Commit
•
921e45e
1
Parent(s):
a5bc9fe
Upload 9 files
Browse files- README.md +202 -0
- adapter_config.json +29 -0
- adapter_model.safetensors +3 -0
- optimizer.pt +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- tokenizer.json +0 -0
- tokenizer_config.json +2070 -0
- trainer_state.json +2513 -0
README.md
ADDED
|
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: peft
|
| 3 |
+
base_model: meta-llama/Llama-3.2-11B-Vision
|
| 4 |
+
---
|
| 5 |
+
|
| 6 |
+
# Model Card for Model ID
|
| 7 |
+
|
| 8 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
| 9 |
+
|
| 10 |
+
|
| 11 |
+
|
| 12 |
+
## Model Details
|
| 13 |
+
|
| 14 |
+
### Model Description
|
| 15 |
+
|
| 16 |
+
<!-- Provide a longer summary of what this model is. -->
|
| 17 |
+
|
| 18 |
+
|
| 19 |
+
|
| 20 |
+
- **Developed by:** [More Information Needed]
|
| 21 |
+
- **Funded by [optional]:** [More Information Needed]
|
| 22 |
+
- **Shared by [optional]:** [More Information Needed]
|
| 23 |
+
- **Model type:** [More Information Needed]
|
| 24 |
+
- **Language(s) (NLP):** [More Information Needed]
|
| 25 |
+
- **License:** [More Information Needed]
|
| 26 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
| 27 |
+
|
| 28 |
+
### Model Sources [optional]
|
| 29 |
+
|
| 30 |
+
<!-- Provide the basic links for the model. -->
|
| 31 |
+
|
| 32 |
+
- **Repository:** [More Information Needed]
|
| 33 |
+
- **Paper [optional]:** [More Information Needed]
|
| 34 |
+
- **Demo [optional]:** [More Information Needed]
|
| 35 |
+
|
| 36 |
+
## Uses
|
| 37 |
+
|
| 38 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
| 39 |
+
|
| 40 |
+
### Direct Use
|
| 41 |
+
|
| 42 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
| 43 |
+
|
| 44 |
+
[More Information Needed]
|
| 45 |
+
|
| 46 |
+
### Downstream Use [optional]
|
| 47 |
+
|
| 48 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
| 49 |
+
|
| 50 |
+
[More Information Needed]
|
| 51 |
+
|
| 52 |
+
### Out-of-Scope Use
|
| 53 |
+
|
| 54 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
| 55 |
+
|
| 56 |
+
[More Information Needed]
|
| 57 |
+
|
| 58 |
+
## Bias, Risks, and Limitations
|
| 59 |
+
|
| 60 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
| 61 |
+
|
| 62 |
+
[More Information Needed]
|
| 63 |
+
|
| 64 |
+
### Recommendations
|
| 65 |
+
|
| 66 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
| 67 |
+
|
| 68 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
| 69 |
+
|
| 70 |
+
## How to Get Started with the Model
|
| 71 |
+
|
| 72 |
+
Use the code below to get started with the model.
|
| 73 |
+
|
| 74 |
+
[More Information Needed]
|
| 75 |
+
|
| 76 |
+
## Training Details
|
| 77 |
+
|
| 78 |
+
### Training Data
|
| 79 |
+
|
| 80 |
+
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
| 81 |
+
|
| 82 |
+
[More Information Needed]
|
| 83 |
+
|
| 84 |
+
### Training Procedure
|
| 85 |
+
|
| 86 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
| 87 |
+
|
| 88 |
+
#### Preprocessing [optional]
|
| 89 |
+
|
| 90 |
+
[More Information Needed]
|
| 91 |
+
|
| 92 |
+
|
| 93 |
+
#### Training Hyperparameters
|
| 94 |
+
|
| 95 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
| 96 |
+
|
| 97 |
+
#### Speeds, Sizes, Times [optional]
|
| 98 |
+
|
| 99 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
| 100 |
+
|
| 101 |
+
[More Information Needed]
|
| 102 |
+
|
| 103 |
+
## Evaluation
|
| 104 |
+
|
| 105 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
| 106 |
+
|
| 107 |
+
### Testing Data, Factors & Metrics
|
| 108 |
+
|
| 109 |
+
#### Testing Data
|
| 110 |
+
|
| 111 |
+
<!-- This should link to a Dataset Card if possible. -->
|
| 112 |
+
|
| 113 |
+
[More Information Needed]
|
| 114 |
+
|
| 115 |
+
#### Factors
|
| 116 |
+
|
| 117 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
| 118 |
+
|
| 119 |
+
[More Information Needed]
|
| 120 |
+
|
| 121 |
+
#### Metrics
|
| 122 |
+
|
| 123 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
| 124 |
+
|
| 125 |
+
[More Information Needed]
|
| 126 |
+
|
| 127 |
+
### Results
|
| 128 |
+
|
| 129 |
+
[More Information Needed]
|
| 130 |
+
|
| 131 |
+
#### Summary
|
| 132 |
+
|
| 133 |
+
|
| 134 |
+
|
| 135 |
+
## Model Examination [optional]
|
| 136 |
+
|
| 137 |
+
<!-- Relevant interpretability work for the model goes here -->
|
| 138 |
+
|
| 139 |
+
[More Information Needed]
|
| 140 |
+
|
| 141 |
+
## Environmental Impact
|
| 142 |
+
|
| 143 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
| 144 |
+
|
| 145 |
+
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
| 146 |
+
|
| 147 |
+
- **Hardware Type:** [More Information Needed]
|
| 148 |
+
- **Hours used:** [More Information Needed]
|
| 149 |
+
- **Cloud Provider:** [More Information Needed]
|
| 150 |
+
- **Compute Region:** [More Information Needed]
|
| 151 |
+
- **Carbon Emitted:** [More Information Needed]
|
| 152 |
+
|
| 153 |
+
## Technical Specifications [optional]
|
| 154 |
+
|
| 155 |
+
### Model Architecture and Objective
|
| 156 |
+
|
| 157 |
+
[More Information Needed]
|
| 158 |
+
|
| 159 |
+
### Compute Infrastructure
|
| 160 |
+
|
| 161 |
+
[More Information Needed]
|
| 162 |
+
|
| 163 |
+
#### Hardware
|
| 164 |
+
|
| 165 |
+
[More Information Needed]
|
| 166 |
+
|
| 167 |
+
#### Software
|
| 168 |
+
|
| 169 |
+
[More Information Needed]
|
| 170 |
+
|
| 171 |
+
## Citation [optional]
|
| 172 |
+
|
| 173 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
| 174 |
+
|
| 175 |
+
**BibTeX:**
|
| 176 |
+
|
| 177 |
+
[More Information Needed]
|
| 178 |
+
|
| 179 |
+
**APA:**
|
| 180 |
+
|
| 181 |
+
[More Information Needed]
|
| 182 |
+
|
| 183 |
+
## Glossary [optional]
|
| 184 |
+
|
| 185 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
| 186 |
+
|
| 187 |
+
[More Information Needed]
|
| 188 |
+
|
| 189 |
+
## More Information [optional]
|
| 190 |
+
|
| 191 |
+
[More Information Needed]
|
| 192 |
+
|
| 193 |
+
## Model Card Authors [optional]
|
| 194 |
+
|
| 195 |
+
[More Information Needed]
|
| 196 |
+
|
| 197 |
+
## Model Card Contact
|
| 198 |
+
|
| 199 |
+
[More Information Needed]
|
| 200 |
+
### Framework versions
|
| 201 |
+
|
| 202 |
+
- PEFT 0.12.0
|
adapter_config.json
ADDED
|
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "meta-llama/Llama-3.2-11B-Vision",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"fan_in_fan_out": false,
|
| 7 |
+
"inference_mode": true,
|
| 8 |
+
"init_lora_weights": true,
|
| 9 |
+
"layer_replication": null,
|
| 10 |
+
"layers_pattern": null,
|
| 11 |
+
"layers_to_transform": null,
|
| 12 |
+
"loftq_config": {},
|
| 13 |
+
"lora_alpha": 32,
|
| 14 |
+
"lora_dropout": 0,
|
| 15 |
+
"megatron_config": null,
|
| 16 |
+
"megatron_core": "megatron.core",
|
| 17 |
+
"modules_to_save": null,
|
| 18 |
+
"peft_type": "LORA",
|
| 19 |
+
"r": 16,
|
| 20 |
+
"rank_pattern": {},
|
| 21 |
+
"revision": null,
|
| 22 |
+
"target_modules": [
|
| 23 |
+
"q_proj",
|
| 24 |
+
"v_proj"
|
| 25 |
+
],
|
| 26 |
+
"task_type": "CAUSAL_LM",
|
| 27 |
+
"use_dora": false,
|
| 28 |
+
"use_rslora": false
|
| 29 |
+
}
|
adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a8e254b35aaf7f623394baf3159e6ae63dda53b43873da3941158f0f1af07fb4
|
| 3 |
+
size 262144
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fcb9333fe25b592b0b58293607bb9e3e64031eb6ece93c27104eae03e67bb83b
|
| 3 |
+
size 262144
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d245e05e72192c132e0f2edb6fdcae0c578c890f0fe912f17ec7b0bba2d38cc3
|
| 3 |
+
size 14244
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0400507617532be0e03a939f41d86f6ad931630794032d2f8a004ee6ea1d25fb
|
| 3 |
+
size 1064
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,2070 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"128000": {
|
| 4 |
+
"content": "<|begin_of_text|>",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"128001": {
|
| 12 |
+
"content": "<|end_of_text|>",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"128002": {
|
| 20 |
+
"content": "<|reserved_special_token_0|>",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"128003": {
|
| 28 |
+
"content": "<|reserved_special_token_1|>",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"128004": {
|
| 36 |
+
"content": "<|finetune_right_pad_id|>",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
},
|
| 43 |
+
"128005": {
|
| 44 |
+
"content": "<|step_id|>",
|
| 45 |
+
"lstrip": false,
|
| 46 |
+
"normalized": false,
|
| 47 |
+
"rstrip": false,
|
| 48 |
+
"single_word": false,
|
| 49 |
+
"special": true
|
| 50 |
+
},
|
| 51 |
+
"128006": {
|
| 52 |
+
"content": "<|start_header_id|>",
|
| 53 |
+
"lstrip": false,
|
| 54 |
+
"normalized": false,
|
| 55 |
+
"rstrip": false,
|
| 56 |
+
"single_word": false,
|
| 57 |
+
"special": true
|
| 58 |
+
},
|
| 59 |
+
"128007": {
|
| 60 |
+
"content": "<|end_header_id|>",
|
| 61 |
+
"lstrip": false,
|
| 62 |
+
"normalized": false,
|
| 63 |
+
"rstrip": false,
|
| 64 |
+
"single_word": false,
|
| 65 |
+
"special": true
|
| 66 |
+
},
|
| 67 |
+
"128008": {
|
| 68 |
+
"content": "<|eom_id|>",
|
| 69 |
+
"lstrip": false,
|
| 70 |
+
"normalized": false,
|
| 71 |
+
"rstrip": false,
|
| 72 |
+
"single_word": false,
|
| 73 |
+
"special": true
|
| 74 |
+
},
|
| 75 |
+
"128009": {
|
| 76 |
+
"content": "<|eot_id|>",
|
| 77 |
+
"lstrip": false,
|
| 78 |
+
"normalized": false,
|
| 79 |
+
"rstrip": false,
|
| 80 |
+
"single_word": false,
|
| 81 |
+
"special": true
|
| 82 |
+
},
|
| 83 |
+
"128010": {
|
| 84 |
+
"content": "<|python_tag|>",
|
| 85 |
+
"lstrip": false,
|
| 86 |
+
"normalized": false,
|
| 87 |
+
"rstrip": false,
|
| 88 |
+
"single_word": false,
|
| 89 |
+
"special": true
|
| 90 |
+
},
|
| 91 |
+
"128011": {
|
| 92 |
+
"content": "<|reserved_special_token_2|>",
|
| 93 |
+
"lstrip": false,
|
| 94 |
+
"normalized": false,
|
| 95 |
+
"rstrip": false,
|
| 96 |
+
"single_word": false,
|
| 97 |
+
"special": true
|
| 98 |
+
},
|
| 99 |
+
"128012": {
|
| 100 |
+
"content": "<|reserved_special_token_3|>",
|
| 101 |
+
"lstrip": false,
|
| 102 |
+
"normalized": false,
|
| 103 |
+
"rstrip": false,
|
| 104 |
+
"single_word": false,
|
| 105 |
+
"special": true
|
| 106 |
+
},
|
| 107 |
+
"128013": {
|
| 108 |
+
"content": "<|reserved_special_token_4|>",
|
| 109 |
+
"lstrip": false,
|
| 110 |
+
"normalized": false,
|
| 111 |
+
"rstrip": false,
|
| 112 |
+
"single_word": false,
|
| 113 |
+
"special": true
|
| 114 |
+
},
|
| 115 |
+
"128014": {
|
| 116 |
+
"content": "<|reserved_special_token_5|>",
|
| 117 |
+
"lstrip": false,
|
| 118 |
+
"normalized": false,
|
| 119 |
+
"rstrip": false,
|
| 120 |
+
"single_word": false,
|
| 121 |
+
"special": true
|
| 122 |
+
},
|
| 123 |
+
"128015": {
|
| 124 |
+
"content": "<|reserved_special_token_6|>",
|
| 125 |
+
"lstrip": false,
|
| 126 |
+
"normalized": false,
|
| 127 |
+
"rstrip": false,
|
| 128 |
+
"single_word": false,
|
| 129 |
+
"special": true
|
| 130 |
+
},
|
| 131 |
+
"128016": {
|
| 132 |
+
"content": "<|reserved_special_token_7|>",
|
| 133 |
+
"lstrip": false,
|
| 134 |
+
"normalized": false,
|
| 135 |
+
"rstrip": false,
|
| 136 |
+
"single_word": false,
|
| 137 |
+
"special": true
|
| 138 |
+
},
|
| 139 |
+
"128017": {
|
| 140 |
+
"content": "<|reserved_special_token_8|>",
|
| 141 |
+
"lstrip": false,
|
| 142 |
+
"normalized": false,
|
| 143 |
+
"rstrip": false,
|
| 144 |
+
"single_word": false,
|
| 145 |
+
"special": true
|
| 146 |
+
},
|
| 147 |
+
"128018": {
|
| 148 |
+
"content": "<|reserved_special_token_9|>",
|
| 149 |
+
"lstrip": false,
|
| 150 |
+
"normalized": false,
|
| 151 |
+
"rstrip": false,
|
| 152 |
+
"single_word": false,
|
| 153 |
+
"special": true
|
| 154 |
+
},
|
| 155 |
+
"128019": {
|
| 156 |
+
"content": "<|reserved_special_token_10|>",
|
| 157 |
+
"lstrip": false,
|
| 158 |
+
"normalized": false,
|
| 159 |
+
"rstrip": false,
|
| 160 |
+
"single_word": false,
|
| 161 |
+
"special": true
|
| 162 |
+
},
|
| 163 |
+
"128020": {
|
| 164 |
+
"content": "<|reserved_special_token_11|>",
|
| 165 |
+
"lstrip": false,
|
| 166 |
+
"normalized": false,
|
| 167 |
+
"rstrip": false,
|
| 168 |
+
"single_word": false,
|
| 169 |
+
"special": true
|
| 170 |
+
},
|
| 171 |
+
"128021": {
|
| 172 |
+
"content": "<|reserved_special_token_12|>",
|
| 173 |
+
"lstrip": false,
|
| 174 |
+
"normalized": false,
|
| 175 |
+
"rstrip": false,
|
| 176 |
+
"single_word": false,
|
| 177 |
+
"special": true
|
| 178 |
+
},
|
| 179 |
+
"128022": {
|
| 180 |
+
"content": "<|reserved_special_token_13|>",
|
| 181 |
+
"lstrip": false,
|
| 182 |
+
"normalized": false,
|
| 183 |
+
"rstrip": false,
|
| 184 |
+
"single_word": false,
|
| 185 |
+
"special": true
|
| 186 |
+
},
|
| 187 |
+
"128023": {
|
| 188 |
+
"content": "<|reserved_special_token_14|>",
|
| 189 |
+
"lstrip": false,
|
| 190 |
+
"normalized": false,
|
| 191 |
+
"rstrip": false,
|
| 192 |
+
"single_word": false,
|
| 193 |
+
"special": true
|
| 194 |
+
},
|
| 195 |
+
"128024": {
|
| 196 |
+
"content": "<|reserved_special_token_15|>",
|
| 197 |
+
"lstrip": false,
|
| 198 |
+
"normalized": false,
|
| 199 |
+
"rstrip": false,
|
| 200 |
+
"single_word": false,
|
| 201 |
+
"special": true
|
| 202 |
+
},
|
| 203 |
+
"128025": {
|
| 204 |
+
"content": "<|reserved_special_token_16|>",
|
| 205 |
+
"lstrip": false,
|
| 206 |
+
"normalized": false,
|
| 207 |
+
"rstrip": false,
|
| 208 |
+
"single_word": false,
|
| 209 |
+
"special": true
|
| 210 |
+
},
|
| 211 |
+
"128026": {
|
| 212 |
+
"content": "<|reserved_special_token_17|>",
|
| 213 |
+
"lstrip": false,
|
| 214 |
+
"normalized": false,
|
| 215 |
+
"rstrip": false,
|
| 216 |
+
"single_word": false,
|
| 217 |
+
"special": true
|
| 218 |
+
},
|
| 219 |
+
"128027": {
|
| 220 |
+
"content": "<|reserved_special_token_18|>",
|
| 221 |
+
"lstrip": false,
|
| 222 |
+
"normalized": false,
|
| 223 |
+
"rstrip": false,
|
| 224 |
+
"single_word": false,
|
| 225 |
+
"special": true
|
| 226 |
+
},
|
| 227 |
+
"128028": {
|
| 228 |
+
"content": "<|reserved_special_token_19|>",
|
| 229 |
+
"lstrip": false,
|
| 230 |
+
"normalized": false,
|
| 231 |
+
"rstrip": false,
|
| 232 |
+
"single_word": false,
|
| 233 |
+
"special": true
|
| 234 |
+
},
|
| 235 |
+
"128029": {
|
| 236 |
+
"content": "<|reserved_special_token_20|>",
|
| 237 |
+
"lstrip": false,
|
| 238 |
+
"normalized": false,
|
| 239 |
+
"rstrip": false,
|
| 240 |
+
"single_word": false,
|
| 241 |
+
"special": true
|
| 242 |
+
},
|
| 243 |
+
"128030": {
|
| 244 |
+
"content": "<|reserved_special_token_21|>",
|
| 245 |
+
"lstrip": false,
|
| 246 |
+
"normalized": false,
|
| 247 |
+
"rstrip": false,
|
| 248 |
+
"single_word": false,
|
| 249 |
+
"special": true
|
| 250 |
+
},
|
| 251 |
+
"128031": {
|
| 252 |
+
"content": "<|reserved_special_token_22|>",
|
| 253 |
+
"lstrip": false,
|
| 254 |
+
"normalized": false,
|
| 255 |
+
"rstrip": false,
|
| 256 |
+
"single_word": false,
|
| 257 |
+
"special": true
|
| 258 |
+
},
|
| 259 |
+
"128032": {
|
| 260 |
+
"content": "<|reserved_special_token_23|>",
|
| 261 |
+
"lstrip": false,
|
| 262 |
+
"normalized": false,
|
| 263 |
+
"rstrip": false,
|
| 264 |
+
"single_word": false,
|
| 265 |
+
"special": true
|
| 266 |
+
},
|
| 267 |
+
"128033": {
|
| 268 |
+
"content": "<|reserved_special_token_24|>",
|
| 269 |
+
"lstrip": false,
|
| 270 |
+
"normalized": false,
|
| 271 |
+
"rstrip": false,
|
| 272 |
+
"single_word": false,
|
| 273 |
+
"special": true
|
| 274 |
+
},
|
| 275 |
+
"128034": {
|
| 276 |
+
"content": "<|reserved_special_token_25|>",
|
| 277 |
+
"lstrip": false,
|
| 278 |
+
"normalized": false,
|
| 279 |
+
"rstrip": false,
|
| 280 |
+
"single_word": false,
|
| 281 |
+
"special": true
|
| 282 |
+
},
|
| 283 |
+
"128035": {
|
| 284 |
+
"content": "<|reserved_special_token_26|>",
|
| 285 |
+
"lstrip": false,
|
| 286 |
+
"normalized": false,
|
| 287 |
+
"rstrip": false,
|
| 288 |
+
"single_word": false,
|
| 289 |
+
"special": true
|
| 290 |
+
},
|
| 291 |
+
"128036": {
|
| 292 |
+
"content": "<|reserved_special_token_27|>",
|
| 293 |
+
"lstrip": false,
|
| 294 |
+
"normalized": false,
|
| 295 |
+
"rstrip": false,
|
| 296 |
+
"single_word": false,
|
| 297 |
+
"special": true
|
| 298 |
+
},
|
| 299 |
+
"128037": {
|
| 300 |
+
"content": "<|reserved_special_token_28|>",
|
| 301 |
+
"lstrip": false,
|
| 302 |
+
"normalized": false,
|
| 303 |
+
"rstrip": false,
|
| 304 |
+
"single_word": false,
|
| 305 |
+
"special": true
|
| 306 |
+
},
|
| 307 |
+
"128038": {
|
| 308 |
+
"content": "<|reserved_special_token_29|>",
|
| 309 |
+
"lstrip": false,
|
| 310 |
+
"normalized": false,
|
| 311 |
+
"rstrip": false,
|
| 312 |
+
"single_word": false,
|
| 313 |
+
"special": true
|
| 314 |
+
},
|
| 315 |
+
"128039": {
|
| 316 |
+
"content": "<|reserved_special_token_30|>",
|
| 317 |
+
"lstrip": false,
|
| 318 |
+
"normalized": false,
|
| 319 |
+
"rstrip": false,
|
| 320 |
+
"single_word": false,
|
| 321 |
+
"special": true
|
| 322 |
+
},
|
| 323 |
+
"128040": {
|
| 324 |
+
"content": "<|reserved_special_token_31|>",
|
| 325 |
+
"lstrip": false,
|
| 326 |
+
"normalized": false,
|
| 327 |
+
"rstrip": false,
|
| 328 |
+
"single_word": false,
|
| 329 |
+
"special": true
|
| 330 |
+
},
|
| 331 |
+
"128041": {
|
| 332 |
+
"content": "<|reserved_special_token_32|>",
|
| 333 |
+
"lstrip": false,
|
| 334 |
+
"normalized": false,
|
| 335 |
+
"rstrip": false,
|
| 336 |
+
"single_word": false,
|
| 337 |
+
"special": true
|
| 338 |
+
},
|
| 339 |
+
"128042": {
|
| 340 |
+
"content": "<|reserved_special_token_33|>",
|
| 341 |
+
"lstrip": false,
|
| 342 |
+
"normalized": false,
|
| 343 |
+
"rstrip": false,
|
| 344 |
+
"single_word": false,
|
| 345 |
+
"special": true
|
| 346 |
+
},
|
| 347 |
+
"128043": {
|
| 348 |
+
"content": "<|reserved_special_token_34|>",
|
| 349 |
+
"lstrip": false,
|
| 350 |
+
"normalized": false,
|
| 351 |
+
"rstrip": false,
|
| 352 |
+
"single_word": false,
|
| 353 |
+
"special": true
|
| 354 |
+
},
|
| 355 |
+
"128044": {
|
| 356 |
+
"content": "<|reserved_special_token_35|>",
|
| 357 |
+
"lstrip": false,
|
| 358 |
+
"normalized": false,
|
| 359 |
+
"rstrip": false,
|
| 360 |
+
"single_word": false,
|
| 361 |
+
"special": true
|
| 362 |
+
},
|
| 363 |
+
"128045": {
|
| 364 |
+
"content": "<|reserved_special_token_36|>",
|
| 365 |
+
"lstrip": false,
|
| 366 |
+
"normalized": false,
|
| 367 |
+
"rstrip": false,
|
| 368 |
+
"single_word": false,
|
| 369 |
+
"special": true
|
| 370 |
+
},
|
| 371 |
+
"128046": {
|
| 372 |
+
"content": "<|reserved_special_token_37|>",
|
| 373 |
+
"lstrip": false,
|
| 374 |
+
"normalized": false,
|
| 375 |
+
"rstrip": false,
|
| 376 |
+
"single_word": false,
|
| 377 |
+
"special": true
|
| 378 |
+
},
|
| 379 |
+
"128047": {
|
| 380 |
+
"content": "<|reserved_special_token_38|>",
|
| 381 |
+
"lstrip": false,
|
| 382 |
+
"normalized": false,
|
| 383 |
+
"rstrip": false,
|
| 384 |
+
"single_word": false,
|
| 385 |
+
"special": true
|
| 386 |
+
},
|
| 387 |
+
"128048": {
|
| 388 |
+
"content": "<|reserved_special_token_39|>",
|
| 389 |
+
"lstrip": false,
|
| 390 |
+
"normalized": false,
|
| 391 |
+
"rstrip": false,
|
| 392 |
+
"single_word": false,
|
| 393 |
+
"special": true
|
| 394 |
+
},
|
| 395 |
+
"128049": {
|
| 396 |
+
"content": "<|reserved_special_token_40|>",
|
| 397 |
+
"lstrip": false,
|
| 398 |
+
"normalized": false,
|
| 399 |
+
"rstrip": false,
|
| 400 |
+
"single_word": false,
|
| 401 |
+
"special": true
|
| 402 |
+
},
|
| 403 |
+
"128050": {
|
| 404 |
+
"content": "<|reserved_special_token_41|>",
|
| 405 |
+
"lstrip": false,
|
| 406 |
+
"normalized": false,
|
| 407 |
+
"rstrip": false,
|
| 408 |
+
"single_word": false,
|
| 409 |
+
"special": true
|
| 410 |
+
},
|
| 411 |
+
"128051": {
|
| 412 |
+
"content": "<|reserved_special_token_42|>",
|
| 413 |
+
"lstrip": false,
|
| 414 |
+
"normalized": false,
|
| 415 |
+
"rstrip": false,
|
| 416 |
+
"single_word": false,
|
| 417 |
+
"special": true
|
| 418 |
+
},
|
| 419 |
+
"128052": {
|
| 420 |
+
"content": "<|reserved_special_token_43|>",
|
| 421 |
+
"lstrip": false,
|
| 422 |
+
"normalized": false,
|
| 423 |
+
"rstrip": false,
|
| 424 |
+
"single_word": false,
|
| 425 |
+
"special": true
|
| 426 |
+
},
|
| 427 |
+
"128053": {
|
| 428 |
+
"content": "<|reserved_special_token_44|>",
|
| 429 |
+
"lstrip": false,
|
| 430 |
+
"normalized": false,
|
| 431 |
+
"rstrip": false,
|
| 432 |
+
"single_word": false,
|
| 433 |
+
"special": true
|
| 434 |
+
},
|
| 435 |
+
"128054": {
|
| 436 |
+
"content": "<|reserved_special_token_45|>",
|
| 437 |
+
"lstrip": false,
|
| 438 |
+
"normalized": false,
|
| 439 |
+
"rstrip": false,
|
| 440 |
+
"single_word": false,
|
| 441 |
+
"special": true
|
| 442 |
+
},
|
| 443 |
+
"128055": {
|
| 444 |
+
"content": "<|reserved_special_token_46|>",
|
| 445 |
+
"lstrip": false,
|
| 446 |
+
"normalized": false,
|
| 447 |
+
"rstrip": false,
|
| 448 |
+
"single_word": false,
|
| 449 |
+
"special": true
|
| 450 |
+
},
|
| 451 |
+
"128056": {
|
| 452 |
+
"content": "<|reserved_special_token_47|>",
|
| 453 |
+
"lstrip": false,
|
| 454 |
+
"normalized": false,
|
| 455 |
+
"rstrip": false,
|
| 456 |
+
"single_word": false,
|
| 457 |
+
"special": true
|
| 458 |
+
},
|
| 459 |
+
"128057": {
|
| 460 |
+
"content": "<|reserved_special_token_48|>",
|
| 461 |
+
"lstrip": false,
|
| 462 |
+
"normalized": false,
|
| 463 |
+
"rstrip": false,
|
| 464 |
+
"single_word": false,
|
| 465 |
+
"special": true
|
| 466 |
+
},
|
| 467 |
+
"128058": {
|
| 468 |
+
"content": "<|reserved_special_token_49|>",
|
| 469 |
+
"lstrip": false,
|
| 470 |
+
"normalized": false,
|
| 471 |
+
"rstrip": false,
|
| 472 |
+
"single_word": false,
|
| 473 |
+
"special": true
|
| 474 |
+
},
|
| 475 |
+
"128059": {
|
| 476 |
+
"content": "<|reserved_special_token_50|>",
|
| 477 |
+
"lstrip": false,
|
| 478 |
+
"normalized": false,
|
| 479 |
+
"rstrip": false,
|
| 480 |
+
"single_word": false,
|
| 481 |
+
"special": true
|
| 482 |
+
},
|
| 483 |
+
"128060": {
|
| 484 |
+
"content": "<|reserved_special_token_51|>",
|
| 485 |
+
"lstrip": false,
|
| 486 |
+
"normalized": false,
|
| 487 |
+
"rstrip": false,
|
| 488 |
+
"single_word": false,
|
| 489 |
+
"special": true
|
| 490 |
+
},
|
| 491 |
+
"128061": {
|
| 492 |
+
"content": "<|reserved_special_token_52|>",
|
| 493 |
+
"lstrip": false,
|
| 494 |
+
"normalized": false,
|
| 495 |
+
"rstrip": false,
|
| 496 |
+
"single_word": false,
|
| 497 |
+
"special": true
|
| 498 |
+
},
|
| 499 |
+
"128062": {
|
| 500 |
+
"content": "<|reserved_special_token_53|>",
|
| 501 |
+
"lstrip": false,
|
| 502 |
+
"normalized": false,
|
| 503 |
+
"rstrip": false,
|
| 504 |
+
"single_word": false,
|
| 505 |
+
"special": true
|
| 506 |
+
},
|
| 507 |
+
"128063": {
|
| 508 |
+
"content": "<|reserved_special_token_54|>",
|
| 509 |
+
"lstrip": false,
|
| 510 |
+
"normalized": false,
|
| 511 |
+
"rstrip": false,
|
| 512 |
+
"single_word": false,
|
| 513 |
+
"special": true
|
| 514 |
+
},
|
| 515 |
+
"128064": {
|
| 516 |
+
"content": "<|reserved_special_token_55|>",
|
| 517 |
+
"lstrip": false,
|
| 518 |
+
"normalized": false,
|
| 519 |
+
"rstrip": false,
|
| 520 |
+
"single_word": false,
|
| 521 |
+
"special": true
|
| 522 |
+
},
|
| 523 |
+
"128065": {
|
| 524 |
+
"content": "<|reserved_special_token_56|>",
|
| 525 |
+
"lstrip": false,
|
| 526 |
+
"normalized": false,
|
| 527 |
+
"rstrip": false,
|
| 528 |
+
"single_word": false,
|
| 529 |
+
"special": true
|
| 530 |
+
},
|
| 531 |
+
"128066": {
|
| 532 |
+
"content": "<|reserved_special_token_57|>",
|
| 533 |
+
"lstrip": false,
|
| 534 |
+
"normalized": false,
|
| 535 |
+
"rstrip": false,
|
| 536 |
+
"single_word": false,
|
| 537 |
+
"special": true
|
| 538 |
+
},
|
| 539 |
+
"128067": {
|
| 540 |
+
"content": "<|reserved_special_token_58|>",
|
| 541 |
+
"lstrip": false,
|
| 542 |
+
"normalized": false,
|
| 543 |
+
"rstrip": false,
|
| 544 |
+
"single_word": false,
|
| 545 |
+
"special": true
|
| 546 |
+
},
|
| 547 |
+
"128068": {
|
| 548 |
+
"content": "<|reserved_special_token_59|>",
|
| 549 |
+
"lstrip": false,
|
| 550 |
+
"normalized": false,
|
| 551 |
+
"rstrip": false,
|
| 552 |
+
"single_word": false,
|
| 553 |
+
"special": true
|
| 554 |
+
},
|
| 555 |
+
"128069": {
|
| 556 |
+
"content": "<|reserved_special_token_60|>",
|
| 557 |
+
"lstrip": false,
|
| 558 |
+
"normalized": false,
|
| 559 |
+
"rstrip": false,
|
| 560 |
+
"single_word": false,
|
| 561 |
+
"special": true
|
| 562 |
+
},
|
| 563 |
+
"128070": {
|
| 564 |
+
"content": "<|reserved_special_token_61|>",
|
| 565 |
+
"lstrip": false,
|
| 566 |
+
"normalized": false,
|
| 567 |
+
"rstrip": false,
|
| 568 |
+
"single_word": false,
|
| 569 |
+
"special": true
|
| 570 |
+
},
|
| 571 |
+
"128071": {
|
| 572 |
+
"content": "<|reserved_special_token_62|>",
|
| 573 |
+
"lstrip": false,
|
| 574 |
+
"normalized": false,
|
| 575 |
+
"rstrip": false,
|
| 576 |
+
"single_word": false,
|
| 577 |
+
"special": true
|
| 578 |
+
},
|
| 579 |
+
"128072": {
|
| 580 |
+
"content": "<|reserved_special_token_63|>",
|
| 581 |
+
"lstrip": false,
|
| 582 |
+
"normalized": false,
|
| 583 |
+
"rstrip": false,
|
| 584 |
+
"single_word": false,
|
| 585 |
+
"special": true
|
| 586 |
+
},
|
| 587 |
+
"128073": {
|
| 588 |
+
"content": "<|reserved_special_token_64|>",
|
| 589 |
+
"lstrip": false,
|
| 590 |
+
"normalized": false,
|
| 591 |
+
"rstrip": false,
|
| 592 |
+
"single_word": false,
|
| 593 |
+
"special": true
|
| 594 |
+
},
|
| 595 |
+
"128074": {
|
| 596 |
+
"content": "<|reserved_special_token_65|>",
|
| 597 |
+
"lstrip": false,
|
| 598 |
+
"normalized": false,
|
| 599 |
+
"rstrip": false,
|
| 600 |
+
"single_word": false,
|
| 601 |
+
"special": true
|
| 602 |
+
},
|
| 603 |
+
"128075": {
|
| 604 |
+
"content": "<|reserved_special_token_66|>",
|
| 605 |
+
"lstrip": false,
|
| 606 |
+
"normalized": false,
|
| 607 |
+
"rstrip": false,
|
| 608 |
+
"single_word": false,
|
| 609 |
+
"special": true
|
| 610 |
+
},
|
| 611 |
+
"128076": {
|
| 612 |
+
"content": "<|reserved_special_token_67|>",
|
| 613 |
+
"lstrip": false,
|
| 614 |
+
"normalized": false,
|
| 615 |
+
"rstrip": false,
|
| 616 |
+
"single_word": false,
|
| 617 |
+
"special": true
|
| 618 |
+
},
|
| 619 |
+
"128077": {
|
| 620 |
+
"content": "<|reserved_special_token_68|>",
|
| 621 |
+
"lstrip": false,
|
| 622 |
+
"normalized": false,
|
| 623 |
+
"rstrip": false,
|
| 624 |
+
"single_word": false,
|
| 625 |
+
"special": true
|
| 626 |
+
},
|
| 627 |
+
"128078": {
|
| 628 |
+
"content": "<|reserved_special_token_69|>",
|
| 629 |
+
"lstrip": false,
|
| 630 |
+
"normalized": false,
|
| 631 |
+
"rstrip": false,
|
| 632 |
+
"single_word": false,
|
| 633 |
+
"special": true
|
| 634 |
+
},
|
| 635 |
+
"128079": {
|
| 636 |
+
"content": "<|reserved_special_token_70|>",
|
| 637 |
+
"lstrip": false,
|
| 638 |
+
"normalized": false,
|
| 639 |
+
"rstrip": false,
|
| 640 |
+
"single_word": false,
|
| 641 |
+
"special": true
|
| 642 |
+
},
|
| 643 |
+
"128080": {
|
| 644 |
+
"content": "<|reserved_special_token_71|>",
|
| 645 |
+
"lstrip": false,
|
| 646 |
+
"normalized": false,
|
| 647 |
+
"rstrip": false,
|
| 648 |
+
"single_word": false,
|
| 649 |
+
"special": true
|
| 650 |
+
},
|
| 651 |
+
"128081": {
|
| 652 |
+
"content": "<|reserved_special_token_72|>",
|
| 653 |
+
"lstrip": false,
|
| 654 |
+
"normalized": false,
|
| 655 |
+
"rstrip": false,
|
| 656 |
+
"single_word": false,
|
| 657 |
+
"special": true
|
| 658 |
+
},
|
| 659 |
+
"128082": {
|
| 660 |
+
"content": "<|reserved_special_token_73|>",
|
| 661 |
+
"lstrip": false,
|
| 662 |
+
"normalized": false,
|
| 663 |
+
"rstrip": false,
|
| 664 |
+
"single_word": false,
|
| 665 |
+
"special": true
|
| 666 |
+
},
|
| 667 |
+
"128083": {
|
| 668 |
+
"content": "<|reserved_special_token_74|>",
|
| 669 |
+
"lstrip": false,
|
| 670 |
+
"normalized": false,
|
| 671 |
+
"rstrip": false,
|
| 672 |
+
"single_word": false,
|
| 673 |
+
"special": true
|
| 674 |
+
},
|
| 675 |
+
"128084": {
|
| 676 |
+
"content": "<|reserved_special_token_75|>",
|
| 677 |
+
"lstrip": false,
|
| 678 |
+
"normalized": false,
|
| 679 |
+
"rstrip": false,
|
| 680 |
+
"single_word": false,
|
| 681 |
+
"special": true
|
| 682 |
+
},
|
| 683 |
+
"128085": {
|
| 684 |
+
"content": "<|reserved_special_token_76|>",
|
| 685 |
+
"lstrip": false,
|
| 686 |
+
"normalized": false,
|
| 687 |
+
"rstrip": false,
|
| 688 |
+
"single_word": false,
|
| 689 |
+
"special": true
|
| 690 |
+
},
|
| 691 |
+
"128086": {
|
| 692 |
+
"content": "<|reserved_special_token_77|>",
|
| 693 |
+
"lstrip": false,
|
| 694 |
+
"normalized": false,
|
| 695 |
+
"rstrip": false,
|
| 696 |
+
"single_word": false,
|
| 697 |
+
"special": true
|
| 698 |
+
},
|
| 699 |
+
"128087": {
|
| 700 |
+
"content": "<|reserved_special_token_78|>",
|
| 701 |
+
"lstrip": false,
|
| 702 |
+
"normalized": false,
|
| 703 |
+
"rstrip": false,
|
| 704 |
+
"single_word": false,
|
| 705 |
+
"special": true
|
| 706 |
+
},
|
| 707 |
+
"128088": {
|
| 708 |
+
"content": "<|reserved_special_token_79|>",
|
| 709 |
+
"lstrip": false,
|
| 710 |
+
"normalized": false,
|
| 711 |
+
"rstrip": false,
|
| 712 |
+
"single_word": false,
|
| 713 |
+
"special": true
|
| 714 |
+
},
|
| 715 |
+
"128089": {
|
| 716 |
+
"content": "<|reserved_special_token_80|>",
|
| 717 |
+
"lstrip": false,
|
| 718 |
+
"normalized": false,
|
| 719 |
+
"rstrip": false,
|
| 720 |
+
"single_word": false,
|
| 721 |
+
"special": true
|
| 722 |
+
},
|
| 723 |
+
"128090": {
|
| 724 |
+
"content": "<|reserved_special_token_81|>",
|
| 725 |
+
"lstrip": false,
|
| 726 |
+
"normalized": false,
|
| 727 |
+
"rstrip": false,
|
| 728 |
+
"single_word": false,
|
| 729 |
+
"special": true
|
| 730 |
+
},
|
| 731 |
+
"128091": {
|
| 732 |
+
"content": "<|reserved_special_token_82|>",
|
| 733 |
+
"lstrip": false,
|
| 734 |
+
"normalized": false,
|
| 735 |
+
"rstrip": false,
|
| 736 |
+
"single_word": false,
|
| 737 |
+
"special": true
|
| 738 |
+
},
|
| 739 |
+
"128092": {
|
| 740 |
+
"content": "<|reserved_special_token_83|>",
|
| 741 |
+
"lstrip": false,
|
| 742 |
+
"normalized": false,
|
| 743 |
+
"rstrip": false,
|
| 744 |
+
"single_word": false,
|
| 745 |
+
"special": true
|
| 746 |
+
},
|
| 747 |
+
"128093": {
|
| 748 |
+
"content": "<|reserved_special_token_84|>",
|
| 749 |
+
"lstrip": false,
|
| 750 |
+
"normalized": false,
|
| 751 |
+
"rstrip": false,
|
| 752 |
+
"single_word": false,
|
| 753 |
+
"special": true
|
| 754 |
+
},
|
| 755 |
+
"128094": {
|
| 756 |
+
"content": "<|reserved_special_token_85|>",
|
| 757 |
+
"lstrip": false,
|
| 758 |
+
"normalized": false,
|
| 759 |
+
"rstrip": false,
|
| 760 |
+
"single_word": false,
|
| 761 |
+
"special": true
|
| 762 |
+
},
|
| 763 |
+
"128095": {
|
| 764 |
+
"content": "<|reserved_special_token_86|>",
|
| 765 |
+
"lstrip": false,
|
| 766 |
+
"normalized": false,
|
| 767 |
+
"rstrip": false,
|
| 768 |
+
"single_word": false,
|
| 769 |
+
"special": true
|
| 770 |
+
},
|
| 771 |
+
"128096": {
|
| 772 |
+
"content": "<|reserved_special_token_87|>",
|
| 773 |
+
"lstrip": false,
|
| 774 |
+
"normalized": false,
|
| 775 |
+
"rstrip": false,
|
| 776 |
+
"single_word": false,
|
| 777 |
+
"special": true
|
| 778 |
+
},
|
| 779 |
+
"128097": {
|
| 780 |
+
"content": "<|reserved_special_token_88|>",
|
| 781 |
+
"lstrip": false,
|
| 782 |
+
"normalized": false,
|
| 783 |
+
"rstrip": false,
|
| 784 |
+
"single_word": false,
|
| 785 |
+
"special": true
|
| 786 |
+
},
|
| 787 |
+
"128098": {
|
| 788 |
+
"content": "<|reserved_special_token_89|>",
|
| 789 |
+
"lstrip": false,
|
| 790 |
+
"normalized": false,
|
| 791 |
+
"rstrip": false,
|
| 792 |
+
"single_word": false,
|
| 793 |
+
"special": true
|
| 794 |
+
},
|
| 795 |
+
"128099": {
|
| 796 |
+
"content": "<|reserved_special_token_90|>",
|
| 797 |
+
"lstrip": false,
|
| 798 |
+
"normalized": false,
|
| 799 |
+
"rstrip": false,
|
| 800 |
+
"single_word": false,
|
| 801 |
+
"special": true
|
| 802 |
+
},
|
| 803 |
+
"128100": {
|
| 804 |
+
"content": "<|reserved_special_token_91|>",
|
| 805 |
+
"lstrip": false,
|
| 806 |
+
"normalized": false,
|
| 807 |
+
"rstrip": false,
|
| 808 |
+
"single_word": false,
|
| 809 |
+
"special": true
|
| 810 |
+
},
|
| 811 |
+
"128101": {
|
| 812 |
+
"content": "<|reserved_special_token_92|>",
|
| 813 |
+
"lstrip": false,
|
| 814 |
+
"normalized": false,
|
| 815 |
+
"rstrip": false,
|
| 816 |
+
"single_word": false,
|
| 817 |
+
"special": true
|
| 818 |
+
},
|
| 819 |
+
"128102": {
|
| 820 |
+
"content": "<|reserved_special_token_93|>",
|
| 821 |
+
"lstrip": false,
|
| 822 |
+
"normalized": false,
|
| 823 |
+
"rstrip": false,
|
| 824 |
+
"single_word": false,
|
| 825 |
+
"special": true
|
| 826 |
+
},
|
| 827 |
+
"128103": {
|
| 828 |
+
"content": "<|reserved_special_token_94|>",
|
| 829 |
+
"lstrip": false,
|
| 830 |
+
"normalized": false,
|
| 831 |
+
"rstrip": false,
|
| 832 |
+
"single_word": false,
|
| 833 |
+
"special": true
|
| 834 |
+
},
|
| 835 |
+
"128104": {
|
| 836 |
+
"content": "<|reserved_special_token_95|>",
|
| 837 |
+
"lstrip": false,
|
| 838 |
+
"normalized": false,
|
| 839 |
+
"rstrip": false,
|
| 840 |
+
"single_word": false,
|
| 841 |
+
"special": true
|
| 842 |
+
},
|
| 843 |
+
"128105": {
|
| 844 |
+
"content": "<|reserved_special_token_96|>",
|
| 845 |
+
"lstrip": false,
|
| 846 |
+
"normalized": false,
|
| 847 |
+
"rstrip": false,
|
| 848 |
+
"single_word": false,
|
| 849 |
+
"special": true
|
| 850 |
+
},
|
| 851 |
+
"128106": {
|
| 852 |
+
"content": "<|reserved_special_token_97|>",
|
| 853 |
+
"lstrip": false,
|
| 854 |
+
"normalized": false,
|
| 855 |
+
"rstrip": false,
|
| 856 |
+
"single_word": false,
|
| 857 |
+
"special": true
|
| 858 |
+
},
|
| 859 |
+
"128107": {
|
| 860 |
+
"content": "<|reserved_special_token_98|>",
|
| 861 |
+
"lstrip": false,
|
| 862 |
+
"normalized": false,
|
| 863 |
+
"rstrip": false,
|
| 864 |
+
"single_word": false,
|
| 865 |
+
"special": true
|
| 866 |
+
},
|
| 867 |
+
"128108": {
|
| 868 |
+
"content": "<|reserved_special_token_99|>",
|
| 869 |
+
"lstrip": false,
|
| 870 |
+
"normalized": false,
|
| 871 |
+
"rstrip": false,
|
| 872 |
+
"single_word": false,
|
| 873 |
+
"special": true
|
| 874 |
+
},
|
| 875 |
+
"128109": {
|
| 876 |
+
"content": "<|reserved_special_token_100|>",
|
| 877 |
+
"lstrip": false,
|
| 878 |
+
"normalized": false,
|
| 879 |
+
"rstrip": false,
|
| 880 |
+
"single_word": false,
|
| 881 |
+
"special": true
|
| 882 |
+
},
|
| 883 |
+
"128110": {
|
| 884 |
+
"content": "<|reserved_special_token_101|>",
|
| 885 |
+
"lstrip": false,
|
| 886 |
+
"normalized": false,
|
| 887 |
+
"rstrip": false,
|
| 888 |
+
"single_word": false,
|
| 889 |
+
"special": true
|
| 890 |
+
},
|
| 891 |
+
"128111": {
|
| 892 |
+
"content": "<|reserved_special_token_102|>",
|
| 893 |
+
"lstrip": false,
|
| 894 |
+
"normalized": false,
|
| 895 |
+
"rstrip": false,
|
| 896 |
+
"single_word": false,
|
| 897 |
+
"special": true
|
| 898 |
+
},
|
| 899 |
+
"128112": {
|
| 900 |
+
"content": "<|reserved_special_token_103|>",
|
| 901 |
+
"lstrip": false,
|
| 902 |
+
"normalized": false,
|
| 903 |
+
"rstrip": false,
|
| 904 |
+
"single_word": false,
|
| 905 |
+
"special": true
|
| 906 |
+
},
|
| 907 |
+
"128113": {
|
| 908 |
+
"content": "<|reserved_special_token_104|>",
|
| 909 |
+
"lstrip": false,
|
| 910 |
+
"normalized": false,
|
| 911 |
+
"rstrip": false,
|
| 912 |
+
"single_word": false,
|
| 913 |
+
"special": true
|
| 914 |
+
},
|
| 915 |
+
"128114": {
|
| 916 |
+
"content": "<|reserved_special_token_105|>",
|
| 917 |
+
"lstrip": false,
|
| 918 |
+
"normalized": false,
|
| 919 |
+
"rstrip": false,
|
| 920 |
+
"single_word": false,
|
| 921 |
+
"special": true
|
| 922 |
+
},
|
| 923 |
+
"128115": {
|
| 924 |
+
"content": "<|reserved_special_token_106|>",
|
| 925 |
+
"lstrip": false,
|
| 926 |
+
"normalized": false,
|
| 927 |
+
"rstrip": false,
|
| 928 |
+
"single_word": false,
|
| 929 |
+
"special": true
|
| 930 |
+
},
|
| 931 |
+
"128116": {
|
| 932 |
+
"content": "<|reserved_special_token_107|>",
|
| 933 |
+
"lstrip": false,
|
| 934 |
+
"normalized": false,
|
| 935 |
+
"rstrip": false,
|
| 936 |
+
"single_word": false,
|
| 937 |
+
"special": true
|
| 938 |
+
},
|
| 939 |
+
"128117": {
|
| 940 |
+
"content": "<|reserved_special_token_108|>",
|
| 941 |
+
"lstrip": false,
|
| 942 |
+
"normalized": false,
|
| 943 |
+
"rstrip": false,
|
| 944 |
+
"single_word": false,
|
| 945 |
+
"special": true
|
| 946 |
+
},
|
| 947 |
+
"128118": {
|
| 948 |
+
"content": "<|reserved_special_token_109|>",
|
| 949 |
+
"lstrip": false,
|
| 950 |
+
"normalized": false,
|
| 951 |
+
"rstrip": false,
|
| 952 |
+
"single_word": false,
|
| 953 |
+
"special": true
|
| 954 |
+
},
|
| 955 |
+
"128119": {
|
| 956 |
+
"content": "<|reserved_special_token_110|>",
|
| 957 |
+
"lstrip": false,
|
| 958 |
+
"normalized": false,
|
| 959 |
+
"rstrip": false,
|
| 960 |
+
"single_word": false,
|
| 961 |
+
"special": true
|
| 962 |
+
},
|
| 963 |
+
"128120": {
|
| 964 |
+
"content": "<|reserved_special_token_111|>",
|
| 965 |
+
"lstrip": false,
|
| 966 |
+
"normalized": false,
|
| 967 |
+
"rstrip": false,
|
| 968 |
+
"single_word": false,
|
| 969 |
+
"special": true
|
| 970 |
+
},
|
| 971 |
+
"128121": {
|
| 972 |
+
"content": "<|reserved_special_token_112|>",
|
| 973 |
+
"lstrip": false,
|
| 974 |
+
"normalized": false,
|
| 975 |
+
"rstrip": false,
|
| 976 |
+
"single_word": false,
|
| 977 |
+
"special": true
|
| 978 |
+
},
|
| 979 |
+
"128122": {
|
| 980 |
+
"content": "<|reserved_special_token_113|>",
|
| 981 |
+
"lstrip": false,
|
| 982 |
+
"normalized": false,
|
| 983 |
+
"rstrip": false,
|
| 984 |
+
"single_word": false,
|
| 985 |
+
"special": true
|
| 986 |
+
},
|
| 987 |
+
"128123": {
|
| 988 |
+
"content": "<|reserved_special_token_114|>",
|
| 989 |
+
"lstrip": false,
|
| 990 |
+
"normalized": false,
|
| 991 |
+
"rstrip": false,
|
| 992 |
+
"single_word": false,
|
| 993 |
+
"special": true
|
| 994 |
+
},
|
| 995 |
+
"128124": {
|
| 996 |
+
"content": "<|reserved_special_token_115|>",
|
| 997 |
+
"lstrip": false,
|
| 998 |
+
"normalized": false,
|
| 999 |
+
"rstrip": false,
|
| 1000 |
+
"single_word": false,
|
| 1001 |
+
"special": true
|
| 1002 |
+
},
|
| 1003 |
+
"128125": {
|
| 1004 |
+
"content": "<|reserved_special_token_116|>",
|
| 1005 |
+
"lstrip": false,
|
| 1006 |
+
"normalized": false,
|
| 1007 |
+
"rstrip": false,
|
| 1008 |
+
"single_word": false,
|
| 1009 |
+
"special": true
|
| 1010 |
+
},
|
| 1011 |
+
"128126": {
|
| 1012 |
+
"content": "<|reserved_special_token_117|>",
|
| 1013 |
+
"lstrip": false,
|
| 1014 |
+
"normalized": false,
|
| 1015 |
+
"rstrip": false,
|
| 1016 |
+
"single_word": false,
|
| 1017 |
+
"special": true
|
| 1018 |
+
},
|
| 1019 |
+
"128127": {
|
| 1020 |
+
"content": "<|reserved_special_token_118|>",
|
| 1021 |
+
"lstrip": false,
|
| 1022 |
+
"normalized": false,
|
| 1023 |
+
"rstrip": false,
|
| 1024 |
+
"single_word": false,
|
| 1025 |
+
"special": true
|
| 1026 |
+
},
|
| 1027 |
+
"128128": {
|
| 1028 |
+
"content": "<|reserved_special_token_119|>",
|
| 1029 |
+
"lstrip": false,
|
| 1030 |
+
"normalized": false,
|
| 1031 |
+
"rstrip": false,
|
| 1032 |
+
"single_word": false,
|
| 1033 |
+
"special": true
|
| 1034 |
+
},
|
| 1035 |
+
"128129": {
|
| 1036 |
+
"content": "<|reserved_special_token_120|>",
|
| 1037 |
+
"lstrip": false,
|
| 1038 |
+
"normalized": false,
|
| 1039 |
+
"rstrip": false,
|
| 1040 |
+
"single_word": false,
|
| 1041 |
+
"special": true
|
| 1042 |
+
},
|
| 1043 |
+
"128130": {
|
| 1044 |
+
"content": "<|reserved_special_token_121|>",
|
| 1045 |
+
"lstrip": false,
|
| 1046 |
+
"normalized": false,
|
| 1047 |
+
"rstrip": false,
|
| 1048 |
+
"single_word": false,
|
| 1049 |
+
"special": true
|
| 1050 |
+
},
|
| 1051 |
+
"128131": {
|
| 1052 |
+
"content": "<|reserved_special_token_122|>",
|
| 1053 |
+
"lstrip": false,
|
| 1054 |
+
"normalized": false,
|
| 1055 |
+
"rstrip": false,
|
| 1056 |
+
"single_word": false,
|
| 1057 |
+
"special": true
|
| 1058 |
+
},
|
| 1059 |
+
"128132": {
|
| 1060 |
+
"content": "<|reserved_special_token_123|>",
|
| 1061 |
+
"lstrip": false,
|
| 1062 |
+
"normalized": false,
|
| 1063 |
+
"rstrip": false,
|
| 1064 |
+
"single_word": false,
|
| 1065 |
+
"special": true
|
| 1066 |
+
},
|
| 1067 |
+
"128133": {
|
| 1068 |
+
"content": "<|reserved_special_token_124|>",
|
| 1069 |
+
"lstrip": false,
|
| 1070 |
+
"normalized": false,
|
| 1071 |
+
"rstrip": false,
|
| 1072 |
+
"single_word": false,
|
| 1073 |
+
"special": true
|
| 1074 |
+
},
|
| 1075 |
+
"128134": {
|
| 1076 |
+
"content": "<|reserved_special_token_125|>",
|
| 1077 |
+
"lstrip": false,
|
| 1078 |
+
"normalized": false,
|
| 1079 |
+
"rstrip": false,
|
| 1080 |
+
"single_word": false,
|
| 1081 |
+
"special": true
|
| 1082 |
+
},
|
| 1083 |
+
"128135": {
|
| 1084 |
+
"content": "<|reserved_special_token_126|>",
|
| 1085 |
+
"lstrip": false,
|
| 1086 |
+
"normalized": false,
|
| 1087 |
+
"rstrip": false,
|
| 1088 |
+
"single_word": false,
|
| 1089 |
+
"special": true
|
| 1090 |
+
},
|
| 1091 |
+
"128136": {
|
| 1092 |
+
"content": "<|reserved_special_token_127|>",
|
| 1093 |
+
"lstrip": false,
|
| 1094 |
+
"normalized": false,
|
| 1095 |
+
"rstrip": false,
|
| 1096 |
+
"single_word": false,
|
| 1097 |
+
"special": true
|
| 1098 |
+
},
|
| 1099 |
+
"128137": {
|
| 1100 |
+
"content": "<|reserved_special_token_128|>",
|
| 1101 |
+
"lstrip": false,
|
| 1102 |
+
"normalized": false,
|
| 1103 |
+
"rstrip": false,
|
| 1104 |
+
"single_word": false,
|
| 1105 |
+
"special": true
|
| 1106 |
+
},
|
| 1107 |
+
"128138": {
|
| 1108 |
+
"content": "<|reserved_special_token_129|>",
|
| 1109 |
+
"lstrip": false,
|
| 1110 |
+
"normalized": false,
|
| 1111 |
+
"rstrip": false,
|
| 1112 |
+
"single_word": false,
|
| 1113 |
+
"special": true
|
| 1114 |
+
},
|
| 1115 |
+
"128139": {
|
| 1116 |
+
"content": "<|reserved_special_token_130|>",
|
| 1117 |
+
"lstrip": false,
|
| 1118 |
+
"normalized": false,
|
| 1119 |
+
"rstrip": false,
|
| 1120 |
+
"single_word": false,
|
| 1121 |
+
"special": true
|
| 1122 |
+
},
|
| 1123 |
+
"128140": {
|
| 1124 |
+
"content": "<|reserved_special_token_131|>",
|
| 1125 |
+
"lstrip": false,
|
| 1126 |
+
"normalized": false,
|
| 1127 |
+
"rstrip": false,
|
| 1128 |
+
"single_word": false,
|
| 1129 |
+
"special": true
|
| 1130 |
+
},
|
| 1131 |
+
"128141": {
|
| 1132 |
+
"content": "<|reserved_special_token_132|>",
|
| 1133 |
+
"lstrip": false,
|
| 1134 |
+
"normalized": false,
|
| 1135 |
+
"rstrip": false,
|
| 1136 |
+
"single_word": false,
|
| 1137 |
+
"special": true
|
| 1138 |
+
},
|
| 1139 |
+
"128142": {
|
| 1140 |
+
"content": "<|reserved_special_token_133|>",
|
| 1141 |
+
"lstrip": false,
|
| 1142 |
+
"normalized": false,
|
| 1143 |
+
"rstrip": false,
|
| 1144 |
+
"single_word": false,
|
| 1145 |
+
"special": true
|
| 1146 |
+
},
|
| 1147 |
+
"128143": {
|
| 1148 |
+
"content": "<|reserved_special_token_134|>",
|
| 1149 |
+
"lstrip": false,
|
| 1150 |
+
"normalized": false,
|
| 1151 |
+
"rstrip": false,
|
| 1152 |
+
"single_word": false,
|
| 1153 |
+
"special": true
|
| 1154 |
+
},
|
| 1155 |
+
"128144": {
|
| 1156 |
+
"content": "<|reserved_special_token_135|>",
|
| 1157 |
+
"lstrip": false,
|
| 1158 |
+
"normalized": false,
|
| 1159 |
+
"rstrip": false,
|
| 1160 |
+
"single_word": false,
|
| 1161 |
+
"special": true
|
| 1162 |
+
},
|
| 1163 |
+
"128145": {
|
| 1164 |
+
"content": "<|reserved_special_token_136|>",
|
| 1165 |
+
"lstrip": false,
|
| 1166 |
+
"normalized": false,
|
| 1167 |
+
"rstrip": false,
|
| 1168 |
+
"single_word": false,
|
| 1169 |
+
"special": true
|
| 1170 |
+
},
|
| 1171 |
+
"128146": {
|
| 1172 |
+
"content": "<|reserved_special_token_137|>",
|
| 1173 |
+
"lstrip": false,
|
| 1174 |
+
"normalized": false,
|
| 1175 |
+
"rstrip": false,
|
| 1176 |
+
"single_word": false,
|
| 1177 |
+
"special": true
|
| 1178 |
+
},
|
| 1179 |
+
"128147": {
|
| 1180 |
+
"content": "<|reserved_special_token_138|>",
|
| 1181 |
+
"lstrip": false,
|
| 1182 |
+
"normalized": false,
|
| 1183 |
+
"rstrip": false,
|
| 1184 |
+
"single_word": false,
|
| 1185 |
+
"special": true
|
| 1186 |
+
},
|
| 1187 |
+
"128148": {
|
| 1188 |
+
"content": "<|reserved_special_token_139|>",
|
| 1189 |
+
"lstrip": false,
|
| 1190 |
+
"normalized": false,
|
| 1191 |
+
"rstrip": false,
|
| 1192 |
+
"single_word": false,
|
| 1193 |
+
"special": true
|
| 1194 |
+
},
|
| 1195 |
+
"128149": {
|
| 1196 |
+
"content": "<|reserved_special_token_140|>",
|
| 1197 |
+
"lstrip": false,
|
| 1198 |
+
"normalized": false,
|
| 1199 |
+
"rstrip": false,
|
| 1200 |
+
"single_word": false,
|
| 1201 |
+
"special": true
|
| 1202 |
+
},
|
| 1203 |
+
"128150": {
|
| 1204 |
+
"content": "<|reserved_special_token_141|>",
|
| 1205 |
+
"lstrip": false,
|
| 1206 |
+
"normalized": false,
|
| 1207 |
+
"rstrip": false,
|
| 1208 |
+
"single_word": false,
|
| 1209 |
+
"special": true
|
| 1210 |
+
},
|
| 1211 |
+
"128151": {
|
| 1212 |
+
"content": "<|reserved_special_token_142|>",
|
| 1213 |
+
"lstrip": false,
|
| 1214 |
+
"normalized": false,
|
| 1215 |
+
"rstrip": false,
|
| 1216 |
+
"single_word": false,
|
| 1217 |
+
"special": true
|
| 1218 |
+
},
|
| 1219 |
+
"128152": {
|
| 1220 |
+
"content": "<|reserved_special_token_143|>",
|
| 1221 |
+
"lstrip": false,
|
| 1222 |
+
"normalized": false,
|
| 1223 |
+
"rstrip": false,
|
| 1224 |
+
"single_word": false,
|
| 1225 |
+
"special": true
|
| 1226 |
+
},
|
| 1227 |
+
"128153": {
|
| 1228 |
+
"content": "<|reserved_special_token_144|>",
|
| 1229 |
+
"lstrip": false,
|
| 1230 |
+
"normalized": false,
|
| 1231 |
+
"rstrip": false,
|
| 1232 |
+
"single_word": false,
|
| 1233 |
+
"special": true
|
| 1234 |
+
},
|
| 1235 |
+
"128154": {
|
| 1236 |
+
"content": "<|reserved_special_token_145|>",
|
| 1237 |
+
"lstrip": false,
|
| 1238 |
+
"normalized": false,
|
| 1239 |
+
"rstrip": false,
|
| 1240 |
+
"single_word": false,
|
| 1241 |
+
"special": true
|
| 1242 |
+
},
|
| 1243 |
+
"128155": {
|
| 1244 |
+
"content": "<|reserved_special_token_146|>",
|
| 1245 |
+
"lstrip": false,
|
| 1246 |
+
"normalized": false,
|
| 1247 |
+
"rstrip": false,
|
| 1248 |
+
"single_word": false,
|
| 1249 |
+
"special": true
|
| 1250 |
+
},
|
| 1251 |
+
"128156": {
|
| 1252 |
+
"content": "<|reserved_special_token_147|>",
|
| 1253 |
+
"lstrip": false,
|
| 1254 |
+
"normalized": false,
|
| 1255 |
+
"rstrip": false,
|
| 1256 |
+
"single_word": false,
|
| 1257 |
+
"special": true
|
| 1258 |
+
},
|
| 1259 |
+
"128157": {
|
| 1260 |
+
"content": "<|reserved_special_token_148|>",
|
| 1261 |
+
"lstrip": false,
|
| 1262 |
+
"normalized": false,
|
| 1263 |
+
"rstrip": false,
|
| 1264 |
+
"single_word": false,
|
| 1265 |
+
"special": true
|
| 1266 |
+
},
|
| 1267 |
+
"128158": {
|
| 1268 |
+
"content": "<|reserved_special_token_149|>",
|
| 1269 |
+
"lstrip": false,
|
| 1270 |
+
"normalized": false,
|
| 1271 |
+
"rstrip": false,
|
| 1272 |
+
"single_word": false,
|
| 1273 |
+
"special": true
|
| 1274 |
+
},
|
| 1275 |
+
"128159": {
|
| 1276 |
+
"content": "<|reserved_special_token_150|>",
|
| 1277 |
+
"lstrip": false,
|
| 1278 |
+
"normalized": false,
|
| 1279 |
+
"rstrip": false,
|
| 1280 |
+
"single_word": false,
|
| 1281 |
+
"special": true
|
| 1282 |
+
},
|
| 1283 |
+
"128160": {
|
| 1284 |
+
"content": "<|reserved_special_token_151|>",
|
| 1285 |
+
"lstrip": false,
|
| 1286 |
+
"normalized": false,
|
| 1287 |
+
"rstrip": false,
|
| 1288 |
+
"single_word": false,
|
| 1289 |
+
"special": true
|
| 1290 |
+
},
|
| 1291 |
+
"128161": {
|
| 1292 |
+
"content": "<|reserved_special_token_152|>",
|
| 1293 |
+
"lstrip": false,
|
| 1294 |
+
"normalized": false,
|
| 1295 |
+
"rstrip": false,
|
| 1296 |
+
"single_word": false,
|
| 1297 |
+
"special": true
|
| 1298 |
+
},
|
| 1299 |
+
"128162": {
|
| 1300 |
+
"content": "<|reserved_special_token_153|>",
|
| 1301 |
+
"lstrip": false,
|
| 1302 |
+
"normalized": false,
|
| 1303 |
+
"rstrip": false,
|
| 1304 |
+
"single_word": false,
|
| 1305 |
+
"special": true
|
| 1306 |
+
},
|
| 1307 |
+
"128163": {
|
| 1308 |
+
"content": "<|reserved_special_token_154|>",
|
| 1309 |
+
"lstrip": false,
|
| 1310 |
+
"normalized": false,
|
| 1311 |
+
"rstrip": false,
|
| 1312 |
+
"single_word": false,
|
| 1313 |
+
"special": true
|
| 1314 |
+
},
|
| 1315 |
+
"128164": {
|
| 1316 |
+
"content": "<|reserved_special_token_155|>",
|
| 1317 |
+
"lstrip": false,
|
| 1318 |
+
"normalized": false,
|
| 1319 |
+
"rstrip": false,
|
| 1320 |
+
"single_word": false,
|
| 1321 |
+
"special": true
|
| 1322 |
+
},
|
| 1323 |
+
"128165": {
|
| 1324 |
+
"content": "<|reserved_special_token_156|>",
|
| 1325 |
+
"lstrip": false,
|
| 1326 |
+
"normalized": false,
|
| 1327 |
+
"rstrip": false,
|
| 1328 |
+
"single_word": false,
|
| 1329 |
+
"special": true
|
| 1330 |
+
},
|
| 1331 |
+
"128166": {
|
| 1332 |
+
"content": "<|reserved_special_token_157|>",
|
| 1333 |
+
"lstrip": false,
|
| 1334 |
+
"normalized": false,
|
| 1335 |
+
"rstrip": false,
|
| 1336 |
+
"single_word": false,
|
| 1337 |
+
"special": true
|
| 1338 |
+
},
|
| 1339 |
+
"128167": {
|
| 1340 |
+
"content": "<|reserved_special_token_158|>",
|
| 1341 |
+
"lstrip": false,
|
| 1342 |
+
"normalized": false,
|
| 1343 |
+
"rstrip": false,
|
| 1344 |
+
"single_word": false,
|
| 1345 |
+
"special": true
|
| 1346 |
+
},
|
| 1347 |
+
"128168": {
|
| 1348 |
+
"content": "<|reserved_special_token_159|>",
|
| 1349 |
+
"lstrip": false,
|
| 1350 |
+
"normalized": false,
|
| 1351 |
+
"rstrip": false,
|
| 1352 |
+
"single_word": false,
|
| 1353 |
+
"special": true
|
| 1354 |
+
},
|
| 1355 |
+
"128169": {
|
| 1356 |
+
"content": "<|reserved_special_token_160|>",
|
| 1357 |
+
"lstrip": false,
|
| 1358 |
+
"normalized": false,
|
| 1359 |
+
"rstrip": false,
|
| 1360 |
+
"single_word": false,
|
| 1361 |
+
"special": true
|
| 1362 |
+
},
|
| 1363 |
+
"128170": {
|
| 1364 |
+
"content": "<|reserved_special_token_161|>",
|
| 1365 |
+
"lstrip": false,
|
| 1366 |
+
"normalized": false,
|
| 1367 |
+
"rstrip": false,
|
| 1368 |
+
"single_word": false,
|
| 1369 |
+
"special": true
|
| 1370 |
+
},
|
| 1371 |
+
"128171": {
|
| 1372 |
+
"content": "<|reserved_special_token_162|>",
|
| 1373 |
+
"lstrip": false,
|
| 1374 |
+
"normalized": false,
|
| 1375 |
+
"rstrip": false,
|
| 1376 |
+
"single_word": false,
|
| 1377 |
+
"special": true
|
| 1378 |
+
},
|
| 1379 |
+
"128172": {
|
| 1380 |
+
"content": "<|reserved_special_token_163|>",
|
| 1381 |
+
"lstrip": false,
|
| 1382 |
+
"normalized": false,
|
| 1383 |
+
"rstrip": false,
|
| 1384 |
+
"single_word": false,
|
| 1385 |
+
"special": true
|
| 1386 |
+
},
|
| 1387 |
+
"128173": {
|
| 1388 |
+
"content": "<|reserved_special_token_164|>",
|
| 1389 |
+
"lstrip": false,
|
| 1390 |
+
"normalized": false,
|
| 1391 |
+
"rstrip": false,
|
| 1392 |
+
"single_word": false,
|
| 1393 |
+
"special": true
|
| 1394 |
+
},
|
| 1395 |
+
"128174": {
|
| 1396 |
+
"content": "<|reserved_special_token_165|>",
|
| 1397 |
+
"lstrip": false,
|
| 1398 |
+
"normalized": false,
|
| 1399 |
+
"rstrip": false,
|
| 1400 |
+
"single_word": false,
|
| 1401 |
+
"special": true
|
| 1402 |
+
},
|
| 1403 |
+
"128175": {
|
| 1404 |
+
"content": "<|reserved_special_token_166|>",
|
| 1405 |
+
"lstrip": false,
|
| 1406 |
+
"normalized": false,
|
| 1407 |
+
"rstrip": false,
|
| 1408 |
+
"single_word": false,
|
| 1409 |
+
"special": true
|
| 1410 |
+
},
|
| 1411 |
+
"128176": {
|
| 1412 |
+
"content": "<|reserved_special_token_167|>",
|
| 1413 |
+
"lstrip": false,
|
| 1414 |
+
"normalized": false,
|
| 1415 |
+
"rstrip": false,
|
| 1416 |
+
"single_word": false,
|
| 1417 |
+
"special": true
|
| 1418 |
+
},
|
| 1419 |
+
"128177": {
|
| 1420 |
+
"content": "<|reserved_special_token_168|>",
|
| 1421 |
+
"lstrip": false,
|
| 1422 |
+
"normalized": false,
|
| 1423 |
+
"rstrip": false,
|
| 1424 |
+
"single_word": false,
|
| 1425 |
+
"special": true
|
| 1426 |
+
},
|
| 1427 |
+
"128178": {
|
| 1428 |
+
"content": "<|reserved_special_token_169|>",
|
| 1429 |
+
"lstrip": false,
|
| 1430 |
+
"normalized": false,
|
| 1431 |
+
"rstrip": false,
|
| 1432 |
+
"single_word": false,
|
| 1433 |
+
"special": true
|
| 1434 |
+
},
|
| 1435 |
+
"128179": {
|
| 1436 |
+
"content": "<|reserved_special_token_170|>",
|
| 1437 |
+
"lstrip": false,
|
| 1438 |
+
"normalized": false,
|
| 1439 |
+
"rstrip": false,
|
| 1440 |
+
"single_word": false,
|
| 1441 |
+
"special": true
|
| 1442 |
+
},
|
| 1443 |
+
"128180": {
|
| 1444 |
+
"content": "<|reserved_special_token_171|>",
|
| 1445 |
+
"lstrip": false,
|
| 1446 |
+
"normalized": false,
|
| 1447 |
+
"rstrip": false,
|
| 1448 |
+
"single_word": false,
|
| 1449 |
+
"special": true
|
| 1450 |
+
},
|
| 1451 |
+
"128181": {
|
| 1452 |
+
"content": "<|reserved_special_token_172|>",
|
| 1453 |
+
"lstrip": false,
|
| 1454 |
+
"normalized": false,
|
| 1455 |
+
"rstrip": false,
|
| 1456 |
+
"single_word": false,
|
| 1457 |
+
"special": true
|
| 1458 |
+
},
|
| 1459 |
+
"128182": {
|
| 1460 |
+
"content": "<|reserved_special_token_173|>",
|
| 1461 |
+
"lstrip": false,
|
| 1462 |
+
"normalized": false,
|
| 1463 |
+
"rstrip": false,
|
| 1464 |
+
"single_word": false,
|
| 1465 |
+
"special": true
|
| 1466 |
+
},
|
| 1467 |
+
"128183": {
|
| 1468 |
+
"content": "<|reserved_special_token_174|>",
|
| 1469 |
+
"lstrip": false,
|
| 1470 |
+
"normalized": false,
|
| 1471 |
+
"rstrip": false,
|
| 1472 |
+
"single_word": false,
|
| 1473 |
+
"special": true
|
| 1474 |
+
},
|
| 1475 |
+
"128184": {
|
| 1476 |
+
"content": "<|reserved_special_token_175|>",
|
| 1477 |
+
"lstrip": false,
|
| 1478 |
+
"normalized": false,
|
| 1479 |
+
"rstrip": false,
|
| 1480 |
+
"single_word": false,
|
| 1481 |
+
"special": true
|
| 1482 |
+
},
|
| 1483 |
+
"128185": {
|
| 1484 |
+
"content": "<|reserved_special_token_176|>",
|
| 1485 |
+
"lstrip": false,
|
| 1486 |
+
"normalized": false,
|
| 1487 |
+
"rstrip": false,
|
| 1488 |
+
"single_word": false,
|
| 1489 |
+
"special": true
|
| 1490 |
+
},
|
| 1491 |
+
"128186": {
|
| 1492 |
+
"content": "<|reserved_special_token_177|>",
|
| 1493 |
+
"lstrip": false,
|
| 1494 |
+
"normalized": false,
|
| 1495 |
+
"rstrip": false,
|
| 1496 |
+
"single_word": false,
|
| 1497 |
+
"special": true
|
| 1498 |
+
},
|
| 1499 |
+
"128187": {
|
| 1500 |
+
"content": "<|reserved_special_token_178|>",
|
| 1501 |
+
"lstrip": false,
|
| 1502 |
+
"normalized": false,
|
| 1503 |
+
"rstrip": false,
|
| 1504 |
+
"single_word": false,
|
| 1505 |
+
"special": true
|
| 1506 |
+
},
|
| 1507 |
+
"128188": {
|
| 1508 |
+
"content": "<|reserved_special_token_179|>",
|
| 1509 |
+
"lstrip": false,
|
| 1510 |
+
"normalized": false,
|
| 1511 |
+
"rstrip": false,
|
| 1512 |
+
"single_word": false,
|
| 1513 |
+
"special": true
|
| 1514 |
+
},
|
| 1515 |
+
"128189": {
|
| 1516 |
+
"content": "<|reserved_special_token_180|>",
|
| 1517 |
+
"lstrip": false,
|
| 1518 |
+
"normalized": false,
|
| 1519 |
+
"rstrip": false,
|
| 1520 |
+
"single_word": false,
|
| 1521 |
+
"special": true
|
| 1522 |
+
},
|
| 1523 |
+
"128190": {
|
| 1524 |
+
"content": "<|reserved_special_token_181|>",
|
| 1525 |
+
"lstrip": false,
|
| 1526 |
+
"normalized": false,
|
| 1527 |
+
"rstrip": false,
|
| 1528 |
+
"single_word": false,
|
| 1529 |
+
"special": true
|
| 1530 |
+
},
|
| 1531 |
+
"128191": {
|
| 1532 |
+
"content": "<|reserved_special_token_182|>",
|
| 1533 |
+
"lstrip": false,
|
| 1534 |
+
"normalized": false,
|
| 1535 |
+
"rstrip": false,
|
| 1536 |
+
"single_word": false,
|
| 1537 |
+
"special": true
|
| 1538 |
+
},
|
| 1539 |
+
"128192": {
|
| 1540 |
+
"content": "<|reserved_special_token_183|>",
|
| 1541 |
+
"lstrip": false,
|
| 1542 |
+
"normalized": false,
|
| 1543 |
+
"rstrip": false,
|
| 1544 |
+
"single_word": false,
|
| 1545 |
+
"special": true
|
| 1546 |
+
},
|
| 1547 |
+
"128193": {
|
| 1548 |
+
"content": "<|reserved_special_token_184|>",
|
| 1549 |
+
"lstrip": false,
|
| 1550 |
+
"normalized": false,
|
| 1551 |
+
"rstrip": false,
|
| 1552 |
+
"single_word": false,
|
| 1553 |
+
"special": true
|
| 1554 |
+
},
|
| 1555 |
+
"128194": {
|
| 1556 |
+
"content": "<|reserved_special_token_185|>",
|
| 1557 |
+
"lstrip": false,
|
| 1558 |
+
"normalized": false,
|
| 1559 |
+
"rstrip": false,
|
| 1560 |
+
"single_word": false,
|
| 1561 |
+
"special": true
|
| 1562 |
+
},
|
| 1563 |
+
"128195": {
|
| 1564 |
+
"content": "<|reserved_special_token_186|>",
|
| 1565 |
+
"lstrip": false,
|
| 1566 |
+
"normalized": false,
|
| 1567 |
+
"rstrip": false,
|
| 1568 |
+
"single_word": false,
|
| 1569 |
+
"special": true
|
| 1570 |
+
},
|
| 1571 |
+
"128196": {
|
| 1572 |
+
"content": "<|reserved_special_token_187|>",
|
| 1573 |
+
"lstrip": false,
|
| 1574 |
+
"normalized": false,
|
| 1575 |
+
"rstrip": false,
|
| 1576 |
+
"single_word": false,
|
| 1577 |
+
"special": true
|
| 1578 |
+
},
|
| 1579 |
+
"128197": {
|
| 1580 |
+
"content": "<|reserved_special_token_188|>",
|
| 1581 |
+
"lstrip": false,
|
| 1582 |
+
"normalized": false,
|
| 1583 |
+
"rstrip": false,
|
| 1584 |
+
"single_word": false,
|
| 1585 |
+
"special": true
|
| 1586 |
+
},
|
| 1587 |
+
"128198": {
|
| 1588 |
+
"content": "<|reserved_special_token_189|>",
|
| 1589 |
+
"lstrip": false,
|
| 1590 |
+
"normalized": false,
|
| 1591 |
+
"rstrip": false,
|
| 1592 |
+
"single_word": false,
|
| 1593 |
+
"special": true
|
| 1594 |
+
},
|
| 1595 |
+
"128199": {
|
| 1596 |
+
"content": "<|reserved_special_token_190|>",
|
| 1597 |
+
"lstrip": false,
|
| 1598 |
+
"normalized": false,
|
| 1599 |
+
"rstrip": false,
|
| 1600 |
+
"single_word": false,
|
| 1601 |
+
"special": true
|
| 1602 |
+
},
|
| 1603 |
+
"128200": {
|
| 1604 |
+
"content": "<|reserved_special_token_191|>",
|
| 1605 |
+
"lstrip": false,
|
| 1606 |
+
"normalized": false,
|
| 1607 |
+
"rstrip": false,
|
| 1608 |
+
"single_word": false,
|
| 1609 |
+
"special": true
|
| 1610 |
+
},
|
| 1611 |
+
"128201": {
|
| 1612 |
+
"content": "<|reserved_special_token_192|>",
|
| 1613 |
+
"lstrip": false,
|
| 1614 |
+
"normalized": false,
|
| 1615 |
+
"rstrip": false,
|
| 1616 |
+
"single_word": false,
|
| 1617 |
+
"special": true
|
| 1618 |
+
},
|
| 1619 |
+
"128202": {
|
| 1620 |
+
"content": "<|reserved_special_token_193|>",
|
| 1621 |
+
"lstrip": false,
|
| 1622 |
+
"normalized": false,
|
| 1623 |
+
"rstrip": false,
|
| 1624 |
+
"single_word": false,
|
| 1625 |
+
"special": true
|
| 1626 |
+
},
|
| 1627 |
+
"128203": {
|
| 1628 |
+
"content": "<|reserved_special_token_194|>",
|
| 1629 |
+
"lstrip": false,
|
| 1630 |
+
"normalized": false,
|
| 1631 |
+
"rstrip": false,
|
| 1632 |
+
"single_word": false,
|
| 1633 |
+
"special": true
|
| 1634 |
+
},
|
| 1635 |
+
"128204": {
|
| 1636 |
+
"content": "<|reserved_special_token_195|>",
|
| 1637 |
+
"lstrip": false,
|
| 1638 |
+
"normalized": false,
|
| 1639 |
+
"rstrip": false,
|
| 1640 |
+
"single_word": false,
|
| 1641 |
+
"special": true
|
| 1642 |
+
},
|
| 1643 |
+
"128205": {
|
| 1644 |
+
"content": "<|reserved_special_token_196|>",
|
| 1645 |
+
"lstrip": false,
|
| 1646 |
+
"normalized": false,
|
| 1647 |
+
"rstrip": false,
|
| 1648 |
+
"single_word": false,
|
| 1649 |
+
"special": true
|
| 1650 |
+
},
|
| 1651 |
+
"128206": {
|
| 1652 |
+
"content": "<|reserved_special_token_197|>",
|
| 1653 |
+
"lstrip": false,
|
| 1654 |
+
"normalized": false,
|
| 1655 |
+
"rstrip": false,
|
| 1656 |
+
"single_word": false,
|
| 1657 |
+
"special": true
|
| 1658 |
+
},
|
| 1659 |
+
"128207": {
|
| 1660 |
+
"content": "<|reserved_special_token_198|>",
|
| 1661 |
+
"lstrip": false,
|
| 1662 |
+
"normalized": false,
|
| 1663 |
+
"rstrip": false,
|
| 1664 |
+
"single_word": false,
|
| 1665 |
+
"special": true
|
| 1666 |
+
},
|
| 1667 |
+
"128208": {
|
| 1668 |
+
"content": "<|reserved_special_token_199|>",
|
| 1669 |
+
"lstrip": false,
|
| 1670 |
+
"normalized": false,
|
| 1671 |
+
"rstrip": false,
|
| 1672 |
+
"single_word": false,
|
| 1673 |
+
"special": true
|
| 1674 |
+
},
|
| 1675 |
+
"128209": {
|
| 1676 |
+
"content": "<|reserved_special_token_200|>",
|
| 1677 |
+
"lstrip": false,
|
| 1678 |
+
"normalized": false,
|
| 1679 |
+
"rstrip": false,
|
| 1680 |
+
"single_word": false,
|
| 1681 |
+
"special": true
|
| 1682 |
+
},
|
| 1683 |
+
"128210": {
|
| 1684 |
+
"content": "<|reserved_special_token_201|>",
|
| 1685 |
+
"lstrip": false,
|
| 1686 |
+
"normalized": false,
|
| 1687 |
+
"rstrip": false,
|
| 1688 |
+
"single_word": false,
|
| 1689 |
+
"special": true
|
| 1690 |
+
},
|
| 1691 |
+
"128211": {
|
| 1692 |
+
"content": "<|reserved_special_token_202|>",
|
| 1693 |
+
"lstrip": false,
|
| 1694 |
+
"normalized": false,
|
| 1695 |
+
"rstrip": false,
|
| 1696 |
+
"single_word": false,
|
| 1697 |
+
"special": true
|
| 1698 |
+
},
|
| 1699 |
+
"128212": {
|
| 1700 |
+
"content": "<|reserved_special_token_203|>",
|
| 1701 |
+
"lstrip": false,
|
| 1702 |
+
"normalized": false,
|
| 1703 |
+
"rstrip": false,
|
| 1704 |
+
"single_word": false,
|
| 1705 |
+
"special": true
|
| 1706 |
+
},
|
| 1707 |
+
"128213": {
|
| 1708 |
+
"content": "<|reserved_special_token_204|>",
|
| 1709 |
+
"lstrip": false,
|
| 1710 |
+
"normalized": false,
|
| 1711 |
+
"rstrip": false,
|
| 1712 |
+
"single_word": false,
|
| 1713 |
+
"special": true
|
| 1714 |
+
},
|
| 1715 |
+
"128214": {
|
| 1716 |
+
"content": "<|reserved_special_token_205|>",
|
| 1717 |
+
"lstrip": false,
|
| 1718 |
+
"normalized": false,
|
| 1719 |
+
"rstrip": false,
|
| 1720 |
+
"single_word": false,
|
| 1721 |
+
"special": true
|
| 1722 |
+
},
|
| 1723 |
+
"128215": {
|
| 1724 |
+
"content": "<|reserved_special_token_206|>",
|
| 1725 |
+
"lstrip": false,
|
| 1726 |
+
"normalized": false,
|
| 1727 |
+
"rstrip": false,
|
| 1728 |
+
"single_word": false,
|
| 1729 |
+
"special": true
|
| 1730 |
+
},
|
| 1731 |
+
"128216": {
|
| 1732 |
+
"content": "<|reserved_special_token_207|>",
|
| 1733 |
+
"lstrip": false,
|
| 1734 |
+
"normalized": false,
|
| 1735 |
+
"rstrip": false,
|
| 1736 |
+
"single_word": false,
|
| 1737 |
+
"special": true
|
| 1738 |
+
},
|
| 1739 |
+
"128217": {
|
| 1740 |
+
"content": "<|reserved_special_token_208|>",
|
| 1741 |
+
"lstrip": false,
|
| 1742 |
+
"normalized": false,
|
| 1743 |
+
"rstrip": false,
|
| 1744 |
+
"single_word": false,
|
| 1745 |
+
"special": true
|
| 1746 |
+
},
|
| 1747 |
+
"128218": {
|
| 1748 |
+
"content": "<|reserved_special_token_209|>",
|
| 1749 |
+
"lstrip": false,
|
| 1750 |
+
"normalized": false,
|
| 1751 |
+
"rstrip": false,
|
| 1752 |
+
"single_word": false,
|
| 1753 |
+
"special": true
|
| 1754 |
+
},
|
| 1755 |
+
"128219": {
|
| 1756 |
+
"content": "<|reserved_special_token_210|>",
|
| 1757 |
+
"lstrip": false,
|
| 1758 |
+
"normalized": false,
|
| 1759 |
+
"rstrip": false,
|
| 1760 |
+
"single_word": false,
|
| 1761 |
+
"special": true
|
| 1762 |
+
},
|
| 1763 |
+
"128220": {
|
| 1764 |
+
"content": "<|reserved_special_token_211|>",
|
| 1765 |
+
"lstrip": false,
|
| 1766 |
+
"normalized": false,
|
| 1767 |
+
"rstrip": false,
|
| 1768 |
+
"single_word": false,
|
| 1769 |
+
"special": true
|
| 1770 |
+
},
|
| 1771 |
+
"128221": {
|
| 1772 |
+
"content": "<|reserved_special_token_212|>",
|
| 1773 |
+
"lstrip": false,
|
| 1774 |
+
"normalized": false,
|
| 1775 |
+
"rstrip": false,
|
| 1776 |
+
"single_word": false,
|
| 1777 |
+
"special": true
|
| 1778 |
+
},
|
| 1779 |
+
"128222": {
|
| 1780 |
+
"content": "<|reserved_special_token_213|>",
|
| 1781 |
+
"lstrip": false,
|
| 1782 |
+
"normalized": false,
|
| 1783 |
+
"rstrip": false,
|
| 1784 |
+
"single_word": false,
|
| 1785 |
+
"special": true
|
| 1786 |
+
},
|
| 1787 |
+
"128223": {
|
| 1788 |
+
"content": "<|reserved_special_token_214|>",
|
| 1789 |
+
"lstrip": false,
|
| 1790 |
+
"normalized": false,
|
| 1791 |
+
"rstrip": false,
|
| 1792 |
+
"single_word": false,
|
| 1793 |
+
"special": true
|
| 1794 |
+
},
|
| 1795 |
+
"128224": {
|
| 1796 |
+
"content": "<|reserved_special_token_215|>",
|
| 1797 |
+
"lstrip": false,
|
| 1798 |
+
"normalized": false,
|
| 1799 |
+
"rstrip": false,
|
| 1800 |
+
"single_word": false,
|
| 1801 |
+
"special": true
|
| 1802 |
+
},
|
| 1803 |
+
"128225": {
|
| 1804 |
+
"content": "<|reserved_special_token_216|>",
|
| 1805 |
+
"lstrip": false,
|
| 1806 |
+
"normalized": false,
|
| 1807 |
+
"rstrip": false,
|
| 1808 |
+
"single_word": false,
|
| 1809 |
+
"special": true
|
| 1810 |
+
},
|
| 1811 |
+
"128226": {
|
| 1812 |
+
"content": "<|reserved_special_token_217|>",
|
| 1813 |
+
"lstrip": false,
|
| 1814 |
+
"normalized": false,
|
| 1815 |
+
"rstrip": false,
|
| 1816 |
+
"single_word": false,
|
| 1817 |
+
"special": true
|
| 1818 |
+
},
|
| 1819 |
+
"128227": {
|
| 1820 |
+
"content": "<|reserved_special_token_218|>",
|
| 1821 |
+
"lstrip": false,
|
| 1822 |
+
"normalized": false,
|
| 1823 |
+
"rstrip": false,
|
| 1824 |
+
"single_word": false,
|
| 1825 |
+
"special": true
|
| 1826 |
+
},
|
| 1827 |
+
"128228": {
|
| 1828 |
+
"content": "<|reserved_special_token_219|>",
|
| 1829 |
+
"lstrip": false,
|
| 1830 |
+
"normalized": false,
|
| 1831 |
+
"rstrip": false,
|
| 1832 |
+
"single_word": false,
|
| 1833 |
+
"special": true
|
| 1834 |
+
},
|
| 1835 |
+
"128229": {
|
| 1836 |
+
"content": "<|reserved_special_token_220|>",
|
| 1837 |
+
"lstrip": false,
|
| 1838 |
+
"normalized": false,
|
| 1839 |
+
"rstrip": false,
|
| 1840 |
+
"single_word": false,
|
| 1841 |
+
"special": true
|
| 1842 |
+
},
|
| 1843 |
+
"128230": {
|
| 1844 |
+
"content": "<|reserved_special_token_221|>",
|
| 1845 |
+
"lstrip": false,
|
| 1846 |
+
"normalized": false,
|
| 1847 |
+
"rstrip": false,
|
| 1848 |
+
"single_word": false,
|
| 1849 |
+
"special": true
|
| 1850 |
+
},
|
| 1851 |
+
"128231": {
|
| 1852 |
+
"content": "<|reserved_special_token_222|>",
|
| 1853 |
+
"lstrip": false,
|
| 1854 |
+
"normalized": false,
|
| 1855 |
+
"rstrip": false,
|
| 1856 |
+
"single_word": false,
|
| 1857 |
+
"special": true
|
| 1858 |
+
},
|
| 1859 |
+
"128232": {
|
| 1860 |
+
"content": "<|reserved_special_token_223|>",
|
| 1861 |
+
"lstrip": false,
|
| 1862 |
+
"normalized": false,
|
| 1863 |
+
"rstrip": false,
|
| 1864 |
+
"single_word": false,
|
| 1865 |
+
"special": true
|
| 1866 |
+
},
|
| 1867 |
+
"128233": {
|
| 1868 |
+
"content": "<|reserved_special_token_224|>",
|
| 1869 |
+
"lstrip": false,
|
| 1870 |
+
"normalized": false,
|
| 1871 |
+
"rstrip": false,
|
| 1872 |
+
"single_word": false,
|
| 1873 |
+
"special": true
|
| 1874 |
+
},
|
| 1875 |
+
"128234": {
|
| 1876 |
+
"content": "<|reserved_special_token_225|>",
|
| 1877 |
+
"lstrip": false,
|
| 1878 |
+
"normalized": false,
|
| 1879 |
+
"rstrip": false,
|
| 1880 |
+
"single_word": false,
|
| 1881 |
+
"special": true
|
| 1882 |
+
},
|
| 1883 |
+
"128235": {
|
| 1884 |
+
"content": "<|reserved_special_token_226|>",
|
| 1885 |
+
"lstrip": false,
|
| 1886 |
+
"normalized": false,
|
| 1887 |
+
"rstrip": false,
|
| 1888 |
+
"single_word": false,
|
| 1889 |
+
"special": true
|
| 1890 |
+
},
|
| 1891 |
+
"128236": {
|
| 1892 |
+
"content": "<|reserved_special_token_227|>",
|
| 1893 |
+
"lstrip": false,
|
| 1894 |
+
"normalized": false,
|
| 1895 |
+
"rstrip": false,
|
| 1896 |
+
"single_word": false,
|
| 1897 |
+
"special": true
|
| 1898 |
+
},
|
| 1899 |
+
"128237": {
|
| 1900 |
+
"content": "<|reserved_special_token_228|>",
|
| 1901 |
+
"lstrip": false,
|
| 1902 |
+
"normalized": false,
|
| 1903 |
+
"rstrip": false,
|
| 1904 |
+
"single_word": false,
|
| 1905 |
+
"special": true
|
| 1906 |
+
},
|
| 1907 |
+
"128238": {
|
| 1908 |
+
"content": "<|reserved_special_token_229|>",
|
| 1909 |
+
"lstrip": false,
|
| 1910 |
+
"normalized": false,
|
| 1911 |
+
"rstrip": false,
|
| 1912 |
+
"single_word": false,
|
| 1913 |
+
"special": true
|
| 1914 |
+
},
|
| 1915 |
+
"128239": {
|
| 1916 |
+
"content": "<|reserved_special_token_230|>",
|
| 1917 |
+
"lstrip": false,
|
| 1918 |
+
"normalized": false,
|
| 1919 |
+
"rstrip": false,
|
| 1920 |
+
"single_word": false,
|
| 1921 |
+
"special": true
|
| 1922 |
+
},
|
| 1923 |
+
"128240": {
|
| 1924 |
+
"content": "<|reserved_special_token_231|>",
|
| 1925 |
+
"lstrip": false,
|
| 1926 |
+
"normalized": false,
|
| 1927 |
+
"rstrip": false,
|
| 1928 |
+
"single_word": false,
|
| 1929 |
+
"special": true
|
| 1930 |
+
},
|
| 1931 |
+
"128241": {
|
| 1932 |
+
"content": "<|reserved_special_token_232|>",
|
| 1933 |
+
"lstrip": false,
|
| 1934 |
+
"normalized": false,
|
| 1935 |
+
"rstrip": false,
|
| 1936 |
+
"single_word": false,
|
| 1937 |
+
"special": true
|
| 1938 |
+
},
|
| 1939 |
+
"128242": {
|
| 1940 |
+
"content": "<|reserved_special_token_233|>",
|
| 1941 |
+
"lstrip": false,
|
| 1942 |
+
"normalized": false,
|
| 1943 |
+
"rstrip": false,
|
| 1944 |
+
"single_word": false,
|
| 1945 |
+
"special": true
|
| 1946 |
+
},
|
| 1947 |
+
"128243": {
|
| 1948 |
+
"content": "<|reserved_special_token_234|>",
|
| 1949 |
+
"lstrip": false,
|
| 1950 |
+
"normalized": false,
|
| 1951 |
+
"rstrip": false,
|
| 1952 |
+
"single_word": false,
|
| 1953 |
+
"special": true
|
| 1954 |
+
},
|
| 1955 |
+
"128244": {
|
| 1956 |
+
"content": "<|reserved_special_token_235|>",
|
| 1957 |
+
"lstrip": false,
|
| 1958 |
+
"normalized": false,
|
| 1959 |
+
"rstrip": false,
|
| 1960 |
+
"single_word": false,
|
| 1961 |
+
"special": true
|
| 1962 |
+
},
|
| 1963 |
+
"128245": {
|
| 1964 |
+
"content": "<|reserved_special_token_236|>",
|
| 1965 |
+
"lstrip": false,
|
| 1966 |
+
"normalized": false,
|
| 1967 |
+
"rstrip": false,
|
| 1968 |
+
"single_word": false,
|
| 1969 |
+
"special": true
|
| 1970 |
+
},
|
| 1971 |
+
"128246": {
|
| 1972 |
+
"content": "<|reserved_special_token_237|>",
|
| 1973 |
+
"lstrip": false,
|
| 1974 |
+
"normalized": false,
|
| 1975 |
+
"rstrip": false,
|
| 1976 |
+
"single_word": false,
|
| 1977 |
+
"special": true
|
| 1978 |
+
},
|
| 1979 |
+
"128247": {
|
| 1980 |
+
"content": "<|reserved_special_token_238|>",
|
| 1981 |
+
"lstrip": false,
|
| 1982 |
+
"normalized": false,
|
| 1983 |
+
"rstrip": false,
|
| 1984 |
+
"single_word": false,
|
| 1985 |
+
"special": true
|
| 1986 |
+
},
|
| 1987 |
+
"128248": {
|
| 1988 |
+
"content": "<|reserved_special_token_239|>",
|
| 1989 |
+
"lstrip": false,
|
| 1990 |
+
"normalized": false,
|
| 1991 |
+
"rstrip": false,
|
| 1992 |
+
"single_word": false,
|
| 1993 |
+
"special": true
|
| 1994 |
+
},
|
| 1995 |
+
"128249": {
|
| 1996 |
+
"content": "<|reserved_special_token_240|>",
|
| 1997 |
+
"lstrip": false,
|
| 1998 |
+
"normalized": false,
|
| 1999 |
+
"rstrip": false,
|
| 2000 |
+
"single_word": false,
|
| 2001 |
+
"special": true
|
| 2002 |
+
},
|
| 2003 |
+
"128250": {
|
| 2004 |
+
"content": "<|reserved_special_token_241|>",
|
| 2005 |
+
"lstrip": false,
|
| 2006 |
+
"normalized": false,
|
| 2007 |
+
"rstrip": false,
|
| 2008 |
+
"single_word": false,
|
| 2009 |
+
"special": true
|
| 2010 |
+
},
|
| 2011 |
+
"128251": {
|
| 2012 |
+
"content": "<|reserved_special_token_242|>",
|
| 2013 |
+
"lstrip": false,
|
| 2014 |
+
"normalized": false,
|
| 2015 |
+
"rstrip": false,
|
| 2016 |
+
"single_word": false,
|
| 2017 |
+
"special": true
|
| 2018 |
+
},
|
| 2019 |
+
"128252": {
|
| 2020 |
+
"content": "<|reserved_special_token_243|>",
|
| 2021 |
+
"lstrip": false,
|
| 2022 |
+
"normalized": false,
|
| 2023 |
+
"rstrip": false,
|
| 2024 |
+
"single_word": false,
|
| 2025 |
+
"special": true
|
| 2026 |
+
},
|
| 2027 |
+
"128253": {
|
| 2028 |
+
"content": "<|reserved_special_token_244|>",
|
| 2029 |
+
"lstrip": false,
|
| 2030 |
+
"normalized": false,
|
| 2031 |
+
"rstrip": false,
|
| 2032 |
+
"single_word": false,
|
| 2033 |
+
"special": true
|
| 2034 |
+
},
|
| 2035 |
+
"128254": {
|
| 2036 |
+
"content": "<|reserved_special_token_245|>",
|
| 2037 |
+
"lstrip": false,
|
| 2038 |
+
"normalized": false,
|
| 2039 |
+
"rstrip": false,
|
| 2040 |
+
"single_word": false,
|
| 2041 |
+
"special": true
|
| 2042 |
+
},
|
| 2043 |
+
"128255": {
|
| 2044 |
+
"content": "<|reserved_special_token_246|>",
|
| 2045 |
+
"lstrip": false,
|
| 2046 |
+
"normalized": false,
|
| 2047 |
+
"rstrip": false,
|
| 2048 |
+
"single_word": false,
|
| 2049 |
+
"special": true
|
| 2050 |
+
},
|
| 2051 |
+
"128256": {
|
| 2052 |
+
"content": "<|image|>",
|
| 2053 |
+
"lstrip": false,
|
| 2054 |
+
"normalized": false,
|
| 2055 |
+
"rstrip": false,
|
| 2056 |
+
"single_word": false,
|
| 2057 |
+
"special": true
|
| 2058 |
+
}
|
| 2059 |
+
},
|
| 2060 |
+
"bos_token": "<|begin_of_text|>",
|
| 2061 |
+
"clean_up_tokenization_spaces": true,
|
| 2062 |
+
"eos_token": "<|end_of_text|>",
|
| 2063 |
+
"model_input_names": [
|
| 2064 |
+
"input_ids",
|
| 2065 |
+
"attention_mask"
|
| 2066 |
+
],
|
| 2067 |
+
"model_max_length": 131072,
|
| 2068 |
+
"pad_token": "<|finetune_right_pad_id|>",
|
| 2069 |
+
"tokenizer_class": "PreTrainedTokenizerFast"
|
| 2070 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,2513 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 9.72549019607843,
|
| 5 |
+
"eval_steps": 31,
|
| 6 |
+
"global_step": 310,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.03137254901960784,
|
| 13 |
+
"grad_norm": 17.784626007080078,
|
| 14 |
+
"learning_rate": 2e-05,
|
| 15 |
+
"loss": 7.7199,
|
| 16 |
+
"num_input_tokens_seen": 789,
|
| 17 |
+
"step": 1
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.06274509803921569,
|
| 21 |
+
"grad_norm": 12.485037803649902,
|
| 22 |
+
"learning_rate": 4e-05,
|
| 23 |
+
"loss": 5.2762,
|
| 24 |
+
"num_input_tokens_seen": 1656,
|
| 25 |
+
"step": 2
|
| 26 |
+
},
|
| 27 |
+
{
|
| 28 |
+
"epoch": 0.09411764705882353,
|
| 29 |
+
"grad_norm": 7.9316840171813965,
|
| 30 |
+
"learning_rate": 6e-05,
|
| 31 |
+
"loss": 4.3107,
|
| 32 |
+
"num_input_tokens_seen": 2529,
|
| 33 |
+
"step": 3
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 0.12549019607843137,
|
| 37 |
+
"grad_norm": 9.721095085144043,
|
| 38 |
+
"learning_rate": 8e-05,
|
| 39 |
+
"loss": 4.8054,
|
| 40 |
+
"num_input_tokens_seen": 3389,
|
| 41 |
+
"step": 4
|
| 42 |
+
},
|
| 43 |
+
{
|
| 44 |
+
"epoch": 0.1568627450980392,
|
| 45 |
+
"grad_norm": 8.977057456970215,
|
| 46 |
+
"learning_rate": 0.0001,
|
| 47 |
+
"loss": 5.4644,
|
| 48 |
+
"num_input_tokens_seen": 4244,
|
| 49 |
+
"step": 5
|
| 50 |
+
},
|
| 51 |
+
{
|
| 52 |
+
"epoch": 0.18823529411764706,
|
| 53 |
+
"grad_norm": 10.086724281311035,
|
| 54 |
+
"learning_rate": 0.00012,
|
| 55 |
+
"loss": 5.6263,
|
| 56 |
+
"num_input_tokens_seen": 5059,
|
| 57 |
+
"step": 6
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 0.2196078431372549,
|
| 61 |
+
"grad_norm": 13.49176025390625,
|
| 62 |
+
"learning_rate": 0.00014,
|
| 63 |
+
"loss": 5.4706,
|
| 64 |
+
"num_input_tokens_seen": 5918,
|
| 65 |
+
"step": 7
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.25098039215686274,
|
| 69 |
+
"grad_norm": 11.12248706817627,
|
| 70 |
+
"learning_rate": 0.00016,
|
| 71 |
+
"loss": 4.4177,
|
| 72 |
+
"num_input_tokens_seen": 6758,
|
| 73 |
+
"step": 8
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.2823529411764706,
|
| 77 |
+
"grad_norm": 6.923247814178467,
|
| 78 |
+
"learning_rate": 0.00018,
|
| 79 |
+
"loss": 3.9388,
|
| 80 |
+
"num_input_tokens_seen": 7653,
|
| 81 |
+
"step": 9
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 0.3137254901960784,
|
| 85 |
+
"grad_norm": 11.242279052734375,
|
| 86 |
+
"learning_rate": 0.0002,
|
| 87 |
+
"loss": 4.3202,
|
| 88 |
+
"num_input_tokens_seen": 8464,
|
| 89 |
+
"step": 10
|
| 90 |
+
},
|
| 91 |
+
{
|
| 92 |
+
"epoch": 0.34509803921568627,
|
| 93 |
+
"grad_norm": 8.588418960571289,
|
| 94 |
+
"learning_rate": 0.00019995065603657316,
|
| 95 |
+
"loss": 3.116,
|
| 96 |
+
"num_input_tokens_seen": 9348,
|
| 97 |
+
"step": 11
|
| 98 |
+
},
|
| 99 |
+
{
|
| 100 |
+
"epoch": 0.3764705882352941,
|
| 101 |
+
"grad_norm": 9.73305892944336,
|
| 102 |
+
"learning_rate": 0.00019980267284282717,
|
| 103 |
+
"loss": 2.723,
|
| 104 |
+
"num_input_tokens_seen": 10204,
|
| 105 |
+
"step": 12
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 0.40784313725490196,
|
| 109 |
+
"grad_norm": 15.396673202514648,
|
| 110 |
+
"learning_rate": 0.00019955619646030802,
|
| 111 |
+
"loss": 2.4929,
|
| 112 |
+
"num_input_tokens_seen": 11030,
|
| 113 |
+
"step": 13
|
| 114 |
+
},
|
| 115 |
+
{
|
| 116 |
+
"epoch": 0.4392156862745098,
|
| 117 |
+
"grad_norm": 24.212421417236328,
|
| 118 |
+
"learning_rate": 0.0001992114701314478,
|
| 119 |
+
"loss": 2.7489,
|
| 120 |
+
"num_input_tokens_seen": 11845,
|
| 121 |
+
"step": 14
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.47058823529411764,
|
| 125 |
+
"grad_norm": 14.499921798706055,
|
| 126 |
+
"learning_rate": 0.00019876883405951377,
|
| 127 |
+
"loss": 1.8677,
|
| 128 |
+
"num_input_tokens_seen": 12686,
|
| 129 |
+
"step": 15
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.5019607843137255,
|
| 133 |
+
"grad_norm": 16.502588272094727,
|
| 134 |
+
"learning_rate": 0.0001982287250728689,
|
| 135 |
+
"loss": 1.3637,
|
| 136 |
+
"num_input_tokens_seen": 13505,
|
| 137 |
+
"step": 16
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 0.5333333333333333,
|
| 141 |
+
"grad_norm": 14.297043800354004,
|
| 142 |
+
"learning_rate": 0.00019759167619387476,
|
| 143 |
+
"loss": 1.5026,
|
| 144 |
+
"num_input_tokens_seen": 14344,
|
| 145 |
+
"step": 17
|
| 146 |
+
},
|
| 147 |
+
{
|
| 148 |
+
"epoch": 0.5647058823529412,
|
| 149 |
+
"grad_norm": 9.703812599182129,
|
| 150 |
+
"learning_rate": 0.0001968583161128631,
|
| 151 |
+
"loss": 1.4165,
|
| 152 |
+
"num_input_tokens_seen": 15218,
|
| 153 |
+
"step": 18
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 0.596078431372549,
|
| 157 |
+
"grad_norm": 12.656659126281738,
|
| 158 |
+
"learning_rate": 0.0001960293685676943,
|
| 159 |
+
"loss": 1.0906,
|
| 160 |
+
"num_input_tokens_seen": 16040,
|
| 161 |
+
"step": 19
|
| 162 |
+
},
|
| 163 |
+
{
|
| 164 |
+
"epoch": 0.6274509803921569,
|
| 165 |
+
"grad_norm": 58.49094772338867,
|
| 166 |
+
"learning_rate": 0.00019510565162951537,
|
| 167 |
+
"loss": 0.9817,
|
| 168 |
+
"num_input_tokens_seen": 16874,
|
| 169 |
+
"step": 20
|
| 170 |
+
},
|
| 171 |
+
{
|
| 172 |
+
"epoch": 0.6588235294117647,
|
| 173 |
+
"grad_norm": 9.382222175598145,
|
| 174 |
+
"learning_rate": 0.00019408807689542257,
|
| 175 |
+
"loss": 1.1198,
|
| 176 |
+
"num_input_tokens_seen": 17682,
|
| 177 |
+
"step": 21
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.6901960784313725,
|
| 181 |
+
"grad_norm": 10.244654655456543,
|
| 182 |
+
"learning_rate": 0.00019297764858882514,
|
| 183 |
+
"loss": 1.2596,
|
| 184 |
+
"num_input_tokens_seen": 18539,
|
| 185 |
+
"step": 22
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.7215686274509804,
|
| 189 |
+
"grad_norm": 8.23478889465332,
|
| 190 |
+
"learning_rate": 0.00019177546256839812,
|
| 191 |
+
"loss": 1.2768,
|
| 192 |
+
"num_input_tokens_seen": 19432,
|
| 193 |
+
"step": 23
|
| 194 |
+
},
|
| 195 |
+
{
|
| 196 |
+
"epoch": 0.7529411764705882,
|
| 197 |
+
"grad_norm": 19.18866729736328,
|
| 198 |
+
"learning_rate": 0.00019048270524660196,
|
| 199 |
+
"loss": 1.3043,
|
| 200 |
+
"num_input_tokens_seen": 20264,
|
| 201 |
+
"step": 24
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 0.7843137254901961,
|
| 205 |
+
"grad_norm": 6.661506175994873,
|
| 206 |
+
"learning_rate": 0.0001891006524188368,
|
| 207 |
+
"loss": 0.8769,
|
| 208 |
+
"num_input_tokens_seen": 21113,
|
| 209 |
+
"step": 25
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 0.8156862745098039,
|
| 213 |
+
"grad_norm": 6.4282546043396,
|
| 214 |
+
"learning_rate": 0.00018763066800438636,
|
| 215 |
+
"loss": 1.0473,
|
| 216 |
+
"num_input_tokens_seen": 21966,
|
| 217 |
+
"step": 26
|
| 218 |
+
},
|
| 219 |
+
{
|
| 220 |
+
"epoch": 0.8470588235294118,
|
| 221 |
+
"grad_norm": 11.599508285522461,
|
| 222 |
+
"learning_rate": 0.0001860742027003944,
|
| 223 |
+
"loss": 1.0205,
|
| 224 |
+
"num_input_tokens_seen": 22821,
|
| 225 |
+
"step": 27
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 0.8784313725490196,
|
| 229 |
+
"grad_norm": 9.272802352905273,
|
| 230 |
+
"learning_rate": 0.00018443279255020152,
|
| 231 |
+
"loss": 1.2292,
|
| 232 |
+
"num_input_tokens_seen": 23733,
|
| 233 |
+
"step": 28
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.9098039215686274,
|
| 237 |
+
"grad_norm": 7.99858283996582,
|
| 238 |
+
"learning_rate": 0.00018270805742745617,
|
| 239 |
+
"loss": 1.1247,
|
| 240 |
+
"num_input_tokens_seen": 24593,
|
| 241 |
+
"step": 29
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 0.9411764705882353,
|
| 245 |
+
"grad_norm": 10.046642303466797,
|
| 246 |
+
"learning_rate": 0.00018090169943749476,
|
| 247 |
+
"loss": 1.2097,
|
| 248 |
+
"num_input_tokens_seen": 25425,
|
| 249 |
+
"step": 30
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 0.9725490196078431,
|
| 253 |
+
"grad_norm": 9.499373435974121,
|
| 254 |
+
"learning_rate": 0.00017901550123756904,
|
| 255 |
+
"loss": 1.1345,
|
| 256 |
+
"num_input_tokens_seen": 26228,
|
| 257 |
+
"step": 31
|
| 258 |
+
},
|
| 259 |
+
{
|
| 260 |
+
"epoch": 1.003921568627451,
|
| 261 |
+
"grad_norm": 5.625377178192139,
|
| 262 |
+
"learning_rate": 0.00017705132427757895,
|
| 263 |
+
"loss": 1.1178,
|
| 264 |
+
"num_input_tokens_seen": 27085,
|
| 265 |
+
"step": 32
|
| 266 |
+
},
|
| 267 |
+
{
|
| 268 |
+
"epoch": 1.035294117647059,
|
| 269 |
+
"grad_norm": 4.716068744659424,
|
| 270 |
+
"learning_rate": 0.00017501110696304596,
|
| 271 |
+
"loss": 0.8997,
|
| 272 |
+
"num_input_tokens_seen": 27917,
|
| 273 |
+
"step": 33
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 1.0666666666666667,
|
| 277 |
+
"grad_norm": 4.880837440490723,
|
| 278 |
+
"learning_rate": 0.00017289686274214118,
|
| 279 |
+
"loss": 0.654,
|
| 280 |
+
"num_input_tokens_seen": 28796,
|
| 281 |
+
"step": 34
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 1.0980392156862746,
|
| 285 |
+
"grad_norm": 3.4638915061950684,
|
| 286 |
+
"learning_rate": 0.00017071067811865476,
|
| 287 |
+
"loss": 0.7083,
|
| 288 |
+
"num_input_tokens_seen": 29650,
|
| 289 |
+
"step": 35
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 1.1294117647058823,
|
| 293 |
+
"grad_norm": 6.4757561683654785,
|
| 294 |
+
"learning_rate": 0.00016845471059286887,
|
| 295 |
+
"loss": 0.981,
|
| 296 |
+
"num_input_tokens_seen": 30477,
|
| 297 |
+
"step": 36
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 1.1607843137254903,
|
| 301 |
+
"grad_norm": 6.666485786437988,
|
| 302 |
+
"learning_rate": 0.00016613118653236518,
|
| 303 |
+
"loss": 1.1384,
|
| 304 |
+
"num_input_tokens_seen": 31314,
|
| 305 |
+
"step": 37
|
| 306 |
+
},
|
| 307 |
+
{
|
| 308 |
+
"epoch": 1.192156862745098,
|
| 309 |
+
"grad_norm": 6.810871601104736,
|
| 310 |
+
"learning_rate": 0.000163742398974869,
|
| 311 |
+
"loss": 1.0914,
|
| 312 |
+
"num_input_tokens_seen": 32129,
|
| 313 |
+
"step": 38
|
| 314 |
+
},
|
| 315 |
+
{
|
| 316 |
+
"epoch": 1.223529411764706,
|
| 317 |
+
"grad_norm": 4.342460632324219,
|
| 318 |
+
"learning_rate": 0.00016129070536529766,
|
| 319 |
+
"loss": 0.784,
|
| 320 |
+
"num_input_tokens_seen": 32980,
|
| 321 |
+
"step": 39
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 1.2549019607843137,
|
| 325 |
+
"grad_norm": 6.6151204109191895,
|
| 326 |
+
"learning_rate": 0.0001587785252292473,
|
| 327 |
+
"loss": 1.151,
|
| 328 |
+
"num_input_tokens_seen": 33811,
|
| 329 |
+
"step": 40
|
| 330 |
+
},
|
| 331 |
+
{
|
| 332 |
+
"epoch": 1.2862745098039214,
|
| 333 |
+
"grad_norm": 6.701898097991943,
|
| 334 |
+
"learning_rate": 0.00015620833778521307,
|
| 335 |
+
"loss": 1.1066,
|
| 336 |
+
"num_input_tokens_seen": 34640,
|
| 337 |
+
"step": 41
|
| 338 |
+
},
|
| 339 |
+
{
|
| 340 |
+
"epoch": 1.3176470588235294,
|
| 341 |
+
"grad_norm": 3.7148549556732178,
|
| 342 |
+
"learning_rate": 0.00015358267949789966,
|
| 343 |
+
"loss": 1.1097,
|
| 344 |
+
"num_input_tokens_seen": 35540,
|
| 345 |
+
"step": 42
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 1.3490196078431373,
|
| 349 |
+
"grad_norm": 4.791841506958008,
|
| 350 |
+
"learning_rate": 0.00015090414157503714,
|
| 351 |
+
"loss": 0.9391,
|
| 352 |
+
"num_input_tokens_seen": 36388,
|
| 353 |
+
"step": 43
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 1.380392156862745,
|
| 357 |
+
"grad_norm": 6.712942123413086,
|
| 358 |
+
"learning_rate": 0.00014817536741017152,
|
| 359 |
+
"loss": 0.8025,
|
| 360 |
+
"num_input_tokens_seen": 37254,
|
| 361 |
+
"step": 44
|
| 362 |
+
},
|
| 363 |
+
{
|
| 364 |
+
"epoch": 1.4117647058823528,
|
| 365 |
+
"grad_norm": 3.204245090484619,
|
| 366 |
+
"learning_rate": 0.00014539904997395468,
|
| 367 |
+
"loss": 0.6842,
|
| 368 |
+
"num_input_tokens_seen": 38098,
|
| 369 |
+
"step": 45
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 1.4431372549019608,
|
| 373 |
+
"grad_norm": 4.535635471343994,
|
| 374 |
+
"learning_rate": 0.00014257792915650728,
|
| 375 |
+
"loss": 0.7039,
|
| 376 |
+
"num_input_tokens_seen": 39024,
|
| 377 |
+
"step": 46
|
| 378 |
+
},
|
| 379 |
+
{
|
| 380 |
+
"epoch": 1.4745098039215687,
|
| 381 |
+
"grad_norm": 5.812551021575928,
|
| 382 |
+
"learning_rate": 0.00013971478906347806,
|
| 383 |
+
"loss": 1.0178,
|
| 384 |
+
"num_input_tokens_seen": 39876,
|
| 385 |
+
"step": 47
|
| 386 |
+
},
|
| 387 |
+
{
|
| 388 |
+
"epoch": 1.5058823529411764,
|
| 389 |
+
"grad_norm": 5.7899169921875,
|
| 390 |
+
"learning_rate": 0.00013681245526846783,
|
| 391 |
+
"loss": 0.8895,
|
| 392 |
+
"num_input_tokens_seen": 40691,
|
| 393 |
+
"step": 48
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 1.5372549019607842,
|
| 397 |
+
"grad_norm": 4.779058933258057,
|
| 398 |
+
"learning_rate": 0.00013387379202452917,
|
| 399 |
+
"loss": 0.7015,
|
| 400 |
+
"num_input_tokens_seen": 41529,
|
| 401 |
+
"step": 49
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 1.5686274509803921,
|
| 405 |
+
"grad_norm": 4.17733907699585,
|
| 406 |
+
"learning_rate": 0.00013090169943749476,
|
| 407 |
+
"loss": 0.8385,
|
| 408 |
+
"num_input_tokens_seen": 42347,
|
| 409 |
+
"step": 50
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 1.6,
|
| 413 |
+
"grad_norm": 3.26069974899292,
|
| 414 |
+
"learning_rate": 0.00012789911060392294,
|
| 415 |
+
"loss": 0.6932,
|
| 416 |
+
"num_input_tokens_seen": 43170,
|
| 417 |
+
"step": 51
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 1.6313725490196078,
|
| 421 |
+
"grad_norm": 3.7764294147491455,
|
| 422 |
+
"learning_rate": 0.00012486898871648546,
|
| 423 |
+
"loss": 0.6722,
|
| 424 |
+
"num_input_tokens_seen": 44017,
|
| 425 |
+
"step": 52
|
| 426 |
+
},
|
| 427 |
+
{
|
| 428 |
+
"epoch": 1.6627450980392156,
|
| 429 |
+
"grad_norm": 5.631955146789551,
|
| 430 |
+
"learning_rate": 0.00012181432413965425,
|
| 431 |
+
"loss": 0.8225,
|
| 432 |
+
"num_input_tokens_seen": 44895,
|
| 433 |
+
"step": 53
|
| 434 |
+
},
|
| 435 |
+
{
|
| 436 |
+
"epoch": 1.6941176470588235,
|
| 437 |
+
"grad_norm": 3.0410749912261963,
|
| 438 |
+
"learning_rate": 0.00011873813145857249,
|
| 439 |
+
"loss": 0.5853,
|
| 440 |
+
"num_input_tokens_seen": 45780,
|
| 441 |
+
"step": 54
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 1.7254901960784315,
|
| 445 |
+
"grad_norm": 6.754289627075195,
|
| 446 |
+
"learning_rate": 0.00011564344650402312,
|
| 447 |
+
"loss": 0.8272,
|
| 448 |
+
"num_input_tokens_seen": 46623,
|
| 449 |
+
"step": 55
|
| 450 |
+
},
|
| 451 |
+
{
|
| 452 |
+
"epoch": 1.7568627450980392,
|
| 453 |
+
"grad_norm": 4.92588472366333,
|
| 454 |
+
"learning_rate": 0.00011253332335643046,
|
| 455 |
+
"loss": 0.588,
|
| 456 |
+
"num_input_tokens_seen": 47446,
|
| 457 |
+
"step": 56
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 1.788235294117647,
|
| 461 |
+
"grad_norm": 5.982916831970215,
|
| 462 |
+
"learning_rate": 0.00010941083133185143,
|
| 463 |
+
"loss": 0.9413,
|
| 464 |
+
"num_input_tokens_seen": 48260,
|
| 465 |
+
"step": 57
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 1.8196078431372549,
|
| 469 |
+
"grad_norm": 3.09069561958313,
|
| 470 |
+
"learning_rate": 0.00010627905195293135,
|
| 471 |
+
"loss": 0.7281,
|
| 472 |
+
"num_input_tokens_seen": 49095,
|
| 473 |
+
"step": 58
|
| 474 |
+
},
|
| 475 |
+
{
|
| 476 |
+
"epoch": 1.8509803921568628,
|
| 477 |
+
"grad_norm": 7.942086219787598,
|
| 478 |
+
"learning_rate": 0.00010314107590781284,
|
| 479 |
+
"loss": 0.8998,
|
| 480 |
+
"num_input_tokens_seen": 49948,
|
| 481 |
+
"step": 59
|
| 482 |
+
},
|
| 483 |
+
{
|
| 484 |
+
"epoch": 1.8823529411764706,
|
| 485 |
+
"grad_norm": 6.040829181671143,
|
| 486 |
+
"learning_rate": 0.0001,
|
| 487 |
+
"loss": 0.7494,
|
| 488 |
+
"num_input_tokens_seen": 50794,
|
| 489 |
+
"step": 60
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 1.9137254901960783,
|
| 493 |
+
"grad_norm": 5.524172782897949,
|
| 494 |
+
"learning_rate": 9.685892409218717e-05,
|
| 495 |
+
"loss": 1.1642,
|
| 496 |
+
"num_input_tokens_seen": 51649,
|
| 497 |
+
"step": 61
|
| 498 |
+
},
|
| 499 |
+
{
|
| 500 |
+
"epoch": 1.9450980392156862,
|
| 501 |
+
"grad_norm": 4.093544960021973,
|
| 502 |
+
"learning_rate": 9.372094804706867e-05,
|
| 503 |
+
"loss": 0.9137,
|
| 504 |
+
"num_input_tokens_seen": 52499,
|
| 505 |
+
"step": 62
|
| 506 |
+
},
|
| 507 |
+
{
|
| 508 |
+
"epoch": 1.9764705882352942,
|
| 509 |
+
"grad_norm": 3.3669676780700684,
|
| 510 |
+
"learning_rate": 9.058916866814858e-05,
|
| 511 |
+
"loss": 0.7343,
|
| 512 |
+
"num_input_tokens_seen": 53345,
|
| 513 |
+
"step": 63
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 2.007843137254902,
|
| 517 |
+
"grad_norm": 6.184525966644287,
|
| 518 |
+
"learning_rate": 8.746667664356956e-05,
|
| 519 |
+
"loss": 0.8992,
|
| 520 |
+
"num_input_tokens_seen": 54201,
|
| 521 |
+
"step": 64
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 2.0392156862745097,
|
| 525 |
+
"grad_norm": 4.793566703796387,
|
| 526 |
+
"learning_rate": 8.435655349597695e-05,
|
| 527 |
+
"loss": 0.6028,
|
| 528 |
+
"num_input_tokens_seen": 55036,
|
| 529 |
+
"step": 65
|
| 530 |
+
},
|
| 531 |
+
{
|
| 532 |
+
"epoch": 2.070588235294118,
|
| 533 |
+
"grad_norm": 4.015380859375,
|
| 534 |
+
"learning_rate": 8.126186854142752e-05,
|
| 535 |
+
"loss": 0.6597,
|
| 536 |
+
"num_input_tokens_seen": 55868,
|
| 537 |
+
"step": 66
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 2.1019607843137256,
|
| 541 |
+
"grad_norm": 2.2828500270843506,
|
| 542 |
+
"learning_rate": 7.818567586034575e-05,
|
| 543 |
+
"loss": 0.5288,
|
| 544 |
+
"num_input_tokens_seen": 56724,
|
| 545 |
+
"step": 67
|
| 546 |
+
},
|
| 547 |
+
{
|
| 548 |
+
"epoch": 2.1333333333333333,
|
| 549 |
+
"grad_norm": 3.3936123847961426,
|
| 550 |
+
"learning_rate": 7.513101128351454e-05,
|
| 551 |
+
"loss": 0.6818,
|
| 552 |
+
"num_input_tokens_seen": 57579,
|
| 553 |
+
"step": 68
|
| 554 |
+
},
|
| 555 |
+
{
|
| 556 |
+
"epoch": 2.164705882352941,
|
| 557 |
+
"grad_norm": 3.684924602508545,
|
| 558 |
+
"learning_rate": 7.210088939607708e-05,
|
| 559 |
+
"loss": 0.7798,
|
| 560 |
+
"num_input_tokens_seen": 58425,
|
| 561 |
+
"step": 69
|
| 562 |
+
},
|
| 563 |
+
{
|
| 564 |
+
"epoch": 2.196078431372549,
|
| 565 |
+
"grad_norm": 3.1493935585021973,
|
| 566 |
+
"learning_rate": 6.909830056250524e-05,
|
| 567 |
+
"loss": 0.7207,
|
| 568 |
+
"num_input_tokens_seen": 59270,
|
| 569 |
+
"step": 70
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 2.227450980392157,
|
| 573 |
+
"grad_norm": 5.103849411010742,
|
| 574 |
+
"learning_rate": 6.612620797547087e-05,
|
| 575 |
+
"loss": 0.6483,
|
| 576 |
+
"num_input_tokens_seen": 60127,
|
| 577 |
+
"step": 71
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 2.2588235294117647,
|
| 581 |
+
"grad_norm": 1.9273674488067627,
|
| 582 |
+
"learning_rate": 6.318754473153221e-05,
|
| 583 |
+
"loss": 0.5992,
|
| 584 |
+
"num_input_tokens_seen": 61059,
|
| 585 |
+
"step": 72
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 2.2901960784313724,
|
| 589 |
+
"grad_norm": 2.9266533851623535,
|
| 590 |
+
"learning_rate": 6.0285210936521955e-05,
|
| 591 |
+
"loss": 0.6952,
|
| 592 |
+
"num_input_tokens_seen": 61905,
|
| 593 |
+
"step": 73
|
| 594 |
+
},
|
| 595 |
+
{
|
| 596 |
+
"epoch": 2.3215686274509806,
|
| 597 |
+
"grad_norm": 2.3648922443389893,
|
| 598 |
+
"learning_rate": 5.7422070843492734e-05,
|
| 599 |
+
"loss": 0.5068,
|
| 600 |
+
"num_input_tokens_seen": 62745,
|
| 601 |
+
"step": 74
|
| 602 |
+
},
|
| 603 |
+
{
|
| 604 |
+
"epoch": 2.3529411764705883,
|
| 605 |
+
"grad_norm": 3.8562815189361572,
|
| 606 |
+
"learning_rate": 5.4600950026045326e-05,
|
| 607 |
+
"loss": 0.7024,
|
| 608 |
+
"num_input_tokens_seen": 63594,
|
| 609 |
+
"step": 75
|
| 610 |
+
},
|
| 611 |
+
{
|
| 612 |
+
"epoch": 2.384313725490196,
|
| 613 |
+
"grad_norm": 2.478416919708252,
|
| 614 |
+
"learning_rate": 5.182463258982846e-05,
|
| 615 |
+
"loss": 0.5721,
|
| 616 |
+
"num_input_tokens_seen": 64453,
|
| 617 |
+
"step": 76
|
| 618 |
+
},
|
| 619 |
+
{
|
| 620 |
+
"epoch": 2.4156862745098038,
|
| 621 |
+
"grad_norm": 2.117917776107788,
|
| 622 |
+
"learning_rate": 4.909585842496292e-05,
|
| 623 |
+
"loss": 0.4472,
|
| 624 |
+
"num_input_tokens_seen": 65284,
|
| 625 |
+
"step": 77
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 2.447058823529412,
|
| 629 |
+
"grad_norm": 2.4827864170074463,
|
| 630 |
+
"learning_rate": 4.641732050210036e-05,
|
| 631 |
+
"loss": 0.414,
|
| 632 |
+
"num_input_tokens_seen": 66110,
|
| 633 |
+
"step": 78
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 2.4784313725490197,
|
| 637 |
+
"grad_norm": 3.7768778800964355,
|
| 638 |
+
"learning_rate": 4.3791662214786934e-05,
|
| 639 |
+
"loss": 0.5808,
|
| 640 |
+
"num_input_tokens_seen": 66934,
|
| 641 |
+
"step": 79
|
| 642 |
+
},
|
| 643 |
+
{
|
| 644 |
+
"epoch": 2.5098039215686274,
|
| 645 |
+
"grad_norm": 3.4247841835021973,
|
| 646 |
+
"learning_rate": 4.12214747707527e-05,
|
| 647 |
+
"loss": 0.5447,
|
| 648 |
+
"num_input_tokens_seen": 67775,
|
| 649 |
+
"step": 80
|
| 650 |
+
},
|
| 651 |
+
{
|
| 652 |
+
"epoch": 2.541176470588235,
|
| 653 |
+
"grad_norm": 4.182628631591797,
|
| 654 |
+
"learning_rate": 3.8709294634702376e-05,
|
| 655 |
+
"loss": 0.4573,
|
| 656 |
+
"num_input_tokens_seen": 68630,
|
| 657 |
+
"step": 81
|
| 658 |
+
},
|
| 659 |
+
{
|
| 660 |
+
"epoch": 2.572549019607843,
|
| 661 |
+
"grad_norm": 4.045778274536133,
|
| 662 |
+
"learning_rate": 3.6257601025131026e-05,
|
| 663 |
+
"loss": 0.7857,
|
| 664 |
+
"num_input_tokens_seen": 69484,
|
| 665 |
+
"step": 82
|
| 666 |
+
},
|
| 667 |
+
{
|
| 668 |
+
"epoch": 2.603921568627451,
|
| 669 |
+
"grad_norm": 2.6151039600372314,
|
| 670 |
+
"learning_rate": 3.386881346763483e-05,
|
| 671 |
+
"loss": 0.7443,
|
| 672 |
+
"num_input_tokens_seen": 70355,
|
| 673 |
+
"step": 83
|
| 674 |
+
},
|
| 675 |
+
{
|
| 676 |
+
"epoch": 2.635294117647059,
|
| 677 |
+
"grad_norm": 3.3898870944976807,
|
| 678 |
+
"learning_rate": 3.154528940713113e-05,
|
| 679 |
+
"loss": 0.5147,
|
| 680 |
+
"num_input_tokens_seen": 71198,
|
| 681 |
+
"step": 84
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 2.6666666666666665,
|
| 685 |
+
"grad_norm": 1.8886942863464355,
|
| 686 |
+
"learning_rate": 2.9289321881345254e-05,
|
| 687 |
+
"loss": 0.3022,
|
| 688 |
+
"num_input_tokens_seen": 72040,
|
| 689 |
+
"step": 85
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 2.6980392156862747,
|
| 693 |
+
"grad_norm": 5.151848316192627,
|
| 694 |
+
"learning_rate": 2.7103137257858868e-05,
|
| 695 |
+
"loss": 0.3934,
|
| 696 |
+
"num_input_tokens_seen": 72907,
|
| 697 |
+
"step": 86
|
| 698 |
+
},
|
| 699 |
+
{
|
| 700 |
+
"epoch": 2.7294117647058824,
|
| 701 |
+
"grad_norm": 3.1100125312805176,
|
| 702 |
+
"learning_rate": 2.4988893036954043e-05,
|
| 703 |
+
"loss": 0.6222,
|
| 704 |
+
"num_input_tokens_seen": 73742,
|
| 705 |
+
"step": 87
|
| 706 |
+
},
|
| 707 |
+
{
|
| 708 |
+
"epoch": 2.76078431372549,
|
| 709 |
+
"grad_norm": 2.5638794898986816,
|
| 710 |
+
"learning_rate": 2.2948675722421086e-05,
|
| 711 |
+
"loss": 0.5721,
|
| 712 |
+
"num_input_tokens_seen": 74587,
|
| 713 |
+
"step": 88
|
| 714 |
+
},
|
| 715 |
+
{
|
| 716 |
+
"epoch": 2.792156862745098,
|
| 717 |
+
"grad_norm": 3.2768828868865967,
|
| 718 |
+
"learning_rate": 2.098449876243098e-05,
|
| 719 |
+
"loss": 0.5144,
|
| 720 |
+
"num_input_tokens_seen": 75433,
|
| 721 |
+
"step": 89
|
| 722 |
+
},
|
| 723 |
+
{
|
| 724 |
+
"epoch": 2.8235294117647056,
|
| 725 |
+
"grad_norm": 4.178157806396484,
|
| 726 |
+
"learning_rate": 1.9098300562505266e-05,
|
| 727 |
+
"loss": 0.463,
|
| 728 |
+
"num_input_tokens_seen": 76218,
|
| 729 |
+
"step": 90
|
| 730 |
+
},
|
| 731 |
+
{
|
| 732 |
+
"epoch": 2.854901960784314,
|
| 733 |
+
"grad_norm": 4.432765960693359,
|
| 734 |
+
"learning_rate": 1.7291942572543807e-05,
|
| 735 |
+
"loss": 0.6351,
|
| 736 |
+
"num_input_tokens_seen": 77053,
|
| 737 |
+
"step": 91
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 2.8862745098039215,
|
| 741 |
+
"grad_norm": 2.8439605236053467,
|
| 742 |
+
"learning_rate": 1.5567207449798515e-05,
|
| 743 |
+
"loss": 0.5897,
|
| 744 |
+
"num_input_tokens_seen": 77899,
|
| 745 |
+
"step": 92
|
| 746 |
+
},
|
| 747 |
+
{
|
| 748 |
+
"epoch": 2.9176470588235293,
|
| 749 |
+
"grad_norm": 3.0817153453826904,
|
| 750 |
+
"learning_rate": 1.3925797299605625e-05,
|
| 751 |
+
"loss": 0.6083,
|
| 752 |
+
"num_input_tokens_seen": 78767,
|
| 753 |
+
"step": 93
|
| 754 |
+
},
|
| 755 |
+
{
|
| 756 |
+
"epoch": 2.9490196078431374,
|
| 757 |
+
"grad_norm": 3.2820534706115723,
|
| 758 |
+
"learning_rate": 1.2369331995613643e-05,
|
| 759 |
+
"loss": 0.5075,
|
| 760 |
+
"num_input_tokens_seen": 79591,
|
| 761 |
+
"step": 94
|
| 762 |
+
},
|
| 763 |
+
{
|
| 764 |
+
"epoch": 2.980392156862745,
|
| 765 |
+
"grad_norm": 4.051931858062744,
|
| 766 |
+
"learning_rate": 1.0899347581163221e-05,
|
| 767 |
+
"loss": 0.4958,
|
| 768 |
+
"num_input_tokens_seen": 80422,
|
| 769 |
+
"step": 95
|
| 770 |
+
},
|
| 771 |
+
{
|
| 772 |
+
"epoch": 3.011764705882353,
|
| 773 |
+
"grad_norm": 3.6439077854156494,
|
| 774 |
+
"learning_rate": 9.517294753398042e-06,
|
| 775 |
+
"loss": 0.8383,
|
| 776 |
+
"num_input_tokens_seen": 81282,
|
| 777 |
+
"step": 96
|
| 778 |
+
},
|
| 779 |
+
{
|
| 780 |
+
"epoch": 3.0431372549019606,
|
| 781 |
+
"grad_norm": 3.559818983078003,
|
| 782 |
+
"learning_rate": 8.224537431601908e-06,
|
| 783 |
+
"loss": 0.5131,
|
| 784 |
+
"num_input_tokens_seen": 82101,
|
| 785 |
+
"step": 97
|
| 786 |
+
},
|
| 787 |
+
{
|
| 788 |
+
"epoch": 3.074509803921569,
|
| 789 |
+
"grad_norm": 2.2776846885681152,
|
| 790 |
+
"learning_rate": 7.022351411174866e-06,
|
| 791 |
+
"loss": 0.5896,
|
| 792 |
+
"num_input_tokens_seen": 82989,
|
| 793 |
+
"step": 98
|
| 794 |
+
},
|
| 795 |
+
{
|
| 796 |
+
"epoch": 3.1058823529411765,
|
| 797 |
+
"grad_norm": 2.8956410884857178,
|
| 798 |
+
"learning_rate": 5.911923104577455e-06,
|
| 799 |
+
"loss": 0.5902,
|
| 800 |
+
"num_input_tokens_seen": 83838,
|
| 801 |
+
"step": 99
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 3.1372549019607843,
|
| 805 |
+
"grad_norm": 2.3653640747070312,
|
| 806 |
+
"learning_rate": 4.8943483704846585e-06,
|
| 807 |
+
"loss": 0.278,
|
| 808 |
+
"num_input_tokens_seen": 84654,
|
| 809 |
+
"step": 100
|
| 810 |
+
},
|
| 811 |
+
{
|
| 812 |
+
"epoch": 3.168627450980392,
|
| 813 |
+
"grad_norm": 2.7463765144348145,
|
| 814 |
+
"learning_rate": 3.970631432305694e-06,
|
| 815 |
+
"loss": 0.4051,
|
| 816 |
+
"num_input_tokens_seen": 85493,
|
| 817 |
+
"step": 101
|
| 818 |
+
},
|
| 819 |
+
{
|
| 820 |
+
"epoch": 3.2,
|
| 821 |
+
"grad_norm": 1.9491956233978271,
|
| 822 |
+
"learning_rate": 3.141683887136904e-06,
|
| 823 |
+
"loss": 0.3255,
|
| 824 |
+
"num_input_tokens_seen": 86381,
|
| 825 |
+
"step": 102
|
| 826 |
+
},
|
| 827 |
+
{
|
| 828 |
+
"epoch": 3.231372549019608,
|
| 829 |
+
"grad_norm": 3.7543513774871826,
|
| 830 |
+
"learning_rate": 2.4083238061252678e-06,
|
| 831 |
+
"loss": 0.5123,
|
| 832 |
+
"num_input_tokens_seen": 87182,
|
| 833 |
+
"step": 103
|
| 834 |
+
},
|
| 835 |
+
{
|
| 836 |
+
"epoch": 3.2627450980392156,
|
| 837 |
+
"grad_norm": 2.68157958984375,
|
| 838 |
+
"learning_rate": 1.771274927131128e-06,
|
| 839 |
+
"loss": 0.5409,
|
| 840 |
+
"num_input_tokens_seen": 88059,
|
| 841 |
+
"step": 104
|
| 842 |
+
},
|
| 843 |
+
{
|
| 844 |
+
"epoch": 3.2941176470588234,
|
| 845 |
+
"grad_norm": 2.971251964569092,
|
| 846 |
+
"learning_rate": 1.231165940486234e-06,
|
| 847 |
+
"loss": 0.3435,
|
| 848 |
+
"num_input_tokens_seen": 88889,
|
| 849 |
+
"step": 105
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 3.3254901960784315,
|
| 853 |
+
"grad_norm": 2.606720209121704,
|
| 854 |
+
"learning_rate": 7.885298685522235e-07,
|
| 855 |
+
"loss": 0.5119,
|
| 856 |
+
"num_input_tokens_seen": 89747,
|
| 857 |
+
"step": 106
|
| 858 |
+
},
|
| 859 |
+
{
|
| 860 |
+
"epoch": 3.3568627450980393,
|
| 861 |
+
"grad_norm": 2.622124433517456,
|
| 862 |
+
"learning_rate": 4.438035396920004e-07,
|
| 863 |
+
"loss": 0.5565,
|
| 864 |
+
"num_input_tokens_seen": 90612,
|
| 865 |
+
"step": 107
|
| 866 |
+
},
|
| 867 |
+
{
|
| 868 |
+
"epoch": 3.388235294117647,
|
| 869 |
+
"grad_norm": 2.256873846054077,
|
| 870 |
+
"learning_rate": 1.973271571728441e-07,
|
| 871 |
+
"loss": 0.4164,
|
| 872 |
+
"num_input_tokens_seen": 91453,
|
| 873 |
+
"step": 108
|
| 874 |
+
},
|
| 875 |
+
{
|
| 876 |
+
"epoch": 3.4196078431372547,
|
| 877 |
+
"grad_norm": 3.2237167358398438,
|
| 878 |
+
"learning_rate": 4.934396342684e-08,
|
| 879 |
+
"loss": 0.5135,
|
| 880 |
+
"num_input_tokens_seen": 92304,
|
| 881 |
+
"step": 109
|
| 882 |
+
},
|
| 883 |
+
{
|
| 884 |
+
"epoch": 3.450980392156863,
|
| 885 |
+
"grad_norm": 2.807044267654419,
|
| 886 |
+
"learning_rate": 0.0002,
|
| 887 |
+
"loss": 0.4391,
|
| 888 |
+
"num_input_tokens_seen": 93130,
|
| 889 |
+
"step": 110
|
| 890 |
+
},
|
| 891 |
+
{
|
| 892 |
+
"epoch": 3.4823529411764707,
|
| 893 |
+
"grad_norm": 2.9154107570648193,
|
| 894 |
+
"learning_rate": 0.00019995065603657316,
|
| 895 |
+
"loss": 0.5719,
|
| 896 |
+
"num_input_tokens_seen": 93953,
|
| 897 |
+
"step": 111
|
| 898 |
+
},
|
| 899 |
+
{
|
| 900 |
+
"epoch": 3.5137254901960784,
|
| 901 |
+
"grad_norm": 3.265385150909424,
|
| 902 |
+
"learning_rate": 0.00019980267284282717,
|
| 903 |
+
"loss": 0.7463,
|
| 904 |
+
"num_input_tokens_seen": 94803,
|
| 905 |
+
"step": 112
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"epoch": 3.545098039215686,
|
| 909 |
+
"grad_norm": 5.992981910705566,
|
| 910 |
+
"learning_rate": 0.00019955619646030802,
|
| 911 |
+
"loss": 0.7756,
|
| 912 |
+
"num_input_tokens_seen": 95673,
|
| 913 |
+
"step": 113
|
| 914 |
+
},
|
| 915 |
+
{
|
| 916 |
+
"epoch": 3.576470588235294,
|
| 917 |
+
"grad_norm": 6.979043483734131,
|
| 918 |
+
"learning_rate": 0.0001992114701314478,
|
| 919 |
+
"loss": 0.5761,
|
| 920 |
+
"num_input_tokens_seen": 96559,
|
| 921 |
+
"step": 114
|
| 922 |
+
},
|
| 923 |
+
{
|
| 924 |
+
"epoch": 3.607843137254902,
|
| 925 |
+
"grad_norm": 9.418047904968262,
|
| 926 |
+
"learning_rate": 0.00019876883405951377,
|
| 927 |
+
"loss": 0.7796,
|
| 928 |
+
"num_input_tokens_seen": 97366,
|
| 929 |
+
"step": 115
|
| 930 |
+
},
|
| 931 |
+
{
|
| 932 |
+
"epoch": 3.6392156862745098,
|
| 933 |
+
"grad_norm": 3.6083357334136963,
|
| 934 |
+
"learning_rate": 0.00019822872507286888,
|
| 935 |
+
"loss": 0.3696,
|
| 936 |
+
"num_input_tokens_seen": 98197,
|
| 937 |
+
"step": 116
|
| 938 |
+
},
|
| 939 |
+
{
|
| 940 |
+
"epoch": 3.6705882352941175,
|
| 941 |
+
"grad_norm": 4.184770584106445,
|
| 942 |
+
"learning_rate": 0.00019759167619387476,
|
| 943 |
+
"loss": 0.4349,
|
| 944 |
+
"num_input_tokens_seen": 99019,
|
| 945 |
+
"step": 117
|
| 946 |
+
},
|
| 947 |
+
{
|
| 948 |
+
"epoch": 3.7019607843137257,
|
| 949 |
+
"grad_norm": 5.8201799392700195,
|
| 950 |
+
"learning_rate": 0.0001968583161128631,
|
| 951 |
+
"loss": 0.434,
|
| 952 |
+
"num_input_tokens_seen": 99866,
|
| 953 |
+
"step": 118
|
| 954 |
+
},
|
| 955 |
+
{
|
| 956 |
+
"epoch": 3.7333333333333334,
|
| 957 |
+
"grad_norm": 5.535106182098389,
|
| 958 |
+
"learning_rate": 0.0001960293685676943,
|
| 959 |
+
"loss": 0.6474,
|
| 960 |
+
"num_input_tokens_seen": 100723,
|
| 961 |
+
"step": 119
|
| 962 |
+
},
|
| 963 |
+
{
|
| 964 |
+
"epoch": 3.764705882352941,
|
| 965 |
+
"grad_norm": 3.3299312591552734,
|
| 966 |
+
"learning_rate": 0.00019510565162951537,
|
| 967 |
+
"loss": 0.4361,
|
| 968 |
+
"num_input_tokens_seen": 101581,
|
| 969 |
+
"step": 120
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 3.796078431372549,
|
| 973 |
+
"grad_norm": 7.6674323081970215,
|
| 974 |
+
"learning_rate": 0.00019408807689542257,
|
| 975 |
+
"loss": 0.575,
|
| 976 |
+
"num_input_tokens_seen": 102418,
|
| 977 |
+
"step": 121
|
| 978 |
+
},
|
| 979 |
+
{
|
| 980 |
+
"epoch": 3.8274509803921566,
|
| 981 |
+
"grad_norm": 7.189317226409912,
|
| 982 |
+
"learning_rate": 0.00019297764858882514,
|
| 983 |
+
"loss": 0.8572,
|
| 984 |
+
"num_input_tokens_seen": 103281,
|
| 985 |
+
"step": 122
|
| 986 |
+
},
|
| 987 |
+
{
|
| 988 |
+
"epoch": 3.8588235294117648,
|
| 989 |
+
"grad_norm": 4.600097179412842,
|
| 990 |
+
"learning_rate": 0.00019177546256839812,
|
| 991 |
+
"loss": 0.6253,
|
| 992 |
+
"num_input_tokens_seen": 104128,
|
| 993 |
+
"step": 123
|
| 994 |
+
},
|
| 995 |
+
{
|
| 996 |
+
"epoch": 3.8901960784313725,
|
| 997 |
+
"grad_norm": 6.0382585525512695,
|
| 998 |
+
"learning_rate": 0.00019048270524660193,
|
| 999 |
+
"loss": 0.4465,
|
| 1000 |
+
"num_input_tokens_seen": 104972,
|
| 1001 |
+
"step": 124
|
| 1002 |
+
},
|
| 1003 |
+
{
|
| 1004 |
+
"epoch": 3.9215686274509802,
|
| 1005 |
+
"grad_norm": 5.221591949462891,
|
| 1006 |
+
"learning_rate": 0.0001891006524188368,
|
| 1007 |
+
"loss": 0.6236,
|
| 1008 |
+
"num_input_tokens_seen": 105833,
|
| 1009 |
+
"step": 125
|
| 1010 |
+
},
|
| 1011 |
+
{
|
| 1012 |
+
"epoch": 3.9529411764705884,
|
| 1013 |
+
"grad_norm": 4.43485164642334,
|
| 1014 |
+
"learning_rate": 0.0001876306680043864,
|
| 1015 |
+
"loss": 0.6026,
|
| 1016 |
+
"num_input_tokens_seen": 106656,
|
| 1017 |
+
"step": 126
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 3.984313725490196,
|
| 1021 |
+
"grad_norm": 4.633317947387695,
|
| 1022 |
+
"learning_rate": 0.0001860742027003944,
|
| 1023 |
+
"loss": 0.4891,
|
| 1024 |
+
"num_input_tokens_seen": 107479,
|
| 1025 |
+
"step": 127
|
| 1026 |
+
},
|
| 1027 |
+
{
|
| 1028 |
+
"epoch": 4.015686274509804,
|
| 1029 |
+
"grad_norm": 2.710853338241577,
|
| 1030 |
+
"learning_rate": 0.00018443279255020155,
|
| 1031 |
+
"loss": 0.4361,
|
| 1032 |
+
"num_input_tokens_seen": 108376,
|
| 1033 |
+
"step": 128
|
| 1034 |
+
},
|
| 1035 |
+
{
|
| 1036 |
+
"epoch": 4.047058823529412,
|
| 1037 |
+
"grad_norm": 3.0707015991210938,
|
| 1038 |
+
"learning_rate": 0.0001827080574274562,
|
| 1039 |
+
"loss": 0.4198,
|
| 1040 |
+
"num_input_tokens_seen": 109228,
|
| 1041 |
+
"step": 129
|
| 1042 |
+
},
|
| 1043 |
+
{
|
| 1044 |
+
"epoch": 4.078431372549019,
|
| 1045 |
+
"grad_norm": 2.8015506267547607,
|
| 1046 |
+
"learning_rate": 0.0001809016994374947,
|
| 1047 |
+
"loss": 0.4515,
|
| 1048 |
+
"num_input_tokens_seen": 110061,
|
| 1049 |
+
"step": 130
|
| 1050 |
+
},
|
| 1051 |
+
{
|
| 1052 |
+
"epoch": 4.109803921568627,
|
| 1053 |
+
"grad_norm": 3.3442440032958984,
|
| 1054 |
+
"learning_rate": 0.00017901550123756906,
|
| 1055 |
+
"loss": 0.3318,
|
| 1056 |
+
"num_input_tokens_seen": 110927,
|
| 1057 |
+
"step": 131
|
| 1058 |
+
},
|
| 1059 |
+
{
|
| 1060 |
+
"epoch": 4.141176470588236,
|
| 1061 |
+
"grad_norm": 2.747676372528076,
|
| 1062 |
+
"learning_rate": 0.00017705132427757895,
|
| 1063 |
+
"loss": 0.4279,
|
| 1064 |
+
"num_input_tokens_seen": 111786,
|
| 1065 |
+
"step": 132
|
| 1066 |
+
},
|
| 1067 |
+
{
|
| 1068 |
+
"epoch": 4.172549019607843,
|
| 1069 |
+
"grad_norm": 3.85593581199646,
|
| 1070 |
+
"learning_rate": 0.00017501110696304596,
|
| 1071 |
+
"loss": 0.3526,
|
| 1072 |
+
"num_input_tokens_seen": 112632,
|
| 1073 |
+
"step": 133
|
| 1074 |
+
},
|
| 1075 |
+
{
|
| 1076 |
+
"epoch": 4.203921568627451,
|
| 1077 |
+
"grad_norm": 3.7865078449249268,
|
| 1078 |
+
"learning_rate": 0.00017289686274214118,
|
| 1079 |
+
"loss": 0.4617,
|
| 1080 |
+
"num_input_tokens_seen": 113486,
|
| 1081 |
+
"step": 134
|
| 1082 |
+
},
|
| 1083 |
+
{
|
| 1084 |
+
"epoch": 4.235294117647059,
|
| 1085 |
+
"grad_norm": 2.6525180339813232,
|
| 1086 |
+
"learning_rate": 0.00017071067811865476,
|
| 1087 |
+
"loss": 0.2388,
|
| 1088 |
+
"num_input_tokens_seen": 114336,
|
| 1089 |
+
"step": 135
|
| 1090 |
+
},
|
| 1091 |
+
{
|
| 1092 |
+
"epoch": 4.266666666666667,
|
| 1093 |
+
"grad_norm": 10.199384689331055,
|
| 1094 |
+
"learning_rate": 0.00016845471059286887,
|
| 1095 |
+
"loss": 0.4286,
|
| 1096 |
+
"num_input_tokens_seen": 115202,
|
| 1097 |
+
"step": 136
|
| 1098 |
+
},
|
| 1099 |
+
{
|
| 1100 |
+
"epoch": 4.298039215686274,
|
| 1101 |
+
"grad_norm": 3.65986967086792,
|
| 1102 |
+
"learning_rate": 0.00016613118653236518,
|
| 1103 |
+
"loss": 0.478,
|
| 1104 |
+
"num_input_tokens_seen": 116036,
|
| 1105 |
+
"step": 137
|
| 1106 |
+
},
|
| 1107 |
+
{
|
| 1108 |
+
"epoch": 4.329411764705882,
|
| 1109 |
+
"grad_norm": 2.575523614883423,
|
| 1110 |
+
"learning_rate": 0.000163742398974869,
|
| 1111 |
+
"loss": 0.229,
|
| 1112 |
+
"num_input_tokens_seen": 116868,
|
| 1113 |
+
"step": 138
|
| 1114 |
+
},
|
| 1115 |
+
{
|
| 1116 |
+
"epoch": 4.36078431372549,
|
| 1117 |
+
"grad_norm": 5.756189346313477,
|
| 1118 |
+
"learning_rate": 0.00016129070536529766,
|
| 1119 |
+
"loss": 0.5141,
|
| 1120 |
+
"num_input_tokens_seen": 117745,
|
| 1121 |
+
"step": 139
|
| 1122 |
+
},
|
| 1123 |
+
{
|
| 1124 |
+
"epoch": 4.392156862745098,
|
| 1125 |
+
"grad_norm": 3.640237331390381,
|
| 1126 |
+
"learning_rate": 0.0001587785252292473,
|
| 1127 |
+
"loss": 0.2679,
|
| 1128 |
+
"num_input_tokens_seen": 118582,
|
| 1129 |
+
"step": 140
|
| 1130 |
+
},
|
| 1131 |
+
{
|
| 1132 |
+
"epoch": 4.423529411764706,
|
| 1133 |
+
"grad_norm": 4.511353015899658,
|
| 1134 |
+
"learning_rate": 0.00015620833778521304,
|
| 1135 |
+
"loss": 0.381,
|
| 1136 |
+
"num_input_tokens_seen": 119445,
|
| 1137 |
+
"step": 141
|
| 1138 |
+
},
|
| 1139 |
+
{
|
| 1140 |
+
"epoch": 4.454901960784314,
|
| 1141 |
+
"grad_norm": 12.773442268371582,
|
| 1142 |
+
"learning_rate": 0.00015358267949789966,
|
| 1143 |
+
"loss": 0.5296,
|
| 1144 |
+
"num_input_tokens_seen": 120241,
|
| 1145 |
+
"step": 142
|
| 1146 |
+
},
|
| 1147 |
+
{
|
| 1148 |
+
"epoch": 4.486274509803922,
|
| 1149 |
+
"grad_norm": 3.347665548324585,
|
| 1150 |
+
"learning_rate": 0.00015090414157503714,
|
| 1151 |
+
"loss": 0.3427,
|
| 1152 |
+
"num_input_tokens_seen": 121096,
|
| 1153 |
+
"step": 143
|
| 1154 |
+
},
|
| 1155 |
+
{
|
| 1156 |
+
"epoch": 4.517647058823529,
|
| 1157 |
+
"grad_norm": 3.0967466831207275,
|
| 1158 |
+
"learning_rate": 0.00014817536741017158,
|
| 1159 |
+
"loss": 0.3916,
|
| 1160 |
+
"num_input_tokens_seen": 121910,
|
| 1161 |
+
"step": 144
|
| 1162 |
+
},
|
| 1163 |
+
{
|
| 1164 |
+
"epoch": 4.549019607843137,
|
| 1165 |
+
"grad_norm": 2.6861841678619385,
|
| 1166 |
+
"learning_rate": 0.00014539904997395468,
|
| 1167 |
+
"loss": 0.3054,
|
| 1168 |
+
"num_input_tokens_seen": 122762,
|
| 1169 |
+
"step": 145
|
| 1170 |
+
},
|
| 1171 |
+
{
|
| 1172 |
+
"epoch": 4.580392156862745,
|
| 1173 |
+
"grad_norm": 4.615218162536621,
|
| 1174 |
+
"learning_rate": 0.0001425779291565073,
|
| 1175 |
+
"loss": 0.3923,
|
| 1176 |
+
"num_input_tokens_seen": 123593,
|
| 1177 |
+
"step": 146
|
| 1178 |
+
},
|
| 1179 |
+
{
|
| 1180 |
+
"epoch": 4.6117647058823525,
|
| 1181 |
+
"grad_norm": 6.789853572845459,
|
| 1182 |
+
"learning_rate": 0.00013971478906347803,
|
| 1183 |
+
"loss": 0.438,
|
| 1184 |
+
"num_input_tokens_seen": 124446,
|
| 1185 |
+
"step": 147
|
| 1186 |
+
},
|
| 1187 |
+
{
|
| 1188 |
+
"epoch": 4.643137254901961,
|
| 1189 |
+
"grad_norm": 4.128298282623291,
|
| 1190 |
+
"learning_rate": 0.00013681245526846777,
|
| 1191 |
+
"loss": 0.4208,
|
| 1192 |
+
"num_input_tokens_seen": 125313,
|
| 1193 |
+
"step": 148
|
| 1194 |
+
},
|
| 1195 |
+
{
|
| 1196 |
+
"epoch": 4.674509803921569,
|
| 1197 |
+
"grad_norm": 3.4282140731811523,
|
| 1198 |
+
"learning_rate": 0.00013387379202452917,
|
| 1199 |
+
"loss": 0.3717,
|
| 1200 |
+
"num_input_tokens_seen": 126184,
|
| 1201 |
+
"step": 149
|
| 1202 |
+
},
|
| 1203 |
+
{
|
| 1204 |
+
"epoch": 4.705882352941177,
|
| 1205 |
+
"grad_norm": 6.779294967651367,
|
| 1206 |
+
"learning_rate": 0.00013090169943749476,
|
| 1207 |
+
"loss": 0.4152,
|
| 1208 |
+
"num_input_tokens_seen": 127026,
|
| 1209 |
+
"step": 150
|
| 1210 |
+
},
|
| 1211 |
+
{
|
| 1212 |
+
"epoch": 4.737254901960784,
|
| 1213 |
+
"grad_norm": 3.086122989654541,
|
| 1214 |
+
"learning_rate": 0.00012789911060392294,
|
| 1215 |
+
"loss": 0.3011,
|
| 1216 |
+
"num_input_tokens_seen": 127883,
|
| 1217 |
+
"step": 151
|
| 1218 |
+
},
|
| 1219 |
+
{
|
| 1220 |
+
"epoch": 4.768627450980392,
|
| 1221 |
+
"grad_norm": 5.97057580947876,
|
| 1222 |
+
"learning_rate": 0.0001248689887164855,
|
| 1223 |
+
"loss": 0.3705,
|
| 1224 |
+
"num_input_tokens_seen": 128689,
|
| 1225 |
+
"step": 152
|
| 1226 |
+
},
|
| 1227 |
+
{
|
| 1228 |
+
"epoch": 4.8,
|
| 1229 |
+
"grad_norm": 4.796477317810059,
|
| 1230 |
+
"learning_rate": 0.00012181432413965421,
|
| 1231 |
+
"loss": 0.4362,
|
| 1232 |
+
"num_input_tokens_seen": 129520,
|
| 1233 |
+
"step": 153
|
| 1234 |
+
},
|
| 1235 |
+
{
|
| 1236 |
+
"epoch": 4.8313725490196076,
|
| 1237 |
+
"grad_norm": 3.3298208713531494,
|
| 1238 |
+
"learning_rate": 0.00011873813145857249,
|
| 1239 |
+
"loss": 0.4988,
|
| 1240 |
+
"num_input_tokens_seen": 130406,
|
| 1241 |
+
"step": 154
|
| 1242 |
+
},
|
| 1243 |
+
{
|
| 1244 |
+
"epoch": 4.862745098039216,
|
| 1245 |
+
"grad_norm": 3.887026071548462,
|
| 1246 |
+
"learning_rate": 0.00011564344650402312,
|
| 1247 |
+
"loss": 0.5444,
|
| 1248 |
+
"num_input_tokens_seen": 131276,
|
| 1249 |
+
"step": 155
|
| 1250 |
+
},
|
| 1251 |
+
{
|
| 1252 |
+
"epoch": 4.894117647058824,
|
| 1253 |
+
"grad_norm": 6.220418453216553,
|
| 1254 |
+
"learning_rate": 0.00011253332335643046,
|
| 1255 |
+
"loss": 0.4078,
|
| 1256 |
+
"num_input_tokens_seen": 132090,
|
| 1257 |
+
"step": 156
|
| 1258 |
+
},
|
| 1259 |
+
{
|
| 1260 |
+
"epoch": 4.925490196078432,
|
| 1261 |
+
"grad_norm": 2.757842779159546,
|
| 1262 |
+
"learning_rate": 0.00010941083133185146,
|
| 1263 |
+
"loss": 0.3539,
|
| 1264 |
+
"num_input_tokens_seen": 132909,
|
| 1265 |
+
"step": 157
|
| 1266 |
+
},
|
| 1267 |
+
{
|
| 1268 |
+
"epoch": 4.956862745098039,
|
| 1269 |
+
"grad_norm": 2.275514602661133,
|
| 1270 |
+
"learning_rate": 0.00010627905195293135,
|
| 1271 |
+
"loss": 0.3512,
|
| 1272 |
+
"num_input_tokens_seen": 133799,
|
| 1273 |
+
"step": 158
|
| 1274 |
+
},
|
| 1275 |
+
{
|
| 1276 |
+
"epoch": 4.988235294117647,
|
| 1277 |
+
"grad_norm": 3.4296388626098633,
|
| 1278 |
+
"learning_rate": 0.00010314107590781284,
|
| 1279 |
+
"loss": 0.3426,
|
| 1280 |
+
"num_input_tokens_seen": 134640,
|
| 1281 |
+
"step": 159
|
| 1282 |
+
},
|
| 1283 |
+
{
|
| 1284 |
+
"epoch": 5.019607843137255,
|
| 1285 |
+
"grad_norm": 1.8311214447021484,
|
| 1286 |
+
"learning_rate": 0.0001,
|
| 1287 |
+
"loss": 0.1619,
|
| 1288 |
+
"num_input_tokens_seen": 135491,
|
| 1289 |
+
"step": 160
|
| 1290 |
+
},
|
| 1291 |
+
{
|
| 1292 |
+
"epoch": 5.050980392156863,
|
| 1293 |
+
"grad_norm": 2.676769495010376,
|
| 1294 |
+
"learning_rate": 9.685892409218724e-05,
|
| 1295 |
+
"loss": 0.221,
|
| 1296 |
+
"num_input_tokens_seen": 136317,
|
| 1297 |
+
"step": 161
|
| 1298 |
+
},
|
| 1299 |
+
{
|
| 1300 |
+
"epoch": 5.08235294117647,
|
| 1301 |
+
"grad_norm": 1.8601126670837402,
|
| 1302 |
+
"learning_rate": 9.372094804706867e-05,
|
| 1303 |
+
"loss": 0.2427,
|
| 1304 |
+
"num_input_tokens_seen": 137191,
|
| 1305 |
+
"step": 162
|
| 1306 |
+
},
|
| 1307 |
+
{
|
| 1308 |
+
"epoch": 5.113725490196078,
|
| 1309 |
+
"grad_norm": 1.8501461744308472,
|
| 1310 |
+
"learning_rate": 9.058916866814858e-05,
|
| 1311 |
+
"loss": 0.2443,
|
| 1312 |
+
"num_input_tokens_seen": 138029,
|
| 1313 |
+
"step": 163
|
| 1314 |
+
},
|
| 1315 |
+
{
|
| 1316 |
+
"epoch": 5.145098039215687,
|
| 1317 |
+
"grad_norm": 1.612574815750122,
|
| 1318 |
+
"learning_rate": 8.746667664356956e-05,
|
| 1319 |
+
"loss": 0.1391,
|
| 1320 |
+
"num_input_tokens_seen": 138848,
|
| 1321 |
+
"step": 164
|
| 1322 |
+
},
|
| 1323 |
+
{
|
| 1324 |
+
"epoch": 5.176470588235294,
|
| 1325 |
+
"grad_norm": 1.7896589040756226,
|
| 1326 |
+
"learning_rate": 8.435655349597684e-05,
|
| 1327 |
+
"loss": 0.0778,
|
| 1328 |
+
"num_input_tokens_seen": 139648,
|
| 1329 |
+
"step": 165
|
| 1330 |
+
},
|
| 1331 |
+
{
|
| 1332 |
+
"epoch": 5.207843137254902,
|
| 1333 |
+
"grad_norm": 3.172090530395508,
|
| 1334 |
+
"learning_rate": 8.126186854142752e-05,
|
| 1335 |
+
"loss": 0.2737,
|
| 1336 |
+
"num_input_tokens_seen": 140500,
|
| 1337 |
+
"step": 166
|
| 1338 |
+
},
|
| 1339 |
+
{
|
| 1340 |
+
"epoch": 5.23921568627451,
|
| 1341 |
+
"grad_norm": 2.280182361602783,
|
| 1342 |
+
"learning_rate": 7.818567586034581e-05,
|
| 1343 |
+
"loss": 0.18,
|
| 1344 |
+
"num_input_tokens_seen": 141331,
|
| 1345 |
+
"step": 167
|
| 1346 |
+
},
|
| 1347 |
+
{
|
| 1348 |
+
"epoch": 5.270588235294118,
|
| 1349 |
+
"grad_norm": 3.10487699508667,
|
| 1350 |
+
"learning_rate": 7.513101128351459e-05,
|
| 1351 |
+
"loss": 0.2636,
|
| 1352 |
+
"num_input_tokens_seen": 142188,
|
| 1353 |
+
"step": 168
|
| 1354 |
+
},
|
| 1355 |
+
{
|
| 1356 |
+
"epoch": 5.301960784313725,
|
| 1357 |
+
"grad_norm": 2.16359543800354,
|
| 1358 |
+
"learning_rate": 7.210088939607707e-05,
|
| 1359 |
+
"loss": 0.1788,
|
| 1360 |
+
"num_input_tokens_seen": 143005,
|
| 1361 |
+
"step": 169
|
| 1362 |
+
},
|
| 1363 |
+
{
|
| 1364 |
+
"epoch": 5.333333333333333,
|
| 1365 |
+
"grad_norm": 3.690769910812378,
|
| 1366 |
+
"learning_rate": 6.909830056250524e-05,
|
| 1367 |
+
"loss": 0.1271,
|
| 1368 |
+
"num_input_tokens_seen": 143796,
|
| 1369 |
+
"step": 170
|
| 1370 |
+
},
|
| 1371 |
+
{
|
| 1372 |
+
"epoch": 5.364705882352941,
|
| 1373 |
+
"grad_norm": 4.808859348297119,
|
| 1374 |
+
"learning_rate": 6.612620797547091e-05,
|
| 1375 |
+
"loss": 0.1235,
|
| 1376 |
+
"num_input_tokens_seen": 144594,
|
| 1377 |
+
"step": 171
|
| 1378 |
+
},
|
| 1379 |
+
{
|
| 1380 |
+
"epoch": 5.396078431372549,
|
| 1381 |
+
"grad_norm": 2.4017834663391113,
|
| 1382 |
+
"learning_rate": 6.318754473153218e-05,
|
| 1383 |
+
"loss": 0.1417,
|
| 1384 |
+
"num_input_tokens_seen": 145432,
|
| 1385 |
+
"step": 172
|
| 1386 |
+
},
|
| 1387 |
+
{
|
| 1388 |
+
"epoch": 5.427450980392157,
|
| 1389 |
+
"grad_norm": 10.861905097961426,
|
| 1390 |
+
"learning_rate": 6.0285210936521976e-05,
|
| 1391 |
+
"loss": 0.3499,
|
| 1392 |
+
"num_input_tokens_seen": 146307,
|
| 1393 |
+
"step": 173
|
| 1394 |
+
},
|
| 1395 |
+
{
|
| 1396 |
+
"epoch": 5.458823529411765,
|
| 1397 |
+
"grad_norm": 6.508179664611816,
|
| 1398 |
+
"learning_rate": 5.742207084349277e-05,
|
| 1399 |
+
"loss": 0.2636,
|
| 1400 |
+
"num_input_tokens_seen": 147159,
|
| 1401 |
+
"step": 174
|
| 1402 |
+
},
|
| 1403 |
+
{
|
| 1404 |
+
"epoch": 5.490196078431373,
|
| 1405 |
+
"grad_norm": 3.551328659057617,
|
| 1406 |
+
"learning_rate": 5.4600950026045285e-05,
|
| 1407 |
+
"loss": 0.1685,
|
| 1408 |
+
"num_input_tokens_seen": 147990,
|
| 1409 |
+
"step": 175
|
| 1410 |
+
},
|
| 1411 |
+
{
|
| 1412 |
+
"epoch": 5.52156862745098,
|
| 1413 |
+
"grad_norm": 5.636049747467041,
|
| 1414 |
+
"learning_rate": 5.182463258982846e-05,
|
| 1415 |
+
"loss": 0.2804,
|
| 1416 |
+
"num_input_tokens_seen": 148782,
|
| 1417 |
+
"step": 176
|
| 1418 |
+
},
|
| 1419 |
+
{
|
| 1420 |
+
"epoch": 5.552941176470588,
|
| 1421 |
+
"grad_norm": 4.598341941833496,
|
| 1422 |
+
"learning_rate": 4.909585842496292e-05,
|
| 1423 |
+
"loss": 0.3087,
|
| 1424 |
+
"num_input_tokens_seen": 149687,
|
| 1425 |
+
"step": 177
|
| 1426 |
+
},
|
| 1427 |
+
{
|
| 1428 |
+
"epoch": 5.584313725490196,
|
| 1429 |
+
"grad_norm": 5.29741907119751,
|
| 1430 |
+
"learning_rate": 4.6417320502100316e-05,
|
| 1431 |
+
"loss": 0.3299,
|
| 1432 |
+
"num_input_tokens_seen": 150565,
|
| 1433 |
+
"step": 178
|
| 1434 |
+
},
|
| 1435 |
+
{
|
| 1436 |
+
"epoch": 5.6156862745098035,
|
| 1437 |
+
"grad_norm": 3.7548561096191406,
|
| 1438 |
+
"learning_rate": 4.379166221478697e-05,
|
| 1439 |
+
"loss": 0.3047,
|
| 1440 |
+
"num_input_tokens_seen": 151419,
|
| 1441 |
+
"step": 179
|
| 1442 |
+
},
|
| 1443 |
+
{
|
| 1444 |
+
"epoch": 5.647058823529412,
|
| 1445 |
+
"grad_norm": 2.995479106903076,
|
| 1446 |
+
"learning_rate": 4.12214747707527e-05,
|
| 1447 |
+
"loss": 0.2234,
|
| 1448 |
+
"num_input_tokens_seen": 152249,
|
| 1449 |
+
"step": 180
|
| 1450 |
+
},
|
| 1451 |
+
{
|
| 1452 |
+
"epoch": 5.67843137254902,
|
| 1453 |
+
"grad_norm": 2.391935110092163,
|
| 1454 |
+
"learning_rate": 3.8709294634702376e-05,
|
| 1455 |
+
"loss": 0.1819,
|
| 1456 |
+
"num_input_tokens_seen": 153097,
|
| 1457 |
+
"step": 181
|
| 1458 |
+
},
|
| 1459 |
+
{
|
| 1460 |
+
"epoch": 5.709803921568628,
|
| 1461 |
+
"grad_norm": 2.5566658973693848,
|
| 1462 |
+
"learning_rate": 3.625760102513099e-05,
|
| 1463 |
+
"loss": 0.2642,
|
| 1464 |
+
"num_input_tokens_seen": 153970,
|
| 1465 |
+
"step": 182
|
| 1466 |
+
},
|
| 1467 |
+
{
|
| 1468 |
+
"epoch": 5.741176470588235,
|
| 1469 |
+
"grad_norm": 2.3486950397491455,
|
| 1470 |
+
"learning_rate": 3.386881346763483e-05,
|
| 1471 |
+
"loss": 0.1399,
|
| 1472 |
+
"num_input_tokens_seen": 154821,
|
| 1473 |
+
"step": 183
|
| 1474 |
+
},
|
| 1475 |
+
{
|
| 1476 |
+
"epoch": 5.772549019607843,
|
| 1477 |
+
"grad_norm": 3.2803895473480225,
|
| 1478 |
+
"learning_rate": 3.15452894071312e-05,
|
| 1479 |
+
"loss": 0.2416,
|
| 1480 |
+
"num_input_tokens_seen": 155654,
|
| 1481 |
+
"step": 184
|
| 1482 |
+
},
|
| 1483 |
+
{
|
| 1484 |
+
"epoch": 5.803921568627451,
|
| 1485 |
+
"grad_norm": 3.5313189029693604,
|
| 1486 |
+
"learning_rate": 2.9289321881345254e-05,
|
| 1487 |
+
"loss": 0.1808,
|
| 1488 |
+
"num_input_tokens_seen": 156464,
|
| 1489 |
+
"step": 185
|
| 1490 |
+
},
|
| 1491 |
+
{
|
| 1492 |
+
"epoch": 5.8352941176470585,
|
| 1493 |
+
"grad_norm": 2.8547775745391846,
|
| 1494 |
+
"learning_rate": 2.7103137257858868e-05,
|
| 1495 |
+
"loss": 0.2565,
|
| 1496 |
+
"num_input_tokens_seen": 157360,
|
| 1497 |
+
"step": 186
|
| 1498 |
+
},
|
| 1499 |
+
{
|
| 1500 |
+
"epoch": 5.866666666666667,
|
| 1501 |
+
"grad_norm": 2.3218977451324463,
|
| 1502 |
+
"learning_rate": 2.4988893036954043e-05,
|
| 1503 |
+
"loss": 0.1691,
|
| 1504 |
+
"num_input_tokens_seen": 158193,
|
| 1505 |
+
"step": 187
|
| 1506 |
+
},
|
| 1507 |
+
{
|
| 1508 |
+
"epoch": 5.898039215686275,
|
| 1509 |
+
"grad_norm": 2.2196223735809326,
|
| 1510 |
+
"learning_rate": 2.2948675722421032e-05,
|
| 1511 |
+
"loss": 0.4082,
|
| 1512 |
+
"num_input_tokens_seen": 159122,
|
| 1513 |
+
"step": 188
|
| 1514 |
+
},
|
| 1515 |
+
{
|
| 1516 |
+
"epoch": 5.929411764705883,
|
| 1517 |
+
"grad_norm": 2.5707294940948486,
|
| 1518 |
+
"learning_rate": 2.098449876243096e-05,
|
| 1519 |
+
"loss": 0.2091,
|
| 1520 |
+
"num_input_tokens_seen": 159987,
|
| 1521 |
+
"step": 189
|
| 1522 |
+
},
|
| 1523 |
+
{
|
| 1524 |
+
"epoch": 5.96078431372549,
|
| 1525 |
+
"grad_norm": 3.849001407623291,
|
| 1526 |
+
"learning_rate": 1.909830056250529e-05,
|
| 1527 |
+
"loss": 0.258,
|
| 1528 |
+
"num_input_tokens_seen": 160876,
|
| 1529 |
+
"step": 190
|
| 1530 |
+
},
|
| 1531 |
+
{
|
| 1532 |
+
"epoch": 5.992156862745098,
|
| 1533 |
+
"grad_norm": 7.267693042755127,
|
| 1534 |
+
"learning_rate": 1.7291942572543807e-05,
|
| 1535 |
+
"loss": 0.3389,
|
| 1536 |
+
"num_input_tokens_seen": 161713,
|
| 1537 |
+
"step": 191
|
| 1538 |
+
},
|
| 1539 |
+
{
|
| 1540 |
+
"epoch": 6.023529411764706,
|
| 1541 |
+
"grad_norm": 2.107445240020752,
|
| 1542 |
+
"learning_rate": 1.5567207449798495e-05,
|
| 1543 |
+
"loss": 0.1413,
|
| 1544 |
+
"num_input_tokens_seen": 162530,
|
| 1545 |
+
"step": 192
|
| 1546 |
+
},
|
| 1547 |
+
{
|
| 1548 |
+
"epoch": 6.0549019607843135,
|
| 1549 |
+
"grad_norm": 1.9133341312408447,
|
| 1550 |
+
"learning_rate": 1.3925797299605625e-05,
|
| 1551 |
+
"loss": 0.098,
|
| 1552 |
+
"num_input_tokens_seen": 163339,
|
| 1553 |
+
"step": 193
|
| 1554 |
+
},
|
| 1555 |
+
{
|
| 1556 |
+
"epoch": 6.086274509803921,
|
| 1557 |
+
"grad_norm": 2.2540628910064697,
|
| 1558 |
+
"learning_rate": 1.2369331995613665e-05,
|
| 1559 |
+
"loss": 0.1409,
|
| 1560 |
+
"num_input_tokens_seen": 164183,
|
| 1561 |
+
"step": 194
|
| 1562 |
+
},
|
| 1563 |
+
{
|
| 1564 |
+
"epoch": 6.117647058823529,
|
| 1565 |
+
"grad_norm": 1.5692024230957031,
|
| 1566 |
+
"learning_rate": 1.08993475811632e-05,
|
| 1567 |
+
"loss": 0.1951,
|
| 1568 |
+
"num_input_tokens_seen": 165009,
|
| 1569 |
+
"step": 195
|
| 1570 |
+
},
|
| 1571 |
+
{
|
| 1572 |
+
"epoch": 6.149019607843138,
|
| 1573 |
+
"grad_norm": 1.885223150253296,
|
| 1574 |
+
"learning_rate": 9.517294753398064e-06,
|
| 1575 |
+
"loss": 0.1493,
|
| 1576 |
+
"num_input_tokens_seen": 165856,
|
| 1577 |
+
"step": 196
|
| 1578 |
+
},
|
| 1579 |
+
{
|
| 1580 |
+
"epoch": 6.180392156862745,
|
| 1581 |
+
"grad_norm": 1.3335139751434326,
|
| 1582 |
+
"learning_rate": 8.224537431601908e-06,
|
| 1583 |
+
"loss": 0.054,
|
| 1584 |
+
"num_input_tokens_seen": 166686,
|
| 1585 |
+
"step": 197
|
| 1586 |
+
},
|
| 1587 |
+
{
|
| 1588 |
+
"epoch": 6.211764705882353,
|
| 1589 |
+
"grad_norm": 2.255988359451294,
|
| 1590 |
+
"learning_rate": 7.022351411174855e-06,
|
| 1591 |
+
"loss": 0.1965,
|
| 1592 |
+
"num_input_tokens_seen": 167544,
|
| 1593 |
+
"step": 198
|
| 1594 |
+
},
|
| 1595 |
+
{
|
| 1596 |
+
"epoch": 6.243137254901961,
|
| 1597 |
+
"grad_norm": 4.721761703491211,
|
| 1598 |
+
"learning_rate": 5.911923104577455e-06,
|
| 1599 |
+
"loss": 0.1935,
|
| 1600 |
+
"num_input_tokens_seen": 168348,
|
| 1601 |
+
"step": 199
|
| 1602 |
+
},
|
| 1603 |
+
{
|
| 1604 |
+
"epoch": 6.2745098039215685,
|
| 1605 |
+
"grad_norm": 2.2551510334014893,
|
| 1606 |
+
"learning_rate": 4.8943483704846585e-06,
|
| 1607 |
+
"loss": 0.1393,
|
| 1608 |
+
"num_input_tokens_seen": 169231,
|
| 1609 |
+
"step": 200
|
| 1610 |
+
},
|
| 1611 |
+
{
|
| 1612 |
+
"epoch": 6.305882352941176,
|
| 1613 |
+
"grad_norm": 1.8611195087432861,
|
| 1614 |
+
"learning_rate": 3.970631432305694e-06,
|
| 1615 |
+
"loss": 0.1288,
|
| 1616 |
+
"num_input_tokens_seen": 170060,
|
| 1617 |
+
"step": 201
|
| 1618 |
+
},
|
| 1619 |
+
{
|
| 1620 |
+
"epoch": 6.337254901960784,
|
| 1621 |
+
"grad_norm": 2.192089796066284,
|
| 1622 |
+
"learning_rate": 3.141683887136904e-06,
|
| 1623 |
+
"loss": 0.2037,
|
| 1624 |
+
"num_input_tokens_seen": 170917,
|
| 1625 |
+
"step": 202
|
| 1626 |
+
},
|
| 1627 |
+
{
|
| 1628 |
+
"epoch": 6.368627450980393,
|
| 1629 |
+
"grad_norm": 1.2144159078598022,
|
| 1630 |
+
"learning_rate": 2.4083238061252678e-06,
|
| 1631 |
+
"loss": 0.0774,
|
| 1632 |
+
"num_input_tokens_seen": 171774,
|
| 1633 |
+
"step": 203
|
| 1634 |
+
},
|
| 1635 |
+
{
|
| 1636 |
+
"epoch": 6.4,
|
| 1637 |
+
"grad_norm": 1.9125508069992065,
|
| 1638 |
+
"learning_rate": 1.771274927131139e-06,
|
| 1639 |
+
"loss": 0.1388,
|
| 1640 |
+
"num_input_tokens_seen": 172589,
|
| 1641 |
+
"step": 204
|
| 1642 |
+
},
|
| 1643 |
+
{
|
| 1644 |
+
"epoch": 6.431372549019608,
|
| 1645 |
+
"grad_norm": 1.6493868827819824,
|
| 1646 |
+
"learning_rate": 1.231165940486223e-06,
|
| 1647 |
+
"loss": 0.1192,
|
| 1648 |
+
"num_input_tokens_seen": 173418,
|
| 1649 |
+
"step": 205
|
| 1650 |
+
},
|
| 1651 |
+
{
|
| 1652 |
+
"epoch": 6.462745098039216,
|
| 1653 |
+
"grad_norm": 1.91011643409729,
|
| 1654 |
+
"learning_rate": 7.885298685522235e-07,
|
| 1655 |
+
"loss": 0.0885,
|
| 1656 |
+
"num_input_tokens_seen": 174236,
|
| 1657 |
+
"step": 206
|
| 1658 |
+
},
|
| 1659 |
+
{
|
| 1660 |
+
"epoch": 6.4941176470588236,
|
| 1661 |
+
"grad_norm": 1.8174355030059814,
|
| 1662 |
+
"learning_rate": 4.438035396920115e-07,
|
| 1663 |
+
"loss": 0.2875,
|
| 1664 |
+
"num_input_tokens_seen": 175172,
|
| 1665 |
+
"step": 207
|
| 1666 |
+
},
|
| 1667 |
+
{
|
| 1668 |
+
"epoch": 6.525490196078431,
|
| 1669 |
+
"grad_norm": 1.7092390060424805,
|
| 1670 |
+
"learning_rate": 1.973271571728441e-07,
|
| 1671 |
+
"loss": 0.1039,
|
| 1672 |
+
"num_input_tokens_seen": 176023,
|
| 1673 |
+
"step": 208
|
| 1674 |
+
},
|
| 1675 |
+
{
|
| 1676 |
+
"epoch": 6.556862745098039,
|
| 1677 |
+
"grad_norm": 1.8284764289855957,
|
| 1678 |
+
"learning_rate": 4.934396342684e-08,
|
| 1679 |
+
"loss": 0.1365,
|
| 1680 |
+
"num_input_tokens_seen": 176906,
|
| 1681 |
+
"step": 209
|
| 1682 |
+
},
|
| 1683 |
+
{
|
| 1684 |
+
"epoch": 6.588235294117647,
|
| 1685 |
+
"grad_norm": 1.697880506515503,
|
| 1686 |
+
"learning_rate": 0.0002,
|
| 1687 |
+
"loss": 0.1889,
|
| 1688 |
+
"num_input_tokens_seen": 177795,
|
| 1689 |
+
"step": 210
|
| 1690 |
+
},
|
| 1691 |
+
{
|
| 1692 |
+
"epoch": 6.6196078431372545,
|
| 1693 |
+
"grad_norm": 1.8329994678497314,
|
| 1694 |
+
"learning_rate": 0.00019995065603657314,
|
| 1695 |
+
"loss": 0.2207,
|
| 1696 |
+
"num_input_tokens_seen": 178672,
|
| 1697 |
+
"step": 211
|
| 1698 |
+
},
|
| 1699 |
+
{
|
| 1700 |
+
"epoch": 6.650980392156863,
|
| 1701 |
+
"grad_norm": 2.528137683868408,
|
| 1702 |
+
"learning_rate": 0.00019980267284282717,
|
| 1703 |
+
"loss": 0.1294,
|
| 1704 |
+
"num_input_tokens_seen": 179466,
|
| 1705 |
+
"step": 212
|
| 1706 |
+
},
|
| 1707 |
+
{
|
| 1708 |
+
"epoch": 6.682352941176471,
|
| 1709 |
+
"grad_norm": 5.707077503204346,
|
| 1710 |
+
"learning_rate": 0.00019955619646030802,
|
| 1711 |
+
"loss": 0.1878,
|
| 1712 |
+
"num_input_tokens_seen": 180332,
|
| 1713 |
+
"step": 213
|
| 1714 |
+
},
|
| 1715 |
+
{
|
| 1716 |
+
"epoch": 6.713725490196079,
|
| 1717 |
+
"grad_norm": 5.38962459564209,
|
| 1718 |
+
"learning_rate": 0.0001992114701314478,
|
| 1719 |
+
"loss": 0.1539,
|
| 1720 |
+
"num_input_tokens_seen": 181169,
|
| 1721 |
+
"step": 214
|
| 1722 |
+
},
|
| 1723 |
+
{
|
| 1724 |
+
"epoch": 6.745098039215686,
|
| 1725 |
+
"grad_norm": 8.556888580322266,
|
| 1726 |
+
"learning_rate": 0.00019876883405951377,
|
| 1727 |
+
"loss": 0.3257,
|
| 1728 |
+
"num_input_tokens_seen": 182059,
|
| 1729 |
+
"step": 215
|
| 1730 |
+
},
|
| 1731 |
+
{
|
| 1732 |
+
"epoch": 6.776470588235294,
|
| 1733 |
+
"grad_norm": 5.112634658813477,
|
| 1734 |
+
"learning_rate": 0.00019822872507286888,
|
| 1735 |
+
"loss": 0.1682,
|
| 1736 |
+
"num_input_tokens_seen": 182890,
|
| 1737 |
+
"step": 216
|
| 1738 |
+
},
|
| 1739 |
+
{
|
| 1740 |
+
"epoch": 6.807843137254902,
|
| 1741 |
+
"grad_norm": 5.386922359466553,
|
| 1742 |
+
"learning_rate": 0.00019759167619387476,
|
| 1743 |
+
"loss": 0.1355,
|
| 1744 |
+
"num_input_tokens_seen": 183734,
|
| 1745 |
+
"step": 217
|
| 1746 |
+
},
|
| 1747 |
+
{
|
| 1748 |
+
"epoch": 6.8392156862745095,
|
| 1749 |
+
"grad_norm": 9.67380142211914,
|
| 1750 |
+
"learning_rate": 0.0001968583161128631,
|
| 1751 |
+
"loss": 0.1565,
|
| 1752 |
+
"num_input_tokens_seen": 184542,
|
| 1753 |
+
"step": 218
|
| 1754 |
+
},
|
| 1755 |
+
{
|
| 1756 |
+
"epoch": 6.870588235294118,
|
| 1757 |
+
"grad_norm": 4.442196369171143,
|
| 1758 |
+
"learning_rate": 0.00019602936856769434,
|
| 1759 |
+
"loss": 0.1822,
|
| 1760 |
+
"num_input_tokens_seen": 185420,
|
| 1761 |
+
"step": 219
|
| 1762 |
+
},
|
| 1763 |
+
{
|
| 1764 |
+
"epoch": 6.901960784313726,
|
| 1765 |
+
"grad_norm": 6.283408164978027,
|
| 1766 |
+
"learning_rate": 0.0001951056516295154,
|
| 1767 |
+
"loss": 0.2803,
|
| 1768 |
+
"num_input_tokens_seen": 186278,
|
| 1769 |
+
"step": 220
|
| 1770 |
+
},
|
| 1771 |
+
{
|
| 1772 |
+
"epoch": 6.933333333333334,
|
| 1773 |
+
"grad_norm": 2.322974920272827,
|
| 1774 |
+
"learning_rate": 0.0001940880768954225,
|
| 1775 |
+
"loss": 0.175,
|
| 1776 |
+
"num_input_tokens_seen": 187146,
|
| 1777 |
+
"step": 221
|
| 1778 |
+
},
|
| 1779 |
+
{
|
| 1780 |
+
"epoch": 6.964705882352941,
|
| 1781 |
+
"grad_norm": 4.757282733917236,
|
| 1782 |
+
"learning_rate": 0.00019297764858882514,
|
| 1783 |
+
"loss": 0.2458,
|
| 1784 |
+
"num_input_tokens_seen": 187998,
|
| 1785 |
+
"step": 222
|
| 1786 |
+
},
|
| 1787 |
+
{
|
| 1788 |
+
"epoch": 6.996078431372549,
|
| 1789 |
+
"grad_norm": 10.94787883758545,
|
| 1790 |
+
"learning_rate": 0.00019177546256839812,
|
| 1791 |
+
"loss": 0.4605,
|
| 1792 |
+
"num_input_tokens_seen": 188820,
|
| 1793 |
+
"step": 223
|
| 1794 |
+
},
|
| 1795 |
+
{
|
| 1796 |
+
"epoch": 7.027450980392157,
|
| 1797 |
+
"grad_norm": 3.9081947803497314,
|
| 1798 |
+
"learning_rate": 0.00019048270524660193,
|
| 1799 |
+
"loss": 0.1243,
|
| 1800 |
+
"num_input_tokens_seen": 189615,
|
| 1801 |
+
"step": 224
|
| 1802 |
+
},
|
| 1803 |
+
{
|
| 1804 |
+
"epoch": 7.0588235294117645,
|
| 1805 |
+
"grad_norm": 4.866150856018066,
|
| 1806 |
+
"learning_rate": 0.0001891006524188368,
|
| 1807 |
+
"loss": 0.2121,
|
| 1808 |
+
"num_input_tokens_seen": 190498,
|
| 1809 |
+
"step": 225
|
| 1810 |
+
},
|
| 1811 |
+
{
|
| 1812 |
+
"epoch": 7.090196078431372,
|
| 1813 |
+
"grad_norm": 2.8364100456237793,
|
| 1814 |
+
"learning_rate": 0.00018763066800438636,
|
| 1815 |
+
"loss": 0.2427,
|
| 1816 |
+
"num_input_tokens_seen": 191385,
|
| 1817 |
+
"step": 226
|
| 1818 |
+
},
|
| 1819 |
+
{
|
| 1820 |
+
"epoch": 7.12156862745098,
|
| 1821 |
+
"grad_norm": 1.5343717336654663,
|
| 1822 |
+
"learning_rate": 0.0001860742027003944,
|
| 1823 |
+
"loss": 0.0782,
|
| 1824 |
+
"num_input_tokens_seen": 192218,
|
| 1825 |
+
"step": 227
|
| 1826 |
+
},
|
| 1827 |
+
{
|
| 1828 |
+
"epoch": 7.152941176470589,
|
| 1829 |
+
"grad_norm": 2.824655771255493,
|
| 1830 |
+
"learning_rate": 0.0001844327925502015,
|
| 1831 |
+
"loss": 0.0852,
|
| 1832 |
+
"num_input_tokens_seen": 193056,
|
| 1833 |
+
"step": 228
|
| 1834 |
+
},
|
| 1835 |
+
{
|
| 1836 |
+
"epoch": 7.184313725490196,
|
| 1837 |
+
"grad_norm": 6.053825378417969,
|
| 1838 |
+
"learning_rate": 0.0001827080574274562,
|
| 1839 |
+
"loss": 0.2932,
|
| 1840 |
+
"num_input_tokens_seen": 193874,
|
| 1841 |
+
"step": 229
|
| 1842 |
+
},
|
| 1843 |
+
{
|
| 1844 |
+
"epoch": 7.215686274509804,
|
| 1845 |
+
"grad_norm": 7.972029685974121,
|
| 1846 |
+
"learning_rate": 0.0001809016994374948,
|
| 1847 |
+
"loss": 0.1712,
|
| 1848 |
+
"num_input_tokens_seen": 194758,
|
| 1849 |
+
"step": 230
|
| 1850 |
+
},
|
| 1851 |
+
{
|
| 1852 |
+
"epoch": 7.247058823529412,
|
| 1853 |
+
"grad_norm": 3.326019287109375,
|
| 1854 |
+
"learning_rate": 0.00017901550123756906,
|
| 1855 |
+
"loss": 0.1383,
|
| 1856 |
+
"num_input_tokens_seen": 195658,
|
| 1857 |
+
"step": 231
|
| 1858 |
+
},
|
| 1859 |
+
{
|
| 1860 |
+
"epoch": 7.2784313725490195,
|
| 1861 |
+
"grad_norm": 2.4085988998413086,
|
| 1862 |
+
"learning_rate": 0.000177051324277579,
|
| 1863 |
+
"loss": 0.0777,
|
| 1864 |
+
"num_input_tokens_seen": 196482,
|
| 1865 |
+
"step": 232
|
| 1866 |
+
},
|
| 1867 |
+
{
|
| 1868 |
+
"epoch": 7.309803921568627,
|
| 1869 |
+
"grad_norm": 4.651546001434326,
|
| 1870 |
+
"learning_rate": 0.00017501110696304596,
|
| 1871 |
+
"loss": 0.1553,
|
| 1872 |
+
"num_input_tokens_seen": 197329,
|
| 1873 |
+
"step": 233
|
| 1874 |
+
},
|
| 1875 |
+
{
|
| 1876 |
+
"epoch": 7.341176470588235,
|
| 1877 |
+
"grad_norm": 2.4471681118011475,
|
| 1878 |
+
"learning_rate": 0.00017289686274214112,
|
| 1879 |
+
"loss": 0.1341,
|
| 1880 |
+
"num_input_tokens_seen": 198158,
|
| 1881 |
+
"step": 234
|
| 1882 |
+
},
|
| 1883 |
+
{
|
| 1884 |
+
"epoch": 7.372549019607844,
|
| 1885 |
+
"grad_norm": 4.855953216552734,
|
| 1886 |
+
"learning_rate": 0.00017071067811865476,
|
| 1887 |
+
"loss": 0.081,
|
| 1888 |
+
"num_input_tokens_seen": 198961,
|
| 1889 |
+
"step": 235
|
| 1890 |
+
},
|
| 1891 |
+
{
|
| 1892 |
+
"epoch": 7.403921568627451,
|
| 1893 |
+
"grad_norm": 6.432670593261719,
|
| 1894 |
+
"learning_rate": 0.00016845471059286893,
|
| 1895 |
+
"loss": 0.0946,
|
| 1896 |
+
"num_input_tokens_seen": 199788,
|
| 1897 |
+
"step": 236
|
| 1898 |
+
},
|
| 1899 |
+
{
|
| 1900 |
+
"epoch": 7.435294117647059,
|
| 1901 |
+
"grad_norm": 4.775556564331055,
|
| 1902 |
+
"learning_rate": 0.00016613118653236518,
|
| 1903 |
+
"loss": 0.1548,
|
| 1904 |
+
"num_input_tokens_seen": 200637,
|
| 1905 |
+
"step": 237
|
| 1906 |
+
},
|
| 1907 |
+
{
|
| 1908 |
+
"epoch": 7.466666666666667,
|
| 1909 |
+
"grad_norm": 4.532850742340088,
|
| 1910 |
+
"learning_rate": 0.0001637423989748689,
|
| 1911 |
+
"loss": 0.0952,
|
| 1912 |
+
"num_input_tokens_seen": 201482,
|
| 1913 |
+
"step": 238
|
| 1914 |
+
},
|
| 1915 |
+
{
|
| 1916 |
+
"epoch": 7.4980392156862745,
|
| 1917 |
+
"grad_norm": 7.549116134643555,
|
| 1918 |
+
"learning_rate": 0.00016129070536529766,
|
| 1919 |
+
"loss": 0.2452,
|
| 1920 |
+
"num_input_tokens_seen": 202333,
|
| 1921 |
+
"step": 239
|
| 1922 |
+
},
|
| 1923 |
+
{
|
| 1924 |
+
"epoch": 7.529411764705882,
|
| 1925 |
+
"grad_norm": 3.5515332221984863,
|
| 1926 |
+
"learning_rate": 0.00015877852522924726,
|
| 1927 |
+
"loss": 0.1033,
|
| 1928 |
+
"num_input_tokens_seen": 203151,
|
| 1929 |
+
"step": 240
|
| 1930 |
+
},
|
| 1931 |
+
{
|
| 1932 |
+
"epoch": 7.56078431372549,
|
| 1933 |
+
"grad_norm": 4.602539539337158,
|
| 1934 |
+
"learning_rate": 0.00015620833778521304,
|
| 1935 |
+
"loss": 0.1349,
|
| 1936 |
+
"num_input_tokens_seen": 204022,
|
| 1937 |
+
"step": 241
|
| 1938 |
+
},
|
| 1939 |
+
{
|
| 1940 |
+
"epoch": 7.592156862745098,
|
| 1941 |
+
"grad_norm": 2.6608591079711914,
|
| 1942 |
+
"learning_rate": 0.00015358267949789971,
|
| 1943 |
+
"loss": 0.1057,
|
| 1944 |
+
"num_input_tokens_seen": 204856,
|
| 1945 |
+
"step": 242
|
| 1946 |
+
},
|
| 1947 |
+
{
|
| 1948 |
+
"epoch": 7.623529411764705,
|
| 1949 |
+
"grad_norm": 5.953851699829102,
|
| 1950 |
+
"learning_rate": 0.00015090414157503714,
|
| 1951 |
+
"loss": 0.168,
|
| 1952 |
+
"num_input_tokens_seen": 205751,
|
| 1953 |
+
"step": 243
|
| 1954 |
+
},
|
| 1955 |
+
{
|
| 1956 |
+
"epoch": 7.654901960784314,
|
| 1957 |
+
"grad_norm": 2.4022793769836426,
|
| 1958 |
+
"learning_rate": 0.00014817536741017158,
|
| 1959 |
+
"loss": 0.1534,
|
| 1960 |
+
"num_input_tokens_seen": 206614,
|
| 1961 |
+
"step": 244
|
| 1962 |
+
},
|
| 1963 |
+
{
|
| 1964 |
+
"epoch": 7.686274509803922,
|
| 1965 |
+
"grad_norm": 5.277859210968018,
|
| 1966 |
+
"learning_rate": 0.00014539904997395468,
|
| 1967 |
+
"loss": 0.1876,
|
| 1968 |
+
"num_input_tokens_seen": 207442,
|
| 1969 |
+
"step": 245
|
| 1970 |
+
},
|
| 1971 |
+
{
|
| 1972 |
+
"epoch": 7.7176470588235295,
|
| 1973 |
+
"grad_norm": 3.6555447578430176,
|
| 1974 |
+
"learning_rate": 0.0001425779291565073,
|
| 1975 |
+
"loss": 0.1528,
|
| 1976 |
+
"num_input_tokens_seen": 208268,
|
| 1977 |
+
"step": 246
|
| 1978 |
+
},
|
| 1979 |
+
{
|
| 1980 |
+
"epoch": 7.749019607843137,
|
| 1981 |
+
"grad_norm": 13.82836627960205,
|
| 1982 |
+
"learning_rate": 0.00013971478906347803,
|
| 1983 |
+
"loss": 0.2893,
|
| 1984 |
+
"num_input_tokens_seen": 209161,
|
| 1985 |
+
"step": 247
|
| 1986 |
+
},
|
| 1987 |
+
{
|
| 1988 |
+
"epoch": 7.780392156862745,
|
| 1989 |
+
"grad_norm": 4.631089687347412,
|
| 1990 |
+
"learning_rate": 0.00013681245526846785,
|
| 1991 |
+
"loss": 0.1996,
|
| 1992 |
+
"num_input_tokens_seen": 209987,
|
| 1993 |
+
"step": 248
|
| 1994 |
+
},
|
| 1995 |
+
{
|
| 1996 |
+
"epoch": 7.811764705882353,
|
| 1997 |
+
"grad_norm": 5.084930419921875,
|
| 1998 |
+
"learning_rate": 0.00013387379202452922,
|
| 1999 |
+
"loss": 0.2305,
|
| 2000 |
+
"num_input_tokens_seen": 210827,
|
| 2001 |
+
"step": 249
|
| 2002 |
+
},
|
| 2003 |
+
{
|
| 2004 |
+
"epoch": 7.8431372549019605,
|
| 2005 |
+
"grad_norm": 4.121197700500488,
|
| 2006 |
+
"learning_rate": 0.00013090169943749463,
|
| 2007 |
+
"loss": 0.3338,
|
| 2008 |
+
"num_input_tokens_seen": 211698,
|
| 2009 |
+
"step": 250
|
| 2010 |
+
},
|
| 2011 |
+
{
|
| 2012 |
+
"epoch": 7.874509803921569,
|
| 2013 |
+
"grad_norm": 3.6635348796844482,
|
| 2014 |
+
"learning_rate": 0.0001278991106039229,
|
| 2015 |
+
"loss": 0.2121,
|
| 2016 |
+
"num_input_tokens_seen": 212549,
|
| 2017 |
+
"step": 251
|
| 2018 |
+
},
|
| 2019 |
+
{
|
| 2020 |
+
"epoch": 7.905882352941177,
|
| 2021 |
+
"grad_norm": 2.271726369857788,
|
| 2022 |
+
"learning_rate": 0.0001248689887164855,
|
| 2023 |
+
"loss": 0.0888,
|
| 2024 |
+
"num_input_tokens_seen": 213388,
|
| 2025 |
+
"step": 252
|
| 2026 |
+
},
|
| 2027 |
+
{
|
| 2028 |
+
"epoch": 7.9372549019607845,
|
| 2029 |
+
"grad_norm": 2.883363962173462,
|
| 2030 |
+
"learning_rate": 0.00012181432413965421,
|
| 2031 |
+
"loss": 0.2263,
|
| 2032 |
+
"num_input_tokens_seen": 214226,
|
| 2033 |
+
"step": 253
|
| 2034 |
+
},
|
| 2035 |
+
{
|
| 2036 |
+
"epoch": 7.968627450980392,
|
| 2037 |
+
"grad_norm": 5.223812580108643,
|
| 2038 |
+
"learning_rate": 0.00011873813145857249,
|
| 2039 |
+
"loss": 0.1085,
|
| 2040 |
+
"num_input_tokens_seen": 215089,
|
| 2041 |
+
"step": 254
|
| 2042 |
+
},
|
| 2043 |
+
{
|
| 2044 |
+
"epoch": 8.0,
|
| 2045 |
+
"grad_norm": 3.1294803619384766,
|
| 2046 |
+
"learning_rate": 0.00011564344650402304,
|
| 2047 |
+
"loss": 0.2069,
|
| 2048 |
+
"num_input_tokens_seen": 215904,
|
| 2049 |
+
"step": 255
|
| 2050 |
+
},
|
| 2051 |
+
{
|
| 2052 |
+
"epoch": 8.031372549019608,
|
| 2053 |
+
"grad_norm": 3.5736420154571533,
|
| 2054 |
+
"learning_rate": 0.00011253332335643046,
|
| 2055 |
+
"loss": 0.0774,
|
| 2056 |
+
"num_input_tokens_seen": 216721,
|
| 2057 |
+
"step": 256
|
| 2058 |
+
},
|
| 2059 |
+
{
|
| 2060 |
+
"epoch": 8.062745098039215,
|
| 2061 |
+
"grad_norm": 1.6127935647964478,
|
| 2062 |
+
"learning_rate": 0.00010941083133185139,
|
| 2063 |
+
"loss": 0.0487,
|
| 2064 |
+
"num_input_tokens_seen": 217568,
|
| 2065 |
+
"step": 257
|
| 2066 |
+
},
|
| 2067 |
+
{
|
| 2068 |
+
"epoch": 8.094117647058823,
|
| 2069 |
+
"grad_norm": 1.9943934679031372,
|
| 2070 |
+
"learning_rate": 0.00010627905195293135,
|
| 2071 |
+
"loss": 0.049,
|
| 2072 |
+
"num_input_tokens_seen": 218393,
|
| 2073 |
+
"step": 258
|
| 2074 |
+
},
|
| 2075 |
+
{
|
| 2076 |
+
"epoch": 8.125490196078431,
|
| 2077 |
+
"grad_norm": 5.851587772369385,
|
| 2078 |
+
"learning_rate": 0.00010314107590781291,
|
| 2079 |
+
"loss": 0.121,
|
| 2080 |
+
"num_input_tokens_seen": 219230,
|
| 2081 |
+
"step": 259
|
| 2082 |
+
},
|
| 2083 |
+
{
|
| 2084 |
+
"epoch": 8.156862745098039,
|
| 2085 |
+
"grad_norm": 2.693629026412964,
|
| 2086 |
+
"learning_rate": 0.0001,
|
| 2087 |
+
"loss": 0.0664,
|
| 2088 |
+
"num_input_tokens_seen": 220048,
|
| 2089 |
+
"step": 260
|
| 2090 |
+
},
|
| 2091 |
+
{
|
| 2092 |
+
"epoch": 8.188235294117646,
|
| 2093 |
+
"grad_norm": 6.576751708984375,
|
| 2094 |
+
"learning_rate": 9.685892409218724e-05,
|
| 2095 |
+
"loss": 0.0818,
|
| 2096 |
+
"num_input_tokens_seen": 220906,
|
| 2097 |
+
"step": 261
|
| 2098 |
+
},
|
| 2099 |
+
{
|
| 2100 |
+
"epoch": 8.219607843137254,
|
| 2101 |
+
"grad_norm": 1.8238303661346436,
|
| 2102 |
+
"learning_rate": 9.372094804706867e-05,
|
| 2103 |
+
"loss": 0.0977,
|
| 2104 |
+
"num_input_tokens_seen": 221795,
|
| 2105 |
+
"step": 262
|
| 2106 |
+
},
|
| 2107 |
+
{
|
| 2108 |
+
"epoch": 8.250980392156862,
|
| 2109 |
+
"grad_norm": 2.1661157608032227,
|
| 2110 |
+
"learning_rate": 9.058916866814851e-05,
|
| 2111 |
+
"loss": 0.0617,
|
| 2112 |
+
"num_input_tokens_seen": 222644,
|
| 2113 |
+
"step": 263
|
| 2114 |
+
},
|
| 2115 |
+
{
|
| 2116 |
+
"epoch": 8.282352941176471,
|
| 2117 |
+
"grad_norm": 3.1537587642669678,
|
| 2118 |
+
"learning_rate": 8.746667664356956e-05,
|
| 2119 |
+
"loss": 0.1102,
|
| 2120 |
+
"num_input_tokens_seen": 223465,
|
| 2121 |
+
"step": 264
|
| 2122 |
+
},
|
| 2123 |
+
{
|
| 2124 |
+
"epoch": 8.313725490196079,
|
| 2125 |
+
"grad_norm": 12.85554027557373,
|
| 2126 |
+
"learning_rate": 8.435655349597699e-05,
|
| 2127 |
+
"loss": 0.1478,
|
| 2128 |
+
"num_input_tokens_seen": 224302,
|
| 2129 |
+
"step": 265
|
| 2130 |
+
},
|
| 2131 |
+
{
|
| 2132 |
+
"epoch": 8.345098039215687,
|
| 2133 |
+
"grad_norm": 4.586164474487305,
|
| 2134 |
+
"learning_rate": 8.126186854142752e-05,
|
| 2135 |
+
"loss": 0.2202,
|
| 2136 |
+
"num_input_tokens_seen": 225154,
|
| 2137 |
+
"step": 266
|
| 2138 |
+
},
|
| 2139 |
+
{
|
| 2140 |
+
"epoch": 8.376470588235295,
|
| 2141 |
+
"grad_norm": 3.9367291927337646,
|
| 2142 |
+
"learning_rate": 7.818567586034566e-05,
|
| 2143 |
+
"loss": 0.0682,
|
| 2144 |
+
"num_input_tokens_seen": 226040,
|
| 2145 |
+
"step": 267
|
| 2146 |
+
},
|
| 2147 |
+
{
|
| 2148 |
+
"epoch": 8.407843137254902,
|
| 2149 |
+
"grad_norm": 2.0368969440460205,
|
| 2150 |
+
"learning_rate": 7.513101128351452e-05,
|
| 2151 |
+
"loss": 0.0402,
|
| 2152 |
+
"num_input_tokens_seen": 226847,
|
| 2153 |
+
"step": 268
|
| 2154 |
+
},
|
| 2155 |
+
{
|
| 2156 |
+
"epoch": 8.43921568627451,
|
| 2157 |
+
"grad_norm": 1.0436691045761108,
|
| 2158 |
+
"learning_rate": 7.210088939607714e-05,
|
| 2159 |
+
"loss": 0.0185,
|
| 2160 |
+
"num_input_tokens_seen": 227680,
|
| 2161 |
+
"step": 269
|
| 2162 |
+
},
|
| 2163 |
+
{
|
| 2164 |
+
"epoch": 8.470588235294118,
|
| 2165 |
+
"grad_norm": 1.8092098236083984,
|
| 2166 |
+
"learning_rate": 6.909830056250524e-05,
|
| 2167 |
+
"loss": 0.0442,
|
| 2168 |
+
"num_input_tokens_seen": 228543,
|
| 2169 |
+
"step": 270
|
| 2170 |
+
},
|
| 2171 |
+
{
|
| 2172 |
+
"epoch": 8.501960784313725,
|
| 2173 |
+
"grad_norm": 1.526930332183838,
|
| 2174 |
+
"learning_rate": 6.612620797547091e-05,
|
| 2175 |
+
"loss": 0.0362,
|
| 2176 |
+
"num_input_tokens_seen": 229373,
|
| 2177 |
+
"step": 271
|
| 2178 |
+
},
|
| 2179 |
+
{
|
| 2180 |
+
"epoch": 8.533333333333333,
|
| 2181 |
+
"grad_norm": 1.8258460760116577,
|
| 2182 |
+
"learning_rate": 6.318754473153218e-05,
|
| 2183 |
+
"loss": 0.0457,
|
| 2184 |
+
"num_input_tokens_seen": 230190,
|
| 2185 |
+
"step": 272
|
| 2186 |
+
},
|
| 2187 |
+
{
|
| 2188 |
+
"epoch": 8.564705882352941,
|
| 2189 |
+
"grad_norm": 1.3038586378097534,
|
| 2190 |
+
"learning_rate": 6.0285210936521976e-05,
|
| 2191 |
+
"loss": 0.0831,
|
| 2192 |
+
"num_input_tokens_seen": 231024,
|
| 2193 |
+
"step": 273
|
| 2194 |
+
},
|
| 2195 |
+
{
|
| 2196 |
+
"epoch": 8.596078431372549,
|
| 2197 |
+
"grad_norm": 5.259337902069092,
|
| 2198 |
+
"learning_rate": 5.7422070843492734e-05,
|
| 2199 |
+
"loss": 0.1228,
|
| 2200 |
+
"num_input_tokens_seen": 231915,
|
| 2201 |
+
"step": 274
|
| 2202 |
+
},
|
| 2203 |
+
{
|
| 2204 |
+
"epoch": 8.627450980392156,
|
| 2205 |
+
"grad_norm": 0.8257218599319458,
|
| 2206 |
+
"learning_rate": 5.460095002604537e-05,
|
| 2207 |
+
"loss": 0.0171,
|
| 2208 |
+
"num_input_tokens_seen": 232711,
|
| 2209 |
+
"step": 275
|
| 2210 |
+
},
|
| 2211 |
+
{
|
| 2212 |
+
"epoch": 8.658823529411764,
|
| 2213 |
+
"grad_norm": 1.649411916732788,
|
| 2214 |
+
"learning_rate": 5.182463258982846e-05,
|
| 2215 |
+
"loss": 0.0366,
|
| 2216 |
+
"num_input_tokens_seen": 233534,
|
| 2217 |
+
"step": 276
|
| 2218 |
+
},
|
| 2219 |
+
{
|
| 2220 |
+
"epoch": 8.690196078431372,
|
| 2221 |
+
"grad_norm": 4.529787540435791,
|
| 2222 |
+
"learning_rate": 4.909585842496292e-05,
|
| 2223 |
+
"loss": 0.1006,
|
| 2224 |
+
"num_input_tokens_seen": 234406,
|
| 2225 |
+
"step": 277
|
| 2226 |
+
},
|
| 2227 |
+
{
|
| 2228 |
+
"epoch": 8.72156862745098,
|
| 2229 |
+
"grad_norm": 3.721914052963257,
|
| 2230 |
+
"learning_rate": 4.6417320502100425e-05,
|
| 2231 |
+
"loss": 0.1088,
|
| 2232 |
+
"num_input_tokens_seen": 235270,
|
| 2233 |
+
"step": 278
|
| 2234 |
+
},
|
| 2235 |
+
{
|
| 2236 |
+
"epoch": 8.75294117647059,
|
| 2237 |
+
"grad_norm": 8.44381046295166,
|
| 2238 |
+
"learning_rate": 4.379166221478697e-05,
|
| 2239 |
+
"loss": 0.1685,
|
| 2240 |
+
"num_input_tokens_seen": 236150,
|
| 2241 |
+
"step": 279
|
| 2242 |
+
},
|
| 2243 |
+
{
|
| 2244 |
+
"epoch": 8.784313725490197,
|
| 2245 |
+
"grad_norm": 3.0152742862701416,
|
| 2246 |
+
"learning_rate": 4.122147477075266e-05,
|
| 2247 |
+
"loss": 0.0961,
|
| 2248 |
+
"num_input_tokens_seen": 237030,
|
| 2249 |
+
"step": 280
|
| 2250 |
+
},
|
| 2251 |
+
{
|
| 2252 |
+
"epoch": 8.815686274509805,
|
| 2253 |
+
"grad_norm": 2.386852502822876,
|
| 2254 |
+
"learning_rate": 3.8709294634702376e-05,
|
| 2255 |
+
"loss": 0.112,
|
| 2256 |
+
"num_input_tokens_seen": 237889,
|
| 2257 |
+
"step": 281
|
| 2258 |
+
},
|
| 2259 |
+
{
|
| 2260 |
+
"epoch": 8.847058823529412,
|
| 2261 |
+
"grad_norm": 3.819979667663574,
|
| 2262 |
+
"learning_rate": 3.6257601025131094e-05,
|
| 2263 |
+
"loss": 0.0342,
|
| 2264 |
+
"num_input_tokens_seen": 238703,
|
| 2265 |
+
"step": 282
|
| 2266 |
+
},
|
| 2267 |
+
{
|
| 2268 |
+
"epoch": 8.87843137254902,
|
| 2269 |
+
"grad_norm": 2.879319190979004,
|
| 2270 |
+
"learning_rate": 3.386881346763483e-05,
|
| 2271 |
+
"loss": 0.1328,
|
| 2272 |
+
"num_input_tokens_seen": 239619,
|
| 2273 |
+
"step": 283
|
| 2274 |
+
},
|
| 2275 |
+
{
|
| 2276 |
+
"epoch": 8.909803921568628,
|
| 2277 |
+
"grad_norm": 4.421603679656982,
|
| 2278 |
+
"learning_rate": 3.1545289407131097e-05,
|
| 2279 |
+
"loss": 0.141,
|
| 2280 |
+
"num_input_tokens_seen": 240466,
|
| 2281 |
+
"step": 284
|
| 2282 |
+
},
|
| 2283 |
+
{
|
| 2284 |
+
"epoch": 8.941176470588236,
|
| 2285 |
+
"grad_norm": 1.440587043762207,
|
| 2286 |
+
"learning_rate": 2.9289321881345254e-05,
|
| 2287 |
+
"loss": 0.0686,
|
| 2288 |
+
"num_input_tokens_seen": 241295,
|
| 2289 |
+
"step": 285
|
| 2290 |
+
},
|
| 2291 |
+
{
|
| 2292 |
+
"epoch": 8.972549019607843,
|
| 2293 |
+
"grad_norm": 1.706859827041626,
|
| 2294 |
+
"learning_rate": 2.71031372578588e-05,
|
| 2295 |
+
"loss": 0.0272,
|
| 2296 |
+
"num_input_tokens_seen": 242157,
|
| 2297 |
+
"step": 286
|
| 2298 |
+
},
|
| 2299 |
+
{
|
| 2300 |
+
"epoch": 9.003921568627451,
|
| 2301 |
+
"grad_norm": 1.8288636207580566,
|
| 2302 |
+
"learning_rate": 2.4988893036954043e-05,
|
| 2303 |
+
"loss": 0.0571,
|
| 2304 |
+
"num_input_tokens_seen": 243008,
|
| 2305 |
+
"step": 287
|
| 2306 |
+
},
|
| 2307 |
+
{
|
| 2308 |
+
"epoch": 9.035294117647059,
|
| 2309 |
+
"grad_norm": 0.7292274236679077,
|
| 2310 |
+
"learning_rate": 2.294867572242112e-05,
|
| 2311 |
+
"loss": 0.0109,
|
| 2312 |
+
"num_input_tokens_seen": 243807,
|
| 2313 |
+
"step": 288
|
| 2314 |
+
},
|
| 2315 |
+
{
|
| 2316 |
+
"epoch": 9.066666666666666,
|
| 2317 |
+
"grad_norm": 1.1452817916870117,
|
| 2318 |
+
"learning_rate": 2.098449876243096e-05,
|
| 2319 |
+
"loss": 0.0239,
|
| 2320 |
+
"num_input_tokens_seen": 244652,
|
| 2321 |
+
"step": 289
|
| 2322 |
+
},
|
| 2323 |
+
{
|
| 2324 |
+
"epoch": 9.098039215686274,
|
| 2325 |
+
"grad_norm": 1.0900837182998657,
|
| 2326 |
+
"learning_rate": 1.909830056250529e-05,
|
| 2327 |
+
"loss": 0.0197,
|
| 2328 |
+
"num_input_tokens_seen": 245514,
|
| 2329 |
+
"step": 290
|
| 2330 |
+
},
|
| 2331 |
+
{
|
| 2332 |
+
"epoch": 9.129411764705882,
|
| 2333 |
+
"grad_norm": 1.1233842372894287,
|
| 2334 |
+
"learning_rate": 1.7291942572543807e-05,
|
| 2335 |
+
"loss": 0.059,
|
| 2336 |
+
"num_input_tokens_seen": 246368,
|
| 2337 |
+
"step": 291
|
| 2338 |
+
},
|
| 2339 |
+
{
|
| 2340 |
+
"epoch": 9.16078431372549,
|
| 2341 |
+
"grad_norm": 1.2153921127319336,
|
| 2342 |
+
"learning_rate": 1.5567207449798515e-05,
|
| 2343 |
+
"loss": 0.0487,
|
| 2344 |
+
"num_input_tokens_seen": 247234,
|
| 2345 |
+
"step": 292
|
| 2346 |
+
},
|
| 2347 |
+
{
|
| 2348 |
+
"epoch": 9.192156862745097,
|
| 2349 |
+
"grad_norm": 1.7913979291915894,
|
| 2350 |
+
"learning_rate": 1.3925797299605625e-05,
|
| 2351 |
+
"loss": 0.0462,
|
| 2352 |
+
"num_input_tokens_seen": 248080,
|
| 2353 |
+
"step": 293
|
| 2354 |
+
},
|
| 2355 |
+
{
|
| 2356 |
+
"epoch": 9.223529411764705,
|
| 2357 |
+
"grad_norm": 0.9466875195503235,
|
| 2358 |
+
"learning_rate": 1.2369331995613665e-05,
|
| 2359 |
+
"loss": 0.0196,
|
| 2360 |
+
"num_input_tokens_seen": 248920,
|
| 2361 |
+
"step": 294
|
| 2362 |
+
},
|
| 2363 |
+
{
|
| 2364 |
+
"epoch": 9.254901960784313,
|
| 2365 |
+
"grad_norm": 2.3814680576324463,
|
| 2366 |
+
"learning_rate": 1.0899347581163277e-05,
|
| 2367 |
+
"loss": 0.021,
|
| 2368 |
+
"num_input_tokens_seen": 249739,
|
| 2369 |
+
"step": 295
|
| 2370 |
+
},
|
| 2371 |
+
{
|
| 2372 |
+
"epoch": 9.286274509803922,
|
| 2373 |
+
"grad_norm": 1.2178651094436646,
|
| 2374 |
+
"learning_rate": 9.517294753397998e-06,
|
| 2375 |
+
"loss": 0.0089,
|
| 2376 |
+
"num_input_tokens_seen": 250537,
|
| 2377 |
+
"step": 296
|
| 2378 |
+
},
|
| 2379 |
+
{
|
| 2380 |
+
"epoch": 9.31764705882353,
|
| 2381 |
+
"grad_norm": 3.2499518394470215,
|
| 2382 |
+
"learning_rate": 8.224537431601864e-06,
|
| 2383 |
+
"loss": 0.0794,
|
| 2384 |
+
"num_input_tokens_seen": 251375,
|
| 2385 |
+
"step": 297
|
| 2386 |
+
},
|
| 2387 |
+
{
|
| 2388 |
+
"epoch": 9.349019607843138,
|
| 2389 |
+
"grad_norm": 2.116999626159668,
|
| 2390 |
+
"learning_rate": 7.022351411174888e-06,
|
| 2391 |
+
"loss": 0.0815,
|
| 2392 |
+
"num_input_tokens_seen": 252200,
|
| 2393 |
+
"step": 298
|
| 2394 |
+
},
|
| 2395 |
+
{
|
| 2396 |
+
"epoch": 9.380392156862746,
|
| 2397 |
+
"grad_norm": 1.607701301574707,
|
| 2398 |
+
"learning_rate": 5.911923104577455e-06,
|
| 2399 |
+
"loss": 0.0686,
|
| 2400 |
+
"num_input_tokens_seen": 253122,
|
| 2401 |
+
"step": 299
|
| 2402 |
+
},
|
| 2403 |
+
{
|
| 2404 |
+
"epoch": 9.411764705882353,
|
| 2405 |
+
"grad_norm": 1.501824975013733,
|
| 2406 |
+
"learning_rate": 4.8943483704846585e-06,
|
| 2407 |
+
"loss": 0.0453,
|
| 2408 |
+
"num_input_tokens_seen": 253966,
|
| 2409 |
+
"step": 300
|
| 2410 |
+
},
|
| 2411 |
+
{
|
| 2412 |
+
"epoch": 9.443137254901961,
|
| 2413 |
+
"grad_norm": 0.8923909664154053,
|
| 2414 |
+
"learning_rate": 3.970631432305694e-06,
|
| 2415 |
+
"loss": 0.0136,
|
| 2416 |
+
"num_input_tokens_seen": 254841,
|
| 2417 |
+
"step": 301
|
| 2418 |
+
},
|
| 2419 |
+
{
|
| 2420 |
+
"epoch": 9.474509803921569,
|
| 2421 |
+
"grad_norm": 1.3790185451507568,
|
| 2422 |
+
"learning_rate": 3.141683887136904e-06,
|
| 2423 |
+
"loss": 0.0812,
|
| 2424 |
+
"num_input_tokens_seen": 255706,
|
| 2425 |
+
"step": 302
|
| 2426 |
+
},
|
| 2427 |
+
{
|
| 2428 |
+
"epoch": 9.505882352941176,
|
| 2429 |
+
"grad_norm": 0.6012554168701172,
|
| 2430 |
+
"learning_rate": 2.4083238061252567e-06,
|
| 2431 |
+
"loss": 0.012,
|
| 2432 |
+
"num_input_tokens_seen": 256525,
|
| 2433 |
+
"step": 303
|
| 2434 |
+
},
|
| 2435 |
+
{
|
| 2436 |
+
"epoch": 9.537254901960784,
|
| 2437 |
+
"grad_norm": 0.9253413677215576,
|
| 2438 |
+
"learning_rate": 1.771274927131139e-06,
|
| 2439 |
+
"loss": 0.0088,
|
| 2440 |
+
"num_input_tokens_seen": 257340,
|
| 2441 |
+
"step": 304
|
| 2442 |
+
},
|
| 2443 |
+
{
|
| 2444 |
+
"epoch": 9.568627450980392,
|
| 2445 |
+
"grad_norm": 0.8364208936691284,
|
| 2446 |
+
"learning_rate": 1.2311659404862453e-06,
|
| 2447 |
+
"loss": 0.0128,
|
| 2448 |
+
"num_input_tokens_seen": 258165,
|
| 2449 |
+
"step": 305
|
| 2450 |
+
},
|
| 2451 |
+
{
|
| 2452 |
+
"epoch": 9.6,
|
| 2453 |
+
"grad_norm": 1.1087877750396729,
|
| 2454 |
+
"learning_rate": 7.885298685522235e-07,
|
| 2455 |
+
"loss": 0.0406,
|
| 2456 |
+
"num_input_tokens_seen": 259015,
|
| 2457 |
+
"step": 306
|
| 2458 |
+
},
|
| 2459 |
+
{
|
| 2460 |
+
"epoch": 9.631372549019607,
|
| 2461 |
+
"grad_norm": 1.227319359779358,
|
| 2462 |
+
"learning_rate": 4.438035396920115e-07,
|
| 2463 |
+
"loss": 0.0136,
|
| 2464 |
+
"num_input_tokens_seen": 259833,
|
| 2465 |
+
"step": 307
|
| 2466 |
+
},
|
| 2467 |
+
{
|
| 2468 |
+
"epoch": 9.662745098039215,
|
| 2469 |
+
"grad_norm": 1.0235058069229126,
|
| 2470 |
+
"learning_rate": 1.973271571728441e-07,
|
| 2471 |
+
"loss": 0.037,
|
| 2472 |
+
"num_input_tokens_seen": 260686,
|
| 2473 |
+
"step": 308
|
| 2474 |
+
},
|
| 2475 |
+
{
|
| 2476 |
+
"epoch": 9.694117647058823,
|
| 2477 |
+
"grad_norm": 1.069370150566101,
|
| 2478 |
+
"learning_rate": 4.934396342684e-08,
|
| 2479 |
+
"loss": 0.0366,
|
| 2480 |
+
"num_input_tokens_seen": 261513,
|
| 2481 |
+
"step": 309
|
| 2482 |
+
},
|
| 2483 |
+
{
|
| 2484 |
+
"epoch": 9.72549019607843,
|
| 2485 |
+
"grad_norm": 1.2721508741378784,
|
| 2486 |
+
"learning_rate": 0.0,
|
| 2487 |
+
"loss": 0.0282,
|
| 2488 |
+
"num_input_tokens_seen": 262364,
|
| 2489 |
+
"step": 310
|
| 2490 |
+
}
|
| 2491 |
+
],
|
| 2492 |
+
"logging_steps": 1,
|
| 2493 |
+
"max_steps": 310,
|
| 2494 |
+
"num_input_tokens_seen": 262364,
|
| 2495 |
+
"num_train_epochs": 10,
|
| 2496 |
+
"save_steps": 31,
|
| 2497 |
+
"stateful_callbacks": {
|
| 2498 |
+
"TrainerControl": {
|
| 2499 |
+
"args": {
|
| 2500 |
+
"should_epoch_stop": false,
|
| 2501 |
+
"should_evaluate": false,
|
| 2502 |
+
"should_log": false,
|
| 2503 |
+
"should_save": true,
|
| 2504 |
+
"should_training_stop": true
|
| 2505 |
+
},
|
| 2506 |
+
"attributes": {}
|
| 2507 |
+
}
|
| 2508 |
+
},
|
| 2509 |
+
"total_flos": 1.5870993062052984e+16,
|
| 2510 |
+
"train_batch_size": 1,
|
| 2511 |
+
"trial_name": null,
|
| 2512 |
+
"trial_params": null
|
| 2513 |
+
}
|