Commit
•
9a07646
1
Parent(s):
ce25271
Training in progress, step 4000, checkpoint
Browse files- checkpoint-4000/README.md +202 -0
- checkpoint-4000/adapter_config.json +34 -0
- checkpoint-4000/adapter_model.safetensors +3 -0
- checkpoint-4000/optimizer.pt +3 -0
- checkpoint-4000/rng_state.pth +3 -0
- checkpoint-4000/scheduler.pt +3 -0
- checkpoint-4000/special_tokens_map.json +34 -0
- checkpoint-4000/tokenizer.json +3 -0
- checkpoint-4000/tokenizer.model +3 -0
- checkpoint-4000/tokenizer_config.json +1758 -0
- checkpoint-4000/trainer_state.json +2833 -0
- checkpoint-4000/training_args.bin +3 -0
checkpoint-4000/README.md
ADDED
|
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: peft
|
| 3 |
+
base_model: /mnt/sea/Punjabi_LLM/NEW/gemma_pa_llm_exp1_merged_66000
|
| 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 0.10.0
|
checkpoint-4000/adapter_config.json
ADDED
|
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "/mnt/sea/Punjabi_LLM/NEW/gemma_pa_llm_exp1_merged_66000",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"fan_in_fan_out": false,
|
| 7 |
+
"inference_mode": true,
|
| 8 |
+
"init_lora_weights": true,
|
| 9 |
+
"layer_replication": null,
|
| 10 |
+
"layers_pattern": null,
|
| 11 |
+
"layers_to_transform": null,
|
| 12 |
+
"loftq_config": {},
|
| 13 |
+
"lora_alpha": 64,
|
| 14 |
+
"lora_dropout": 0,
|
| 15 |
+
"megatron_config": null,
|
| 16 |
+
"megatron_core": "megatron.core",
|
| 17 |
+
"modules_to_save": null,
|
| 18 |
+
"peft_type": "LORA",
|
| 19 |
+
"r": 32,
|
| 20 |
+
"rank_pattern": {},
|
| 21 |
+
"revision": "unsloth",
|
| 22 |
+
"target_modules": [
|
| 23 |
+
"up_proj",
|
| 24 |
+
"o_proj",
|
| 25 |
+
"k_proj",
|
| 26 |
+
"v_proj",
|
| 27 |
+
"down_proj",
|
| 28 |
+
"q_proj",
|
| 29 |
+
"gate_proj"
|
| 30 |
+
],
|
| 31 |
+
"task_type": "CAUSAL_LM",
|
| 32 |
+
"use_dora": false,
|
| 33 |
+
"use_rslora": false
|
| 34 |
+
}
|
checkpoint-4000/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9d09ce8bc93d228f4774e282a7bf9dcabb2874ff10a46653019607f2cb709163
|
| 3 |
+
size 156926880
|
checkpoint-4000/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b1c46ae47be3460ab6142848da71078b8a84d5e628557a06a01dd085e33b3481
|
| 3 |
+
size 313937658
|
checkpoint-4000/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f7361d096916f558d6b135e234cb87021fe9c6dc7f10a56868e5238d1d27c50e
|
| 3 |
+
size 14244
|
checkpoint-4000/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d2c89f5fe79b840807ffd6c92850a646f018ab324f89083986ba3192bc161de2
|
| 3 |
+
size 1064
|
checkpoint-4000/special_tokens_map.json
ADDED
|
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<start_of_turn>",
|
| 4 |
+
"<end_of_turn>"
|
| 5 |
+
],
|
| 6 |
+
"bos_token": {
|
| 7 |
+
"content": "<bos>",
|
| 8 |
+
"lstrip": false,
|
| 9 |
+
"normalized": false,
|
| 10 |
+
"rstrip": false,
|
| 11 |
+
"single_word": false
|
| 12 |
+
},
|
| 13 |
+
"eos_token": {
|
| 14 |
+
"content": "<eos>",
|
| 15 |
+
"lstrip": false,
|
| 16 |
+
"normalized": false,
|
| 17 |
+
"rstrip": false,
|
| 18 |
+
"single_word": false
|
| 19 |
+
},
|
| 20 |
+
"pad_token": {
|
| 21 |
+
"content": "<pad>",
|
| 22 |
+
"lstrip": false,
|
| 23 |
+
"normalized": false,
|
| 24 |
+
"rstrip": false,
|
| 25 |
+
"single_word": false
|
| 26 |
+
},
|
| 27 |
+
"unk_token": {
|
| 28 |
+
"content": "<unk>",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false
|
| 33 |
+
}
|
| 34 |
+
}
|
checkpoint-4000/tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7da53ca29fb16f6b2489482fc0bc6a394162cdab14d12764a1755ebc583fea79
|
| 3 |
+
size 17518525
|
checkpoint-4000/tokenizer.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:61a7b147390c64585d6c3543dd6fc636906c9af3865a5548f27f31aee1d4c8e2
|
| 3 |
+
size 4241003
|
checkpoint-4000/tokenizer_config.json
ADDED
|
@@ -0,0 +1,1758 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": true,
|
| 3 |
+
"add_eos_token": false,
|
| 4 |
+
"added_tokens_decoder": {
|
| 5 |
+
"0": {
|
| 6 |
+
"content": "<pad>",
|
| 7 |
+
"lstrip": false,
|
| 8 |
+
"normalized": false,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false,
|
| 11 |
+
"special": true
|
| 12 |
+
},
|
| 13 |
+
"1": {
|
| 14 |
+
"content": "<eos>",
|
| 15 |
+
"lstrip": false,
|
| 16 |
+
"normalized": false,
|
| 17 |
+
"rstrip": false,
|
| 18 |
+
"single_word": false,
|
| 19 |
+
"special": true
|
| 20 |
+
},
|
| 21 |
+
"2": {
|
| 22 |
+
"content": "<bos>",
|
| 23 |
+
"lstrip": false,
|
| 24 |
+
"normalized": false,
|
| 25 |
+
"rstrip": false,
|
| 26 |
+
"single_word": false,
|
| 27 |
+
"special": true
|
| 28 |
+
},
|
| 29 |
+
"3": {
|
| 30 |
+
"content": "<unk>",
|
| 31 |
+
"lstrip": false,
|
| 32 |
+
"normalized": false,
|
| 33 |
+
"rstrip": false,
|
| 34 |
+
"single_word": false,
|
| 35 |
+
"special": true
|
| 36 |
+
},
|
| 37 |
+
"4": {
|
| 38 |
+
"content": "<mask>",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": false,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false,
|
| 43 |
+
"special": false
|
| 44 |
+
},
|
| 45 |
+
"5": {
|
| 46 |
+
"content": "<2mass>",
|
| 47 |
+
"lstrip": false,
|
| 48 |
+
"normalized": false,
|
| 49 |
+
"rstrip": false,
|
| 50 |
+
"single_word": false,
|
| 51 |
+
"special": false
|
| 52 |
+
},
|
| 53 |
+
"6": {
|
| 54 |
+
"content": "[@BOS@]",
|
| 55 |
+
"lstrip": false,
|
| 56 |
+
"normalized": false,
|
| 57 |
+
"rstrip": false,
|
| 58 |
+
"single_word": false,
|
| 59 |
+
"special": false
|
| 60 |
+
},
|
| 61 |
+
"7": {
|
| 62 |
+
"content": "<unused0>",
|
| 63 |
+
"lstrip": false,
|
| 64 |
+
"normalized": false,
|
| 65 |
+
"rstrip": false,
|
| 66 |
+
"single_word": false,
|
| 67 |
+
"special": false
|
| 68 |
+
},
|
| 69 |
+
"8": {
|
| 70 |
+
"content": "<unused1>",
|
| 71 |
+
"lstrip": false,
|
| 72 |
+
"normalized": false,
|
| 73 |
+
"rstrip": false,
|
| 74 |
+
"single_word": false,
|
| 75 |
+
"special": false
|
| 76 |
+
},
|
| 77 |
+
"9": {
|
| 78 |
+
"content": "<unused2>",
|
| 79 |
+
"lstrip": false,
|
| 80 |
+
"normalized": false,
|
| 81 |
+
"rstrip": false,
|
| 82 |
+
"single_word": false,
|
| 83 |
+
"special": false
|
| 84 |
+
},
|
| 85 |
+
"10": {
|
| 86 |
+
"content": "<unused3>",
|
| 87 |
+
"lstrip": false,
|
| 88 |
+
"normalized": false,
|
| 89 |
+
"rstrip": false,
|
| 90 |
+
"single_word": false,
|
| 91 |
+
"special": false
|
| 92 |
+
},
|
| 93 |
+
"11": {
|
| 94 |
+
"content": "<unused4>",
|
| 95 |
+
"lstrip": false,
|
| 96 |
+
"normalized": false,
|
| 97 |
+
"rstrip": false,
|
| 98 |
+
"single_word": false,
|
| 99 |
+
"special": false
|
| 100 |
+
},
|
| 101 |
+
"12": {
|
| 102 |
+
"content": "<unused5>",
|
| 103 |
+
"lstrip": false,
|
| 104 |
+
"normalized": false,
|
| 105 |
+
"rstrip": false,
|
| 106 |
+
"single_word": false,
|
| 107 |
+
"special": false
|
| 108 |
+
},
|
| 109 |
+
"13": {
|
| 110 |
+
"content": "<unused6>",
|
| 111 |
+
"lstrip": false,
|
| 112 |
+
"normalized": false,
|
| 113 |
+
"rstrip": false,
|
| 114 |
+
"single_word": false,
|
| 115 |
+
"special": false
|
| 116 |
+
},
|
| 117 |
+
"14": {
|
| 118 |
+
"content": "<unused7>",
|
| 119 |
+
"lstrip": false,
|
| 120 |
+
"normalized": false,
|
| 121 |
+
"rstrip": false,
|
| 122 |
+
"single_word": false,
|
| 123 |
+
"special": false
|
| 124 |
+
},
|
| 125 |
+
"15": {
|
| 126 |
+
"content": "<unused8>",
|
| 127 |
+
"lstrip": false,
|
| 128 |
+
"normalized": false,
|
| 129 |
+
"rstrip": false,
|
| 130 |
+
"single_word": false,
|
| 131 |
+
"special": false
|
| 132 |
+
},
|
| 133 |
+
"16": {
|
| 134 |
+
"content": "<unused9>",
|
| 135 |
+
"lstrip": false,
|
| 136 |
+
"normalized": false,
|
| 137 |
+
"rstrip": false,
|
| 138 |
+
"single_word": false,
|
| 139 |
+
"special": false
|
| 140 |
+
},
|
| 141 |
+
"17": {
|
| 142 |
+
"content": "<unused10>",
|
| 143 |
+
"lstrip": false,
|
| 144 |
+
"normalized": false,
|
| 145 |
+
"rstrip": false,
|
| 146 |
+
"single_word": false,
|
| 147 |
+
"special": false
|
| 148 |
+
},
|
| 149 |
+
"18": {
|
| 150 |
+
"content": "<unused11>",
|
| 151 |
+
"lstrip": false,
|
| 152 |
+
"normalized": false,
|
| 153 |
+
"rstrip": false,
|
| 154 |
+
"single_word": false,
|
| 155 |
+
"special": false
|
| 156 |
+
},
|
| 157 |
+
"19": {
|
| 158 |
+
"content": "<unused12>",
|
| 159 |
+
"lstrip": false,
|
| 160 |
+
"normalized": false,
|
| 161 |
+
"rstrip": false,
|
| 162 |
+
"single_word": false,
|
| 163 |
+
"special": false
|
| 164 |
+
},
|
| 165 |
+
"20": {
|
| 166 |
+
"content": "<unused13>",
|
| 167 |
+
"lstrip": false,
|
| 168 |
+
"normalized": false,
|
| 169 |
+
"rstrip": false,
|
| 170 |
+
"single_word": false,
|
| 171 |
+
"special": false
|
| 172 |
+
},
|
| 173 |
+
"21": {
|
| 174 |
+
"content": "<unused14>",
|
| 175 |
+
"lstrip": false,
|
| 176 |
+
"normalized": false,
|
| 177 |
+
"rstrip": false,
|
| 178 |
+
"single_word": false,
|
| 179 |
+
"special": false
|
| 180 |
+
},
|
| 181 |
+
"22": {
|
| 182 |
+
"content": "<unused15>",
|
| 183 |
+
"lstrip": false,
|
| 184 |
+
"normalized": false,
|
| 185 |
+
"rstrip": false,
|
| 186 |
+
"single_word": false,
|
| 187 |
+
"special": false
|
| 188 |
+
},
|
| 189 |
+
"23": {
|
| 190 |
+
"content": "<unused16>",
|
| 191 |
+
"lstrip": false,
|
| 192 |
+
"normalized": false,
|
| 193 |
+
"rstrip": false,
|
| 194 |
+
"single_word": false,
|
| 195 |
+
"special": false
|
| 196 |
+
},
|
| 197 |
+
"24": {
|
| 198 |
+
"content": "<unused17>",
|
| 199 |
+
"lstrip": false,
|
| 200 |
+
"normalized": false,
|
| 201 |
+
"rstrip": false,
|
| 202 |
+
"single_word": false,
|
| 203 |
+
"special": false
|
| 204 |
+
},
|
| 205 |
+
"25": {
|
| 206 |
+
"content": "<unused18>",
|
| 207 |
+
"lstrip": false,
|
| 208 |
+
"normalized": false,
|
| 209 |
+
"rstrip": false,
|
| 210 |
+
"single_word": false,
|
| 211 |
+
"special": false
|
| 212 |
+
},
|
| 213 |
+
"26": {
|
| 214 |
+
"content": "<unused19>",
|
| 215 |
+
"lstrip": false,
|
| 216 |
+
"normalized": false,
|
| 217 |
+
"rstrip": false,
|
| 218 |
+
"single_word": false,
|
| 219 |
+
"special": false
|
| 220 |
+
},
|
| 221 |
+
"27": {
|
| 222 |
+
"content": "<unused20>",
|
| 223 |
+
"lstrip": false,
|
| 224 |
+
"normalized": false,
|
| 225 |
+
"rstrip": false,
|
| 226 |
+
"single_word": false,
|
| 227 |
+
"special": false
|
| 228 |
+
},
|
| 229 |
+
"28": {
|
| 230 |
+
"content": "<unused21>",
|
| 231 |
+
"lstrip": false,
|
| 232 |
+
"normalized": false,
|
| 233 |
+
"rstrip": false,
|
| 234 |
+
"single_word": false,
|
| 235 |
+
"special": false
|
| 236 |
+
},
|
| 237 |
+
"29": {
|
| 238 |
+
"content": "<unused22>",
|
| 239 |
+
"lstrip": false,
|
| 240 |
+
"normalized": false,
|
| 241 |
+
"rstrip": false,
|
| 242 |
+
"single_word": false,
|
| 243 |
+
"special": false
|
| 244 |
+
},
|
| 245 |
+
"30": {
|
| 246 |
+
"content": "<unused23>",
|
| 247 |
+
"lstrip": false,
|
| 248 |
+
"normalized": false,
|
| 249 |
+
"rstrip": false,
|
| 250 |
+
"single_word": false,
|
| 251 |
+
"special": false
|
| 252 |
+
},
|
| 253 |
+
"31": {
|
| 254 |
+
"content": "<unused24>",
|
| 255 |
+
"lstrip": false,
|
| 256 |
+
"normalized": false,
|
| 257 |
+
"rstrip": false,
|
| 258 |
+
"single_word": false,
|
| 259 |
+
"special": false
|
| 260 |
+
},
|
| 261 |
+
"32": {
|
| 262 |
+
"content": "<unused25>",
|
| 263 |
+
"lstrip": false,
|
| 264 |
+
"normalized": false,
|
| 265 |
+
"rstrip": false,
|
| 266 |
+
"single_word": false,
|
| 267 |
+
"special": false
|
| 268 |
+
},
|
| 269 |
+
"33": {
|
| 270 |
+
"content": "<unused26>",
|
| 271 |
+
"lstrip": false,
|
| 272 |
+
"normalized": false,
|
| 273 |
+
"rstrip": false,
|
| 274 |
+
"single_word": false,
|
| 275 |
+
"special": false
|
| 276 |
+
},
|
| 277 |
+
"34": {
|
| 278 |
+
"content": "<unused27>",
|
| 279 |
+
"lstrip": false,
|
| 280 |
+
"normalized": false,
|
| 281 |
+
"rstrip": false,
|
| 282 |
+
"single_word": false,
|
| 283 |
+
"special": false
|
| 284 |
+
},
|
| 285 |
+
"35": {
|
| 286 |
+
"content": "<unused28>",
|
| 287 |
+
"lstrip": false,
|
| 288 |
+
"normalized": false,
|
| 289 |
+
"rstrip": false,
|
| 290 |
+
"single_word": false,
|
| 291 |
+
"special": false
|
| 292 |
+
},
|
| 293 |
+
"36": {
|
| 294 |
+
"content": "<unused29>",
|
| 295 |
+
"lstrip": false,
|
| 296 |
+
"normalized": false,
|
| 297 |
+
"rstrip": false,
|
| 298 |
+
"single_word": false,
|
| 299 |
+
"special": false
|
| 300 |
+
},
|
| 301 |
+
"37": {
|
| 302 |
+
"content": "<unused30>",
|
| 303 |
+
"lstrip": false,
|
| 304 |
+
"normalized": false,
|
| 305 |
+
"rstrip": false,
|
| 306 |
+
"single_word": false,
|
| 307 |
+
"special": false
|
| 308 |
+
},
|
| 309 |
+
"38": {
|
| 310 |
+
"content": "<unused31>",
|
| 311 |
+
"lstrip": false,
|
| 312 |
+
"normalized": false,
|
| 313 |
+
"rstrip": false,
|
| 314 |
+
"single_word": false,
|
| 315 |
+
"special": false
|
| 316 |
+
},
|
| 317 |
+
"39": {
|
| 318 |
+
"content": "<unused32>",
|
| 319 |
+
"lstrip": false,
|
| 320 |
+
"normalized": false,
|
| 321 |
+
"rstrip": false,
|
| 322 |
+
"single_word": false,
|
| 323 |
+
"special": false
|
| 324 |
+
},
|
| 325 |
+
"40": {
|
| 326 |
+
"content": "<unused33>",
|
| 327 |
+
"lstrip": false,
|
| 328 |
+
"normalized": false,
|
| 329 |
+
"rstrip": false,
|
| 330 |
+
"single_word": false,
|
| 331 |
+
"special": false
|
| 332 |
+
},
|
| 333 |
+
"41": {
|
| 334 |
+
"content": "<unused34>",
|
| 335 |
+
"lstrip": false,
|
| 336 |
+
"normalized": false,
|
| 337 |
+
"rstrip": false,
|
| 338 |
+
"single_word": false,
|
| 339 |
+
"special": false
|
| 340 |
+
},
|
| 341 |
+
"42": {
|
| 342 |
+
"content": "<unused35>",
|
| 343 |
+
"lstrip": false,
|
| 344 |
+
"normalized": false,
|
| 345 |
+
"rstrip": false,
|
| 346 |
+
"single_word": false,
|
| 347 |
+
"special": false
|
| 348 |
+
},
|
| 349 |
+
"43": {
|
| 350 |
+
"content": "<unused36>",
|
| 351 |
+
"lstrip": false,
|
| 352 |
+
"normalized": false,
|
| 353 |
+
"rstrip": false,
|
| 354 |
+
"single_word": false,
|
| 355 |
+
"special": false
|
| 356 |
+
},
|
| 357 |
+
"44": {
|
| 358 |
+
"content": "<unused37>",
|
| 359 |
+
"lstrip": false,
|
| 360 |
+
"normalized": false,
|
| 361 |
+
"rstrip": false,
|
| 362 |
+
"single_word": false,
|
| 363 |
+
"special": false
|
| 364 |
+
},
|
| 365 |
+
"45": {
|
| 366 |
+
"content": "<unused38>",
|
| 367 |
+
"lstrip": false,
|
| 368 |
+
"normalized": false,
|
| 369 |
+
"rstrip": false,
|
| 370 |
+
"single_word": false,
|
| 371 |
+
"special": false
|
| 372 |
+
},
|
| 373 |
+
"46": {
|
| 374 |
+
"content": "<unused39>",
|
| 375 |
+
"lstrip": false,
|
| 376 |
+
"normalized": false,
|
| 377 |
+
"rstrip": false,
|
| 378 |
+
"single_word": false,
|
| 379 |
+
"special": false
|
| 380 |
+
},
|
| 381 |
+
"47": {
|
| 382 |
+
"content": "<unused40>",
|
| 383 |
+
"lstrip": false,
|
| 384 |
+
"normalized": false,
|
| 385 |
+
"rstrip": false,
|
| 386 |
+
"single_word": false,
|
| 387 |
+
"special": false
|
| 388 |
+
},
|
| 389 |
+
"48": {
|
| 390 |
+
"content": "<unused41>",
|
| 391 |
+
"lstrip": false,
|
| 392 |
+
"normalized": false,
|
| 393 |
+
"rstrip": false,
|
| 394 |
+
"single_word": false,
|
| 395 |
+
"special": false
|
| 396 |
+
},
|
| 397 |
+
"49": {
|
| 398 |
+
"content": "<unused42>",
|
| 399 |
+
"lstrip": false,
|
| 400 |
+
"normalized": false,
|
| 401 |
+
"rstrip": false,
|
| 402 |
+
"single_word": false,
|
| 403 |
+
"special": false
|
| 404 |
+
},
|
| 405 |
+
"50": {
|
| 406 |
+
"content": "<unused43>",
|
| 407 |
+
"lstrip": false,
|
| 408 |
+
"normalized": false,
|
| 409 |
+
"rstrip": false,
|
| 410 |
+
"single_word": false,
|
| 411 |
+
"special": false
|
| 412 |
+
},
|
| 413 |
+
"51": {
|
| 414 |
+
"content": "<unused44>",
|
| 415 |
+
"lstrip": false,
|
| 416 |
+
"normalized": false,
|
| 417 |
+
"rstrip": false,
|
| 418 |
+
"single_word": false,
|
| 419 |
+
"special": false
|
| 420 |
+
},
|
| 421 |
+
"52": {
|
| 422 |
+
"content": "<unused45>",
|
| 423 |
+
"lstrip": false,
|
| 424 |
+
"normalized": false,
|
| 425 |
+
"rstrip": false,
|
| 426 |
+
"single_word": false,
|
| 427 |
+
"special": false
|
| 428 |
+
},
|
| 429 |
+
"53": {
|
| 430 |
+
"content": "<unused46>",
|
| 431 |
+
"lstrip": false,
|
| 432 |
+
"normalized": false,
|
| 433 |
+
"rstrip": false,
|
| 434 |
+
"single_word": false,
|
| 435 |
+
"special": false
|
| 436 |
+
},
|
| 437 |
+
"54": {
|
| 438 |
+
"content": "<unused47>",
|
| 439 |
+
"lstrip": false,
|
| 440 |
+
"normalized": false,
|
| 441 |
+
"rstrip": false,
|
| 442 |
+
"single_word": false,
|
| 443 |
+
"special": false
|
| 444 |
+
},
|
| 445 |
+
"55": {
|
| 446 |
+
"content": "<unused48>",
|
| 447 |
+
"lstrip": false,
|
| 448 |
+
"normalized": false,
|
| 449 |
+
"rstrip": false,
|
| 450 |
+
"single_word": false,
|
| 451 |
+
"special": false
|
| 452 |
+
},
|
| 453 |
+
"56": {
|
| 454 |
+
"content": "<unused49>",
|
| 455 |
+
"lstrip": false,
|
| 456 |
+
"normalized": false,
|
| 457 |
+
"rstrip": false,
|
| 458 |
+
"single_word": false,
|
| 459 |
+
"special": false
|
| 460 |
+
},
|
| 461 |
+
"57": {
|
| 462 |
+
"content": "<unused50>",
|
| 463 |
+
"lstrip": false,
|
| 464 |
+
"normalized": false,
|
| 465 |
+
"rstrip": false,
|
| 466 |
+
"single_word": false,
|
| 467 |
+
"special": false
|
| 468 |
+
},
|
| 469 |
+
"58": {
|
| 470 |
+
"content": "<unused51>",
|
| 471 |
+
"lstrip": false,
|
| 472 |
+
"normalized": false,
|
| 473 |
+
"rstrip": false,
|
| 474 |
+
"single_word": false,
|
| 475 |
+
"special": false
|
| 476 |
+
},
|
| 477 |
+
"59": {
|
| 478 |
+
"content": "<unused52>",
|
| 479 |
+
"lstrip": false,
|
| 480 |
+
"normalized": false,
|
| 481 |
+
"rstrip": false,
|
| 482 |
+
"single_word": false,
|
| 483 |
+
"special": false
|
| 484 |
+
},
|
| 485 |
+
"60": {
|
| 486 |
+
"content": "<unused53>",
|
| 487 |
+
"lstrip": false,
|
| 488 |
+
"normalized": false,
|
| 489 |
+
"rstrip": false,
|
| 490 |
+
"single_word": false,
|
| 491 |
+
"special": false
|
| 492 |
+
},
|
| 493 |
+
"61": {
|
| 494 |
+
"content": "<unused54>",
|
| 495 |
+
"lstrip": false,
|
| 496 |
+
"normalized": false,
|
| 497 |
+
"rstrip": false,
|
| 498 |
+
"single_word": false,
|
| 499 |
+
"special": false
|
| 500 |
+
},
|
| 501 |
+
"62": {
|
| 502 |
+
"content": "<unused55>",
|
| 503 |
+
"lstrip": false,
|
| 504 |
+
"normalized": false,
|
| 505 |
+
"rstrip": false,
|
| 506 |
+
"single_word": false,
|
| 507 |
+
"special": false
|
| 508 |
+
},
|
| 509 |
+
"63": {
|
| 510 |
+
"content": "<unused56>",
|
| 511 |
+
"lstrip": false,
|
| 512 |
+
"normalized": false,
|
| 513 |
+
"rstrip": false,
|
| 514 |
+
"single_word": false,
|
| 515 |
+
"special": false
|
| 516 |
+
},
|
| 517 |
+
"64": {
|
| 518 |
+
"content": "<unused57>",
|
| 519 |
+
"lstrip": false,
|
| 520 |
+
"normalized": false,
|
| 521 |
+
"rstrip": false,
|
| 522 |
+
"single_word": false,
|
| 523 |
+
"special": false
|
| 524 |
+
},
|
| 525 |
+
"65": {
|
| 526 |
+
"content": "<unused58>",
|
| 527 |
+
"lstrip": false,
|
| 528 |
+
"normalized": false,
|
| 529 |
+
"rstrip": false,
|
| 530 |
+
"single_word": false,
|
| 531 |
+
"special": false
|
| 532 |
+
},
|
| 533 |
+
"66": {
|
| 534 |
+
"content": "<unused59>",
|
| 535 |
+
"lstrip": false,
|
| 536 |
+
"normalized": false,
|
| 537 |
+
"rstrip": false,
|
| 538 |
+
"single_word": false,
|
| 539 |
+
"special": false
|
| 540 |
+
},
|
| 541 |
+
"67": {
|
| 542 |
+
"content": "<unused60>",
|
| 543 |
+
"lstrip": false,
|
| 544 |
+
"normalized": false,
|
| 545 |
+
"rstrip": false,
|
| 546 |
+
"single_word": false,
|
| 547 |
+
"special": false
|
| 548 |
+
},
|
| 549 |
+
"68": {
|
| 550 |
+
"content": "<unused61>",
|
| 551 |
+
"lstrip": false,
|
| 552 |
+
"normalized": false,
|
| 553 |
+
"rstrip": false,
|
| 554 |
+
"single_word": false,
|
| 555 |
+
"special": false
|
| 556 |
+
},
|
| 557 |
+
"69": {
|
| 558 |
+
"content": "<unused62>",
|
| 559 |
+
"lstrip": false,
|
| 560 |
+
"normalized": false,
|
| 561 |
+
"rstrip": false,
|
| 562 |
+
"single_word": false,
|
| 563 |
+
"special": false
|
| 564 |
+
},
|
| 565 |
+
"70": {
|
| 566 |
+
"content": "<unused63>",
|
| 567 |
+
"lstrip": false,
|
| 568 |
+
"normalized": false,
|
| 569 |
+
"rstrip": false,
|
| 570 |
+
"single_word": false,
|
| 571 |
+
"special": false
|
| 572 |
+
},
|
| 573 |
+
"71": {
|
| 574 |
+
"content": "<unused64>",
|
| 575 |
+
"lstrip": false,
|
| 576 |
+
"normalized": false,
|
| 577 |
+
"rstrip": false,
|
| 578 |
+
"single_word": false,
|
| 579 |
+
"special": false
|
| 580 |
+
},
|
| 581 |
+
"72": {
|
| 582 |
+
"content": "<unused65>",
|
| 583 |
+
"lstrip": false,
|
| 584 |
+
"normalized": false,
|
| 585 |
+
"rstrip": false,
|
| 586 |
+
"single_word": false,
|
| 587 |
+
"special": false
|
| 588 |
+
},
|
| 589 |
+
"73": {
|
| 590 |
+
"content": "<unused66>",
|
| 591 |
+
"lstrip": false,
|
| 592 |
+
"normalized": false,
|
| 593 |
+
"rstrip": false,
|
| 594 |
+
"single_word": false,
|
| 595 |
+
"special": false
|
| 596 |
+
},
|
| 597 |
+
"74": {
|
| 598 |
+
"content": "<unused67>",
|
| 599 |
+
"lstrip": false,
|
| 600 |
+
"normalized": false,
|
| 601 |
+
"rstrip": false,
|
| 602 |
+
"single_word": false,
|
| 603 |
+
"special": false
|
| 604 |
+
},
|
| 605 |
+
"75": {
|
| 606 |
+
"content": "<unused68>",
|
| 607 |
+
"lstrip": false,
|
| 608 |
+
"normalized": false,
|
| 609 |
+
"rstrip": false,
|
| 610 |
+
"single_word": false,
|
| 611 |
+
"special": false
|
| 612 |
+
},
|
| 613 |
+
"76": {
|
| 614 |
+
"content": "<unused69>",
|
| 615 |
+
"lstrip": false,
|
| 616 |
+
"normalized": false,
|
| 617 |
+
"rstrip": false,
|
| 618 |
+
"single_word": false,
|
| 619 |
+
"special": false
|
| 620 |
+
},
|
| 621 |
+
"77": {
|
| 622 |
+
"content": "<unused70>",
|
| 623 |
+
"lstrip": false,
|
| 624 |
+
"normalized": false,
|
| 625 |
+
"rstrip": false,
|
| 626 |
+
"single_word": false,
|
| 627 |
+
"special": false
|
| 628 |
+
},
|
| 629 |
+
"78": {
|
| 630 |
+
"content": "<unused71>",
|
| 631 |
+
"lstrip": false,
|
| 632 |
+
"normalized": false,
|
| 633 |
+
"rstrip": false,
|
| 634 |
+
"single_word": false,
|
| 635 |
+
"special": false
|
| 636 |
+
},
|
| 637 |
+
"79": {
|
| 638 |
+
"content": "<unused72>",
|
| 639 |
+
"lstrip": false,
|
| 640 |
+
"normalized": false,
|
| 641 |
+
"rstrip": false,
|
| 642 |
+
"single_word": false,
|
| 643 |
+
"special": false
|
| 644 |
+
},
|
| 645 |
+
"80": {
|
| 646 |
+
"content": "<unused73>",
|
| 647 |
+
"lstrip": false,
|
| 648 |
+
"normalized": false,
|
| 649 |
+
"rstrip": false,
|
| 650 |
+
"single_word": false,
|
| 651 |
+
"special": false
|
| 652 |
+
},
|
| 653 |
+
"81": {
|
| 654 |
+
"content": "<unused74>",
|
| 655 |
+
"lstrip": false,
|
| 656 |
+
"normalized": false,
|
| 657 |
+
"rstrip": false,
|
| 658 |
+
"single_word": false,
|
| 659 |
+
"special": false
|
| 660 |
+
},
|
| 661 |
+
"82": {
|
| 662 |
+
"content": "<unused75>",
|
| 663 |
+
"lstrip": false,
|
| 664 |
+
"normalized": false,
|
| 665 |
+
"rstrip": false,
|
| 666 |
+
"single_word": false,
|
| 667 |
+
"special": false
|
| 668 |
+
},
|
| 669 |
+
"83": {
|
| 670 |
+
"content": "<unused76>",
|
| 671 |
+
"lstrip": false,
|
| 672 |
+
"normalized": false,
|
| 673 |
+
"rstrip": false,
|
| 674 |
+
"single_word": false,
|
| 675 |
+
"special": false
|
| 676 |
+
},
|
| 677 |
+
"84": {
|
| 678 |
+
"content": "<unused77>",
|
| 679 |
+
"lstrip": false,
|
| 680 |
+
"normalized": false,
|
| 681 |
+
"rstrip": false,
|
| 682 |
+
"single_word": false,
|
| 683 |
+
"special": false
|
| 684 |
+
},
|
| 685 |
+
"85": {
|
| 686 |
+
"content": "<unused78>",
|
| 687 |
+
"lstrip": false,
|
| 688 |
+
"normalized": false,
|
| 689 |
+
"rstrip": false,
|
| 690 |
+
"single_word": false,
|
| 691 |
+
"special": false
|
| 692 |
+
},
|
| 693 |
+
"86": {
|
| 694 |
+
"content": "<unused79>",
|
| 695 |
+
"lstrip": false,
|
| 696 |
+
"normalized": false,
|
| 697 |
+
"rstrip": false,
|
| 698 |
+
"single_word": false,
|
| 699 |
+
"special": false
|
| 700 |
+
},
|
| 701 |
+
"87": {
|
| 702 |
+
"content": "<unused80>",
|
| 703 |
+
"lstrip": false,
|
| 704 |
+
"normalized": false,
|
| 705 |
+
"rstrip": false,
|
| 706 |
+
"single_word": false,
|
| 707 |
+
"special": false
|
| 708 |
+
},
|
| 709 |
+
"88": {
|
| 710 |
+
"content": "<unused81>",
|
| 711 |
+
"lstrip": false,
|
| 712 |
+
"normalized": false,
|
| 713 |
+
"rstrip": false,
|
| 714 |
+
"single_word": false,
|
| 715 |
+
"special": false
|
| 716 |
+
},
|
| 717 |
+
"89": {
|
| 718 |
+
"content": "<unused82>",
|
| 719 |
+
"lstrip": false,
|
| 720 |
+
"normalized": false,
|
| 721 |
+
"rstrip": false,
|
| 722 |
+
"single_word": false,
|
| 723 |
+
"special": false
|
| 724 |
+
},
|
| 725 |
+
"90": {
|
| 726 |
+
"content": "<unused83>",
|
| 727 |
+
"lstrip": false,
|
| 728 |
+
"normalized": false,
|
| 729 |
+
"rstrip": false,
|
| 730 |
+
"single_word": false,
|
| 731 |
+
"special": false
|
| 732 |
+
},
|
| 733 |
+
"91": {
|
| 734 |
+
"content": "<unused84>",
|
| 735 |
+
"lstrip": false,
|
| 736 |
+
"normalized": false,
|
| 737 |
+
"rstrip": false,
|
| 738 |
+
"single_word": false,
|
| 739 |
+
"special": false
|
| 740 |
+
},
|
| 741 |
+
"92": {
|
| 742 |
+
"content": "<unused85>",
|
| 743 |
+
"lstrip": false,
|
| 744 |
+
"normalized": false,
|
| 745 |
+
"rstrip": false,
|
| 746 |
+
"single_word": false,
|
| 747 |
+
"special": false
|
| 748 |
+
},
|
| 749 |
+
"93": {
|
| 750 |
+
"content": "<unused86>",
|
| 751 |
+
"lstrip": false,
|
| 752 |
+
"normalized": false,
|
| 753 |
+
"rstrip": false,
|
| 754 |
+
"single_word": false,
|
| 755 |
+
"special": false
|
| 756 |
+
},
|
| 757 |
+
"94": {
|
| 758 |
+
"content": "<unused87>",
|
| 759 |
+
"lstrip": false,
|
| 760 |
+
"normalized": false,
|
| 761 |
+
"rstrip": false,
|
| 762 |
+
"single_word": false,
|
| 763 |
+
"special": false
|
| 764 |
+
},
|
| 765 |
+
"95": {
|
| 766 |
+
"content": "<unused88>",
|
| 767 |
+
"lstrip": false,
|
| 768 |
+
"normalized": false,
|
| 769 |
+
"rstrip": false,
|
| 770 |
+
"single_word": false,
|
| 771 |
+
"special": false
|
| 772 |
+
},
|
| 773 |
+
"96": {
|
| 774 |
+
"content": "<unused89>",
|
| 775 |
+
"lstrip": false,
|
| 776 |
+
"normalized": false,
|
| 777 |
+
"rstrip": false,
|
| 778 |
+
"single_word": false,
|
| 779 |
+
"special": false
|
| 780 |
+
},
|
| 781 |
+
"97": {
|
| 782 |
+
"content": "<unused90>",
|
| 783 |
+
"lstrip": false,
|
| 784 |
+
"normalized": false,
|
| 785 |
+
"rstrip": false,
|
| 786 |
+
"single_word": false,
|
| 787 |
+
"special": false
|
| 788 |
+
},
|
| 789 |
+
"98": {
|
| 790 |
+
"content": "<unused91>",
|
| 791 |
+
"lstrip": false,
|
| 792 |
+
"normalized": false,
|
| 793 |
+
"rstrip": false,
|
| 794 |
+
"single_word": false,
|
| 795 |
+
"special": false
|
| 796 |
+
},
|
| 797 |
+
"99": {
|
| 798 |
+
"content": "<unused92>",
|
| 799 |
+
"lstrip": false,
|
| 800 |
+
"normalized": false,
|
| 801 |
+
"rstrip": false,
|
| 802 |
+
"single_word": false,
|
| 803 |
+
"special": false
|
| 804 |
+
},
|
| 805 |
+
"100": {
|
| 806 |
+
"content": "<unused93>",
|
| 807 |
+
"lstrip": false,
|
| 808 |
+
"normalized": false,
|
| 809 |
+
"rstrip": false,
|
| 810 |
+
"single_word": false,
|
| 811 |
+
"special": false
|
| 812 |
+
},
|
| 813 |
+
"101": {
|
| 814 |
+
"content": "<unused94>",
|
| 815 |
+
"lstrip": false,
|
| 816 |
+
"normalized": false,
|
| 817 |
+
"rstrip": false,
|
| 818 |
+
"single_word": false,
|
| 819 |
+
"special": false
|
| 820 |
+
},
|
| 821 |
+
"102": {
|
| 822 |
+
"content": "<unused95>",
|
| 823 |
+
"lstrip": false,
|
| 824 |
+
"normalized": false,
|
| 825 |
+
"rstrip": false,
|
| 826 |
+
"single_word": false,
|
| 827 |
+
"special": false
|
| 828 |
+
},
|
| 829 |
+
"103": {
|
| 830 |
+
"content": "<unused96>",
|
| 831 |
+
"lstrip": false,
|
| 832 |
+
"normalized": false,
|
| 833 |
+
"rstrip": false,
|
| 834 |
+
"single_word": false,
|
| 835 |
+
"special": false
|
| 836 |
+
},
|
| 837 |
+
"104": {
|
| 838 |
+
"content": "<unused97>",
|
| 839 |
+
"lstrip": false,
|
| 840 |
+
"normalized": false,
|
| 841 |
+
"rstrip": false,
|
| 842 |
+
"single_word": false,
|
| 843 |
+
"special": false
|
| 844 |
+
},
|
| 845 |
+
"105": {
|
| 846 |
+
"content": "<unused98>",
|
| 847 |
+
"lstrip": false,
|
| 848 |
+
"normalized": false,
|
| 849 |
+
"rstrip": false,
|
| 850 |
+
"single_word": false,
|
| 851 |
+
"special": false
|
| 852 |
+
},
|
| 853 |
+
"106": {
|
| 854 |
+
"content": "<start_of_turn>",
|
| 855 |
+
"lstrip": false,
|
| 856 |
+
"normalized": false,
|
| 857 |
+
"rstrip": false,
|
| 858 |
+
"single_word": false,
|
| 859 |
+
"special": true
|
| 860 |
+
},
|
| 861 |
+
"107": {
|
| 862 |
+
"content": "<end_of_turn>",
|
| 863 |
+
"lstrip": false,
|
| 864 |
+
"normalized": false,
|
| 865 |
+
"rstrip": false,
|
| 866 |
+
"single_word": false,
|
| 867 |
+
"special": true
|
| 868 |
+
},
|
| 869 |
+
"108": {
|
| 870 |
+
"content": "\n",
|
| 871 |
+
"lstrip": false,
|
| 872 |
+
"normalized": false,
|
| 873 |
+
"rstrip": false,
|
| 874 |
+
"single_word": false,
|
| 875 |
+
"special": false
|
| 876 |
+
},
|
| 877 |
+
"109": {
|
| 878 |
+
"content": "\n\n",
|
| 879 |
+
"lstrip": false,
|
| 880 |
+
"normalized": false,
|
| 881 |
+
"rstrip": false,
|
| 882 |
+
"single_word": false,
|
| 883 |
+
"special": false
|
| 884 |
+
},
|
| 885 |
+
"110": {
|
| 886 |
+
"content": "\n\n\n",
|
| 887 |
+
"lstrip": false,
|
| 888 |
+
"normalized": false,
|
| 889 |
+
"rstrip": false,
|
| 890 |
+
"single_word": false,
|
| 891 |
+
"special": false
|
| 892 |
+
},
|
| 893 |
+
"111": {
|
| 894 |
+
"content": "\n\n\n\n",
|
| 895 |
+
"lstrip": false,
|
| 896 |
+
"normalized": false,
|
| 897 |
+
"rstrip": false,
|
| 898 |
+
"single_word": false,
|
| 899 |
+
"special": false
|
| 900 |
+
},
|
| 901 |
+
"112": {
|
| 902 |
+
"content": "\n\n\n\n\n",
|
| 903 |
+
"lstrip": false,
|
| 904 |
+
"normalized": false,
|
| 905 |
+
"rstrip": false,
|
| 906 |
+
"single_word": false,
|
| 907 |
+
"special": false
|
| 908 |
+
},
|
| 909 |
+
"113": {
|
| 910 |
+
"content": "\n\n\n\n\n\n",
|
| 911 |
+
"lstrip": false,
|
| 912 |
+
"normalized": false,
|
| 913 |
+
"rstrip": false,
|
| 914 |
+
"single_word": false,
|
| 915 |
+
"special": false
|
| 916 |
+
},
|
| 917 |
+
"114": {
|
| 918 |
+
"content": "\n\n\n\n\n\n\n",
|
| 919 |
+
"lstrip": false,
|
| 920 |
+
"normalized": false,
|
| 921 |
+
"rstrip": false,
|
| 922 |
+
"single_word": false,
|
| 923 |
+
"special": false
|
| 924 |
+
},
|
| 925 |
+
"115": {
|
| 926 |
+
"content": "\n\n\n\n\n\n\n\n",
|
| 927 |
+
"lstrip": false,
|
| 928 |
+
"normalized": false,
|
| 929 |
+
"rstrip": false,
|
| 930 |
+
"single_word": false,
|
| 931 |
+
"special": false
|
| 932 |
+
},
|
| 933 |
+
"116": {
|
| 934 |
+
"content": "\n\n\n\n\n\n\n\n\n",
|
| 935 |
+
"lstrip": false,
|
| 936 |
+
"normalized": false,
|
| 937 |
+
"rstrip": false,
|
| 938 |
+
"single_word": false,
|
| 939 |
+
"special": false
|
| 940 |
+
},
|
| 941 |
+
"117": {
|
| 942 |
+
"content": "\n\n\n\n\n\n\n\n\n\n",
|
| 943 |
+
"lstrip": false,
|
| 944 |
+
"normalized": false,
|
| 945 |
+
"rstrip": false,
|
| 946 |
+
"single_word": false,
|
| 947 |
+
"special": false
|
| 948 |
+
},
|
| 949 |
+
"118": {
|
| 950 |
+
"content": "\n\n\n\n\n\n\n\n\n\n\n",
|
| 951 |
+
"lstrip": false,
|
| 952 |
+
"normalized": false,
|
| 953 |
+
"rstrip": false,
|
| 954 |
+
"single_word": false,
|
| 955 |
+
"special": false
|
| 956 |
+
},
|
| 957 |
+
"119": {
|
| 958 |
+
"content": "\n\n\n\n\n\n\n\n\n\n\n\n",
|
| 959 |
+
"lstrip": false,
|
| 960 |
+
"normalized": false,
|
| 961 |
+
"rstrip": false,
|
| 962 |
+
"single_word": false,
|
| 963 |
+
"special": false
|
| 964 |
+
},
|
| 965 |
+
"120": {
|
| 966 |
+
"content": "\n\n\n\n\n\n\n\n\n\n\n\n\n",
|
| 967 |
+
"lstrip": false,
|
| 968 |
+
"normalized": false,
|
| 969 |
+
"rstrip": false,
|
| 970 |
+
"single_word": false,
|
| 971 |
+
"special": false
|
| 972 |
+
},
|
| 973 |
+
"121": {
|
| 974 |
+
"content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
|
| 975 |
+
"lstrip": false,
|
| 976 |
+
"normalized": false,
|
| 977 |
+
"rstrip": false,
|
| 978 |
+
"single_word": false,
|
| 979 |
+
"special": false
|
| 980 |
+
},
|
| 981 |
+
"122": {
|
| 982 |
+
"content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
|
| 983 |
+
"lstrip": false,
|
| 984 |
+
"normalized": false,
|
| 985 |
+
"rstrip": false,
|
| 986 |
+
"single_word": false,
|
| 987 |
+
"special": false
|
| 988 |
+
},
|
| 989 |
+
"123": {
|
| 990 |
+
"content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
|
| 991 |
+
"lstrip": false,
|
| 992 |
+
"normalized": false,
|
| 993 |
+
"rstrip": false,
|
| 994 |
+
"single_word": false,
|
| 995 |
+
"special": false
|
| 996 |
+
},
|
| 997 |
+
"124": {
|
| 998 |
+
"content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
|
| 999 |
+
"lstrip": false,
|
| 1000 |
+
"normalized": false,
|
| 1001 |
+
"rstrip": false,
|
| 1002 |
+
"single_word": false,
|
| 1003 |
+
"special": false
|
| 1004 |
+
},
|
| 1005 |
+
"125": {
|
| 1006 |
+
"content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
|
| 1007 |
+
"lstrip": false,
|
| 1008 |
+
"normalized": false,
|
| 1009 |
+
"rstrip": false,
|
| 1010 |
+
"single_word": false,
|
| 1011 |
+
"special": false
|
| 1012 |
+
},
|
| 1013 |
+
"126": {
|
| 1014 |
+
"content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
|
| 1015 |
+
"lstrip": false,
|
| 1016 |
+
"normalized": false,
|
| 1017 |
+
"rstrip": false,
|
| 1018 |
+
"single_word": false,
|
| 1019 |
+
"special": false
|
| 1020 |
+
},
|
| 1021 |
+
"127": {
|
| 1022 |
+
"content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
|
| 1023 |
+
"lstrip": false,
|
| 1024 |
+
"normalized": false,
|
| 1025 |
+
"rstrip": false,
|
| 1026 |
+
"single_word": false,
|
| 1027 |
+
"special": false
|
| 1028 |
+
},
|
| 1029 |
+
"128": {
|
| 1030 |
+
"content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
|
| 1031 |
+
"lstrip": false,
|
| 1032 |
+
"normalized": false,
|
| 1033 |
+
"rstrip": false,
|
| 1034 |
+
"single_word": false,
|
| 1035 |
+
"special": false
|
| 1036 |
+
},
|
| 1037 |
+
"129": {
|
| 1038 |
+
"content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
|
| 1039 |
+
"lstrip": false,
|
| 1040 |
+
"normalized": false,
|
| 1041 |
+
"rstrip": false,
|
| 1042 |
+
"single_word": false,
|
| 1043 |
+
"special": false
|
| 1044 |
+
},
|
| 1045 |
+
"130": {
|
| 1046 |
+
"content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
|
| 1047 |
+
"lstrip": false,
|
| 1048 |
+
"normalized": false,
|
| 1049 |
+
"rstrip": false,
|
| 1050 |
+
"single_word": false,
|
| 1051 |
+
"special": false
|
| 1052 |
+
},
|
| 1053 |
+
"131": {
|
| 1054 |
+
"content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
|
| 1055 |
+
"lstrip": false,
|
| 1056 |
+
"normalized": false,
|
| 1057 |
+
"rstrip": false,
|
| 1058 |
+
"single_word": false,
|
| 1059 |
+
"special": false
|
| 1060 |
+
},
|
| 1061 |
+
"132": {
|
| 1062 |
+
"content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
|
| 1063 |
+
"lstrip": false,
|
| 1064 |
+
"normalized": false,
|
| 1065 |
+
"rstrip": false,
|
| 1066 |
+
"single_word": false,
|
| 1067 |
+
"special": false
|
| 1068 |
+
},
|
| 1069 |
+
"133": {
|
| 1070 |
+
"content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
|
| 1071 |
+
"lstrip": false,
|
| 1072 |
+
"normalized": false,
|
| 1073 |
+
"rstrip": false,
|
| 1074 |
+
"single_word": false,
|
| 1075 |
+
"special": false
|
| 1076 |
+
},
|
| 1077 |
+
"134": {
|
| 1078 |
+
"content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
|
| 1079 |
+
"lstrip": false,
|
| 1080 |
+
"normalized": false,
|
| 1081 |
+
"rstrip": false,
|
| 1082 |
+
"single_word": false,
|
| 1083 |
+
"special": false
|
| 1084 |
+
},
|
| 1085 |
+
"135": {
|
| 1086 |
+
"content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
|
| 1087 |
+
"lstrip": false,
|
| 1088 |
+
"normalized": false,
|
| 1089 |
+
"rstrip": false,
|
| 1090 |
+
"single_word": false,
|
| 1091 |
+
"special": false
|
| 1092 |
+
},
|
| 1093 |
+
"136": {
|
| 1094 |
+
"content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
|
| 1095 |
+
"lstrip": false,
|
| 1096 |
+
"normalized": false,
|
| 1097 |
+
"rstrip": false,
|
| 1098 |
+
"single_word": false,
|
| 1099 |
+
"special": false
|
| 1100 |
+
},
|
| 1101 |
+
"137": {
|
| 1102 |
+
"content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
|
| 1103 |
+
"lstrip": false,
|
| 1104 |
+
"normalized": false,
|
| 1105 |
+
"rstrip": false,
|
| 1106 |
+
"single_word": false,
|
| 1107 |
+
"special": false
|
| 1108 |
+
},
|
| 1109 |
+
"138": {
|
| 1110 |
+
"content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
|
| 1111 |
+
"lstrip": false,
|
| 1112 |
+
"normalized": false,
|
| 1113 |
+
"rstrip": false,
|
| 1114 |
+
"single_word": false,
|
| 1115 |
+
"special": false
|
| 1116 |
+
},
|
| 1117 |
+
"139": {
|
| 1118 |
+
"content": "▁▁",
|
| 1119 |
+
"lstrip": false,
|
| 1120 |
+
"normalized": false,
|
| 1121 |
+
"rstrip": false,
|
| 1122 |
+
"single_word": false,
|
| 1123 |
+
"special": false
|
| 1124 |
+
},
|
| 1125 |
+
"140": {
|
| 1126 |
+
"content": "▁▁▁",
|
| 1127 |
+
"lstrip": false,
|
| 1128 |
+
"normalized": false,
|
| 1129 |
+
"rstrip": false,
|
| 1130 |
+
"single_word": false,
|
| 1131 |
+
"special": false
|
| 1132 |
+
},
|
| 1133 |
+
"141": {
|
| 1134 |
+
"content": "▁▁▁▁",
|
| 1135 |
+
"lstrip": false,
|
| 1136 |
+
"normalized": false,
|
| 1137 |
+
"rstrip": false,
|
| 1138 |
+
"single_word": false,
|
| 1139 |
+
"special": false
|
| 1140 |
+
},
|
| 1141 |
+
"142": {
|
| 1142 |
+
"content": "▁▁▁▁▁",
|
| 1143 |
+
"lstrip": false,
|
| 1144 |
+
"normalized": false,
|
| 1145 |
+
"rstrip": false,
|
| 1146 |
+
"single_word": false,
|
| 1147 |
+
"special": false
|
| 1148 |
+
},
|
| 1149 |
+
"143": {
|
| 1150 |
+
"content": "▁▁▁▁▁▁",
|
| 1151 |
+
"lstrip": false,
|
| 1152 |
+
"normalized": false,
|
| 1153 |
+
"rstrip": false,
|
| 1154 |
+
"single_word": false,
|
| 1155 |
+
"special": false
|
| 1156 |
+
},
|
| 1157 |
+
"144": {
|
| 1158 |
+
"content": "▁▁▁▁▁▁▁",
|
| 1159 |
+
"lstrip": false,
|
| 1160 |
+
"normalized": false,
|
| 1161 |
+
"rstrip": false,
|
| 1162 |
+
"single_word": false,
|
| 1163 |
+
"special": false
|
| 1164 |
+
},
|
| 1165 |
+
"145": {
|
| 1166 |
+
"content": "▁▁▁▁▁▁▁▁",
|
| 1167 |
+
"lstrip": false,
|
| 1168 |
+
"normalized": false,
|
| 1169 |
+
"rstrip": false,
|
| 1170 |
+
"single_word": false,
|
| 1171 |
+
"special": false
|
| 1172 |
+
},
|
| 1173 |
+
"146": {
|
| 1174 |
+
"content": "▁▁▁▁▁▁▁▁▁",
|
| 1175 |
+
"lstrip": false,
|
| 1176 |
+
"normalized": false,
|
| 1177 |
+
"rstrip": false,
|
| 1178 |
+
"single_word": false,
|
| 1179 |
+
"special": false
|
| 1180 |
+
},
|
| 1181 |
+
"147": {
|
| 1182 |
+
"content": "▁▁▁▁▁▁▁▁▁▁",
|
| 1183 |
+
"lstrip": false,
|
| 1184 |
+
"normalized": false,
|
| 1185 |
+
"rstrip": false,
|
| 1186 |
+
"single_word": false,
|
| 1187 |
+
"special": false
|
| 1188 |
+
},
|
| 1189 |
+
"148": {
|
| 1190 |
+
"content": "▁▁▁▁▁▁▁▁▁▁▁",
|
| 1191 |
+
"lstrip": false,
|
| 1192 |
+
"normalized": false,
|
| 1193 |
+
"rstrip": false,
|
| 1194 |
+
"single_word": false,
|
| 1195 |
+
"special": false
|
| 1196 |
+
},
|
| 1197 |
+
"149": {
|
| 1198 |
+
"content": "▁▁▁▁▁▁▁▁▁▁▁▁",
|
| 1199 |
+
"lstrip": false,
|
| 1200 |
+
"normalized": false,
|
| 1201 |
+
"rstrip": false,
|
| 1202 |
+
"single_word": false,
|
| 1203 |
+
"special": false
|
| 1204 |
+
},
|
| 1205 |
+
"150": {
|
| 1206 |
+
"content": "▁▁▁▁▁▁▁▁▁▁▁▁▁",
|
| 1207 |
+
"lstrip": false,
|
| 1208 |
+
"normalized": false,
|
| 1209 |
+
"rstrip": false,
|
| 1210 |
+
"single_word": false,
|
| 1211 |
+
"special": false
|
| 1212 |
+
},
|
| 1213 |
+
"151": {
|
| 1214 |
+
"content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
|
| 1215 |
+
"lstrip": false,
|
| 1216 |
+
"normalized": false,
|
| 1217 |
+
"rstrip": false,
|
| 1218 |
+
"single_word": false,
|
| 1219 |
+
"special": false
|
| 1220 |
+
},
|
| 1221 |
+
"152": {
|
| 1222 |
+
"content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
|
| 1223 |
+
"lstrip": false,
|
| 1224 |
+
"normalized": false,
|
| 1225 |
+
"rstrip": false,
|
| 1226 |
+
"single_word": false,
|
| 1227 |
+
"special": false
|
| 1228 |
+
},
|
| 1229 |
+
"153": {
|
| 1230 |
+
"content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
|
| 1231 |
+
"lstrip": false,
|
| 1232 |
+
"normalized": false,
|
| 1233 |
+
"rstrip": false,
|
| 1234 |
+
"single_word": false,
|
| 1235 |
+
"special": false
|
| 1236 |
+
},
|
| 1237 |
+
"154": {
|
| 1238 |
+
"content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
|
| 1239 |
+
"lstrip": false,
|
| 1240 |
+
"normalized": false,
|
| 1241 |
+
"rstrip": false,
|
| 1242 |
+
"single_word": false,
|
| 1243 |
+
"special": false
|
| 1244 |
+
},
|
| 1245 |
+
"155": {
|
| 1246 |
+
"content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
|
| 1247 |
+
"lstrip": false,
|
| 1248 |
+
"normalized": false,
|
| 1249 |
+
"rstrip": false,
|
| 1250 |
+
"single_word": false,
|
| 1251 |
+
"special": false
|
| 1252 |
+
},
|
| 1253 |
+
"156": {
|
| 1254 |
+
"content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
|
| 1255 |
+
"lstrip": false,
|
| 1256 |
+
"normalized": false,
|
| 1257 |
+
"rstrip": false,
|
| 1258 |
+
"single_word": false,
|
| 1259 |
+
"special": false
|
| 1260 |
+
},
|
| 1261 |
+
"157": {
|
| 1262 |
+
"content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
|
| 1263 |
+
"lstrip": false,
|
| 1264 |
+
"normalized": false,
|
| 1265 |
+
"rstrip": false,
|
| 1266 |
+
"single_word": false,
|
| 1267 |
+
"special": false
|
| 1268 |
+
},
|
| 1269 |
+
"158": {
|
| 1270 |
+
"content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
|
| 1271 |
+
"lstrip": false,
|
| 1272 |
+
"normalized": false,
|
| 1273 |
+
"rstrip": false,
|
| 1274 |
+
"single_word": false,
|
| 1275 |
+
"special": false
|
| 1276 |
+
},
|
| 1277 |
+
"159": {
|
| 1278 |
+
"content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
|
| 1279 |
+
"lstrip": false,
|
| 1280 |
+
"normalized": false,
|
| 1281 |
+
"rstrip": false,
|
| 1282 |
+
"single_word": false,
|
| 1283 |
+
"special": false
|
| 1284 |
+
},
|
| 1285 |
+
"160": {
|
| 1286 |
+
"content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
|
| 1287 |
+
"lstrip": false,
|
| 1288 |
+
"normalized": false,
|
| 1289 |
+
"rstrip": false,
|
| 1290 |
+
"single_word": false,
|
| 1291 |
+
"special": false
|
| 1292 |
+
},
|
| 1293 |
+
"161": {
|
| 1294 |
+
"content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
|
| 1295 |
+
"lstrip": false,
|
| 1296 |
+
"normalized": false,
|
| 1297 |
+
"rstrip": false,
|
| 1298 |
+
"single_word": false,
|
| 1299 |
+
"special": false
|
| 1300 |
+
},
|
| 1301 |
+
"162": {
|
| 1302 |
+
"content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
|
| 1303 |
+
"lstrip": false,
|
| 1304 |
+
"normalized": false,
|
| 1305 |
+
"rstrip": false,
|
| 1306 |
+
"single_word": false,
|
| 1307 |
+
"special": false
|
| 1308 |
+
},
|
| 1309 |
+
"163": {
|
| 1310 |
+
"content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
|
| 1311 |
+
"lstrip": false,
|
| 1312 |
+
"normalized": false,
|
| 1313 |
+
"rstrip": false,
|
| 1314 |
+
"single_word": false,
|
| 1315 |
+
"special": false
|
| 1316 |
+
},
|
| 1317 |
+
"164": {
|
| 1318 |
+
"content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
|
| 1319 |
+
"lstrip": false,
|
| 1320 |
+
"normalized": false,
|
| 1321 |
+
"rstrip": false,
|
| 1322 |
+
"single_word": false,
|
| 1323 |
+
"special": false
|
| 1324 |
+
},
|
| 1325 |
+
"165": {
|
| 1326 |
+
"content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
|
| 1327 |
+
"lstrip": false,
|
| 1328 |
+
"normalized": false,
|
| 1329 |
+
"rstrip": false,
|
| 1330 |
+
"single_word": false,
|
| 1331 |
+
"special": false
|
| 1332 |
+
},
|
| 1333 |
+
"166": {
|
| 1334 |
+
"content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
|
| 1335 |
+
"lstrip": false,
|
| 1336 |
+
"normalized": false,
|
| 1337 |
+
"rstrip": false,
|
| 1338 |
+
"single_word": false,
|
| 1339 |
+
"special": false
|
| 1340 |
+
},
|
| 1341 |
+
"167": {
|
| 1342 |
+
"content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
|
| 1343 |
+
"lstrip": false,
|
| 1344 |
+
"normalized": false,
|
| 1345 |
+
"rstrip": false,
|
| 1346 |
+
"single_word": false,
|
| 1347 |
+
"special": false
|
| 1348 |
+
},
|
| 1349 |
+
"168": {
|
| 1350 |
+
"content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
|
| 1351 |
+
"lstrip": false,
|
| 1352 |
+
"normalized": false,
|
| 1353 |
+
"rstrip": false,
|
| 1354 |
+
"single_word": false,
|
| 1355 |
+
"special": false
|
| 1356 |
+
},
|
| 1357 |
+
"169": {
|
| 1358 |
+
"content": "<table>",
|
| 1359 |
+
"lstrip": false,
|
| 1360 |
+
"normalized": false,
|
| 1361 |
+
"rstrip": false,
|
| 1362 |
+
"single_word": false,
|
| 1363 |
+
"special": false
|
| 1364 |
+
},
|
| 1365 |
+
"170": {
|
| 1366 |
+
"content": "<caption>",
|
| 1367 |
+
"lstrip": false,
|
| 1368 |
+
"normalized": false,
|
| 1369 |
+
"rstrip": false,
|
| 1370 |
+
"single_word": false,
|
| 1371 |
+
"special": false
|
| 1372 |
+
},
|
| 1373 |
+
"171": {
|
| 1374 |
+
"content": "<thead>",
|
| 1375 |
+
"lstrip": false,
|
| 1376 |
+
"normalized": false,
|
| 1377 |
+
"rstrip": false,
|
| 1378 |
+
"single_word": false,
|
| 1379 |
+
"special": false
|
| 1380 |
+
},
|
| 1381 |
+
"172": {
|
| 1382 |
+
"content": "<tbody>",
|
| 1383 |
+
"lstrip": false,
|
| 1384 |
+
"normalized": false,
|
| 1385 |
+
"rstrip": false,
|
| 1386 |
+
"single_word": false,
|
| 1387 |
+
"special": false
|
| 1388 |
+
},
|
| 1389 |
+
"173": {
|
| 1390 |
+
"content": "<tfoot>",
|
| 1391 |
+
"lstrip": false,
|
| 1392 |
+
"normalized": false,
|
| 1393 |
+
"rstrip": false,
|
| 1394 |
+
"single_word": false,
|
| 1395 |
+
"special": false
|
| 1396 |
+
},
|
| 1397 |
+
"174": {
|
| 1398 |
+
"content": "<tr>",
|
| 1399 |
+
"lstrip": false,
|
| 1400 |
+
"normalized": false,
|
| 1401 |
+
"rstrip": false,
|
| 1402 |
+
"single_word": false,
|
| 1403 |
+
"special": false
|
| 1404 |
+
},
|
| 1405 |
+
"175": {
|
| 1406 |
+
"content": "<th>",
|
| 1407 |
+
"lstrip": false,
|
| 1408 |
+
"normalized": false,
|
| 1409 |
+
"rstrip": false,
|
| 1410 |
+
"single_word": false,
|
| 1411 |
+
"special": false
|
| 1412 |
+
},
|
| 1413 |
+
"176": {
|
| 1414 |
+
"content": "<td>",
|
| 1415 |
+
"lstrip": false,
|
| 1416 |
+
"normalized": false,
|
| 1417 |
+
"rstrip": false,
|
| 1418 |
+
"single_word": false,
|
| 1419 |
+
"special": false
|
| 1420 |
+
},
|
| 1421 |
+
"177": {
|
| 1422 |
+
"content": "</table>",
|
| 1423 |
+
"lstrip": false,
|
| 1424 |
+
"normalized": false,
|
| 1425 |
+
"rstrip": false,
|
| 1426 |
+
"single_word": false,
|
| 1427 |
+
"special": false
|
| 1428 |
+
},
|
| 1429 |
+
"178": {
|
| 1430 |
+
"content": "</caption>",
|
| 1431 |
+
"lstrip": false,
|
| 1432 |
+
"normalized": false,
|
| 1433 |
+
"rstrip": false,
|
| 1434 |
+
"single_word": false,
|
| 1435 |
+
"special": false
|
| 1436 |
+
},
|
| 1437 |
+
"179": {
|
| 1438 |
+
"content": "</thead>",
|
| 1439 |
+
"lstrip": false,
|
| 1440 |
+
"normalized": false,
|
| 1441 |
+
"rstrip": false,
|
| 1442 |
+
"single_word": false,
|
| 1443 |
+
"special": false
|
| 1444 |
+
},
|
| 1445 |
+
"180": {
|
| 1446 |
+
"content": "</tbody>",
|
| 1447 |
+
"lstrip": false,
|
| 1448 |
+
"normalized": false,
|
| 1449 |
+
"rstrip": false,
|
| 1450 |
+
"single_word": false,
|
| 1451 |
+
"special": false
|
| 1452 |
+
},
|
| 1453 |
+
"181": {
|
| 1454 |
+
"content": "</tfoot>",
|
| 1455 |
+
"lstrip": false,
|
| 1456 |
+
"normalized": false,
|
| 1457 |
+
"rstrip": false,
|
| 1458 |
+
"single_word": false,
|
| 1459 |
+
"special": false
|
| 1460 |
+
},
|
| 1461 |
+
"182": {
|
| 1462 |
+
"content": "</tr>",
|
| 1463 |
+
"lstrip": false,
|
| 1464 |
+
"normalized": false,
|
| 1465 |
+
"rstrip": false,
|
| 1466 |
+
"single_word": false,
|
| 1467 |
+
"special": false
|
| 1468 |
+
},
|
| 1469 |
+
"183": {
|
| 1470 |
+
"content": "</th>",
|
| 1471 |
+
"lstrip": false,
|
| 1472 |
+
"normalized": false,
|
| 1473 |
+
"rstrip": false,
|
| 1474 |
+
"single_word": false,
|
| 1475 |
+
"special": false
|
| 1476 |
+
},
|
| 1477 |
+
"184": {
|
| 1478 |
+
"content": "</td>",
|
| 1479 |
+
"lstrip": false,
|
| 1480 |
+
"normalized": false,
|
| 1481 |
+
"rstrip": false,
|
| 1482 |
+
"single_word": false,
|
| 1483 |
+
"special": false
|
| 1484 |
+
},
|
| 1485 |
+
"185": {
|
| 1486 |
+
"content": "<h1>",
|
| 1487 |
+
"lstrip": false,
|
| 1488 |
+
"normalized": false,
|
| 1489 |
+
"rstrip": false,
|
| 1490 |
+
"single_word": false,
|
| 1491 |
+
"special": false
|
| 1492 |
+
},
|
| 1493 |
+
"186": {
|
| 1494 |
+
"content": "<h2>",
|
| 1495 |
+
"lstrip": false,
|
| 1496 |
+
"normalized": false,
|
| 1497 |
+
"rstrip": false,
|
| 1498 |
+
"single_word": false,
|
| 1499 |
+
"special": false
|
| 1500 |
+
},
|
| 1501 |
+
"187": {
|
| 1502 |
+
"content": "<h3>",
|
| 1503 |
+
"lstrip": false,
|
| 1504 |
+
"normalized": false,
|
| 1505 |
+
"rstrip": false,
|
| 1506 |
+
"single_word": false,
|
| 1507 |
+
"special": false
|
| 1508 |
+
},
|
| 1509 |
+
"188": {
|
| 1510 |
+
"content": "<h4>",
|
| 1511 |
+
"lstrip": false,
|
| 1512 |
+
"normalized": false,
|
| 1513 |
+
"rstrip": false,
|
| 1514 |
+
"single_word": false,
|
| 1515 |
+
"special": false
|
| 1516 |
+
},
|
| 1517 |
+
"189": {
|
| 1518 |
+
"content": "<h5>",
|
| 1519 |
+
"lstrip": false,
|
| 1520 |
+
"normalized": false,
|
| 1521 |
+
"rstrip": false,
|
| 1522 |
+
"single_word": false,
|
| 1523 |
+
"special": false
|
| 1524 |
+
},
|
| 1525 |
+
"190": {
|
| 1526 |
+
"content": "<h6>",
|
| 1527 |
+
"lstrip": false,
|
| 1528 |
+
"normalized": false,
|
| 1529 |
+
"rstrip": false,
|
| 1530 |
+
"single_word": false,
|
| 1531 |
+
"special": false
|
| 1532 |
+
},
|
| 1533 |
+
"191": {
|
| 1534 |
+
"content": "<blockquote>",
|
| 1535 |
+
"lstrip": false,
|
| 1536 |
+
"normalized": false,
|
| 1537 |
+
"rstrip": false,
|
| 1538 |
+
"single_word": false,
|
| 1539 |
+
"special": false
|
| 1540 |
+
},
|
| 1541 |
+
"192": {
|
| 1542 |
+
"content": "</h1>",
|
| 1543 |
+
"lstrip": false,
|
| 1544 |
+
"normalized": false,
|
| 1545 |
+
"rstrip": false,
|
| 1546 |
+
"single_word": false,
|
| 1547 |
+
"special": false
|
| 1548 |
+
},
|
| 1549 |
+
"193": {
|
| 1550 |
+
"content": "</h2>",
|
| 1551 |
+
"lstrip": false,
|
| 1552 |
+
"normalized": false,
|
| 1553 |
+
"rstrip": false,
|
| 1554 |
+
"single_word": false,
|
| 1555 |
+
"special": false
|
| 1556 |
+
},
|
| 1557 |
+
"194": {
|
| 1558 |
+
"content": "</h3>",
|
| 1559 |
+
"lstrip": false,
|
| 1560 |
+
"normalized": false,
|
| 1561 |
+
"rstrip": false,
|
| 1562 |
+
"single_word": false,
|
| 1563 |
+
"special": false
|
| 1564 |
+
},
|
| 1565 |
+
"195": {
|
| 1566 |
+
"content": "</h4>",
|
| 1567 |
+
"lstrip": false,
|
| 1568 |
+
"normalized": false,
|
| 1569 |
+
"rstrip": false,
|
| 1570 |
+
"single_word": false,
|
| 1571 |
+
"special": false
|
| 1572 |
+
},
|
| 1573 |
+
"196": {
|
| 1574 |
+
"content": "</h5>",
|
| 1575 |
+
"lstrip": false,
|
| 1576 |
+
"normalized": false,
|
| 1577 |
+
"rstrip": false,
|
| 1578 |
+
"single_word": false,
|
| 1579 |
+
"special": false
|
| 1580 |
+
},
|
| 1581 |
+
"197": {
|
| 1582 |
+
"content": "</h6>",
|
| 1583 |
+
"lstrip": false,
|
| 1584 |
+
"normalized": false,
|
| 1585 |
+
"rstrip": false,
|
| 1586 |
+
"single_word": false,
|
| 1587 |
+
"special": false
|
| 1588 |
+
},
|
| 1589 |
+
"198": {
|
| 1590 |
+
"content": "</blockquote>",
|
| 1591 |
+
"lstrip": false,
|
| 1592 |
+
"normalized": false,
|
| 1593 |
+
"rstrip": false,
|
| 1594 |
+
"single_word": false,
|
| 1595 |
+
"special": false
|
| 1596 |
+
},
|
| 1597 |
+
"199": {
|
| 1598 |
+
"content": "<strong>",
|
| 1599 |
+
"lstrip": false,
|
| 1600 |
+
"normalized": false,
|
| 1601 |
+
"rstrip": false,
|
| 1602 |
+
"single_word": false,
|
| 1603 |
+
"special": false
|
| 1604 |
+
},
|
| 1605 |
+
"200": {
|
| 1606 |
+
"content": "<em>",
|
| 1607 |
+
"lstrip": false,
|
| 1608 |
+
"normalized": false,
|
| 1609 |
+
"rstrip": false,
|
| 1610 |
+
"single_word": false,
|
| 1611 |
+
"special": false
|
| 1612 |
+
},
|
| 1613 |
+
"201": {
|
| 1614 |
+
"content": "<b>",
|
| 1615 |
+
"lstrip": false,
|
| 1616 |
+
"normalized": false,
|
| 1617 |
+
"rstrip": false,
|
| 1618 |
+
"single_word": false,
|
| 1619 |
+
"special": false
|
| 1620 |
+
},
|
| 1621 |
+
"202": {
|
| 1622 |
+
"content": "<i>",
|
| 1623 |
+
"lstrip": false,
|
| 1624 |
+
"normalized": false,
|
| 1625 |
+
"rstrip": false,
|
| 1626 |
+
"single_word": false,
|
| 1627 |
+
"special": false
|
| 1628 |
+
},
|
| 1629 |
+
"203": {
|
| 1630 |
+
"content": "<u>",
|
| 1631 |
+
"lstrip": false,
|
| 1632 |
+
"normalized": false,
|
| 1633 |
+
"rstrip": false,
|
| 1634 |
+
"single_word": false,
|
| 1635 |
+
"special": false
|
| 1636 |
+
},
|
| 1637 |
+
"204": {
|
| 1638 |
+
"content": "<s>",
|
| 1639 |
+
"lstrip": false,
|
| 1640 |
+
"normalized": false,
|
| 1641 |
+
"rstrip": false,
|
| 1642 |
+
"single_word": false,
|
| 1643 |
+
"special": false
|
| 1644 |
+
},
|
| 1645 |
+
"205": {
|
| 1646 |
+
"content": "<sub>",
|
| 1647 |
+
"lstrip": false,
|
| 1648 |
+
"normalized": false,
|
| 1649 |
+
"rstrip": false,
|
| 1650 |
+
"single_word": false,
|
| 1651 |
+
"special": false
|
| 1652 |
+
},
|
| 1653 |
+
"206": {
|
| 1654 |
+
"content": "<sup>",
|
| 1655 |
+
"lstrip": false,
|
| 1656 |
+
"normalized": false,
|
| 1657 |
+
"rstrip": false,
|
| 1658 |
+
"single_word": false,
|
| 1659 |
+
"special": false
|
| 1660 |
+
},
|
| 1661 |
+
"207": {
|
| 1662 |
+
"content": "<code>",
|
| 1663 |
+
"lstrip": false,
|
| 1664 |
+
"normalized": false,
|
| 1665 |
+
"rstrip": false,
|
| 1666 |
+
"single_word": false,
|
| 1667 |
+
"special": false
|
| 1668 |
+
},
|
| 1669 |
+
"208": {
|
| 1670 |
+
"content": "</strong>",
|
| 1671 |
+
"lstrip": false,
|
| 1672 |
+
"normalized": false,
|
| 1673 |
+
"rstrip": false,
|
| 1674 |
+
"single_word": false,
|
| 1675 |
+
"special": false
|
| 1676 |
+
},
|
| 1677 |
+
"209": {
|
| 1678 |
+
"content": "</em>",
|
| 1679 |
+
"lstrip": false,
|
| 1680 |
+
"normalized": false,
|
| 1681 |
+
"rstrip": false,
|
| 1682 |
+
"single_word": false,
|
| 1683 |
+
"special": false
|
| 1684 |
+
},
|
| 1685 |
+
"210": {
|
| 1686 |
+
"content": "</b>",
|
| 1687 |
+
"lstrip": false,
|
| 1688 |
+
"normalized": false,
|
| 1689 |
+
"rstrip": false,
|
| 1690 |
+
"single_word": false,
|
| 1691 |
+
"special": false
|
| 1692 |
+
},
|
| 1693 |
+
"211": {
|
| 1694 |
+
"content": "</i>",
|
| 1695 |
+
"lstrip": false,
|
| 1696 |
+
"normalized": false,
|
| 1697 |
+
"rstrip": false,
|
| 1698 |
+
"single_word": false,
|
| 1699 |
+
"special": false
|
| 1700 |
+
},
|
| 1701 |
+
"212": {
|
| 1702 |
+
"content": "</u>",
|
| 1703 |
+
"lstrip": false,
|
| 1704 |
+
"normalized": false,
|
| 1705 |
+
"rstrip": false,
|
| 1706 |
+
"single_word": false,
|
| 1707 |
+
"special": false
|
| 1708 |
+
},
|
| 1709 |
+
"213": {
|
| 1710 |
+
"content": "</s>",
|
| 1711 |
+
"lstrip": false,
|
| 1712 |
+
"normalized": false,
|
| 1713 |
+
"rstrip": false,
|
| 1714 |
+
"single_word": false,
|
| 1715 |
+
"special": false
|
| 1716 |
+
},
|
| 1717 |
+
"214": {
|
| 1718 |
+
"content": "</sub>",
|
| 1719 |
+
"lstrip": false,
|
| 1720 |
+
"normalized": false,
|
| 1721 |
+
"rstrip": false,
|
| 1722 |
+
"single_word": false,
|
| 1723 |
+
"special": false
|
| 1724 |
+
},
|
| 1725 |
+
"215": {
|
| 1726 |
+
"content": "</sup>",
|
| 1727 |
+
"lstrip": false,
|
| 1728 |
+
"normalized": false,
|
| 1729 |
+
"rstrip": false,
|
| 1730 |
+
"single_word": false,
|
| 1731 |
+
"special": false
|
| 1732 |
+
},
|
| 1733 |
+
"216": {
|
| 1734 |
+
"content": "</code>",
|
| 1735 |
+
"lstrip": false,
|
| 1736 |
+
"normalized": false,
|
| 1737 |
+
"rstrip": false,
|
| 1738 |
+
"single_word": false,
|
| 1739 |
+
"special": false
|
| 1740 |
+
}
|
| 1741 |
+
},
|
| 1742 |
+
"additional_special_tokens": [
|
| 1743 |
+
"<start_of_turn>",
|
| 1744 |
+
"<end_of_turn>"
|
| 1745 |
+
],
|
| 1746 |
+
"bos_token": "<bos>",
|
| 1747 |
+
"chat_template": "{{ bos_token }}{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{{'<start_of_turn>'}}{% if message['from'] == 'system' %}{{'system'}}{% elif message['from'] == 'gpt' %}{{'model'}}{% elif message['from'] == 'human' %}{{'user'}}{% endif %}{{'\n' + message['value'] + '<end_of_turn>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<start_of_turn>model\n' }}{% endif %}",
|
| 1748 |
+
"clean_up_tokenization_spaces": false,
|
| 1749 |
+
"eos_token": "<eos>",
|
| 1750 |
+
"model_max_length": 8192,
|
| 1751 |
+
"pad_token": "<pad>",
|
| 1752 |
+
"padding_side": "right",
|
| 1753 |
+
"sp_model_kwargs": {},
|
| 1754 |
+
"spaces_between_special_tokens": false,
|
| 1755 |
+
"tokenizer_class": "GemmaTokenizer",
|
| 1756 |
+
"unk_token": "<unk>",
|
| 1757 |
+
"use_default_system_prompt": false
|
| 1758 |
+
}
|
checkpoint-4000/trainer_state.json
ADDED
|
@@ -0,0 +1,2833 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.10415672114641832,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 4000,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.0002603918028660458,
|
| 13 |
+
"grad_norm": 0.4500846266746521,
|
| 14 |
+
"learning_rate": 5.194805194805195e-06,
|
| 15 |
+
"loss": 1.0381,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.0005207836057320916,
|
| 20 |
+
"grad_norm": 0.35188010334968567,
|
| 21 |
+
"learning_rate": 1.038961038961039e-05,
|
| 22 |
+
"loss": 1.0108,
|
| 23 |
+
"step": 20
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.0007811754085981374,
|
| 27 |
+
"grad_norm": 0.2300374060869217,
|
| 28 |
+
"learning_rate": 1.5584415584415583e-05,
|
| 29 |
+
"loss": 0.9668,
|
| 30 |
+
"step": 30
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.0010415672114641832,
|
| 34 |
+
"grad_norm": 0.16189467906951904,
|
| 35 |
+
"learning_rate": 2.077922077922078e-05,
|
| 36 |
+
"loss": 0.918,
|
| 37 |
+
"step": 40
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.001301959014330229,
|
| 41 |
+
"grad_norm": 0.18843211233615875,
|
| 42 |
+
"learning_rate": 2.5974025974025972e-05,
|
| 43 |
+
"loss": 0.9265,
|
| 44 |
+
"step": 50
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.0015623508171962747,
|
| 48 |
+
"grad_norm": 0.20334510505199432,
|
| 49 |
+
"learning_rate": 3.1168831168831166e-05,
|
| 50 |
+
"loss": 0.9234,
|
| 51 |
+
"step": 60
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.0018227426200623205,
|
| 55 |
+
"grad_norm": 0.1745327115058899,
|
| 56 |
+
"learning_rate": 3.6363636363636364e-05,
|
| 57 |
+
"loss": 0.881,
|
| 58 |
+
"step": 70
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.0020831344229283663,
|
| 62 |
+
"grad_norm": 0.18667331337928772,
|
| 63 |
+
"learning_rate": 4.155844155844156e-05,
|
| 64 |
+
"loss": 0.8592,
|
| 65 |
+
"step": 80
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.002343526225794412,
|
| 69 |
+
"grad_norm": 0.1848158985376358,
|
| 70 |
+
"learning_rate": 4.675324675324675e-05,
|
| 71 |
+
"loss": 0.8537,
|
| 72 |
+
"step": 90
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.002603918028660458,
|
| 76 |
+
"grad_norm": 0.17589879035949707,
|
| 77 |
+
"learning_rate": 5.1948051948051944e-05,
|
| 78 |
+
"loss": 0.8518,
|
| 79 |
+
"step": 100
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.0028643098315265037,
|
| 83 |
+
"grad_norm": 0.2132624089717865,
|
| 84 |
+
"learning_rate": 5.714285714285714e-05,
|
| 85 |
+
"loss": 0.8511,
|
| 86 |
+
"step": 110
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.0031247016343925495,
|
| 90 |
+
"grad_norm": 0.23070092499256134,
|
| 91 |
+
"learning_rate": 6.233766233766233e-05,
|
| 92 |
+
"loss": 0.7975,
|
| 93 |
+
"step": 120
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.0033850934372585953,
|
| 97 |
+
"grad_norm": 0.25368157029151917,
|
| 98 |
+
"learning_rate": 6.753246753246754e-05,
|
| 99 |
+
"loss": 0.8134,
|
| 100 |
+
"step": 130
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.003645485240124641,
|
| 104 |
+
"grad_norm": 0.22897231578826904,
|
| 105 |
+
"learning_rate": 7.272727272727273e-05,
|
| 106 |
+
"loss": 0.8322,
|
| 107 |
+
"step": 140
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.003905877042990687,
|
| 111 |
+
"grad_norm": 0.19932536780834198,
|
| 112 |
+
"learning_rate": 7.792207792207793e-05,
|
| 113 |
+
"loss": 0.7959,
|
| 114 |
+
"step": 150
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.004166268845856733,
|
| 118 |
+
"grad_norm": 0.21011792123317719,
|
| 119 |
+
"learning_rate": 8.311688311688312e-05,
|
| 120 |
+
"loss": 0.8102,
|
| 121 |
+
"step": 160
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.004426660648722778,
|
| 125 |
+
"grad_norm": 0.20594824850559235,
|
| 126 |
+
"learning_rate": 8.831168831168831e-05,
|
| 127 |
+
"loss": 0.8128,
|
| 128 |
+
"step": 170
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.004687052451588824,
|
| 132 |
+
"grad_norm": 0.20465536415576935,
|
| 133 |
+
"learning_rate": 9.35064935064935e-05,
|
| 134 |
+
"loss": 0.7989,
|
| 135 |
+
"step": 180
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.00494744425445487,
|
| 139 |
+
"grad_norm": 0.4109392762184143,
|
| 140 |
+
"learning_rate": 9.870129870129871e-05,
|
| 141 |
+
"loss": 0.8108,
|
| 142 |
+
"step": 190
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.005207836057320916,
|
| 146 |
+
"grad_norm": 0.4293076694011688,
|
| 147 |
+
"learning_rate": 0.00010389610389610389,
|
| 148 |
+
"loss": 0.8101,
|
| 149 |
+
"step": 200
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.005468227860186962,
|
| 153 |
+
"grad_norm": 0.31628963351249695,
|
| 154 |
+
"learning_rate": 0.00010909090909090909,
|
| 155 |
+
"loss": 0.7989,
|
| 156 |
+
"step": 210
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.005728619663053007,
|
| 160 |
+
"grad_norm": 0.24642810225486755,
|
| 161 |
+
"learning_rate": 0.00011428571428571428,
|
| 162 |
+
"loss": 0.7751,
|
| 163 |
+
"step": 220
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.005989011465919053,
|
| 167 |
+
"grad_norm": 0.3599106967449188,
|
| 168 |
+
"learning_rate": 0.00011948051948051949,
|
| 169 |
+
"loss": 0.8063,
|
| 170 |
+
"step": 230
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.006249403268785099,
|
| 174 |
+
"grad_norm": 0.17053447663784027,
|
| 175 |
+
"learning_rate": 0.00012467532467532467,
|
| 176 |
+
"loss": 0.7751,
|
| 177 |
+
"step": 240
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.006509795071651145,
|
| 181 |
+
"grad_norm": 0.17303769290447235,
|
| 182 |
+
"learning_rate": 0.00012987012987012987,
|
| 183 |
+
"loss": 0.7883,
|
| 184 |
+
"step": 250
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.0067701868745171905,
|
| 188 |
+
"grad_norm": 0.1815861016511917,
|
| 189 |
+
"learning_rate": 0.00013506493506493507,
|
| 190 |
+
"loss": 0.788,
|
| 191 |
+
"step": 260
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.007030578677383236,
|
| 195 |
+
"grad_norm": 0.24125365912914276,
|
| 196 |
+
"learning_rate": 0.00014025974025974028,
|
| 197 |
+
"loss": 0.8018,
|
| 198 |
+
"step": 270
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.007290970480249282,
|
| 202 |
+
"grad_norm": 0.19443446397781372,
|
| 203 |
+
"learning_rate": 0.00014545454545454546,
|
| 204 |
+
"loss": 0.7908,
|
| 205 |
+
"step": 280
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.007551362283115328,
|
| 209 |
+
"grad_norm": 0.17829768359661102,
|
| 210 |
+
"learning_rate": 0.00015064935064935066,
|
| 211 |
+
"loss": 0.8033,
|
| 212 |
+
"step": 290
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.007811754085981374,
|
| 216 |
+
"grad_norm": 0.19535653293132782,
|
| 217 |
+
"learning_rate": 0.00015584415584415587,
|
| 218 |
+
"loss": 0.7997,
|
| 219 |
+
"step": 300
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.008072145888847419,
|
| 223 |
+
"grad_norm": 0.19930541515350342,
|
| 224 |
+
"learning_rate": 0.00016103896103896104,
|
| 225 |
+
"loss": 0.7945,
|
| 226 |
+
"step": 310
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.008332537691713465,
|
| 230 |
+
"grad_norm": 0.2156297266483307,
|
| 231 |
+
"learning_rate": 0.00016623376623376625,
|
| 232 |
+
"loss": 0.8018,
|
| 233 |
+
"step": 320
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.00859292949457951,
|
| 237 |
+
"grad_norm": 0.1924206018447876,
|
| 238 |
+
"learning_rate": 0.00017142857142857143,
|
| 239 |
+
"loss": 0.7746,
|
| 240 |
+
"step": 330
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.008853321297445557,
|
| 244 |
+
"grad_norm": 0.2294880747795105,
|
| 245 |
+
"learning_rate": 0.00017662337662337663,
|
| 246 |
+
"loss": 0.8152,
|
| 247 |
+
"step": 340
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.009113713100311602,
|
| 251 |
+
"grad_norm": 0.16817067563533783,
|
| 252 |
+
"learning_rate": 0.00018181818181818183,
|
| 253 |
+
"loss": 0.7972,
|
| 254 |
+
"step": 350
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.009374104903177648,
|
| 258 |
+
"grad_norm": 0.18544812500476837,
|
| 259 |
+
"learning_rate": 0.000187012987012987,
|
| 260 |
+
"loss": 0.7801,
|
| 261 |
+
"step": 360
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.009634496706043693,
|
| 265 |
+
"grad_norm": 0.19597066938877106,
|
| 266 |
+
"learning_rate": 0.00019220779220779222,
|
| 267 |
+
"loss": 0.7706,
|
| 268 |
+
"step": 370
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 0.00989488850890974,
|
| 272 |
+
"grad_norm": 0.40291881561279297,
|
| 273 |
+
"learning_rate": 0.00019740259740259742,
|
| 274 |
+
"loss": 0.7911,
|
| 275 |
+
"step": 380
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.010155280311775785,
|
| 279 |
+
"grad_norm": 0.23841074109077454,
|
| 280 |
+
"learning_rate": 0.00019999996515752773,
|
| 281 |
+
"loss": 0.7861,
|
| 282 |
+
"step": 390
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.010415672114641832,
|
| 286 |
+
"grad_norm": 0.1675388514995575,
|
| 287 |
+
"learning_rate": 0.00019999968641789507,
|
| 288 |
+
"loss": 0.788,
|
| 289 |
+
"step": 400
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.010676063917507876,
|
| 293 |
+
"grad_norm": 1.8860758543014526,
|
| 294 |
+
"learning_rate": 0.0001999991289394067,
|
| 295 |
+
"loss": 0.7632,
|
| 296 |
+
"step": 410
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.010936455720373923,
|
| 300 |
+
"grad_norm": 0.17022117972373962,
|
| 301 |
+
"learning_rate": 0.00019999829272361654,
|
| 302 |
+
"loss": 0.784,
|
| 303 |
+
"step": 420
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.011196847523239968,
|
| 307 |
+
"grad_norm": 0.21460269391536713,
|
| 308 |
+
"learning_rate": 0.00019999717777285545,
|
| 309 |
+
"loss": 0.761,
|
| 310 |
+
"step": 430
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 0.011457239326106015,
|
| 314 |
+
"grad_norm": 0.19413785636425018,
|
| 315 |
+
"learning_rate": 0.00019999578409023126,
|
| 316 |
+
"loss": 0.7772,
|
| 317 |
+
"step": 440
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.01171763112897206,
|
| 321 |
+
"grad_norm": 0.20223405957221985,
|
| 322 |
+
"learning_rate": 0.00019999411167962868,
|
| 323 |
+
"loss": 0.7811,
|
| 324 |
+
"step": 450
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.011978022931838106,
|
| 328 |
+
"grad_norm": 0.15166303515434265,
|
| 329 |
+
"learning_rate": 0.00019999216054570942,
|
| 330 |
+
"loss": 0.7709,
|
| 331 |
+
"step": 460
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.012238414734704151,
|
| 335 |
+
"grad_norm": 0.16307081282138824,
|
| 336 |
+
"learning_rate": 0.00019998993069391205,
|
| 337 |
+
"loss": 0.7811,
|
| 338 |
+
"step": 470
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.012498806537570198,
|
| 342 |
+
"grad_norm": 0.15996049344539642,
|
| 343 |
+
"learning_rate": 0.00019998742213045206,
|
| 344 |
+
"loss": 0.7599,
|
| 345 |
+
"step": 480
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.012759198340436243,
|
| 349 |
+
"grad_norm": 0.17560279369354248,
|
| 350 |
+
"learning_rate": 0.00019998463486232179,
|
| 351 |
+
"loss": 0.7572,
|
| 352 |
+
"step": 490
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 0.01301959014330229,
|
| 356 |
+
"grad_norm": 0.17571642994880676,
|
| 357 |
+
"learning_rate": 0.0001999815688972905,
|
| 358 |
+
"loss": 0.7643,
|
| 359 |
+
"step": 500
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 0.013279981946168334,
|
| 363 |
+
"grad_norm": 0.17719799280166626,
|
| 364 |
+
"learning_rate": 0.00019997822424390422,
|
| 365 |
+
"loss": 0.7923,
|
| 366 |
+
"step": 510
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 0.013540373749034381,
|
| 370 |
+
"grad_norm": 0.19846616685390472,
|
| 371 |
+
"learning_rate": 0.00019997460091148586,
|
| 372 |
+
"loss": 0.7674,
|
| 373 |
+
"step": 520
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 0.013800765551900426,
|
| 377 |
+
"grad_norm": 0.2715558111667633,
|
| 378 |
+
"learning_rate": 0.00019997069891013503,
|
| 379 |
+
"loss": 0.7421,
|
| 380 |
+
"step": 530
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 0.014061157354766473,
|
| 384 |
+
"grad_norm": 0.1725197583436966,
|
| 385 |
+
"learning_rate": 0.00019996651825072826,
|
| 386 |
+
"loss": 0.7663,
|
| 387 |
+
"step": 540
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.014321549157632518,
|
| 391 |
+
"grad_norm": 0.15060502290725708,
|
| 392 |
+
"learning_rate": 0.00019996205894491856,
|
| 393 |
+
"loss": 0.7794,
|
| 394 |
+
"step": 550
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 0.014581940960498564,
|
| 398 |
+
"grad_norm": 0.16645808517932892,
|
| 399 |
+
"learning_rate": 0.00019995732100513592,
|
| 400 |
+
"loss": 0.752,
|
| 401 |
+
"step": 560
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 0.014842332763364609,
|
| 405 |
+
"grad_norm": 0.1736789345741272,
|
| 406 |
+
"learning_rate": 0.00019995230444458682,
|
| 407 |
+
"loss": 0.7788,
|
| 408 |
+
"step": 570
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 0.015102724566230656,
|
| 412 |
+
"grad_norm": 0.15416319668293,
|
| 413 |
+
"learning_rate": 0.0001999470092772544,
|
| 414 |
+
"loss": 0.7656,
|
| 415 |
+
"step": 580
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 0.0153631163690967,
|
| 419 |
+
"grad_norm": 0.16610187292099,
|
| 420 |
+
"learning_rate": 0.00019994143551789839,
|
| 421 |
+
"loss": 0.7676,
|
| 422 |
+
"step": 590
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 0.015623508171962747,
|
| 426 |
+
"grad_norm": 0.15843011438846588,
|
| 427 |
+
"learning_rate": 0.00019993558318205507,
|
| 428 |
+
"loss": 0.7746,
|
| 429 |
+
"step": 600
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.015883899974828794,
|
| 433 |
+
"grad_norm": 0.26837801933288574,
|
| 434 |
+
"learning_rate": 0.00019992945228603724,
|
| 435 |
+
"loss": 0.7617,
|
| 436 |
+
"step": 610
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 0.016144291777694837,
|
| 440 |
+
"grad_norm": 0.15099173784255981,
|
| 441 |
+
"learning_rate": 0.0001999230428469341,
|
| 442 |
+
"loss": 0.7601,
|
| 443 |
+
"step": 620
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 0.016404683580560884,
|
| 447 |
+
"grad_norm": 0.15511856973171234,
|
| 448 |
+
"learning_rate": 0.00019991635488261138,
|
| 449 |
+
"loss": 0.7647,
|
| 450 |
+
"step": 630
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 0.01666507538342693,
|
| 454 |
+
"grad_norm": 0.14919579029083252,
|
| 455 |
+
"learning_rate": 0.00019990938841171104,
|
| 456 |
+
"loss": 0.7692,
|
| 457 |
+
"step": 640
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 0.016925467186292977,
|
| 461 |
+
"grad_norm": 0.15838642418384552,
|
| 462 |
+
"learning_rate": 0.0001999021434536514,
|
| 463 |
+
"loss": 0.7763,
|
| 464 |
+
"step": 650
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 0.01718585898915902,
|
| 468 |
+
"grad_norm": 0.15956635773181915,
|
| 469 |
+
"learning_rate": 0.00019989462002862704,
|
| 470 |
+
"loss": 0.7598,
|
| 471 |
+
"step": 660
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.017446250792025067,
|
| 475 |
+
"grad_norm": 0.1499069333076477,
|
| 476 |
+
"learning_rate": 0.0001998868181576088,
|
| 477 |
+
"loss": 0.7626,
|
| 478 |
+
"step": 670
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 0.017706642594891114,
|
| 482 |
+
"grad_norm": 0.2170073390007019,
|
| 483 |
+
"learning_rate": 0.00019987873786234348,
|
| 484 |
+
"loss": 0.7569,
|
| 485 |
+
"step": 680
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 0.01796703439775716,
|
| 489 |
+
"grad_norm": 0.17841948568820953,
|
| 490 |
+
"learning_rate": 0.00019987037916535417,
|
| 491 |
+
"loss": 0.7494,
|
| 492 |
+
"step": 690
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 0.018227426200623204,
|
| 496 |
+
"grad_norm": 0.2066909372806549,
|
| 497 |
+
"learning_rate": 0.0001998617420899398,
|
| 498 |
+
"loss": 0.7609,
|
| 499 |
+
"step": 700
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 0.01848781800348925,
|
| 503 |
+
"grad_norm": 0.17015361785888672,
|
| 504 |
+
"learning_rate": 0.0001998528266601754,
|
| 505 |
+
"loss": 0.7761,
|
| 506 |
+
"step": 710
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 0.018748209806355297,
|
| 510 |
+
"grad_norm": 0.22166290879249573,
|
| 511 |
+
"learning_rate": 0.0001998436329009118,
|
| 512 |
+
"loss": 0.7573,
|
| 513 |
+
"step": 720
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.01900860160922134,
|
| 517 |
+
"grad_norm": 0.15084640681743622,
|
| 518 |
+
"learning_rate": 0.00019983416083777563,
|
| 519 |
+
"loss": 0.7775,
|
| 520 |
+
"step": 730
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 0.019268993412087387,
|
| 524 |
+
"grad_norm": 0.17800921201705933,
|
| 525 |
+
"learning_rate": 0.0001998244104971693,
|
| 526 |
+
"loss": 0.7359,
|
| 527 |
+
"step": 740
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 0.019529385214953433,
|
| 531 |
+
"grad_norm": 0.17354707419872284,
|
| 532 |
+
"learning_rate": 0.0001998143819062709,
|
| 533 |
+
"loss": 0.7415,
|
| 534 |
+
"step": 750
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 0.01978977701781948,
|
| 538 |
+
"grad_norm": 0.16408118605613708,
|
| 539 |
+
"learning_rate": 0.00019980407509303413,
|
| 540 |
+
"loss": 0.7708,
|
| 541 |
+
"step": 760
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 0.020050168820685523,
|
| 545 |
+
"grad_norm": 0.16820089519023895,
|
| 546 |
+
"learning_rate": 0.00019979349008618808,
|
| 547 |
+
"loss": 0.791,
|
| 548 |
+
"step": 770
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 0.02031056062355157,
|
| 552 |
+
"grad_norm": 0.15958388149738312,
|
| 553 |
+
"learning_rate": 0.00019978262691523743,
|
| 554 |
+
"loss": 0.7412,
|
| 555 |
+
"step": 780
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 0.020570952426417616,
|
| 559 |
+
"grad_norm": 0.1646542251110077,
|
| 560 |
+
"learning_rate": 0.00019977148561046217,
|
| 561 |
+
"loss": 0.7529,
|
| 562 |
+
"step": 790
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 0.020831344229283663,
|
| 566 |
+
"grad_norm": 0.17032025754451752,
|
| 567 |
+
"learning_rate": 0.0001997600662029175,
|
| 568 |
+
"loss": 0.7656,
|
| 569 |
+
"step": 800
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 0.021091736032149706,
|
| 573 |
+
"grad_norm": 0.17189227044582367,
|
| 574 |
+
"learning_rate": 0.00019974836872443388,
|
| 575 |
+
"loss": 0.7433,
|
| 576 |
+
"step": 810
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 0.021352127835015753,
|
| 580 |
+
"grad_norm": 0.16334249079227448,
|
| 581 |
+
"learning_rate": 0.0001997363932076168,
|
| 582 |
+
"loss": 0.7703,
|
| 583 |
+
"step": 820
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 0.0216125196378818,
|
| 587 |
+
"grad_norm": 0.1676424890756607,
|
| 588 |
+
"learning_rate": 0.00019972413968584682,
|
| 589 |
+
"loss": 0.7603,
|
| 590 |
+
"step": 830
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 0.021872911440747846,
|
| 594 |
+
"grad_norm": 0.16826209425926208,
|
| 595 |
+
"learning_rate": 0.0001997116081932793,
|
| 596 |
+
"loss": 0.7569,
|
| 597 |
+
"step": 840
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 0.02213330324361389,
|
| 601 |
+
"grad_norm": 0.1876436173915863,
|
| 602 |
+
"learning_rate": 0.0001996987987648446,
|
| 603 |
+
"loss": 0.7553,
|
| 604 |
+
"step": 850
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 0.022393695046479936,
|
| 608 |
+
"grad_norm": 0.17252250015735626,
|
| 609 |
+
"learning_rate": 0.0001996857114362476,
|
| 610 |
+
"loss": 0.7644,
|
| 611 |
+
"step": 860
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 0.022654086849345983,
|
| 615 |
+
"grad_norm": 0.1632252335548401,
|
| 616 |
+
"learning_rate": 0.00019967234624396793,
|
| 617 |
+
"loss": 0.7568,
|
| 618 |
+
"step": 870
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 0.02291447865221203,
|
| 622 |
+
"grad_norm": 0.1818259060382843,
|
| 623 |
+
"learning_rate": 0.00019965870322525965,
|
| 624 |
+
"loss": 0.7672,
|
| 625 |
+
"step": 880
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 0.023174870455078073,
|
| 629 |
+
"grad_norm": 0.15418195724487305,
|
| 630 |
+
"learning_rate": 0.0001996447824181513,
|
| 631 |
+
"loss": 0.7642,
|
| 632 |
+
"step": 890
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 0.02343526225794412,
|
| 636 |
+
"grad_norm": 0.17383505403995514,
|
| 637 |
+
"learning_rate": 0.0001996305838614457,
|
| 638 |
+
"loss": 0.7607,
|
| 639 |
+
"step": 900
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 0.023695654060810166,
|
| 643 |
+
"grad_norm": 0.17794272303581238,
|
| 644 |
+
"learning_rate": 0.00019961610759471984,
|
| 645 |
+
"loss": 0.7588,
|
| 646 |
+
"step": 910
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 0.023956045863676213,
|
| 650 |
+
"grad_norm": 0.1909121572971344,
|
| 651 |
+
"learning_rate": 0.00019960135365832486,
|
| 652 |
+
"loss": 0.7438,
|
| 653 |
+
"step": 920
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 0.024216437666542256,
|
| 657 |
+
"grad_norm": 0.17758873105049133,
|
| 658 |
+
"learning_rate": 0.00019958632209338587,
|
| 659 |
+
"loss": 0.7323,
|
| 660 |
+
"step": 930
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 0.024476829469408302,
|
| 664 |
+
"grad_norm": 0.15553662180900574,
|
| 665 |
+
"learning_rate": 0.00019957101294180174,
|
| 666 |
+
"loss": 0.7508,
|
| 667 |
+
"step": 940
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 0.02473722127227435,
|
| 671 |
+
"grad_norm": 0.15310749411582947,
|
| 672 |
+
"learning_rate": 0.00019955542624624522,
|
| 673 |
+
"loss": 0.7563,
|
| 674 |
+
"step": 950
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 0.024997613075140396,
|
| 678 |
+
"grad_norm": 0.1628728210926056,
|
| 679 |
+
"learning_rate": 0.00019953956205016256,
|
| 680 |
+
"loss": 0.7524,
|
| 681 |
+
"step": 960
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 0.02525800487800644,
|
| 685 |
+
"grad_norm": 0.16211454570293427,
|
| 686 |
+
"learning_rate": 0.00019952342039777362,
|
| 687 |
+
"loss": 0.7564,
|
| 688 |
+
"step": 970
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 0.025518396680872486,
|
| 692 |
+
"grad_norm": 0.15663012862205505,
|
| 693 |
+
"learning_rate": 0.00019950700133407163,
|
| 694 |
+
"loss": 0.7395,
|
| 695 |
+
"step": 980
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 0.025778788483738532,
|
| 699 |
+
"grad_norm": 0.1684863567352295,
|
| 700 |
+
"learning_rate": 0.00019949030490482296,
|
| 701 |
+
"loss": 0.753,
|
| 702 |
+
"step": 990
|
| 703 |
+
},
|
| 704 |
+
{
|
| 705 |
+
"epoch": 0.02603918028660458,
|
| 706 |
+
"grad_norm": 0.1561436653137207,
|
| 707 |
+
"learning_rate": 0.0001994733311565673,
|
| 708 |
+
"loss": 0.7409,
|
| 709 |
+
"step": 1000
|
| 710 |
+
},
|
| 711 |
+
{
|
| 712 |
+
"epoch": 0.026299572089470622,
|
| 713 |
+
"grad_norm": 0.1781485229730606,
|
| 714 |
+
"learning_rate": 0.0001994560801366171,
|
| 715 |
+
"loss": 0.762,
|
| 716 |
+
"step": 1010
|
| 717 |
+
},
|
| 718 |
+
{
|
| 719 |
+
"epoch": 0.02655996389233667,
|
| 720 |
+
"grad_norm": 0.15422071516513824,
|
| 721 |
+
"learning_rate": 0.00019943855189305792,
|
| 722 |
+
"loss": 0.7291,
|
| 723 |
+
"step": 1020
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 0.026820355695202715,
|
| 727 |
+
"grad_norm": 0.17980527877807617,
|
| 728 |
+
"learning_rate": 0.00019942074647474786,
|
| 729 |
+
"loss": 0.7732,
|
| 730 |
+
"step": 1030
|
| 731 |
+
},
|
| 732 |
+
{
|
| 733 |
+
"epoch": 0.027080747498068762,
|
| 734 |
+
"grad_norm": 0.15810626745224,
|
| 735 |
+
"learning_rate": 0.00019940266393131775,
|
| 736 |
+
"loss": 0.7764,
|
| 737 |
+
"step": 1040
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 0.027341139300934805,
|
| 741 |
+
"grad_norm": 0.16385480761528015,
|
| 742 |
+
"learning_rate": 0.00019938430431317081,
|
| 743 |
+
"loss": 0.7404,
|
| 744 |
+
"step": 1050
|
| 745 |
+
},
|
| 746 |
+
{
|
| 747 |
+
"epoch": 0.027601531103800852,
|
| 748 |
+
"grad_norm": 0.15134255588054657,
|
| 749 |
+
"learning_rate": 0.00019936566767148257,
|
| 750 |
+
"loss": 0.7506,
|
| 751 |
+
"step": 1060
|
| 752 |
+
},
|
| 753 |
+
{
|
| 754 |
+
"epoch": 0.0278619229066669,
|
| 755 |
+
"grad_norm": 0.1592187136411667,
|
| 756 |
+
"learning_rate": 0.00019934675405820077,
|
| 757 |
+
"loss": 0.73,
|
| 758 |
+
"step": 1070
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 0.028122314709532945,
|
| 762 |
+
"grad_norm": 0.16852422058582306,
|
| 763 |
+
"learning_rate": 0.00019932756352604515,
|
| 764 |
+
"loss": 0.7443,
|
| 765 |
+
"step": 1080
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 0.02838270651239899,
|
| 769 |
+
"grad_norm": 0.15741507709026337,
|
| 770 |
+
"learning_rate": 0.00019930809612850735,
|
| 771 |
+
"loss": 0.7377,
|
| 772 |
+
"step": 1090
|
| 773 |
+
},
|
| 774 |
+
{
|
| 775 |
+
"epoch": 0.028643098315265035,
|
| 776 |
+
"grad_norm": 0.22424879670143127,
|
| 777 |
+
"learning_rate": 0.00019928835191985076,
|
| 778 |
+
"loss": 0.7544,
|
| 779 |
+
"step": 1100
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 0.028903490118131082,
|
| 783 |
+
"grad_norm": 0.2047310769557953,
|
| 784 |
+
"learning_rate": 0.0001992683309551103,
|
| 785 |
+
"loss": 0.7441,
|
| 786 |
+
"step": 1110
|
| 787 |
+
},
|
| 788 |
+
{
|
| 789 |
+
"epoch": 0.02916388192099713,
|
| 790 |
+
"grad_norm": 0.16392463445663452,
|
| 791 |
+
"learning_rate": 0.00019924803329009243,
|
| 792 |
+
"loss": 0.7606,
|
| 793 |
+
"step": 1120
|
| 794 |
+
},
|
| 795 |
+
{
|
| 796 |
+
"epoch": 0.02942427372386317,
|
| 797 |
+
"grad_norm": 0.16227149963378906,
|
| 798 |
+
"learning_rate": 0.00019922745898137473,
|
| 799 |
+
"loss": 0.736,
|
| 800 |
+
"step": 1130
|
| 801 |
+
},
|
| 802 |
+
{
|
| 803 |
+
"epoch": 0.029684665526729218,
|
| 804 |
+
"grad_norm": 0.15652808547019958,
|
| 805 |
+
"learning_rate": 0.00019920660808630598,
|
| 806 |
+
"loss": 0.7513,
|
| 807 |
+
"step": 1140
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 0.029945057329595265,
|
| 811 |
+
"grad_norm": 0.15162768959999084,
|
| 812 |
+
"learning_rate": 0.00019918548066300592,
|
| 813 |
+
"loss": 0.7303,
|
| 814 |
+
"step": 1150
|
| 815 |
+
},
|
| 816 |
+
{
|
| 817 |
+
"epoch": 0.03020544913246131,
|
| 818 |
+
"grad_norm": 0.17650415003299713,
|
| 819 |
+
"learning_rate": 0.0001991640767703651,
|
| 820 |
+
"loss": 0.7254,
|
| 821 |
+
"step": 1160
|
| 822 |
+
},
|
| 823 |
+
{
|
| 824 |
+
"epoch": 0.030465840935327355,
|
| 825 |
+
"grad_norm": 0.1594468355178833,
|
| 826 |
+
"learning_rate": 0.00019914239646804462,
|
| 827 |
+
"loss": 0.741,
|
| 828 |
+
"step": 1170
|
| 829 |
+
},
|
| 830 |
+
{
|
| 831 |
+
"epoch": 0.0307262327381934,
|
| 832 |
+
"grad_norm": 0.17928367853164673,
|
| 833 |
+
"learning_rate": 0.00019912043981647616,
|
| 834 |
+
"loss": 0.7515,
|
| 835 |
+
"step": 1180
|
| 836 |
+
},
|
| 837 |
+
{
|
| 838 |
+
"epoch": 0.030986624541059448,
|
| 839 |
+
"grad_norm": 0.17009998857975006,
|
| 840 |
+
"learning_rate": 0.00019909820687686157,
|
| 841 |
+
"loss": 0.7539,
|
| 842 |
+
"step": 1190
|
| 843 |
+
},
|
| 844 |
+
{
|
| 845 |
+
"epoch": 0.031247016343925495,
|
| 846 |
+
"grad_norm": 0.16556763648986816,
|
| 847 |
+
"learning_rate": 0.0001990756977111729,
|
| 848 |
+
"loss": 0.7418,
|
| 849 |
+
"step": 1200
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 0.03150740814679154,
|
| 853 |
+
"grad_norm": 0.1561640352010727,
|
| 854 |
+
"learning_rate": 0.0001990529123821522,
|
| 855 |
+
"loss": 0.7465,
|
| 856 |
+
"step": 1210
|
| 857 |
+
},
|
| 858 |
+
{
|
| 859 |
+
"epoch": 0.03176779994965759,
|
| 860 |
+
"grad_norm": 0.15182287991046906,
|
| 861 |
+
"learning_rate": 0.00019902985095331113,
|
| 862 |
+
"loss": 0.7694,
|
| 863 |
+
"step": 1220
|
| 864 |
+
},
|
| 865 |
+
{
|
| 866 |
+
"epoch": 0.03202819175252363,
|
| 867 |
+
"grad_norm": 0.15173685550689697,
|
| 868 |
+
"learning_rate": 0.00019900651348893114,
|
| 869 |
+
"loss": 0.7519,
|
| 870 |
+
"step": 1230
|
| 871 |
+
},
|
| 872 |
+
{
|
| 873 |
+
"epoch": 0.032288583555389674,
|
| 874 |
+
"grad_norm": 0.16535787284374237,
|
| 875 |
+
"learning_rate": 0.00019898290005406296,
|
| 876 |
+
"loss": 0.7646,
|
| 877 |
+
"step": 1240
|
| 878 |
+
},
|
| 879 |
+
{
|
| 880 |
+
"epoch": 0.032548975358255725,
|
| 881 |
+
"grad_norm": 0.19272534549236298,
|
| 882 |
+
"learning_rate": 0.00019895901071452667,
|
| 883 |
+
"loss": 0.7655,
|
| 884 |
+
"step": 1250
|
| 885 |
+
},
|
| 886 |
+
{
|
| 887 |
+
"epoch": 0.03280936716112177,
|
| 888 |
+
"grad_norm": 0.1672705113887787,
|
| 889 |
+
"learning_rate": 0.0001989348455369113,
|
| 890 |
+
"loss": 0.7486,
|
| 891 |
+
"step": 1260
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 0.03306975896398781,
|
| 895 |
+
"grad_norm": 0.1525493860244751,
|
| 896 |
+
"learning_rate": 0.0001989104045885748,
|
| 897 |
+
"loss": 0.7546,
|
| 898 |
+
"step": 1270
|
| 899 |
+
},
|
| 900 |
+
{
|
| 901 |
+
"epoch": 0.03333015076685386,
|
| 902 |
+
"grad_norm": 0.16333037614822388,
|
| 903 |
+
"learning_rate": 0.00019888568793764385,
|
| 904 |
+
"loss": 0.7299,
|
| 905 |
+
"step": 1280
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"epoch": 0.033590542569719904,
|
| 909 |
+
"grad_norm": 0.1590205729007721,
|
| 910 |
+
"learning_rate": 0.00019886069565301355,
|
| 911 |
+
"loss": 0.762,
|
| 912 |
+
"step": 1290
|
| 913 |
+
},
|
| 914 |
+
{
|
| 915 |
+
"epoch": 0.033850934372585954,
|
| 916 |
+
"grad_norm": 0.15006420016288757,
|
| 917 |
+
"learning_rate": 0.00019883542780434733,
|
| 918 |
+
"loss": 0.7531,
|
| 919 |
+
"step": 1300
|
| 920 |
+
},
|
| 921 |
+
{
|
| 922 |
+
"epoch": 0.034111326175452,
|
| 923 |
+
"grad_norm": 0.18390792608261108,
|
| 924 |
+
"learning_rate": 0.0001988098844620767,
|
| 925 |
+
"loss": 0.7621,
|
| 926 |
+
"step": 1310
|
| 927 |
+
},
|
| 928 |
+
{
|
| 929 |
+
"epoch": 0.03437171797831804,
|
| 930 |
+
"grad_norm": 0.17046166956424713,
|
| 931 |
+
"learning_rate": 0.0001987840656974011,
|
| 932 |
+
"loss": 0.7422,
|
| 933 |
+
"step": 1320
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 0.03463210978118409,
|
| 937 |
+
"grad_norm": 0.15121813118457794,
|
| 938 |
+
"learning_rate": 0.00019875797158228775,
|
| 939 |
+
"loss": 0.7555,
|
| 940 |
+
"step": 1330
|
| 941 |
+
},
|
| 942 |
+
{
|
| 943 |
+
"epoch": 0.034892501584050134,
|
| 944 |
+
"grad_norm": 0.16219307482242584,
|
| 945 |
+
"learning_rate": 0.00019873160218947125,
|
| 946 |
+
"loss": 0.7301,
|
| 947 |
+
"step": 1340
|
| 948 |
+
},
|
| 949 |
+
{
|
| 950 |
+
"epoch": 0.03515289338691618,
|
| 951 |
+
"grad_norm": 0.1779986321926117,
|
| 952 |
+
"learning_rate": 0.00019870495759245362,
|
| 953 |
+
"loss": 0.7356,
|
| 954 |
+
"step": 1350
|
| 955 |
+
},
|
| 956 |
+
{
|
| 957 |
+
"epoch": 0.03541328518978223,
|
| 958 |
+
"grad_norm": 0.16951359808444977,
|
| 959 |
+
"learning_rate": 0.0001986780378655039,
|
| 960 |
+
"loss": 0.7645,
|
| 961 |
+
"step": 1360
|
| 962 |
+
},
|
| 963 |
+
{
|
| 964 |
+
"epoch": 0.03567367699264827,
|
| 965 |
+
"grad_norm": 0.16620802879333496,
|
| 966 |
+
"learning_rate": 0.0001986508430836581,
|
| 967 |
+
"loss": 0.7331,
|
| 968 |
+
"step": 1370
|
| 969 |
+
},
|
| 970 |
+
{
|
| 971 |
+
"epoch": 0.03593406879551432,
|
| 972 |
+
"grad_norm": 0.1577858328819275,
|
| 973 |
+
"learning_rate": 0.0001986233733227188,
|
| 974 |
+
"loss": 0.7667,
|
| 975 |
+
"step": 1380
|
| 976 |
+
},
|
| 977 |
+
{
|
| 978 |
+
"epoch": 0.036194460598380364,
|
| 979 |
+
"grad_norm": 0.1637091338634491,
|
| 980 |
+
"learning_rate": 0.00019859562865925525,
|
| 981 |
+
"loss": 0.7521,
|
| 982 |
+
"step": 1390
|
| 983 |
+
},
|
| 984 |
+
{
|
| 985 |
+
"epoch": 0.03645485240124641,
|
| 986 |
+
"grad_norm": 0.15061691403388977,
|
| 987 |
+
"learning_rate": 0.00019856760917060277,
|
| 988 |
+
"loss": 0.744,
|
| 989 |
+
"step": 1400
|
| 990 |
+
},
|
| 991 |
+
{
|
| 992 |
+
"epoch": 0.03671524420411246,
|
| 993 |
+
"grad_norm": 0.15373477339744568,
|
| 994 |
+
"learning_rate": 0.00019853931493486287,
|
| 995 |
+
"loss": 0.7677,
|
| 996 |
+
"step": 1410
|
| 997 |
+
},
|
| 998 |
+
{
|
| 999 |
+
"epoch": 0.0369756360069785,
|
| 1000 |
+
"grad_norm": 0.16468606889247894,
|
| 1001 |
+
"learning_rate": 0.00019851074603090277,
|
| 1002 |
+
"loss": 0.7179,
|
| 1003 |
+
"step": 1420
|
| 1004 |
+
},
|
| 1005 |
+
{
|
| 1006 |
+
"epoch": 0.037236027809844544,
|
| 1007 |
+
"grad_norm": 0.16084876656532288,
|
| 1008 |
+
"learning_rate": 0.00019848190253835536,
|
| 1009 |
+
"loss": 0.749,
|
| 1010 |
+
"step": 1430
|
| 1011 |
+
},
|
| 1012 |
+
{
|
| 1013 |
+
"epoch": 0.037496419612710594,
|
| 1014 |
+
"grad_norm": 0.16743004322052002,
|
| 1015 |
+
"learning_rate": 0.00019845278453761896,
|
| 1016 |
+
"loss": 0.7483,
|
| 1017 |
+
"step": 1440
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 0.03775681141557664,
|
| 1021 |
+
"grad_norm": 0.17335088551044464,
|
| 1022 |
+
"learning_rate": 0.00019842339210985696,
|
| 1023 |
+
"loss": 0.735,
|
| 1024 |
+
"step": 1450
|
| 1025 |
+
},
|
| 1026 |
+
{
|
| 1027 |
+
"epoch": 0.03801720321844268,
|
| 1028 |
+
"grad_norm": 0.1546197235584259,
|
| 1029 |
+
"learning_rate": 0.00019839372533699774,
|
| 1030 |
+
"loss": 0.7549,
|
| 1031 |
+
"step": 1460
|
| 1032 |
+
},
|
| 1033 |
+
{
|
| 1034 |
+
"epoch": 0.03827759502130873,
|
| 1035 |
+
"grad_norm": 0.16218656301498413,
|
| 1036 |
+
"learning_rate": 0.00019836378430173438,
|
| 1037 |
+
"loss": 0.7425,
|
| 1038 |
+
"step": 1470
|
| 1039 |
+
},
|
| 1040 |
+
{
|
| 1041 |
+
"epoch": 0.03853798682417477,
|
| 1042 |
+
"grad_norm": 0.1712743639945984,
|
| 1043 |
+
"learning_rate": 0.0001983335690875245,
|
| 1044 |
+
"loss": 0.733,
|
| 1045 |
+
"step": 1480
|
| 1046 |
+
},
|
| 1047 |
+
{
|
| 1048 |
+
"epoch": 0.03879837862704082,
|
| 1049 |
+
"grad_norm": 0.15490613877773285,
|
| 1050 |
+
"learning_rate": 0.00019830307977858984,
|
| 1051 |
+
"loss": 0.7265,
|
| 1052 |
+
"step": 1490
|
| 1053 |
+
},
|
| 1054 |
+
{
|
| 1055 |
+
"epoch": 0.03905877042990687,
|
| 1056 |
+
"grad_norm": 0.1646670252084732,
|
| 1057 |
+
"learning_rate": 0.00019827231645991623,
|
| 1058 |
+
"loss": 0.7315,
|
| 1059 |
+
"step": 1500
|
| 1060 |
+
},
|
| 1061 |
+
{
|
| 1062 |
+
"epoch": 0.03931916223277291,
|
| 1063 |
+
"grad_norm": 0.1599082201719284,
|
| 1064 |
+
"learning_rate": 0.00019824127921725326,
|
| 1065 |
+
"loss": 0.7293,
|
| 1066 |
+
"step": 1510
|
| 1067 |
+
},
|
| 1068 |
+
{
|
| 1069 |
+
"epoch": 0.03957955403563896,
|
| 1070 |
+
"grad_norm": 0.1565747708082199,
|
| 1071 |
+
"learning_rate": 0.00019820996813711407,
|
| 1072 |
+
"loss": 0.7396,
|
| 1073 |
+
"step": 1520
|
| 1074 |
+
},
|
| 1075 |
+
{
|
| 1076 |
+
"epoch": 0.039839945838505,
|
| 1077 |
+
"grad_norm": 0.154826357960701,
|
| 1078 |
+
"learning_rate": 0.0001981783833067751,
|
| 1079 |
+
"loss": 0.7217,
|
| 1080 |
+
"step": 1530
|
| 1081 |
+
},
|
| 1082 |
+
{
|
| 1083 |
+
"epoch": 0.040100337641371046,
|
| 1084 |
+
"grad_norm": 0.16705222427845,
|
| 1085 |
+
"learning_rate": 0.0001981465248142758,
|
| 1086 |
+
"loss": 0.761,
|
| 1087 |
+
"step": 1540
|
| 1088 |
+
},
|
| 1089 |
+
{
|
| 1090 |
+
"epoch": 0.040360729444237096,
|
| 1091 |
+
"grad_norm": 0.15651623904705048,
|
| 1092 |
+
"learning_rate": 0.00019811439274841842,
|
| 1093 |
+
"loss": 0.7565,
|
| 1094 |
+
"step": 1550
|
| 1095 |
+
},
|
| 1096 |
+
{
|
| 1097 |
+
"epoch": 0.04062112124710314,
|
| 1098 |
+
"grad_norm": 0.16211090981960297,
|
| 1099 |
+
"learning_rate": 0.00019808198719876782,
|
| 1100 |
+
"loss": 0.7555,
|
| 1101 |
+
"step": 1560
|
| 1102 |
+
},
|
| 1103 |
+
{
|
| 1104 |
+
"epoch": 0.04088151304996919,
|
| 1105 |
+
"grad_norm": 0.16856881976127625,
|
| 1106 |
+
"learning_rate": 0.00019804930825565112,
|
| 1107 |
+
"loss": 0.7567,
|
| 1108 |
+
"step": 1570
|
| 1109 |
+
},
|
| 1110 |
+
{
|
| 1111 |
+
"epoch": 0.04114190485283523,
|
| 1112 |
+
"grad_norm": 0.1588718593120575,
|
| 1113 |
+
"learning_rate": 0.00019801635601015752,
|
| 1114 |
+
"loss": 0.729,
|
| 1115 |
+
"step": 1580
|
| 1116 |
+
},
|
| 1117 |
+
{
|
| 1118 |
+
"epoch": 0.041402296655701276,
|
| 1119 |
+
"grad_norm": 0.17078711092472076,
|
| 1120 |
+
"learning_rate": 0.00019798313055413808,
|
| 1121 |
+
"loss": 0.7418,
|
| 1122 |
+
"step": 1590
|
| 1123 |
+
},
|
| 1124 |
+
{
|
| 1125 |
+
"epoch": 0.041662688458567326,
|
| 1126 |
+
"grad_norm": 0.16652734577655792,
|
| 1127 |
+
"learning_rate": 0.00019794963198020525,
|
| 1128 |
+
"loss": 0.7341,
|
| 1129 |
+
"step": 1600
|
| 1130 |
+
},
|
| 1131 |
+
{
|
| 1132 |
+
"epoch": 0.04192308026143337,
|
| 1133 |
+
"grad_norm": 0.15535488724708557,
|
| 1134 |
+
"learning_rate": 0.00019791586038173296,
|
| 1135 |
+
"loss": 0.7396,
|
| 1136 |
+
"step": 1610
|
| 1137 |
+
},
|
| 1138 |
+
{
|
| 1139 |
+
"epoch": 0.04218347206429941,
|
| 1140 |
+
"grad_norm": 0.3506317734718323,
|
| 1141 |
+
"learning_rate": 0.00019788181585285602,
|
| 1142 |
+
"loss": 0.7345,
|
| 1143 |
+
"step": 1620
|
| 1144 |
+
},
|
| 1145 |
+
{
|
| 1146 |
+
"epoch": 0.04244386386716546,
|
| 1147 |
+
"grad_norm": 0.16875872015953064,
|
| 1148 |
+
"learning_rate": 0.00019784749848847003,
|
| 1149 |
+
"loss": 0.7214,
|
| 1150 |
+
"step": 1630
|
| 1151 |
+
},
|
| 1152 |
+
{
|
| 1153 |
+
"epoch": 0.042704255670031506,
|
| 1154 |
+
"grad_norm": 0.17675861716270447,
|
| 1155 |
+
"learning_rate": 0.0001978129083842312,
|
| 1156 |
+
"loss": 0.7431,
|
| 1157 |
+
"step": 1640
|
| 1158 |
+
},
|
| 1159 |
+
{
|
| 1160 |
+
"epoch": 0.042964647472897556,
|
| 1161 |
+
"grad_norm": 0.15601837635040283,
|
| 1162 |
+
"learning_rate": 0.00019777804563655583,
|
| 1163 |
+
"loss": 0.7215,
|
| 1164 |
+
"step": 1650
|
| 1165 |
+
},
|
| 1166 |
+
{
|
| 1167 |
+
"epoch": 0.0432250392757636,
|
| 1168 |
+
"grad_norm": 0.1874823123216629,
|
| 1169 |
+
"learning_rate": 0.00019774291034262026,
|
| 1170 |
+
"loss": 0.727,
|
| 1171 |
+
"step": 1660
|
| 1172 |
+
},
|
| 1173 |
+
{
|
| 1174 |
+
"epoch": 0.04348543107862964,
|
| 1175 |
+
"grad_norm": 0.17005637288093567,
|
| 1176 |
+
"learning_rate": 0.00019770750260036054,
|
| 1177 |
+
"loss": 0.7446,
|
| 1178 |
+
"step": 1670
|
| 1179 |
+
},
|
| 1180 |
+
{
|
| 1181 |
+
"epoch": 0.04374582288149569,
|
| 1182 |
+
"grad_norm": 0.17069579660892487,
|
| 1183 |
+
"learning_rate": 0.00019767182250847207,
|
| 1184 |
+
"loss": 0.7266,
|
| 1185 |
+
"step": 1680
|
| 1186 |
+
},
|
| 1187 |
+
{
|
| 1188 |
+
"epoch": 0.044006214684361736,
|
| 1189 |
+
"grad_norm": 0.16133156418800354,
|
| 1190 |
+
"learning_rate": 0.00019763587016640948,
|
| 1191 |
+
"loss": 0.7568,
|
| 1192 |
+
"step": 1690
|
| 1193 |
+
},
|
| 1194 |
+
{
|
| 1195 |
+
"epoch": 0.04426660648722778,
|
| 1196 |
+
"grad_norm": 0.16229428350925446,
|
| 1197 |
+
"learning_rate": 0.00019759964567438623,
|
| 1198 |
+
"loss": 0.7402,
|
| 1199 |
+
"step": 1700
|
| 1200 |
+
},
|
| 1201 |
+
{
|
| 1202 |
+
"epoch": 0.04452699829009383,
|
| 1203 |
+
"grad_norm": 0.1622512936592102,
|
| 1204 |
+
"learning_rate": 0.00019756314913337432,
|
| 1205 |
+
"loss": 0.7536,
|
| 1206 |
+
"step": 1710
|
| 1207 |
+
},
|
| 1208 |
+
{
|
| 1209 |
+
"epoch": 0.04478739009295987,
|
| 1210 |
+
"grad_norm": 0.2161218672990799,
|
| 1211 |
+
"learning_rate": 0.00019752638064510415,
|
| 1212 |
+
"loss": 0.723,
|
| 1213 |
+
"step": 1720
|
| 1214 |
+
},
|
| 1215 |
+
{
|
| 1216 |
+
"epoch": 0.04504778189582592,
|
| 1217 |
+
"grad_norm": 0.154169961810112,
|
| 1218 |
+
"learning_rate": 0.00019748934031206414,
|
| 1219 |
+
"loss": 0.7441,
|
| 1220 |
+
"step": 1730
|
| 1221 |
+
},
|
| 1222 |
+
{
|
| 1223 |
+
"epoch": 0.045308173698691966,
|
| 1224 |
+
"grad_norm": 0.15468057990074158,
|
| 1225 |
+
"learning_rate": 0.00019745202823750034,
|
| 1226 |
+
"loss": 0.7349,
|
| 1227 |
+
"step": 1740
|
| 1228 |
+
},
|
| 1229 |
+
{
|
| 1230 |
+
"epoch": 0.04556856550155801,
|
| 1231 |
+
"grad_norm": 0.2015281468629837,
|
| 1232 |
+
"learning_rate": 0.0001974144445254164,
|
| 1233 |
+
"loss": 0.726,
|
| 1234 |
+
"step": 1750
|
| 1235 |
+
},
|
| 1236 |
+
{
|
| 1237 |
+
"epoch": 0.04582895730442406,
|
| 1238 |
+
"grad_norm": 0.1931644082069397,
|
| 1239 |
+
"learning_rate": 0.00019737658928057302,
|
| 1240 |
+
"loss": 0.7604,
|
| 1241 |
+
"step": 1760
|
| 1242 |
+
},
|
| 1243 |
+
{
|
| 1244 |
+
"epoch": 0.0460893491072901,
|
| 1245 |
+
"grad_norm": 0.1528482288122177,
|
| 1246 |
+
"learning_rate": 0.00019733846260848776,
|
| 1247 |
+
"loss": 0.7408,
|
| 1248 |
+
"step": 1770
|
| 1249 |
+
},
|
| 1250 |
+
{
|
| 1251 |
+
"epoch": 0.046349740910156145,
|
| 1252 |
+
"grad_norm": 0.16370061039924622,
|
| 1253 |
+
"learning_rate": 0.0001973000646154349,
|
| 1254 |
+
"loss": 0.7647,
|
| 1255 |
+
"step": 1780
|
| 1256 |
+
},
|
| 1257 |
+
{
|
| 1258 |
+
"epoch": 0.046610132713022195,
|
| 1259 |
+
"grad_norm": 0.16271348297595978,
|
| 1260 |
+
"learning_rate": 0.00019726139540844484,
|
| 1261 |
+
"loss": 0.7212,
|
| 1262 |
+
"step": 1790
|
| 1263 |
+
},
|
| 1264 |
+
{
|
| 1265 |
+
"epoch": 0.04687052451588824,
|
| 1266 |
+
"grad_norm": 0.16218173503875732,
|
| 1267 |
+
"learning_rate": 0.00019722245509530401,
|
| 1268 |
+
"loss": 0.735,
|
| 1269 |
+
"step": 1800
|
| 1270 |
+
},
|
| 1271 |
+
{
|
| 1272 |
+
"epoch": 0.04713091631875429,
|
| 1273 |
+
"grad_norm": 0.17063820362091064,
|
| 1274 |
+
"learning_rate": 0.00019718324378455458,
|
| 1275 |
+
"loss": 0.7311,
|
| 1276 |
+
"step": 1810
|
| 1277 |
+
},
|
| 1278 |
+
{
|
| 1279 |
+
"epoch": 0.04739130812162033,
|
| 1280 |
+
"grad_norm": 0.1678459346294403,
|
| 1281 |
+
"learning_rate": 0.00019714376158549404,
|
| 1282 |
+
"loss": 0.7486,
|
| 1283 |
+
"step": 1820
|
| 1284 |
+
},
|
| 1285 |
+
{
|
| 1286 |
+
"epoch": 0.047651699924486375,
|
| 1287 |
+
"grad_norm": 0.15926459431648254,
|
| 1288 |
+
"learning_rate": 0.00019710400860817494,
|
| 1289 |
+
"loss": 0.743,
|
| 1290 |
+
"step": 1830
|
| 1291 |
+
},
|
| 1292 |
+
{
|
| 1293 |
+
"epoch": 0.047912091727352425,
|
| 1294 |
+
"grad_norm": 0.1775251179933548,
|
| 1295 |
+
"learning_rate": 0.00019706398496340463,
|
| 1296 |
+
"loss": 0.7512,
|
| 1297 |
+
"step": 1840
|
| 1298 |
+
},
|
| 1299 |
+
{
|
| 1300 |
+
"epoch": 0.04817248353021847,
|
| 1301 |
+
"grad_norm": 0.1572408229112625,
|
| 1302 |
+
"learning_rate": 0.00019702369076274494,
|
| 1303 |
+
"loss": 0.733,
|
| 1304 |
+
"step": 1850
|
| 1305 |
+
},
|
| 1306 |
+
{
|
| 1307 |
+
"epoch": 0.04843287533308451,
|
| 1308 |
+
"grad_norm": 0.29658186435699463,
|
| 1309 |
+
"learning_rate": 0.0001969831261185118,
|
| 1310 |
+
"loss": 0.7297,
|
| 1311 |
+
"step": 1860
|
| 1312 |
+
},
|
| 1313 |
+
{
|
| 1314 |
+
"epoch": 0.04869326713595056,
|
| 1315 |
+
"grad_norm": 0.16520118713378906,
|
| 1316 |
+
"learning_rate": 0.00019694229114377494,
|
| 1317 |
+
"loss": 0.721,
|
| 1318 |
+
"step": 1870
|
| 1319 |
+
},
|
| 1320 |
+
{
|
| 1321 |
+
"epoch": 0.048953658938816605,
|
| 1322 |
+
"grad_norm": 0.17762574553489685,
|
| 1323 |
+
"learning_rate": 0.00019690118595235774,
|
| 1324 |
+
"loss": 0.7304,
|
| 1325 |
+
"step": 1880
|
| 1326 |
+
},
|
| 1327 |
+
{
|
| 1328 |
+
"epoch": 0.049214050741682655,
|
| 1329 |
+
"grad_norm": 0.16636615991592407,
|
| 1330 |
+
"learning_rate": 0.00019685981065883663,
|
| 1331 |
+
"loss": 0.7257,
|
| 1332 |
+
"step": 1890
|
| 1333 |
+
},
|
| 1334 |
+
{
|
| 1335 |
+
"epoch": 0.0494744425445487,
|
| 1336 |
+
"grad_norm": 0.1622323989868164,
|
| 1337 |
+
"learning_rate": 0.00019681816537854102,
|
| 1338 |
+
"loss": 0.7353,
|
| 1339 |
+
"step": 1900
|
| 1340 |
+
},
|
| 1341 |
+
{
|
| 1342 |
+
"epoch": 0.04973483434741474,
|
| 1343 |
+
"grad_norm": 0.17419832944869995,
|
| 1344 |
+
"learning_rate": 0.00019677625022755289,
|
| 1345 |
+
"loss": 0.7452,
|
| 1346 |
+
"step": 1910
|
| 1347 |
+
},
|
| 1348 |
+
{
|
| 1349 |
+
"epoch": 0.04999522615028079,
|
| 1350 |
+
"grad_norm": 0.17460434138774872,
|
| 1351 |
+
"learning_rate": 0.00019673406532270634,
|
| 1352 |
+
"loss": 0.7391,
|
| 1353 |
+
"step": 1920
|
| 1354 |
+
},
|
| 1355 |
+
{
|
| 1356 |
+
"epoch": 0.050255617953146835,
|
| 1357 |
+
"grad_norm": 0.15844550728797913,
|
| 1358 |
+
"learning_rate": 0.00019669161078158753,
|
| 1359 |
+
"loss": 0.7327,
|
| 1360 |
+
"step": 1930
|
| 1361 |
+
},
|
| 1362 |
+
{
|
| 1363 |
+
"epoch": 0.05051600975601288,
|
| 1364 |
+
"grad_norm": 0.1638839989900589,
|
| 1365 |
+
"learning_rate": 0.0001966488867225341,
|
| 1366 |
+
"loss": 0.745,
|
| 1367 |
+
"step": 1940
|
| 1368 |
+
},
|
| 1369 |
+
{
|
| 1370 |
+
"epoch": 0.05077640155887893,
|
| 1371 |
+
"grad_norm": 0.1587786227464676,
|
| 1372 |
+
"learning_rate": 0.00019660589326463498,
|
| 1373 |
+
"loss": 0.7476,
|
| 1374 |
+
"step": 1950
|
| 1375 |
+
},
|
| 1376 |
+
{
|
| 1377 |
+
"epoch": 0.05103679336174497,
|
| 1378 |
+
"grad_norm": 0.15708380937576294,
|
| 1379 |
+
"learning_rate": 0.00019656263052773002,
|
| 1380 |
+
"loss": 0.7208,
|
| 1381 |
+
"step": 1960
|
| 1382 |
+
},
|
| 1383 |
+
{
|
| 1384 |
+
"epoch": 0.05129718516461102,
|
| 1385 |
+
"grad_norm": 0.15816234052181244,
|
| 1386 |
+
"learning_rate": 0.00019651909863240965,
|
| 1387 |
+
"loss": 0.7262,
|
| 1388 |
+
"step": 1970
|
| 1389 |
+
},
|
| 1390 |
+
{
|
| 1391 |
+
"epoch": 0.051557576967477065,
|
| 1392 |
+
"grad_norm": 0.16749270260334015,
|
| 1393 |
+
"learning_rate": 0.00019647529770001456,
|
| 1394 |
+
"loss": 0.7284,
|
| 1395 |
+
"step": 1980
|
| 1396 |
+
},
|
| 1397 |
+
{
|
| 1398 |
+
"epoch": 0.05181796877034311,
|
| 1399 |
+
"grad_norm": 0.16943767666816711,
|
| 1400 |
+
"learning_rate": 0.00019643122785263536,
|
| 1401 |
+
"loss": 0.7225,
|
| 1402 |
+
"step": 1990
|
| 1403 |
+
},
|
| 1404 |
+
{
|
| 1405 |
+
"epoch": 0.05207836057320916,
|
| 1406 |
+
"grad_norm": 0.42929205298423767,
|
| 1407 |
+
"learning_rate": 0.00019638688921311224,
|
| 1408 |
+
"loss": 0.7305,
|
| 1409 |
+
"step": 2000
|
| 1410 |
+
},
|
| 1411 |
+
{
|
| 1412 |
+
"epoch": 0.0523387523760752,
|
| 1413 |
+
"grad_norm": 0.15851692855358124,
|
| 1414 |
+
"learning_rate": 0.00019634228190503454,
|
| 1415 |
+
"loss": 0.7344,
|
| 1416 |
+
"step": 2010
|
| 1417 |
+
},
|
| 1418 |
+
{
|
| 1419 |
+
"epoch": 0.052599144178941244,
|
| 1420 |
+
"grad_norm": 0.16053883731365204,
|
| 1421 |
+
"learning_rate": 0.00019629740605274062,
|
| 1422 |
+
"loss": 0.7468,
|
| 1423 |
+
"step": 2020
|
| 1424 |
+
},
|
| 1425 |
+
{
|
| 1426 |
+
"epoch": 0.052859535981807294,
|
| 1427 |
+
"grad_norm": 0.16504009068012238,
|
| 1428 |
+
"learning_rate": 0.00019625226178131728,
|
| 1429 |
+
"loss": 0.7375,
|
| 1430 |
+
"step": 2030
|
| 1431 |
+
},
|
| 1432 |
+
{
|
| 1433 |
+
"epoch": 0.05311992778467334,
|
| 1434 |
+
"grad_norm": 0.1618044674396515,
|
| 1435 |
+
"learning_rate": 0.00019620684921659953,
|
| 1436 |
+
"loss": 0.7201,
|
| 1437 |
+
"step": 2040
|
| 1438 |
+
},
|
| 1439 |
+
{
|
| 1440 |
+
"epoch": 0.05338031958753939,
|
| 1441 |
+
"grad_norm": 0.15512776374816895,
|
| 1442 |
+
"learning_rate": 0.00019616116848517027,
|
| 1443 |
+
"loss": 0.7355,
|
| 1444 |
+
"step": 2050
|
| 1445 |
+
},
|
| 1446 |
+
{
|
| 1447 |
+
"epoch": 0.05364071139040543,
|
| 1448 |
+
"grad_norm": 0.17377036809921265,
|
| 1449 |
+
"learning_rate": 0.00019611521971435979,
|
| 1450 |
+
"loss": 0.7226,
|
| 1451 |
+
"step": 2060
|
| 1452 |
+
},
|
| 1453 |
+
{
|
| 1454 |
+
"epoch": 0.053901103193271474,
|
| 1455 |
+
"grad_norm": 0.1685250997543335,
|
| 1456 |
+
"learning_rate": 0.0001960690030322456,
|
| 1457 |
+
"loss": 0.7483,
|
| 1458 |
+
"step": 2070
|
| 1459 |
+
},
|
| 1460 |
+
{
|
| 1461 |
+
"epoch": 0.054161494996137524,
|
| 1462 |
+
"grad_norm": 0.18394522368907928,
|
| 1463 |
+
"learning_rate": 0.00019602251856765194,
|
| 1464 |
+
"loss": 0.7385,
|
| 1465 |
+
"step": 2080
|
| 1466 |
+
},
|
| 1467 |
+
{
|
| 1468 |
+
"epoch": 0.05442188679900357,
|
| 1469 |
+
"grad_norm": 0.1753673106431961,
|
| 1470 |
+
"learning_rate": 0.0001959757664501495,
|
| 1471 |
+
"loss": 0.7378,
|
| 1472 |
+
"step": 2090
|
| 1473 |
+
},
|
| 1474 |
+
{
|
| 1475 |
+
"epoch": 0.05468227860186961,
|
| 1476 |
+
"grad_norm": 0.1795465052127838,
|
| 1477 |
+
"learning_rate": 0.000195928746810055,
|
| 1478 |
+
"loss": 0.748,
|
| 1479 |
+
"step": 2100
|
| 1480 |
+
},
|
| 1481 |
+
{
|
| 1482 |
+
"epoch": 0.05494267040473566,
|
| 1483 |
+
"grad_norm": 0.16327305138111115,
|
| 1484 |
+
"learning_rate": 0.0001958814597784309,
|
| 1485 |
+
"loss": 0.7306,
|
| 1486 |
+
"step": 2110
|
| 1487 |
+
},
|
| 1488 |
+
{
|
| 1489 |
+
"epoch": 0.055203062207601704,
|
| 1490 |
+
"grad_norm": 0.15880291163921356,
|
| 1491 |
+
"learning_rate": 0.00019583390548708486,
|
| 1492 |
+
"loss": 0.7281,
|
| 1493 |
+
"step": 2120
|
| 1494 |
+
},
|
| 1495 |
+
{
|
| 1496 |
+
"epoch": 0.05546345401046775,
|
| 1497 |
+
"grad_norm": 0.1702323853969574,
|
| 1498 |
+
"learning_rate": 0.0001957860840685696,
|
| 1499 |
+
"loss": 0.7407,
|
| 1500 |
+
"step": 2130
|
| 1501 |
+
},
|
| 1502 |
+
{
|
| 1503 |
+
"epoch": 0.0557238458133338,
|
| 1504 |
+
"grad_norm": 0.16931670904159546,
|
| 1505 |
+
"learning_rate": 0.0001957379956561825,
|
| 1506 |
+
"loss": 0.7272,
|
| 1507 |
+
"step": 2140
|
| 1508 |
+
},
|
| 1509 |
+
{
|
| 1510 |
+
"epoch": 0.05598423761619984,
|
| 1511 |
+
"grad_norm": 0.15455976128578186,
|
| 1512 |
+
"learning_rate": 0.000195689640383965,
|
| 1513 |
+
"loss": 0.7398,
|
| 1514 |
+
"step": 2150
|
| 1515 |
+
},
|
| 1516 |
+
{
|
| 1517 |
+
"epoch": 0.05624462941906589,
|
| 1518 |
+
"grad_norm": 0.16061417758464813,
|
| 1519 |
+
"learning_rate": 0.0001956410183867024,
|
| 1520 |
+
"loss": 0.749,
|
| 1521 |
+
"step": 2160
|
| 1522 |
+
},
|
| 1523 |
+
{
|
| 1524 |
+
"epoch": 0.056505021221931934,
|
| 1525 |
+
"grad_norm": 0.14933143556118011,
|
| 1526 |
+
"learning_rate": 0.00019559212979992365,
|
| 1527 |
+
"loss": 0.7418,
|
| 1528 |
+
"step": 2170
|
| 1529 |
+
},
|
| 1530 |
+
{
|
| 1531 |
+
"epoch": 0.05676541302479798,
|
| 1532 |
+
"grad_norm": 0.1592816412448883,
|
| 1533 |
+
"learning_rate": 0.00019554297475990058,
|
| 1534 |
+
"loss": 0.7423,
|
| 1535 |
+
"step": 2180
|
| 1536 |
+
},
|
| 1537 |
+
{
|
| 1538 |
+
"epoch": 0.05702580482766403,
|
| 1539 |
+
"grad_norm": 0.1677238792181015,
|
| 1540 |
+
"learning_rate": 0.00019549355340364787,
|
| 1541 |
+
"loss": 0.7101,
|
| 1542 |
+
"step": 2190
|
| 1543 |
+
},
|
| 1544 |
+
{
|
| 1545 |
+
"epoch": 0.05728619663053007,
|
| 1546 |
+
"grad_norm": 0.3558599054813385,
|
| 1547 |
+
"learning_rate": 0.00019544386586892238,
|
| 1548 |
+
"loss": 0.725,
|
| 1549 |
+
"step": 2200
|
| 1550 |
+
},
|
| 1551 |
+
{
|
| 1552 |
+
"epoch": 0.05754658843339611,
|
| 1553 |
+
"grad_norm": 0.1746376007795334,
|
| 1554 |
+
"learning_rate": 0.00019539391229422313,
|
| 1555 |
+
"loss": 0.7479,
|
| 1556 |
+
"step": 2210
|
| 1557 |
+
},
|
| 1558 |
+
{
|
| 1559 |
+
"epoch": 0.057806980236262163,
|
| 1560 |
+
"grad_norm": 0.15979182720184326,
|
| 1561 |
+
"learning_rate": 0.00019534369281879049,
|
| 1562 |
+
"loss": 0.7352,
|
| 1563 |
+
"step": 2220
|
| 1564 |
+
},
|
| 1565 |
+
{
|
| 1566 |
+
"epoch": 0.05806737203912821,
|
| 1567 |
+
"grad_norm": 0.16173166036605835,
|
| 1568 |
+
"learning_rate": 0.0001952932075826061,
|
| 1569 |
+
"loss": 0.7364,
|
| 1570 |
+
"step": 2230
|
| 1571 |
+
},
|
| 1572 |
+
{
|
| 1573 |
+
"epoch": 0.05832776384199426,
|
| 1574 |
+
"grad_norm": 0.1514744907617569,
|
| 1575 |
+
"learning_rate": 0.00019524245672639245,
|
| 1576 |
+
"loss": 0.734,
|
| 1577 |
+
"step": 2240
|
| 1578 |
+
},
|
| 1579 |
+
{
|
| 1580 |
+
"epoch": 0.0585881556448603,
|
| 1581 |
+
"grad_norm": 0.16860373318195343,
|
| 1582 |
+
"learning_rate": 0.00019519144039161222,
|
| 1583 |
+
"loss": 0.7098,
|
| 1584 |
+
"step": 2250
|
| 1585 |
+
},
|
| 1586 |
+
{
|
| 1587 |
+
"epoch": 0.05884854744772634,
|
| 1588 |
+
"grad_norm": 0.16847743093967438,
|
| 1589 |
+
"learning_rate": 0.00019514015872046833,
|
| 1590 |
+
"loss": 0.7103,
|
| 1591 |
+
"step": 2260
|
| 1592 |
+
},
|
| 1593 |
+
{
|
| 1594 |
+
"epoch": 0.05910893925059239,
|
| 1595 |
+
"grad_norm": 0.16181516647338867,
|
| 1596 |
+
"learning_rate": 0.00019508861185590307,
|
| 1597 |
+
"loss": 0.7561,
|
| 1598 |
+
"step": 2270
|
| 1599 |
+
},
|
| 1600 |
+
{
|
| 1601 |
+
"epoch": 0.059369331053458436,
|
| 1602 |
+
"grad_norm": 0.16594484448432922,
|
| 1603 |
+
"learning_rate": 0.0001950367999415981,
|
| 1604 |
+
"loss": 0.7308,
|
| 1605 |
+
"step": 2280
|
| 1606 |
+
},
|
| 1607 |
+
{
|
| 1608 |
+
"epoch": 0.05962972285632448,
|
| 1609 |
+
"grad_norm": 0.166441410779953,
|
| 1610 |
+
"learning_rate": 0.00019498472312197375,
|
| 1611 |
+
"loss": 0.735,
|
| 1612 |
+
"step": 2290
|
| 1613 |
+
},
|
| 1614 |
+
{
|
| 1615 |
+
"epoch": 0.05989011465919053,
|
| 1616 |
+
"grad_norm": 0.16273920238018036,
|
| 1617 |
+
"learning_rate": 0.00019493238154218886,
|
| 1618 |
+
"loss": 0.7458,
|
| 1619 |
+
"step": 2300
|
| 1620 |
+
},
|
| 1621 |
+
{
|
| 1622 |
+
"epoch": 0.06015050646205657,
|
| 1623 |
+
"grad_norm": 0.16227276623249054,
|
| 1624 |
+
"learning_rate": 0.00019487977534814012,
|
| 1625 |
+
"loss": 0.7143,
|
| 1626 |
+
"step": 2310
|
| 1627 |
+
},
|
| 1628 |
+
{
|
| 1629 |
+
"epoch": 0.06041089826492262,
|
| 1630 |
+
"grad_norm": 0.1619606912136078,
|
| 1631 |
+
"learning_rate": 0.000194826904686462,
|
| 1632 |
+
"loss": 0.7285,
|
| 1633 |
+
"step": 2320
|
| 1634 |
+
},
|
| 1635 |
+
{
|
| 1636 |
+
"epoch": 0.060671290067788666,
|
| 1637 |
+
"grad_norm": 0.1596045345067978,
|
| 1638 |
+
"learning_rate": 0.00019477376970452603,
|
| 1639 |
+
"loss": 0.7513,
|
| 1640 |
+
"step": 2330
|
| 1641 |
+
},
|
| 1642 |
+
{
|
| 1643 |
+
"epoch": 0.06093168187065471,
|
| 1644 |
+
"grad_norm": 0.17504757642745972,
|
| 1645 |
+
"learning_rate": 0.00019472037055044044,
|
| 1646 |
+
"loss": 0.7376,
|
| 1647 |
+
"step": 2340
|
| 1648 |
+
},
|
| 1649 |
+
{
|
| 1650 |
+
"epoch": 0.06119207367352076,
|
| 1651 |
+
"grad_norm": 0.1559167355298996,
|
| 1652 |
+
"learning_rate": 0.00019466670737304992,
|
| 1653 |
+
"loss": 0.7339,
|
| 1654 |
+
"step": 2350
|
| 1655 |
+
},
|
| 1656 |
+
{
|
| 1657 |
+
"epoch": 0.0614524654763868,
|
| 1658 |
+
"grad_norm": 0.1624836027622223,
|
| 1659 |
+
"learning_rate": 0.0001946127803219351,
|
| 1660 |
+
"loss": 0.7258,
|
| 1661 |
+
"step": 2360
|
| 1662 |
+
},
|
| 1663 |
+
{
|
| 1664 |
+
"epoch": 0.061712857279252846,
|
| 1665 |
+
"grad_norm": 0.17907138168811798,
|
| 1666 |
+
"learning_rate": 0.00019455858954741206,
|
| 1667 |
+
"loss": 0.72,
|
| 1668 |
+
"step": 2370
|
| 1669 |
+
},
|
| 1670 |
+
{
|
| 1671 |
+
"epoch": 0.061973249082118896,
|
| 1672 |
+
"grad_norm": 0.15922705829143524,
|
| 1673 |
+
"learning_rate": 0.00019450413520053202,
|
| 1674 |
+
"loss": 0.7187,
|
| 1675 |
+
"step": 2380
|
| 1676 |
+
},
|
| 1677 |
+
{
|
| 1678 |
+
"epoch": 0.06223364088498494,
|
| 1679 |
+
"grad_norm": 0.1552513986825943,
|
| 1680 |
+
"learning_rate": 0.0001944494174330809,
|
| 1681 |
+
"loss": 0.7183,
|
| 1682 |
+
"step": 2390
|
| 1683 |
+
},
|
| 1684 |
+
{
|
| 1685 |
+
"epoch": 0.06249403268785099,
|
| 1686 |
+
"grad_norm": 0.16838514804840088,
|
| 1687 |
+
"learning_rate": 0.00019439443639757885,
|
| 1688 |
+
"loss": 0.7286,
|
| 1689 |
+
"step": 2400
|
| 1690 |
+
},
|
| 1691 |
+
{
|
| 1692 |
+
"epoch": 0.06275442449071703,
|
| 1693 |
+
"grad_norm": 0.17352423071861267,
|
| 1694 |
+
"learning_rate": 0.00019433919224727986,
|
| 1695 |
+
"loss": 0.7436,
|
| 1696 |
+
"step": 2410
|
| 1697 |
+
},
|
| 1698 |
+
{
|
| 1699 |
+
"epoch": 0.06301481629358308,
|
| 1700 |
+
"grad_norm": 0.17366603016853333,
|
| 1701 |
+
"learning_rate": 0.0001942836851361713,
|
| 1702 |
+
"loss": 0.7265,
|
| 1703 |
+
"step": 2420
|
| 1704 |
+
},
|
| 1705 |
+
{
|
| 1706 |
+
"epoch": 0.06327520809644913,
|
| 1707 |
+
"grad_norm": 0.14833413064479828,
|
| 1708 |
+
"learning_rate": 0.00019422791521897357,
|
| 1709 |
+
"loss": 0.7234,
|
| 1710 |
+
"step": 2430
|
| 1711 |
+
},
|
| 1712 |
+
{
|
| 1713 |
+
"epoch": 0.06353559989931518,
|
| 1714 |
+
"grad_norm": 0.16602723300457,
|
| 1715 |
+
"learning_rate": 0.00019417188265113958,
|
| 1716 |
+
"loss": 0.725,
|
| 1717 |
+
"step": 2440
|
| 1718 |
+
},
|
| 1719 |
+
{
|
| 1720 |
+
"epoch": 0.06379599170218121,
|
| 1721 |
+
"grad_norm": 0.17290353775024414,
|
| 1722 |
+
"learning_rate": 0.00019411558758885438,
|
| 1723 |
+
"loss": 0.7174,
|
| 1724 |
+
"step": 2450
|
| 1725 |
+
},
|
| 1726 |
+
{
|
| 1727 |
+
"epoch": 0.06405638350504726,
|
| 1728 |
+
"grad_norm": 0.16486665606498718,
|
| 1729 |
+
"learning_rate": 0.0001940590301890346,
|
| 1730 |
+
"loss": 0.7301,
|
| 1731 |
+
"step": 2460
|
| 1732 |
+
},
|
| 1733 |
+
{
|
| 1734 |
+
"epoch": 0.06431677530791331,
|
| 1735 |
+
"grad_norm": 0.16255232691764832,
|
| 1736 |
+
"learning_rate": 0.00019400221060932827,
|
| 1737 |
+
"loss": 0.7462,
|
| 1738 |
+
"step": 2470
|
| 1739 |
+
},
|
| 1740 |
+
{
|
| 1741 |
+
"epoch": 0.06457716711077935,
|
| 1742 |
+
"grad_norm": 0.16139757633209229,
|
| 1743 |
+
"learning_rate": 0.0001939451290081141,
|
| 1744 |
+
"loss": 0.7424,
|
| 1745 |
+
"step": 2480
|
| 1746 |
+
},
|
| 1747 |
+
{
|
| 1748 |
+
"epoch": 0.0648375589136454,
|
| 1749 |
+
"grad_norm": 0.165597602725029,
|
| 1750 |
+
"learning_rate": 0.00019388778554450117,
|
| 1751 |
+
"loss": 0.7426,
|
| 1752 |
+
"step": 2490
|
| 1753 |
+
},
|
| 1754 |
+
{
|
| 1755 |
+
"epoch": 0.06509795071651145,
|
| 1756 |
+
"grad_norm": 0.19819000363349915,
|
| 1757 |
+
"learning_rate": 0.00019383018037832854,
|
| 1758 |
+
"loss": 0.7356,
|
| 1759 |
+
"step": 2500
|
| 1760 |
+
},
|
| 1761 |
+
{
|
| 1762 |
+
"epoch": 0.06535834251937749,
|
| 1763 |
+
"grad_norm": 0.16469696164131165,
|
| 1764 |
+
"learning_rate": 0.00019377231367016467,
|
| 1765 |
+
"loss": 0.718,
|
| 1766 |
+
"step": 2510
|
| 1767 |
+
},
|
| 1768 |
+
{
|
| 1769 |
+
"epoch": 0.06561873432224354,
|
| 1770 |
+
"grad_norm": 0.1644965261220932,
|
| 1771 |
+
"learning_rate": 0.00019371418558130702,
|
| 1772 |
+
"loss": 0.7253,
|
| 1773 |
+
"step": 2520
|
| 1774 |
+
},
|
| 1775 |
+
{
|
| 1776 |
+
"epoch": 0.06587912612510959,
|
| 1777 |
+
"grad_norm": 0.15347526967525482,
|
| 1778 |
+
"learning_rate": 0.00019365579627378174,
|
| 1779 |
+
"loss": 0.7214,
|
| 1780 |
+
"step": 2530
|
| 1781 |
+
},
|
| 1782 |
+
{
|
| 1783 |
+
"epoch": 0.06613951792797562,
|
| 1784 |
+
"grad_norm": 0.1618672013282776,
|
| 1785 |
+
"learning_rate": 0.00019359714591034302,
|
| 1786 |
+
"loss": 0.7204,
|
| 1787 |
+
"step": 2540
|
| 1788 |
+
},
|
| 1789 |
+
{
|
| 1790 |
+
"epoch": 0.06639990973084167,
|
| 1791 |
+
"grad_norm": 0.17043665051460266,
|
| 1792 |
+
"learning_rate": 0.00019353823465447268,
|
| 1793 |
+
"loss": 0.7278,
|
| 1794 |
+
"step": 2550
|
| 1795 |
+
},
|
| 1796 |
+
{
|
| 1797 |
+
"epoch": 0.06666030153370772,
|
| 1798 |
+
"grad_norm": 0.15762579441070557,
|
| 1799 |
+
"learning_rate": 0.00019347906267037983,
|
| 1800 |
+
"loss": 0.7283,
|
| 1801 |
+
"step": 2560
|
| 1802 |
+
},
|
| 1803 |
+
{
|
| 1804 |
+
"epoch": 0.06692069333657376,
|
| 1805 |
+
"grad_norm": 0.1622801572084427,
|
| 1806 |
+
"learning_rate": 0.00019341963012300029,
|
| 1807 |
+
"loss": 0.7193,
|
| 1808 |
+
"step": 2570
|
| 1809 |
+
},
|
| 1810 |
+
{
|
| 1811 |
+
"epoch": 0.06718108513943981,
|
| 1812 |
+
"grad_norm": 0.16705769300460815,
|
| 1813 |
+
"learning_rate": 0.00019335993717799617,
|
| 1814 |
+
"loss": 0.7414,
|
| 1815 |
+
"step": 2580
|
| 1816 |
+
},
|
| 1817 |
+
{
|
| 1818 |
+
"epoch": 0.06744147694230586,
|
| 1819 |
+
"grad_norm": 0.15886452794075012,
|
| 1820 |
+
"learning_rate": 0.00019329998400175545,
|
| 1821 |
+
"loss": 0.7242,
|
| 1822 |
+
"step": 2590
|
| 1823 |
+
},
|
| 1824 |
+
{
|
| 1825 |
+
"epoch": 0.06770186874517191,
|
| 1826 |
+
"grad_norm": 0.17994090914726257,
|
| 1827 |
+
"learning_rate": 0.00019323977076139142,
|
| 1828 |
+
"loss": 0.7017,
|
| 1829 |
+
"step": 2600
|
| 1830 |
+
},
|
| 1831 |
+
{
|
| 1832 |
+
"epoch": 0.06796226054803794,
|
| 1833 |
+
"grad_norm": 0.1609068214893341,
|
| 1834 |
+
"learning_rate": 0.00019317929762474232,
|
| 1835 |
+
"loss": 0.7352,
|
| 1836 |
+
"step": 2610
|
| 1837 |
+
},
|
| 1838 |
+
{
|
| 1839 |
+
"epoch": 0.068222652350904,
|
| 1840 |
+
"grad_norm": 0.15605950355529785,
|
| 1841 |
+
"learning_rate": 0.0001931185647603708,
|
| 1842 |
+
"loss": 0.7249,
|
| 1843 |
+
"step": 2620
|
| 1844 |
+
},
|
| 1845 |
+
{
|
| 1846 |
+
"epoch": 0.06848304415377005,
|
| 1847 |
+
"grad_norm": 0.16057750582695007,
|
| 1848 |
+
"learning_rate": 0.00019305757233756352,
|
| 1849 |
+
"loss": 0.7521,
|
| 1850 |
+
"step": 2630
|
| 1851 |
+
},
|
| 1852 |
+
{
|
| 1853 |
+
"epoch": 0.06874343595663608,
|
| 1854 |
+
"grad_norm": 0.1703862100839615,
|
| 1855 |
+
"learning_rate": 0.00019299632052633054,
|
| 1856 |
+
"loss": 0.7245,
|
| 1857 |
+
"step": 2640
|
| 1858 |
+
},
|
| 1859 |
+
{
|
| 1860 |
+
"epoch": 0.06900382775950213,
|
| 1861 |
+
"grad_norm": 0.16324444115161896,
|
| 1862 |
+
"learning_rate": 0.00019293480949740505,
|
| 1863 |
+
"loss": 0.7395,
|
| 1864 |
+
"step": 2650
|
| 1865 |
+
},
|
| 1866 |
+
{
|
| 1867 |
+
"epoch": 0.06926421956236818,
|
| 1868 |
+
"grad_norm": 0.15283791720867157,
|
| 1869 |
+
"learning_rate": 0.00019287303942224266,
|
| 1870 |
+
"loss": 0.7158,
|
| 1871 |
+
"step": 2660
|
| 1872 |
+
},
|
| 1873 |
+
{
|
| 1874 |
+
"epoch": 0.06952461136523422,
|
| 1875 |
+
"grad_norm": 0.1882282942533493,
|
| 1876 |
+
"learning_rate": 0.00019281101047302114,
|
| 1877 |
+
"loss": 0.724,
|
| 1878 |
+
"step": 2670
|
| 1879 |
+
},
|
| 1880 |
+
{
|
| 1881 |
+
"epoch": 0.06978500316810027,
|
| 1882 |
+
"grad_norm": 0.16147953271865845,
|
| 1883 |
+
"learning_rate": 0.00019274872282263984,
|
| 1884 |
+
"loss": 0.7365,
|
| 1885 |
+
"step": 2680
|
| 1886 |
+
},
|
| 1887 |
+
{
|
| 1888 |
+
"epoch": 0.07004539497096632,
|
| 1889 |
+
"grad_norm": 0.1614103466272354,
|
| 1890 |
+
"learning_rate": 0.00019268617664471916,
|
| 1891 |
+
"loss": 0.7206,
|
| 1892 |
+
"step": 2690
|
| 1893 |
+
},
|
| 1894 |
+
{
|
| 1895 |
+
"epoch": 0.07030578677383235,
|
| 1896 |
+
"grad_norm": 0.16784432530403137,
|
| 1897 |
+
"learning_rate": 0.00019262337211360016,
|
| 1898 |
+
"loss": 0.7279,
|
| 1899 |
+
"step": 2700
|
| 1900 |
+
},
|
| 1901 |
+
{
|
| 1902 |
+
"epoch": 0.0705661785766984,
|
| 1903 |
+
"grad_norm": 0.15966112911701202,
|
| 1904 |
+
"learning_rate": 0.000192560309404344,
|
| 1905 |
+
"loss": 0.7274,
|
| 1906 |
+
"step": 2710
|
| 1907 |
+
},
|
| 1908 |
+
{
|
| 1909 |
+
"epoch": 0.07082657037956445,
|
| 1910 |
+
"grad_norm": 0.16970521211624146,
|
| 1911 |
+
"learning_rate": 0.0001924969886927315,
|
| 1912 |
+
"loss": 0.7038,
|
| 1913 |
+
"step": 2720
|
| 1914 |
+
},
|
| 1915 |
+
{
|
| 1916 |
+
"epoch": 0.07108696218243049,
|
| 1917 |
+
"grad_norm": 0.16143856942653656,
|
| 1918 |
+
"learning_rate": 0.00019243341015526272,
|
| 1919 |
+
"loss": 0.7097,
|
| 1920 |
+
"step": 2730
|
| 1921 |
+
},
|
| 1922 |
+
{
|
| 1923 |
+
"epoch": 0.07134735398529654,
|
| 1924 |
+
"grad_norm": 0.16041269898414612,
|
| 1925 |
+
"learning_rate": 0.00019236957396915623,
|
| 1926 |
+
"loss": 0.722,
|
| 1927 |
+
"step": 2740
|
| 1928 |
+
},
|
| 1929 |
+
{
|
| 1930 |
+
"epoch": 0.07160774578816259,
|
| 1931 |
+
"grad_norm": 0.15845969319343567,
|
| 1932 |
+
"learning_rate": 0.00019230548031234882,
|
| 1933 |
+
"loss": 0.7238,
|
| 1934 |
+
"step": 2750
|
| 1935 |
+
},
|
| 1936 |
+
{
|
| 1937 |
+
"epoch": 0.07186813759102864,
|
| 1938 |
+
"grad_norm": 0.14966030418872833,
|
| 1939 |
+
"learning_rate": 0.00019224112936349502,
|
| 1940 |
+
"loss": 0.7182,
|
| 1941 |
+
"step": 2760
|
| 1942 |
+
},
|
| 1943 |
+
{
|
| 1944 |
+
"epoch": 0.07212852939389468,
|
| 1945 |
+
"grad_norm": 0.16525116562843323,
|
| 1946 |
+
"learning_rate": 0.00019217652130196653,
|
| 1947 |
+
"loss": 0.7397,
|
| 1948 |
+
"step": 2770
|
| 1949 |
+
},
|
| 1950 |
+
{
|
| 1951 |
+
"epoch": 0.07238892119676073,
|
| 1952 |
+
"grad_norm": 0.18119119107723236,
|
| 1953 |
+
"learning_rate": 0.0001921116563078516,
|
| 1954 |
+
"loss": 0.7222,
|
| 1955 |
+
"step": 2780
|
| 1956 |
+
},
|
| 1957 |
+
{
|
| 1958 |
+
"epoch": 0.07264931299962678,
|
| 1959 |
+
"grad_norm": 0.1709197610616684,
|
| 1960 |
+
"learning_rate": 0.00019204653456195478,
|
| 1961 |
+
"loss": 0.7068,
|
| 1962 |
+
"step": 2790
|
| 1963 |
+
},
|
| 1964 |
+
{
|
| 1965 |
+
"epoch": 0.07290970480249281,
|
| 1966 |
+
"grad_norm": 0.16309161484241486,
|
| 1967 |
+
"learning_rate": 0.00019198115624579625,
|
| 1968 |
+
"loss": 0.7349,
|
| 1969 |
+
"step": 2800
|
| 1970 |
+
},
|
| 1971 |
+
{
|
| 1972 |
+
"epoch": 0.07317009660535886,
|
| 1973 |
+
"grad_norm": 0.1736750453710556,
|
| 1974 |
+
"learning_rate": 0.00019191552154161135,
|
| 1975 |
+
"loss": 0.7445,
|
| 1976 |
+
"step": 2810
|
| 1977 |
+
},
|
| 1978 |
+
{
|
| 1979 |
+
"epoch": 0.07343048840822491,
|
| 1980 |
+
"grad_norm": 0.15009112656116486,
|
| 1981 |
+
"learning_rate": 0.00019184963063235006,
|
| 1982 |
+
"loss": 0.7034,
|
| 1983 |
+
"step": 2820
|
| 1984 |
+
},
|
| 1985 |
+
{
|
| 1986 |
+
"epoch": 0.07369088021109095,
|
| 1987 |
+
"grad_norm": 0.17244628071784973,
|
| 1988 |
+
"learning_rate": 0.0001917834837016766,
|
| 1989 |
+
"loss": 0.7285,
|
| 1990 |
+
"step": 2830
|
| 1991 |
+
},
|
| 1992 |
+
{
|
| 1993 |
+
"epoch": 0.073951272013957,
|
| 1994 |
+
"grad_norm": 0.15991820394992828,
|
| 1995 |
+
"learning_rate": 0.00019171708093396861,
|
| 1996 |
+
"loss": 0.7096,
|
| 1997 |
+
"step": 2840
|
| 1998 |
+
},
|
| 1999 |
+
{
|
| 2000 |
+
"epoch": 0.07421166381682305,
|
| 2001 |
+
"grad_norm": 0.17037667334079742,
|
| 2002 |
+
"learning_rate": 0.0001916504225143171,
|
| 2003 |
+
"loss": 0.7177,
|
| 2004 |
+
"step": 2850
|
| 2005 |
+
},
|
| 2006 |
+
{
|
| 2007 |
+
"epoch": 0.07447205561968909,
|
| 2008 |
+
"grad_norm": 0.16700348258018494,
|
| 2009 |
+
"learning_rate": 0.00019158350862852553,
|
| 2010 |
+
"loss": 0.7453,
|
| 2011 |
+
"step": 2860
|
| 2012 |
+
},
|
| 2013 |
+
{
|
| 2014 |
+
"epoch": 0.07473244742255514,
|
| 2015 |
+
"grad_norm": 0.17683659493923187,
|
| 2016 |
+
"learning_rate": 0.00019151633946310948,
|
| 2017 |
+
"loss": 0.7331,
|
| 2018 |
+
"step": 2870
|
| 2019 |
+
},
|
| 2020 |
+
{
|
| 2021 |
+
"epoch": 0.07499283922542119,
|
| 2022 |
+
"grad_norm": 0.16364306211471558,
|
| 2023 |
+
"learning_rate": 0.00019144891520529608,
|
| 2024 |
+
"loss": 0.7347,
|
| 2025 |
+
"step": 2880
|
| 2026 |
+
},
|
| 2027 |
+
{
|
| 2028 |
+
"epoch": 0.07525323102828722,
|
| 2029 |
+
"grad_norm": 0.1781424731016159,
|
| 2030 |
+
"learning_rate": 0.00019138123604302355,
|
| 2031 |
+
"loss": 0.7169,
|
| 2032 |
+
"step": 2890
|
| 2033 |
+
},
|
| 2034 |
+
{
|
| 2035 |
+
"epoch": 0.07551362283115327,
|
| 2036 |
+
"grad_norm": 0.16007259488105774,
|
| 2037 |
+
"learning_rate": 0.00019131330216494064,
|
| 2038 |
+
"loss": 0.7269,
|
| 2039 |
+
"step": 2900
|
| 2040 |
+
},
|
| 2041 |
+
{
|
| 2042 |
+
"epoch": 0.07577401463401932,
|
| 2043 |
+
"grad_norm": 0.1604921519756317,
|
| 2044 |
+
"learning_rate": 0.00019124511376040598,
|
| 2045 |
+
"loss": 0.7094,
|
| 2046 |
+
"step": 2910
|
| 2047 |
+
},
|
| 2048 |
+
{
|
| 2049 |
+
"epoch": 0.07603440643688536,
|
| 2050 |
+
"grad_norm": 0.16649965941905975,
|
| 2051 |
+
"learning_rate": 0.00019117667101948782,
|
| 2052 |
+
"loss": 0.7271,
|
| 2053 |
+
"step": 2920
|
| 2054 |
+
},
|
| 2055 |
+
{
|
| 2056 |
+
"epoch": 0.07629479823975141,
|
| 2057 |
+
"grad_norm": 0.16084066033363342,
|
| 2058 |
+
"learning_rate": 0.0001911079741329632,
|
| 2059 |
+
"loss": 0.7239,
|
| 2060 |
+
"step": 2930
|
| 2061 |
+
},
|
| 2062 |
+
{
|
| 2063 |
+
"epoch": 0.07655519004261746,
|
| 2064 |
+
"grad_norm": 0.1651066243648529,
|
| 2065 |
+
"learning_rate": 0.0001910390232923177,
|
| 2066 |
+
"loss": 0.7304,
|
| 2067 |
+
"step": 2940
|
| 2068 |
+
},
|
| 2069 |
+
{
|
| 2070 |
+
"epoch": 0.07681558184548351,
|
| 2071 |
+
"grad_norm": 0.1528957635164261,
|
| 2072 |
+
"learning_rate": 0.00019096981868974467,
|
| 2073 |
+
"loss": 0.7068,
|
| 2074 |
+
"step": 2950
|
| 2075 |
+
},
|
| 2076 |
+
{
|
| 2077 |
+
"epoch": 0.07707597364834955,
|
| 2078 |
+
"grad_norm": 0.172830730676651,
|
| 2079 |
+
"learning_rate": 0.00019090036051814483,
|
| 2080 |
+
"loss": 0.7277,
|
| 2081 |
+
"step": 2960
|
| 2082 |
+
},
|
| 2083 |
+
{
|
| 2084 |
+
"epoch": 0.0773363654512156,
|
| 2085 |
+
"grad_norm": 0.15909147262573242,
|
| 2086 |
+
"learning_rate": 0.00019083064897112571,
|
| 2087 |
+
"loss": 0.7135,
|
| 2088 |
+
"step": 2970
|
| 2089 |
+
},
|
| 2090 |
+
{
|
| 2091 |
+
"epoch": 0.07759675725408165,
|
| 2092 |
+
"grad_norm": 0.16273066401481628,
|
| 2093 |
+
"learning_rate": 0.0001907606842430011,
|
| 2094 |
+
"loss": 0.7346,
|
| 2095 |
+
"step": 2980
|
| 2096 |
+
},
|
| 2097 |
+
{
|
| 2098 |
+
"epoch": 0.07785714905694768,
|
| 2099 |
+
"grad_norm": 0.1595291793346405,
|
| 2100 |
+
"learning_rate": 0.00019069046652879049,
|
| 2101 |
+
"loss": 0.7377,
|
| 2102 |
+
"step": 2990
|
| 2103 |
+
},
|
| 2104 |
+
{
|
| 2105 |
+
"epoch": 0.07811754085981373,
|
| 2106 |
+
"grad_norm": 0.15573470294475555,
|
| 2107 |
+
"learning_rate": 0.0001906199960242185,
|
| 2108 |
+
"loss": 0.7026,
|
| 2109 |
+
"step": 3000
|
| 2110 |
+
},
|
| 2111 |
+
{
|
| 2112 |
+
"epoch": 0.07837793266267978,
|
| 2113 |
+
"grad_norm": 0.1670667678117752,
|
| 2114 |
+
"learning_rate": 0.0001905492729257145,
|
| 2115 |
+
"loss": 0.7231,
|
| 2116 |
+
"step": 3010
|
| 2117 |
+
},
|
| 2118 |
+
{
|
| 2119 |
+
"epoch": 0.07863832446554582,
|
| 2120 |
+
"grad_norm": 0.17074571549892426,
|
| 2121 |
+
"learning_rate": 0.00019047829743041184,
|
| 2122 |
+
"loss": 0.7003,
|
| 2123 |
+
"step": 3020
|
| 2124 |
+
},
|
| 2125 |
+
{
|
| 2126 |
+
"epoch": 0.07889871626841187,
|
| 2127 |
+
"grad_norm": 0.16979442536830902,
|
| 2128 |
+
"learning_rate": 0.00019040706973614738,
|
| 2129 |
+
"loss": 0.7217,
|
| 2130 |
+
"step": 3030
|
| 2131 |
+
},
|
| 2132 |
+
{
|
| 2133 |
+
"epoch": 0.07915910807127792,
|
| 2134 |
+
"grad_norm": 0.15843816101551056,
|
| 2135 |
+
"learning_rate": 0.00019033559004146103,
|
| 2136 |
+
"loss": 0.7334,
|
| 2137 |
+
"step": 3040
|
| 2138 |
+
},
|
| 2139 |
+
{
|
| 2140 |
+
"epoch": 0.07941949987414396,
|
| 2141 |
+
"grad_norm": 0.1607016921043396,
|
| 2142 |
+
"learning_rate": 0.0001902638585455951,
|
| 2143 |
+
"loss": 0.7271,
|
| 2144 |
+
"step": 3050
|
| 2145 |
+
},
|
| 2146 |
+
{
|
| 2147 |
+
"epoch": 0.07967989167701,
|
| 2148 |
+
"grad_norm": 0.1619115173816681,
|
| 2149 |
+
"learning_rate": 0.0001901918754484938,
|
| 2150 |
+
"loss": 0.7144,
|
| 2151 |
+
"step": 3060
|
| 2152 |
+
},
|
| 2153 |
+
{
|
| 2154 |
+
"epoch": 0.07994028347987606,
|
| 2155 |
+
"grad_norm": 0.1638360172510147,
|
| 2156 |
+
"learning_rate": 0.00019011964095080254,
|
| 2157 |
+
"loss": 0.7149,
|
| 2158 |
+
"step": 3070
|
| 2159 |
+
},
|
| 2160 |
+
{
|
| 2161 |
+
"epoch": 0.08020067528274209,
|
| 2162 |
+
"grad_norm": 0.16503652930259705,
|
| 2163 |
+
"learning_rate": 0.00019004715525386764,
|
| 2164 |
+
"loss": 0.7011,
|
| 2165 |
+
"step": 3080
|
| 2166 |
+
},
|
| 2167 |
+
{
|
| 2168 |
+
"epoch": 0.08046106708560814,
|
| 2169 |
+
"grad_norm": 0.16763822734355927,
|
| 2170 |
+
"learning_rate": 0.00018997441855973552,
|
| 2171 |
+
"loss": 0.7145,
|
| 2172 |
+
"step": 3090
|
| 2173 |
+
},
|
| 2174 |
+
{
|
| 2175 |
+
"epoch": 0.08072145888847419,
|
| 2176 |
+
"grad_norm": 0.1621125340461731,
|
| 2177 |
+
"learning_rate": 0.0001899014310711522,
|
| 2178 |
+
"loss": 0.7318,
|
| 2179 |
+
"step": 3100
|
| 2180 |
+
},
|
| 2181 |
+
{
|
| 2182 |
+
"epoch": 0.08098185069134024,
|
| 2183 |
+
"grad_norm": 0.16480112075805664,
|
| 2184 |
+
"learning_rate": 0.0001898281929915629,
|
| 2185 |
+
"loss": 0.7145,
|
| 2186 |
+
"step": 3110
|
| 2187 |
+
},
|
| 2188 |
+
{
|
| 2189 |
+
"epoch": 0.08124224249420628,
|
| 2190 |
+
"grad_norm": 0.1805388629436493,
|
| 2191 |
+
"learning_rate": 0.00018975470452511112,
|
| 2192 |
+
"loss": 0.7102,
|
| 2193 |
+
"step": 3120
|
| 2194 |
+
},
|
| 2195 |
+
{
|
| 2196 |
+
"epoch": 0.08150263429707233,
|
| 2197 |
+
"grad_norm": 0.1902652531862259,
|
| 2198 |
+
"learning_rate": 0.00018968096587663853,
|
| 2199 |
+
"loss": 0.7281,
|
| 2200 |
+
"step": 3130
|
| 2201 |
+
},
|
| 2202 |
+
{
|
| 2203 |
+
"epoch": 0.08176302609993838,
|
| 2204 |
+
"grad_norm": 0.1732487976551056,
|
| 2205 |
+
"learning_rate": 0.00018960697725168397,
|
| 2206 |
+
"loss": 0.7434,
|
| 2207 |
+
"step": 3140
|
| 2208 |
+
},
|
| 2209 |
+
{
|
| 2210 |
+
"epoch": 0.08202341790280442,
|
| 2211 |
+
"grad_norm": 0.1662171334028244,
|
| 2212 |
+
"learning_rate": 0.00018953273885648314,
|
| 2213 |
+
"loss": 0.716,
|
| 2214 |
+
"step": 3150
|
| 2215 |
+
},
|
| 2216 |
+
{
|
| 2217 |
+
"epoch": 0.08228380970567047,
|
| 2218 |
+
"grad_norm": 0.16129222512245178,
|
| 2219 |
+
"learning_rate": 0.00018945825089796797,
|
| 2220 |
+
"loss": 0.7318,
|
| 2221 |
+
"step": 3160
|
| 2222 |
+
},
|
| 2223 |
+
{
|
| 2224 |
+
"epoch": 0.08254420150853652,
|
| 2225 |
+
"grad_norm": 0.16837772727012634,
|
| 2226 |
+
"learning_rate": 0.00018938351358376596,
|
| 2227 |
+
"loss": 0.7137,
|
| 2228 |
+
"step": 3170
|
| 2229 |
+
},
|
| 2230 |
+
{
|
| 2231 |
+
"epoch": 0.08280459331140255,
|
| 2232 |
+
"grad_norm": 0.1618524193763733,
|
| 2233 |
+
"learning_rate": 0.00018930852712219974,
|
| 2234 |
+
"loss": 0.7079,
|
| 2235 |
+
"step": 3180
|
| 2236 |
+
},
|
| 2237 |
+
{
|
| 2238 |
+
"epoch": 0.0830649851142686,
|
| 2239 |
+
"grad_norm": 0.16333432495594025,
|
| 2240 |
+
"learning_rate": 0.00018923329172228632,
|
| 2241 |
+
"loss": 0.7062,
|
| 2242 |
+
"step": 3190
|
| 2243 |
+
},
|
| 2244 |
+
{
|
| 2245 |
+
"epoch": 0.08332537691713465,
|
| 2246 |
+
"grad_norm": 0.15985700488090515,
|
| 2247 |
+
"learning_rate": 0.00018915780759373672,
|
| 2248 |
+
"loss": 0.7277,
|
| 2249 |
+
"step": 3200
|
| 2250 |
+
},
|
| 2251 |
+
{
|
| 2252 |
+
"epoch": 0.08358576872000069,
|
| 2253 |
+
"grad_norm": 0.16181236505508423,
|
| 2254 |
+
"learning_rate": 0.0001890820749469551,
|
| 2255 |
+
"loss": 0.7048,
|
| 2256 |
+
"step": 3210
|
| 2257 |
+
},
|
| 2258 |
+
{
|
| 2259 |
+
"epoch": 0.08384616052286674,
|
| 2260 |
+
"grad_norm": 0.1679672747850418,
|
| 2261 |
+
"learning_rate": 0.00018900609399303853,
|
| 2262 |
+
"loss": 0.73,
|
| 2263 |
+
"step": 3220
|
| 2264 |
+
},
|
| 2265 |
+
{
|
| 2266 |
+
"epoch": 0.08410655232573279,
|
| 2267 |
+
"grad_norm": 0.16680286824703217,
|
| 2268 |
+
"learning_rate": 0.00018892986494377606,
|
| 2269 |
+
"loss": 0.7169,
|
| 2270 |
+
"step": 3230
|
| 2271 |
+
},
|
| 2272 |
+
{
|
| 2273 |
+
"epoch": 0.08436694412859883,
|
| 2274 |
+
"grad_norm": 0.15980315208435059,
|
| 2275 |
+
"learning_rate": 0.00018885338801164834,
|
| 2276 |
+
"loss": 0.7346,
|
| 2277 |
+
"step": 3240
|
| 2278 |
+
},
|
| 2279 |
+
{
|
| 2280 |
+
"epoch": 0.08462733593146488,
|
| 2281 |
+
"grad_norm": 0.16863352060317993,
|
| 2282 |
+
"learning_rate": 0.00018877666340982695,
|
| 2283 |
+
"loss": 0.7256,
|
| 2284 |
+
"step": 3250
|
| 2285 |
+
},
|
| 2286 |
+
{
|
| 2287 |
+
"epoch": 0.08488772773433093,
|
| 2288 |
+
"grad_norm": 0.1657836139202118,
|
| 2289 |
+
"learning_rate": 0.0001886996913521739,
|
| 2290 |
+
"loss": 0.7219,
|
| 2291 |
+
"step": 3260
|
| 2292 |
+
},
|
| 2293 |
+
{
|
| 2294 |
+
"epoch": 0.08514811953719698,
|
| 2295 |
+
"grad_norm": 0.1683470606803894,
|
| 2296 |
+
"learning_rate": 0.00018862247205324087,
|
| 2297 |
+
"loss": 0.7279,
|
| 2298 |
+
"step": 3270
|
| 2299 |
+
},
|
| 2300 |
+
{
|
| 2301 |
+
"epoch": 0.08540851134006301,
|
| 2302 |
+
"grad_norm": 0.1686122715473175,
|
| 2303 |
+
"learning_rate": 0.00018854500572826867,
|
| 2304 |
+
"loss": 0.7178,
|
| 2305 |
+
"step": 3280
|
| 2306 |
+
},
|
| 2307 |
+
{
|
| 2308 |
+
"epoch": 0.08566890314292906,
|
| 2309 |
+
"grad_norm": 0.16122782230377197,
|
| 2310 |
+
"learning_rate": 0.00018846729259318682,
|
| 2311 |
+
"loss": 0.7289,
|
| 2312 |
+
"step": 3290
|
| 2313 |
+
},
|
| 2314 |
+
{
|
| 2315 |
+
"epoch": 0.08592929494579511,
|
| 2316 |
+
"grad_norm": 0.1920589804649353,
|
| 2317 |
+
"learning_rate": 0.0001883893328646126,
|
| 2318 |
+
"loss": 0.7264,
|
| 2319 |
+
"step": 3300
|
| 2320 |
+
},
|
| 2321 |
+
{
|
| 2322 |
+
"epoch": 0.08618968674866115,
|
| 2323 |
+
"grad_norm": 0.17415335774421692,
|
| 2324 |
+
"learning_rate": 0.00018831112675985083,
|
| 2325 |
+
"loss": 0.7378,
|
| 2326 |
+
"step": 3310
|
| 2327 |
+
},
|
| 2328 |
+
{
|
| 2329 |
+
"epoch": 0.0864500785515272,
|
| 2330 |
+
"grad_norm": 0.16903561353683472,
|
| 2331 |
+
"learning_rate": 0.00018823267449689292,
|
| 2332 |
+
"loss": 0.702,
|
| 2333 |
+
"step": 3320
|
| 2334 |
+
},
|
| 2335 |
+
{
|
| 2336 |
+
"epoch": 0.08671047035439325,
|
| 2337 |
+
"grad_norm": 0.17158570885658264,
|
| 2338 |
+
"learning_rate": 0.00018815397629441658,
|
| 2339 |
+
"loss": 0.7264,
|
| 2340 |
+
"step": 3330
|
| 2341 |
+
},
|
| 2342 |
+
{
|
| 2343 |
+
"epoch": 0.08697086215725928,
|
| 2344 |
+
"grad_norm": 0.17094087600708008,
|
| 2345 |
+
"learning_rate": 0.0001880750323717849,
|
| 2346 |
+
"loss": 0.741,
|
| 2347 |
+
"step": 3340
|
| 2348 |
+
},
|
| 2349 |
+
{
|
| 2350 |
+
"epoch": 0.08723125396012534,
|
| 2351 |
+
"grad_norm": 0.1618223935365677,
|
| 2352 |
+
"learning_rate": 0.000187995842949046,
|
| 2353 |
+
"loss": 0.7084,
|
| 2354 |
+
"step": 3350
|
| 2355 |
+
},
|
| 2356 |
+
{
|
| 2357 |
+
"epoch": 0.08749164576299139,
|
| 2358 |
+
"grad_norm": 0.1671626716852188,
|
| 2359 |
+
"learning_rate": 0.0001879164082469322,
|
| 2360 |
+
"loss": 0.7236,
|
| 2361 |
+
"step": 3360
|
| 2362 |
+
},
|
| 2363 |
+
{
|
| 2364 |
+
"epoch": 0.08775203756585742,
|
| 2365 |
+
"grad_norm": 0.1681569665670395,
|
| 2366 |
+
"learning_rate": 0.00018783672848685966,
|
| 2367 |
+
"loss": 0.7382,
|
| 2368 |
+
"step": 3370
|
| 2369 |
+
},
|
| 2370 |
+
{
|
| 2371 |
+
"epoch": 0.08801242936872347,
|
| 2372 |
+
"grad_norm": 0.16421955823898315,
|
| 2373 |
+
"learning_rate": 0.00018775680389092748,
|
| 2374 |
+
"loss": 0.717,
|
| 2375 |
+
"step": 3380
|
| 2376 |
+
},
|
| 2377 |
+
{
|
| 2378 |
+
"epoch": 0.08827282117158952,
|
| 2379 |
+
"grad_norm": 0.174809530377388,
|
| 2380 |
+
"learning_rate": 0.00018767663468191725,
|
| 2381 |
+
"loss": 0.7225,
|
| 2382 |
+
"step": 3390
|
| 2383 |
+
},
|
| 2384 |
+
{
|
| 2385 |
+
"epoch": 0.08853321297445556,
|
| 2386 |
+
"grad_norm": 0.16181902587413788,
|
| 2387 |
+
"learning_rate": 0.00018759622108329243,
|
| 2388 |
+
"loss": 0.7014,
|
| 2389 |
+
"step": 3400
|
| 2390 |
+
},
|
| 2391 |
+
{
|
| 2392 |
+
"epoch": 0.08879360477732161,
|
| 2393 |
+
"grad_norm": 0.15579254925251007,
|
| 2394 |
+
"learning_rate": 0.0001875155633191977,
|
| 2395 |
+
"loss": 0.7125,
|
| 2396 |
+
"step": 3410
|
| 2397 |
+
},
|
| 2398 |
+
{
|
| 2399 |
+
"epoch": 0.08905399658018766,
|
| 2400 |
+
"grad_norm": 0.16342496871948242,
|
| 2401 |
+
"learning_rate": 0.00018743466161445823,
|
| 2402 |
+
"loss": 0.7075,
|
| 2403 |
+
"step": 3420
|
| 2404 |
+
},
|
| 2405 |
+
{
|
| 2406 |
+
"epoch": 0.08931438838305371,
|
| 2407 |
+
"grad_norm": 0.17215611040592194,
|
| 2408 |
+
"learning_rate": 0.00018735351619457923,
|
| 2409 |
+
"loss": 0.7331,
|
| 2410 |
+
"step": 3430
|
| 2411 |
+
},
|
| 2412 |
+
{
|
| 2413 |
+
"epoch": 0.08957478018591974,
|
| 2414 |
+
"grad_norm": 0.1682904213666916,
|
| 2415 |
+
"learning_rate": 0.00018727212728574522,
|
| 2416 |
+
"loss": 0.734,
|
| 2417 |
+
"step": 3440
|
| 2418 |
+
},
|
| 2419 |
+
{
|
| 2420 |
+
"epoch": 0.0898351719887858,
|
| 2421 |
+
"grad_norm": 0.16969889402389526,
|
| 2422 |
+
"learning_rate": 0.00018719049511481948,
|
| 2423 |
+
"loss": 0.7224,
|
| 2424 |
+
"step": 3450
|
| 2425 |
+
},
|
| 2426 |
+
{
|
| 2427 |
+
"epoch": 0.09009556379165184,
|
| 2428 |
+
"grad_norm": 0.16607950627803802,
|
| 2429 |
+
"learning_rate": 0.00018710861990934324,
|
| 2430 |
+
"loss": 0.7218,
|
| 2431 |
+
"step": 3460
|
| 2432 |
+
},
|
| 2433 |
+
{
|
| 2434 |
+
"epoch": 0.09035595559451788,
|
| 2435 |
+
"grad_norm": 0.16665585339069366,
|
| 2436 |
+
"learning_rate": 0.00018702650189753525,
|
| 2437 |
+
"loss": 0.7152,
|
| 2438 |
+
"step": 3470
|
| 2439 |
+
},
|
| 2440 |
+
{
|
| 2441 |
+
"epoch": 0.09061634739738393,
|
| 2442 |
+
"grad_norm": 0.16812992095947266,
|
| 2443 |
+
"learning_rate": 0.00018694414130829103,
|
| 2444 |
+
"loss": 0.7097,
|
| 2445 |
+
"step": 3480
|
| 2446 |
+
},
|
| 2447 |
+
{
|
| 2448 |
+
"epoch": 0.09087673920024998,
|
| 2449 |
+
"grad_norm": 0.16855508089065552,
|
| 2450 |
+
"learning_rate": 0.00018686153837118224,
|
| 2451 |
+
"loss": 0.7268,
|
| 2452 |
+
"step": 3490
|
| 2453 |
+
},
|
| 2454 |
+
{
|
| 2455 |
+
"epoch": 0.09113713100311602,
|
| 2456 |
+
"grad_norm": 0.1634734570980072,
|
| 2457 |
+
"learning_rate": 0.00018677869331645613,
|
| 2458 |
+
"loss": 0.7485,
|
| 2459 |
+
"step": 3500
|
| 2460 |
+
},
|
| 2461 |
+
{
|
| 2462 |
+
"epoch": 0.09139752280598207,
|
| 2463 |
+
"grad_norm": 0.17040792107582092,
|
| 2464 |
+
"learning_rate": 0.00018669560637503478,
|
| 2465 |
+
"loss": 0.7529,
|
| 2466 |
+
"step": 3510
|
| 2467 |
+
},
|
| 2468 |
+
{
|
| 2469 |
+
"epoch": 0.09165791460884812,
|
| 2470 |
+
"grad_norm": 0.16575287282466888,
|
| 2471 |
+
"learning_rate": 0.00018661227777851447,
|
| 2472 |
+
"loss": 0.7053,
|
| 2473 |
+
"step": 3520
|
| 2474 |
+
},
|
| 2475 |
+
{
|
| 2476 |
+
"epoch": 0.09191830641171415,
|
| 2477 |
+
"grad_norm": 0.16195647418498993,
|
| 2478 |
+
"learning_rate": 0.00018652870775916515,
|
| 2479 |
+
"loss": 0.7498,
|
| 2480 |
+
"step": 3530
|
| 2481 |
+
},
|
| 2482 |
+
{
|
| 2483 |
+
"epoch": 0.0921786982145802,
|
| 2484 |
+
"grad_norm": 0.16672903299331665,
|
| 2485 |
+
"learning_rate": 0.00018644489654992956,
|
| 2486 |
+
"loss": 0.7168,
|
| 2487 |
+
"step": 3540
|
| 2488 |
+
},
|
| 2489 |
+
{
|
| 2490 |
+
"epoch": 0.09243909001744625,
|
| 2491 |
+
"grad_norm": 0.16135342419147491,
|
| 2492 |
+
"learning_rate": 0.00018636084438442298,
|
| 2493 |
+
"loss": 0.6868,
|
| 2494 |
+
"step": 3550
|
| 2495 |
+
},
|
| 2496 |
+
{
|
| 2497 |
+
"epoch": 0.09269948182031229,
|
| 2498 |
+
"grad_norm": 0.16677817702293396,
|
| 2499 |
+
"learning_rate": 0.0001862765514969321,
|
| 2500 |
+
"loss": 0.7128,
|
| 2501 |
+
"step": 3560
|
| 2502 |
+
},
|
| 2503 |
+
{
|
| 2504 |
+
"epoch": 0.09295987362317834,
|
| 2505 |
+
"grad_norm": 0.16983947157859802,
|
| 2506 |
+
"learning_rate": 0.00018619201812241474,
|
| 2507 |
+
"loss": 0.7189,
|
| 2508 |
+
"step": 3570
|
| 2509 |
+
},
|
| 2510 |
+
{
|
| 2511 |
+
"epoch": 0.09322026542604439,
|
| 2512 |
+
"grad_norm": 0.17054444551467896,
|
| 2513 |
+
"learning_rate": 0.00018610724449649895,
|
| 2514 |
+
"loss": 0.6916,
|
| 2515 |
+
"step": 3580
|
| 2516 |
+
},
|
| 2517 |
+
{
|
| 2518 |
+
"epoch": 0.09348065722891043,
|
| 2519 |
+
"grad_norm": 0.1672518253326416,
|
| 2520 |
+
"learning_rate": 0.0001860222308554825,
|
| 2521 |
+
"loss": 0.7002,
|
| 2522 |
+
"step": 3590
|
| 2523 |
+
},
|
| 2524 |
+
{
|
| 2525 |
+
"epoch": 0.09374104903177648,
|
| 2526 |
+
"grad_norm": 0.16726090013980865,
|
| 2527 |
+
"learning_rate": 0.00018593697743633225,
|
| 2528 |
+
"loss": 0.7153,
|
| 2529 |
+
"step": 3600
|
| 2530 |
+
},
|
| 2531 |
+
{
|
| 2532 |
+
"epoch": 0.09400144083464253,
|
| 2533 |
+
"grad_norm": 0.16627268493175507,
|
| 2534 |
+
"learning_rate": 0.0001858514844766833,
|
| 2535 |
+
"loss": 0.7121,
|
| 2536 |
+
"step": 3610
|
| 2537 |
+
},
|
| 2538 |
+
{
|
| 2539 |
+
"epoch": 0.09426183263750858,
|
| 2540 |
+
"grad_norm": 0.16322413086891174,
|
| 2541 |
+
"learning_rate": 0.00018576575221483852,
|
| 2542 |
+
"loss": 0.7018,
|
| 2543 |
+
"step": 3620
|
| 2544 |
+
},
|
| 2545 |
+
{
|
| 2546 |
+
"epoch": 0.09452222444037461,
|
| 2547 |
+
"grad_norm": 0.1642254739999771,
|
| 2548 |
+
"learning_rate": 0.00018567978088976776,
|
| 2549 |
+
"loss": 0.706,
|
| 2550 |
+
"step": 3630
|
| 2551 |
+
},
|
| 2552 |
+
{
|
| 2553 |
+
"epoch": 0.09478261624324066,
|
| 2554 |
+
"grad_norm": 0.17001990973949432,
|
| 2555 |
+
"learning_rate": 0.00018559357074110727,
|
| 2556 |
+
"loss": 0.7236,
|
| 2557 |
+
"step": 3640
|
| 2558 |
+
},
|
| 2559 |
+
{
|
| 2560 |
+
"epoch": 0.09504300804610671,
|
| 2561 |
+
"grad_norm": 0.166624054312706,
|
| 2562 |
+
"learning_rate": 0.00018550712200915897,
|
| 2563 |
+
"loss": 0.7129,
|
| 2564 |
+
"step": 3650
|
| 2565 |
+
},
|
| 2566 |
+
{
|
| 2567 |
+
"epoch": 0.09530339984897275,
|
| 2568 |
+
"grad_norm": 0.17228394746780396,
|
| 2569 |
+
"learning_rate": 0.00018542043493488986,
|
| 2570 |
+
"loss": 0.7096,
|
| 2571 |
+
"step": 3660
|
| 2572 |
+
},
|
| 2573 |
+
{
|
| 2574 |
+
"epoch": 0.0955637916518388,
|
| 2575 |
+
"grad_norm": 0.17133943736553192,
|
| 2576 |
+
"learning_rate": 0.0001853335097599312,
|
| 2577 |
+
"loss": 0.7164,
|
| 2578 |
+
"step": 3670
|
| 2579 |
+
},
|
| 2580 |
+
{
|
| 2581 |
+
"epoch": 0.09582418345470485,
|
| 2582 |
+
"grad_norm": 0.16100934147834778,
|
| 2583 |
+
"learning_rate": 0.00018524634672657805,
|
| 2584 |
+
"loss": 0.711,
|
| 2585 |
+
"step": 3680
|
| 2586 |
+
},
|
| 2587 |
+
{
|
| 2588 |
+
"epoch": 0.09608457525757089,
|
| 2589 |
+
"grad_norm": 0.17711074650287628,
|
| 2590 |
+
"learning_rate": 0.00018515894607778837,
|
| 2591 |
+
"loss": 0.7153,
|
| 2592 |
+
"step": 3690
|
| 2593 |
+
},
|
| 2594 |
+
{
|
| 2595 |
+
"epoch": 0.09634496706043694,
|
| 2596 |
+
"grad_norm": 0.20850953459739685,
|
| 2597 |
+
"learning_rate": 0.00018507130805718252,
|
| 2598 |
+
"loss": 0.7309,
|
| 2599 |
+
"step": 3700
|
| 2600 |
+
},
|
| 2601 |
+
{
|
| 2602 |
+
"epoch": 0.09660535886330299,
|
| 2603 |
+
"grad_norm": 0.15805912017822266,
|
| 2604 |
+
"learning_rate": 0.00018498343290904246,
|
| 2605 |
+
"loss": 0.72,
|
| 2606 |
+
"step": 3710
|
| 2607 |
+
},
|
| 2608 |
+
{
|
| 2609 |
+
"epoch": 0.09686575066616902,
|
| 2610 |
+
"grad_norm": 0.17850877344608307,
|
| 2611 |
+
"learning_rate": 0.00018489532087831114,
|
| 2612 |
+
"loss": 0.7235,
|
| 2613 |
+
"step": 3720
|
| 2614 |
+
},
|
| 2615 |
+
{
|
| 2616 |
+
"epoch": 0.09712614246903507,
|
| 2617 |
+
"grad_norm": 0.16705553233623505,
|
| 2618 |
+
"learning_rate": 0.0001848069722105918,
|
| 2619 |
+
"loss": 0.7233,
|
| 2620 |
+
"step": 3730
|
| 2621 |
+
},
|
| 2622 |
+
{
|
| 2623 |
+
"epoch": 0.09738653427190112,
|
| 2624 |
+
"grad_norm": 0.17024511098861694,
|
| 2625 |
+
"learning_rate": 0.0001847183871521473,
|
| 2626 |
+
"loss": 0.7127,
|
| 2627 |
+
"step": 3740
|
| 2628 |
+
},
|
| 2629 |
+
{
|
| 2630 |
+
"epoch": 0.09764692607476716,
|
| 2631 |
+
"grad_norm": 0.16217222809791565,
|
| 2632 |
+
"learning_rate": 0.0001846295659498994,
|
| 2633 |
+
"loss": 0.6844,
|
| 2634 |
+
"step": 3750
|
| 2635 |
+
},
|
| 2636 |
+
{
|
| 2637 |
+
"epoch": 0.09790731787763321,
|
| 2638 |
+
"grad_norm": 0.20443694293498993,
|
| 2639 |
+
"learning_rate": 0.00018454050885142803,
|
| 2640 |
+
"loss": 0.7327,
|
| 2641 |
+
"step": 3760
|
| 2642 |
+
},
|
| 2643 |
+
{
|
| 2644 |
+
"epoch": 0.09816770968049926,
|
| 2645 |
+
"grad_norm": 0.16370315849781036,
|
| 2646 |
+
"learning_rate": 0.00018445121610497072,
|
| 2647 |
+
"loss": 0.7191,
|
| 2648 |
+
"step": 3770
|
| 2649 |
+
},
|
| 2650 |
+
{
|
| 2651 |
+
"epoch": 0.09842810148336531,
|
| 2652 |
+
"grad_norm": 0.16387638449668884,
|
| 2653 |
+
"learning_rate": 0.00018436168795942187,
|
| 2654 |
+
"loss": 0.724,
|
| 2655 |
+
"step": 3780
|
| 2656 |
+
},
|
| 2657 |
+
{
|
| 2658 |
+
"epoch": 0.09868849328623135,
|
| 2659 |
+
"grad_norm": 0.1664215326309204,
|
| 2660 |
+
"learning_rate": 0.00018427192466433193,
|
| 2661 |
+
"loss": 0.6955,
|
| 2662 |
+
"step": 3790
|
| 2663 |
+
},
|
| 2664 |
+
{
|
| 2665 |
+
"epoch": 0.0989488850890974,
|
| 2666 |
+
"grad_norm": 0.17285983264446259,
|
| 2667 |
+
"learning_rate": 0.0001841819264699069,
|
| 2668 |
+
"loss": 0.7063,
|
| 2669 |
+
"step": 3800
|
| 2670 |
+
},
|
| 2671 |
+
{
|
| 2672 |
+
"epoch": 0.09920927689196345,
|
| 2673 |
+
"grad_norm": 0.1637914627790451,
|
| 2674 |
+
"learning_rate": 0.00018409169362700753,
|
| 2675 |
+
"loss": 0.7211,
|
| 2676 |
+
"step": 3810
|
| 2677 |
+
},
|
| 2678 |
+
{
|
| 2679 |
+
"epoch": 0.09946966869482948,
|
| 2680 |
+
"grad_norm": 0.1695072054862976,
|
| 2681 |
+
"learning_rate": 0.00018400122638714855,
|
| 2682 |
+
"loss": 0.7172,
|
| 2683 |
+
"step": 3820
|
| 2684 |
+
},
|
| 2685 |
+
{
|
| 2686 |
+
"epoch": 0.09973006049769553,
|
| 2687 |
+
"grad_norm": 0.16097985208034515,
|
| 2688 |
+
"learning_rate": 0.00018391052500249812,
|
| 2689 |
+
"loss": 0.7073,
|
| 2690 |
+
"step": 3830
|
| 2691 |
+
},
|
| 2692 |
+
{
|
| 2693 |
+
"epoch": 0.09999045230056158,
|
| 2694 |
+
"grad_norm": 0.16112865507602692,
|
| 2695 |
+
"learning_rate": 0.00018381958972587707,
|
| 2696 |
+
"loss": 0.7126,
|
| 2697 |
+
"step": 3840
|
| 2698 |
+
},
|
| 2699 |
+
{
|
| 2700 |
+
"epoch": 0.10025084410342762,
|
| 2701 |
+
"grad_norm": 0.16681082546710968,
|
| 2702 |
+
"learning_rate": 0.0001837284208107581,
|
| 2703 |
+
"loss": 0.7331,
|
| 2704 |
+
"step": 3850
|
| 2705 |
+
},
|
| 2706 |
+
{
|
| 2707 |
+
"epoch": 0.10051123590629367,
|
| 2708 |
+
"grad_norm": 0.16337643563747406,
|
| 2709 |
+
"learning_rate": 0.0001836370185112652,
|
| 2710 |
+
"loss": 0.7185,
|
| 2711 |
+
"step": 3860
|
| 2712 |
+
},
|
| 2713 |
+
{
|
| 2714 |
+
"epoch": 0.10077162770915972,
|
| 2715 |
+
"grad_norm": 0.16530117392539978,
|
| 2716 |
+
"learning_rate": 0.0001835453830821729,
|
| 2717 |
+
"loss": 0.7058,
|
| 2718 |
+
"step": 3870
|
| 2719 |
+
},
|
| 2720 |
+
{
|
| 2721 |
+
"epoch": 0.10103201951202576,
|
| 2722 |
+
"grad_norm": 0.1671489030122757,
|
| 2723 |
+
"learning_rate": 0.00018345351477890554,
|
| 2724 |
+
"loss": 0.7225,
|
| 2725 |
+
"step": 3880
|
| 2726 |
+
},
|
| 2727 |
+
{
|
| 2728 |
+
"epoch": 0.1012924113148918,
|
| 2729 |
+
"grad_norm": 0.1631312221288681,
|
| 2730 |
+
"learning_rate": 0.00018336141385753661,
|
| 2731 |
+
"loss": 0.7189,
|
| 2732 |
+
"step": 3890
|
| 2733 |
+
},
|
| 2734 |
+
{
|
| 2735 |
+
"epoch": 0.10155280311775786,
|
| 2736 |
+
"grad_norm": 0.16685089468955994,
|
| 2737 |
+
"learning_rate": 0.00018326908057478795,
|
| 2738 |
+
"loss": 0.7076,
|
| 2739 |
+
"step": 3900
|
| 2740 |
+
},
|
| 2741 |
+
{
|
| 2742 |
+
"epoch": 0.10181319492062389,
|
| 2743 |
+
"grad_norm": 0.16232247650623322,
|
| 2744 |
+
"learning_rate": 0.00018317651518802913,
|
| 2745 |
+
"loss": 0.7168,
|
| 2746 |
+
"step": 3910
|
| 2747 |
+
},
|
| 2748 |
+
{
|
| 2749 |
+
"epoch": 0.10207358672348994,
|
| 2750 |
+
"grad_norm": 0.16136577725410461,
|
| 2751 |
+
"learning_rate": 0.0001830837179552766,
|
| 2752 |
+
"loss": 0.7335,
|
| 2753 |
+
"step": 3920
|
| 2754 |
+
},
|
| 2755 |
+
{
|
| 2756 |
+
"epoch": 0.10233397852635599,
|
| 2757 |
+
"grad_norm": 0.17820622026920319,
|
| 2758 |
+
"learning_rate": 0.00018299068913519312,
|
| 2759 |
+
"loss": 0.7071,
|
| 2760 |
+
"step": 3930
|
| 2761 |
+
},
|
| 2762 |
+
{
|
| 2763 |
+
"epoch": 0.10259437032922204,
|
| 2764 |
+
"grad_norm": 0.15879027545452118,
|
| 2765 |
+
"learning_rate": 0.00018289742898708707,
|
| 2766 |
+
"loss": 0.7301,
|
| 2767 |
+
"step": 3940
|
| 2768 |
+
},
|
| 2769 |
+
{
|
| 2770 |
+
"epoch": 0.10285476213208808,
|
| 2771 |
+
"grad_norm": 0.1569281965494156,
|
| 2772 |
+
"learning_rate": 0.00018280393777091143,
|
| 2773 |
+
"loss": 0.7018,
|
| 2774 |
+
"step": 3950
|
| 2775 |
+
},
|
| 2776 |
+
{
|
| 2777 |
+
"epoch": 0.10311515393495413,
|
| 2778 |
+
"grad_norm": 0.15729983150959015,
|
| 2779 |
+
"learning_rate": 0.00018271021574726336,
|
| 2780 |
+
"loss": 0.717,
|
| 2781 |
+
"step": 3960
|
| 2782 |
+
},
|
| 2783 |
+
{
|
| 2784 |
+
"epoch": 0.10337554573782018,
|
| 2785 |
+
"grad_norm": 0.1715734452009201,
|
| 2786 |
+
"learning_rate": 0.00018261626317738348,
|
| 2787 |
+
"loss": 0.7008,
|
| 2788 |
+
"step": 3970
|
| 2789 |
+
},
|
| 2790 |
+
{
|
| 2791 |
+
"epoch": 0.10363593754068622,
|
| 2792 |
+
"grad_norm": 0.16048088669776917,
|
| 2793 |
+
"learning_rate": 0.00018252208032315482,
|
| 2794 |
+
"loss": 0.7108,
|
| 2795 |
+
"step": 3980
|
| 2796 |
+
},
|
| 2797 |
+
{
|
| 2798 |
+
"epoch": 0.10389632934355227,
|
| 2799 |
+
"grad_norm": 0.1652391403913498,
|
| 2800 |
+
"learning_rate": 0.00018242766744710248,
|
| 2801 |
+
"loss": 0.7164,
|
| 2802 |
+
"step": 3990
|
| 2803 |
+
},
|
| 2804 |
+
{
|
| 2805 |
+
"epoch": 0.10415672114641832,
|
| 2806 |
+
"grad_norm": 0.17617185413837433,
|
| 2807 |
+
"learning_rate": 0.0001823330248123926,
|
| 2808 |
+
"loss": 0.7152,
|
| 2809 |
+
"step": 4000
|
| 2810 |
+
}
|
| 2811 |
+
],
|
| 2812 |
+
"logging_steps": 10,
|
| 2813 |
+
"max_steps": 19202,
|
| 2814 |
+
"num_input_tokens_seen": 0,
|
| 2815 |
+
"num_train_epochs": 1,
|
| 2816 |
+
"save_steps": 500,
|
| 2817 |
+
"stateful_callbacks": {
|
| 2818 |
+
"TrainerControl": {
|
| 2819 |
+
"args": {
|
| 2820 |
+
"should_epoch_stop": false,
|
| 2821 |
+
"should_evaluate": false,
|
| 2822 |
+
"should_log": false,
|
| 2823 |
+
"should_save": true,
|
| 2824 |
+
"should_training_stop": false
|
| 2825 |
+
},
|
| 2826 |
+
"attributes": {}
|
| 2827 |
+
}
|
| 2828 |
+
},
|
| 2829 |
+
"total_flos": 1.87666935054336e+18,
|
| 2830 |
+
"train_batch_size": 5,
|
| 2831 |
+
"trial_name": null,
|
| 2832 |
+
"trial_params": null
|
| 2833 |
+
}
|
checkpoint-4000/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b36cfb63c6def28c162a2b6861063a037833f0f4cca8b4264eca4ae4af09f403
|
| 3 |
+
size 5240
|