"learning_rate": 1.2973068745570518e-05,
|
| 933 |
+
"loss": 0.4666,
|
| 934 |
+
"step": 10700
|
| 935 |
+
},
|
| 936 |
+
{
|
| 937 |
+
"epoch": 3.0083574189504474,
|
| 938 |
+
"grad_norm": 1.1003024578094482,
|
| 939 |
+
"learning_rate": 1.2618710134656272e-05,
|
| 940 |
+
"loss": 0.4456,
|
| 941 |
+
"step": 10800
|
| 942 |
+
},
|
| 943 |
+
{
|
| 944 |
+
"epoch": 3.036215482118606,
|
| 945 |
+
"grad_norm": 1.417353630065918,
|
| 946 |
+
"learning_rate": 1.2264351523742028e-05,
|
| 947 |
+
"loss": 0.4594,
|
| 948 |
+
"step": 10900
|
| 949 |
+
},
|
| 950 |
+
{
|
| 951 |
+
"epoch": 3.064073545286764,
|
| 952 |
+
"grad_norm": 1.1961385011672974,
|
| 953 |
+
"learning_rate": 1.1909992912827782e-05,
|
| 954 |
+
"loss": 0.4478,
|
| 955 |
+
"step": 11000
|
| 956 |
+
},
|
| 957 |
+
{
|
| 958 |
+
"epoch": 3.064073545286764,
|
| 959 |
+
"eval_loss": 0.4131682813167572,
|
| 960 |
+
"eval_runtime": 592.6765,
|
| 961 |
+
"eval_samples_per_second": 48.453,
|
| 962 |
+
"eval_steps_per_second": 3.029,
|
| 963 |
+
"step": 11000
|
| 964 |
+
},
|
| 965 |
+
{
|
| 966 |
+
"epoch": 3.091931608454922,
|
| 967 |
+
"grad_norm": 1.3566352128982544,
|
| 968 |
+
"learning_rate": 1.1555634301913537e-05,
|
| 969 |
+
"loss": 0.4416,
|
| 970 |
+
"step": 11100
|
| 971 |
+
},
|
| 972 |
+
{
|
| 973 |
+
"epoch": 3.1197896716230806,
|
| 974 |
+
"grad_norm": 1.3073431253433228,
|
| 975 |
+
"learning_rate": 1.1201275690999293e-05,
|
| 976 |
+
"loss": 0.4509,
|
| 977 |
+
"step": 11200
|
| 978 |
+
},
|
| 979 |
+
{
|
| 980 |
+
"epoch": 3.1476477347912386,
|
| 981 |
+
"grad_norm": 1.3190025091171265,
|
| 982 |
+
"learning_rate": 1.0846917080085047e-05,
|
| 983 |
+
"loss": 0.4513,
|
| 984 |
+
"step": 11300
|
| 985 |
+
},
|
| 986 |
+
{
|
| 987 |
+
"epoch": 3.175505797959397,
|
| 988 |
+
"grad_norm": 1.3781085014343262,
|
| 989 |
+
"learning_rate": 1.0492558469170801e-05,
|
| 990 |
+
"loss": 0.4437,
|
| 991 |
+
"step": 11400
|
| 992 |
+
},
|
| 993 |
+
{
|
| 994 |
+
"epoch": 3.203363861127555,
|
| 995 |
+
"grad_norm": 1.306618332862854,
|
| 996 |
+
"learning_rate": 1.0138199858256555e-05,
|
| 997 |
+
"loss": 0.4454,
|
| 998 |
+
"step": 11500
|
| 999 |
+
},
|
| 1000 |
+
{
|
| 1001 |
+
"epoch": 3.203363861127555,
|
| 1002 |
+
"eval_loss": 0.4108191132545471,
|
| 1003 |
+
"eval_runtime": 593.9192,
|
| 1004 |
+
"eval_samples_per_second": 48.352,
|
| 1005 |
+
"eval_steps_per_second": 3.022,
|
| 1006 |
+
"step": 11500
|
| 1007 |
+
},
|
| 1008 |
+
{
|
| 1009 |
+
"epoch": 3.2312219242957134,
|
| 1010 |
+
"grad_norm": 1.4700162410736084,
|
| 1011 |
+
"learning_rate": 9.783841247342311e-06,
|
| 1012 |
+
"loss": 0.4471,
|
| 1013 |
+
"step": 11600
|
| 1014 |
+
},
|
| 1015 |
+
{
|
| 1016 |
+
"epoch": 3.2590799874638714,
|
| 1017 |
+
"grad_norm": 1.1304278373718262,
|
| 1018 |
+
"learning_rate": 9.429482636428065e-06,
|
| 1019 |
+
"loss": 0.4536,
|
| 1020 |
+
"step": 11700
|
| 1021 |
+
},
|
| 1022 |
+
{
|
| 1023 |
+
"epoch": 3.28693805063203,
|
| 1024 |
+
"grad_norm": 1.4289369583129883,
|
| 1025 |
+
"learning_rate": 9.075124025513821e-06,
|
| 1026 |
+
"loss": 0.4474,
|
| 1027 |
+
"step": 11800
|
| 1028 |
+
},
|
| 1029 |
+
{
|
| 1030 |
+
"epoch": 3.3147961138001882,
|
| 1031 |
+
"grad_norm": 1.3017057180404663,
|
| 1032 |
+
"learning_rate": 8.720765414599575e-06,
|
| 1033 |
+
"loss": 0.4449,
|
| 1034 |
+
"step": 11900
|
| 1035 |
+
},
|
| 1036 |
+
{
|
| 1037 |
+
"epoch": 3.342654176968346,
|
| 1038 |
+
"grad_norm": 1.4927443265914917,
|
| 1039 |
+
"learning_rate": 8.36640680368533e-06,
|
| 1040 |
+
"loss": 0.4557,
|
| 1041 |
+
"step": 12000
|
| 1042 |
+
},
|
| 1043 |
+
{
|
| 1044 |
+
"epoch": 3.342654176968346,
|
| 1045 |
+
"eval_loss": 0.4085528552532196,
|
| 1046 |
+
"eval_runtime": 592.2863,
|
| 1047 |
+
"eval_samples_per_second": 48.485,
|
| 1048 |
+
"eval_steps_per_second": 3.031,
|
| 1049 |
+
"step": 12000
|
| 1050 |
+
},
|
| 1051 |
+
{
|
| 1052 |
+
"epoch": 3.3705122401365046,
|
| 1053 |
+
"grad_norm": 1.4530751705169678,
|
| 1054 |
+
"learning_rate": 8.012048192771085e-06,
|
| 1055 |
+
"loss": 0.455,
|
| 1056 |
+
"step": 12100
|
| 1057 |
+
},
|
| 1058 |
+
{
|
| 1059 |
+
"epoch": 3.3983703033046626,
|
| 1060 |
+
"grad_norm": 1.4134407043457031,
|
| 1061 |
+
"learning_rate": 7.65768958185684e-06,
|
| 1062 |
+
"loss": 0.4504,
|
| 1063 |
+
"step": 12200
|
| 1064 |
+
},
|
| 1065 |
+
{
|
| 1066 |
+
"epoch": 3.426228366472821,
|
| 1067 |
+
"grad_norm": 1.2031890153884888,
|
| 1068 |
+
"learning_rate": 7.303330970942594e-06,
|
| 1069 |
+
"loss": 0.4473,
|
| 1070 |
+
"step": 12300
|
| 1071 |
+
},
|
| 1072 |
+
{
|
| 1073 |
+
"epoch": 3.454086429640979,
|
| 1074 |
+
"grad_norm": 1.3506805896759033,
|
| 1075 |
+
"learning_rate": 6.94897236002835e-06,
|
| 1076 |
+
"loss": 0.4452,
|
| 1077 |
+
"step": 12400
|
| 1078 |
+
},
|
| 1079 |
+
{
|
| 1080 |
+
"epoch": 3.4819444928091374,
|
| 1081 |
+
"grad_norm": 1.6460970640182495,
|
| 1082 |
+
"learning_rate": 6.594613749114104e-06,
|
| 1083 |
+
"loss": 0.4475,
|
| 1084 |
+
"step": 12500
|
| 1085 |
+
},
|
| 1086 |
+
{
|
| 1087 |
+
"epoch": 3.4819444928091374,
|
| 1088 |
+
"eval_loss": 0.40733858942985535,
|
| 1089 |
+
"eval_runtime": 593.8096,
|
| 1090 |
+
"eval_samples_per_second": 48.361,
|
| 1091 |
+
"eval_steps_per_second": 3.023,
|
| 1092 |
+
"step": 12500
|
| 1093 |
+
},
|
| 1094 |
+
{
|
| 1095 |
+
"epoch": 3.509802555977296,
|
| 1096 |
+
"grad_norm": 1.34632408618927,
|
| 1097 |
+
"learning_rate": 6.240255138199858e-06,
|
| 1098 |
+
"loss": 0.4472,
|
| 1099 |
+
"step": 12600
|
| 1100 |
+
},
|
| 1101 |
+
{
|
| 1102 |
+
"epoch": 3.537660619145454,
|
| 1103 |
+
"grad_norm": 1.1388472318649292,
|
| 1104 |
+
"learning_rate": 5.885896527285613e-06,
|
| 1105 |
+
"loss": 0.4504,
|
| 1106 |
+
"step": 12700
|
| 1107 |
+
},
|
| 1108 |
+
{
|
| 1109 |
+
"epoch": 3.5655186823136122,
|
| 1110 |
+
"grad_norm": 1.3838173151016235,
|
| 1111 |
+
"learning_rate": 5.531537916371368e-06,
|
| 1112 |
+
"loss": 0.4509,
|
| 1113 |
+
"step": 12800
|
| 1114 |
+
},
|
| 1115 |
+
{
|
| 1116 |
+
"epoch": 3.59337674548177,
|
| 1117 |
+
"grad_norm": 1.2048169374465942,
|
| 1118 |
+
"learning_rate": 5.1771793054571225e-06,
|
| 1119 |
+
"loss": 0.4484,
|
| 1120 |
+
"step": 12900
|
| 1121 |
+
},
|
| 1122 |
+
{
|
| 1123 |
+
"epoch": 3.6212348086499286,
|
| 1124 |
+
"grad_norm": 1.337014079093933,
|
| 1125 |
+
"learning_rate": 4.8228206945428775e-06,
|
| 1126 |
+
"loss": 0.4514,
|
| 1127 |
+
"step": 13000
|
| 1128 |
+
},
|
| 1129 |
+
{
|
| 1130 |
+
"epoch": 3.6212348086499286,
|
| 1131 |
+
"eval_loss": 0.40576237440109253,
|
| 1132 |
+
"eval_runtime": 592.3205,
|
| 1133 |
+
"eval_samples_per_second": 48.482,
|
| 1134 |
+
"eval_steps_per_second": 3.03,
|
| 1135 |
+
"step": 13000
|
| 1136 |
+
},
|
| 1137 |
+
{
|
| 1138 |
+
"epoch": 3.6490928718180866,
|
| 1139 |
+
"grad_norm": 1.2974600791931152,
|
| 1140 |
+
"learning_rate": 4.4684620836286326e-06,
|
| 1141 |
+
"loss": 0.4449,
|
| 1142 |
+
"step": 13100
|
| 1143 |
+
},
|
| 1144 |
+
{
|
| 1145 |
+
"epoch": 3.676950934986245,
|
| 1146 |
+
"grad_norm": 1.1322963237762451,
|
| 1147 |
+
"learning_rate": 4.114103472714388e-06,
|
| 1148 |
+
"loss": 0.4514,
|
| 1149 |
+
"step": 13200
|
| 1150 |
+
},
|
| 1151 |
+
{
|
| 1152 |
+
"epoch": 3.7048089981544035,
|
| 1153 |
+
"grad_norm": 1.2485069036483765,
|
| 1154 |
+
"learning_rate": 3.7597448618001422e-06,
|
| 1155 |
+
"loss": 0.441,
|
| 1156 |
+
"step": 13300
|
| 1157 |
+
},
|
| 1158 |
+
{
|
| 1159 |
+
"epoch": 3.7326670613225614,
|
| 1160 |
+
"grad_norm": 1.3043463230133057,
|
| 1161 |
+
"learning_rate": 3.405386250885897e-06,
|
| 1162 |
+
"loss": 0.4429,
|
| 1163 |
+
"step": 13400
|
| 1164 |
+
},
|
| 1165 |
+
{
|
| 1166 |
+
"epoch": 3.76052512449072,
|
| 1167 |
+
"grad_norm": 1.22727632522583,
|
| 1168 |
+
"learning_rate": 3.0510276399716515e-06,
|
| 1169 |
+
"loss": 0.4461,
|
| 1170 |
+
"step": 13500
|
| 1171 |
+
},
|
| 1172 |
+
{
|
| 1173 |
+
"epoch": 3.76052512449072,
|
| 1174 |
+
"eval_loss": 0.40465712547302246,
|
| 1175 |
+
"eval_runtime": 593.0804,
|
| 1176 |
+
"eval_samples_per_second": 48.42,
|
| 1177 |
+
"eval_steps_per_second": 3.027,
|
| 1178 |
+
"step": 13500
|
| 1179 |
+
},
|
| 1180 |
+
{
|
| 1181 |
+
"epoch": 3.7883831876588783,
|
| 1182 |
+
"grad_norm": 1.322852611541748,
|
| 1183 |
+
"learning_rate": 2.696669029057406e-06,
|
| 1184 |
+
"loss": 0.4495,
|
| 1185 |
+
"step": 13600
|
| 1186 |
+
},
|
| 1187 |
+
{
|
| 1188 |
+
"epoch": 3.8162412508270362,
|
| 1189 |
+
"grad_norm": 1.18853759765625,
|
| 1190 |
+
"learning_rate": 2.342310418143161e-06,
|
| 1191 |
+
"loss": 0.4363,
|
| 1192 |
+
"step": 13700
|
| 1193 |
+
},
|
| 1194 |
+
{
|
| 1195 |
+
"epoch": 3.8440993139951942,
|
| 1196 |
+
"grad_norm": 1.22146475315094,
|
| 1197 |
+
"learning_rate": 1.987951807228916e-06,
|
| 1198 |
+
"loss": 0.4393,
|
| 1199 |
+
"step": 13800
|
| 1200 |
+
},
|
| 1201 |
+
{
|
| 1202 |
+
"epoch": 3.8719573771633526,
|
| 1203 |
+
"grad_norm": 1.3995431661605835,
|
| 1204 |
+
"learning_rate": 1.6335931963146704e-06,
|
| 1205 |
+
"loss": 0.4475,
|
| 1206 |
+
"step": 13900
|
| 1207 |
+
},
|
| 1208 |
+
{
|
| 1209 |
+
"epoch": 3.899815440331511,
|
| 1210 |
+
"grad_norm": 1.402491807937622,
|
| 1211 |
+
"learning_rate": 1.2792345854004253e-06,
|
| 1212 |
+
"loss": 0.445,
|
| 1213 |
+
"step": 14000
|
| 1214 |
+
},
|
| 1215 |
+
{
|
| 1216 |
+
"epoch": 3.899815440331511,
|
| 1217 |
+
"eval_loss": 0.4038073718547821,
|
| 1218 |
+
"eval_runtime": 594.2622,
|
| 1219 |
+
"eval_samples_per_second": 48.324,
|
| 1220 |
+
"eval_steps_per_second": 3.021,
|
| 1221 |
+
"step": 14000
|
| 1222 |
+
}
|
| 1223 |
+
],
|
| 1224 |
+
"logging_steps": 100,
|
| 1225 |
+
"max_steps": 14360,
|
| 1226 |
+
"num_input_tokens_seen": 0,
|
| 1227 |
+
"num_train_epochs": 4,
|
| 1228 |
+
"save_steps": 500,
|
| 1229 |
+
"stateful_callbacks": {
|
| 1230 |
+
"TrainerControl": {
|
| 1231 |
+
"args": {
|
| 1232 |
+
"should_epoch_stop": false,
|
| 1233 |
+
"should_evaluate": false,
|
| 1234 |
+
"should_log": false,
|
| 1235 |
+
"should_save": true,
|
| 1236 |
+
"should_training_stop": false
|
| 1237 |
+
},
|
| 1238 |
+
"attributes": {}
|
| 1239 |
+
}
|
| 1240 |
+
},
|
| 1241 |
+
"total_flos": 4.932896695826283e+21,
|
| 1242 |
+
"train_batch_size": 4,
|
| 1243 |
+
"trial_name": null,
|
| 1244 |
+
"trial_params": null
|
| 1245 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3ebac2dfd955401b10729cffe3d6f2cf3db168592c54addf497fd98fd6c104b7
|
| 3 |
+
size 5905
|