Commit
•
ab7ab0b
1
Parent(s):
955783d
pretrain_model and pretrain_model_token
Browse files- README.md +202 -0
- adapter_config.json +15 -0
- adapter_model.safetensors +3 -0
- optimizer.pt +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +125 -0
- spiece.model +3 -0
- tokenizer.json +0 -0
- tokenizer_config.json +938 -0
- trainer_state.json +2404 -0
- training_args.bin +3 -0
README.md
CHANGED
|
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: google/flan-t5-base
|
| 3 |
+
library_name: peft
|
| 4 |
+
---
|
| 5 |
+
|
| 6 |
+
# Model Card for Model ID
|
| 7 |
+
|
| 8 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
| 9 |
+
|
| 10 |
+
|
| 11 |
+
|
| 12 |
+
## Model Details
|
| 13 |
+
|
| 14 |
+
### Model Description
|
| 15 |
+
|
| 16 |
+
<!-- Provide a longer summary of what this model is. -->
|
| 17 |
+
|
| 18 |
+
|
| 19 |
+
|
| 20 |
+
- **Developed by:** [More Information Needed]
|
| 21 |
+
- **Funded by [optional]:** [More Information Needed]
|
| 22 |
+
- **Shared by [optional]:** [More Information Needed]
|
| 23 |
+
- **Model type:** [More Information Needed]
|
| 24 |
+
- **Language(s) (NLP):** [More Information Needed]
|
| 25 |
+
- **License:** [More Information Needed]
|
| 26 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
| 27 |
+
|
| 28 |
+
### Model Sources [optional]
|
| 29 |
+
|
| 30 |
+
<!-- Provide the basic links for the model. -->
|
| 31 |
+
|
| 32 |
+
- **Repository:** [More Information Needed]
|
| 33 |
+
- **Paper [optional]:** [More Information Needed]
|
| 34 |
+
- **Demo [optional]:** [More Information Needed]
|
| 35 |
+
|
| 36 |
+
## Uses
|
| 37 |
+
|
| 38 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
| 39 |
+
|
| 40 |
+
### Direct Use
|
| 41 |
+
|
| 42 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
| 43 |
+
|
| 44 |
+
[More Information Needed]
|
| 45 |
+
|
| 46 |
+
### Downstream Use [optional]
|
| 47 |
+
|
| 48 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
| 49 |
+
|
| 50 |
+
[More Information Needed]
|
| 51 |
+
|
| 52 |
+
### Out-of-Scope Use
|
| 53 |
+
|
| 54 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
| 55 |
+
|
| 56 |
+
[More Information Needed]
|
| 57 |
+
|
| 58 |
+
## Bias, Risks, and Limitations
|
| 59 |
+
|
| 60 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
| 61 |
+
|
| 62 |
+
[More Information Needed]
|
| 63 |
+
|
| 64 |
+
### Recommendations
|
| 65 |
+
|
| 66 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
| 67 |
+
|
| 68 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
| 69 |
+
|
| 70 |
+
## How to Get Started with the Model
|
| 71 |
+
|
| 72 |
+
Use the code below to get started with the model.
|
| 73 |
+
|
| 74 |
+
[More Information Needed]
|
| 75 |
+
|
| 76 |
+
## Training Details
|
| 77 |
+
|
| 78 |
+
### Training Data
|
| 79 |
+
|
| 80 |
+
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
| 81 |
+
|
| 82 |
+
[More Information Needed]
|
| 83 |
+
|
| 84 |
+
### Training Procedure
|
| 85 |
+
|
| 86 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
| 87 |
+
|
| 88 |
+
#### Preprocessing [optional]
|
| 89 |
+
|
| 90 |
+
[More Information Needed]
|
| 91 |
+
|
| 92 |
+
|
| 93 |
+
#### Training Hyperparameters
|
| 94 |
+
|
| 95 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
| 96 |
+
|
| 97 |
+
#### Speeds, Sizes, Times [optional]
|
| 98 |
+
|
| 99 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
| 100 |
+
|
| 101 |
+
[More Information Needed]
|
| 102 |
+
|
| 103 |
+
## Evaluation
|
| 104 |
+
|
| 105 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
| 106 |
+
|
| 107 |
+
### Testing Data, Factors & Metrics
|
| 108 |
+
|
| 109 |
+
#### Testing Data
|
| 110 |
+
|
| 111 |
+
<!-- This should link to a Dataset Card if possible. -->
|
| 112 |
+
|
| 113 |
+
[More Information Needed]
|
| 114 |
+
|
| 115 |
+
#### Factors
|
| 116 |
+
|
| 117 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
| 118 |
+
|
| 119 |
+
[More Information Needed]
|
| 120 |
+
|
| 121 |
+
#### Metrics
|
| 122 |
+
|
| 123 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
| 124 |
+
|
| 125 |
+
[More Information Needed]
|
| 126 |
+
|
| 127 |
+
### Results
|
| 128 |
+
|
| 129 |
+
[More Information Needed]
|
| 130 |
+
|
| 131 |
+
#### Summary
|
| 132 |
+
|
| 133 |
+
|
| 134 |
+
|
| 135 |
+
## Model Examination [optional]
|
| 136 |
+
|
| 137 |
+
<!-- Relevant interpretability work for the model goes here -->
|
| 138 |
+
|
| 139 |
+
[More Information Needed]
|
| 140 |
+
|
| 141 |
+
## Environmental Impact
|
| 142 |
+
|
| 143 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
| 144 |
+
|
| 145 |
+
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
| 146 |
+
|
| 147 |
+
- **Hardware Type:** [More Information Needed]
|
| 148 |
+
- **Hours used:** [More Information Needed]
|
| 149 |
+
- **Cloud Provider:** [More Information Needed]
|
| 150 |
+
- **Compute Region:** [More Information Needed]
|
| 151 |
+
- **Carbon Emitted:** [More Information Needed]
|
| 152 |
+
|
| 153 |
+
## Technical Specifications [optional]
|
| 154 |
+
|
| 155 |
+
### Model Architecture and Objective
|
| 156 |
+
|
| 157 |
+
[More Information Needed]
|
| 158 |
+
|
| 159 |
+
### Compute Infrastructure
|
| 160 |
+
|
| 161 |
+
[More Information Needed]
|
| 162 |
+
|
| 163 |
+
#### Hardware
|
| 164 |
+
|
| 165 |
+
[More Information Needed]
|
| 166 |
+
|
| 167 |
+
#### Software
|
| 168 |
+
|
| 169 |
+
[More Information Needed]
|
| 170 |
+
|
| 171 |
+
## Citation [optional]
|
| 172 |
+
|
| 173 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
| 174 |
+
|
| 175 |
+
**BibTeX:**
|
| 176 |
+
|
| 177 |
+
[More Information Needed]
|
| 178 |
+
|
| 179 |
+
**APA:**
|
| 180 |
+
|
| 181 |
+
[More Information Needed]
|
| 182 |
+
|
| 183 |
+
## Glossary [optional]
|
| 184 |
+
|
| 185 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
| 186 |
+
|
| 187 |
+
[More Information Needed]
|
| 188 |
+
|
| 189 |
+
## More Information [optional]
|
| 190 |
+
|
| 191 |
+
[More Information Needed]
|
| 192 |
+
|
| 193 |
+
## Model Card Authors [optional]
|
| 194 |
+
|
| 195 |
+
[More Information Needed]
|
| 196 |
+
|
| 197 |
+
## Model Card Contact
|
| 198 |
+
|
| 199 |
+
[More Information Needed]
|
| 200 |
+
### Framework versions
|
| 201 |
+
|
| 202 |
+
- PEFT 0.12.0
|
adapter_config.json
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"auto_mapping": null,
|
| 3 |
+
"base_model_name_or_path": "google/flan-t5-base",
|
| 4 |
+
"encoder_hidden_size": 768,
|
| 5 |
+
"inference_mode": true,
|
| 6 |
+
"num_attention_heads": 12,
|
| 7 |
+
"num_layers": 12,
|
| 8 |
+
"num_transformer_submodules": 2,
|
| 9 |
+
"num_virtual_tokens": 10,
|
| 10 |
+
"peft_type": "PREFIX_TUNING",
|
| 11 |
+
"prefix_projection": false,
|
| 12 |
+
"revision": null,
|
| 13 |
+
"task_type": "SEQ_2_SEQ_LM",
|
| 14 |
+
"token_dim": 768
|
| 15 |
+
}
|
adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:50e5f56cb93e24519f87e06380a4cc165e236a5672284e023124d8b8c4312b6a
|
| 3 |
+
size 737408
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a1668a50bc4fc5ae4ac8fd5df156755023b953a0faa22f5edffea9330864a0cb
|
| 3 |
+
size 1476706
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5ae8573da8e876fe7f247a4c33de1fa7a0566597332f73823e08b18a4a13a070
|
| 3 |
+
size 14244
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fc0c458265c2047c4bc0087443c96faa043c845ded72e30ee4cd296ade663989
|
| 3 |
+
size 1064
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,125 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<extra_id_0>",
|
| 4 |
+
"<extra_id_1>",
|
| 5 |
+
"<extra_id_2>",
|
| 6 |
+
"<extra_id_3>",
|
| 7 |
+
"<extra_id_4>",
|
| 8 |
+
"<extra_id_5>",
|
| 9 |
+
"<extra_id_6>",
|
| 10 |
+
"<extra_id_7>",
|
| 11 |
+
"<extra_id_8>",
|
| 12 |
+
"<extra_id_9>",
|
| 13 |
+
"<extra_id_10>",
|
| 14 |
+
"<extra_id_11>",
|
| 15 |
+
"<extra_id_12>",
|
| 16 |
+
"<extra_id_13>",
|
| 17 |
+
"<extra_id_14>",
|
| 18 |
+
"<extra_id_15>",
|
| 19 |
+
"<extra_id_16>",
|
| 20 |
+
"<extra_id_17>",
|
| 21 |
+
"<extra_id_18>",
|
| 22 |
+
"<extra_id_19>",
|
| 23 |
+
"<extra_id_20>",
|
| 24 |
+
"<extra_id_21>",
|
| 25 |
+
"<extra_id_22>",
|
| 26 |
+
"<extra_id_23>",
|
| 27 |
+
"<extra_id_24>",
|
| 28 |
+
"<extra_id_25>",
|
| 29 |
+
"<extra_id_26>",
|
| 30 |
+
"<extra_id_27>",
|
| 31 |
+
"<extra_id_28>",
|
| 32 |
+
"<extra_id_29>",
|
| 33 |
+
"<extra_id_30>",
|
| 34 |
+
"<extra_id_31>",
|
| 35 |
+
"<extra_id_32>",
|
| 36 |
+
"<extra_id_33>",
|
| 37 |
+
"<extra_id_34>",
|
| 38 |
+
"<extra_id_35>",
|
| 39 |
+
"<extra_id_36>",
|
| 40 |
+
"<extra_id_37>",
|
| 41 |
+
"<extra_id_38>",
|
| 42 |
+
"<extra_id_39>",
|
| 43 |
+
"<extra_id_40>",
|
| 44 |
+
"<extra_id_41>",
|
| 45 |
+
"<extra_id_42>",
|
| 46 |
+
"<extra_id_43>",
|
| 47 |
+
"<extra_id_44>",
|
| 48 |
+
"<extra_id_45>",
|
| 49 |
+
"<extra_id_46>",
|
| 50 |
+
"<extra_id_47>",
|
| 51 |
+
"<extra_id_48>",
|
| 52 |
+
"<extra_id_49>",
|
| 53 |
+
"<extra_id_50>",
|
| 54 |
+
"<extra_id_51>",
|
| 55 |
+
"<extra_id_52>",
|
| 56 |
+
"<extra_id_53>",
|
| 57 |
+
"<extra_id_54>",
|
| 58 |
+
"<extra_id_55>",
|
| 59 |
+
"<extra_id_56>",
|
| 60 |
+
"<extra_id_57>",
|
| 61 |
+
"<extra_id_58>",
|
| 62 |
+
"<extra_id_59>",
|
| 63 |
+
"<extra_id_60>",
|
| 64 |
+
"<extra_id_61>",
|
| 65 |
+
"<extra_id_62>",
|
| 66 |
+
"<extra_id_63>",
|
| 67 |
+
"<extra_id_64>",
|
| 68 |
+
"<extra_id_65>",
|
| 69 |
+
"<extra_id_66>",
|
| 70 |
+
"<extra_id_67>",
|
| 71 |
+
"<extra_id_68>",
|
| 72 |
+
"<extra_id_69>",
|
| 73 |
+
"<extra_id_70>",
|
| 74 |
+
"<extra_id_71>",
|
| 75 |
+
"<extra_id_72>",
|
| 76 |
+
"<extra_id_73>",
|
| 77 |
+
"<extra_id_74>",
|
| 78 |
+
"<extra_id_75>",
|
| 79 |
+
"<extra_id_76>",
|
| 80 |
+
"<extra_id_77>",
|
| 81 |
+
"<extra_id_78>",
|
| 82 |
+
"<extra_id_79>",
|
| 83 |
+
"<extra_id_80>",
|
| 84 |
+
"<extra_id_81>",
|
| 85 |
+
"<extra_id_82>",
|
| 86 |
+
"<extra_id_83>",
|
| 87 |
+
"<extra_id_84>",
|
| 88 |
+
"<extra_id_85>",
|
| 89 |
+
"<extra_id_86>",
|
| 90 |
+
"<extra_id_87>",
|
| 91 |
+
"<extra_id_88>",
|
| 92 |
+
"<extra_id_89>",
|
| 93 |
+
"<extra_id_90>",
|
| 94 |
+
"<extra_id_91>",
|
| 95 |
+
"<extra_id_92>",
|
| 96 |
+
"<extra_id_93>",
|
| 97 |
+
"<extra_id_94>",
|
| 98 |
+
"<extra_id_95>",
|
| 99 |
+
"<extra_id_96>",
|
| 100 |
+
"<extra_id_97>",
|
| 101 |
+
"<extra_id_98>",
|
| 102 |
+
"<extra_id_99>"
|
| 103 |
+
],
|
| 104 |
+
"eos_token": {
|
| 105 |
+
"content": "</s>",
|
| 106 |
+
"lstrip": false,
|
| 107 |
+
"normalized": false,
|
| 108 |
+
"rstrip": false,
|
| 109 |
+
"single_word": false
|
| 110 |
+
},
|
| 111 |
+
"pad_token": {
|
| 112 |
+
"content": "<pad>",
|
| 113 |
+
"lstrip": false,
|
| 114 |
+
"normalized": false,
|
| 115 |
+
"rstrip": false,
|
| 116 |
+
"single_word": false
|
| 117 |
+
},
|
| 118 |
+
"unk_token": {
|
| 119 |
+
"content": "<unk>",
|
| 120 |
+
"lstrip": false,
|
| 121 |
+
"normalized": false,
|
| 122 |
+
"rstrip": false,
|
| 123 |
+
"single_word": false
|
| 124 |
+
}
|
| 125 |
+
}
|
spiece.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d60acb128cf7b7f2536e8f38a5b18a05535c9e14c7a355904270e15b0945ea86
|
| 3 |
+
size 791656
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,938 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "<pad>",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"1": {
|
| 12 |
+
"content": "</s>",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"2": {
|
| 20 |
+
"content": "<unk>",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"32000": {
|
| 28 |
+
"content": "<extra_id_99>",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"32001": {
|
| 36 |
+
"content": "<extra_id_98>",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
},
|
| 43 |
+
"32002": {
|
| 44 |
+
"content": "<extra_id_97>",
|
| 45 |
+
"lstrip": false,
|
| 46 |
+
"normalized": false,
|
| 47 |
+
"rstrip": false,
|
| 48 |
+
"single_word": false,
|
| 49 |
+
"special": true
|
| 50 |
+
},
|
| 51 |
+
"32003": {
|
| 52 |
+
"content": "<extra_id_96>",
|
| 53 |
+
"lstrip": false,
|
| 54 |
+
"normalized": false,
|
| 55 |
+
"rstrip": false,
|
| 56 |
+
"single_word": false,
|
| 57 |
+
"special": true
|
| 58 |
+
},
|
| 59 |
+
"32004": {
|
| 60 |
+
"content": "<extra_id_95>",
|
| 61 |
+
"lstrip": false,
|
| 62 |
+
"normalized": false,
|
| 63 |
+
"rstrip": false,
|
| 64 |
+
"single_word": false,
|
| 65 |
+
"special": true
|
| 66 |
+
},
|
| 67 |
+
"32005": {
|
| 68 |
+
"content": "<extra_id_94>",
|
| 69 |
+
"lstrip": false,
|
| 70 |
+
"normalized": false,
|
| 71 |
+
"rstrip": false,
|
| 72 |
+
"single_word": false,
|
| 73 |
+
"special": true
|
| 74 |
+
},
|
| 75 |
+
"32006": {
|
| 76 |
+
"content": "<extra_id_93>",
|
| 77 |
+
"lstrip": false,
|
| 78 |
+
"normalized": false,
|
| 79 |
+
"rstrip": false,
|
| 80 |
+
"single_word": false,
|
| 81 |
+
"special": true
|
| 82 |
+
},
|
| 83 |
+
"32007": {
|
| 84 |
+
"content": "<extra_id_92>",
|
| 85 |
+
"lstrip": false,
|
| 86 |
+
"normalized": false,
|
| 87 |
+
"rstrip": false,
|
| 88 |
+
"single_word": false,
|
| 89 |
+
"special": true
|
| 90 |
+
},
|
| 91 |
+
"32008": {
|
| 92 |
+
"content": "<extra_id_91>",
|
| 93 |
+
"lstrip": false,
|
| 94 |
+
"normalized": false,
|
| 95 |
+
"rstrip": false,
|
| 96 |
+
"single_word": false,
|
| 97 |
+
"special": true
|
| 98 |
+
},
|
| 99 |
+
"32009": {
|
| 100 |
+
"content": "<extra_id_90>",
|
| 101 |
+
"lstrip": false,
|
| 102 |
+
"normalized": false,
|
| 103 |
+
"rstrip": false,
|
| 104 |
+
"single_word": false,
|
| 105 |
+
"special": true
|
| 106 |
+
},
|
| 107 |
+
"32010": {
|
| 108 |
+
"content": "<extra_id_89>",
|
| 109 |
+
"lstrip": false,
|
| 110 |
+
"normalized": false,
|
| 111 |
+
"rstrip": false,
|
| 112 |
+
"single_word": false,
|
| 113 |
+
"special": true
|
| 114 |
+
},
|
| 115 |
+
"32011": {
|
| 116 |
+
"content": "<extra_id_88>",
|
| 117 |
+
"lstrip": false,
|
| 118 |
+
"normalized": false,
|
| 119 |
+
"rstrip": false,
|
| 120 |
+
"single_word": false,
|
| 121 |
+
"special": true
|
| 122 |
+
},
|
| 123 |
+
"32012": {
|
| 124 |
+
"content": "<extra_id_87>",
|
| 125 |
+
"lstrip": false,
|
| 126 |
+
"normalized": false,
|
| 127 |
+
"rstrip": false,
|
| 128 |
+
"single_word": false,
|
| 129 |
+
"special": true
|
| 130 |
+
},
|
| 131 |
+
"32013": {
|
| 132 |
+
"content": "<extra_id_86>",
|
| 133 |
+
"lstrip": false,
|
| 134 |
+
"normalized": false,
|
| 135 |
+
"rstrip": false,
|
| 136 |
+
"single_word": false,
|
| 137 |
+
"special": true
|
| 138 |
+
},
|
| 139 |
+
"32014": {
|
| 140 |
+
"content": "<extra_id_85>",
|
| 141 |
+
"lstrip": false,
|
| 142 |
+
"normalized": false,
|
| 143 |
+
"rstrip": false,
|
| 144 |
+
"single_word": false,
|
| 145 |
+
"special": true
|
| 146 |
+
},
|
| 147 |
+
"32015": {
|
| 148 |
+
"content": "<extra_id_84>",
|
| 149 |
+
"lstrip": false,
|
| 150 |
+
"normalized": false,
|
| 151 |
+
"rstrip": false,
|
| 152 |
+
"single_word": false,
|
| 153 |
+
"special": true
|
| 154 |
+
},
|
| 155 |
+
"32016": {
|
| 156 |
+
"content": "<extra_id_83>",
|
| 157 |
+
"lstrip": false,
|
| 158 |
+
"normalized": false,
|
| 159 |
+
"rstrip": false,
|
| 160 |
+
"single_word": false,
|
| 161 |
+
"special": true
|
| 162 |
+
},
|
| 163 |
+
"32017": {
|
| 164 |
+
"content": "<extra_id_82>",
|
| 165 |
+
"lstrip": false,
|
| 166 |
+
"normalized": false,
|
| 167 |
+
"rstrip": false,
|
| 168 |
+
"single_word": false,
|
| 169 |
+
"special": true
|
| 170 |
+
},
|
| 171 |
+
"32018": {
|
| 172 |
+
"content": "<extra_id_81>",
|
| 173 |
+
"lstrip": false,
|
| 174 |
+
"normalized": false,
|
| 175 |
+
"rstrip": false,
|
| 176 |
+
"single_word": false,
|
| 177 |
+
"special": true
|
| 178 |
+
},
|
| 179 |
+
"32019": {
|
| 180 |
+
"content": "<extra_id_80>",
|
| 181 |
+
"lstrip": false,
|
| 182 |
+
"normalized": false,
|
| 183 |
+
"rstrip": false,
|
| 184 |
+
"single_word": false,
|
| 185 |
+
"special": true
|
| 186 |
+
},
|
| 187 |
+
"32020": {
|
| 188 |
+
"content": "<extra_id_79>",
|
| 189 |
+
"lstrip": false,
|
| 190 |
+
"normalized": false,
|
| 191 |
+
"rstrip": false,
|
| 192 |
+
"single_word": false,
|
| 193 |
+
"special": true
|
| 194 |
+
},
|
| 195 |
+
"32021": {
|
| 196 |
+
"content": "<extra_id_78>",
|
| 197 |
+
"lstrip": false,
|
| 198 |
+
"normalized": false,
|
| 199 |
+
"rstrip": false,
|
| 200 |
+
"single_word": false,
|
| 201 |
+
"special": true
|
| 202 |
+
},
|
| 203 |
+
"32022": {
|
| 204 |
+
"content": "<extra_id_77>",
|
| 205 |
+
"lstrip": false,
|
| 206 |
+
"normalized": false,
|
| 207 |
+
"rstrip": false,
|
| 208 |
+
"single_word": false,
|
| 209 |
+
"special": true
|
| 210 |
+
},
|
| 211 |
+
"32023": {
|
| 212 |
+
"content": "<extra_id_76>",
|
| 213 |
+
"lstrip": false,
|
| 214 |
+
"normalized": false,
|
| 215 |
+
"rstrip": false,
|
| 216 |
+
"single_word": false,
|
| 217 |
+
"special": true
|
| 218 |
+
},
|
| 219 |
+
"32024": {
|
| 220 |
+
"content": "<extra_id_75>",
|
| 221 |
+
"lstrip": false,
|
| 222 |
+
"normalized": false,
|
| 223 |
+
"rstrip": false,
|
| 224 |
+
"single_word": false,
|
| 225 |
+
"special": true
|
| 226 |
+
},
|
| 227 |
+
"32025": {
|
| 228 |
+
"content": "<extra_id_74>",
|
| 229 |
+
"lstrip": false,
|
| 230 |
+
"normalized": false,
|
| 231 |
+
"rstrip": false,
|
| 232 |
+
"single_word": false,
|
| 233 |
+
"special": true
|
| 234 |
+
},
|
| 235 |
+
"32026": {
|
| 236 |
+
"content": "<extra_id_73>",
|
| 237 |
+
"lstrip": false,
|
| 238 |
+
"normalized": false,
|
| 239 |
+
"rstrip": false,
|
| 240 |
+
"single_word": false,
|
| 241 |
+
"special": true
|
| 242 |
+
},
|
| 243 |
+
"32027": {
|
| 244 |
+
"content": "<extra_id_72>",
|
| 245 |
+
"lstrip": false,
|
| 246 |
+
"normalized": false,
|
| 247 |
+
"rstrip": false,
|
| 248 |
+
"single_word": false,
|
| 249 |
+
"special": true
|
| 250 |
+
},
|
| 251 |
+
"32028": {
|
| 252 |
+
"content": "<extra_id_71>",
|
| 253 |
+
"lstrip": false,
|
| 254 |
+
"normalized": false,
|
| 255 |
+
"rstrip": false,
|
| 256 |
+
"single_word": false,
|
| 257 |
+
"special": true
|
| 258 |
+
},
|
| 259 |
+
"32029": {
|
| 260 |
+
"content": "<extra_id_70>",
|
| 261 |
+
"lstrip": false,
|
| 262 |
+
"normalized": false,
|
| 263 |
+
"rstrip": false,
|
| 264 |
+
"single_word": false,
|
| 265 |
+
"special": true
|
| 266 |
+
},
|
| 267 |
+
"32030": {
|
| 268 |
+
"content": "<extra_id_69>",
|
| 269 |
+
"lstrip": false,
|
| 270 |
+
"normalized": false,
|
| 271 |
+
"rstrip": false,
|
| 272 |
+
"single_word": false,
|
| 273 |
+
"special": true
|
| 274 |
+
},
|
| 275 |
+
"32031": {
|
| 276 |
+
"content": "<extra_id_68>",
|
| 277 |
+
"lstrip": false,
|
| 278 |
+
"normalized": false,
|
| 279 |
+
"rstrip": false,
|
| 280 |
+
"single_word": false,
|
| 281 |
+
"special": true
|
| 282 |
+
},
|
| 283 |
+
"32032": {
|
| 284 |
+
"content": "<extra_id_67>",
|
| 285 |
+
"lstrip": false,
|
| 286 |
+
"normalized": false,
|
| 287 |
+
"rstrip": false,
|
| 288 |
+
"single_word": false,
|
| 289 |
+
"special": true
|
| 290 |
+
},
|
| 291 |
+
"32033": {
|
| 292 |
+
"content": "<extra_id_66>",
|
| 293 |
+
"lstrip": false,
|
| 294 |
+
"normalized": false,
|
| 295 |
+
"rstrip": false,
|
| 296 |
+
"single_word": false,
|
| 297 |
+
"special": true
|
| 298 |
+
},
|
| 299 |
+
"32034": {
|
| 300 |
+
"content": "<extra_id_65>",
|
| 301 |
+
"lstrip": false,
|
| 302 |
+
"normalized": false,
|
| 303 |
+
"rstrip": false,
|
| 304 |
+
"single_word": false,
|
| 305 |
+
"special": true
|
| 306 |
+
},
|
| 307 |
+
"32035": {
|
| 308 |
+
"content": "<extra_id_64>",
|
| 309 |
+
"lstrip": false,
|
| 310 |
+
"normalized": false,
|
| 311 |
+
"rstrip": false,
|
| 312 |
+
"single_word": false,
|
| 313 |
+
"special": true
|
| 314 |
+
},
|
| 315 |
+
"32036": {
|
| 316 |
+
"content": "<extra_id_63>",
|
| 317 |
+
"lstrip": false,
|
| 318 |
+
"normalized": false,
|
| 319 |
+
"rstrip": false,
|
| 320 |
+
"single_word": false,
|
| 321 |
+
"special": true
|
| 322 |
+
},
|
| 323 |
+
"32037": {
|
| 324 |
+
"content": "<extra_id_62>",
|
| 325 |
+
"lstrip": false,
|
| 326 |
+
"normalized": false,
|
| 327 |
+
"rstrip": false,
|
| 328 |
+
"single_word": false,
|
| 329 |
+
"special": true
|
| 330 |
+
},
|
| 331 |
+
"32038": {
|
| 332 |
+
"content": "<extra_id_61>",
|
| 333 |
+
"lstrip": false,
|
| 334 |
+
"normalized": false,
|
| 335 |
+
"rstrip": false,
|
| 336 |
+
"single_word": false,
|
| 337 |
+
"special": true
|
| 338 |
+
},
|
| 339 |
+
"32039": {
|
| 340 |
+
"content": "<extra_id_60>",
|
| 341 |
+
"lstrip": false,
|
| 342 |
+
"normalized": false,
|
| 343 |
+
"rstrip": false,
|
| 344 |
+
"single_word": false,
|
| 345 |
+
"special": true
|
| 346 |
+
},
|
| 347 |
+
"32040": {
|
| 348 |
+
"content": "<extra_id_59>",
|
| 349 |
+
"lstrip": false,
|
| 350 |
+
"normalized": false,
|
| 351 |
+
"rstrip": false,
|
| 352 |
+
"single_word": false,
|
| 353 |
+
"special": true
|
| 354 |
+
},
|
| 355 |
+
"32041": {
|
| 356 |
+
"content": "<extra_id_58>",
|
| 357 |
+
"lstrip": false,
|
| 358 |
+
"normalized": false,
|
| 359 |
+
"rstrip": false,
|
| 360 |
+
"single_word": false,
|
| 361 |
+
"special": true
|
| 362 |
+
},
|
| 363 |
+
"32042": {
|
| 364 |
+
"content": "<extra_id_57>",
|
| 365 |
+
"lstrip": false,
|
| 366 |
+
"normalized": false,
|
| 367 |
+
"rstrip": false,
|
| 368 |
+
"single_word": false,
|
| 369 |
+
"special": true
|
| 370 |
+
},
|
| 371 |
+
"32043": {
|
| 372 |
+
"content": "<extra_id_56>",
|
| 373 |
+
"lstrip": false,
|
| 374 |
+
"normalized": false,
|
| 375 |
+
"rstrip": false,
|
| 376 |
+
"single_word": false,
|
| 377 |
+
"special": true
|
| 378 |
+
},
|
| 379 |
+
"32044": {
|
| 380 |
+
"content": "<extra_id_55>",
|
| 381 |
+
"lstrip": false,
|
| 382 |
+
"normalized": false,
|
| 383 |
+
"rstrip": false,
|
| 384 |
+
"single_word": false,
|
| 385 |
+
"special": true
|
| 386 |
+
},
|
| 387 |
+
"32045": {
|
| 388 |
+
"content": "<extra_id_54>",
|
| 389 |
+
"lstrip": false,
|
| 390 |
+
"normalized": false,
|
| 391 |
+
"rstrip": false,
|
| 392 |
+
"single_word": false,
|
| 393 |
+
"special": true
|
| 394 |
+
},
|
| 395 |
+
"32046": {
|
| 396 |
+
"content": "<extra_id_53>",
|
| 397 |
+
"lstrip": false,
|
| 398 |
+
"normalized": false,
|
| 399 |
+
"rstrip": false,
|
| 400 |
+
"single_word": false,
|
| 401 |
+
"special": true
|
| 402 |
+
},
|
| 403 |
+
"32047": {
|
| 404 |
+
"content": "<extra_id_52>",
|
| 405 |
+
"lstrip": false,
|
| 406 |
+
"normalized": false,
|
| 407 |
+
"rstrip": false,
|
| 408 |
+
"single_word": false,
|
| 409 |
+
"special": true
|
| 410 |
+
},
|
| 411 |
+
"32048": {
|
| 412 |
+
"content": "<extra_id_51>",
|
| 413 |
+
"lstrip": false,
|
| 414 |
+
"normalized": false,
|
| 415 |
+
"rstrip": false,
|
| 416 |
+
"single_word": false,
|
| 417 |
+
"special": true
|
| 418 |
+
},
|
| 419 |
+
"32049": {
|
| 420 |
+
"content": "<extra_id_50>",
|
| 421 |
+
"lstrip": false,
|
| 422 |
+
"normalized": false,
|
| 423 |
+
"rstrip": false,
|
| 424 |
+
"single_word": false,
|
| 425 |
+
"special": true
|
| 426 |
+
},
|
| 427 |
+
"32050": {
|
| 428 |
+
"content": "<extra_id_49>",
|
| 429 |
+
"lstrip": false,
|
| 430 |
+
"normalized": false,
|
| 431 |
+
"rstrip": false,
|
| 432 |
+
"single_word": false,
|
| 433 |
+
"special": true
|
| 434 |
+
},
|
| 435 |
+
"32051": {
|
| 436 |
+
"content": "<extra_id_48>",
|
| 437 |
+
"lstrip": false,
|
| 438 |
+
"normalized": false,
|
| 439 |
+
"rstrip": false,
|
| 440 |
+
"single_word": false,
|
| 441 |
+
"special": true
|
| 442 |
+
},
|
| 443 |
+
"32052": {
|
| 444 |
+
"content": "<extra_id_47>",
|
| 445 |
+
"lstrip": false,
|
| 446 |
+
"normalized": false,
|
| 447 |
+
"rstrip": false,
|
| 448 |
+
"single_word": false,
|
| 449 |
+
"special": true
|
| 450 |
+
},
|
| 451 |
+
"32053": {
|
| 452 |
+
"content": "<extra_id_46>",
|
| 453 |
+
"lstrip": false,
|
| 454 |
+
"normalized": false,
|
| 455 |
+
"rstrip": false,
|
| 456 |
+
"single_word": false,
|
| 457 |
+
"special": true
|
| 458 |
+
},
|
| 459 |
+
"32054": {
|
| 460 |
+
"content": "<extra_id_45>",
|
| 461 |
+
"lstrip": false,
|
| 462 |
+
"normalized": false,
|
| 463 |
+
"rstrip": false,
|
| 464 |
+
"single_word": false,
|
| 465 |
+
"special": true
|
| 466 |
+
},
|
| 467 |
+
"32055": {
|
| 468 |
+
"content": "<extra_id_44>",
|
| 469 |
+
"lstrip": false,
|
| 470 |
+
"normalized": false,
|
| 471 |
+
"rstrip": false,
|
| 472 |
+
"single_word": false,
|
| 473 |
+
"special": true
|
| 474 |
+
},
|
| 475 |
+
"32056": {
|
| 476 |
+
"content": "<extra_id_43>",
|
| 477 |
+
"lstrip": false,
|
| 478 |
+
"normalized": false,
|
| 479 |
+
"rstrip": false,
|
| 480 |
+
"single_word": false,
|
| 481 |
+
"special": true
|
| 482 |
+
},
|
| 483 |
+
"32057": {
|
| 484 |
+
"content": "<extra_id_42>",
|
| 485 |
+
"lstrip": false,
|
| 486 |
+
"normalized": false,
|
| 487 |
+
"rstrip": false,
|
| 488 |
+
"single_word": false,
|
| 489 |
+
"special": true
|
| 490 |
+
},
|
| 491 |
+
"32058": {
|
| 492 |
+
"content": "<extra_id_41>",
|
| 493 |
+
"lstrip": false,
|
| 494 |
+
"normalized": false,
|
| 495 |
+
"rstrip": false,
|
| 496 |
+
"single_word": false,
|
| 497 |
+
"special": true
|
| 498 |
+
},
|
| 499 |
+
"32059": {
|
| 500 |
+
"content": "<extra_id_40>",
|
| 501 |
+
"lstrip": false,
|
| 502 |
+
"normalized": false,
|
| 503 |
+
"rstrip": false,
|
| 504 |
+
"single_word": false,
|
| 505 |
+
"special": true
|
| 506 |
+
},
|
| 507 |
+
"32060": {
|
| 508 |
+
"content": "<extra_id_39>",
|
| 509 |
+
"lstrip": false,
|
| 510 |
+
"normalized": false,
|
| 511 |
+
"rstrip": false,
|
| 512 |
+
"single_word": false,
|
| 513 |
+
"special": true
|
| 514 |
+
},
|
| 515 |
+
"32061": {
|
| 516 |
+
"content": "<extra_id_38>",
|
| 517 |
+
"lstrip": false,
|
| 518 |
+
"normalized": false,
|
| 519 |
+
"rstrip": false,
|
| 520 |
+
"single_word": false,
|
| 521 |
+
"special": true
|
| 522 |
+
},
|
| 523 |
+
"32062": {
|
| 524 |
+
"content": "<extra_id_37>",
|
| 525 |
+
"lstrip": false,
|
| 526 |
+
"normalized": false,
|
| 527 |
+
"rstrip": false,
|
| 528 |
+
"single_word": false,
|
| 529 |
+
"special": true
|
| 530 |
+
},
|
| 531 |
+
"32063": {
|
| 532 |
+
"content": "<extra_id_36>",
|
| 533 |
+
"lstrip": false,
|
| 534 |
+
"normalized": false,
|
| 535 |
+
"rstrip": false,
|
| 536 |
+
"single_word": false,
|
| 537 |
+
"special": true
|
| 538 |
+
},
|
| 539 |
+
"32064": {
|
| 540 |
+
"content": "<extra_id_35>",
|
| 541 |
+
"lstrip": false,
|
| 542 |
+
"normalized": false,
|
| 543 |
+
"rstrip": false,
|
| 544 |
+
"single_word": false,
|
| 545 |
+
"special": true
|
| 546 |
+
},
|
| 547 |
+
"32065": {
|
| 548 |
+
"content": "<extra_id_34>",
|
| 549 |
+
"lstrip": false,
|
| 550 |
+
"normalized": false,
|
| 551 |
+
"rstrip": false,
|
| 552 |
+
"single_word": false,
|
| 553 |
+
"special": true
|
| 554 |
+
},
|
| 555 |
+
"32066": {
|
| 556 |
+
"content": "<extra_id_33>",
|
| 557 |
+
"lstrip": false,
|
| 558 |
+
"normalized": false,
|
| 559 |
+
"rstrip": false,
|
| 560 |
+
"single_word": false,
|
| 561 |
+
"special": true
|
| 562 |
+
},
|
| 563 |
+
"32067": {
|
| 564 |
+
"content": "<extra_id_32>",
|
| 565 |
+
"lstrip": false,
|
| 566 |
+
"normalized": false,
|
| 567 |
+
"rstrip": false,
|
| 568 |
+
"single_word": false,
|
| 569 |
+
"special": true
|
| 570 |
+
},
|
| 571 |
+
"32068": {
|
| 572 |
+
"content": "<extra_id_31>",
|
| 573 |
+
"lstrip": false,
|
| 574 |
+
"normalized": false,
|
| 575 |
+
"rstrip": false,
|
| 576 |
+
"single_word": false,
|
| 577 |
+
"special": true
|
| 578 |
+
},
|
| 579 |
+
"32069": {
|
| 580 |
+
"content": "<extra_id_30>",
|
| 581 |
+
"lstrip": false,
|
| 582 |
+
"normalized": false,
|
| 583 |
+
"rstrip": false,
|
| 584 |
+
"single_word": false,
|
| 585 |
+
"special": true
|
| 586 |
+
},
|
| 587 |
+
"32070": {
|
| 588 |
+
"content": "<extra_id_29>",
|
| 589 |
+
"lstrip": false,
|
| 590 |
+
"normalized": false,
|
| 591 |
+
"rstrip": false,
|
| 592 |
+
"single_word": false,
|
| 593 |
+
"special": true
|
| 594 |
+
},
|
| 595 |
+
"32071": {
|
| 596 |
+
"content": "<extra_id_28>",
|
| 597 |
+
"lstrip": false,
|
| 598 |
+
"normalized": false,
|
| 599 |
+
"rstrip": false,
|
| 600 |
+
"single_word": false,
|
| 601 |
+
"special": true
|
| 602 |
+
},
|
| 603 |
+
"32072": {
|
| 604 |
+
"content": "<extra_id_27>",
|
| 605 |
+
"lstrip": false,
|
| 606 |
+
"normalized": false,
|
| 607 |
+
"rstrip": false,
|
| 608 |
+
"single_word": false,
|
| 609 |
+
"special": true
|
| 610 |
+
},
|
| 611 |
+
"32073": {
|
| 612 |
+
"content": "<extra_id_26>",
|
| 613 |
+
"lstrip": false,
|
| 614 |
+
"normalized": false,
|
| 615 |
+
"rstrip": false,
|
| 616 |
+
"single_word": false,
|
| 617 |
+
"special": true
|
| 618 |
+
},
|
| 619 |
+
"32074": {
|
| 620 |
+
"content": "<extra_id_25>",
|
| 621 |
+
"lstrip": false,
|
| 622 |
+
"normalized": false,
|
| 623 |
+
"rstrip": false,
|
| 624 |
+
"single_word": false,
|
| 625 |
+
"special": true
|
| 626 |
+
},
|
| 627 |
+
"32075": {
|
| 628 |
+
"content": "<extra_id_24>",
|
| 629 |
+
"lstrip": false,
|
| 630 |
+
"normalized": false,
|
| 631 |
+
"rstrip": false,
|
| 632 |
+
"single_word": false,
|
| 633 |
+
"special": true
|
| 634 |
+
},
|
| 635 |
+
"32076": {
|
| 636 |
+
"content": "<extra_id_23>",
|
| 637 |
+
"lstrip": false,
|
| 638 |
+
"normalized": false,
|
| 639 |
+
"rstrip": false,
|
| 640 |
+
"single_word": false,
|
| 641 |
+
"special": true
|
| 642 |
+
},
|
| 643 |
+
"32077": {
|
| 644 |
+
"content": "<extra_id_22>",
|
| 645 |
+
"lstrip": false,
|
| 646 |
+
"normalized": false,
|
| 647 |
+
"rstrip": false,
|
| 648 |
+
"single_word": false,
|
| 649 |
+
"special": true
|
| 650 |
+
},
|
| 651 |
+
"32078": {
|
| 652 |
+
"content": "<extra_id_21>",
|
| 653 |
+
"lstrip": false,
|
| 654 |
+
"normalized": false,
|
| 655 |
+
"rstrip": false,
|
| 656 |
+
"single_word": false,
|
| 657 |
+
"special": true
|
| 658 |
+
},
|
| 659 |
+
"32079": {
|
| 660 |
+
"content": "<extra_id_20>",
|
| 661 |
+
"lstrip": false,
|
| 662 |
+
"normalized": false,
|
| 663 |
+
"rstrip": false,
|
| 664 |
+
"single_word": false,
|
| 665 |
+
"special": true
|
| 666 |
+
},
|
| 667 |
+
"32080": {
|
| 668 |
+
"content": "<extra_id_19>",
|
| 669 |
+
"lstrip": false,
|
| 670 |
+
"normalized": false,
|
| 671 |
+
"rstrip": false,
|
| 672 |
+
"single_word": false,
|
| 673 |
+
"special": true
|
| 674 |
+
},
|
| 675 |
+
"32081": {
|
| 676 |
+
"content": "<extra_id_18>",
|
| 677 |
+
"lstrip": false,
|
| 678 |
+
"normalized": false,
|
| 679 |
+
"rstrip": false,
|
| 680 |
+
"single_word": false,
|
| 681 |
+
"special": true
|
| 682 |
+
},
|
| 683 |
+
"32082": {
|
| 684 |
+
"content": "<extra_id_17>",
|
| 685 |
+
"lstrip": false,
|
| 686 |
+
"normalized": false,
|
| 687 |
+
"rstrip": false,
|
| 688 |
+
"single_word": false,
|
| 689 |
+
"special": true
|
| 690 |
+
},
|
| 691 |
+
"32083": {
|
| 692 |
+
"content": "<extra_id_16>",
|
| 693 |
+
"lstrip": false,
|
| 694 |
+
"normalized": false,
|
| 695 |
+
"rstrip": false,
|
| 696 |
+
"single_word": false,
|
| 697 |
+
"special": true
|
| 698 |
+
},
|
| 699 |
+
"32084": {
|
| 700 |
+
"content": "<extra_id_15>",
|
| 701 |
+
"lstrip": false,
|
| 702 |
+
"normalized": false,
|
| 703 |
+
"rstrip": false,
|
| 704 |
+
"single_word": false,
|
| 705 |
+
"special": true
|
| 706 |
+
},
|
| 707 |
+
"32085": {
|
| 708 |
+
"content": "<extra_id_14>",
|
| 709 |
+
"lstrip": false,
|
| 710 |
+
"normalized": false,
|
| 711 |
+
"rstrip": false,
|
| 712 |
+
"single_word": false,
|
| 713 |
+
"special": true
|
| 714 |
+
},
|
| 715 |
+
"32086": {
|
| 716 |
+
"content": "<extra_id_13>",
|
| 717 |
+
"lstrip": false,
|
| 718 |
+
"normalized": false,
|
| 719 |
+
"rstrip": false,
|
| 720 |
+
"single_word": false,
|
| 721 |
+
"special": true
|
| 722 |
+
},
|
| 723 |
+
"32087": {
|
| 724 |
+
"content": "<extra_id_12>",
|
| 725 |
+
"lstrip": false,
|
| 726 |
+
"normalized": false,
|
| 727 |
+
"rstrip": false,
|
| 728 |
+
"single_word": false,
|
| 729 |
+
"special": true
|
| 730 |
+
},
|
| 731 |
+
"32088": {
|
| 732 |
+
"content": "<extra_id_11>",
|
| 733 |
+
"lstrip": false,
|
| 734 |
+
"normalized": false,
|
| 735 |
+
"rstrip": false,
|
| 736 |
+
"single_word": false,
|
| 737 |
+
"special": true
|
| 738 |
+
},
|
| 739 |
+
"32089": {
|
| 740 |
+
"content": "<extra_id_10>",
|
| 741 |
+
"lstrip": false,
|
| 742 |
+
"normalized": false,
|
| 743 |
+
"rstrip": false,
|
| 744 |
+
"single_word": false,
|
| 745 |
+
"special": true
|
| 746 |
+
},
|
| 747 |
+
"32090": {
|
| 748 |
+
"content": "<extra_id_9>",
|
| 749 |
+
"lstrip": false,
|
| 750 |
+
"normalized": false,
|
| 751 |
+
"rstrip": false,
|
| 752 |
+
"single_word": false,
|
| 753 |
+
"special": true
|
| 754 |
+
},
|
| 755 |
+
"32091": {
|
| 756 |
+
"content": "<extra_id_8>",
|
| 757 |
+
"lstrip": false,
|
| 758 |
+
"normalized": false,
|
| 759 |
+
"rstrip": false,
|
| 760 |
+
"single_word": false,
|
| 761 |
+
"special": true
|
| 762 |
+
},
|
| 763 |
+
"32092": {
|
| 764 |
+
"content": "<extra_id_7>",
|
| 765 |
+
"lstrip": false,
|
| 766 |
+
"normalized": false,
|
| 767 |
+
"rstrip": false,
|
| 768 |
+
"single_word": false,
|
| 769 |
+
"special": true
|
| 770 |
+
},
|
| 771 |
+
"32093": {
|
| 772 |
+
"content": "<extra_id_6>",
|
| 773 |
+
"lstrip": false,
|
| 774 |
+
"normalized": false,
|
| 775 |
+
"rstrip": false,
|
| 776 |
+
"single_word": false,
|
| 777 |
+
"special": true
|
| 778 |
+
},
|
| 779 |
+
"32094": {
|
| 780 |
+
"content": "<extra_id_5>",
|
| 781 |
+
"lstrip": false,
|
| 782 |
+
"normalized": false,
|
| 783 |
+
"rstrip": false,
|
| 784 |
+
"single_word": false,
|
| 785 |
+
"special": true
|
| 786 |
+
},
|
| 787 |
+
"32095": {
|
| 788 |
+
"content": "<extra_id_4>",
|
| 789 |
+
"lstrip": false,
|
| 790 |
+
"normalized": false,
|
| 791 |
+
"rstrip": false,
|
| 792 |
+
"single_word": false,
|
| 793 |
+
"special": true
|
| 794 |
+
},
|
| 795 |
+
"32096": {
|
| 796 |
+
"content": "<extra_id_3>",
|
| 797 |
+
"lstrip": false,
|
| 798 |
+
"normalized": false,
|
| 799 |
+
"rstrip": false,
|
| 800 |
+
"single_word": false,
|
| 801 |
+
"special": true
|
| 802 |
+
},
|
| 803 |
+
"32097": {
|
| 804 |
+
"content": "<extra_id_2>",
|
| 805 |
+
"lstrip": false,
|
| 806 |
+
"normalized": false,
|
| 807 |
+
"rstrip": false,
|
| 808 |
+
"single_word": false,
|
| 809 |
+
"special": true
|
| 810 |
+
},
|
| 811 |
+
"32098": {
|
| 812 |
+
"content": "<extra_id_1>",
|
| 813 |
+
"lstrip": false,
|
| 814 |
+
"normalized": false,
|
| 815 |
+
"rstrip": false,
|
| 816 |
+
"single_word": false,
|
| 817 |
+
"special": true
|
| 818 |
+
},
|
| 819 |
+
"32099": {
|
| 820 |
+
"content": "<extra_id_0>",
|
| 821 |
+
"lstrip": false,
|
| 822 |
+
"normalized": false,
|
| 823 |
+
"rstrip": false,
|
| 824 |
+
"single_word": false,
|
| 825 |
+
"special": true
|
| 826 |
+
}
|
| 827 |
+
},
|
| 828 |
+
"additional_special_tokens": [
|
| 829 |
+
"<extra_id_0>",
|
| 830 |
+
"<extra_id_1>",
|
| 831 |
+
"<extra_id_2>",
|
| 832 |
+
"<extra_id_3>",
|
| 833 |
+
"<extra_id_4>",
|
| 834 |
+
"<extra_id_5>",
|
| 835 |
+
"<extra_id_6>",
|
| 836 |
+
"<extra_id_7>",
|
| 837 |
+
"<extra_id_8>",
|
| 838 |
+
"<extra_id_9>",
|
| 839 |
+
"<extra_id_10>",
|
| 840 |
+
"<extra_id_11>",
|
| 841 |
+
"<extra_id_12>",
|
| 842 |
+
"<extra_id_13>",
|
| 843 |
+
"<extra_id_14>",
|
| 844 |
+
"<extra_id_15>",
|
| 845 |
+
"<extra_id_16>",
|
| 846 |
+
"<extra_id_17>",
|
| 847 |
+
"<extra_id_18>",
|
| 848 |
+
"<extra_id_19>",
|
| 849 |
+
"<extra_id_20>",
|
| 850 |
+
"<extra_id_21>",
|
| 851 |
+
"<extra_id_22>",
|
| 852 |
+
"<extra_id_23>",
|
| 853 |
+
"<extra_id_24>",
|
| 854 |
+
"<extra_id_25>",
|
| 855 |
+
"<extra_id_26>",
|
| 856 |
+
"<extra_id_27>",
|
| 857 |
+
"<extra_id_28>",
|
| 858 |
+
"<extra_id_29>",
|
| 859 |
+
"<extra_id_30>",
|
| 860 |
+
"<extra_id_31>",
|
| 861 |
+
"<extra_id_32>",
|
| 862 |
+
"<extra_id_33>",
|
| 863 |
+
"<extra_id_34>",
|
| 864 |
+
"<extra_id_35>",
|
| 865 |
+
"<extra_id_36>",
|
| 866 |
+
"<extra_id_37>",
|
| 867 |
+
"<extra_id_38>",
|
| 868 |
+
"<extra_id_39>",
|
| 869 |
+
"<extra_id_40>",
|
| 870 |
+
"<extra_id_41>",
|
| 871 |
+
"<extra_id_42>",
|
| 872 |
+
"<extra_id_43>",
|
| 873 |
+
"<extra_id_44>",
|
| 874 |
+
"<extra_id_45>",
|
| 875 |
+
"<extra_id_46>",
|
| 876 |
+
"<extra_id_47>",
|
| 877 |
+
"<extra_id_48>",
|
| 878 |
+
"<extra_id_49>",
|
| 879 |
+
"<extra_id_50>",
|
| 880 |
+
"<extra_id_51>",
|
| 881 |
+
"<extra_id_52>",
|
| 882 |
+
"<extra_id_53>",
|
| 883 |
+
"<extra_id_54>",
|
| 884 |
+
"<extra_id_55>",
|
| 885 |
+
"<extra_id_56>",
|
| 886 |
+
"<extra_id_57>",
|
| 887 |
+
"<extra_id_58>",
|
| 888 |
+
"<extra_id_59>",
|
| 889 |
+
"<extra_id_60>",
|
| 890 |
+
"<extra_id_61>",
|
| 891 |
+
"<extra_id_62>",
|
| 892 |
+
"<extra_id_63>",
|
| 893 |
+
"<extra_id_64>",
|
| 894 |
+
"<extra_id_65>",
|
| 895 |
+
"<extra_id_66>",
|
| 896 |
+
"<extra_id_67>",
|
| 897 |
+
"<extra_id_68>",
|
| 898 |
+
"<extra_id_69>",
|
| 899 |
+
"<extra_id_70>",
|
| 900 |
+
"<extra_id_71>",
|
| 901 |
+
"<extra_id_72>",
|
| 902 |
+
"<extra_id_73>",
|
| 903 |
+
"<extra_id_74>",
|
| 904 |
+
"<extra_id_75>",
|
| 905 |
+
"<extra_id_76>",
|
| 906 |
+
"<extra_id_77>",
|
| 907 |
+
"<extra_id_78>",
|
| 908 |
+
"<extra_id_79>",
|
| 909 |
+
"<extra_id_80>",
|
| 910 |
+
"<extra_id_81>",
|
| 911 |
+
"<extra_id_82>",
|
| 912 |
+
"<extra_id_83>",
|
| 913 |
+
"<extra_id_84>",
|
| 914 |
+
"<extra_id_85>",
|
| 915 |
+
"<extra_id_86>",
|
| 916 |
+
"<extra_id_87>",
|
| 917 |
+
"<extra_id_88>",
|
| 918 |
+
"<extra_id_89>",
|
| 919 |
+
"<extra_id_90>",
|
| 920 |
+
"<extra_id_91>",
|
| 921 |
+
"<extra_id_92>",
|
| 922 |
+
"<extra_id_93>",
|
| 923 |
+
"<extra_id_94>",
|
| 924 |
+
"<extra_id_95>",
|
| 925 |
+
"<extra_id_96>",
|
| 926 |
+
"<extra_id_97>",
|
| 927 |
+
"<extra_id_98>",
|
| 928 |
+
"<extra_id_99>"
|
| 929 |
+
],
|
| 930 |
+
"clean_up_tokenization_spaces": true,
|
| 931 |
+
"eos_token": "</s>",
|
| 932 |
+
"extra_ids": 100,
|
| 933 |
+
"model_max_length": 512,
|
| 934 |
+
"pad_token": "<pad>",
|
| 935 |
+
"sp_model_kwargs": {},
|
| 936 |
+
"tokenizer_class": "T5Tokenizer",
|
| 937 |
+
"unk_token": "<unk>"
|
| 938 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,2404 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 3.9158332347869873,
|
| 3 |
+
"best_model_checkpoint": "/content/drive/MyDrive/checkpoints/checkpoint-3342",
|
| 4 |
+
"epoch": 3.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 3342,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.008976660682226212,
|
| 13 |
+
"grad_norm": 0.31800901889801025,
|
| 14 |
+
"learning_rate": 0.0004997755834829443,
|
| 15 |
+
"loss": 45.5673,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.017953321364452424,
|
| 20 |
+
"grad_norm": 0.35396715998649597,
|
| 21 |
+
"learning_rate": 0.0004995511669658887,
|
| 22 |
+
"loss": 45.3249,
|
| 23 |
+
"step": 20
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.026929982046678635,
|
| 27 |
+
"grad_norm": 0.37757596373558044,
|
| 28 |
+
"learning_rate": 0.000499326750448833,
|
| 29 |
+
"loss": 44.7853,
|
| 30 |
+
"step": 30
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.03590664272890485,
|
| 34 |
+
"grad_norm": 0.38259994983673096,
|
| 35 |
+
"learning_rate": 0.0004991023339317774,
|
| 36 |
+
"loss": 44.8996,
|
| 37 |
+
"step": 40
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.04488330341113106,
|
| 41 |
+
"grad_norm": 0.38321229815483093,
|
| 42 |
+
"learning_rate": 0.0004988779174147217,
|
| 43 |
+
"loss": 44.1242,
|
| 44 |
+
"step": 50
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.05385996409335727,
|
| 48 |
+
"grad_norm": 0.42167848348617554,
|
| 49 |
+
"learning_rate": 0.0004986535008976661,
|
| 50 |
+
"loss": 44.4739,
|
| 51 |
+
"step": 60
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.06283662477558348,
|
| 55 |
+
"grad_norm": 0.40018683671951294,
|
| 56 |
+
"learning_rate": 0.0004984290843806105,
|
| 57 |
+
"loss": 44.4548,
|
| 58 |
+
"step": 70
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.0718132854578097,
|
| 62 |
+
"grad_norm": 0.39394208788871765,
|
| 63 |
+
"learning_rate": 0.0004982046678635547,
|
| 64 |
+
"loss": 43.4622,
|
| 65 |
+
"step": 80
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.0807899461400359,
|
| 69 |
+
"grad_norm": 0.3660307228565216,
|
| 70 |
+
"learning_rate": 0.0004979802513464991,
|
| 71 |
+
"loss": 43.0475,
|
| 72 |
+
"step": 90
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.08976660682226212,
|
| 76 |
+
"grad_norm": 0.36663416028022766,
|
| 77 |
+
"learning_rate": 0.0004977558348294434,
|
| 78 |
+
"loss": 42.8994,
|
| 79 |
+
"step": 100
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.09874326750448834,
|
| 83 |
+
"grad_norm": 0.40418022871017456,
|
| 84 |
+
"learning_rate": 0.0004975314183123878,
|
| 85 |
+
"loss": 43.0499,
|
| 86 |
+
"step": 110
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.10771992818671454,
|
| 90 |
+
"grad_norm": 0.32946863770484924,
|
| 91 |
+
"learning_rate": 0.0004973070017953322,
|
| 92 |
+
"loss": 43.0516,
|
| 93 |
+
"step": 120
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.11669658886894076,
|
| 97 |
+
"grad_norm": 0.36427420377731323,
|
| 98 |
+
"learning_rate": 0.0004970825852782765,
|
| 99 |
+
"loss": 43.0005,
|
| 100 |
+
"step": 130
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.12567324955116696,
|
| 104 |
+
"grad_norm": 0.3754049837589264,
|
| 105 |
+
"learning_rate": 0.0004968581687612209,
|
| 106 |
+
"loss": 42.3461,
|
| 107 |
+
"step": 140
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.13464991023339318,
|
| 111 |
+
"grad_norm": 0.3867158889770508,
|
| 112 |
+
"learning_rate": 0.0004966337522441652,
|
| 113 |
+
"loss": 42.5113,
|
| 114 |
+
"step": 150
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.1436265709156194,
|
| 118 |
+
"grad_norm": 0.35019099712371826,
|
| 119 |
+
"learning_rate": 0.0004964093357271095,
|
| 120 |
+
"loss": 41.8364,
|
| 121 |
+
"step": 160
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.1526032315978456,
|
| 125 |
+
"grad_norm": 0.37168896198272705,
|
| 126 |
+
"learning_rate": 0.0004961849192100539,
|
| 127 |
+
"loss": 42.4202,
|
| 128 |
+
"step": 170
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.1615798922800718,
|
| 132 |
+
"grad_norm": 0.36585116386413574,
|
| 133 |
+
"learning_rate": 0.0004959605026929982,
|
| 134 |
+
"loss": 41.5454,
|
| 135 |
+
"step": 180
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.17055655296229802,
|
| 139 |
+
"grad_norm": 0.4089430272579193,
|
| 140 |
+
"learning_rate": 0.0004957360861759426,
|
| 141 |
+
"loss": 41.0863,
|
| 142 |
+
"step": 190
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.17953321364452424,
|
| 146 |
+
"grad_norm": 0.3681723475456238,
|
| 147 |
+
"learning_rate": 0.0004955116696588868,
|
| 148 |
+
"loss": 41.0869,
|
| 149 |
+
"step": 200
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.18850987432675045,
|
| 153 |
+
"grad_norm": 0.3823374807834625,
|
| 154 |
+
"learning_rate": 0.0004952872531418312,
|
| 155 |
+
"loss": 41.0254,
|
| 156 |
+
"step": 210
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.19748653500897667,
|
| 160 |
+
"grad_norm": 0.3909670412540436,
|
| 161 |
+
"learning_rate": 0.0004950628366247755,
|
| 162 |
+
"loss": 41.0026,
|
| 163 |
+
"step": 220
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.20646319569120286,
|
| 167 |
+
"grad_norm": 0.39831164479255676,
|
| 168 |
+
"learning_rate": 0.0004948384201077199,
|
| 169 |
+
"loss": 40.3224,
|
| 170 |
+
"step": 230
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.21543985637342908,
|
| 174 |
+
"grad_norm": 0.3801274597644806,
|
| 175 |
+
"learning_rate": 0.0004946140035906643,
|
| 176 |
+
"loss": 40.4711,
|
| 177 |
+
"step": 240
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.2244165170556553,
|
| 181 |
+
"grad_norm": 0.39255771040916443,
|
| 182 |
+
"learning_rate": 0.0004943895870736086,
|
| 183 |
+
"loss": 39.9713,
|
| 184 |
+
"step": 250
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.2333931777378815,
|
| 188 |
+
"grad_norm": 0.400642067193985,
|
| 189 |
+
"learning_rate": 0.000494165170556553,
|
| 190 |
+
"loss": 39.3574,
|
| 191 |
+
"step": 260
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.24236983842010773,
|
| 195 |
+
"grad_norm": 0.44542375206947327,
|
| 196 |
+
"learning_rate": 0.0004939407540394973,
|
| 197 |
+
"loss": 39.4756,
|
| 198 |
+
"step": 270
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.2513464991023339,
|
| 202 |
+
"grad_norm": 0.41471394896507263,
|
| 203 |
+
"learning_rate": 0.0004937163375224417,
|
| 204 |
+
"loss": 39.4551,
|
| 205 |
+
"step": 280
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.26032315978456017,
|
| 209 |
+
"grad_norm": 0.3956909775733948,
|
| 210 |
+
"learning_rate": 0.000493491921005386,
|
| 211 |
+
"loss": 39.0815,
|
| 212 |
+
"step": 290
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.26929982046678635,
|
| 216 |
+
"grad_norm": 0.5405673384666443,
|
| 217 |
+
"learning_rate": 0.0004932675044883304,
|
| 218 |
+
"loss": 38.7405,
|
| 219 |
+
"step": 300
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.27827648114901254,
|
| 223 |
+
"grad_norm": 0.4720427691936493,
|
| 224 |
+
"learning_rate": 0.0004930430879712747,
|
| 225 |
+
"loss": 38.1905,
|
| 226 |
+
"step": 310
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.2872531418312388,
|
| 230 |
+
"grad_norm": 0.4677943289279938,
|
| 231 |
+
"learning_rate": 0.0004928186714542191,
|
| 232 |
+
"loss": 38.023,
|
| 233 |
+
"step": 320
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.296229802513465,
|
| 237 |
+
"grad_norm": 0.4742816090583801,
|
| 238 |
+
"learning_rate": 0.0004925942549371633,
|
| 239 |
+
"loss": 37.6844,
|
| 240 |
+
"step": 330
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.3052064631956912,
|
| 244 |
+
"grad_norm": 0.463733047246933,
|
| 245 |
+
"learning_rate": 0.0004923698384201077,
|
| 246 |
+
"loss": 37.4262,
|
| 247 |
+
"step": 340
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.3141831238779174,
|
| 251 |
+
"grad_norm": 0.48447635769844055,
|
| 252 |
+
"learning_rate": 0.000492145421903052,
|
| 253 |
+
"loss": 37.1974,
|
| 254 |
+
"step": 350
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.3231597845601436,
|
| 258 |
+
"grad_norm": 0.5126340389251709,
|
| 259 |
+
"learning_rate": 0.0004919210053859964,
|
| 260 |
+
"loss": 36.4875,
|
| 261 |
+
"step": 360
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.33213644524236985,
|
| 265 |
+
"grad_norm": 0.5128099322319031,
|
| 266 |
+
"learning_rate": 0.0004916965888689407,
|
| 267 |
+
"loss": 36.8894,
|
| 268 |
+
"step": 370
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 0.34111310592459604,
|
| 272 |
+
"grad_norm": 0.5677986741065979,
|
| 273 |
+
"learning_rate": 0.0004914721723518851,
|
| 274 |
+
"loss": 36.0053,
|
| 275 |
+
"step": 380
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.3500897666068223,
|
| 279 |
+
"grad_norm": 0.6088815927505493,
|
| 280 |
+
"learning_rate": 0.0004912477558348294,
|
| 281 |
+
"loss": 36.2308,
|
| 282 |
+
"step": 390
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.3590664272890485,
|
| 286 |
+
"grad_norm": 0.5765969157218933,
|
| 287 |
+
"learning_rate": 0.0004910233393177738,
|
| 288 |
+
"loss": 35.4461,
|
| 289 |
+
"step": 400
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.36804308797127466,
|
| 293 |
+
"grad_norm": 0.5858592391014099,
|
| 294 |
+
"learning_rate": 0.0004907989228007182,
|
| 295 |
+
"loss": 35.0571,
|
| 296 |
+
"step": 410
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.3770197486535009,
|
| 300 |
+
"grad_norm": 0.6825990080833435,
|
| 301 |
+
"learning_rate": 0.0004905745062836625,
|
| 302 |
+
"loss": 34.717,
|
| 303 |
+
"step": 420
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.3859964093357271,
|
| 307 |
+
"grad_norm": 0.7166014313697815,
|
| 308 |
+
"learning_rate": 0.0004903500897666069,
|
| 309 |
+
"loss": 33.8366,
|
| 310 |
+
"step": 430
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 0.39497307001795334,
|
| 314 |
+
"grad_norm": 0.6887209415435791,
|
| 315 |
+
"learning_rate": 0.0004901256732495512,
|
| 316 |
+
"loss": 33.7563,
|
| 317 |
+
"step": 440
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.40394973070017953,
|
| 321 |
+
"grad_norm": 0.7413772344589233,
|
| 322 |
+
"learning_rate": 0.0004899012567324956,
|
| 323 |
+
"loss": 33.1205,
|
| 324 |
+
"step": 450
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.4129263913824057,
|
| 328 |
+
"grad_norm": 0.7537035942077637,
|
| 329 |
+
"learning_rate": 0.0004896768402154398,
|
| 330 |
+
"loss": 32.9826,
|
| 331 |
+
"step": 460
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.42190305206463197,
|
| 335 |
+
"grad_norm": 0.730989396572113,
|
| 336 |
+
"learning_rate": 0.0004894524236983842,
|
| 337 |
+
"loss": 31.9265,
|
| 338 |
+
"step": 470
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.43087971274685816,
|
| 342 |
+
"grad_norm": 0.9165148735046387,
|
| 343 |
+
"learning_rate": 0.0004892280071813285,
|
| 344 |
+
"loss": 31.3014,
|
| 345 |
+
"step": 480
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.4398563734290844,
|
| 349 |
+
"grad_norm": 0.8587144613265991,
|
| 350 |
+
"learning_rate": 0.0004890035906642729,
|
| 351 |
+
"loss": 30.889,
|
| 352 |
+
"step": 490
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 0.4488330341113106,
|
| 356 |
+
"grad_norm": 0.9183847904205322,
|
| 357 |
+
"learning_rate": 0.0004887791741472172,
|
| 358 |
+
"loss": 30.1653,
|
| 359 |
+
"step": 500
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 0.4578096947935368,
|
| 363 |
+
"grad_norm": 0.9044579863548279,
|
| 364 |
+
"learning_rate": 0.0004885547576301616,
|
| 365 |
+
"loss": 29.9274,
|
| 366 |
+
"step": 510
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 0.466786355475763,
|
| 370 |
+
"grad_norm": 0.8621285557746887,
|
| 371 |
+
"learning_rate": 0.0004883303411131059,
|
| 372 |
+
"loss": 29.5479,
|
| 373 |
+
"step": 520
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 0.4757630161579892,
|
| 377 |
+
"grad_norm": 1.1030315160751343,
|
| 378 |
+
"learning_rate": 0.0004881059245960503,
|
| 379 |
+
"loss": 29.1674,
|
| 380 |
+
"step": 530
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 0.48473967684021546,
|
| 384 |
+
"grad_norm": 1.071616768836975,
|
| 385 |
+
"learning_rate": 0.00048788150807899463,
|
| 386 |
+
"loss": 28.5656,
|
| 387 |
+
"step": 540
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.49371633752244165,
|
| 391 |
+
"grad_norm": 0.9452396035194397,
|
| 392 |
+
"learning_rate": 0.000487657091561939,
|
| 393 |
+
"loss": 28.1162,
|
| 394 |
+
"step": 550
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 0.5026929982046678,
|
| 398 |
+
"grad_norm": 0.9999839067459106,
|
| 399 |
+
"learning_rate": 0.0004874326750448833,
|
| 400 |
+
"loss": 27.1627,
|
| 401 |
+
"step": 560
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 0.5116696588868941,
|
| 405 |
+
"grad_norm": 1.5522288084030151,
|
| 406 |
+
"learning_rate": 0.00048720825852782766,
|
| 407 |
+
"loss": 26.8812,
|
| 408 |
+
"step": 570
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 0.5206463195691203,
|
| 412 |
+
"grad_norm": 1.1541786193847656,
|
| 413 |
+
"learning_rate": 0.000486983842010772,
|
| 414 |
+
"loss": 26.2589,
|
| 415 |
+
"step": 580
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 0.5296229802513465,
|
| 419 |
+
"grad_norm": 0.9977880120277405,
|
| 420 |
+
"learning_rate": 0.00048675942549371634,
|
| 421 |
+
"loss": 26.168,
|
| 422 |
+
"step": 590
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 0.5385996409335727,
|
| 426 |
+
"grad_norm": 0.9028811454772949,
|
| 427 |
+
"learning_rate": 0.0004865350089766607,
|
| 428 |
+
"loss": 24.9378,
|
| 429 |
+
"step": 600
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.547576301615799,
|
| 433 |
+
"grad_norm": 1.0026092529296875,
|
| 434 |
+
"learning_rate": 0.00048631059245960503,
|
| 435 |
+
"loss": 25.0135,
|
| 436 |
+
"step": 610
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 0.5565529622980251,
|
| 440 |
+
"grad_norm": 1.0198203325271606,
|
| 441 |
+
"learning_rate": 0.00048608617594254937,
|
| 442 |
+
"loss": 24.6053,
|
| 443 |
+
"step": 620
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 0.5655296229802513,
|
| 447 |
+
"grad_norm": 1.1564388275146484,
|
| 448 |
+
"learning_rate": 0.0004858617594254937,
|
| 449 |
+
"loss": 24.0813,
|
| 450 |
+
"step": 630
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 0.5745062836624776,
|
| 454 |
+
"grad_norm": 0.8892808556556702,
|
| 455 |
+
"learning_rate": 0.0004856373429084381,
|
| 456 |
+
"loss": 23.7441,
|
| 457 |
+
"step": 640
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 0.5834829443447038,
|
| 461 |
+
"grad_norm": 1.1114846467971802,
|
| 462 |
+
"learning_rate": 0.0004854129263913824,
|
| 463 |
+
"loss": 22.8734,
|
| 464 |
+
"step": 650
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 0.59245960502693,
|
| 468 |
+
"grad_norm": 1.0558847188949585,
|
| 469 |
+
"learning_rate": 0.0004851885098743268,
|
| 470 |
+
"loss": 22.3045,
|
| 471 |
+
"step": 660
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.6014362657091562,
|
| 475 |
+
"grad_norm": 0.8897343277931213,
|
| 476 |
+
"learning_rate": 0.0004849640933572711,
|
| 477 |
+
"loss": 21.977,
|
| 478 |
+
"step": 670
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 0.6104129263913824,
|
| 482 |
+
"grad_norm": 0.9796168208122253,
|
| 483 |
+
"learning_rate": 0.0004847396768402155,
|
| 484 |
+
"loss": 21.5113,
|
| 485 |
+
"step": 680
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 0.6193895870736086,
|
| 489 |
+
"grad_norm": 0.8519884943962097,
|
| 490 |
+
"learning_rate": 0.0004845152603231598,
|
| 491 |
+
"loss": 20.9744,
|
| 492 |
+
"step": 690
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 0.6283662477558348,
|
| 496 |
+
"grad_norm": 1.1632051467895508,
|
| 497 |
+
"learning_rate": 0.00048429084380610416,
|
| 498 |
+
"loss": 20.271,
|
| 499 |
+
"step": 700
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 0.6373429084380611,
|
| 503 |
+
"grad_norm": 0.9868700504302979,
|
| 504 |
+
"learning_rate": 0.0004840664272890485,
|
| 505 |
+
"loss": 19.9961,
|
| 506 |
+
"step": 710
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 0.6463195691202872,
|
| 510 |
+
"grad_norm": 0.9679480791091919,
|
| 511 |
+
"learning_rate": 0.0004838420107719928,
|
| 512 |
+
"loss": 19.4405,
|
| 513 |
+
"step": 720
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.6552962298025135,
|
| 517 |
+
"grad_norm": 1.0145677328109741,
|
| 518 |
+
"learning_rate": 0.0004836175942549372,
|
| 519 |
+
"loss": 19.2046,
|
| 520 |
+
"step": 730
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 0.6642728904847397,
|
| 524 |
+
"grad_norm": 1.0279533863067627,
|
| 525 |
+
"learning_rate": 0.00048339317773788147,
|
| 526 |
+
"loss": 18.2792,
|
| 527 |
+
"step": 740
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 0.6732495511669659,
|
| 531 |
+
"grad_norm": 1.2876602411270142,
|
| 532 |
+
"learning_rate": 0.00048316876122082587,
|
| 533 |
+
"loss": 17.8022,
|
| 534 |
+
"step": 750
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 0.6822262118491921,
|
| 538 |
+
"grad_norm": 1.0419774055480957,
|
| 539 |
+
"learning_rate": 0.0004829443447037702,
|
| 540 |
+
"loss": 17.4577,
|
| 541 |
+
"step": 760
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 0.6912028725314183,
|
| 545 |
+
"grad_norm": 1.0887730121612549,
|
| 546 |
+
"learning_rate": 0.00048271992818671455,
|
| 547 |
+
"loss": 16.5106,
|
| 548 |
+
"step": 770
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 0.7001795332136446,
|
| 552 |
+
"grad_norm": 1.1203436851501465,
|
| 553 |
+
"learning_rate": 0.0004824955116696589,
|
| 554 |
+
"loss": 16.4582,
|
| 555 |
+
"step": 780
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 0.7091561938958707,
|
| 559 |
+
"grad_norm": 1.0770111083984375,
|
| 560 |
+
"learning_rate": 0.00048227109515260324,
|
| 561 |
+
"loss": 16.003,
|
| 562 |
+
"step": 790
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 0.718132854578097,
|
| 566 |
+
"grad_norm": 1.2158771753311157,
|
| 567 |
+
"learning_rate": 0.0004820466786355476,
|
| 568 |
+
"loss": 15.2694,
|
| 569 |
+
"step": 800
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 0.7271095152603232,
|
| 573 |
+
"grad_norm": 1.1706403493881226,
|
| 574 |
+
"learning_rate": 0.000481822262118492,
|
| 575 |
+
"loss": 14.9252,
|
| 576 |
+
"step": 810
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 0.7360861759425493,
|
| 580 |
+
"grad_norm": 1.189310908317566,
|
| 581 |
+
"learning_rate": 0.00048159784560143626,
|
| 582 |
+
"loss": 14.4921,
|
| 583 |
+
"step": 820
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 0.7450628366247756,
|
| 587 |
+
"grad_norm": 1.6199108362197876,
|
| 588 |
+
"learning_rate": 0.00048137342908438066,
|
| 589 |
+
"loss": 13.9443,
|
| 590 |
+
"step": 830
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 0.7540394973070018,
|
| 594 |
+
"grad_norm": 1.1757200956344604,
|
| 595 |
+
"learning_rate": 0.00048114901256732494,
|
| 596 |
+
"loss": 13.8288,
|
| 597 |
+
"step": 840
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 0.7630161579892281,
|
| 601 |
+
"grad_norm": 1.2064054012298584,
|
| 602 |
+
"learning_rate": 0.00048092459605026934,
|
| 603 |
+
"loss": 12.9563,
|
| 604 |
+
"step": 850
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 0.7719928186714542,
|
| 608 |
+
"grad_norm": 1.1954108476638794,
|
| 609 |
+
"learning_rate": 0.00048070017953321363,
|
| 610 |
+
"loss": 12.1382,
|
| 611 |
+
"step": 860
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 0.7809694793536804,
|
| 615 |
+
"grad_norm": 1.5387598276138306,
|
| 616 |
+
"learning_rate": 0.00048047576301615797,
|
| 617 |
+
"loss": 12.1248,
|
| 618 |
+
"step": 870
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 0.7899461400359067,
|
| 622 |
+
"grad_norm": 1.2923359870910645,
|
| 623 |
+
"learning_rate": 0.00048025134649910237,
|
| 624 |
+
"loss": 11.7902,
|
| 625 |
+
"step": 880
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 0.7989228007181328,
|
| 629 |
+
"grad_norm": 0.9865145683288574,
|
| 630 |
+
"learning_rate": 0.00048002692998204665,
|
| 631 |
+
"loss": 10.7329,
|
| 632 |
+
"step": 890
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 0.8078994614003591,
|
| 636 |
+
"grad_norm": 1.140541672706604,
|
| 637 |
+
"learning_rate": 0.00047980251346499105,
|
| 638 |
+
"loss": 10.5986,
|
| 639 |
+
"step": 900
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 0.8168761220825853,
|
| 643 |
+
"grad_norm": 1.1022454500198364,
|
| 644 |
+
"learning_rate": 0.00047957809694793534,
|
| 645 |
+
"loss": 10.2782,
|
| 646 |
+
"step": 910
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 0.8258527827648114,
|
| 650 |
+
"grad_norm": 0.8876429200172424,
|
| 651 |
+
"learning_rate": 0.00047935368043087973,
|
| 652 |
+
"loss": 9.3573,
|
| 653 |
+
"step": 920
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 0.8348294434470377,
|
| 657 |
+
"grad_norm": 0.9144046306610107,
|
| 658 |
+
"learning_rate": 0.0004791292639138241,
|
| 659 |
+
"loss": 9.4616,
|
| 660 |
+
"step": 930
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 0.8438061041292639,
|
| 664 |
+
"grad_norm": 1.022176742553711,
|
| 665 |
+
"learning_rate": 0.0004789048473967684,
|
| 666 |
+
"loss": 9.0571,
|
| 667 |
+
"step": 940
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 0.8527827648114902,
|
| 671 |
+
"grad_norm": 0.9050130248069763,
|
| 672 |
+
"learning_rate": 0.00047868043087971276,
|
| 673 |
+
"loss": 8.4811,
|
| 674 |
+
"step": 950
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 0.8617594254937163,
|
| 678 |
+
"grad_norm": 0.8372008800506592,
|
| 679 |
+
"learning_rate": 0.0004784560143626571,
|
| 680 |
+
"loss": 8.3873,
|
| 681 |
+
"step": 960
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 0.8707360861759426,
|
| 685 |
+
"grad_norm": 0.8663610816001892,
|
| 686 |
+
"learning_rate": 0.00047823159784560144,
|
| 687 |
+
"loss": 8.0233,
|
| 688 |
+
"step": 970
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 0.8797127468581688,
|
| 692 |
+
"grad_norm": 0.6936354637145996,
|
| 693 |
+
"learning_rate": 0.00047800718132854584,
|
| 694 |
+
"loss": 7.8054,
|
| 695 |
+
"step": 980
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 0.8886894075403949,
|
| 699 |
+
"grad_norm": 0.5529871582984924,
|
| 700 |
+
"learning_rate": 0.00047778276481149013,
|
| 701 |
+
"loss": 7.6013,
|
| 702 |
+
"step": 990
|
| 703 |
+
},
|
| 704 |
+
{
|
| 705 |
+
"epoch": 0.8976660682226212,
|
| 706 |
+
"grad_norm": 0.6260952353477478,
|
| 707 |
+
"learning_rate": 0.00047755834829443447,
|
| 708 |
+
"loss": 7.4237,
|
| 709 |
+
"step": 1000
|
| 710 |
+
},
|
| 711 |
+
{
|
| 712 |
+
"epoch": 0.9066427289048474,
|
| 713 |
+
"grad_norm": 0.851337730884552,
|
| 714 |
+
"learning_rate": 0.0004773339317773788,
|
| 715 |
+
"loss": 7.2549,
|
| 716 |
+
"step": 1010
|
| 717 |
+
},
|
| 718 |
+
{
|
| 719 |
+
"epoch": 0.9156193895870736,
|
| 720 |
+
"grad_norm": 0.6702756285667419,
|
| 721 |
+
"learning_rate": 0.00047710951526032315,
|
| 722 |
+
"loss": 7.0967,
|
| 723 |
+
"step": 1020
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 0.9245960502692998,
|
| 727 |
+
"grad_norm": 0.6650304794311523,
|
| 728 |
+
"learning_rate": 0.0004768850987432675,
|
| 729 |
+
"loss": 6.9988,
|
| 730 |
+
"step": 1030
|
| 731 |
+
},
|
| 732 |
+
{
|
| 733 |
+
"epoch": 0.933572710951526,
|
| 734 |
+
"grad_norm": 0.551717221736908,
|
| 735 |
+
"learning_rate": 0.00047666068222621184,
|
| 736 |
+
"loss": 6.5465,
|
| 737 |
+
"step": 1040
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 0.9425493716337523,
|
| 741 |
+
"grad_norm": 0.4560067653656006,
|
| 742 |
+
"learning_rate": 0.00047643626570915623,
|
| 743 |
+
"loss": 6.5641,
|
| 744 |
+
"step": 1050
|
| 745 |
+
},
|
| 746 |
+
{
|
| 747 |
+
"epoch": 0.9515260323159784,
|
| 748 |
+
"grad_norm": 0.4556948244571686,
|
| 749 |
+
"learning_rate": 0.0004762118491921005,
|
| 750 |
+
"loss": 6.6911,
|
| 751 |
+
"step": 1060
|
| 752 |
+
},
|
| 753 |
+
{
|
| 754 |
+
"epoch": 0.9605026929982047,
|
| 755 |
+
"grad_norm": 0.8652740716934204,
|
| 756 |
+
"learning_rate": 0.0004759874326750449,
|
| 757 |
+
"loss": 6.7453,
|
| 758 |
+
"step": 1070
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 0.9694793536804309,
|
| 762 |
+
"grad_norm": 0.32210618257522583,
|
| 763 |
+
"learning_rate": 0.0004757630161579892,
|
| 764 |
+
"loss": 6.5263,
|
| 765 |
+
"step": 1080
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 0.9784560143626571,
|
| 769 |
+
"grad_norm": 1.9738398790359497,
|
| 770 |
+
"learning_rate": 0.0004755385996409336,
|
| 771 |
+
"loss": 6.4019,
|
| 772 |
+
"step": 1090
|
| 773 |
+
},
|
| 774 |
+
{
|
| 775 |
+
"epoch": 0.9874326750448833,
|
| 776 |
+
"grad_norm": 0.31478866934776306,
|
| 777 |
+
"learning_rate": 0.00047531418312387794,
|
| 778 |
+
"loss": 6.266,
|
| 779 |
+
"step": 1100
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 0.9964093357271095,
|
| 783 |
+
"grad_norm": 0.39359068870544434,
|
| 784 |
+
"learning_rate": 0.0004750897666068223,
|
| 785 |
+
"loss": 6.2422,
|
| 786 |
+
"step": 1110
|
| 787 |
+
},
|
| 788 |
+
{
|
| 789 |
+
"epoch": 1.0,
|
| 790 |
+
"eval_loss": 5.025014400482178,
|
| 791 |
+
"eval_runtime": 436.9889,
|
| 792 |
+
"eval_samples_per_second": 10.197,
|
| 793 |
+
"eval_steps_per_second": 1.275,
|
| 794 |
+
"step": 1114
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 1.0053859964093357,
|
| 798 |
+
"grad_norm": 0.3087250888347626,
|
| 799 |
+
"learning_rate": 0.0004748653500897666,
|
| 800 |
+
"loss": 6.1059,
|
| 801 |
+
"step": 1120
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 1.014362657091562,
|
| 805 |
+
"grad_norm": 0.4997764825820923,
|
| 806 |
+
"learning_rate": 0.00047464093357271097,
|
| 807 |
+
"loss": 6.1567,
|
| 808 |
+
"step": 1130
|
| 809 |
+
},
|
| 810 |
+
{
|
| 811 |
+
"epoch": 1.0233393177737882,
|
| 812 |
+
"grad_norm": 0.4492017328739166,
|
| 813 |
+
"learning_rate": 0.0004744165170556553,
|
| 814 |
+
"loss": 6.0689,
|
| 815 |
+
"step": 1140
|
| 816 |
+
},
|
| 817 |
+
{
|
| 818 |
+
"epoch": 1.0323159784560143,
|
| 819 |
+
"grad_norm": 0.35565611720085144,
|
| 820 |
+
"learning_rate": 0.00047419210053859965,
|
| 821 |
+
"loss": 5.9551,
|
| 822 |
+
"step": 1150
|
| 823 |
+
},
|
| 824 |
+
{
|
| 825 |
+
"epoch": 1.0412926391382407,
|
| 826 |
+
"grad_norm": 0.28686025738716125,
|
| 827 |
+
"learning_rate": 0.000473967684021544,
|
| 828 |
+
"loss": 5.9306,
|
| 829 |
+
"step": 1160
|
| 830 |
+
},
|
| 831 |
+
{
|
| 832 |
+
"epoch": 1.0502692998204668,
|
| 833 |
+
"grad_norm": 0.28098103404045105,
|
| 834 |
+
"learning_rate": 0.00047374326750448834,
|
| 835 |
+
"loss": 5.8205,
|
| 836 |
+
"step": 1170
|
| 837 |
+
},
|
| 838 |
+
{
|
| 839 |
+
"epoch": 1.059245960502693,
|
| 840 |
+
"grad_norm": 0.3124157190322876,
|
| 841 |
+
"learning_rate": 0.0004735188509874327,
|
| 842 |
+
"loss": 5.7734,
|
| 843 |
+
"step": 1180
|
| 844 |
+
},
|
| 845 |
+
{
|
| 846 |
+
"epoch": 1.0682226211849193,
|
| 847 |
+
"grad_norm": 0.27604150772094727,
|
| 848 |
+
"learning_rate": 0.000473294434470377,
|
| 849 |
+
"loss": 5.8549,
|
| 850 |
+
"step": 1190
|
| 851 |
+
},
|
| 852 |
+
{
|
| 853 |
+
"epoch": 1.0771992818671454,
|
| 854 |
+
"grad_norm": 0.48105934262275696,
|
| 855 |
+
"learning_rate": 0.00047307001795332136,
|
| 856 |
+
"loss": 5.8208,
|
| 857 |
+
"step": 1200
|
| 858 |
+
},
|
| 859 |
+
{
|
| 860 |
+
"epoch": 1.0861759425493716,
|
| 861 |
+
"grad_norm": 0.33073532581329346,
|
| 862 |
+
"learning_rate": 0.0004728456014362657,
|
| 863 |
+
"loss": 5.7798,
|
| 864 |
+
"step": 1210
|
| 865 |
+
},
|
| 866 |
+
{
|
| 867 |
+
"epoch": 1.095152603231598,
|
| 868 |
+
"grad_norm": 0.24770517647266388,
|
| 869 |
+
"learning_rate": 0.0004726211849192101,
|
| 870 |
+
"loss": 5.6513,
|
| 871 |
+
"step": 1220
|
| 872 |
+
},
|
| 873 |
+
{
|
| 874 |
+
"epoch": 1.104129263913824,
|
| 875 |
+
"grad_norm": 0.23116350173950195,
|
| 876 |
+
"learning_rate": 0.0004723967684021544,
|
| 877 |
+
"loss": 5.6458,
|
| 878 |
+
"step": 1230
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"epoch": 1.1131059245960502,
|
| 882 |
+
"grad_norm": 0.2757456302642822,
|
| 883 |
+
"learning_rate": 0.0004721723518850988,
|
| 884 |
+
"loss": 5.7592,
|
| 885 |
+
"step": 1240
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 1.1220825852782765,
|
| 889 |
+
"grad_norm": 0.23286688327789307,
|
| 890 |
+
"learning_rate": 0.00047194793536804307,
|
| 891 |
+
"loss": 5.6889,
|
| 892 |
+
"step": 1250
|
| 893 |
+
},
|
| 894 |
+
{
|
| 895 |
+
"epoch": 1.1310592459605027,
|
| 896 |
+
"grad_norm": 0.1967301219701767,
|
| 897 |
+
"learning_rate": 0.00047172351885098747,
|
| 898 |
+
"loss": 5.5865,
|
| 899 |
+
"step": 1260
|
| 900 |
+
},
|
| 901 |
+
{
|
| 902 |
+
"epoch": 1.140035906642729,
|
| 903 |
+
"grad_norm": 0.22576653957366943,
|
| 904 |
+
"learning_rate": 0.0004714991023339318,
|
| 905 |
+
"loss": 5.4764,
|
| 906 |
+
"step": 1270
|
| 907 |
+
},
|
| 908 |
+
{
|
| 909 |
+
"epoch": 1.1490125673249552,
|
| 910 |
+
"grad_norm": 0.217813640832901,
|
| 911 |
+
"learning_rate": 0.00047127468581687615,
|
| 912 |
+
"loss": 5.6309,
|
| 913 |
+
"step": 1280
|
| 914 |
+
},
|
| 915 |
+
{
|
| 916 |
+
"epoch": 1.1579892280071813,
|
| 917 |
+
"grad_norm": 0.1798250824213028,
|
| 918 |
+
"learning_rate": 0.0004710502692998205,
|
| 919 |
+
"loss": 5.4452,
|
| 920 |
+
"step": 1290
|
| 921 |
+
},
|
| 922 |
+
{
|
| 923 |
+
"epoch": 1.1669658886894076,
|
| 924 |
+
"grad_norm": 0.22210471332073212,
|
| 925 |
+
"learning_rate": 0.0004708258527827648,
|
| 926 |
+
"loss": 5.5905,
|
| 927 |
+
"step": 1300
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"epoch": 1.1759425493716338,
|
| 931 |
+
"grad_norm": 0.24236564338207245,
|
| 932 |
+
"learning_rate": 0.0004706014362657092,
|
| 933 |
+
"loss": 5.5106,
|
| 934 |
+
"step": 1310
|
| 935 |
+
},
|
| 936 |
+
{
|
| 937 |
+
"epoch": 1.18491921005386,
|
| 938 |
+
"grad_norm": 0.205738365650177,
|
| 939 |
+
"learning_rate": 0.00047037701974865346,
|
| 940 |
+
"loss": 5.4863,
|
| 941 |
+
"step": 1320
|
| 942 |
+
},
|
| 943 |
+
{
|
| 944 |
+
"epoch": 1.1938958707360863,
|
| 945 |
+
"grad_norm": 0.2275596708059311,
|
| 946 |
+
"learning_rate": 0.00047015260323159786,
|
| 947 |
+
"loss": 5.4782,
|
| 948 |
+
"step": 1330
|
| 949 |
+
},
|
| 950 |
+
{
|
| 951 |
+
"epoch": 1.2028725314183124,
|
| 952 |
+
"grad_norm": 0.40637847781181335,
|
| 953 |
+
"learning_rate": 0.0004699281867145422,
|
| 954 |
+
"loss": 5.4103,
|
| 955 |
+
"step": 1340
|
| 956 |
+
},
|
| 957 |
+
{
|
| 958 |
+
"epoch": 1.2118491921005385,
|
| 959 |
+
"grad_norm": 0.17678338289260864,
|
| 960 |
+
"learning_rate": 0.00046970377019748654,
|
| 961 |
+
"loss": 5.3858,
|
| 962 |
+
"step": 1350
|
| 963 |
+
},
|
| 964 |
+
{
|
| 965 |
+
"epoch": 1.220825852782765,
|
| 966 |
+
"grad_norm": 0.1862853765487671,
|
| 967 |
+
"learning_rate": 0.0004694793536804309,
|
| 968 |
+
"loss": 5.379,
|
| 969 |
+
"step": 1360
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 1.229802513464991,
|
| 973 |
+
"grad_norm": 0.12334032356739044,
|
| 974 |
+
"learning_rate": 0.0004692549371633752,
|
| 975 |
+
"loss": 5.396,
|
| 976 |
+
"step": 1370
|
| 977 |
+
},
|
| 978 |
+
{
|
| 979 |
+
"epoch": 1.2387791741472172,
|
| 980 |
+
"grad_norm": 0.15632939338684082,
|
| 981 |
+
"learning_rate": 0.00046903052064631957,
|
| 982 |
+
"loss": 5.3853,
|
| 983 |
+
"step": 1380
|
| 984 |
+
},
|
| 985 |
+
{
|
| 986 |
+
"epoch": 1.2477558348294435,
|
| 987 |
+
"grad_norm": 0.18021011352539062,
|
| 988 |
+
"learning_rate": 0.00046880610412926396,
|
| 989 |
+
"loss": 5.2905,
|
| 990 |
+
"step": 1390
|
| 991 |
+
},
|
| 992 |
+
{
|
| 993 |
+
"epoch": 1.2567324955116697,
|
| 994 |
+
"grad_norm": 0.15651032328605652,
|
| 995 |
+
"learning_rate": 0.00046858168761220825,
|
| 996 |
+
"loss": 5.4102,
|
| 997 |
+
"step": 1400
|
| 998 |
+
},
|
| 999 |
+
{
|
| 1000 |
+
"epoch": 1.2657091561938958,
|
| 1001 |
+
"grad_norm": 0.15990717709064484,
|
| 1002 |
+
"learning_rate": 0.00046835727109515265,
|
| 1003 |
+
"loss": 5.3213,
|
| 1004 |
+
"step": 1410
|
| 1005 |
+
},
|
| 1006 |
+
{
|
| 1007 |
+
"epoch": 1.2746858168761221,
|
| 1008 |
+
"grad_norm": 0.23683366179466248,
|
| 1009 |
+
"learning_rate": 0.00046813285457809694,
|
| 1010 |
+
"loss": 5.3596,
|
| 1011 |
+
"step": 1420
|
| 1012 |
+
},
|
| 1013 |
+
{
|
| 1014 |
+
"epoch": 1.2836624775583483,
|
| 1015 |
+
"grad_norm": 0.17186540365219116,
|
| 1016 |
+
"learning_rate": 0.0004679084380610413,
|
| 1017 |
+
"loss": 5.2734,
|
| 1018 |
+
"step": 1430
|
| 1019 |
+
},
|
| 1020 |
+
{
|
| 1021 |
+
"epoch": 1.2926391382405744,
|
| 1022 |
+
"grad_norm": 0.12084522843360901,
|
| 1023 |
+
"learning_rate": 0.0004676840215439857,
|
| 1024 |
+
"loss": 5.2741,
|
| 1025 |
+
"step": 1440
|
| 1026 |
+
},
|
| 1027 |
+
{
|
| 1028 |
+
"epoch": 1.3016157989228008,
|
| 1029 |
+
"grad_norm": 0.13929304480552673,
|
| 1030 |
+
"learning_rate": 0.00046745960502692996,
|
| 1031 |
+
"loss": 5.2734,
|
| 1032 |
+
"step": 1450
|
| 1033 |
+
},
|
| 1034 |
+
{
|
| 1035 |
+
"epoch": 1.310592459605027,
|
| 1036 |
+
"grad_norm": 0.22931580245494843,
|
| 1037 |
+
"learning_rate": 0.00046723518850987436,
|
| 1038 |
+
"loss": 5.2281,
|
| 1039 |
+
"step": 1460
|
| 1040 |
+
},
|
| 1041 |
+
{
|
| 1042 |
+
"epoch": 1.319569120287253,
|
| 1043 |
+
"grad_norm": 0.13986773788928986,
|
| 1044 |
+
"learning_rate": 0.00046701077199281865,
|
| 1045 |
+
"loss": 5.2185,
|
| 1046 |
+
"step": 1470
|
| 1047 |
+
},
|
| 1048 |
+
{
|
| 1049 |
+
"epoch": 1.3285457809694794,
|
| 1050 |
+
"grad_norm": 0.11496925354003906,
|
| 1051 |
+
"learning_rate": 0.00046678635547576304,
|
| 1052 |
+
"loss": 5.2082,
|
| 1053 |
+
"step": 1480
|
| 1054 |
+
},
|
| 1055 |
+
{
|
| 1056 |
+
"epoch": 1.3375224416517055,
|
| 1057 |
+
"grad_norm": 0.2594555616378784,
|
| 1058 |
+
"learning_rate": 0.00046656193895870733,
|
| 1059 |
+
"loss": 5.1917,
|
| 1060 |
+
"step": 1490
|
| 1061 |
+
},
|
| 1062 |
+
{
|
| 1063 |
+
"epoch": 1.3464991023339317,
|
| 1064 |
+
"grad_norm": 0.13332834839820862,
|
| 1065 |
+
"learning_rate": 0.0004663375224416517,
|
| 1066 |
+
"loss": 5.1701,
|
| 1067 |
+
"step": 1500
|
| 1068 |
+
},
|
| 1069 |
+
{
|
| 1070 |
+
"epoch": 1.355475763016158,
|
| 1071 |
+
"grad_norm": 0.1260669082403183,
|
| 1072 |
+
"learning_rate": 0.00046611310592459607,
|
| 1073 |
+
"loss": 5.1703,
|
| 1074 |
+
"step": 1510
|
| 1075 |
+
},
|
| 1076 |
+
{
|
| 1077 |
+
"epoch": 1.3644524236983842,
|
| 1078 |
+
"grad_norm": 0.17557017505168915,
|
| 1079 |
+
"learning_rate": 0.0004658886894075404,
|
| 1080 |
+
"loss": 5.1374,
|
| 1081 |
+
"step": 1520
|
| 1082 |
+
},
|
| 1083 |
+
{
|
| 1084 |
+
"epoch": 1.3734290843806103,
|
| 1085 |
+
"grad_norm": 0.1354808807373047,
|
| 1086 |
+
"learning_rate": 0.00046566427289048475,
|
| 1087 |
+
"loss": 5.1732,
|
| 1088 |
+
"step": 1530
|
| 1089 |
+
},
|
| 1090 |
+
{
|
| 1091 |
+
"epoch": 1.3824057450628366,
|
| 1092 |
+
"grad_norm": 0.16720908880233765,
|
| 1093 |
+
"learning_rate": 0.0004654398563734291,
|
| 1094 |
+
"loss": 5.3396,
|
| 1095 |
+
"step": 1540
|
| 1096 |
+
},
|
| 1097 |
+
{
|
| 1098 |
+
"epoch": 1.3913824057450628,
|
| 1099 |
+
"grad_norm": 0.19078396260738373,
|
| 1100 |
+
"learning_rate": 0.00046521543985637343,
|
| 1101 |
+
"loss": 5.1455,
|
| 1102 |
+
"step": 1550
|
| 1103 |
+
},
|
| 1104 |
+
{
|
| 1105 |
+
"epoch": 1.400359066427289,
|
| 1106 |
+
"grad_norm": 0.2168230563402176,
|
| 1107 |
+
"learning_rate": 0.00046499102333931783,
|
| 1108 |
+
"loss": 5.1026,
|
| 1109 |
+
"step": 1560
|
| 1110 |
+
},
|
| 1111 |
+
{
|
| 1112 |
+
"epoch": 1.4093357271095153,
|
| 1113 |
+
"grad_norm": 0.12317873537540436,
|
| 1114 |
+
"learning_rate": 0.0004647666068222621,
|
| 1115 |
+
"loss": 5.1632,
|
| 1116 |
+
"step": 1570
|
| 1117 |
+
},
|
| 1118 |
+
{
|
| 1119 |
+
"epoch": 1.4183123877917414,
|
| 1120 |
+
"grad_norm": 0.16298305988311768,
|
| 1121 |
+
"learning_rate": 0.00046454219030520646,
|
| 1122 |
+
"loss": 5.1489,
|
| 1123 |
+
"step": 1580
|
| 1124 |
+
},
|
| 1125 |
+
{
|
| 1126 |
+
"epoch": 1.4272890484739678,
|
| 1127 |
+
"grad_norm": 0.09502866864204407,
|
| 1128 |
+
"learning_rate": 0.0004643177737881508,
|
| 1129 |
+
"loss": 5.1068,
|
| 1130 |
+
"step": 1590
|
| 1131 |
+
},
|
| 1132 |
+
{
|
| 1133 |
+
"epoch": 1.436265709156194,
|
| 1134 |
+
"grad_norm": 0.15911273658275604,
|
| 1135 |
+
"learning_rate": 0.00046409335727109514,
|
| 1136 |
+
"loss": 5.0888,
|
| 1137 |
+
"step": 1600
|
| 1138 |
+
},
|
| 1139 |
+
{
|
| 1140 |
+
"epoch": 1.44524236983842,
|
| 1141 |
+
"grad_norm": 0.12198328226804733,
|
| 1142 |
+
"learning_rate": 0.00046386894075403954,
|
| 1143 |
+
"loss": 5.071,
|
| 1144 |
+
"step": 1610
|
| 1145 |
+
},
|
| 1146 |
+
{
|
| 1147 |
+
"epoch": 1.4542190305206464,
|
| 1148 |
+
"grad_norm": 0.11831381171941757,
|
| 1149 |
+
"learning_rate": 0.00046364452423698383,
|
| 1150 |
+
"loss": 5.0809,
|
| 1151 |
+
"step": 1620
|
| 1152 |
+
},
|
| 1153 |
+
{
|
| 1154 |
+
"epoch": 1.4631956912028725,
|
| 1155 |
+
"grad_norm": 0.1053285300731659,
|
| 1156 |
+
"learning_rate": 0.0004634201077199282,
|
| 1157 |
+
"loss": 5.0774,
|
| 1158 |
+
"step": 1630
|
| 1159 |
+
},
|
| 1160 |
+
{
|
| 1161 |
+
"epoch": 1.4721723518850989,
|
| 1162 |
+
"grad_norm": 0.1193586066365242,
|
| 1163 |
+
"learning_rate": 0.0004631956912028725,
|
| 1164 |
+
"loss": 5.0553,
|
| 1165 |
+
"step": 1640
|
| 1166 |
+
},
|
| 1167 |
+
{
|
| 1168 |
+
"epoch": 1.481149012567325,
|
| 1169 |
+
"grad_norm": 0.16306863725185394,
|
| 1170 |
+
"learning_rate": 0.0004629712746858169,
|
| 1171 |
+
"loss": 5.0607,
|
| 1172 |
+
"step": 1650
|
| 1173 |
+
},
|
| 1174 |
+
{
|
| 1175 |
+
"epoch": 1.4901256732495511,
|
| 1176 |
+
"grad_norm": 0.12861207127571106,
|
| 1177 |
+
"learning_rate": 0.0004627468581687612,
|
| 1178 |
+
"loss": 5.0656,
|
| 1179 |
+
"step": 1660
|
| 1180 |
+
},
|
| 1181 |
+
{
|
| 1182 |
+
"epoch": 1.4991023339317775,
|
| 1183 |
+
"grad_norm": 0.08006058633327484,
|
| 1184 |
+
"learning_rate": 0.0004625224416517056,
|
| 1185 |
+
"loss": 5.0515,
|
| 1186 |
+
"step": 1670
|
| 1187 |
+
},
|
| 1188 |
+
{
|
| 1189 |
+
"epoch": 1.5080789946140036,
|
| 1190 |
+
"grad_norm": 0.11404240876436234,
|
| 1191 |
+
"learning_rate": 0.00046229802513464993,
|
| 1192 |
+
"loss": 5.0098,
|
| 1193 |
+
"step": 1680
|
| 1194 |
+
},
|
| 1195 |
+
{
|
| 1196 |
+
"epoch": 1.5170556552962298,
|
| 1197 |
+
"grad_norm": 0.13075587153434753,
|
| 1198 |
+
"learning_rate": 0.0004620736086175943,
|
| 1199 |
+
"loss": 4.9911,
|
| 1200 |
+
"step": 1690
|
| 1201 |
+
},
|
| 1202 |
+
{
|
| 1203 |
+
"epoch": 1.5260323159784561,
|
| 1204 |
+
"grad_norm": 0.17212539911270142,
|
| 1205 |
+
"learning_rate": 0.0004618491921005386,
|
| 1206 |
+
"loss": 5.0541,
|
| 1207 |
+
"step": 1700
|
| 1208 |
+
},
|
| 1209 |
+
{
|
| 1210 |
+
"epoch": 1.5350089766606823,
|
| 1211 |
+
"grad_norm": 0.07674333453178406,
|
| 1212 |
+
"learning_rate": 0.00046162477558348296,
|
| 1213 |
+
"loss": 5.0126,
|
| 1214 |
+
"step": 1710
|
| 1215 |
+
},
|
| 1216 |
+
{
|
| 1217 |
+
"epoch": 1.5439856373429084,
|
| 1218 |
+
"grad_norm": 0.1121719628572464,
|
| 1219 |
+
"learning_rate": 0.0004614003590664273,
|
| 1220 |
+
"loss": 5.0082,
|
| 1221 |
+
"step": 1720
|
| 1222 |
+
},
|
| 1223 |
+
{
|
| 1224 |
+
"epoch": 1.5529622980251347,
|
| 1225 |
+
"grad_norm": 0.16214531660079956,
|
| 1226 |
+
"learning_rate": 0.00046117594254937164,
|
| 1227 |
+
"loss": 4.9905,
|
| 1228 |
+
"step": 1730
|
| 1229 |
+
},
|
| 1230 |
+
{
|
| 1231 |
+
"epoch": 1.5619389587073609,
|
| 1232 |
+
"grad_norm": 0.12353977560997009,
|
| 1233 |
+
"learning_rate": 0.000460951526032316,
|
| 1234 |
+
"loss": 4.9644,
|
| 1235 |
+
"step": 1740
|
| 1236 |
+
},
|
| 1237 |
+
{
|
| 1238 |
+
"epoch": 1.570915619389587,
|
| 1239 |
+
"grad_norm": 0.15267392992973328,
|
| 1240 |
+
"learning_rate": 0.0004607271095152603,
|
| 1241 |
+
"loss": 4.9708,
|
| 1242 |
+
"step": 1750
|
| 1243 |
+
},
|
| 1244 |
+
{
|
| 1245 |
+
"epoch": 1.5798922800718134,
|
| 1246 |
+
"grad_norm": 0.17361833155155182,
|
| 1247 |
+
"learning_rate": 0.00046050269299820467,
|
| 1248 |
+
"loss": 4.9869,
|
| 1249 |
+
"step": 1760
|
| 1250 |
+
},
|
| 1251 |
+
{
|
| 1252 |
+
"epoch": 1.5888689407540395,
|
| 1253 |
+
"grad_norm": 0.2920306622982025,
|
| 1254 |
+
"learning_rate": 0.000460278276481149,
|
| 1255 |
+
"loss": 4.9322,
|
| 1256 |
+
"step": 1770
|
| 1257 |
+
},
|
| 1258 |
+
{
|
| 1259 |
+
"epoch": 1.5978456014362656,
|
| 1260 |
+
"grad_norm": 0.09478717297315598,
|
| 1261 |
+
"learning_rate": 0.0004600538599640934,
|
| 1262 |
+
"loss": 4.9247,
|
| 1263 |
+
"step": 1780
|
| 1264 |
+
},
|
| 1265 |
+
{
|
| 1266 |
+
"epoch": 1.606822262118492,
|
| 1267 |
+
"grad_norm": 0.09164275228977203,
|
| 1268 |
+
"learning_rate": 0.0004598294434470377,
|
| 1269 |
+
"loss": 4.9086,
|
| 1270 |
+
"step": 1790
|
| 1271 |
+
},
|
| 1272 |
+
{
|
| 1273 |
+
"epoch": 1.6157989228007181,
|
| 1274 |
+
"grad_norm": 0.07962439954280853,
|
| 1275 |
+
"learning_rate": 0.0004596050269299821,
|
| 1276 |
+
"loss": 4.9412,
|
| 1277 |
+
"step": 1800
|
| 1278 |
+
},
|
| 1279 |
+
{
|
| 1280 |
+
"epoch": 1.6247755834829443,
|
| 1281 |
+
"grad_norm": 0.08752849698066711,
|
| 1282 |
+
"learning_rate": 0.0004593806104129264,
|
| 1283 |
+
"loss": 4.9291,
|
| 1284 |
+
"step": 1810
|
| 1285 |
+
},
|
| 1286 |
+
{
|
| 1287 |
+
"epoch": 1.6337522441651706,
|
| 1288 |
+
"grad_norm": 0.09293937683105469,
|
| 1289 |
+
"learning_rate": 0.0004591561938958708,
|
| 1290 |
+
"loss": 4.9652,
|
| 1291 |
+
"step": 1820
|
| 1292 |
+
},
|
| 1293 |
+
{
|
| 1294 |
+
"epoch": 1.6427289048473968,
|
| 1295 |
+
"grad_norm": 0.09523571282625198,
|
| 1296 |
+
"learning_rate": 0.00045893177737881506,
|
| 1297 |
+
"loss": 4.9137,
|
| 1298 |
+
"step": 1830
|
| 1299 |
+
},
|
| 1300 |
+
{
|
| 1301 |
+
"epoch": 1.6517055655296229,
|
| 1302 |
+
"grad_norm": 0.09075015783309937,
|
| 1303 |
+
"learning_rate": 0.00045870736086175946,
|
| 1304 |
+
"loss": 4.8925,
|
| 1305 |
+
"step": 1840
|
| 1306 |
+
},
|
| 1307 |
+
{
|
| 1308 |
+
"epoch": 1.6606822262118492,
|
| 1309 |
+
"grad_norm": 0.14088210463523865,
|
| 1310 |
+
"learning_rate": 0.0004584829443447038,
|
| 1311 |
+
"loss": 4.8941,
|
| 1312 |
+
"step": 1850
|
| 1313 |
+
},
|
| 1314 |
+
{
|
| 1315 |
+
"epoch": 1.6696588868940754,
|
| 1316 |
+
"grad_norm": 0.06859997659921646,
|
| 1317 |
+
"learning_rate": 0.0004582585278276481,
|
| 1318 |
+
"loss": 4.8731,
|
| 1319 |
+
"step": 1860
|
| 1320 |
+
},
|
| 1321 |
+
{
|
| 1322 |
+
"epoch": 1.6786355475763015,
|
| 1323 |
+
"grad_norm": 0.06676523387432098,
|
| 1324 |
+
"learning_rate": 0.0004580341113105925,
|
| 1325 |
+
"loss": 4.8615,
|
| 1326 |
+
"step": 1870
|
| 1327 |
+
},
|
| 1328 |
+
{
|
| 1329 |
+
"epoch": 1.6876122082585279,
|
| 1330 |
+
"grad_norm": 0.08721990138292313,
|
| 1331 |
+
"learning_rate": 0.00045780969479353677,
|
| 1332 |
+
"loss": 4.8847,
|
| 1333 |
+
"step": 1880
|
| 1334 |
+
},
|
| 1335 |
+
{
|
| 1336 |
+
"epoch": 1.696588868940754,
|
| 1337 |
+
"grad_norm": 0.08681096136569977,
|
| 1338 |
+
"learning_rate": 0.00045758527827648117,
|
| 1339 |
+
"loss": 4.884,
|
| 1340 |
+
"step": 1890
|
| 1341 |
+
},
|
| 1342 |
+
{
|
| 1343 |
+
"epoch": 1.7055655296229801,
|
| 1344 |
+
"grad_norm": 0.1754937767982483,
|
| 1345 |
+
"learning_rate": 0.0004573608617594255,
|
| 1346 |
+
"loss": 4.8663,
|
| 1347 |
+
"step": 1900
|
| 1348 |
+
},
|
| 1349 |
+
{
|
| 1350 |
+
"epoch": 1.7145421903052065,
|
| 1351 |
+
"grad_norm": 0.07060963660478592,
|
| 1352 |
+
"learning_rate": 0.00045713644524236985,
|
| 1353 |
+
"loss": 4.9142,
|
| 1354 |
+
"step": 1910
|
| 1355 |
+
},
|
| 1356 |
+
{
|
| 1357 |
+
"epoch": 1.7235188509874326,
|
| 1358 |
+
"grad_norm": 0.12035933881998062,
|
| 1359 |
+
"learning_rate": 0.0004569120287253142,
|
| 1360 |
+
"loss": 4.8599,
|
| 1361 |
+
"step": 1920
|
| 1362 |
+
},
|
| 1363 |
+
{
|
| 1364 |
+
"epoch": 1.7324955116696588,
|
| 1365 |
+
"grad_norm": 0.11212557554244995,
|
| 1366 |
+
"learning_rate": 0.00045668761220825853,
|
| 1367 |
+
"loss": 4.8899,
|
| 1368 |
+
"step": 1930
|
| 1369 |
+
},
|
| 1370 |
+
{
|
| 1371 |
+
"epoch": 1.7414721723518851,
|
| 1372 |
+
"grad_norm": 0.058452803641557693,
|
| 1373 |
+
"learning_rate": 0.0004564631956912029,
|
| 1374 |
+
"loss": 4.8454,
|
| 1375 |
+
"step": 1940
|
| 1376 |
+
},
|
| 1377 |
+
{
|
| 1378 |
+
"epoch": 1.7504488330341115,
|
| 1379 |
+
"grad_norm": 0.1073731780052185,
|
| 1380 |
+
"learning_rate": 0.0004562387791741472,
|
| 1381 |
+
"loss": 4.8546,
|
| 1382 |
+
"step": 1950
|
| 1383 |
+
},
|
| 1384 |
+
{
|
| 1385 |
+
"epoch": 1.7594254937163374,
|
| 1386 |
+
"grad_norm": 0.12025927007198334,
|
| 1387 |
+
"learning_rate": 0.00045601436265709156,
|
| 1388 |
+
"loss": 4.8446,
|
| 1389 |
+
"step": 1960
|
| 1390 |
+
},
|
| 1391 |
+
{
|
| 1392 |
+
"epoch": 1.7684021543985637,
|
| 1393 |
+
"grad_norm": 0.08838968724012375,
|
| 1394 |
+
"learning_rate": 0.00045578994614003596,
|
| 1395 |
+
"loss": 4.8625,
|
| 1396 |
+
"step": 1970
|
| 1397 |
+
},
|
| 1398 |
+
{
|
| 1399 |
+
"epoch": 1.77737881508079,
|
| 1400 |
+
"grad_norm": 0.0963386595249176,
|
| 1401 |
+
"learning_rate": 0.00045556552962298024,
|
| 1402 |
+
"loss": 4.8518,
|
| 1403 |
+
"step": 1980
|
| 1404 |
+
},
|
| 1405 |
+
{
|
| 1406 |
+
"epoch": 1.786355475763016,
|
| 1407 |
+
"grad_norm": 0.10317738354206085,
|
| 1408 |
+
"learning_rate": 0.00045534111310592464,
|
| 1409 |
+
"loss": 4.8161,
|
| 1410 |
+
"step": 1990
|
| 1411 |
+
},
|
| 1412 |
+
{
|
| 1413 |
+
"epoch": 1.7953321364452424,
|
| 1414 |
+
"grad_norm": 2.792144536972046,
|
| 1415 |
+
"learning_rate": 0.00045511669658886893,
|
| 1416 |
+
"loss": 4.8589,
|
| 1417 |
+
"step": 2000
|
| 1418 |
+
},
|
| 1419 |
+
{
|
| 1420 |
+
"epoch": 1.8043087971274687,
|
| 1421 |
+
"grad_norm": 0.08297235518693924,
|
| 1422 |
+
"learning_rate": 0.00045489228007181327,
|
| 1423 |
+
"loss": 4.8135,
|
| 1424 |
+
"step": 2010
|
| 1425 |
+
},
|
| 1426 |
+
{
|
| 1427 |
+
"epoch": 1.8132854578096946,
|
| 1428 |
+
"grad_norm": 0.080784372985363,
|
| 1429 |
+
"learning_rate": 0.00045466786355475767,
|
| 1430 |
+
"loss": 4.8436,
|
| 1431 |
+
"step": 2020
|
| 1432 |
+
},
|
| 1433 |
+
{
|
| 1434 |
+
"epoch": 1.822262118491921,
|
| 1435 |
+
"grad_norm": 0.08878181129693985,
|
| 1436 |
+
"learning_rate": 0.00045444344703770195,
|
| 1437 |
+
"loss": 4.8532,
|
| 1438 |
+
"step": 2030
|
| 1439 |
+
},
|
| 1440 |
+
{
|
| 1441 |
+
"epoch": 1.8312387791741473,
|
| 1442 |
+
"grad_norm": 0.0814034566283226,
|
| 1443 |
+
"learning_rate": 0.00045421903052064635,
|
| 1444 |
+
"loss": 4.7992,
|
| 1445 |
+
"step": 2040
|
| 1446 |
+
},
|
| 1447 |
+
{
|
| 1448 |
+
"epoch": 1.8402154398563735,
|
| 1449 |
+
"grad_norm": 0.05908200889825821,
|
| 1450 |
+
"learning_rate": 0.00045399461400359064,
|
| 1451 |
+
"loss": 4.8005,
|
| 1452 |
+
"step": 2050
|
| 1453 |
+
},
|
| 1454 |
+
{
|
| 1455 |
+
"epoch": 1.8491921005385996,
|
| 1456 |
+
"grad_norm": 0.06837856769561768,
|
| 1457 |
+
"learning_rate": 0.00045377019748653503,
|
| 1458 |
+
"loss": 4.802,
|
| 1459 |
+
"step": 2060
|
| 1460 |
+
},
|
| 1461 |
+
{
|
| 1462 |
+
"epoch": 1.858168761220826,
|
| 1463 |
+
"grad_norm": 0.06775591522455215,
|
| 1464 |
+
"learning_rate": 0.0004535457809694794,
|
| 1465 |
+
"loss": 4.7847,
|
| 1466 |
+
"step": 2070
|
| 1467 |
+
},
|
| 1468 |
+
{
|
| 1469 |
+
"epoch": 1.867145421903052,
|
| 1470 |
+
"grad_norm": 0.27018266916275024,
|
| 1471 |
+
"learning_rate": 0.0004533213644524237,
|
| 1472 |
+
"loss": 4.7918,
|
| 1473 |
+
"step": 2080
|
| 1474 |
+
},
|
| 1475 |
+
{
|
| 1476 |
+
"epoch": 1.8761220825852782,
|
| 1477 |
+
"grad_norm": 0.21435914933681488,
|
| 1478 |
+
"learning_rate": 0.00045309694793536806,
|
| 1479 |
+
"loss": 4.8033,
|
| 1480 |
+
"step": 2090
|
| 1481 |
+
},
|
| 1482 |
+
{
|
| 1483 |
+
"epoch": 1.8850987432675046,
|
| 1484 |
+
"grad_norm": 0.07224582880735397,
|
| 1485 |
+
"learning_rate": 0.0004528725314183124,
|
| 1486 |
+
"loss": 4.7639,
|
| 1487 |
+
"step": 2100
|
| 1488 |
+
},
|
| 1489 |
+
{
|
| 1490 |
+
"epoch": 1.8940754039497307,
|
| 1491 |
+
"grad_norm": 0.08708648383617401,
|
| 1492 |
+
"learning_rate": 0.00045264811490125674,
|
| 1493 |
+
"loss": 4.7894,
|
| 1494 |
+
"step": 2110
|
| 1495 |
+
},
|
| 1496 |
+
{
|
| 1497 |
+
"epoch": 1.9030520646319569,
|
| 1498 |
+
"grad_norm": 0.08637712150812149,
|
| 1499 |
+
"learning_rate": 0.0004524236983842011,
|
| 1500 |
+
"loss": 4.7745,
|
| 1501 |
+
"step": 2120
|
| 1502 |
+
},
|
| 1503 |
+
{
|
| 1504 |
+
"epoch": 1.9120287253141832,
|
| 1505 |
+
"grad_norm": 0.06233949586749077,
|
| 1506 |
+
"learning_rate": 0.0004521992818671454,
|
| 1507 |
+
"loss": 4.783,
|
| 1508 |
+
"step": 2130
|
| 1509 |
+
},
|
| 1510 |
+
{
|
| 1511 |
+
"epoch": 1.9210053859964094,
|
| 1512 |
+
"grad_norm": 0.07999356091022491,
|
| 1513 |
+
"learning_rate": 0.0004519748653500898,
|
| 1514 |
+
"loss": 4.7585,
|
| 1515 |
+
"step": 2140
|
| 1516 |
+
},
|
| 1517 |
+
{
|
| 1518 |
+
"epoch": 1.9299820466786355,
|
| 1519 |
+
"grad_norm": 0.09440754354000092,
|
| 1520 |
+
"learning_rate": 0.0004517504488330341,
|
| 1521 |
+
"loss": 4.7653,
|
| 1522 |
+
"step": 2150
|
| 1523 |
+
},
|
| 1524 |
+
{
|
| 1525 |
+
"epoch": 1.9389587073608618,
|
| 1526 |
+
"grad_norm": 0.09272520244121552,
|
| 1527 |
+
"learning_rate": 0.00045152603231597845,
|
| 1528 |
+
"loss": 4.7523,
|
| 1529 |
+
"step": 2160
|
| 1530 |
+
},
|
| 1531 |
+
{
|
| 1532 |
+
"epoch": 1.947935368043088,
|
| 1533 |
+
"grad_norm": 0.08041410148143768,
|
| 1534 |
+
"learning_rate": 0.0004513016157989228,
|
| 1535 |
+
"loss": 4.7593,
|
| 1536 |
+
"step": 2170
|
| 1537 |
+
},
|
| 1538 |
+
{
|
| 1539 |
+
"epoch": 1.9569120287253141,
|
| 1540 |
+
"grad_norm": 0.048107001930475235,
|
| 1541 |
+
"learning_rate": 0.00045107719928186714,
|
| 1542 |
+
"loss": 4.7392,
|
| 1543 |
+
"step": 2180
|
| 1544 |
+
},
|
| 1545 |
+
{
|
| 1546 |
+
"epoch": 1.9658886894075405,
|
| 1547 |
+
"grad_norm": 0.07445549219846725,
|
| 1548 |
+
"learning_rate": 0.00045085278276481153,
|
| 1549 |
+
"loss": 4.7288,
|
| 1550 |
+
"step": 2190
|
| 1551 |
+
},
|
| 1552 |
+
{
|
| 1553 |
+
"epoch": 1.9748653500897666,
|
| 1554 |
+
"grad_norm": 0.06540877372026443,
|
| 1555 |
+
"learning_rate": 0.0004506283662477558,
|
| 1556 |
+
"loss": 4.7311,
|
| 1557 |
+
"step": 2200
|
| 1558 |
+
},
|
| 1559 |
+
{
|
| 1560 |
+
"epoch": 1.9838420107719927,
|
| 1561 |
+
"grad_norm": 0.05422632023692131,
|
| 1562 |
+
"learning_rate": 0.0004504039497307002,
|
| 1563 |
+
"loss": 4.728,
|
| 1564 |
+
"step": 2210
|
| 1565 |
+
},
|
| 1566 |
+
{
|
| 1567 |
+
"epoch": 1.992818671454219,
|
| 1568 |
+
"grad_norm": 0.05353199318051338,
|
| 1569 |
+
"learning_rate": 0.0004501795332136445,
|
| 1570 |
+
"loss": 4.7274,
|
| 1571 |
+
"step": 2220
|
| 1572 |
+
},
|
| 1573 |
+
{
|
| 1574 |
+
"epoch": 2.0,
|
| 1575 |
+
"eval_loss": 4.539531707763672,
|
| 1576 |
+
"eval_runtime": 437.126,
|
| 1577 |
+
"eval_samples_per_second": 10.194,
|
| 1578 |
+
"eval_steps_per_second": 1.274,
|
| 1579 |
+
"step": 2228
|
| 1580 |
+
},
|
| 1581 |
+
{
|
| 1582 |
+
"epoch": 2.0017953321364454,
|
| 1583 |
+
"grad_norm": 0.05564208701252937,
|
| 1584 |
+
"learning_rate": 0.0004499551166965889,
|
| 1585 |
+
"loss": 4.7397,
|
| 1586 |
+
"step": 2230
|
| 1587 |
+
},
|
| 1588 |
+
{
|
| 1589 |
+
"epoch": 2.0107719928186714,
|
| 1590 |
+
"grad_norm": 0.05997077003121376,
|
| 1591 |
+
"learning_rate": 0.00044973070017953324,
|
| 1592 |
+
"loss": 4.714,
|
| 1593 |
+
"step": 2240
|
| 1594 |
+
},
|
| 1595 |
+
{
|
| 1596 |
+
"epoch": 2.0197486535008977,
|
| 1597 |
+
"grad_norm": 0.0496087446808815,
|
| 1598 |
+
"learning_rate": 0.0004495062836624776,
|
| 1599 |
+
"loss": 4.7431,
|
| 1600 |
+
"step": 2250
|
| 1601 |
+
},
|
| 1602 |
+
{
|
| 1603 |
+
"epoch": 2.028725314183124,
|
| 1604 |
+
"grad_norm": 0.08797594904899597,
|
| 1605 |
+
"learning_rate": 0.0004492818671454219,
|
| 1606 |
+
"loss": 4.7186,
|
| 1607 |
+
"step": 2260
|
| 1608 |
+
},
|
| 1609 |
+
{
|
| 1610 |
+
"epoch": 2.03770197486535,
|
| 1611 |
+
"grad_norm": 0.05270407721400261,
|
| 1612 |
+
"learning_rate": 0.00044905745062836627,
|
| 1613 |
+
"loss": 4.7419,
|
| 1614 |
+
"step": 2270
|
| 1615 |
+
},
|
| 1616 |
+
{
|
| 1617 |
+
"epoch": 2.0466786355475763,
|
| 1618 |
+
"grad_norm": 0.06538320332765579,
|
| 1619 |
+
"learning_rate": 0.0004488330341113106,
|
| 1620 |
+
"loss": 4.714,
|
| 1621 |
+
"step": 2280
|
| 1622 |
+
},
|
| 1623 |
+
{
|
| 1624 |
+
"epoch": 2.0556552962298027,
|
| 1625 |
+
"grad_norm": 0.060536161065101624,
|
| 1626 |
+
"learning_rate": 0.0004486086175942549,
|
| 1627 |
+
"loss": 4.691,
|
| 1628 |
+
"step": 2290
|
| 1629 |
+
},
|
| 1630 |
+
{
|
| 1631 |
+
"epoch": 2.0646319569120286,
|
| 1632 |
+
"grad_norm": 0.10158341377973557,
|
| 1633 |
+
"learning_rate": 0.0004483842010771993,
|
| 1634 |
+
"loss": 4.702,
|
| 1635 |
+
"step": 2300
|
| 1636 |
+
},
|
| 1637 |
+
{
|
| 1638 |
+
"epoch": 2.073608617594255,
|
| 1639 |
+
"grad_norm": 0.08171387016773224,
|
| 1640 |
+
"learning_rate": 0.00044815978456014363,
|
| 1641 |
+
"loss": 4.7029,
|
| 1642 |
+
"step": 2310
|
| 1643 |
+
},
|
| 1644 |
+
{
|
| 1645 |
+
"epoch": 2.0825852782764813,
|
| 1646 |
+
"grad_norm": 0.07701843976974487,
|
| 1647 |
+
"learning_rate": 0.000447935368043088,
|
| 1648 |
+
"loss": 4.6957,
|
| 1649 |
+
"step": 2320
|
| 1650 |
+
},
|
| 1651 |
+
{
|
| 1652 |
+
"epoch": 2.0915619389587072,
|
| 1653 |
+
"grad_norm": 0.06302302330732346,
|
| 1654 |
+
"learning_rate": 0.0004477109515260323,
|
| 1655 |
+
"loss": 4.6855,
|
| 1656 |
+
"step": 2330
|
| 1657 |
+
},
|
| 1658 |
+
{
|
| 1659 |
+
"epoch": 2.1005385996409336,
|
| 1660 |
+
"grad_norm": 0.12679466605186462,
|
| 1661 |
+
"learning_rate": 0.00044748653500897666,
|
| 1662 |
+
"loss": 4.7147,
|
| 1663 |
+
"step": 2340
|
| 1664 |
+
},
|
| 1665 |
+
{
|
| 1666 |
+
"epoch": 2.10951526032316,
|
| 1667 |
+
"grad_norm": 0.17339470982551575,
|
| 1668 |
+
"learning_rate": 0.000447262118491921,
|
| 1669 |
+
"loss": 4.6697,
|
| 1670 |
+
"step": 2350
|
| 1671 |
+
},
|
| 1672 |
+
{
|
| 1673 |
+
"epoch": 2.118491921005386,
|
| 1674 |
+
"grad_norm": 0.07397322356700897,
|
| 1675 |
+
"learning_rate": 0.0004470377019748654,
|
| 1676 |
+
"loss": 4.6642,
|
| 1677 |
+
"step": 2360
|
| 1678 |
+
},
|
| 1679 |
+
{
|
| 1680 |
+
"epoch": 2.127468581687612,
|
| 1681 |
+
"grad_norm": 0.0524037629365921,
|
| 1682 |
+
"learning_rate": 0.0004468132854578097,
|
| 1683 |
+
"loss": 4.6511,
|
| 1684 |
+
"step": 2370
|
| 1685 |
+
},
|
| 1686 |
+
{
|
| 1687 |
+
"epoch": 2.1364452423698386,
|
| 1688 |
+
"grad_norm": 0.06674987077713013,
|
| 1689 |
+
"learning_rate": 0.0004465888689407541,
|
| 1690 |
+
"loss": 4.6374,
|
| 1691 |
+
"step": 2380
|
| 1692 |
+
},
|
| 1693 |
+
{
|
| 1694 |
+
"epoch": 2.1454219030520645,
|
| 1695 |
+
"grad_norm": 0.04827852547168732,
|
| 1696 |
+
"learning_rate": 0.00044636445242369837,
|
| 1697 |
+
"loss": 4.6531,
|
| 1698 |
+
"step": 2390
|
| 1699 |
+
},
|
| 1700 |
+
{
|
| 1701 |
+
"epoch": 2.154398563734291,
|
| 1702 |
+
"grad_norm": 0.05094282329082489,
|
| 1703 |
+
"learning_rate": 0.00044614003590664277,
|
| 1704 |
+
"loss": 4.6554,
|
| 1705 |
+
"step": 2400
|
| 1706 |
+
},
|
| 1707 |
+
{
|
| 1708 |
+
"epoch": 2.163375224416517,
|
| 1709 |
+
"grad_norm": 0.0653914213180542,
|
| 1710 |
+
"learning_rate": 0.00044591561938958705,
|
| 1711 |
+
"loss": 4.6568,
|
| 1712 |
+
"step": 2410
|
| 1713 |
+
},
|
| 1714 |
+
{
|
| 1715 |
+
"epoch": 2.172351885098743,
|
| 1716 |
+
"grad_norm": 0.06652519851922989,
|
| 1717 |
+
"learning_rate": 0.00044569120287253145,
|
| 1718 |
+
"loss": 4.6533,
|
| 1719 |
+
"step": 2420
|
| 1720 |
+
},
|
| 1721 |
+
{
|
| 1722 |
+
"epoch": 2.1813285457809695,
|
| 1723 |
+
"grad_norm": 0.051527008414268494,
|
| 1724 |
+
"learning_rate": 0.0004454667863554758,
|
| 1725 |
+
"loss": 4.6438,
|
| 1726 |
+
"step": 2430
|
| 1727 |
+
},
|
| 1728 |
+
{
|
| 1729 |
+
"epoch": 2.190305206463196,
|
| 1730 |
+
"grad_norm": 0.047185543924570084,
|
| 1731 |
+
"learning_rate": 0.0004452423698384201,
|
| 1732 |
+
"loss": 4.6157,
|
| 1733 |
+
"step": 2440
|
| 1734 |
+
},
|
| 1735 |
+
{
|
| 1736 |
+
"epoch": 2.1992818671454217,
|
| 1737 |
+
"grad_norm": 0.0524996742606163,
|
| 1738 |
+
"learning_rate": 0.0004450179533213645,
|
| 1739 |
+
"loss": 4.6583,
|
| 1740 |
+
"step": 2450
|
| 1741 |
+
},
|
| 1742 |
+
{
|
| 1743 |
+
"epoch": 2.208258527827648,
|
| 1744 |
+
"grad_norm": 0.055864688009023666,
|
| 1745 |
+
"learning_rate": 0.00044479353680430876,
|
| 1746 |
+
"loss": 4.611,
|
| 1747 |
+
"step": 2460
|
| 1748 |
+
},
|
| 1749 |
+
{
|
| 1750 |
+
"epoch": 2.2172351885098744,
|
| 1751 |
+
"grad_norm": 0.055937688797712326,
|
| 1752 |
+
"learning_rate": 0.00044456912028725316,
|
| 1753 |
+
"loss": 4.6302,
|
| 1754 |
+
"step": 2470
|
| 1755 |
+
},
|
| 1756 |
+
{
|
| 1757 |
+
"epoch": 2.2262118491921004,
|
| 1758 |
+
"grad_norm": 0.07318311929702759,
|
| 1759 |
+
"learning_rate": 0.0004443447037701975,
|
| 1760 |
+
"loss": 4.6383,
|
| 1761 |
+
"step": 2480
|
| 1762 |
+
},
|
| 1763 |
+
{
|
| 1764 |
+
"epoch": 2.2351885098743267,
|
| 1765 |
+
"grad_norm": 0.05302512273192406,
|
| 1766 |
+
"learning_rate": 0.00044412028725314184,
|
| 1767 |
+
"loss": 4.6142,
|
| 1768 |
+
"step": 2490
|
| 1769 |
+
},
|
| 1770 |
+
{
|
| 1771 |
+
"epoch": 2.244165170556553,
|
| 1772 |
+
"grad_norm": 0.050843581557273865,
|
| 1773 |
+
"learning_rate": 0.0004438958707360862,
|
| 1774 |
+
"loss": 4.5937,
|
| 1775 |
+
"step": 2500
|
| 1776 |
+
},
|
| 1777 |
+
{
|
| 1778 |
+
"epoch": 2.253141831238779,
|
| 1779 |
+
"grad_norm": 0.0519312284886837,
|
| 1780 |
+
"learning_rate": 0.0004436714542190305,
|
| 1781 |
+
"loss": 4.6083,
|
| 1782 |
+
"step": 2510
|
| 1783 |
+
},
|
| 1784 |
+
{
|
| 1785 |
+
"epoch": 2.2621184919210053,
|
| 1786 |
+
"grad_norm": 0.05857894569635391,
|
| 1787 |
+
"learning_rate": 0.00044344703770197487,
|
| 1788 |
+
"loss": 4.5765,
|
| 1789 |
+
"step": 2520
|
| 1790 |
+
},
|
| 1791 |
+
{
|
| 1792 |
+
"epoch": 2.2710951526032317,
|
| 1793 |
+
"grad_norm": 0.05550041422247887,
|
| 1794 |
+
"learning_rate": 0.00044322262118491926,
|
| 1795 |
+
"loss": 4.5859,
|
| 1796 |
+
"step": 2530
|
| 1797 |
+
},
|
| 1798 |
+
{
|
| 1799 |
+
"epoch": 2.280071813285458,
|
| 1800 |
+
"grad_norm": 0.10349979996681213,
|
| 1801 |
+
"learning_rate": 0.00044299820466786355,
|
| 1802 |
+
"loss": 4.5765,
|
| 1803 |
+
"step": 2540
|
| 1804 |
+
},
|
| 1805 |
+
{
|
| 1806 |
+
"epoch": 2.289048473967684,
|
| 1807 |
+
"grad_norm": 0.1185607761144638,
|
| 1808 |
+
"learning_rate": 0.00044277378815080795,
|
| 1809 |
+
"loss": 4.5946,
|
| 1810 |
+
"step": 2550
|
| 1811 |
+
},
|
| 1812 |
+
{
|
| 1813 |
+
"epoch": 2.2980251346499103,
|
| 1814 |
+
"grad_norm": 0.09133188426494598,
|
| 1815 |
+
"learning_rate": 0.00044254937163375224,
|
| 1816 |
+
"loss": 4.578,
|
| 1817 |
+
"step": 2560
|
| 1818 |
+
},
|
| 1819 |
+
{
|
| 1820 |
+
"epoch": 2.3070017953321367,
|
| 1821 |
+
"grad_norm": 0.08713024109601974,
|
| 1822 |
+
"learning_rate": 0.00044232495511669663,
|
| 1823 |
+
"loss": 4.6011,
|
| 1824 |
+
"step": 2570
|
| 1825 |
+
},
|
| 1826 |
+
{
|
| 1827 |
+
"epoch": 2.3159784560143626,
|
| 1828 |
+
"grad_norm": 0.05465725436806679,
|
| 1829 |
+
"learning_rate": 0.0004421005385996409,
|
| 1830 |
+
"loss": 4.5755,
|
| 1831 |
+
"step": 2580
|
| 1832 |
+
},
|
| 1833 |
+
{
|
| 1834 |
+
"epoch": 2.324955116696589,
|
| 1835 |
+
"grad_norm": 0.056493621319532394,
|
| 1836 |
+
"learning_rate": 0.00044187612208258526,
|
| 1837 |
+
"loss": 4.5855,
|
| 1838 |
+
"step": 2590
|
| 1839 |
+
},
|
| 1840 |
+
{
|
| 1841 |
+
"epoch": 2.3339317773788153,
|
| 1842 |
+
"grad_norm": 0.047107528895139694,
|
| 1843 |
+
"learning_rate": 0.00044165170556552966,
|
| 1844 |
+
"loss": 4.5681,
|
| 1845 |
+
"step": 2600
|
| 1846 |
+
},
|
| 1847 |
+
{
|
| 1848 |
+
"epoch": 2.342908438061041,
|
| 1849 |
+
"grad_norm": 0.05533495545387268,
|
| 1850 |
+
"learning_rate": 0.00044142728904847394,
|
| 1851 |
+
"loss": 4.5581,
|
| 1852 |
+
"step": 2610
|
| 1853 |
+
},
|
| 1854 |
+
{
|
| 1855 |
+
"epoch": 2.3518850987432676,
|
| 1856 |
+
"grad_norm": 0.0478278249502182,
|
| 1857 |
+
"learning_rate": 0.00044120287253141834,
|
| 1858 |
+
"loss": 4.5425,
|
| 1859 |
+
"step": 2620
|
| 1860 |
+
},
|
| 1861 |
+
{
|
| 1862 |
+
"epoch": 2.360861759425494,
|
| 1863 |
+
"grad_norm": 0.06553395092487335,
|
| 1864 |
+
"learning_rate": 0.00044097845601436263,
|
| 1865 |
+
"loss": 4.5484,
|
| 1866 |
+
"step": 2630
|
| 1867 |
+
},
|
| 1868 |
+
{
|
| 1869 |
+
"epoch": 2.36983842010772,
|
| 1870 |
+
"grad_norm": 0.07375505566596985,
|
| 1871 |
+
"learning_rate": 0.000440754039497307,
|
| 1872 |
+
"loss": 4.541,
|
| 1873 |
+
"step": 2640
|
| 1874 |
+
},
|
| 1875 |
+
{
|
| 1876 |
+
"epoch": 2.378815080789946,
|
| 1877 |
+
"grad_norm": 0.20693852007389069,
|
| 1878 |
+
"learning_rate": 0.00044052962298025137,
|
| 1879 |
+
"loss": 4.5521,
|
| 1880 |
+
"step": 2650
|
| 1881 |
+
},
|
| 1882 |
+
{
|
| 1883 |
+
"epoch": 2.3877917414721725,
|
| 1884 |
+
"grad_norm": 0.056829433888196945,
|
| 1885 |
+
"learning_rate": 0.0004403052064631957,
|
| 1886 |
+
"loss": 4.5588,
|
| 1887 |
+
"step": 2660
|
| 1888 |
+
},
|
| 1889 |
+
{
|
| 1890 |
+
"epoch": 2.3967684021543985,
|
| 1891 |
+
"grad_norm": 0.05583564192056656,
|
| 1892 |
+
"learning_rate": 0.00044008078994614005,
|
| 1893 |
+
"loss": 4.5358,
|
| 1894 |
+
"step": 2670
|
| 1895 |
+
},
|
| 1896 |
+
{
|
| 1897 |
+
"epoch": 2.405745062836625,
|
| 1898 |
+
"grad_norm": 0.07319542020559311,
|
| 1899 |
+
"learning_rate": 0.0004398563734290844,
|
| 1900 |
+
"loss": 4.523,
|
| 1901 |
+
"step": 2680
|
| 1902 |
+
},
|
| 1903 |
+
{
|
| 1904 |
+
"epoch": 2.414721723518851,
|
| 1905 |
+
"grad_norm": 0.052402835339307785,
|
| 1906 |
+
"learning_rate": 0.00043963195691202873,
|
| 1907 |
+
"loss": 4.5096,
|
| 1908 |
+
"step": 2690
|
| 1909 |
+
},
|
| 1910 |
+
{
|
| 1911 |
+
"epoch": 2.423698384201077,
|
| 1912 |
+
"grad_norm": 0.05206010863184929,
|
| 1913 |
+
"learning_rate": 0.00043940754039497313,
|
| 1914 |
+
"loss": 4.5053,
|
| 1915 |
+
"step": 2700
|
| 1916 |
+
},
|
| 1917 |
+
{
|
| 1918 |
+
"epoch": 2.4326750448833034,
|
| 1919 |
+
"grad_norm": 0.05443358048796654,
|
| 1920 |
+
"learning_rate": 0.0004391831238779174,
|
| 1921 |
+
"loss": 4.5501,
|
| 1922 |
+
"step": 2710
|
| 1923 |
+
},
|
| 1924 |
+
{
|
| 1925 |
+
"epoch": 2.44165170556553,
|
| 1926 |
+
"grad_norm": 0.07843279093503952,
|
| 1927 |
+
"learning_rate": 0.00043895870736086176,
|
| 1928 |
+
"loss": 4.5027,
|
| 1929 |
+
"step": 2720
|
| 1930 |
+
},
|
| 1931 |
+
{
|
| 1932 |
+
"epoch": 2.4506283662477557,
|
| 1933 |
+
"grad_norm": 0.046305350959300995,
|
| 1934 |
+
"learning_rate": 0.0004387342908438061,
|
| 1935 |
+
"loss": 4.4975,
|
| 1936 |
+
"step": 2730
|
| 1937 |
+
},
|
| 1938 |
+
{
|
| 1939 |
+
"epoch": 2.459605026929982,
|
| 1940 |
+
"grad_norm": 0.22592291235923767,
|
| 1941 |
+
"learning_rate": 0.00043850987432675044,
|
| 1942 |
+
"loss": 4.5183,
|
| 1943 |
+
"step": 2740
|
| 1944 |
+
},
|
| 1945 |
+
{
|
| 1946 |
+
"epoch": 2.4685816876122084,
|
| 1947 |
+
"grad_norm": 0.05082382634282112,
|
| 1948 |
+
"learning_rate": 0.0004382854578096948,
|
| 1949 |
+
"loss": 4.4864,
|
| 1950 |
+
"step": 2750
|
| 1951 |
+
},
|
| 1952 |
+
{
|
| 1953 |
+
"epoch": 2.4775583482944343,
|
| 1954 |
+
"grad_norm": 0.06731193512678146,
|
| 1955 |
+
"learning_rate": 0.00043806104129263913,
|
| 1956 |
+
"loss": 4.4982,
|
| 1957 |
+
"step": 2760
|
| 1958 |
+
},
|
| 1959 |
+
{
|
| 1960 |
+
"epoch": 2.4865350089766607,
|
| 1961 |
+
"grad_norm": 185.7747039794922,
|
| 1962 |
+
"learning_rate": 0.0004378366247755835,
|
| 1963 |
+
"loss": 4.6692,
|
| 1964 |
+
"step": 2770
|
| 1965 |
+
},
|
| 1966 |
+
{
|
| 1967 |
+
"epoch": 2.495511669658887,
|
| 1968 |
+
"grad_norm": 0.058124568313360214,
|
| 1969 |
+
"learning_rate": 0.0004376122082585278,
|
| 1970 |
+
"loss": 4.4775,
|
| 1971 |
+
"step": 2780
|
| 1972 |
+
},
|
| 1973 |
+
{
|
| 1974 |
+
"epoch": 2.504488330341113,
|
| 1975 |
+
"grad_norm": 0.08968983590602875,
|
| 1976 |
+
"learning_rate": 0.0004373877917414722,
|
| 1977 |
+
"loss": 4.4944,
|
| 1978 |
+
"step": 2790
|
| 1979 |
+
},
|
| 1980 |
+
{
|
| 1981 |
+
"epoch": 2.5134649910233393,
|
| 1982 |
+
"grad_norm": 0.2788603901863098,
|
| 1983 |
+
"learning_rate": 0.0004371633752244165,
|
| 1984 |
+
"loss": 4.503,
|
| 1985 |
+
"step": 2800
|
| 1986 |
+
},
|
| 1987 |
+
{
|
| 1988 |
+
"epoch": 2.5224416517055657,
|
| 1989 |
+
"grad_norm": 0.05559522658586502,
|
| 1990 |
+
"learning_rate": 0.0004369389587073609,
|
| 1991 |
+
"loss": 4.4733,
|
| 1992 |
+
"step": 2810
|
| 1993 |
+
},
|
| 1994 |
+
{
|
| 1995 |
+
"epoch": 2.5314183123877916,
|
| 1996 |
+
"grad_norm": 0.05935097113251686,
|
| 1997 |
+
"learning_rate": 0.00043671454219030523,
|
| 1998 |
+
"loss": 4.4686,
|
| 1999 |
+
"step": 2820
|
| 2000 |
+
},
|
| 2001 |
+
{
|
| 2002 |
+
"epoch": 2.540394973070018,
|
| 2003 |
+
"grad_norm": 0.05860767886042595,
|
| 2004 |
+
"learning_rate": 0.0004364901256732496,
|
| 2005 |
+
"loss": 4.4593,
|
| 2006 |
+
"step": 2830
|
| 2007 |
+
},
|
| 2008 |
+
{
|
| 2009 |
+
"epoch": 2.5493716337522443,
|
| 2010 |
+
"grad_norm": 0.047259800136089325,
|
| 2011 |
+
"learning_rate": 0.0004362657091561939,
|
| 2012 |
+
"loss": 4.4479,
|
| 2013 |
+
"step": 2840
|
| 2014 |
+
},
|
| 2015 |
+
{
|
| 2016 |
+
"epoch": 2.55834829443447,
|
| 2017 |
+
"grad_norm": 0.04901234060525894,
|
| 2018 |
+
"learning_rate": 0.00043604129263913826,
|
| 2019 |
+
"loss": 4.4621,
|
| 2020 |
+
"step": 2850
|
| 2021 |
+
},
|
| 2022 |
+
{
|
| 2023 |
+
"epoch": 2.5673249551166966,
|
| 2024 |
+
"grad_norm": 0.05742761120200157,
|
| 2025 |
+
"learning_rate": 0.0004358168761220826,
|
| 2026 |
+
"loss": 4.4422,
|
| 2027 |
+
"step": 2860
|
| 2028 |
+
},
|
| 2029 |
+
{
|
| 2030 |
+
"epoch": 2.576301615798923,
|
| 2031 |
+
"grad_norm": 0.05717416852712631,
|
| 2032 |
+
"learning_rate": 0.0004355924596050269,
|
| 2033 |
+
"loss": 4.4248,
|
| 2034 |
+
"step": 2870
|
| 2035 |
+
},
|
| 2036 |
+
{
|
| 2037 |
+
"epoch": 2.585278276481149,
|
| 2038 |
+
"grad_norm": 0.0896502435207367,
|
| 2039 |
+
"learning_rate": 0.0004353680430879713,
|
| 2040 |
+
"loss": 4.4368,
|
| 2041 |
+
"step": 2880
|
| 2042 |
+
},
|
| 2043 |
+
{
|
| 2044 |
+
"epoch": 2.594254937163375,
|
| 2045 |
+
"grad_norm": 0.08746081590652466,
|
| 2046 |
+
"learning_rate": 0.0004351436265709156,
|
| 2047 |
+
"loss": 4.4282,
|
| 2048 |
+
"step": 2890
|
| 2049 |
+
},
|
| 2050 |
+
{
|
| 2051 |
+
"epoch": 2.6032315978456015,
|
| 2052 |
+
"grad_norm": 0.07144750654697418,
|
| 2053 |
+
"learning_rate": 0.00043491921005385997,
|
| 2054 |
+
"loss": 4.4794,
|
| 2055 |
+
"step": 2900
|
| 2056 |
+
},
|
| 2057 |
+
{
|
| 2058 |
+
"epoch": 2.6122082585278275,
|
| 2059 |
+
"grad_norm": 0.05990668013691902,
|
| 2060 |
+
"learning_rate": 0.0004346947935368043,
|
| 2061 |
+
"loss": 4.4117,
|
| 2062 |
+
"step": 2910
|
| 2063 |
+
},
|
| 2064 |
+
{
|
| 2065 |
+
"epoch": 2.621184919210054,
|
| 2066 |
+
"grad_norm": 0.07920947670936584,
|
| 2067 |
+
"learning_rate": 0.00043447037701974865,
|
| 2068 |
+
"loss": 4.4179,
|
| 2069 |
+
"step": 2920
|
| 2070 |
+
},
|
| 2071 |
+
{
|
| 2072 |
+
"epoch": 2.63016157989228,
|
| 2073 |
+
"grad_norm": 0.053824532777071,
|
| 2074 |
+
"learning_rate": 0.000434245960502693,
|
| 2075 |
+
"loss": 4.3963,
|
| 2076 |
+
"step": 2930
|
| 2077 |
+
},
|
| 2078 |
+
{
|
| 2079 |
+
"epoch": 2.639138240574506,
|
| 2080 |
+
"grad_norm": 0.06394129246473312,
|
| 2081 |
+
"learning_rate": 0.0004340215439856374,
|
| 2082 |
+
"loss": 4.4045,
|
| 2083 |
+
"step": 2940
|
| 2084 |
+
},
|
| 2085 |
+
{
|
| 2086 |
+
"epoch": 2.6481149012567324,
|
| 2087 |
+
"grad_norm": 0.2640804648399353,
|
| 2088 |
+
"learning_rate": 0.0004337971274685817,
|
| 2089 |
+
"loss": 4.3916,
|
| 2090 |
+
"step": 2950
|
| 2091 |
+
},
|
| 2092 |
+
{
|
| 2093 |
+
"epoch": 2.657091561938959,
|
| 2094 |
+
"grad_norm": 0.04887564107775688,
|
| 2095 |
+
"learning_rate": 0.0004335727109515261,
|
| 2096 |
+
"loss": 4.3892,
|
| 2097 |
+
"step": 2960
|
| 2098 |
+
},
|
| 2099 |
+
{
|
| 2100 |
+
"epoch": 2.6660682226211847,
|
| 2101 |
+
"grad_norm": 0.05104290321469307,
|
| 2102 |
+
"learning_rate": 0.00043334829443447036,
|
| 2103 |
+
"loss": 4.3883,
|
| 2104 |
+
"step": 2970
|
| 2105 |
+
},
|
| 2106 |
+
{
|
| 2107 |
+
"epoch": 2.675044883303411,
|
| 2108 |
+
"grad_norm": 0.18991751968860626,
|
| 2109 |
+
"learning_rate": 0.00043312387791741476,
|
| 2110 |
+
"loss": 4.3747,
|
| 2111 |
+
"step": 2980
|
| 2112 |
+
},
|
| 2113 |
+
{
|
| 2114 |
+
"epoch": 2.6840215439856374,
|
| 2115 |
+
"grad_norm": 0.3262752294540405,
|
| 2116 |
+
"learning_rate": 0.0004328994614003591,
|
| 2117 |
+
"loss": 4.3755,
|
| 2118 |
+
"step": 2990
|
| 2119 |
+
},
|
| 2120 |
+
{
|
| 2121 |
+
"epoch": 2.6929982046678633,
|
| 2122 |
+
"grad_norm": 0.6619095802307129,
|
| 2123 |
+
"learning_rate": 0.0004326750448833034,
|
| 2124 |
+
"loss": 4.3711,
|
| 2125 |
+
"step": 3000
|
| 2126 |
+
},
|
| 2127 |
+
{
|
| 2128 |
+
"epoch": 2.7019748653500897,
|
| 2129 |
+
"grad_norm": 0.06734511256217957,
|
| 2130 |
+
"learning_rate": 0.0004324506283662478,
|
| 2131 |
+
"loss": 4.3606,
|
| 2132 |
+
"step": 3010
|
| 2133 |
+
},
|
| 2134 |
+
{
|
| 2135 |
+
"epoch": 2.710951526032316,
|
| 2136 |
+
"grad_norm": 0.06055251508951187,
|
| 2137 |
+
"learning_rate": 0.00043222621184919207,
|
| 2138 |
+
"loss": 4.3639,
|
| 2139 |
+
"step": 3020
|
| 2140 |
+
},
|
| 2141 |
+
{
|
| 2142 |
+
"epoch": 2.719928186714542,
|
| 2143 |
+
"grad_norm": 0.08325715363025665,
|
| 2144 |
+
"learning_rate": 0.00043200179533213647,
|
| 2145 |
+
"loss": 4.3439,
|
| 2146 |
+
"step": 3030
|
| 2147 |
+
},
|
| 2148 |
+
{
|
| 2149 |
+
"epoch": 2.7289048473967683,
|
| 2150 |
+
"grad_norm": 0.06473597139120102,
|
| 2151 |
+
"learning_rate": 0.00043177737881508075,
|
| 2152 |
+
"loss": 4.3448,
|
| 2153 |
+
"step": 3040
|
| 2154 |
+
},
|
| 2155 |
+
{
|
| 2156 |
+
"epoch": 2.7378815080789947,
|
| 2157 |
+
"grad_norm": 0.062395766377449036,
|
| 2158 |
+
"learning_rate": 0.00043155296229802515,
|
| 2159 |
+
"loss": 4.3262,
|
| 2160 |
+
"step": 3050
|
| 2161 |
+
},
|
| 2162 |
+
{
|
| 2163 |
+
"epoch": 2.7468581687612206,
|
| 2164 |
+
"grad_norm": 0.054201096296310425,
|
| 2165 |
+
"learning_rate": 0.0004313285457809695,
|
| 2166 |
+
"loss": 4.3466,
|
| 2167 |
+
"step": 3060
|
| 2168 |
+
},
|
| 2169 |
+
{
|
| 2170 |
+
"epoch": 2.755834829443447,
|
| 2171 |
+
"grad_norm": 0.05278482288122177,
|
| 2172 |
+
"learning_rate": 0.00043110412926391383,
|
| 2173 |
+
"loss": 4.3493,
|
| 2174 |
+
"step": 3070
|
| 2175 |
+
},
|
| 2176 |
+
{
|
| 2177 |
+
"epoch": 2.7648114901256733,
|
| 2178 |
+
"grad_norm": 0.05334211513400078,
|
| 2179 |
+
"learning_rate": 0.0004308797127468582,
|
| 2180 |
+
"loss": 4.3308,
|
| 2181 |
+
"step": 3080
|
| 2182 |
+
},
|
| 2183 |
+
{
|
| 2184 |
+
"epoch": 2.773788150807899,
|
| 2185 |
+
"grad_norm": 0.06164594739675522,
|
| 2186 |
+
"learning_rate": 0.0004306552962298025,
|
| 2187 |
+
"loss": 4.3166,
|
| 2188 |
+
"step": 3090
|
| 2189 |
+
},
|
| 2190 |
+
{
|
| 2191 |
+
"epoch": 2.7827648114901256,
|
| 2192 |
+
"grad_norm": 0.07043807953596115,
|
| 2193 |
+
"learning_rate": 0.00043043087971274686,
|
| 2194 |
+
"loss": 4.3009,
|
| 2195 |
+
"step": 3100
|
| 2196 |
+
},
|
| 2197 |
+
{
|
| 2198 |
+
"epoch": 2.791741472172352,
|
| 2199 |
+
"grad_norm": 0.05904858186841011,
|
| 2200 |
+
"learning_rate": 0.00043020646319569126,
|
| 2201 |
+
"loss": 4.2982,
|
| 2202 |
+
"step": 3110
|
| 2203 |
+
},
|
| 2204 |
+
{
|
| 2205 |
+
"epoch": 2.800718132854578,
|
| 2206 |
+
"grad_norm": 0.3487374782562256,
|
| 2207 |
+
"learning_rate": 0.00042998204667863554,
|
| 2208 |
+
"loss": 4.2992,
|
| 2209 |
+
"step": 3120
|
| 2210 |
+
},
|
| 2211 |
+
{
|
| 2212 |
+
"epoch": 2.809694793536804,
|
| 2213 |
+
"grad_norm": 0.06090310215950012,
|
| 2214 |
+
"learning_rate": 0.00042975763016157994,
|
| 2215 |
+
"loss": 4.3199,
|
| 2216 |
+
"step": 3130
|
| 2217 |
+
},
|
| 2218 |
+
{
|
| 2219 |
+
"epoch": 2.8186714542190305,
|
| 2220 |
+
"grad_norm": 0.0674201026558876,
|
| 2221 |
+
"learning_rate": 0.0004295332136445242,
|
| 2222 |
+
"loss": 4.2813,
|
| 2223 |
+
"step": 3140
|
| 2224 |
+
},
|
| 2225 |
+
{
|
| 2226 |
+
"epoch": 2.827648114901257,
|
| 2227 |
+
"grad_norm": 0.0564940869808197,
|
| 2228 |
+
"learning_rate": 0.00042930879712746857,
|
| 2229 |
+
"loss": 4.2875,
|
| 2230 |
+
"step": 3150
|
| 2231 |
+
},
|
| 2232 |
+
{
|
| 2233 |
+
"epoch": 2.836624775583483,
|
| 2234 |
+
"grad_norm": 0.08277291059494019,
|
| 2235 |
+
"learning_rate": 0.00042908438061041297,
|
| 2236 |
+
"loss": 4.2741,
|
| 2237 |
+
"step": 3160
|
| 2238 |
+
},
|
| 2239 |
+
{
|
| 2240 |
+
"epoch": 2.845601436265709,
|
| 2241 |
+
"grad_norm": 0.05882051959633827,
|
| 2242 |
+
"learning_rate": 0.00042885996409335725,
|
| 2243 |
+
"loss": 4.2606,
|
| 2244 |
+
"step": 3170
|
| 2245 |
+
},
|
| 2246 |
+
{
|
| 2247 |
+
"epoch": 2.8545780969479355,
|
| 2248 |
+
"grad_norm": 0.056912124156951904,
|
| 2249 |
+
"learning_rate": 0.00042863554757630165,
|
| 2250 |
+
"loss": 4.2387,
|
| 2251 |
+
"step": 3180
|
| 2252 |
+
},
|
| 2253 |
+
{
|
| 2254 |
+
"epoch": 2.8635547576301614,
|
| 2255 |
+
"grad_norm": 0.06803829967975616,
|
| 2256 |
+
"learning_rate": 0.00042841113105924594,
|
| 2257 |
+
"loss": 4.2595,
|
| 2258 |
+
"step": 3190
|
| 2259 |
+
},
|
| 2260 |
+
{
|
| 2261 |
+
"epoch": 2.872531418312388,
|
| 2262 |
+
"grad_norm": 0.38242146372795105,
|
| 2263 |
+
"learning_rate": 0.00042818671454219033,
|
| 2264 |
+
"loss": 4.252,
|
| 2265 |
+
"step": 3200
|
| 2266 |
+
},
|
| 2267 |
+
{
|
| 2268 |
+
"epoch": 2.881508078994614,
|
| 2269 |
+
"grad_norm": 0.06552311778068542,
|
| 2270 |
+
"learning_rate": 0.0004279622980251346,
|
| 2271 |
+
"loss": 4.2386,
|
| 2272 |
+
"step": 3210
|
| 2273 |
+
},
|
| 2274 |
+
{
|
| 2275 |
+
"epoch": 2.89048473967684,
|
| 2276 |
+
"grad_norm": 0.06190953776240349,
|
| 2277 |
+
"learning_rate": 0.000427737881508079,
|
| 2278 |
+
"loss": 4.2279,
|
| 2279 |
+
"step": 3220
|
| 2280 |
+
},
|
| 2281 |
+
{
|
| 2282 |
+
"epoch": 2.8994614003590664,
|
| 2283 |
+
"grad_norm": 0.07202804833650589,
|
| 2284 |
+
"learning_rate": 0.00042751346499102336,
|
| 2285 |
+
"loss": 4.2397,
|
| 2286 |
+
"step": 3230
|
| 2287 |
+
},
|
| 2288 |
+
{
|
| 2289 |
+
"epoch": 2.9084380610412928,
|
| 2290 |
+
"grad_norm": 0.06415878981351852,
|
| 2291 |
+
"learning_rate": 0.0004272890484739677,
|
| 2292 |
+
"loss": 4.2124,
|
| 2293 |
+
"step": 3240
|
| 2294 |
+
},
|
| 2295 |
+
{
|
| 2296 |
+
"epoch": 2.917414721723519,
|
| 2297 |
+
"grad_norm": 0.06290468573570251,
|
| 2298 |
+
"learning_rate": 0.00042706463195691204,
|
| 2299 |
+
"loss": 4.2267,
|
| 2300 |
+
"step": 3250
|
| 2301 |
+
},
|
| 2302 |
+
{
|
| 2303 |
+
"epoch": 2.926391382405745,
|
| 2304 |
+
"grad_norm": 0.05975602567195892,
|
| 2305 |
+
"learning_rate": 0.0004268402154398564,
|
| 2306 |
+
"loss": 4.21,
|
| 2307 |
+
"step": 3260
|
| 2308 |
+
},
|
| 2309 |
+
{
|
| 2310 |
+
"epoch": 2.9353680430879714,
|
| 2311 |
+
"grad_norm": 0.08022774755954742,
|
| 2312 |
+
"learning_rate": 0.0004266157989228007,
|
| 2313 |
+
"loss": 4.2127,
|
| 2314 |
+
"step": 3270
|
| 2315 |
+
},
|
| 2316 |
+
{
|
| 2317 |
+
"epoch": 2.9443447037701977,
|
| 2318 |
+
"grad_norm": 0.11041318625211716,
|
| 2319 |
+
"learning_rate": 0.0004263913824057451,
|
| 2320 |
+
"loss": 4.1903,
|
| 2321 |
+
"step": 3280
|
| 2322 |
+
},
|
| 2323 |
+
{
|
| 2324 |
+
"epoch": 2.9533213644524237,
|
| 2325 |
+
"grad_norm": 0.06093136593699455,
|
| 2326 |
+
"learning_rate": 0.0004261669658886894,
|
| 2327 |
+
"loss": 4.1882,
|
| 2328 |
+
"step": 3290
|
| 2329 |
+
},
|
| 2330 |
+
{
|
| 2331 |
+
"epoch": 2.96229802513465,
|
| 2332 |
+
"grad_norm": 0.060306135565042496,
|
| 2333 |
+
"learning_rate": 0.00042594254937163375,
|
| 2334 |
+
"loss": 4.1874,
|
| 2335 |
+
"step": 3300
|
| 2336 |
+
},
|
| 2337 |
+
{
|
| 2338 |
+
"epoch": 2.9712746858168764,
|
| 2339 |
+
"grad_norm": 0.0592743381857872,
|
| 2340 |
+
"learning_rate": 0.0004257181328545781,
|
| 2341 |
+
"loss": 4.1881,
|
| 2342 |
+
"step": 3310
|
| 2343 |
+
},
|
| 2344 |
+
{
|
| 2345 |
+
"epoch": 2.9802513464991023,
|
| 2346 |
+
"grad_norm": 0.06113787367939949,
|
| 2347 |
+
"learning_rate": 0.00042549371633752244,
|
| 2348 |
+
"loss": 4.1788,
|
| 2349 |
+
"step": 3320
|
| 2350 |
+
},
|
| 2351 |
+
{
|
| 2352 |
+
"epoch": 2.9892280071813286,
|
| 2353 |
+
"grad_norm": 0.0978228747844696,
|
| 2354 |
+
"learning_rate": 0.0004252692998204668,
|
| 2355 |
+
"loss": 4.1714,
|
| 2356 |
+
"step": 3330
|
| 2357 |
+
},
|
| 2358 |
+
{
|
| 2359 |
+
"epoch": 2.998204667863555,
|
| 2360 |
+
"grad_norm": 0.06704937666654587,
|
| 2361 |
+
"learning_rate": 0.0004250448833034111,
|
| 2362 |
+
"loss": 4.1375,
|
| 2363 |
+
"step": 3340
|
| 2364 |
+
},
|
| 2365 |
+
{
|
| 2366 |
+
"epoch": 3.0,
|
| 2367 |
+
"eval_loss": 3.9158332347869873,
|
| 2368 |
+
"eval_runtime": 437.3013,
|
| 2369 |
+
"eval_samples_per_second": 10.19,
|
| 2370 |
+
"eval_steps_per_second": 1.274,
|
| 2371 |
+
"step": 3342
|
| 2372 |
+
}
|
| 2373 |
+
],
|
| 2374 |
+
"logging_steps": 10,
|
| 2375 |
+
"max_steps": 22280,
|
| 2376 |
+
"num_input_tokens_seen": 0,
|
| 2377 |
+
"num_train_epochs": 20,
|
| 2378 |
+
"save_steps": 500,
|
| 2379 |
+
"stateful_callbacks": {
|
| 2380 |
+
"EarlyStoppingCallback": {
|
| 2381 |
+
"args": {
|
| 2382 |
+
"early_stopping_patience": 3,
|
| 2383 |
+
"early_stopping_threshold": 0.0
|
| 2384 |
+
},
|
| 2385 |
+
"attributes": {
|
| 2386 |
+
"early_stopping_patience_counter": 0
|
| 2387 |
+
}
|
| 2388 |
+
},
|
| 2389 |
+
"TrainerControl": {
|
| 2390 |
+
"args": {
|
| 2391 |
+
"should_epoch_stop": false,
|
| 2392 |
+
"should_evaluate": false,
|
| 2393 |
+
"should_log": false,
|
| 2394 |
+
"should_save": true,
|
| 2395 |
+
"should_training_stop": false
|
| 2396 |
+
},
|
| 2397 |
+
"attributes": {}
|
| 2398 |
+
}
|
| 2399 |
+
},
|
| 2400 |
+
"total_flos": 3.661123660598477e+16,
|
| 2401 |
+
"train_batch_size": 8,
|
| 2402 |
+
"trial_name": null,
|
| 2403 |
+
"trial_params": null
|
| 2404 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4d14485bb068ee3a24aafa8a5075f65b2a13aec8aa029042468cd1fbfd22b0a2
|
| 3 |
+
size 5304
|