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/added_tokens.json +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 +1759 -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 |
+
base_model: openchat/openchat-3.5-0106-gemma
|
| 3 |
+
library_name: peft
|
| 4 |
+
---
|
| 5 |
+
|
| 6 |
+
# Model Card for Model ID
|
| 7 |
+
|
| 8 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
| 9 |
+
|
| 10 |
+
|
| 11 |
+
|
| 12 |
+
## Model Details
|
| 13 |
+
|
| 14 |
+
### Model Description
|
| 15 |
+
|
| 16 |
+
<!-- Provide a longer summary of what this model is. -->
|
| 17 |
+
|
| 18 |
+
|
| 19 |
+
|
| 20 |
+
- **Developed by:** [More Information Needed]
|
| 21 |
+
- **Funded by [optional]:** [More Information Needed]
|
| 22 |
+
- **Shared by [optional]:** [More Information Needed]
|
| 23 |
+
- **Model type:** [More Information Needed]
|
| 24 |
+
- **Language(s) (NLP):** [More Information Needed]
|
| 25 |
+
- **License:** [More Information Needed]
|
| 26 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
| 27 |
+
|
| 28 |
+
### Model Sources [optional]
|
| 29 |
+
|
| 30 |
+
<!-- Provide the basic links for the model. -->
|
| 31 |
+
|
| 32 |
+
- **Repository:** [More Information Needed]
|
| 33 |
+
- **Paper [optional]:** [More Information Needed]
|
| 34 |
+
- **Demo [optional]:** [More Information Needed]
|
| 35 |
+
|
| 36 |
+
## Uses
|
| 37 |
+
|
| 38 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
| 39 |
+
|
| 40 |
+
### Direct Use
|
| 41 |
+
|
| 42 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
| 43 |
+
|
| 44 |
+
[More Information Needed]
|
| 45 |
+
|
| 46 |
+
### Downstream Use [optional]
|
| 47 |
+
|
| 48 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
| 49 |
+
|
| 50 |
+
[More Information Needed]
|
| 51 |
+
|
| 52 |
+
### Out-of-Scope Use
|
| 53 |
+
|
| 54 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
| 55 |
+
|
| 56 |
+
[More Information Needed]
|
| 57 |
+
|
| 58 |
+
## Bias, Risks, and Limitations
|
| 59 |
+
|
| 60 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
| 61 |
+
|
| 62 |
+
[More Information Needed]
|
| 63 |
+
|
| 64 |
+
### Recommendations
|
| 65 |
+
|
| 66 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
| 67 |
+
|
| 68 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
| 69 |
+
|
| 70 |
+
## How to Get Started with the Model
|
| 71 |
+
|
| 72 |
+
Use the code below to get started with the model.
|
| 73 |
+
|
| 74 |
+
[More Information Needed]
|
| 75 |
+
|
| 76 |
+
## Training Details
|
| 77 |
+
|
| 78 |
+
### Training Data
|
| 79 |
+
|
| 80 |
+
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
| 81 |
+
|
| 82 |
+
[More Information Needed]
|
| 83 |
+
|
| 84 |
+
### Training Procedure
|
| 85 |
+
|
| 86 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
| 87 |
+
|
| 88 |
+
#### Preprocessing [optional]
|
| 89 |
+
|
| 90 |
+
[More Information Needed]
|
| 91 |
+
|
| 92 |
+
|
| 93 |
+
#### Training Hyperparameters
|
| 94 |
+
|
| 95 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
| 96 |
+
|
| 97 |
+
#### Speeds, Sizes, Times [optional]
|
| 98 |
+
|
| 99 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
| 100 |
+
|
| 101 |
+
[More Information Needed]
|
| 102 |
+
|
| 103 |
+
## Evaluation
|
| 104 |
+
|
| 105 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
| 106 |
+
|
| 107 |
+
### Testing Data, Factors & Metrics
|
| 108 |
+
|
| 109 |
+
#### Testing Data
|
| 110 |
+
|
| 111 |
+
<!-- This should link to a Dataset Card if possible. -->
|
| 112 |
+
|
| 113 |
+
[More Information Needed]
|
| 114 |
+
|
| 115 |
+
#### Factors
|
| 116 |
+
|
| 117 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
| 118 |
+
|
| 119 |
+
[More Information Needed]
|
| 120 |
+
|
| 121 |
+
#### Metrics
|
| 122 |
+
|
| 123 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
| 124 |
+
|
| 125 |
+
[More Information Needed]
|
| 126 |
+
|
| 127 |
+
### Results
|
| 128 |
+
|
| 129 |
+
[More Information Needed]
|
| 130 |
+
|
| 131 |
+
#### Summary
|
| 132 |
+
|
| 133 |
+
|
| 134 |
+
|
| 135 |
+
## Model Examination [optional]
|
| 136 |
+
|
| 137 |
+
<!-- Relevant interpretability work for the model goes here -->
|
| 138 |
+
|
| 139 |
+
[More Information Needed]
|
| 140 |
+
|
| 141 |
+
## Environmental Impact
|
| 142 |
+
|
| 143 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
| 144 |
+
|
| 145 |
+
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
| 146 |
+
|
| 147 |
+
- **Hardware Type:** [More Information Needed]
|
| 148 |
+
- **Hours used:** [More Information Needed]
|
| 149 |
+
- **Cloud Provider:** [More Information Needed]
|
| 150 |
+
- **Compute Region:** [More Information Needed]
|
| 151 |
+
- **Carbon Emitted:** [More Information Needed]
|
| 152 |
+
|
| 153 |
+
## Technical Specifications [optional]
|
| 154 |
+
|
| 155 |
+
### Model Architecture and Objective
|
| 156 |
+
|
| 157 |
+
[More Information Needed]
|
| 158 |
+
|
| 159 |
+
### Compute Infrastructure
|
| 160 |
+
|
| 161 |
+
[More Information Needed]
|
| 162 |
+
|
| 163 |
+
#### Hardware
|
| 164 |
+
|
| 165 |
+
[More Information Needed]
|
| 166 |
+
|
| 167 |
+
#### Software
|
| 168 |
+
|
| 169 |
+
[More Information Needed]
|
| 170 |
+
|
| 171 |
+
## Citation [optional]
|
| 172 |
+
|
| 173 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
| 174 |
+
|
| 175 |
+
**BibTeX:**
|
| 176 |
+
|
| 177 |
+
[More Information Needed]
|
| 178 |
+
|
| 179 |
+
**APA:**
|
| 180 |
+
|
| 181 |
+
[More Information Needed]
|
| 182 |
+
|
| 183 |
+
## Glossary [optional]
|
| 184 |
+
|
| 185 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
| 186 |
+
|
| 187 |
+
[More Information Needed]
|
| 188 |
+
|
| 189 |
+
## More Information [optional]
|
| 190 |
+
|
| 191 |
+
[More Information Needed]
|
| 192 |
+
|
| 193 |
+
## Model Card Authors [optional]
|
| 194 |
+
|
| 195 |
+
[More Information Needed]
|
| 196 |
+
|
| 197 |
+
## Model Card Contact
|
| 198 |
+
|
| 199 |
+
[More Information Needed]
|
| 200 |
+
### Framework versions
|
| 201 |
+
|
| 202 |
+
- PEFT 0.11.1
|
checkpoint-4000/adapter_config.json
ADDED
|
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "openchat/openchat-3.5-0106-gemma",
|
| 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 |
+
"v_proj",
|
| 24 |
+
"k_proj",
|
| 25 |
+
"down_proj",
|
| 26 |
+
"up_proj",
|
| 27 |
+
"gate_proj",
|
| 28 |
+
"q_proj",
|
| 29 |
+
"o_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 sha256:2826755cb7a00d016a5a12ce9f256d508b17b7502e6f204951fa8d265d3f7b34
|
| 3 |
+
size 400084608
|
checkpoint-4000/added_tokens.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"<eos>": 255999
|
| 3 |
+
}
|
checkpoint-4000/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fef6cd37c352874bd0b3910a8e83338e02baf8cc98245a2b2008fd2cbefd2cee
|
| 3 |
+
size 800301754
|
checkpoint-4000/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e8134bcd73fd74cdb29499e4ebb40d8e345c2ed74d26769e5f739442e242daaf
|
| 3 |
+
size 14244
|
checkpoint-4000/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d76687f3512febcbd1f79fec0db44288cff19a74825789c2268a08487546cdce
|
| 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": "<end_of_turn>",
|
| 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:dd301b36064ce277bd2b463a414e956a7e8883ab6fd8ed22e59ebf11ae5dcf60
|
| 3 |
+
size 17518425
|
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 +1,1759 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
"2": {
|
| 14 |
+
"content": "<bos>",
|
| 15 |
+
"lstrip": false,
|
| 16 |
+
"normalized": false,
|
| 17 |
+
"rstrip": false,
|
| 18 |
+
"single_word": false,
|
| 19 |
+
"special": true
|
| 20 |
+
},
|
| 21 |
+
"3": {
|
| 22 |
+
"content": "<unk>",
|
| 23 |
+
"lstrip": false,
|
| 24 |
+
"normalized": false,
|
| 25 |
+
"rstrip": false,
|
| 26 |
+
"single_word": false,
|
| 27 |
+
"special": true
|
| 28 |
+
},
|
| 29 |
+
"4": {
|
| 30 |
+
"content": "<mask>",
|
| 31 |
+
"lstrip": false,
|
| 32 |
+
"normalized": true,
|
| 33 |
+
"rstrip": false,
|
| 34 |
+
"single_word": false,
|
| 35 |
+
"special": false
|
| 36 |
+
},
|
| 37 |
+
"5": {
|
| 38 |
+
"content": "<2mass>",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": true,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false,
|
| 43 |
+
"special": false
|
| 44 |
+
},
|
| 45 |
+
"6": {
|
| 46 |
+
"content": "[@BOS@]",
|
| 47 |
+
"lstrip": false,
|
| 48 |
+
"normalized": true,
|
| 49 |
+
"rstrip": false,
|
| 50 |
+
"single_word": false,
|
| 51 |
+
"special": false
|
| 52 |
+
},
|
| 53 |
+
"7": {
|
| 54 |
+
"content": "<unused0>",
|
| 55 |
+
"lstrip": false,
|
| 56 |
+
"normalized": true,
|
| 57 |
+
"rstrip": false,
|
| 58 |
+
"single_word": false,
|
| 59 |
+
"special": false
|
| 60 |
+
},
|
| 61 |
+
"8": {
|
| 62 |
+
"content": "<unused1>",
|
| 63 |
+
"lstrip": false,
|
| 64 |
+
"normalized": true,
|
| 65 |
+
"rstrip": false,
|
| 66 |
+
"single_word": false,
|
| 67 |
+
"special": false
|
| 68 |
+
},
|
| 69 |
+
"9": {
|
| 70 |
+
"content": "<unused2>",
|
| 71 |
+
"lstrip": false,
|
| 72 |
+
"normalized": true,
|
| 73 |
+
"rstrip": false,
|
| 74 |
+
"single_word": false,
|
| 75 |
+
"special": false
|
| 76 |
+
},
|
| 77 |
+
"10": {
|
| 78 |
+
"content": "<unused3>",
|
| 79 |
+
"lstrip": false,
|
| 80 |
+
"normalized": true,
|
| 81 |
+
"rstrip": false,
|
| 82 |
+
"single_word": false,
|
| 83 |
+
"special": false
|
| 84 |
+
},
|
| 85 |
+
"11": {
|
| 86 |
+
"content": "<unused4>",
|
| 87 |
+
"lstrip": false,
|
| 88 |
+
"normalized": true,
|
| 89 |
+
"rstrip": false,
|
| 90 |
+
"single_word": false,
|
| 91 |
+
"special": false
|
| 92 |
+
},
|
| 93 |
+
"12": {
|
| 94 |
+
"content": "<unused5>",
|
| 95 |
+
"lstrip": false,
|
| 96 |
+
"normalized": true,
|
| 97 |
+
"rstrip": false,
|
| 98 |
+
"single_word": false,
|
| 99 |
+
"special": false
|
| 100 |
+
},
|
| 101 |
+
"13": {
|
| 102 |
+
"content": "<unused6>",
|
| 103 |
+
"lstrip": false,
|
| 104 |
+
"normalized": true,
|
| 105 |
+
"rstrip": false,
|
| 106 |
+
"single_word": false,
|
| 107 |
+
"special": false
|
| 108 |
+
},
|
| 109 |
+
"14": {
|
| 110 |
+
"content": "<unused7>",
|
| 111 |
+
"lstrip": false,
|
| 112 |
+
"normalized": true,
|
| 113 |
+
"rstrip": false,
|
| 114 |
+
"single_word": false,
|
| 115 |
+
"special": false
|
| 116 |
+
},
|
| 117 |
+
"15": {
|
| 118 |
+
"content": "<unused8>",
|
| 119 |
+
"lstrip": false,
|
| 120 |
+
"normalized": true,
|
| 121 |
+
"rstrip": false,
|
| 122 |
+
"single_word": false,
|
| 123 |
+
"special": false
|
| 124 |
+
},
|
| 125 |
+
"16": {
|
| 126 |
+
"content": "<unused9>",
|
| 127 |
+
"lstrip": false,
|
| 128 |
+
"normalized": true,
|
| 129 |
+
"rstrip": false,
|
| 130 |
+
"single_word": false,
|
| 131 |
+
"special": false
|
| 132 |
+
},
|
| 133 |
+
"17": {
|
| 134 |
+
"content": "<unused10>",
|
| 135 |
+
"lstrip": false,
|
| 136 |
+
"normalized": true,
|
| 137 |
+
"rstrip": false,
|
| 138 |
+
"single_word": false,
|
| 139 |
+
"special": false
|
| 140 |
+
},
|
| 141 |
+
"18": {
|
| 142 |
+
"content": "<unused11>",
|
| 143 |
+
"lstrip": false,
|
| 144 |
+
"normalized": true,
|
| 145 |
+
"rstrip": false,
|
| 146 |
+
"single_word": false,
|
| 147 |
+
"special": false
|
| 148 |
+
},
|
| 149 |
+
"19": {
|
| 150 |
+
"content": "<unused12>",
|
| 151 |
+
"lstrip": false,
|
| 152 |
+
"normalized": true,
|
| 153 |
+
"rstrip": false,
|
| 154 |
+
"single_word": false,
|
| 155 |
+
"special": false
|
| 156 |
+
},
|
| 157 |
+
"20": {
|
| 158 |
+
"content": "<unused13>",
|
| 159 |
+
"lstrip": false,
|
| 160 |
+
"normalized": true,
|
| 161 |
+
"rstrip": false,
|
| 162 |
+
"single_word": false,
|
| 163 |
+
"special": false
|
| 164 |
+
},
|
| 165 |
+
"21": {
|
| 166 |
+
"content": "<unused14>",
|
| 167 |
+
"lstrip": false,
|
| 168 |
+
"normalized": true,
|
| 169 |
+
"rstrip": false,
|
| 170 |
+
"single_word": false,
|
| 171 |
+
"special": false
|
| 172 |
+
},
|
| 173 |
+
"22": {
|
| 174 |
+
"content": "<unused15>",
|
| 175 |
+
"lstrip": false,
|
| 176 |
+
"normalized": true,
|
| 177 |
+
"rstrip": false,
|
| 178 |
+
"single_word": false,
|
| 179 |
+
"special": false
|
| 180 |
+
},
|
| 181 |
+
"23": {
|
| 182 |
+
"content": "<unused16>",
|
| 183 |
+
"lstrip": false,
|
| 184 |
+
"normalized": true,
|
| 185 |
+
"rstrip": false,
|
| 186 |
+
"single_word": false,
|
| 187 |
+
"special": false
|
| 188 |
+
},
|
| 189 |
+
"24": {
|
| 190 |
+
"content": "<unused17>",
|
| 191 |
+
"lstrip": false,
|
| 192 |
+
"normalized": true,
|
| 193 |
+
"rstrip": false,
|
| 194 |
+
"single_word": false,
|
| 195 |
+
"special": false
|
| 196 |
+
},
|
| 197 |
+
"25": {
|
| 198 |
+
"content": "<unused18>",
|
| 199 |
+
"lstrip": false,
|
| 200 |
+
"normalized": true,
|
| 201 |
+
"rstrip": false,
|
| 202 |
+
"single_word": false,
|
| 203 |
+
"special": false
|
| 204 |
+
},
|
| 205 |
+
"26": {
|
| 206 |
+
"content": "<unused19>",
|
| 207 |
+
"lstrip": false,
|
| 208 |
+
"normalized": true,
|
| 209 |
+
"rstrip": false,
|
| 210 |
+
"single_word": false,
|
| 211 |
+
"special": false
|
| 212 |
+
},
|
| 213 |
+
"27": {
|
| 214 |
+
"content": "<unused20>",
|
| 215 |
+
"lstrip": false,
|
| 216 |
+
"normalized": true,
|
| 217 |
+
"rstrip": false,
|
| 218 |
+
"single_word": false,
|
| 219 |
+
"special": false
|
| 220 |
+
},
|
| 221 |
+
"28": {
|
| 222 |
+
"content": "<unused21>",
|
| 223 |
+
"lstrip": false,
|
| 224 |
+
"normalized": true,
|
| 225 |
+
"rstrip": false,
|
| 226 |
+
"single_word": false,
|
| 227 |
+
"special": false
|
| 228 |
+
},
|
| 229 |
+
"29": {
|
| 230 |
+
"content": "<unused22>",
|
| 231 |
+
"lstrip": false,
|
| 232 |
+
"normalized": true,
|
| 233 |
+
"rstrip": false,
|
| 234 |
+
"single_word": false,
|
| 235 |
+
"special": false
|
| 236 |
+
},
|
| 237 |
+
"30": {
|
| 238 |
+
"content": "<unused23>",
|
| 239 |
+
"lstrip": false,
|
| 240 |
+
"normalized": true,
|
| 241 |
+
"rstrip": false,
|
| 242 |
+
"single_word": false,
|
| 243 |
+
"special": false
|
| 244 |
+
},
|
| 245 |
+
"31": {
|
| 246 |
+
"content": "<unused24>",
|
| 247 |
+
"lstrip": false,
|
| 248 |
+
"normalized": true,
|
| 249 |
+
"rstrip": false,
|
| 250 |
+
"single_word": false,
|
| 251 |
+
"special": false
|
| 252 |
+
},
|
| 253 |
+
"32": {
|
| 254 |
+
"content": "<unused25>",
|
| 255 |
+
"lstrip": false,
|
| 256 |
+
"normalized": true,
|
| 257 |
+
"rstrip": false,
|
| 258 |
+
"single_word": false,
|
| 259 |
+
"special": false
|
| 260 |
+
},
|
| 261 |
+
"33": {
|
| 262 |
+
"content": "<unused26>",
|
| 263 |
+
"lstrip": false,
|
| 264 |
+
"normalized": true,
|
| 265 |
+
"rstrip": false,
|
| 266 |
+
"single_word": false,
|
| 267 |
+
"special": false
|
| 268 |
+
},
|
| 269 |
+
"34": {
|
| 270 |
+
"content": "<unused27>",
|
| 271 |
+
"lstrip": false,
|
| 272 |
+
"normalized": true,
|
| 273 |
+
"rstrip": false,
|
| 274 |
+
"single_word": false,
|
| 275 |
+
"special": false
|
| 276 |
+
},
|
| 277 |
+
"35": {
|
| 278 |
+
"content": "<unused28>",
|
| 279 |
+
"lstrip": false,
|
| 280 |
+
"normalized": true,
|
| 281 |
+
"rstrip": false,
|
| 282 |
+
"single_word": false,
|
| 283 |
+
"special": false
|
| 284 |
+
},
|
| 285 |
+
"36": {
|
| 286 |
+
"content": "<unused29>",
|
| 287 |
+
"lstrip": false,
|
| 288 |
+
"normalized": true,
|
| 289 |
+
"rstrip": false,
|
| 290 |
+
"single_word": false,
|
| 291 |
+
"special": false
|
| 292 |
+
},
|
| 293 |
+
"37": {
|
| 294 |
+
"content": "<unused30>",
|
| 295 |
+
"lstrip": false,
|
| 296 |
+
"normalized": true,
|
| 297 |
+
"rstrip": false,
|
| 298 |
+
"single_word": false,
|
| 299 |
+
"special": false
|
| 300 |
+
},
|
| 301 |
+
"38": {
|
| 302 |
+
"content": "<unused31>",
|
| 303 |
+
"lstrip": false,
|
| 304 |
+
"normalized": true,
|
| 305 |
+
"rstrip": false,
|
| 306 |
+
"single_word": false,
|
| 307 |
+
"special": false
|
| 308 |
+
},
|
| 309 |
+
"39": {
|
| 310 |
+
"content": "<unused32>",
|
| 311 |
+
"lstrip": false,
|
| 312 |
+
"normalized": true,
|
| 313 |
+
"rstrip": false,
|
| 314 |
+
"single_word": false,
|
| 315 |
+
"special": false
|
| 316 |
+
},
|
| 317 |
+
"40": {
|
| 318 |
+
"content": "<unused33>",
|
| 319 |
+
"lstrip": false,
|
| 320 |
+
"normalized": true,
|
| 321 |
+
"rstrip": false,
|
| 322 |
+
"single_word": false,
|
| 323 |
+
"special": false
|
| 324 |
+
},
|
| 325 |
+
"41": {
|
| 326 |
+
"content": "<unused34>",
|
| 327 |
+
"lstrip": false,
|
| 328 |
+
"normalized": true,
|
| 329 |
+
"rstrip": false,
|
| 330 |
+
"single_word": false,
|
| 331 |
+
"special": false
|
| 332 |
+
},
|
| 333 |
+
"42": {
|
| 334 |
+
"content": "<unused35>",
|
| 335 |
+
"lstrip": false,
|
| 336 |
+
"normalized": true,
|
| 337 |
+
"rstrip": false,
|
| 338 |
+
"single_word": false,
|
| 339 |
+
"special": false
|
| 340 |
+
},
|
| 341 |
+
"43": {
|
| 342 |
+
"content": "<unused36>",
|
| 343 |
+
"lstrip": false,
|
| 344 |
+
"normalized": true,
|
| 345 |
+
"rstrip": false,
|
| 346 |
+
"single_word": false,
|
| 347 |
+
"special": false
|
| 348 |
+
},
|
| 349 |
+
"44": {
|
| 350 |
+
"content": "<unused37>",
|
| 351 |
+
"lstrip": false,
|
| 352 |
+
"normalized": true,
|
| 353 |
+
"rstrip": false,
|
| 354 |
+
"single_word": false,
|
| 355 |
+
"special": false
|
| 356 |
+
},
|
| 357 |
+
"45": {
|
| 358 |
+
"content": "<unused38>",
|
| 359 |
+
"lstrip": false,
|
| 360 |
+
"normalized": true,
|
| 361 |
+
"rstrip": false,
|
| 362 |
+
"single_word": false,
|
| 363 |
+
"special": false
|
| 364 |
+
},
|
| 365 |
+
"46": {
|
| 366 |
+
"content": "<unused39>",
|
| 367 |
+
"lstrip": false,
|
| 368 |
+
"normalized": true,
|
| 369 |
+
"rstrip": false,
|
| 370 |
+
"single_word": false,
|
| 371 |
+
"special": false
|
| 372 |
+
},
|
| 373 |
+
"47": {
|
| 374 |
+
"content": "<unused40>",
|
| 375 |
+
"lstrip": false,
|
| 376 |
+
"normalized": true,
|
| 377 |
+
"rstrip": false,
|
| 378 |
+
"single_word": false,
|
| 379 |
+
"special": false
|
| 380 |
+
},
|
| 381 |
+
"48": {
|
| 382 |
+
"content": "<unused41>",
|
| 383 |
+
"lstrip": false,
|
| 384 |
+
"normalized": true,
|
| 385 |
+
"rstrip": false,
|
| 386 |
+
"single_word": false,
|
| 387 |
+
"special": false
|
| 388 |
+
},
|
| 389 |
+
"49": {
|
| 390 |
+
"content": "<unused42>",
|
| 391 |
+
"lstrip": false,
|
| 392 |
+
"normalized": true,
|
| 393 |
+
"rstrip": false,
|
| 394 |
+
"single_word": false,
|
| 395 |
+
"special": false
|
| 396 |
+
},
|
| 397 |
+
"50": {
|
| 398 |
+
"content": "<unused43>",
|
| 399 |
+
"lstrip": false,
|
| 400 |
+
"normalized": true,
|
| 401 |
+
"rstrip": false,
|
| 402 |
+
"single_word": false,
|
| 403 |
+
"special": false
|
| 404 |
+
},
|
| 405 |
+
"51": {
|
| 406 |
+
"content": "<unused44>",
|
| 407 |
+
"lstrip": false,
|
| 408 |
+
"normalized": true,
|
| 409 |
+
"rstrip": false,
|
| 410 |
+
"single_word": false,
|
| 411 |
+
"special": false
|
| 412 |
+
},
|
| 413 |
+
"52": {
|
| 414 |
+
"content": "<unused45>",
|
| 415 |
+
"lstrip": false,
|
| 416 |
+
"normalized": true,
|
| 417 |
+
"rstrip": false,
|
| 418 |
+
"single_word": false,
|
| 419 |
+
"special": false
|
| 420 |
+
},
|
| 421 |
+
"53": {
|
| 422 |
+
"content": "<unused46>",
|
| 423 |
+
"lstrip": false,
|
| 424 |
+
"normalized": true,
|
| 425 |
+
"rstrip": false,
|
| 426 |
+
"single_word": false,
|
| 427 |
+
"special": false
|
| 428 |
+
},
|
| 429 |
+
"54": {
|
| 430 |
+
"content": "<unused47>",
|
| 431 |
+
"lstrip": false,
|
| 432 |
+
"normalized": true,
|
| 433 |
+
"rstrip": false,
|
| 434 |
+
"single_word": false,
|
| 435 |
+
"special": false
|
| 436 |
+
},
|
| 437 |
+
"55": {
|
| 438 |
+
"content": "<unused48>",
|
| 439 |
+
"lstrip": false,
|
| 440 |
+
"normalized": true,
|
| 441 |
+
"rstrip": false,
|
| 442 |
+
"single_word": false,
|
| 443 |
+
"special": false
|
| 444 |
+
},
|
| 445 |
+
"56": {
|
| 446 |
+
"content": "<unused49>",
|
| 447 |
+
"lstrip": false,
|
| 448 |
+
"normalized": true,
|
| 449 |
+
"rstrip": false,
|
| 450 |
+
"single_word": false,
|
| 451 |
+
"special": false
|
| 452 |
+
},
|
| 453 |
+
"57": {
|
| 454 |
+
"content": "<unused50>",
|
| 455 |
+
"lstrip": false,
|
| 456 |
+
"normalized": true,
|
| 457 |
+
"rstrip": false,
|
| 458 |
+
"single_word": false,
|
| 459 |
+
"special": false
|
| 460 |
+
},
|
| 461 |
+
"58": {
|
| 462 |
+
"content": "<unused51>",
|
| 463 |
+
"lstrip": false,
|
| 464 |
+
"normalized": true,
|
| 465 |
+
"rstrip": false,
|
| 466 |
+
"single_word": false,
|
| 467 |
+
"special": false
|
| 468 |
+
},
|
| 469 |
+
"59": {
|
| 470 |
+
"content": "<unused52>",
|
| 471 |
+
"lstrip": false,
|
| 472 |
+
"normalized": true,
|
| 473 |
+
"rstrip": false,
|
| 474 |
+
"single_word": false,
|
| 475 |
+
"special": false
|
| 476 |
+
},
|
| 477 |
+
"60": {
|
| 478 |
+
"content": "<unused53>",
|
| 479 |
+
"lstrip": false,
|
| 480 |
+
"normalized": true,
|
| 481 |
+
"rstrip": false,
|
| 482 |
+
"single_word": false,
|
| 483 |
+
"special": false
|
| 484 |
+
},
|
| 485 |
+
"61": {
|
| 486 |
+
"content": "<unused54>",
|
| 487 |
+
"lstrip": false,
|
| 488 |
+
"normalized": true,
|
| 489 |
+
"rstrip": false,
|
| 490 |
+
"single_word": false,
|
| 491 |
+
"special": false
|
| 492 |
+
},
|
| 493 |
+
"62": {
|
| 494 |
+
"content": "<unused55>",
|
| 495 |
+
"lstrip": false,
|
| 496 |
+
"normalized": true,
|
| 497 |
+
"rstrip": false,
|
| 498 |
+
"single_word": false,
|
| 499 |
+
"special": false
|
| 500 |
+
},
|
| 501 |
+
"63": {
|
| 502 |
+
"content": "<unused56>",
|
| 503 |
+
"lstrip": false,
|
| 504 |
+
"normalized": true,
|
| 505 |
+
"rstrip": false,
|
| 506 |
+
"single_word": false,
|
| 507 |
+
"special": false
|
| 508 |
+
},
|
| 509 |
+
"64": {
|
| 510 |
+
"content": "<unused57>",
|
| 511 |
+
"lstrip": false,
|
| 512 |
+
"normalized": true,
|
| 513 |
+
"rstrip": false,
|
| 514 |
+
"single_word": false,
|
| 515 |
+
"special": false
|
| 516 |
+
},
|
| 517 |
+
"65": {
|
| 518 |
+
"content": "<unused58>",
|
| 519 |
+
"lstrip": false,
|
| 520 |
+
"normalized": true,
|
| 521 |
+
"rstrip": false,
|
| 522 |
+
"single_word": false,
|
| 523 |
+
"special": false
|
| 524 |
+
},
|
| 525 |
+
"66": {
|
| 526 |
+
"content": "<unused59>",
|
| 527 |
+
"lstrip": false,
|
| 528 |
+
"normalized": true,
|
| 529 |
+
"rstrip": false,
|
| 530 |
+
"single_word": false,
|
| 531 |
+
"special": false
|
| 532 |
+
},
|
| 533 |
+
"67": {
|
| 534 |
+
"content": "<unused60>",
|
| 535 |
+
"lstrip": false,
|
| 536 |
+
"normalized": true,
|
| 537 |
+
"rstrip": false,
|
| 538 |
+
"single_word": false,
|
| 539 |
+
"special": false
|
| 540 |
+
},
|
| 541 |
+
"68": {
|
| 542 |
+
"content": "<unused61>",
|
| 543 |
+
"lstrip": false,
|
| 544 |
+
"normalized": true,
|
| 545 |
+
"rstrip": false,
|
| 546 |
+
"single_word": false,
|
| 547 |
+
"special": false
|
| 548 |
+
},
|
| 549 |
+
"69": {
|
| 550 |
+
"content": "<unused62>",
|
| 551 |
+
"lstrip": false,
|
| 552 |
+
"normalized": true,
|
| 553 |
+
"rstrip": false,
|
| 554 |
+
"single_word": false,
|
| 555 |
+
"special": false
|
| 556 |
+
},
|
| 557 |
+
"70": {
|
| 558 |
+
"content": "<unused63>",
|
| 559 |
+
"lstrip": false,
|
| 560 |
+
"normalized": true,
|
| 561 |
+
"rstrip": false,
|
| 562 |
+
"single_word": false,
|
| 563 |
+
"special": false
|
| 564 |
+
},
|
| 565 |
+
"71": {
|
| 566 |
+
"content": "<unused64>",
|
| 567 |
+
"lstrip": false,
|
| 568 |
+
"normalized": true,
|
| 569 |
+
"rstrip": false,
|
| 570 |
+
"single_word": false,
|
| 571 |
+
"special": false
|
| 572 |
+
},
|
| 573 |
+
"72": {
|
| 574 |
+
"content": "<unused65>",
|
| 575 |
+
"lstrip": false,
|
| 576 |
+
"normalized": true,
|
| 577 |
+
"rstrip": false,
|
| 578 |
+
"single_word": false,
|
| 579 |
+
"special": false
|
| 580 |
+
},
|
| 581 |
+
"73": {
|
| 582 |
+
"content": "<unused66>",
|
| 583 |
+
"lstrip": false,
|
| 584 |
+
"normalized": true,
|
| 585 |
+
"rstrip": false,
|
| 586 |
+
"single_word": false,
|
| 587 |
+
"special": false
|
| 588 |
+
},
|
| 589 |
+
"74": {
|
| 590 |
+
"content": "<unused67>",
|
| 591 |
+
"lstrip": false,
|
| 592 |
+
"normalized": true,
|
| 593 |
+
"rstrip": false,
|
| 594 |
+
"single_word": false,
|
| 595 |
+
"special": false
|
| 596 |
+
},
|
| 597 |
+
"75": {
|
| 598 |
+
"content": "<unused68>",
|
| 599 |
+
"lstrip": false,
|
| 600 |
+
"normalized": true,
|
| 601 |
+
"rstrip": false,
|
| 602 |
+
"single_word": false,
|
| 603 |
+
"special": false
|
| 604 |
+
},
|
| 605 |
+
"76": {
|
| 606 |
+
"content": "<unused69>",
|
| 607 |
+
"lstrip": false,
|
| 608 |
+
"normalized": true,
|
| 609 |
+
"rstrip": false,
|
| 610 |
+
"single_word": false,
|
| 611 |
+
"special": false
|
| 612 |
+
},
|
| 613 |
+
"77": {
|
| 614 |
+
"content": "<unused70>",
|
| 615 |
+
"lstrip": false,
|
| 616 |
+
"normalized": true,
|
| 617 |
+
"rstrip": false,
|
| 618 |
+
"single_word": false,
|
| 619 |
+
"special": false
|
| 620 |
+
},
|
| 621 |
+
"78": {
|
| 622 |
+
"content": "<unused71>",
|
| 623 |
+
"lstrip": false,
|
| 624 |
+
"normalized": true,
|
| 625 |
+
"rstrip": false,
|
| 626 |
+
"single_word": false,
|
| 627 |
+
"special": false
|
| 628 |
+
},
|
| 629 |
+
"79": {
|
| 630 |
+
"content": "<unused72>",
|
| 631 |
+
"lstrip": false,
|
| 632 |
+
"normalized": true,
|
| 633 |
+
"rstrip": false,
|
| 634 |
+
"single_word": false,
|
| 635 |
+
"special": false
|
| 636 |
+
},
|
| 637 |
+
"80": {
|
| 638 |
+
"content": "<unused73>",
|
| 639 |
+
"lstrip": false,
|
| 640 |
+
"normalized": true,
|
| 641 |
+
"rstrip": false,
|
| 642 |
+
"single_word": false,
|
| 643 |
+
"special": false
|
| 644 |
+
},
|
| 645 |
+
"81": {
|
| 646 |
+
"content": "<unused74>",
|
| 647 |
+
"lstrip": false,
|
| 648 |
+
"normalized": true,
|
| 649 |
+
"rstrip": false,
|
| 650 |
+
"single_word": false,
|
| 651 |
+
"special": false
|
| 652 |
+
},
|
| 653 |
+
"82": {
|
| 654 |
+
"content": "<unused75>",
|
| 655 |
+
"lstrip": false,
|
| 656 |
+
"normalized": true,
|
| 657 |
+
"rstrip": false,
|
| 658 |
+
"single_word": false,
|
| 659 |
+
"special": false
|
| 660 |
+
},
|
| 661 |
+
"83": {
|
| 662 |
+
"content": "<unused76>",
|
| 663 |
+
"lstrip": false,
|
| 664 |
+
"normalized": true,
|
| 665 |
+
"rstrip": false,
|
| 666 |
+
"single_word": false,
|
| 667 |
+
"special": false
|
| 668 |
+
},
|
| 669 |
+
"84": {
|
| 670 |
+
"content": "<unused77>",
|
| 671 |
+
"lstrip": false,
|
| 672 |
+
"normalized": true,
|
| 673 |
+
"rstrip": false,
|
| 674 |
+
"single_word": false,
|
| 675 |
+
"special": false
|
| 676 |
+
},
|
| 677 |
+
"85": {
|
| 678 |
+
"content": "<unused78>",
|
| 679 |
+
"lstrip": false,
|
| 680 |
+
"normalized": true,
|
| 681 |
+
"rstrip": false,
|
| 682 |
+
"single_word": false,
|
| 683 |
+
"special": false
|
| 684 |
+
},
|
| 685 |
+
"86": {
|
| 686 |
+
"content": "<unused79>",
|
| 687 |
+
"lstrip": false,
|
| 688 |
+
"normalized": true,
|
| 689 |
+
"rstrip": false,
|
| 690 |
+
"single_word": false,
|
| 691 |
+
"special": false
|
| 692 |
+
},
|
| 693 |
+
"87": {
|
| 694 |
+
"content": "<unused80>",
|
| 695 |
+
"lstrip": false,
|
| 696 |
+
"normalized": true,
|
| 697 |
+
"rstrip": false,
|
| 698 |
+
"single_word": false,
|
| 699 |
+
"special": false
|
| 700 |
+
},
|
| 701 |
+
"88": {
|
| 702 |
+
"content": "<unused81>",
|
| 703 |
+
"lstrip": false,
|
| 704 |
+
"normalized": true,
|
| 705 |
+
"rstrip": false,
|
| 706 |
+
"single_word": false,
|
| 707 |
+
"special": false
|
| 708 |
+
},
|
| 709 |
+
"89": {
|
| 710 |
+
"content": "<unused82>",
|
| 711 |
+
"lstrip": false,
|
| 712 |
+
"normalized": true,
|
| 713 |
+
"rstrip": false,
|
| 714 |
+
"single_word": false,
|
| 715 |
+
"special": false
|
| 716 |
+
},
|
| 717 |
+
"90": {
|
| 718 |
+
"content": "<unused83>",
|
| 719 |
+
"lstrip": false,
|
| 720 |
+
"normalized": true,
|
| 721 |
+
"rstrip": false,
|
| 722 |
+
"single_word": false,
|
| 723 |
+
"special": false
|
| 724 |
+
},
|
| 725 |
+
"91": {
|
| 726 |
+
"content": "<unused84>",
|
| 727 |
+
"lstrip": false,
|
| 728 |
+
"normalized": true,
|
| 729 |
+
"rstrip": false,
|
| 730 |
+
"single_word": false,
|
| 731 |
+
"special": false
|
| 732 |
+
},
|
| 733 |
+
"92": {
|
| 734 |
+
"content": "<unused85>",
|
| 735 |
+
"lstrip": false,
|
| 736 |
+
"normalized": true,
|
| 737 |
+
"rstrip": false,
|
| 738 |
+
"single_word": false,
|
| 739 |
+
"special": false
|
| 740 |
+
},
|
| 741 |
+
"93": {
|
| 742 |
+
"content": "<unused86>",
|
| 743 |
+
"lstrip": false,
|
| 744 |
+
"normalized": true,
|
| 745 |
+
"rstrip": false,
|
| 746 |
+
"single_word": false,
|
| 747 |
+
"special": false
|
| 748 |
+
},
|
| 749 |
+
"94": {
|
| 750 |
+
"content": "<unused87>",
|
| 751 |
+
"lstrip": false,
|
| 752 |
+
"normalized": true,
|
| 753 |
+
"rstrip": false,
|
| 754 |
+
"single_word": false,
|
| 755 |
+
"special": false
|
| 756 |
+
},
|
| 757 |
+
"95": {
|
| 758 |
+
"content": "<unused88>",
|
| 759 |
+
"lstrip": false,
|
| 760 |
+
"normalized": true,
|
| 761 |
+
"rstrip": false,
|
| 762 |
+
"single_word": false,
|
| 763 |
+
"special": false
|
| 764 |
+
},
|
| 765 |
+
"96": {
|
| 766 |
+
"content": "<unused89>",
|
| 767 |
+
"lstrip": false,
|
| 768 |
+
"normalized": true,
|
| 769 |
+
"rstrip": false,
|
| 770 |
+
"single_word": false,
|
| 771 |
+
"special": false
|
| 772 |
+
},
|
| 773 |
+
"97": {
|
| 774 |
+
"content": "<unused90>",
|
| 775 |
+
"lstrip": false,
|
| 776 |
+
"normalized": true,
|
| 777 |
+
"rstrip": false,
|
| 778 |
+
"single_word": false,
|
| 779 |
+
"special": false
|
| 780 |
+
},
|
| 781 |
+
"98": {
|
| 782 |
+
"content": "<unused91>",
|
| 783 |
+
"lstrip": false,
|
| 784 |
+
"normalized": true,
|
| 785 |
+
"rstrip": false,
|
| 786 |
+
"single_word": false,
|
| 787 |
+
"special": false
|
| 788 |
+
},
|
| 789 |
+
"99": {
|
| 790 |
+
"content": "<unused92>",
|
| 791 |
+
"lstrip": false,
|
| 792 |
+
"normalized": true,
|
| 793 |
+
"rstrip": false,
|
| 794 |
+
"single_word": false,
|
| 795 |
+
"special": false
|
| 796 |
+
},
|
| 797 |
+
"100": {
|
| 798 |
+
"content": "<unused93>",
|
| 799 |
+
"lstrip": false,
|
| 800 |
+
"normalized": true,
|
| 801 |
+
"rstrip": false,
|
| 802 |
+
"single_word": false,
|
| 803 |
+
"special": false
|
| 804 |
+
},
|
| 805 |
+
"101": {
|
| 806 |
+
"content": "<unused94>",
|
| 807 |
+
"lstrip": false,
|
| 808 |
+
"normalized": true,
|
| 809 |
+
"rstrip": false,
|
| 810 |
+
"single_word": false,
|
| 811 |
+
"special": false
|
| 812 |
+
},
|
| 813 |
+
"102": {
|
| 814 |
+
"content": "<unused95>",
|
| 815 |
+
"lstrip": false,
|
| 816 |
+
"normalized": true,
|
| 817 |
+
"rstrip": false,
|
| 818 |
+
"single_word": false,
|
| 819 |
+
"special": false
|
| 820 |
+
},
|
| 821 |
+
"103": {
|
| 822 |
+
"content": "<unused96>",
|
| 823 |
+
"lstrip": false,
|
| 824 |
+
"normalized": true,
|
| 825 |
+
"rstrip": false,
|
| 826 |
+
"single_word": false,
|
| 827 |
+
"special": false
|
| 828 |
+
},
|
| 829 |
+
"104": {
|
| 830 |
+
"content": "<unused97>",
|
| 831 |
+
"lstrip": false,
|
| 832 |
+
"normalized": true,
|
| 833 |
+
"rstrip": false,
|
| 834 |
+
"single_word": false,
|
| 835 |
+
"special": false
|
| 836 |
+
},
|
| 837 |
+
"105": {
|
| 838 |
+
"content": "<unused98>",
|
| 839 |
+
"lstrip": false,
|
| 840 |
+
"normalized": true,
|
| 841 |
+
"rstrip": false,
|
| 842 |
+
"single_word": false,
|
| 843 |
+
"special": false
|
| 844 |
+
},
|
| 845 |
+
"106": {
|
| 846 |
+
"content": "<start_of_turn>",
|
| 847 |
+
"lstrip": false,
|
| 848 |
+
"normalized": false,
|
| 849 |
+
"rstrip": false,
|
| 850 |
+
"single_word": false,
|
| 851 |
+
"special": true
|
| 852 |
+
},
|
| 853 |
+
"107": {
|
| 854 |
+
"content": "<end_of_turn>",
|
| 855 |
+
"lstrip": false,
|
| 856 |
+
"normalized": false,
|
| 857 |
+
"rstrip": false,
|
| 858 |
+
"single_word": false,
|
| 859 |
+
"special": true
|
| 860 |
+
},
|
| 861 |
+
"108": {
|
| 862 |
+
"content": "\n",
|
| 863 |
+
"lstrip": false,
|
| 864 |
+
"normalized": true,
|
| 865 |
+
"rstrip": false,
|
| 866 |
+
"single_word": false,
|
| 867 |
+
"special": false
|
| 868 |
+
},
|
| 869 |
+
"109": {
|
| 870 |
+
"content": "\n\n",
|
| 871 |
+
"lstrip": false,
|
| 872 |
+
"normalized": true,
|
| 873 |
+
"rstrip": false,
|
| 874 |
+
"single_word": false,
|
| 875 |
+
"special": false
|
| 876 |
+
},
|
| 877 |
+
"110": {
|
| 878 |
+
"content": "\n\n\n",
|
| 879 |
+
"lstrip": false,
|
| 880 |
+
"normalized": true,
|
| 881 |
+
"rstrip": false,
|
| 882 |
+
"single_word": false,
|
| 883 |
+
"special": false
|
| 884 |
+
},
|
| 885 |
+
"111": {
|
| 886 |
+
"content": "\n\n\n\n",
|
| 887 |
+
"lstrip": false,
|
| 888 |
+
"normalized": true,
|
| 889 |
+
"rstrip": false,
|
| 890 |
+
"single_word": false,
|
| 891 |
+
"special": false
|
| 892 |
+
},
|
| 893 |
+
"112": {
|
| 894 |
+
"content": "\n\n\n\n\n",
|
| 895 |
+
"lstrip": false,
|
| 896 |
+
"normalized": true,
|
| 897 |
+
"rstrip": false,
|
| 898 |
+
"single_word": false,
|
| 899 |
+
"special": false
|
| 900 |
+
},
|
| 901 |
+
"113": {
|
| 902 |
+
"content": "\n\n\n\n\n\n",
|
| 903 |
+
"lstrip": false,
|
| 904 |
+
"normalized": true,
|
| 905 |
+
"rstrip": false,
|
| 906 |
+
"single_word": false,
|
| 907 |
+
"special": false
|
| 908 |
+
},
|
| 909 |
+
"114": {
|
| 910 |
+
"content": "\n\n\n\n\n\n\n",
|
| 911 |
+
"lstrip": false,
|
| 912 |
+
"normalized": true,
|
| 913 |
+
"rstrip": false,
|
| 914 |
+
"single_word": false,
|
| 915 |
+
"special": false
|
| 916 |
+
},
|
| 917 |
+
"115": {
|
| 918 |
+
"content": "\n\n\n\n\n\n\n\n",
|
| 919 |
+
"lstrip": false,
|
| 920 |
+
"normalized": true,
|
| 921 |
+
"rstrip": false,
|
| 922 |
+
"single_word": false,
|
| 923 |
+
"special": false
|
| 924 |
+
},
|
| 925 |
+
"116": {
|
| 926 |
+
"content": "\n\n\n\n\n\n\n\n\n",
|
| 927 |
+
"lstrip": false,
|
| 928 |
+
"normalized": true,
|
| 929 |
+
"rstrip": false,
|
| 930 |
+
"single_word": false,
|
| 931 |
+
"special": false
|
| 932 |
+
},
|
| 933 |
+
"117": {
|
| 934 |
+
"content": "\n\n\n\n\n\n\n\n\n\n",
|
| 935 |
+
"lstrip": false,
|
| 936 |
+
"normalized": true,
|
| 937 |
+
"rstrip": false,
|
| 938 |
+
"single_word": false,
|
| 939 |
+
"special": false
|
| 940 |
+
},
|
| 941 |
+
"118": {
|
| 942 |
+
"content": "\n\n\n\n\n\n\n\n\n\n\n",
|
| 943 |
+
"lstrip": false,
|
| 944 |
+
"normalized": true,
|
| 945 |
+
"rstrip": false,
|
| 946 |
+
"single_word": false,
|
| 947 |
+
"special": false
|
| 948 |
+
},
|
| 949 |
+
"119": {
|
| 950 |
+
"content": "\n\n\n\n\n\n\n\n\n\n\n\n",
|
| 951 |
+
"lstrip": false,
|
| 952 |
+
"normalized": true,
|
| 953 |
+
"rstrip": false,
|
| 954 |
+
"single_word": false,
|
| 955 |
+
"special": false
|
| 956 |
+
},
|
| 957 |
+
"120": {
|
| 958 |
+
"content": "\n\n\n\n\n\n\n\n\n\n\n\n\n",
|
| 959 |
+
"lstrip": false,
|
| 960 |
+
"normalized": true,
|
| 961 |
+
"rstrip": false,
|
| 962 |
+
"single_word": false,
|
| 963 |
+
"special": false
|
| 964 |
+
},
|
| 965 |
+
"121": {
|
| 966 |
+
"content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
|
| 967 |
+
"lstrip": false,
|
| 968 |
+
"normalized": true,
|
| 969 |
+
"rstrip": false,
|
| 970 |
+
"single_word": false,
|
| 971 |
+
"special": false
|
| 972 |
+
},
|
| 973 |
+
"122": {
|
| 974 |
+
"content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
|
| 975 |
+
"lstrip": false,
|
| 976 |
+
"normalized": true,
|
| 977 |
+
"rstrip": false,
|
| 978 |
+
"single_word": false,
|
| 979 |
+
"special": false
|
| 980 |
+
},
|
| 981 |
+
"123": {
|
| 982 |
+
"content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
|
| 983 |
+
"lstrip": false,
|
| 984 |
+
"normalized": true,
|
| 985 |
+
"rstrip": false,
|
| 986 |
+
"single_word": false,
|
| 987 |
+
"special": false
|
| 988 |
+
},
|
| 989 |
+
"124": {
|
| 990 |
+
"content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
|
| 991 |
+
"lstrip": false,
|
| 992 |
+
"normalized": true,
|
| 993 |
+
"rstrip": false,
|
| 994 |
+
"single_word": false,
|
| 995 |
+
"special": false
|
| 996 |
+
},
|
| 997 |
+
"125": {
|
| 998 |
+
"content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
|
| 999 |
+
"lstrip": false,
|
| 1000 |
+
"normalized": true,
|
| 1001 |
+
"rstrip": false,
|
| 1002 |
+
"single_word": false,
|
| 1003 |
+
"special": false
|
| 1004 |
+
},
|
| 1005 |
+
"126": {
|
| 1006 |
+
"content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
|
| 1007 |
+
"lstrip": false,
|
| 1008 |
+
"normalized": true,
|
| 1009 |
+
"rstrip": false,
|
| 1010 |
+
"single_word": false,
|
| 1011 |
+
"special": false
|
| 1012 |
+
},
|
| 1013 |
+
"127": {
|
| 1014 |
+
"content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
|
| 1015 |
+
"lstrip": false,
|
| 1016 |
+
"normalized": true,
|
| 1017 |
+
"rstrip": false,
|
| 1018 |
+
"single_word": false,
|
| 1019 |
+
"special": false
|
| 1020 |
+
},
|
| 1021 |
+
"128": {
|
| 1022 |
+
"content": "\n\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": true,
|
| 1025 |
+
"rstrip": false,
|
| 1026 |
+
"single_word": false,
|
| 1027 |
+
"special": false
|
| 1028 |
+
},
|
| 1029 |
+
"129": {
|
| 1030 |
+
"content": "\n\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": true,
|
| 1033 |
+
"rstrip": false,
|
| 1034 |
+
"single_word": false,
|
| 1035 |
+
"special": false
|
| 1036 |
+
},
|
| 1037 |
+
"130": {
|
| 1038 |
+
"content": "\n\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": true,
|
| 1041 |
+
"rstrip": false,
|
| 1042 |
+
"single_word": false,
|
| 1043 |
+
"special": false
|
| 1044 |
+
},
|
| 1045 |
+
"131": {
|
| 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\n",
|
| 1047 |
+
"lstrip": false,
|
| 1048 |
+
"normalized": true,
|
| 1049 |
+
"rstrip": false,
|
| 1050 |
+
"single_word": false,
|
| 1051 |
+
"special": false
|
| 1052 |
+
},
|
| 1053 |
+
"132": {
|
| 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\n",
|
| 1055 |
+
"lstrip": false,
|
| 1056 |
+
"normalized": true,
|
| 1057 |
+
"rstrip": false,
|
| 1058 |
+
"single_word": false,
|
| 1059 |
+
"special": false
|
| 1060 |
+
},
|
| 1061 |
+
"133": {
|
| 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\n",
|
| 1063 |
+
"lstrip": false,
|
| 1064 |
+
"normalized": true,
|
| 1065 |
+
"rstrip": false,
|
| 1066 |
+
"single_word": false,
|
| 1067 |
+
"special": false
|
| 1068 |
+
},
|
| 1069 |
+
"134": {
|
| 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\n",
|
| 1071 |
+
"lstrip": false,
|
| 1072 |
+
"normalized": true,
|
| 1073 |
+
"rstrip": false,
|
| 1074 |
+
"single_word": false,
|
| 1075 |
+
"special": false
|
| 1076 |
+
},
|
| 1077 |
+
"135": {
|
| 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\n",
|
| 1079 |
+
"lstrip": false,
|
| 1080 |
+
"normalized": true,
|
| 1081 |
+
"rstrip": false,
|
| 1082 |
+
"single_word": false,
|
| 1083 |
+
"special": false
|
| 1084 |
+
},
|
| 1085 |
+
"136": {
|
| 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\n",
|
| 1087 |
+
"lstrip": false,
|
| 1088 |
+
"normalized": true,
|
| 1089 |
+
"rstrip": false,
|
| 1090 |
+
"single_word": false,
|
| 1091 |
+
"special": false
|
| 1092 |
+
},
|
| 1093 |
+
"137": {
|
| 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\n",
|
| 1095 |
+
"lstrip": false,
|
| 1096 |
+
"normalized": true,
|
| 1097 |
+
"rstrip": false,
|
| 1098 |
+
"single_word": false,
|
| 1099 |
+
"special": false
|
| 1100 |
+
},
|
| 1101 |
+
"138": {
|
| 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\n",
|
| 1103 |
+
"lstrip": false,
|
| 1104 |
+
"normalized": true,
|
| 1105 |
+
"rstrip": false,
|
| 1106 |
+
"single_word": false,
|
| 1107 |
+
"special": false
|
| 1108 |
+
},
|
| 1109 |
+
"139": {
|
| 1110 |
+
"content": "▁▁",
|
| 1111 |
+
"lstrip": false,
|
| 1112 |
+
"normalized": true,
|
| 1113 |
+
"rstrip": false,
|
| 1114 |
+
"single_word": false,
|
| 1115 |
+
"special": false
|
| 1116 |
+
},
|
| 1117 |
+
"140": {
|
| 1118 |
+
"content": "▁▁▁",
|
| 1119 |
+
"lstrip": false,
|
| 1120 |
+
"normalized": true,
|
| 1121 |
+
"rstrip": false,
|
| 1122 |
+
"single_word": false,
|
| 1123 |
+
"special": false
|
| 1124 |
+
},
|
| 1125 |
+
"141": {
|
| 1126 |
+
"content": "▁▁▁▁",
|
| 1127 |
+
"lstrip": false,
|
| 1128 |
+
"normalized": true,
|
| 1129 |
+
"rstrip": false,
|
| 1130 |
+
"single_word": false,
|
| 1131 |
+
"special": false
|
| 1132 |
+
},
|
| 1133 |
+
"142": {
|
| 1134 |
+
"content": "▁▁▁▁▁",
|
| 1135 |
+
"lstrip": false,
|
| 1136 |
+
"normalized": true,
|
| 1137 |
+
"rstrip": false,
|
| 1138 |
+
"single_word": false,
|
| 1139 |
+
"special": false
|
| 1140 |
+
},
|
| 1141 |
+
"143": {
|
| 1142 |
+
"content": "▁▁▁▁▁▁",
|
| 1143 |
+
"lstrip": false,
|
| 1144 |
+
"normalized": true,
|
| 1145 |
+
"rstrip": false,
|
| 1146 |
+
"single_word": false,
|
| 1147 |
+
"special": false
|
| 1148 |
+
},
|
| 1149 |
+
"144": {
|
| 1150 |
+
"content": "▁▁▁▁▁▁▁",
|
| 1151 |
+
"lstrip": false,
|
| 1152 |
+
"normalized": true,
|
| 1153 |
+
"rstrip": false,
|
| 1154 |
+
"single_word": false,
|
| 1155 |
+
"special": false
|
| 1156 |
+
},
|
| 1157 |
+
"145": {
|
| 1158 |
+
"content": "▁▁▁▁▁▁▁▁",
|
| 1159 |
+
"lstrip": false,
|
| 1160 |
+
"normalized": true,
|
| 1161 |
+
"rstrip": false,
|
| 1162 |
+
"single_word": false,
|
| 1163 |
+
"special": false
|
| 1164 |
+
},
|
| 1165 |
+
"146": {
|
| 1166 |
+
"content": "▁▁▁▁▁▁▁▁▁",
|
| 1167 |
+
"lstrip": false,
|
| 1168 |
+
"normalized": true,
|
| 1169 |
+
"rstrip": false,
|
| 1170 |
+
"single_word": false,
|
| 1171 |
+
"special": false
|
| 1172 |
+
},
|
| 1173 |
+
"147": {
|
| 1174 |
+
"content": "▁▁▁▁▁▁▁▁▁▁",
|
| 1175 |
+
"lstrip": false,
|
| 1176 |
+
"normalized": true,
|
| 1177 |
+
"rstrip": false,
|
| 1178 |
+
"single_word": false,
|
| 1179 |
+
"special": false
|
| 1180 |
+
},
|
| 1181 |
+
"148": {
|
| 1182 |
+
"content": "▁▁▁▁▁▁▁▁▁▁▁",
|
| 1183 |
+
"lstrip": false,
|
| 1184 |
+
"normalized": true,
|
| 1185 |
+
"rstrip": false,
|
| 1186 |
+
"single_word": false,
|
| 1187 |
+
"special": false
|
| 1188 |
+
},
|
| 1189 |
+
"149": {
|
| 1190 |
+
"content": "▁▁▁▁▁▁▁▁▁▁▁▁",
|
| 1191 |
+
"lstrip": false,
|
| 1192 |
+
"normalized": true,
|
| 1193 |
+
"rstrip": false,
|
| 1194 |
+
"single_word": false,
|
| 1195 |
+
"special": false
|
| 1196 |
+
},
|
| 1197 |
+
"150": {
|
| 1198 |
+
"content": "▁▁▁▁▁▁▁▁▁▁▁▁▁",
|
| 1199 |
+
"lstrip": false,
|
| 1200 |
+
"normalized": true,
|
| 1201 |
+
"rstrip": false,
|
| 1202 |
+
"single_word": false,
|
| 1203 |
+
"special": false
|
| 1204 |
+
},
|
| 1205 |
+
"151": {
|
| 1206 |
+
"content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
|
| 1207 |
+
"lstrip": false,
|
| 1208 |
+
"normalized": true,
|
| 1209 |
+
"rstrip": false,
|
| 1210 |
+
"single_word": false,
|
| 1211 |
+
"special": false
|
| 1212 |
+
},
|
| 1213 |
+
"152": {
|
| 1214 |
+
"content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
|
| 1215 |
+
"lstrip": false,
|
| 1216 |
+
"normalized": true,
|
| 1217 |
+
"rstrip": false,
|
| 1218 |
+
"single_word": false,
|
| 1219 |
+
"special": false
|
| 1220 |
+
},
|
| 1221 |
+
"153": {
|
| 1222 |
+
"content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
|
| 1223 |
+
"lstrip": false,
|
| 1224 |
+
"normalized": true,
|
| 1225 |
+
"rstrip": false,
|
| 1226 |
+
"single_word": false,
|
| 1227 |
+
"special": false
|
| 1228 |
+
},
|
| 1229 |
+
"154": {
|
| 1230 |
+
"content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
|
| 1231 |
+
"lstrip": false,
|
| 1232 |
+
"normalized": true,
|
| 1233 |
+
"rstrip": false,
|
| 1234 |
+
"single_word": false,
|
| 1235 |
+
"special": false
|
| 1236 |
+
},
|
| 1237 |
+
"155": {
|
| 1238 |
+
"content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
|
| 1239 |
+
"lstrip": false,
|
| 1240 |
+
"normalized": true,
|
| 1241 |
+
"rstrip": false,
|
| 1242 |
+
"single_word": false,
|
| 1243 |
+
"special": false
|
| 1244 |
+
},
|
| 1245 |
+
"156": {
|
| 1246 |
+
"content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
|
| 1247 |
+
"lstrip": false,
|
| 1248 |
+
"normalized": true,
|
| 1249 |
+
"rstrip": false,
|
| 1250 |
+
"single_word": false,
|
| 1251 |
+
"special": false
|
| 1252 |
+
},
|
| 1253 |
+
"157": {
|
| 1254 |
+
"content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
|
| 1255 |
+
"lstrip": false,
|
| 1256 |
+
"normalized": true,
|
| 1257 |
+
"rstrip": false,
|
| 1258 |
+
"single_word": false,
|
| 1259 |
+
"special": false
|
| 1260 |
+
},
|
| 1261 |
+
"158": {
|
| 1262 |
+
"content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
|
| 1263 |
+
"lstrip": false,
|
| 1264 |
+
"normalized": true,
|
| 1265 |
+
"rstrip": false,
|
| 1266 |
+
"single_word": false,
|
| 1267 |
+
"special": false
|
| 1268 |
+
},
|
| 1269 |
+
"159": {
|
| 1270 |
+
"content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
|
| 1271 |
+
"lstrip": false,
|
| 1272 |
+
"normalized": true,
|
| 1273 |
+
"rstrip": false,
|
| 1274 |
+
"single_word": false,
|
| 1275 |
+
"special": false
|
| 1276 |
+
},
|
| 1277 |
+
"160": {
|
| 1278 |
+
"content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
|
| 1279 |
+
"lstrip": false,
|
| 1280 |
+
"normalized": true,
|
| 1281 |
+
"rstrip": false,
|
| 1282 |
+
"single_word": false,
|
| 1283 |
+
"special": false
|
| 1284 |
+
},
|
| 1285 |
+
"161": {
|
| 1286 |
+
"content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
|
| 1287 |
+
"lstrip": false,
|
| 1288 |
+
"normalized": true,
|
| 1289 |
+
"rstrip": false,
|
| 1290 |
+
"single_word": false,
|
| 1291 |
+
"special": false
|
| 1292 |
+
},
|
| 1293 |
+
"162": {
|
| 1294 |
+
"content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁���▁▁",
|
| 1295 |
+
"lstrip": false,
|
| 1296 |
+
"normalized": true,
|
| 1297 |
+
"rstrip": false,
|
| 1298 |
+
"single_word": false,
|
| 1299 |
+
"special": false
|
| 1300 |
+
},
|
| 1301 |
+
"163": {
|
| 1302 |
+
"content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
|
| 1303 |
+
"lstrip": false,
|
| 1304 |
+
"normalized": true,
|
| 1305 |
+
"rstrip": false,
|
| 1306 |
+
"single_word": false,
|
| 1307 |
+
"special": false
|
| 1308 |
+
},
|
| 1309 |
+
"164": {
|
| 1310 |
+
"content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
|
| 1311 |
+
"lstrip": false,
|
| 1312 |
+
"normalized": true,
|
| 1313 |
+
"rstrip": false,
|
| 1314 |
+
"single_word": false,
|
| 1315 |
+
"special": false
|
| 1316 |
+
},
|
| 1317 |
+
"165": {
|
| 1318 |
+
"content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
|
| 1319 |
+
"lstrip": false,
|
| 1320 |
+
"normalized": true,
|
| 1321 |
+
"rstrip": false,
|
| 1322 |
+
"single_word": false,
|
| 1323 |
+
"special": false
|
| 1324 |
+
},
|
| 1325 |
+
"166": {
|
| 1326 |
+
"content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
|
| 1327 |
+
"lstrip": false,
|
| 1328 |
+
"normalized": true,
|
| 1329 |
+
"rstrip": false,
|
| 1330 |
+
"single_word": false,
|
| 1331 |
+
"special": false
|
| 1332 |
+
},
|
| 1333 |
+
"167": {
|
| 1334 |
+
"content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
|
| 1335 |
+
"lstrip": false,
|
| 1336 |
+
"normalized": true,
|
| 1337 |
+
"rstrip": false,
|
| 1338 |
+
"single_word": false,
|
| 1339 |
+
"special": false
|
| 1340 |
+
},
|
| 1341 |
+
"168": {
|
| 1342 |
+
"content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
|
| 1343 |
+
"lstrip": false,
|
| 1344 |
+
"normalized": true,
|
| 1345 |
+
"rstrip": false,
|
| 1346 |
+
"single_word": false,
|
| 1347 |
+
"special": false
|
| 1348 |
+
},
|
| 1349 |
+
"169": {
|
| 1350 |
+
"content": "<table>",
|
| 1351 |
+
"lstrip": false,
|
| 1352 |
+
"normalized": true,
|
| 1353 |
+
"rstrip": false,
|
| 1354 |
+
"single_word": false,
|
| 1355 |
+
"special": false
|
| 1356 |
+
},
|
| 1357 |
+
"170": {
|
| 1358 |
+
"content": "<caption>",
|
| 1359 |
+
"lstrip": false,
|
| 1360 |
+
"normalized": true,
|
| 1361 |
+
"rstrip": false,
|
| 1362 |
+
"single_word": false,
|
| 1363 |
+
"special": false
|
| 1364 |
+
},
|
| 1365 |
+
"171": {
|
| 1366 |
+
"content": "<thead>",
|
| 1367 |
+
"lstrip": false,
|
| 1368 |
+
"normalized": true,
|
| 1369 |
+
"rstrip": false,
|
| 1370 |
+
"single_word": false,
|
| 1371 |
+
"special": false
|
| 1372 |
+
},
|
| 1373 |
+
"172": {
|
| 1374 |
+
"content": "<tbody>",
|
| 1375 |
+
"lstrip": false,
|
| 1376 |
+
"normalized": true,
|
| 1377 |
+
"rstrip": false,
|
| 1378 |
+
"single_word": false,
|
| 1379 |
+
"special": false
|
| 1380 |
+
},
|
| 1381 |
+
"173": {
|
| 1382 |
+
"content": "<tfoot>",
|
| 1383 |
+
"lstrip": false,
|
| 1384 |
+
"normalized": true,
|
| 1385 |
+
"rstrip": false,
|
| 1386 |
+
"single_word": false,
|
| 1387 |
+
"special": false
|
| 1388 |
+
},
|
| 1389 |
+
"174": {
|
| 1390 |
+
"content": "<tr>",
|
| 1391 |
+
"lstrip": false,
|
| 1392 |
+
"normalized": true,
|
| 1393 |
+
"rstrip": false,
|
| 1394 |
+
"single_word": false,
|
| 1395 |
+
"special": false
|
| 1396 |
+
},
|
| 1397 |
+
"175": {
|
| 1398 |
+
"content": "<th>",
|
| 1399 |
+
"lstrip": false,
|
| 1400 |
+
"normalized": true,
|
| 1401 |
+
"rstrip": false,
|
| 1402 |
+
"single_word": false,
|
| 1403 |
+
"special": false
|
| 1404 |
+
},
|
| 1405 |
+
"176": {
|
| 1406 |
+
"content": "<td>",
|
| 1407 |
+
"lstrip": false,
|
| 1408 |
+
"normalized": true,
|
| 1409 |
+
"rstrip": false,
|
| 1410 |
+
"single_word": false,
|
| 1411 |
+
"special": false
|
| 1412 |
+
},
|
| 1413 |
+
"177": {
|
| 1414 |
+
"content": "</table>",
|
| 1415 |
+
"lstrip": false,
|
| 1416 |
+
"normalized": true,
|
| 1417 |
+
"rstrip": false,
|
| 1418 |
+
"single_word": false,
|
| 1419 |
+
"special": false
|
| 1420 |
+
},
|
| 1421 |
+
"178": {
|
| 1422 |
+
"content": "</caption>",
|
| 1423 |
+
"lstrip": false,
|
| 1424 |
+
"normalized": true,
|
| 1425 |
+
"rstrip": false,
|
| 1426 |
+
"single_word": false,
|
| 1427 |
+
"special": false
|
| 1428 |
+
},
|
| 1429 |
+
"179": {
|
| 1430 |
+
"content": "</thead>",
|
| 1431 |
+
"lstrip": false,
|
| 1432 |
+
"normalized": true,
|
| 1433 |
+
"rstrip": false,
|
| 1434 |
+
"single_word": false,
|
| 1435 |
+
"special": false
|
| 1436 |
+
},
|
| 1437 |
+
"180": {
|
| 1438 |
+
"content": "</tbody>",
|
| 1439 |
+
"lstrip": false,
|
| 1440 |
+
"normalized": true,
|
| 1441 |
+
"rstrip": false,
|
| 1442 |
+
"single_word": false,
|
| 1443 |
+
"special": false
|
| 1444 |
+
},
|
| 1445 |
+
"181": {
|
| 1446 |
+
"content": "</tfoot>",
|
| 1447 |
+
"lstrip": false,
|
| 1448 |
+
"normalized": true,
|
| 1449 |
+
"rstrip": false,
|
| 1450 |
+
"single_word": false,
|
| 1451 |
+
"special": false
|
| 1452 |
+
},
|
| 1453 |
+
"182": {
|
| 1454 |
+
"content": "</tr>",
|
| 1455 |
+
"lstrip": false,
|
| 1456 |
+
"normalized": true,
|
| 1457 |
+
"rstrip": false,
|
| 1458 |
+
"single_word": false,
|
| 1459 |
+
"special": false
|
| 1460 |
+
},
|
| 1461 |
+
"183": {
|
| 1462 |
+
"content": "</th>",
|
| 1463 |
+
"lstrip": false,
|
| 1464 |
+
"normalized": true,
|
| 1465 |
+
"rstrip": false,
|
| 1466 |
+
"single_word": false,
|
| 1467 |
+
"special": false
|
| 1468 |
+
},
|
| 1469 |
+
"184": {
|
| 1470 |
+
"content": "</td>",
|
| 1471 |
+
"lstrip": false,
|
| 1472 |
+
"normalized": true,
|
| 1473 |
+
"rstrip": false,
|
| 1474 |
+
"single_word": false,
|
| 1475 |
+
"special": false
|
| 1476 |
+
},
|
| 1477 |
+
"185": {
|
| 1478 |
+
"content": "<h1>",
|
| 1479 |
+
"lstrip": false,
|
| 1480 |
+
"normalized": true,
|
| 1481 |
+
"rstrip": false,
|
| 1482 |
+
"single_word": false,
|
| 1483 |
+
"special": false
|
| 1484 |
+
},
|
| 1485 |
+
"186": {
|
| 1486 |
+
"content": "<h2>",
|
| 1487 |
+
"lstrip": false,
|
| 1488 |
+
"normalized": true,
|
| 1489 |
+
"rstrip": false,
|
| 1490 |
+
"single_word": false,
|
| 1491 |
+
"special": false
|
| 1492 |
+
},
|
| 1493 |
+
"187": {
|
| 1494 |
+
"content": "<h3>",
|
| 1495 |
+
"lstrip": false,
|
| 1496 |
+
"normalized": true,
|
| 1497 |
+
"rstrip": false,
|
| 1498 |
+
"single_word": false,
|
| 1499 |
+
"special": false
|
| 1500 |
+
},
|
| 1501 |
+
"188": {
|
| 1502 |
+
"content": "<h4>",
|
| 1503 |
+
"lstrip": false,
|
| 1504 |
+
"normalized": true,
|
| 1505 |
+
"rstrip": false,
|
| 1506 |
+
"single_word": false,
|
| 1507 |
+
"special": false
|
| 1508 |
+
},
|
| 1509 |
+
"189": {
|
| 1510 |
+
"content": "<h5>",
|
| 1511 |
+
"lstrip": false,
|
| 1512 |
+
"normalized": true,
|
| 1513 |
+
"rstrip": false,
|
| 1514 |
+
"single_word": false,
|
| 1515 |
+
"special": false
|
| 1516 |
+
},
|
| 1517 |
+
"190": {
|
| 1518 |
+
"content": "<h6>",
|
| 1519 |
+
"lstrip": false,
|
| 1520 |
+
"normalized": true,
|
| 1521 |
+
"rstrip": false,
|
| 1522 |
+
"single_word": false,
|
| 1523 |
+
"special": false
|
| 1524 |
+
},
|
| 1525 |
+
"191": {
|
| 1526 |
+
"content": "<blockquote>",
|
| 1527 |
+
"lstrip": false,
|
| 1528 |
+
"normalized": true,
|
| 1529 |
+
"rstrip": false,
|
| 1530 |
+
"single_word": false,
|
| 1531 |
+
"special": false
|
| 1532 |
+
},
|
| 1533 |
+
"192": {
|
| 1534 |
+
"content": "</h1>",
|
| 1535 |
+
"lstrip": false,
|
| 1536 |
+
"normalized": true,
|
| 1537 |
+
"rstrip": false,
|
| 1538 |
+
"single_word": false,
|
| 1539 |
+
"special": false
|
| 1540 |
+
},
|
| 1541 |
+
"193": {
|
| 1542 |
+
"content": "</h2>",
|
| 1543 |
+
"lstrip": false,
|
| 1544 |
+
"normalized": true,
|
| 1545 |
+
"rstrip": false,
|
| 1546 |
+
"single_word": false,
|
| 1547 |
+
"special": false
|
| 1548 |
+
},
|
| 1549 |
+
"194": {
|
| 1550 |
+
"content": "</h3>",
|
| 1551 |
+
"lstrip": false,
|
| 1552 |
+
"normalized": true,
|
| 1553 |
+
"rstrip": false,
|
| 1554 |
+
"single_word": false,
|
| 1555 |
+
"special": false
|
| 1556 |
+
},
|
| 1557 |
+
"195": {
|
| 1558 |
+
"content": "</h4>",
|
| 1559 |
+
"lstrip": false,
|
| 1560 |
+
"normalized": true,
|
| 1561 |
+
"rstrip": false,
|
| 1562 |
+
"single_word": false,
|
| 1563 |
+
"special": false
|
| 1564 |
+
},
|
| 1565 |
+
"196": {
|
| 1566 |
+
"content": "</h5>",
|
| 1567 |
+
"lstrip": false,
|
| 1568 |
+
"normalized": true,
|
| 1569 |
+
"rstrip": false,
|
| 1570 |
+
"single_word": false,
|
| 1571 |
+
"special": false
|
| 1572 |
+
},
|
| 1573 |
+
"197": {
|
| 1574 |
+
"content": "</h6>",
|
| 1575 |
+
"lstrip": false,
|
| 1576 |
+
"normalized": true,
|
| 1577 |
+
"rstrip": false,
|
| 1578 |
+
"single_word": false,
|
| 1579 |
+
"special": false
|
| 1580 |
+
},
|
| 1581 |
+
"198": {
|
| 1582 |
+
"content": "</blockquote>",
|
| 1583 |
+
"lstrip": false,
|
| 1584 |
+
"normalized": true,
|
| 1585 |
+
"rstrip": false,
|
| 1586 |
+
"single_word": false,
|
| 1587 |
+
"special": false
|
| 1588 |
+
},
|
| 1589 |
+
"199": {
|
| 1590 |
+
"content": "<strong>",
|
| 1591 |
+
"lstrip": false,
|
| 1592 |
+
"normalized": true,
|
| 1593 |
+
"rstrip": false,
|
| 1594 |
+
"single_word": false,
|
| 1595 |
+
"special": false
|
| 1596 |
+
},
|
| 1597 |
+
"200": {
|
| 1598 |
+
"content": "<em>",
|
| 1599 |
+
"lstrip": false,
|
| 1600 |
+
"normalized": true,
|
| 1601 |
+
"rstrip": false,
|
| 1602 |
+
"single_word": false,
|
| 1603 |
+
"special": false
|
| 1604 |
+
},
|
| 1605 |
+
"201": {
|
| 1606 |
+
"content": "<b>",
|
| 1607 |
+
"lstrip": false,
|
| 1608 |
+
"normalized": true,
|
| 1609 |
+
"rstrip": false,
|
| 1610 |
+
"single_word": false,
|
| 1611 |
+
"special": false
|
| 1612 |
+
},
|
| 1613 |
+
"202": {
|
| 1614 |
+
"content": "<i>",
|
| 1615 |
+
"lstrip": false,
|
| 1616 |
+
"normalized": true,
|
| 1617 |
+
"rstrip": false,
|
| 1618 |
+
"single_word": false,
|
| 1619 |
+
"special": false
|
| 1620 |
+
},
|
| 1621 |
+
"203": {
|
| 1622 |
+
"content": "<u>",
|
| 1623 |
+
"lstrip": false,
|
| 1624 |
+
"normalized": true,
|
| 1625 |
+
"rstrip": false,
|
| 1626 |
+
"single_word": false,
|
| 1627 |
+
"special": false
|
| 1628 |
+
},
|
| 1629 |
+
"204": {
|
| 1630 |
+
"content": "<s>",
|
| 1631 |
+
"lstrip": false,
|
| 1632 |
+
"normalized": true,
|
| 1633 |
+
"rstrip": false,
|
| 1634 |
+
"single_word": false,
|
| 1635 |
+
"special": false
|
| 1636 |
+
},
|
| 1637 |
+
"205": {
|
| 1638 |
+
"content": "<sub>",
|
| 1639 |
+
"lstrip": false,
|
| 1640 |
+
"normalized": true,
|
| 1641 |
+
"rstrip": false,
|
| 1642 |
+
"single_word": false,
|
| 1643 |
+
"special": false
|
| 1644 |
+
},
|
| 1645 |
+
"206": {
|
| 1646 |
+
"content": "<sup>",
|
| 1647 |
+
"lstrip": false,
|
| 1648 |
+
"normalized": true,
|
| 1649 |
+
"rstrip": false,
|
| 1650 |
+
"single_word": false,
|
| 1651 |
+
"special": false
|
| 1652 |
+
},
|
| 1653 |
+
"207": {
|
| 1654 |
+
"content": "<code>",
|
| 1655 |
+
"lstrip": false,
|
| 1656 |
+
"normalized": true,
|
| 1657 |
+
"rstrip": false,
|
| 1658 |
+
"single_word": false,
|
| 1659 |
+
"special": false
|
| 1660 |
+
},
|
| 1661 |
+
"208": {
|
| 1662 |
+
"content": "</strong>",
|
| 1663 |
+
"lstrip": false,
|
| 1664 |
+
"normalized": true,
|
| 1665 |
+
"rstrip": false,
|
| 1666 |
+
"single_word": false,
|
| 1667 |
+
"special": false
|
| 1668 |
+
},
|
| 1669 |
+
"209": {
|
| 1670 |
+
"content": "</em>",
|
| 1671 |
+
"lstrip": false,
|
| 1672 |
+
"normalized": true,
|
| 1673 |
+
"rstrip": false,
|
| 1674 |
+
"single_word": false,
|
| 1675 |
+
"special": false
|
| 1676 |
+
},
|
| 1677 |
+
"210": {
|
| 1678 |
+
"content": "</b>",
|
| 1679 |
+
"lstrip": false,
|
| 1680 |
+
"normalized": true,
|
| 1681 |
+
"rstrip": false,
|
| 1682 |
+
"single_word": false,
|
| 1683 |
+
"special": false
|
| 1684 |
+
},
|
| 1685 |
+
"211": {
|
| 1686 |
+
"content": "</i>",
|
| 1687 |
+
"lstrip": false,
|
| 1688 |
+
"normalized": true,
|
| 1689 |
+
"rstrip": false,
|
| 1690 |
+
"single_word": false,
|
| 1691 |
+
"special": false
|
| 1692 |
+
},
|
| 1693 |
+
"212": {
|
| 1694 |
+
"content": "</u>",
|
| 1695 |
+
"lstrip": false,
|
| 1696 |
+
"normalized": true,
|
| 1697 |
+
"rstrip": false,
|
| 1698 |
+
"single_word": false,
|
| 1699 |
+
"special": false
|
| 1700 |
+
},
|
| 1701 |
+
"213": {
|
| 1702 |
+
"content": "</s>",
|
| 1703 |
+
"lstrip": false,
|
| 1704 |
+
"normalized": true,
|
| 1705 |
+
"rstrip": false,
|
| 1706 |
+
"single_word": false,
|
| 1707 |
+
"special": false
|
| 1708 |
+
},
|
| 1709 |
+
"214": {
|
| 1710 |
+
"content": "</sub>",
|
| 1711 |
+
"lstrip": false,
|
| 1712 |
+
"normalized": true,
|
| 1713 |
+
"rstrip": false,
|
| 1714 |
+
"single_word": false,
|
| 1715 |
+
"special": false
|
| 1716 |
+
},
|
| 1717 |
+
"215": {
|
| 1718 |
+
"content": "</sup>",
|
| 1719 |
+
"lstrip": false,
|
| 1720 |
+
"normalized": true,
|
| 1721 |
+
"rstrip": false,
|
| 1722 |
+
"single_word": false,
|
| 1723 |
+
"special": false
|
| 1724 |
+
},
|
| 1725 |
+
"216": {
|
| 1726 |
+
"content": "</code>",
|
| 1727 |
+
"lstrip": false,
|
| 1728 |
+
"normalized": true,
|
| 1729 |
+
"rstrip": false,
|
| 1730 |
+
"single_word": false,
|
| 1731 |
+
"special": false
|
| 1732 |
+
},
|
| 1733 |
+
"255999": {
|
| 1734 |
+
"content": "<eos>",
|
| 1735 |
+
"lstrip": false,
|
| 1736 |
+
"normalized": false,
|
| 1737 |
+
"rstrip": false,
|
| 1738 |
+
"single_word": false,
|
| 1739 |
+
"special": true
|
| 1740 |
+
}
|
| 1741 |
+
},
|
| 1742 |
+
"additional_special_tokens": [
|
| 1743 |
+
"<start_of_turn>",
|
| 1744 |
+
"<end_of_turn>"
|
| 1745 |
+
],
|
| 1746 |
+
"bos_token": "<bos>",
|
| 1747 |
+
"chat_template": "{{ bos_token }}{% for message in messages %}{{ 'GPT4 Correct ' + message['role'].title() + ': ' + message['content'] + '<end_of_turn>'}}{% endfor %}{% if add_generation_prompt %}{{ 'GPT4 Correct Assistant: ' }}{% endif %}",
|
| 1748 |
+
"clean_up_tokenization_spaces": false,
|
| 1749 |
+
"eos_token": "<end_of_turn>",
|
| 1750 |
+
"legacy": null,
|
| 1751 |
+
"model_max_length": 8192,
|
| 1752 |
+
"pad_token": "<pad>",
|
| 1753 |
+
"padding_side": "right",
|
| 1754 |
+
"sp_model_kwargs": {},
|
| 1755 |
+
"spaces_between_special_tokens": false,
|
| 1756 |
+
"tokenizer_class": "GemmaTokenizer",
|
| 1757 |
+
"unk_token": "<unk>",
|
| 1758 |
+
"use_default_system_prompt": false
|
| 1759 |
+
}
|
checkpoint-4000/trainer_state.json
ADDED
|
@@ -0,0 +1,2833 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.07609047157069757,
|
| 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": 0.0001902261789267439,
|
| 13 |
+
"grad_norm": 7.031089782714844,
|
| 14 |
+
"learning_rate": 1.9022256039566294e-08,
|
| 15 |
+
"loss": 2.4444,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.0003804523578534878,
|
| 20 |
+
"grad_norm": 13.060206413269043,
|
| 21 |
+
"learning_rate": 3.804451207913259e-08,
|
| 22 |
+
"loss": 2.614,
|
| 23 |
+
"step": 20
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.0005706785367802317,
|
| 27 |
+
"grad_norm": 15.187254905700684,
|
| 28 |
+
"learning_rate": 5.7066768118698886e-08,
|
| 29 |
+
"loss": 3.1213,
|
| 30 |
+
"step": 30
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.0007609047157069756,
|
| 34 |
+
"grad_norm": 19.703323364257812,
|
| 35 |
+
"learning_rate": 7.608902415826518e-08,
|
| 36 |
+
"loss": 4.1664,
|
| 37 |
+
"step": 40
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.0009511308946337195,
|
| 41 |
+
"grad_norm": 32.09828186035156,
|
| 42 |
+
"learning_rate": 9.511128019783147e-08,
|
| 43 |
+
"loss": 5.9187,
|
| 44 |
+
"step": 50
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.0011413570735604635,
|
| 48 |
+
"grad_norm": 6.527578830718994,
|
| 49 |
+
"learning_rate": 1.1413353623739777e-07,
|
| 50 |
+
"loss": 2.5169,
|
| 51 |
+
"step": 60
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.0013315832524872073,
|
| 55 |
+
"grad_norm": 8.701460838317871,
|
| 56 |
+
"learning_rate": 1.3315579227696404e-07,
|
| 57 |
+
"loss": 2.6031,
|
| 58 |
+
"step": 70
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.0015218094314139513,
|
| 62 |
+
"grad_norm": 19.97081184387207,
|
| 63 |
+
"learning_rate": 1.5217804831653035e-07,
|
| 64 |
+
"loss": 3.1127,
|
| 65 |
+
"step": 80
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.001712035610340695,
|
| 69 |
+
"grad_norm": 14.284954071044922,
|
| 70 |
+
"learning_rate": 1.7120030435609666e-07,
|
| 71 |
+
"loss": 3.9951,
|
| 72 |
+
"step": 90
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.001902261789267439,
|
| 76 |
+
"grad_norm": 25.341217041015625,
|
| 77 |
+
"learning_rate": 1.9022256039566295e-07,
|
| 78 |
+
"loss": 5.4591,
|
| 79 |
+
"step": 100
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.002092487968194183,
|
| 83 |
+
"grad_norm": 5.924285411834717,
|
| 84 |
+
"learning_rate": 2.0924481643522923e-07,
|
| 85 |
+
"loss": 2.4404,
|
| 86 |
+
"step": 110
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.002282714147120927,
|
| 90 |
+
"grad_norm": 11.63301944732666,
|
| 91 |
+
"learning_rate": 2.2826707247479554e-07,
|
| 92 |
+
"loss": 2.5059,
|
| 93 |
+
"step": 120
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.0024729403260476705,
|
| 97 |
+
"grad_norm": 11.728666305541992,
|
| 98 |
+
"learning_rate": 2.472893285143618e-07,
|
| 99 |
+
"loss": 3.1191,
|
| 100 |
+
"step": 130
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.0026631665049744145,
|
| 104 |
+
"grad_norm": 9.490508079528809,
|
| 105 |
+
"learning_rate": 2.663115845539281e-07,
|
| 106 |
+
"loss": 3.8237,
|
| 107 |
+
"step": 140
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.0028533926839011585,
|
| 111 |
+
"grad_norm": 24.791996002197266,
|
| 112 |
+
"learning_rate": 2.853338405934944e-07,
|
| 113 |
+
"loss": 5.5867,
|
| 114 |
+
"step": 150
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.0030436188628279025,
|
| 118 |
+
"grad_norm": 4.845604419708252,
|
| 119 |
+
"learning_rate": 3.043560966330607e-07,
|
| 120 |
+
"loss": 2.3633,
|
| 121 |
+
"step": 160
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.003233845041754646,
|
| 125 |
+
"grad_norm": 6.938657283782959,
|
| 126 |
+
"learning_rate": 3.2337835267262704e-07,
|
| 127 |
+
"loss": 2.3907,
|
| 128 |
+
"step": 170
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.00342407122068139,
|
| 132 |
+
"grad_norm": 8.972224235534668,
|
| 133 |
+
"learning_rate": 3.424006087121933e-07,
|
| 134 |
+
"loss": 2.6722,
|
| 135 |
+
"step": 180
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.003614297399608134,
|
| 139 |
+
"grad_norm": 9.294358253479004,
|
| 140 |
+
"learning_rate": 3.614228647517596e-07,
|
| 141 |
+
"loss": 3.4523,
|
| 142 |
+
"step": 190
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.003804523578534878,
|
| 146 |
+
"grad_norm": 19.425222396850586,
|
| 147 |
+
"learning_rate": 3.804451207913259e-07,
|
| 148 |
+
"loss": 5.2828,
|
| 149 |
+
"step": 200
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.003994749757461622,
|
| 153 |
+
"grad_norm": 3.1245577335357666,
|
| 154 |
+
"learning_rate": 3.994673768308922e-07,
|
| 155 |
+
"loss": 2.191,
|
| 156 |
+
"step": 210
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.004184975936388366,
|
| 160 |
+
"grad_norm": 4.416078567504883,
|
| 161 |
+
"learning_rate": 4.1848963287045846e-07,
|
| 162 |
+
"loss": 2.4138,
|
| 163 |
+
"step": 220
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.00437520211531511,
|
| 167 |
+
"grad_norm": 8.128155708312988,
|
| 168 |
+
"learning_rate": 4.3751188891002475e-07,
|
| 169 |
+
"loss": 2.4941,
|
| 170 |
+
"step": 230
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.004565428294241854,
|
| 174 |
+
"grad_norm": 5.850177764892578,
|
| 175 |
+
"learning_rate": 4.565341449495911e-07,
|
| 176 |
+
"loss": 3.153,
|
| 177 |
+
"step": 240
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.004755654473168598,
|
| 181 |
+
"grad_norm": 19.345319747924805,
|
| 182 |
+
"learning_rate": 4.7555640098915737e-07,
|
| 183 |
+
"loss": 5.0348,
|
| 184 |
+
"step": 250
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.004945880652095341,
|
| 188 |
+
"grad_norm": 2.327831983566284,
|
| 189 |
+
"learning_rate": 4.945786570287236e-07,
|
| 190 |
+
"loss": 2.1702,
|
| 191 |
+
"step": 260
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.005136106831022085,
|
| 195 |
+
"grad_norm": 2.7916853427886963,
|
| 196 |
+
"learning_rate": 5.136009130682899e-07,
|
| 197 |
+
"loss": 2.1161,
|
| 198 |
+
"step": 270
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.005326333009948829,
|
| 202 |
+
"grad_norm": 3.9358408451080322,
|
| 203 |
+
"learning_rate": 5.326231691078562e-07,
|
| 204 |
+
"loss": 2.2815,
|
| 205 |
+
"step": 280
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.005516559188875573,
|
| 209 |
+
"grad_norm": 4.891003131866455,
|
| 210 |
+
"learning_rate": 5.516454251474225e-07,
|
| 211 |
+
"loss": 2.8836,
|
| 212 |
+
"step": 290
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.005706785367802317,
|
| 216 |
+
"grad_norm": 22.499956130981445,
|
| 217 |
+
"learning_rate": 5.706676811869888e-07,
|
| 218 |
+
"loss": 4.7026,
|
| 219 |
+
"step": 300
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.005897011546729061,
|
| 223 |
+
"grad_norm": 1.9951050281524658,
|
| 224 |
+
"learning_rate": 5.896899372265551e-07,
|
| 225 |
+
"loss": 2.0446,
|
| 226 |
+
"step": 310
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.006087237725655805,
|
| 230 |
+
"grad_norm": 3.147122859954834,
|
| 231 |
+
"learning_rate": 6.087121932661214e-07,
|
| 232 |
+
"loss": 2.138,
|
| 233 |
+
"step": 320
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.006277463904582548,
|
| 237 |
+
"grad_norm": 3.4201011657714844,
|
| 238 |
+
"learning_rate": 6.277344493056876e-07,
|
| 239 |
+
"loss": 2.1024,
|
| 240 |
+
"step": 330
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.006467690083509292,
|
| 244 |
+
"grad_norm": 4.823904991149902,
|
| 245 |
+
"learning_rate": 6.467567053452541e-07,
|
| 246 |
+
"loss": 2.7573,
|
| 247 |
+
"step": 340
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.006657916262436036,
|
| 251 |
+
"grad_norm": 21.016569137573242,
|
| 252 |
+
"learning_rate": 6.657789613848204e-07,
|
| 253 |
+
"loss": 4.1976,
|
| 254 |
+
"step": 350
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.00684814244136278,
|
| 258 |
+
"grad_norm": 1.872706413269043,
|
| 259 |
+
"learning_rate": 6.848012174243867e-07,
|
| 260 |
+
"loss": 1.9986,
|
| 261 |
+
"step": 360
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.007038368620289524,
|
| 265 |
+
"grad_norm": 2.8600945472717285,
|
| 266 |
+
"learning_rate": 7.038234734639529e-07,
|
| 267 |
+
"loss": 1.9909,
|
| 268 |
+
"step": 370
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 0.007228594799216268,
|
| 272 |
+
"grad_norm": 3.7441070079803467,
|
| 273 |
+
"learning_rate": 7.228457295035192e-07,
|
| 274 |
+
"loss": 2.0065,
|
| 275 |
+
"step": 380
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.007418820978143012,
|
| 279 |
+
"grad_norm": 5.4876627922058105,
|
| 280 |
+
"learning_rate": 7.418679855430855e-07,
|
| 281 |
+
"loss": 2.7059,
|
| 282 |
+
"step": 390
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.007609047157069756,
|
| 286 |
+
"grad_norm": 24.044830322265625,
|
| 287 |
+
"learning_rate": 7.608902415826518e-07,
|
| 288 |
+
"loss": 4.0807,
|
| 289 |
+
"step": 400
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.0077992733359964995,
|
| 293 |
+
"grad_norm": 1.6859079599380493,
|
| 294 |
+
"learning_rate": 7.799124976222181e-07,
|
| 295 |
+
"loss": 1.974,
|
| 296 |
+
"step": 410
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.007989499514923244,
|
| 300 |
+
"grad_norm": 2.8750579357147217,
|
| 301 |
+
"learning_rate": 7.989347536617844e-07,
|
| 302 |
+
"loss": 1.835,
|
| 303 |
+
"step": 420
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.008179725693849988,
|
| 307 |
+
"grad_norm": 4.05927038192749,
|
| 308 |
+
"learning_rate": 8.179570097013506e-07,
|
| 309 |
+
"loss": 1.9796,
|
| 310 |
+
"step": 430
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 0.008369951872776732,
|
| 314 |
+
"grad_norm": 6.277343273162842,
|
| 315 |
+
"learning_rate": 8.369792657409169e-07,
|
| 316 |
+
"loss": 2.474,
|
| 317 |
+
"step": 440
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.008560178051703475,
|
| 321 |
+
"grad_norm": 32.71267318725586,
|
| 322 |
+
"learning_rate": 8.560015217804832e-07,
|
| 323 |
+
"loss": 3.7252,
|
| 324 |
+
"step": 450
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.00875040423063022,
|
| 328 |
+
"grad_norm": 1.6604670286178589,
|
| 329 |
+
"learning_rate": 8.750237778200495e-07,
|
| 330 |
+
"loss": 1.851,
|
| 331 |
+
"step": 460
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.008940630409556963,
|
| 335 |
+
"grad_norm": 2.756211280822754,
|
| 336 |
+
"learning_rate": 8.940460338596159e-07,
|
| 337 |
+
"loss": 1.6797,
|
| 338 |
+
"step": 470
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.009130856588483708,
|
| 342 |
+
"grad_norm": 4.476970195770264,
|
| 343 |
+
"learning_rate": 9.130682898991822e-07,
|
| 344 |
+
"loss": 1.8404,
|
| 345 |
+
"step": 480
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.00932108276741045,
|
| 349 |
+
"grad_norm": 6.676766395568848,
|
| 350 |
+
"learning_rate": 9.320905459387485e-07,
|
| 351 |
+
"loss": 2.2254,
|
| 352 |
+
"step": 490
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 0.009511308946337196,
|
| 356 |
+
"grad_norm": 33.66838836669922,
|
| 357 |
+
"learning_rate": 9.511128019783147e-07,
|
| 358 |
+
"loss": 3.3597,
|
| 359 |
+
"step": 500
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 0.009701535125263939,
|
| 363 |
+
"grad_norm": 1.771323561668396,
|
| 364 |
+
"learning_rate": 9.70135058017881e-07,
|
| 365 |
+
"loss": 1.7942,
|
| 366 |
+
"step": 510
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 0.009891761304190682,
|
| 370 |
+
"grad_norm": 3.0909101963043213,
|
| 371 |
+
"learning_rate": 9.891573140574472e-07,
|
| 372 |
+
"loss": 1.7758,
|
| 373 |
+
"step": 520
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 0.010081987483117427,
|
| 377 |
+
"grad_norm": 4.743190765380859,
|
| 378 |
+
"learning_rate": 1.0081795700970136e-06,
|
| 379 |
+
"loss": 1.7564,
|
| 380 |
+
"step": 530
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 0.01027221366204417,
|
| 384 |
+
"grad_norm": 7.06041145324707,
|
| 385 |
+
"learning_rate": 1.0272018261365798e-06,
|
| 386 |
+
"loss": 2.1511,
|
| 387 |
+
"step": 540
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.010462439840970915,
|
| 391 |
+
"grad_norm": 26.422157287597656,
|
| 392 |
+
"learning_rate": 1.0462240821761462e-06,
|
| 393 |
+
"loss": 2.8421,
|
| 394 |
+
"step": 550
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 0.010652666019897658,
|
| 398 |
+
"grad_norm": 1.8234245777130127,
|
| 399 |
+
"learning_rate": 1.0652463382157123e-06,
|
| 400 |
+
"loss": 1.7149,
|
| 401 |
+
"step": 560
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 0.010842892198824403,
|
| 405 |
+
"grad_norm": 3.059401273727417,
|
| 406 |
+
"learning_rate": 1.0842685942552787e-06,
|
| 407 |
+
"loss": 1.647,
|
| 408 |
+
"step": 570
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 0.011033118377751146,
|
| 412 |
+
"grad_norm": 4.818949222564697,
|
| 413 |
+
"learning_rate": 1.103290850294845e-06,
|
| 414 |
+
"loss": 1.5044,
|
| 415 |
+
"step": 580
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 0.01122334455667789,
|
| 419 |
+
"grad_norm": 6.994847774505615,
|
| 420 |
+
"learning_rate": 1.1223131063344113e-06,
|
| 421 |
+
"loss": 1.8919,
|
| 422 |
+
"step": 590
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 0.011413570735604634,
|
| 426 |
+
"grad_norm": 38.19530487060547,
|
| 427 |
+
"learning_rate": 1.1413353623739777e-06,
|
| 428 |
+
"loss": 2.4963,
|
| 429 |
+
"step": 600
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.011603796914531377,
|
| 433 |
+
"grad_norm": 2.0052971839904785,
|
| 434 |
+
"learning_rate": 1.160357618413544e-06,
|
| 435 |
+
"loss": 1.6709,
|
| 436 |
+
"step": 610
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 0.011794023093458122,
|
| 440 |
+
"grad_norm": 1.6200284957885742,
|
| 441 |
+
"learning_rate": 1.1793798744531103e-06,
|
| 442 |
+
"loss": 1.5749,
|
| 443 |
+
"step": 620
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 0.011984249272384865,
|
| 447 |
+
"grad_norm": 2.2375597953796387,
|
| 448 |
+
"learning_rate": 1.1984021304926766e-06,
|
| 449 |
+
"loss": 1.4411,
|
| 450 |
+
"step": 630
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 0.01217447545131161,
|
| 454 |
+
"grad_norm": 5.535067558288574,
|
| 455 |
+
"learning_rate": 1.2174243865322428e-06,
|
| 456 |
+
"loss": 1.845,
|
| 457 |
+
"step": 640
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 0.012364701630238353,
|
| 461 |
+
"grad_norm": 9.7356595993042,
|
| 462 |
+
"learning_rate": 1.2364466425718092e-06,
|
| 463 |
+
"loss": 2.524,
|
| 464 |
+
"step": 650
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 0.012554927809165096,
|
| 468 |
+
"grad_norm": 1.4515656232833862,
|
| 469 |
+
"learning_rate": 1.2554688986113752e-06,
|
| 470 |
+
"loss": 1.6263,
|
| 471 |
+
"step": 660
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.012745153988091841,
|
| 475 |
+
"grad_norm": 1.6473021507263184,
|
| 476 |
+
"learning_rate": 1.2744911546509418e-06,
|
| 477 |
+
"loss": 1.5024,
|
| 478 |
+
"step": 670
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 0.012935380167018585,
|
| 482 |
+
"grad_norm": 2.3517134189605713,
|
| 483 |
+
"learning_rate": 1.2935134106905082e-06,
|
| 484 |
+
"loss": 1.4407,
|
| 485 |
+
"step": 680
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 0.01312560634594533,
|
| 489 |
+
"grad_norm": 2.8996622562408447,
|
| 490 |
+
"learning_rate": 1.3125356667300743e-06,
|
| 491 |
+
"loss": 1.6358,
|
| 492 |
+
"step": 690
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 0.013315832524872073,
|
| 496 |
+
"grad_norm": 11.34484577178955,
|
| 497 |
+
"learning_rate": 1.3315579227696407e-06,
|
| 498 |
+
"loss": 2.2334,
|
| 499 |
+
"step": 700
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 0.013506058703798817,
|
| 503 |
+
"grad_norm": 1.1996574401855469,
|
| 504 |
+
"learning_rate": 1.350580178809207e-06,
|
| 505 |
+
"loss": 1.4753,
|
| 506 |
+
"step": 710
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 0.01369628488272556,
|
| 510 |
+
"grad_norm": 1.6772912740707397,
|
| 511 |
+
"learning_rate": 1.3696024348487733e-06,
|
| 512 |
+
"loss": 1.5256,
|
| 513 |
+
"step": 720
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.013886511061652304,
|
| 517 |
+
"grad_norm": 2.156625986099243,
|
| 518 |
+
"learning_rate": 1.3886246908883395e-06,
|
| 519 |
+
"loss": 1.4419,
|
| 520 |
+
"step": 730
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 0.014076737240579049,
|
| 524 |
+
"grad_norm": 3.710660219192505,
|
| 525 |
+
"learning_rate": 1.4076469469279059e-06,
|
| 526 |
+
"loss": 1.6054,
|
| 527 |
+
"step": 740
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 0.014266963419505792,
|
| 531 |
+
"grad_norm": 7.250610828399658,
|
| 532 |
+
"learning_rate": 1.426669202967472e-06,
|
| 533 |
+
"loss": 2.1039,
|
| 534 |
+
"step": 750
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 0.014457189598432537,
|
| 538 |
+
"grad_norm": 1.4629435539245605,
|
| 539 |
+
"learning_rate": 1.4456914590070384e-06,
|
| 540 |
+
"loss": 1.5061,
|
| 541 |
+
"step": 760
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 0.01464741577735928,
|
| 545 |
+
"grad_norm": 1.7025142908096313,
|
| 546 |
+
"learning_rate": 1.4647137150466046e-06,
|
| 547 |
+
"loss": 1.4471,
|
| 548 |
+
"step": 770
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 0.014837641956286025,
|
| 552 |
+
"grad_norm": 2.418815851211548,
|
| 553 |
+
"learning_rate": 1.483735971086171e-06,
|
| 554 |
+
"loss": 1.3384,
|
| 555 |
+
"step": 780
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 0.015027868135212768,
|
| 559 |
+
"grad_norm": 4.666192531585693,
|
| 560 |
+
"learning_rate": 1.5027582271257372e-06,
|
| 561 |
+
"loss": 1.599,
|
| 562 |
+
"step": 790
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 0.015218094314139513,
|
| 566 |
+
"grad_norm": 8.951377868652344,
|
| 567 |
+
"learning_rate": 1.5217804831653036e-06,
|
| 568 |
+
"loss": 1.9391,
|
| 569 |
+
"step": 800
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 0.015408320493066256,
|
| 573 |
+
"grad_norm": 1.383745551109314,
|
| 574 |
+
"learning_rate": 1.54080273920487e-06,
|
| 575 |
+
"loss": 1.5076,
|
| 576 |
+
"step": 810
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 0.015598546671992999,
|
| 580 |
+
"grad_norm": 1.4020535945892334,
|
| 581 |
+
"learning_rate": 1.5598249952444361e-06,
|
| 582 |
+
"loss": 1.3977,
|
| 583 |
+
"step": 820
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 0.015788772850919744,
|
| 587 |
+
"grad_norm": 2.2491354942321777,
|
| 588 |
+
"learning_rate": 1.5788472512840025e-06,
|
| 589 |
+
"loss": 1.3356,
|
| 590 |
+
"step": 830
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 0.015978999029846487,
|
| 594 |
+
"grad_norm": 3.5490710735321045,
|
| 595 |
+
"learning_rate": 1.5978695073235687e-06,
|
| 596 |
+
"loss": 1.5511,
|
| 597 |
+
"step": 840
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 0.01616922520877323,
|
| 601 |
+
"grad_norm": 11.946330070495605,
|
| 602 |
+
"learning_rate": 1.616891763363135e-06,
|
| 603 |
+
"loss": 1.8743,
|
| 604 |
+
"step": 850
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 0.016359451387699977,
|
| 608 |
+
"grad_norm": 1.4720561504364014,
|
| 609 |
+
"learning_rate": 1.6359140194027013e-06,
|
| 610 |
+
"loss": 1.4478,
|
| 611 |
+
"step": 860
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 0.01654967756662672,
|
| 615 |
+
"grad_norm": 1.6156224012374878,
|
| 616 |
+
"learning_rate": 1.6549362754422677e-06,
|
| 617 |
+
"loss": 1.4235,
|
| 618 |
+
"step": 870
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 0.016739903745553463,
|
| 622 |
+
"grad_norm": 2.14105224609375,
|
| 623 |
+
"learning_rate": 1.6739585314818339e-06,
|
| 624 |
+
"loss": 1.3183,
|
| 625 |
+
"step": 880
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 0.016930129924480206,
|
| 629 |
+
"grad_norm": 4.404923915863037,
|
| 630 |
+
"learning_rate": 1.6929807875214002e-06,
|
| 631 |
+
"loss": 1.3946,
|
| 632 |
+
"step": 890
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 0.01712035610340695,
|
| 636 |
+
"grad_norm": 7.182434558868408,
|
| 637 |
+
"learning_rate": 1.7120030435609664e-06,
|
| 638 |
+
"loss": 1.8036,
|
| 639 |
+
"step": 900
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 0.017310582282333696,
|
| 643 |
+
"grad_norm": 1.494486689567566,
|
| 644 |
+
"learning_rate": 1.7310252996005328e-06,
|
| 645 |
+
"loss": 1.4478,
|
| 646 |
+
"step": 910
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 0.01750080846126044,
|
| 650 |
+
"grad_norm": 1.6941497325897217,
|
| 651 |
+
"learning_rate": 1.750047555640099e-06,
|
| 652 |
+
"loss": 1.3241,
|
| 653 |
+
"step": 920
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 0.017691034640187182,
|
| 657 |
+
"grad_norm": 2.1194875240325928,
|
| 658 |
+
"learning_rate": 1.7690698116796654e-06,
|
| 659 |
+
"loss": 1.189,
|
| 660 |
+
"step": 930
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 0.017881260819113926,
|
| 664 |
+
"grad_norm": 2.8642826080322266,
|
| 665 |
+
"learning_rate": 1.7880920677192318e-06,
|
| 666 |
+
"loss": 1.3617,
|
| 667 |
+
"step": 940
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 0.01807148699804067,
|
| 671 |
+
"grad_norm": 9.907108306884766,
|
| 672 |
+
"learning_rate": 1.807114323758798e-06,
|
| 673 |
+
"loss": 1.7392,
|
| 674 |
+
"step": 950
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 0.018261713176967415,
|
| 678 |
+
"grad_norm": 1.627024531364441,
|
| 679 |
+
"learning_rate": 1.8261365797983643e-06,
|
| 680 |
+
"loss": 1.4536,
|
| 681 |
+
"step": 960
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 0.01845193935589416,
|
| 685 |
+
"grad_norm": 1.7732610702514648,
|
| 686 |
+
"learning_rate": 1.8451588358379305e-06,
|
| 687 |
+
"loss": 1.3351,
|
| 688 |
+
"step": 970
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 0.0186421655348209,
|
| 692 |
+
"grad_norm": 2.412036180496216,
|
| 693 |
+
"learning_rate": 1.864181091877497e-06,
|
| 694 |
+
"loss": 1.2028,
|
| 695 |
+
"step": 980
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 0.018832391713747645,
|
| 699 |
+
"grad_norm": 4.754890441894531,
|
| 700 |
+
"learning_rate": 1.883203347917063e-06,
|
| 701 |
+
"loss": 1.3517,
|
| 702 |
+
"step": 990
|
| 703 |
+
},
|
| 704 |
+
{
|
| 705 |
+
"epoch": 0.01902261789267439,
|
| 706 |
+
"grad_norm": 8.927350997924805,
|
| 707 |
+
"learning_rate": 1.9022256039566295e-06,
|
| 708 |
+
"loss": 1.6531,
|
| 709 |
+
"step": 1000
|
| 710 |
+
},
|
| 711 |
+
{
|
| 712 |
+
"epoch": 0.019212844071601134,
|
| 713 |
+
"grad_norm": 1.6348631381988525,
|
| 714 |
+
"learning_rate": 1.9212478599961954e-06,
|
| 715 |
+
"loss": 1.4934,
|
| 716 |
+
"step": 1010
|
| 717 |
+
},
|
| 718 |
+
{
|
| 719 |
+
"epoch": 0.019403070250527878,
|
| 720 |
+
"grad_norm": 1.9770840406417847,
|
| 721 |
+
"learning_rate": 1.940270116035762e-06,
|
| 722 |
+
"loss": 1.3571,
|
| 723 |
+
"step": 1020
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 0.01959329642945462,
|
| 727 |
+
"grad_norm": 2.404418468475342,
|
| 728 |
+
"learning_rate": 1.9592923720753282e-06,
|
| 729 |
+
"loss": 1.1291,
|
| 730 |
+
"step": 1030
|
| 731 |
+
},
|
| 732 |
+
{
|
| 733 |
+
"epoch": 0.019783522608381364,
|
| 734 |
+
"grad_norm": 3.4404196739196777,
|
| 735 |
+
"learning_rate": 1.9783146281148944e-06,
|
| 736 |
+
"loss": 1.2498,
|
| 737 |
+
"step": 1040
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 0.01997374878730811,
|
| 741 |
+
"grad_norm": 9.02733325958252,
|
| 742 |
+
"learning_rate": 1.9973368841544606e-06,
|
| 743 |
+
"loss": 1.5646,
|
| 744 |
+
"step": 1050
|
| 745 |
+
},
|
| 746 |
+
{
|
| 747 |
+
"epoch": 0.020163974966234854,
|
| 748 |
+
"grad_norm": 1.9403765201568604,
|
| 749 |
+
"learning_rate": 2.016359140194027e-06,
|
| 750 |
+
"loss": 1.3972,
|
| 751 |
+
"step": 1060
|
| 752 |
+
},
|
| 753 |
+
{
|
| 754 |
+
"epoch": 0.020354201145161597,
|
| 755 |
+
"grad_norm": 2.009138584136963,
|
| 756 |
+
"learning_rate": 2.0353813962335938e-06,
|
| 757 |
+
"loss": 1.303,
|
| 758 |
+
"step": 1070
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 0.02054442732408834,
|
| 762 |
+
"grad_norm": 2.1750669479370117,
|
| 763 |
+
"learning_rate": 2.0544036522731595e-06,
|
| 764 |
+
"loss": 1.1875,
|
| 765 |
+
"step": 1080
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 0.020734653503015087,
|
| 769 |
+
"grad_norm": 3.3346753120422363,
|
| 770 |
+
"learning_rate": 2.073425908312726e-06,
|
| 771 |
+
"loss": 1.262,
|
| 772 |
+
"step": 1090
|
| 773 |
+
},
|
| 774 |
+
{
|
| 775 |
+
"epoch": 0.02092487968194183,
|
| 776 |
+
"grad_norm": 8.939334869384766,
|
| 777 |
+
"learning_rate": 2.0924481643522923e-06,
|
| 778 |
+
"loss": 1.547,
|
| 779 |
+
"step": 1100
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 0.021115105860868573,
|
| 783 |
+
"grad_norm": 1.614304780960083,
|
| 784 |
+
"learning_rate": 2.111470420391859e-06,
|
| 785 |
+
"loss": 1.3818,
|
| 786 |
+
"step": 1110
|
| 787 |
+
},
|
| 788 |
+
{
|
| 789 |
+
"epoch": 0.021305332039795316,
|
| 790 |
+
"grad_norm": 1.98068106174469,
|
| 791 |
+
"learning_rate": 2.1304926764314247e-06,
|
| 792 |
+
"loss": 1.2253,
|
| 793 |
+
"step": 1120
|
| 794 |
+
},
|
| 795 |
+
{
|
| 796 |
+
"epoch": 0.02149555821872206,
|
| 797 |
+
"grad_norm": 2.3504743576049805,
|
| 798 |
+
"learning_rate": 2.1495149324709913e-06,
|
| 799 |
+
"loss": 1.1185,
|
| 800 |
+
"step": 1130
|
| 801 |
+
},
|
| 802 |
+
{
|
| 803 |
+
"epoch": 0.021685784397648806,
|
| 804 |
+
"grad_norm": 3.188448667526245,
|
| 805 |
+
"learning_rate": 2.1685371885105575e-06,
|
| 806 |
+
"loss": 1.2133,
|
| 807 |
+
"step": 1140
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 0.02187601057657555,
|
| 811 |
+
"grad_norm": 11.752523422241211,
|
| 812 |
+
"learning_rate": 2.187559444550124e-06,
|
| 813 |
+
"loss": 1.5604,
|
| 814 |
+
"step": 1150
|
| 815 |
+
},
|
| 816 |
+
{
|
| 817 |
+
"epoch": 0.022066236755502292,
|
| 818 |
+
"grad_norm": 1.4586597681045532,
|
| 819 |
+
"learning_rate": 2.20658170058969e-06,
|
| 820 |
+
"loss": 1.2922,
|
| 821 |
+
"step": 1160
|
| 822 |
+
},
|
| 823 |
+
{
|
| 824 |
+
"epoch": 0.022256462934429035,
|
| 825 |
+
"grad_norm": 1.83343505859375,
|
| 826 |
+
"learning_rate": 2.2256039566292564e-06,
|
| 827 |
+
"loss": 1.2738,
|
| 828 |
+
"step": 1170
|
| 829 |
+
},
|
| 830 |
+
{
|
| 831 |
+
"epoch": 0.02244668911335578,
|
| 832 |
+
"grad_norm": 2.553067684173584,
|
| 833 |
+
"learning_rate": 2.2446262126688226e-06,
|
| 834 |
+
"loss": 1.096,
|
| 835 |
+
"step": 1180
|
| 836 |
+
},
|
| 837 |
+
{
|
| 838 |
+
"epoch": 0.022636915292282525,
|
| 839 |
+
"grad_norm": 4.024831771850586,
|
| 840 |
+
"learning_rate": 2.263648468708389e-06,
|
| 841 |
+
"loss": 1.1661,
|
| 842 |
+
"step": 1190
|
| 843 |
+
},
|
| 844 |
+
{
|
| 845 |
+
"epoch": 0.022827141471209268,
|
| 846 |
+
"grad_norm": 11.252798080444336,
|
| 847 |
+
"learning_rate": 2.2826707247479554e-06,
|
| 848 |
+
"loss": 1.4848,
|
| 849 |
+
"step": 1200
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 0.02301736765013601,
|
| 853 |
+
"grad_norm": 2.0187082290649414,
|
| 854 |
+
"learning_rate": 2.3016929807875215e-06,
|
| 855 |
+
"loss": 1.2914,
|
| 856 |
+
"step": 1210
|
| 857 |
+
},
|
| 858 |
+
{
|
| 859 |
+
"epoch": 0.023207593829062755,
|
| 860 |
+
"grad_norm": 2.2791354656219482,
|
| 861 |
+
"learning_rate": 2.320715236827088e-06,
|
| 862 |
+
"loss": 1.2912,
|
| 863 |
+
"step": 1220
|
| 864 |
+
},
|
| 865 |
+
{
|
| 866 |
+
"epoch": 0.0233978200079895,
|
| 867 |
+
"grad_norm": 2.755721092224121,
|
| 868 |
+
"learning_rate": 2.3397374928666543e-06,
|
| 869 |
+
"loss": 1.1446,
|
| 870 |
+
"step": 1230
|
| 871 |
+
},
|
| 872 |
+
{
|
| 873 |
+
"epoch": 0.023588046186916244,
|
| 874 |
+
"grad_norm": 4.635268688201904,
|
| 875 |
+
"learning_rate": 2.3587597489062205e-06,
|
| 876 |
+
"loss": 1.156,
|
| 877 |
+
"step": 1240
|
| 878 |
+
},
|
| 879 |
+
{
|
| 880 |
+
"epoch": 0.023778272365842987,
|
| 881 |
+
"grad_norm": 11.180182456970215,
|
| 882 |
+
"learning_rate": 2.3777820049457867e-06,
|
| 883 |
+
"loss": 1.5128,
|
| 884 |
+
"step": 1250
|
| 885 |
+
},
|
| 886 |
+
{
|
| 887 |
+
"epoch": 0.02396849854476973,
|
| 888 |
+
"grad_norm": 2.6687514781951904,
|
| 889 |
+
"learning_rate": 2.3968042609853533e-06,
|
| 890 |
+
"loss": 1.3078,
|
| 891 |
+
"step": 1260
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 0.024158724723696474,
|
| 895 |
+
"grad_norm": 2.1617326736450195,
|
| 896 |
+
"learning_rate": 2.4158265170249195e-06,
|
| 897 |
+
"loss": 1.187,
|
| 898 |
+
"step": 1270
|
| 899 |
+
},
|
| 900 |
+
{
|
| 901 |
+
"epoch": 0.02434895090262322,
|
| 902 |
+
"grad_norm": 2.7917706966400146,
|
| 903 |
+
"learning_rate": 2.4348487730644856e-06,
|
| 904 |
+
"loss": 1.1008,
|
| 905 |
+
"step": 1280
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"epoch": 0.024539177081549964,
|
| 909 |
+
"grad_norm": 3.9902455806732178,
|
| 910 |
+
"learning_rate": 2.453871029104052e-06,
|
| 911 |
+
"loss": 1.1694,
|
| 912 |
+
"step": 1290
|
| 913 |
+
},
|
| 914 |
+
{
|
| 915 |
+
"epoch": 0.024729403260476707,
|
| 916 |
+
"grad_norm": 10.19775104522705,
|
| 917 |
+
"learning_rate": 2.4728932851436184e-06,
|
| 918 |
+
"loss": 1.4882,
|
| 919 |
+
"step": 1300
|
| 920 |
+
},
|
| 921 |
+
{
|
| 922 |
+
"epoch": 0.02491962943940345,
|
| 923 |
+
"grad_norm": 1.815943956375122,
|
| 924 |
+
"learning_rate": 2.4919155411831846e-06,
|
| 925 |
+
"loss": 1.3296,
|
| 926 |
+
"step": 1310
|
| 927 |
+
},
|
| 928 |
+
{
|
| 929 |
+
"epoch": 0.025109855618330193,
|
| 930 |
+
"grad_norm": 1.7802958488464355,
|
| 931 |
+
"learning_rate": 2.5109377972227504e-06,
|
| 932 |
+
"loss": 1.1588,
|
| 933 |
+
"step": 1320
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 0.02530008179725694,
|
| 937 |
+
"grad_norm": 2.8108973503112793,
|
| 938 |
+
"learning_rate": 2.529960053262317e-06,
|
| 939 |
+
"loss": 1.0912,
|
| 940 |
+
"step": 1330
|
| 941 |
+
},
|
| 942 |
+
{
|
| 943 |
+
"epoch": 0.025490307976183683,
|
| 944 |
+
"grad_norm": 3.822803497314453,
|
| 945 |
+
"learning_rate": 2.5489823093018836e-06,
|
| 946 |
+
"loss": 1.1713,
|
| 947 |
+
"step": 1340
|
| 948 |
+
},
|
| 949 |
+
{
|
| 950 |
+
"epoch": 0.025680534155110426,
|
| 951 |
+
"grad_norm": 10.885619163513184,
|
| 952 |
+
"learning_rate": 2.5680045653414497e-06,
|
| 953 |
+
"loss": 1.4048,
|
| 954 |
+
"step": 1350
|
| 955 |
+
},
|
| 956 |
+
{
|
| 957 |
+
"epoch": 0.02587076033403717,
|
| 958 |
+
"grad_norm": 1.5321264266967773,
|
| 959 |
+
"learning_rate": 2.5870268213810163e-06,
|
| 960 |
+
"loss": 1.2555,
|
| 961 |
+
"step": 1360
|
| 962 |
+
},
|
| 963 |
+
{
|
| 964 |
+
"epoch": 0.026060986512963916,
|
| 965 |
+
"grad_norm": 2.115370512008667,
|
| 966 |
+
"learning_rate": 2.606049077420582e-06,
|
| 967 |
+
"loss": 1.1987,
|
| 968 |
+
"step": 1370
|
| 969 |
+
},
|
| 970 |
+
{
|
| 971 |
+
"epoch": 0.02625121269189066,
|
| 972 |
+
"grad_norm": 2.6233675479888916,
|
| 973 |
+
"learning_rate": 2.6250713334601487e-06,
|
| 974 |
+
"loss": 1.0758,
|
| 975 |
+
"step": 1380
|
| 976 |
+
},
|
| 977 |
+
{
|
| 978 |
+
"epoch": 0.026441438870817402,
|
| 979 |
+
"grad_norm": 3.8407323360443115,
|
| 980 |
+
"learning_rate": 2.644093589499715e-06,
|
| 981 |
+
"loss": 1.1887,
|
| 982 |
+
"step": 1390
|
| 983 |
+
},
|
| 984 |
+
{
|
| 985 |
+
"epoch": 0.026631665049744145,
|
| 986 |
+
"grad_norm": 12.603764533996582,
|
| 987 |
+
"learning_rate": 2.6631158455392815e-06,
|
| 988 |
+
"loss": 1.4082,
|
| 989 |
+
"step": 1400
|
| 990 |
+
},
|
| 991 |
+
{
|
| 992 |
+
"epoch": 0.026821891228670888,
|
| 993 |
+
"grad_norm": 1.6481189727783203,
|
| 994 |
+
"learning_rate": 2.6821381015788472e-06,
|
| 995 |
+
"loss": 1.2527,
|
| 996 |
+
"step": 1410
|
| 997 |
+
},
|
| 998 |
+
{
|
| 999 |
+
"epoch": 0.027012117407597635,
|
| 1000 |
+
"grad_norm": 2.1282284259796143,
|
| 1001 |
+
"learning_rate": 2.701160357618414e-06,
|
| 1002 |
+
"loss": 1.2139,
|
| 1003 |
+
"step": 1420
|
| 1004 |
+
},
|
| 1005 |
+
{
|
| 1006 |
+
"epoch": 0.027202343586524378,
|
| 1007 |
+
"grad_norm": 2.9524528980255127,
|
| 1008 |
+
"learning_rate": 2.72018261365798e-06,
|
| 1009 |
+
"loss": 1.09,
|
| 1010 |
+
"step": 1430
|
| 1011 |
+
},
|
| 1012 |
+
{
|
| 1013 |
+
"epoch": 0.02739256976545112,
|
| 1014 |
+
"grad_norm": 4.275539398193359,
|
| 1015 |
+
"learning_rate": 2.7392048696975466e-06,
|
| 1016 |
+
"loss": 1.1149,
|
| 1017 |
+
"step": 1440
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 0.027582795944377864,
|
| 1021 |
+
"grad_norm": 12.224852561950684,
|
| 1022 |
+
"learning_rate": 2.7582271257371124e-06,
|
| 1023 |
+
"loss": 1.3974,
|
| 1024 |
+
"step": 1450
|
| 1025 |
+
},
|
| 1026 |
+
{
|
| 1027 |
+
"epoch": 0.027773022123304607,
|
| 1028 |
+
"grad_norm": 2.3314363956451416,
|
| 1029 |
+
"learning_rate": 2.777249381776679e-06,
|
| 1030 |
+
"loss": 1.3061,
|
| 1031 |
+
"step": 1460
|
| 1032 |
+
},
|
| 1033 |
+
{
|
| 1034 |
+
"epoch": 0.027963248302231354,
|
| 1035 |
+
"grad_norm": 2.170639991760254,
|
| 1036 |
+
"learning_rate": 2.796271637816245e-06,
|
| 1037 |
+
"loss": 1.2254,
|
| 1038 |
+
"step": 1470
|
| 1039 |
+
},
|
| 1040 |
+
{
|
| 1041 |
+
"epoch": 0.028153474481158097,
|
| 1042 |
+
"grad_norm": 2.8608880043029785,
|
| 1043 |
+
"learning_rate": 2.8152938938558117e-06,
|
| 1044 |
+
"loss": 1.0807,
|
| 1045 |
+
"step": 1480
|
| 1046 |
+
},
|
| 1047 |
+
{
|
| 1048 |
+
"epoch": 0.02834370066008484,
|
| 1049 |
+
"grad_norm": 3.440014600753784,
|
| 1050 |
+
"learning_rate": 2.834316149895378e-06,
|
| 1051 |
+
"loss": 1.1255,
|
| 1052 |
+
"step": 1490
|
| 1053 |
+
},
|
| 1054 |
+
{
|
| 1055 |
+
"epoch": 0.028533926839011584,
|
| 1056 |
+
"grad_norm": 10.175577163696289,
|
| 1057 |
+
"learning_rate": 2.853338405934944e-06,
|
| 1058 |
+
"loss": 1.3387,
|
| 1059 |
+
"step": 1500
|
| 1060 |
+
},
|
| 1061 |
+
{
|
| 1062 |
+
"epoch": 0.02872415301793833,
|
| 1063 |
+
"grad_norm": 2.22709321975708,
|
| 1064 |
+
"learning_rate": 2.8723606619745103e-06,
|
| 1065 |
+
"loss": 1.2654,
|
| 1066 |
+
"step": 1510
|
| 1067 |
+
},
|
| 1068 |
+
{
|
| 1069 |
+
"epoch": 0.028914379196865073,
|
| 1070 |
+
"grad_norm": 1.8235417604446411,
|
| 1071 |
+
"learning_rate": 2.891382918014077e-06,
|
| 1072 |
+
"loss": 1.2287,
|
| 1073 |
+
"step": 1520
|
| 1074 |
+
},
|
| 1075 |
+
{
|
| 1076 |
+
"epoch": 0.029104605375791816,
|
| 1077 |
+
"grad_norm": 2.5544168949127197,
|
| 1078 |
+
"learning_rate": 2.910405174053643e-06,
|
| 1079 |
+
"loss": 0.9776,
|
| 1080 |
+
"step": 1530
|
| 1081 |
+
},
|
| 1082 |
+
{
|
| 1083 |
+
"epoch": 0.02929483155471856,
|
| 1084 |
+
"grad_norm": 4.163671016693115,
|
| 1085 |
+
"learning_rate": 2.9294274300932092e-06,
|
| 1086 |
+
"loss": 1.0837,
|
| 1087 |
+
"step": 1540
|
| 1088 |
+
},
|
| 1089 |
+
{
|
| 1090 |
+
"epoch": 0.029485057733645303,
|
| 1091 |
+
"grad_norm": 10.698822021484375,
|
| 1092 |
+
"learning_rate": 2.9484496861327754e-06,
|
| 1093 |
+
"loss": 1.3228,
|
| 1094 |
+
"step": 1550
|
| 1095 |
+
},
|
| 1096 |
+
{
|
| 1097 |
+
"epoch": 0.02967528391257205,
|
| 1098 |
+
"grad_norm": 1.6194937229156494,
|
| 1099 |
+
"learning_rate": 2.967471942172342e-06,
|
| 1100 |
+
"loss": 1.2534,
|
| 1101 |
+
"step": 1560
|
| 1102 |
+
},
|
| 1103 |
+
{
|
| 1104 |
+
"epoch": 0.029865510091498793,
|
| 1105 |
+
"grad_norm": 1.9834601879119873,
|
| 1106 |
+
"learning_rate": 2.986494198211908e-06,
|
| 1107 |
+
"loss": 1.201,
|
| 1108 |
+
"step": 1570
|
| 1109 |
+
},
|
| 1110 |
+
{
|
| 1111 |
+
"epoch": 0.030055736270425536,
|
| 1112 |
+
"grad_norm": 2.591292142868042,
|
| 1113 |
+
"learning_rate": 3.0055164542514744e-06,
|
| 1114 |
+
"loss": 1.0589,
|
| 1115 |
+
"step": 1580
|
| 1116 |
+
},
|
| 1117 |
+
{
|
| 1118 |
+
"epoch": 0.03024596244935228,
|
| 1119 |
+
"grad_norm": 4.2067670822143555,
|
| 1120 |
+
"learning_rate": 3.0245387102910406e-06,
|
| 1121 |
+
"loss": 1.0603,
|
| 1122 |
+
"step": 1590
|
| 1123 |
+
},
|
| 1124 |
+
{
|
| 1125 |
+
"epoch": 0.030436188628279025,
|
| 1126 |
+
"grad_norm": 9.938916206359863,
|
| 1127 |
+
"learning_rate": 3.043560966330607e-06,
|
| 1128 |
+
"loss": 1.2619,
|
| 1129 |
+
"step": 1600
|
| 1130 |
+
},
|
| 1131 |
+
{
|
| 1132 |
+
"epoch": 0.03062641480720577,
|
| 1133 |
+
"grad_norm": 2.7832484245300293,
|
| 1134 |
+
"learning_rate": 3.0625832223701733e-06,
|
| 1135 |
+
"loss": 1.2533,
|
| 1136 |
+
"step": 1610
|
| 1137 |
+
},
|
| 1138 |
+
{
|
| 1139 |
+
"epoch": 0.030816640986132512,
|
| 1140 |
+
"grad_norm": 2.117129325866699,
|
| 1141 |
+
"learning_rate": 3.08160547840974e-06,
|
| 1142 |
+
"loss": 1.1825,
|
| 1143 |
+
"step": 1620
|
| 1144 |
+
},
|
| 1145 |
+
{
|
| 1146 |
+
"epoch": 0.031006867165059255,
|
| 1147 |
+
"grad_norm": 3.0919687747955322,
|
| 1148 |
+
"learning_rate": 3.1006277344493057e-06,
|
| 1149 |
+
"loss": 1.095,
|
| 1150 |
+
"step": 1630
|
| 1151 |
+
},
|
| 1152 |
+
{
|
| 1153 |
+
"epoch": 0.031197093343985998,
|
| 1154 |
+
"grad_norm": 4.166520595550537,
|
| 1155 |
+
"learning_rate": 3.1196499904888723e-06,
|
| 1156 |
+
"loss": 1.047,
|
| 1157 |
+
"step": 1640
|
| 1158 |
+
},
|
| 1159 |
+
{
|
| 1160 |
+
"epoch": 0.031387319522912745,
|
| 1161 |
+
"grad_norm": 12.0921630859375,
|
| 1162 |
+
"learning_rate": 3.1386722465284385e-06,
|
| 1163 |
+
"loss": 1.3526,
|
| 1164 |
+
"step": 1650
|
| 1165 |
+
},
|
| 1166 |
+
{
|
| 1167 |
+
"epoch": 0.03157754570183949,
|
| 1168 |
+
"grad_norm": 1.9751317501068115,
|
| 1169 |
+
"learning_rate": 3.157694502568005e-06,
|
| 1170 |
+
"loss": 1.2864,
|
| 1171 |
+
"step": 1660
|
| 1172 |
+
},
|
| 1173 |
+
{
|
| 1174 |
+
"epoch": 0.03176777188076623,
|
| 1175 |
+
"grad_norm": 2.2880234718322754,
|
| 1176 |
+
"learning_rate": 3.176716758607571e-06,
|
| 1177 |
+
"loss": 1.1079,
|
| 1178 |
+
"step": 1670
|
| 1179 |
+
},
|
| 1180 |
+
{
|
| 1181 |
+
"epoch": 0.031957998059692974,
|
| 1182 |
+
"grad_norm": 2.804194688796997,
|
| 1183 |
+
"learning_rate": 3.1957390146471374e-06,
|
| 1184 |
+
"loss": 0.9666,
|
| 1185 |
+
"step": 1680
|
| 1186 |
+
},
|
| 1187 |
+
{
|
| 1188 |
+
"epoch": 0.03214822423861972,
|
| 1189 |
+
"grad_norm": 4.810030937194824,
|
| 1190 |
+
"learning_rate": 3.2147612706867036e-06,
|
| 1191 |
+
"loss": 1.0979,
|
| 1192 |
+
"step": 1690
|
| 1193 |
+
},
|
| 1194 |
+
{
|
| 1195 |
+
"epoch": 0.03233845041754646,
|
| 1196 |
+
"grad_norm": 9.718046188354492,
|
| 1197 |
+
"learning_rate": 3.23378352672627e-06,
|
| 1198 |
+
"loss": 1.2383,
|
| 1199 |
+
"step": 1700
|
| 1200 |
+
},
|
| 1201 |
+
{
|
| 1202 |
+
"epoch": 0.032528676596473204,
|
| 1203 |
+
"grad_norm": 2.0624125003814697,
|
| 1204 |
+
"learning_rate": 3.252805782765836e-06,
|
| 1205 |
+
"loss": 1.2589,
|
| 1206 |
+
"step": 1710
|
| 1207 |
+
},
|
| 1208 |
+
{
|
| 1209 |
+
"epoch": 0.032718902775399954,
|
| 1210 |
+
"grad_norm": 2.8751795291900635,
|
| 1211 |
+
"learning_rate": 3.2718280388054026e-06,
|
| 1212 |
+
"loss": 1.1319,
|
| 1213 |
+
"step": 1720
|
| 1214 |
+
},
|
| 1215 |
+
{
|
| 1216 |
+
"epoch": 0.0329091289543267,
|
| 1217 |
+
"grad_norm": 2.805138349533081,
|
| 1218 |
+
"learning_rate": 3.2908502948449687e-06,
|
| 1219 |
+
"loss": 0.9922,
|
| 1220 |
+
"step": 1730
|
| 1221 |
+
},
|
| 1222 |
+
{
|
| 1223 |
+
"epoch": 0.03309935513325344,
|
| 1224 |
+
"grad_norm": 4.693927764892578,
|
| 1225 |
+
"learning_rate": 3.3098725508845353e-06,
|
| 1226 |
+
"loss": 1.0518,
|
| 1227 |
+
"step": 1740
|
| 1228 |
+
},
|
| 1229 |
+
{
|
| 1230 |
+
"epoch": 0.03328958131218018,
|
| 1231 |
+
"grad_norm": 9.922603607177734,
|
| 1232 |
+
"learning_rate": 3.3288948069241015e-06,
|
| 1233 |
+
"loss": 1.2417,
|
| 1234 |
+
"step": 1750
|
| 1235 |
+
},
|
| 1236 |
+
{
|
| 1237 |
+
"epoch": 0.033479807491106926,
|
| 1238 |
+
"grad_norm": 1.9441560506820679,
|
| 1239 |
+
"learning_rate": 3.3479170629636677e-06,
|
| 1240 |
+
"loss": 1.2156,
|
| 1241 |
+
"step": 1760
|
| 1242 |
+
},
|
| 1243 |
+
{
|
| 1244 |
+
"epoch": 0.03367003367003367,
|
| 1245 |
+
"grad_norm": 2.1576952934265137,
|
| 1246 |
+
"learning_rate": 3.366939319003234e-06,
|
| 1247 |
+
"loss": 1.1009,
|
| 1248 |
+
"step": 1770
|
| 1249 |
+
},
|
| 1250 |
+
{
|
| 1251 |
+
"epoch": 0.03386025984896041,
|
| 1252 |
+
"grad_norm": 2.93638014793396,
|
| 1253 |
+
"learning_rate": 3.3859615750428005e-06,
|
| 1254 |
+
"loss": 0.9806,
|
| 1255 |
+
"step": 1780
|
| 1256 |
+
},
|
| 1257 |
+
{
|
| 1258 |
+
"epoch": 0.034050486027887156,
|
| 1259 |
+
"grad_norm": 4.772079944610596,
|
| 1260 |
+
"learning_rate": 3.4049838310823667e-06,
|
| 1261 |
+
"loss": 1.0505,
|
| 1262 |
+
"step": 1790
|
| 1263 |
+
},
|
| 1264 |
+
{
|
| 1265 |
+
"epoch": 0.0342407122068139,
|
| 1266 |
+
"grad_norm": 13.75841236114502,
|
| 1267 |
+
"learning_rate": 3.424006087121933e-06,
|
| 1268 |
+
"loss": 1.2653,
|
| 1269 |
+
"step": 1800
|
| 1270 |
+
},
|
| 1271 |
+
{
|
| 1272 |
+
"epoch": 0.03443093838574065,
|
| 1273 |
+
"grad_norm": 2.011861801147461,
|
| 1274 |
+
"learning_rate": 3.443028343161499e-06,
|
| 1275 |
+
"loss": 1.1962,
|
| 1276 |
+
"step": 1810
|
| 1277 |
+
},
|
| 1278 |
+
{
|
| 1279 |
+
"epoch": 0.03462116456466739,
|
| 1280 |
+
"grad_norm": 2.2049922943115234,
|
| 1281 |
+
"learning_rate": 3.4620505992010656e-06,
|
| 1282 |
+
"loss": 1.1636,
|
| 1283 |
+
"step": 1820
|
| 1284 |
+
},
|
| 1285 |
+
{
|
| 1286 |
+
"epoch": 0.034811390743594135,
|
| 1287 |
+
"grad_norm": 3.468641757965088,
|
| 1288 |
+
"learning_rate": 3.481072855240632e-06,
|
| 1289 |
+
"loss": 1.006,
|
| 1290 |
+
"step": 1830
|
| 1291 |
+
},
|
| 1292 |
+
{
|
| 1293 |
+
"epoch": 0.03500161692252088,
|
| 1294 |
+
"grad_norm": 5.194962024688721,
|
| 1295 |
+
"learning_rate": 3.500095111280198e-06,
|
| 1296 |
+
"loss": 1.035,
|
| 1297 |
+
"step": 1840
|
| 1298 |
+
},
|
| 1299 |
+
{
|
| 1300 |
+
"epoch": 0.03519184310144762,
|
| 1301 |
+
"grad_norm": 9.455286979675293,
|
| 1302 |
+
"learning_rate": 3.519117367319764e-06,
|
| 1303 |
+
"loss": 1.1639,
|
| 1304 |
+
"step": 1850
|
| 1305 |
+
},
|
| 1306 |
+
{
|
| 1307 |
+
"epoch": 0.035382069280374365,
|
| 1308 |
+
"grad_norm": 2.2892448902130127,
|
| 1309 |
+
"learning_rate": 3.5381396233593308e-06,
|
| 1310 |
+
"loss": 1.2648,
|
| 1311 |
+
"step": 1860
|
| 1312 |
+
},
|
| 1313 |
+
{
|
| 1314 |
+
"epoch": 0.03557229545930111,
|
| 1315 |
+
"grad_norm": 2.668325185775757,
|
| 1316 |
+
"learning_rate": 3.557161879398897e-06,
|
| 1317 |
+
"loss": 1.1385,
|
| 1318 |
+
"step": 1870
|
| 1319 |
+
},
|
| 1320 |
+
{
|
| 1321 |
+
"epoch": 0.03576252163822785,
|
| 1322 |
+
"grad_norm": 2.897562265396118,
|
| 1323 |
+
"learning_rate": 3.5761841354384635e-06,
|
| 1324 |
+
"loss": 0.9518,
|
| 1325 |
+
"step": 1880
|
| 1326 |
+
},
|
| 1327 |
+
{
|
| 1328 |
+
"epoch": 0.035952747817154594,
|
| 1329 |
+
"grad_norm": 5.355794906616211,
|
| 1330 |
+
"learning_rate": 3.5952063914780293e-06,
|
| 1331 |
+
"loss": 1.059,
|
| 1332 |
+
"step": 1890
|
| 1333 |
+
},
|
| 1334 |
+
{
|
| 1335 |
+
"epoch": 0.03614297399608134,
|
| 1336 |
+
"grad_norm": 11.731189727783203,
|
| 1337 |
+
"learning_rate": 3.614228647517596e-06,
|
| 1338 |
+
"loss": 1.2406,
|
| 1339 |
+
"step": 1900
|
| 1340 |
+
},
|
| 1341 |
+
{
|
| 1342 |
+
"epoch": 0.03633320017500809,
|
| 1343 |
+
"grad_norm": 2.4913065433502197,
|
| 1344 |
+
"learning_rate": 3.633250903557162e-06,
|
| 1345 |
+
"loss": 1.1554,
|
| 1346 |
+
"step": 1910
|
| 1347 |
+
},
|
| 1348 |
+
{
|
| 1349 |
+
"epoch": 0.03652342635393483,
|
| 1350 |
+
"grad_norm": 2.4660778045654297,
|
| 1351 |
+
"learning_rate": 3.6522731595967287e-06,
|
| 1352 |
+
"loss": 1.1604,
|
| 1353 |
+
"step": 1920
|
| 1354 |
+
},
|
| 1355 |
+
{
|
| 1356 |
+
"epoch": 0.036713652532861574,
|
| 1357 |
+
"grad_norm": 2.8727564811706543,
|
| 1358 |
+
"learning_rate": 3.6712954156362944e-06,
|
| 1359 |
+
"loss": 0.986,
|
| 1360 |
+
"step": 1930
|
| 1361 |
+
},
|
| 1362 |
+
{
|
| 1363 |
+
"epoch": 0.03690387871178832,
|
| 1364 |
+
"grad_norm": 5.380633354187012,
|
| 1365 |
+
"learning_rate": 3.690317671675861e-06,
|
| 1366 |
+
"loss": 0.9519,
|
| 1367 |
+
"step": 1940
|
| 1368 |
+
},
|
| 1369 |
+
{
|
| 1370 |
+
"epoch": 0.03709410489071506,
|
| 1371 |
+
"grad_norm": 9.196549415588379,
|
| 1372 |
+
"learning_rate": 3.709339927715427e-06,
|
| 1373 |
+
"loss": 1.253,
|
| 1374 |
+
"step": 1950
|
| 1375 |
+
},
|
| 1376 |
+
{
|
| 1377 |
+
"epoch": 0.0372843310696418,
|
| 1378 |
+
"grad_norm": 1.7812504768371582,
|
| 1379 |
+
"learning_rate": 3.728362183754994e-06,
|
| 1380 |
+
"loss": 1.2104,
|
| 1381 |
+
"step": 1960
|
| 1382 |
+
},
|
| 1383 |
+
{
|
| 1384 |
+
"epoch": 0.037474557248568546,
|
| 1385 |
+
"grad_norm": 2.1316113471984863,
|
| 1386 |
+
"learning_rate": 3.7473844397945596e-06,
|
| 1387 |
+
"loss": 1.1207,
|
| 1388 |
+
"step": 1970
|
| 1389 |
+
},
|
| 1390 |
+
{
|
| 1391 |
+
"epoch": 0.03766478342749529,
|
| 1392 |
+
"grad_norm": 2.813387155532837,
|
| 1393 |
+
"learning_rate": 3.766406695834126e-06,
|
| 1394 |
+
"loss": 0.9173,
|
| 1395 |
+
"step": 1980
|
| 1396 |
+
},
|
| 1397 |
+
{
|
| 1398 |
+
"epoch": 0.03785500960642203,
|
| 1399 |
+
"grad_norm": 4.0899128913879395,
|
| 1400 |
+
"learning_rate": 3.7854289518736923e-06,
|
| 1401 |
+
"loss": 0.9493,
|
| 1402 |
+
"step": 1990
|
| 1403 |
+
},
|
| 1404 |
+
{
|
| 1405 |
+
"epoch": 0.03804523578534878,
|
| 1406 |
+
"grad_norm": 10.877523422241211,
|
| 1407 |
+
"learning_rate": 3.804451207913259e-06,
|
| 1408 |
+
"loss": 1.2015,
|
| 1409 |
+
"step": 2000
|
| 1410 |
+
},
|
| 1411 |
+
{
|
| 1412 |
+
"epoch": 0.038235461964275526,
|
| 1413 |
+
"grad_norm": 2.7726292610168457,
|
| 1414 |
+
"learning_rate": 3.8234734639528255e-06,
|
| 1415 |
+
"loss": 1.2061,
|
| 1416 |
+
"step": 2010
|
| 1417 |
+
},
|
| 1418 |
+
{
|
| 1419 |
+
"epoch": 0.03842568814320227,
|
| 1420 |
+
"grad_norm": 2.1731584072113037,
|
| 1421 |
+
"learning_rate": 3.842495719992391e-06,
|
| 1422 |
+
"loss": 1.106,
|
| 1423 |
+
"step": 2020
|
| 1424 |
+
},
|
| 1425 |
+
{
|
| 1426 |
+
"epoch": 0.03861591432212901,
|
| 1427 |
+
"grad_norm": 3.7517712116241455,
|
| 1428 |
+
"learning_rate": 3.861517976031958e-06,
|
| 1429 |
+
"loss": 0.9798,
|
| 1430 |
+
"step": 2030
|
| 1431 |
+
},
|
| 1432 |
+
{
|
| 1433 |
+
"epoch": 0.038806140501055755,
|
| 1434 |
+
"grad_norm": 5.391069412231445,
|
| 1435 |
+
"learning_rate": 3.880540232071524e-06,
|
| 1436 |
+
"loss": 0.9718,
|
| 1437 |
+
"step": 2040
|
| 1438 |
+
},
|
| 1439 |
+
{
|
| 1440 |
+
"epoch": 0.0389963666799825,
|
| 1441 |
+
"grad_norm": 9.744902610778809,
|
| 1442 |
+
"learning_rate": 3.89956248811109e-06,
|
| 1443 |
+
"loss": 1.2262,
|
| 1444 |
+
"step": 2050
|
| 1445 |
+
},
|
| 1446 |
+
{
|
| 1447 |
+
"epoch": 0.03918659285890924,
|
| 1448 |
+
"grad_norm": 2.6106269359588623,
|
| 1449 |
+
"learning_rate": 3.9185847441506564e-06,
|
| 1450 |
+
"loss": 1.2071,
|
| 1451 |
+
"step": 2060
|
| 1452 |
+
},
|
| 1453 |
+
{
|
| 1454 |
+
"epoch": 0.039376819037835985,
|
| 1455 |
+
"grad_norm": 3.034111738204956,
|
| 1456 |
+
"learning_rate": 3.937607000190223e-06,
|
| 1457 |
+
"loss": 1.1291,
|
| 1458 |
+
"step": 2070
|
| 1459 |
+
},
|
| 1460 |
+
{
|
| 1461 |
+
"epoch": 0.03956704521676273,
|
| 1462 |
+
"grad_norm": 3.5086514949798584,
|
| 1463 |
+
"learning_rate": 3.956629256229789e-06,
|
| 1464 |
+
"loss": 0.9248,
|
| 1465 |
+
"step": 2080
|
| 1466 |
+
},
|
| 1467 |
+
{
|
| 1468 |
+
"epoch": 0.03975727139568948,
|
| 1469 |
+
"grad_norm": 4.488050937652588,
|
| 1470 |
+
"learning_rate": 3.975651512269356e-06,
|
| 1471 |
+
"loss": 1.0084,
|
| 1472 |
+
"step": 2090
|
| 1473 |
+
},
|
| 1474 |
+
{
|
| 1475 |
+
"epoch": 0.03994749757461622,
|
| 1476 |
+
"grad_norm": 10.10869312286377,
|
| 1477 |
+
"learning_rate": 3.994673768308921e-06,
|
| 1478 |
+
"loss": 1.188,
|
| 1479 |
+
"step": 2100
|
| 1480 |
+
},
|
| 1481 |
+
{
|
| 1482 |
+
"epoch": 0.040137723753542964,
|
| 1483 |
+
"grad_norm": 2.787724256515503,
|
| 1484 |
+
"learning_rate": 4.013696024348488e-06,
|
| 1485 |
+
"loss": 1.153,
|
| 1486 |
+
"step": 2110
|
| 1487 |
+
},
|
| 1488 |
+
{
|
| 1489 |
+
"epoch": 0.04032794993246971,
|
| 1490 |
+
"grad_norm": 2.309357166290283,
|
| 1491 |
+
"learning_rate": 4.032718280388054e-06,
|
| 1492 |
+
"loss": 1.0842,
|
| 1493 |
+
"step": 2120
|
| 1494 |
+
},
|
| 1495 |
+
{
|
| 1496 |
+
"epoch": 0.04051817611139645,
|
| 1497 |
+
"grad_norm": 2.9359734058380127,
|
| 1498 |
+
"learning_rate": 4.0517405364276205e-06,
|
| 1499 |
+
"loss": 0.9549,
|
| 1500 |
+
"step": 2130
|
| 1501 |
+
},
|
| 1502 |
+
{
|
| 1503 |
+
"epoch": 0.040708402290323194,
|
| 1504 |
+
"grad_norm": 4.532121658325195,
|
| 1505 |
+
"learning_rate": 4.0707627924671876e-06,
|
| 1506 |
+
"loss": 0.9548,
|
| 1507 |
+
"step": 2140
|
| 1508 |
+
},
|
| 1509 |
+
{
|
| 1510 |
+
"epoch": 0.04089862846924994,
|
| 1511 |
+
"grad_norm": 9.86694049835205,
|
| 1512 |
+
"learning_rate": 4.089785048506753e-06,
|
| 1513 |
+
"loss": 1.1928,
|
| 1514 |
+
"step": 2150
|
| 1515 |
+
},
|
| 1516 |
+
{
|
| 1517 |
+
"epoch": 0.04108885464817668,
|
| 1518 |
+
"grad_norm": 2.4668540954589844,
|
| 1519 |
+
"learning_rate": 4.108807304546319e-06,
|
| 1520 |
+
"loss": 1.2318,
|
| 1521 |
+
"step": 2160
|
| 1522 |
+
},
|
| 1523 |
+
{
|
| 1524 |
+
"epoch": 0.04127908082710342,
|
| 1525 |
+
"grad_norm": 2.501939296722412,
|
| 1526 |
+
"learning_rate": 4.127829560585886e-06,
|
| 1527 |
+
"loss": 1.11,
|
| 1528 |
+
"step": 2170
|
| 1529 |
+
},
|
| 1530 |
+
{
|
| 1531 |
+
"epoch": 0.04146930700603017,
|
| 1532 |
+
"grad_norm": 2.8509225845336914,
|
| 1533 |
+
"learning_rate": 4.146851816625452e-06,
|
| 1534 |
+
"loss": 0.8994,
|
| 1535 |
+
"step": 2180
|
| 1536 |
+
},
|
| 1537 |
+
{
|
| 1538 |
+
"epoch": 0.041659533184956916,
|
| 1539 |
+
"grad_norm": 4.271004676818848,
|
| 1540 |
+
"learning_rate": 4.1658740726650185e-06,
|
| 1541 |
+
"loss": 0.9308,
|
| 1542 |
+
"step": 2190
|
| 1543 |
+
},
|
| 1544 |
+
{
|
| 1545 |
+
"epoch": 0.04184975936388366,
|
| 1546 |
+
"grad_norm": 8.929543495178223,
|
| 1547 |
+
"learning_rate": 4.184896328704585e-06,
|
| 1548 |
+
"loss": 1.1605,
|
| 1549 |
+
"step": 2200
|
| 1550 |
+
},
|
| 1551 |
+
{
|
| 1552 |
+
"epoch": 0.0420399855428104,
|
| 1553 |
+
"grad_norm": 2.176539421081543,
|
| 1554 |
+
"learning_rate": 4.203918584744151e-06,
|
| 1555 |
+
"loss": 1.1261,
|
| 1556 |
+
"step": 2210
|
| 1557 |
+
},
|
| 1558 |
+
{
|
| 1559 |
+
"epoch": 0.042230211721737146,
|
| 1560 |
+
"grad_norm": 3.0560004711151123,
|
| 1561 |
+
"learning_rate": 4.222940840783718e-06,
|
| 1562 |
+
"loss": 1.1041,
|
| 1563 |
+
"step": 2220
|
| 1564 |
+
},
|
| 1565 |
+
{
|
| 1566 |
+
"epoch": 0.04242043790066389,
|
| 1567 |
+
"grad_norm": 2.956686496734619,
|
| 1568 |
+
"learning_rate": 4.241963096823283e-06,
|
| 1569 |
+
"loss": 0.9188,
|
| 1570 |
+
"step": 2230
|
| 1571 |
+
},
|
| 1572 |
+
{
|
| 1573 |
+
"epoch": 0.04261066407959063,
|
| 1574 |
+
"grad_norm": 4.251719951629639,
|
| 1575 |
+
"learning_rate": 4.260985352862849e-06,
|
| 1576 |
+
"loss": 1.0,
|
| 1577 |
+
"step": 2240
|
| 1578 |
+
},
|
| 1579 |
+
{
|
| 1580 |
+
"epoch": 0.042800890258517375,
|
| 1581 |
+
"grad_norm": 11.712019920349121,
|
| 1582 |
+
"learning_rate": 4.280007608902416e-06,
|
| 1583 |
+
"loss": 1.1977,
|
| 1584 |
+
"step": 2250
|
| 1585 |
+
},
|
| 1586 |
+
{
|
| 1587 |
+
"epoch": 0.04299111643744412,
|
| 1588 |
+
"grad_norm": 3.014216899871826,
|
| 1589 |
+
"learning_rate": 4.2990298649419825e-06,
|
| 1590 |
+
"loss": 1.175,
|
| 1591 |
+
"step": 2260
|
| 1592 |
+
},
|
| 1593 |
+
{
|
| 1594 |
+
"epoch": 0.04318134261637086,
|
| 1595 |
+
"grad_norm": 2.524491786956787,
|
| 1596 |
+
"learning_rate": 4.318052120981549e-06,
|
| 1597 |
+
"loss": 1.0855,
|
| 1598 |
+
"step": 2270
|
| 1599 |
+
},
|
| 1600 |
+
{
|
| 1601 |
+
"epoch": 0.04337156879529761,
|
| 1602 |
+
"grad_norm": 3.5122768878936768,
|
| 1603 |
+
"learning_rate": 4.337074377021115e-06,
|
| 1604 |
+
"loss": 0.8957,
|
| 1605 |
+
"step": 2280
|
| 1606 |
+
},
|
| 1607 |
+
{
|
| 1608 |
+
"epoch": 0.043561794974224355,
|
| 1609 |
+
"grad_norm": 5.294569492340088,
|
| 1610 |
+
"learning_rate": 4.356096633060681e-06,
|
| 1611 |
+
"loss": 0.9801,
|
| 1612 |
+
"step": 2290
|
| 1613 |
+
},
|
| 1614 |
+
{
|
| 1615 |
+
"epoch": 0.0437520211531511,
|
| 1616 |
+
"grad_norm": 12.318851470947266,
|
| 1617 |
+
"learning_rate": 4.375118889100248e-06,
|
| 1618 |
+
"loss": 1.2072,
|
| 1619 |
+
"step": 2300
|
| 1620 |
+
},
|
| 1621 |
+
{
|
| 1622 |
+
"epoch": 0.04394224733207784,
|
| 1623 |
+
"grad_norm": 3.4695818424224854,
|
| 1624 |
+
"learning_rate": 4.394141145139814e-06,
|
| 1625 |
+
"loss": 1.1855,
|
| 1626 |
+
"step": 2310
|
| 1627 |
+
},
|
| 1628 |
+
{
|
| 1629 |
+
"epoch": 0.044132473511004584,
|
| 1630 |
+
"grad_norm": 2.193481683731079,
|
| 1631 |
+
"learning_rate": 4.41316340117938e-06,
|
| 1632 |
+
"loss": 1.0368,
|
| 1633 |
+
"step": 2320
|
| 1634 |
+
},
|
| 1635 |
+
{
|
| 1636 |
+
"epoch": 0.04432269968993133,
|
| 1637 |
+
"grad_norm": 3.3650193214416504,
|
| 1638 |
+
"learning_rate": 4.432185657218947e-06,
|
| 1639 |
+
"loss": 0.9339,
|
| 1640 |
+
"step": 2330
|
| 1641 |
+
},
|
| 1642 |
+
{
|
| 1643 |
+
"epoch": 0.04451292586885807,
|
| 1644 |
+
"grad_norm": 4.817994594573975,
|
| 1645 |
+
"learning_rate": 4.451207913258513e-06,
|
| 1646 |
+
"loss": 0.9878,
|
| 1647 |
+
"step": 2340
|
| 1648 |
+
},
|
| 1649 |
+
{
|
| 1650 |
+
"epoch": 0.044703152047784814,
|
| 1651 |
+
"grad_norm": 11.410785675048828,
|
| 1652 |
+
"learning_rate": 4.470230169298079e-06,
|
| 1653 |
+
"loss": 1.1553,
|
| 1654 |
+
"step": 2350
|
| 1655 |
+
},
|
| 1656 |
+
{
|
| 1657 |
+
"epoch": 0.04489337822671156,
|
| 1658 |
+
"grad_norm": 2.329460620880127,
|
| 1659 |
+
"learning_rate": 4.489252425337645e-06,
|
| 1660 |
+
"loss": 1.1137,
|
| 1661 |
+
"step": 2360
|
| 1662 |
+
},
|
| 1663 |
+
{
|
| 1664 |
+
"epoch": 0.04508360440563831,
|
| 1665 |
+
"grad_norm": 4.1374287605285645,
|
| 1666 |
+
"learning_rate": 4.508274681377211e-06,
|
| 1667 |
+
"loss": 1.0883,
|
| 1668 |
+
"step": 2370
|
| 1669 |
+
},
|
| 1670 |
+
{
|
| 1671 |
+
"epoch": 0.04527383058456505,
|
| 1672 |
+
"grad_norm": 3.188446521759033,
|
| 1673 |
+
"learning_rate": 4.527296937416778e-06,
|
| 1674 |
+
"loss": 0.9459,
|
| 1675 |
+
"step": 2380
|
| 1676 |
+
},
|
| 1677 |
+
{
|
| 1678 |
+
"epoch": 0.04546405676349179,
|
| 1679 |
+
"grad_norm": 6.629786014556885,
|
| 1680 |
+
"learning_rate": 4.5463191934563446e-06,
|
| 1681 |
+
"loss": 0.9519,
|
| 1682 |
+
"step": 2390
|
| 1683 |
+
},
|
| 1684 |
+
{
|
| 1685 |
+
"epoch": 0.045654282942418536,
|
| 1686 |
+
"grad_norm": 12.22085189819336,
|
| 1687 |
+
"learning_rate": 4.565341449495911e-06,
|
| 1688 |
+
"loss": 1.1074,
|
| 1689 |
+
"step": 2400
|
| 1690 |
+
},
|
| 1691 |
+
{
|
| 1692 |
+
"epoch": 0.04584450912134528,
|
| 1693 |
+
"grad_norm": 3.0764682292938232,
|
| 1694 |
+
"learning_rate": 4.584363705535477e-06,
|
| 1695 |
+
"loss": 1.1458,
|
| 1696 |
+
"step": 2410
|
| 1697 |
+
},
|
| 1698 |
+
{
|
| 1699 |
+
"epoch": 0.04603473530027202,
|
| 1700 |
+
"grad_norm": 2.767094135284424,
|
| 1701 |
+
"learning_rate": 4.603385961575043e-06,
|
| 1702 |
+
"loss": 1.0658,
|
| 1703 |
+
"step": 2420
|
| 1704 |
+
},
|
| 1705 |
+
{
|
| 1706 |
+
"epoch": 0.046224961479198766,
|
| 1707 |
+
"grad_norm": 3.757636308670044,
|
| 1708 |
+
"learning_rate": 4.622408217614609e-06,
|
| 1709 |
+
"loss": 0.9337,
|
| 1710 |
+
"step": 2430
|
| 1711 |
+
},
|
| 1712 |
+
{
|
| 1713 |
+
"epoch": 0.04641518765812551,
|
| 1714 |
+
"grad_norm": 5.4339447021484375,
|
| 1715 |
+
"learning_rate": 4.641430473654176e-06,
|
| 1716 |
+
"loss": 0.9154,
|
| 1717 |
+
"step": 2440
|
| 1718 |
+
},
|
| 1719 |
+
{
|
| 1720 |
+
"epoch": 0.04660541383705225,
|
| 1721 |
+
"grad_norm": 11.860993385314941,
|
| 1722 |
+
"learning_rate": 4.660452729693742e-06,
|
| 1723 |
+
"loss": 1.1127,
|
| 1724 |
+
"step": 2450
|
| 1725 |
+
},
|
| 1726 |
+
{
|
| 1727 |
+
"epoch": 0.046795640015979,
|
| 1728 |
+
"grad_norm": 2.824115037918091,
|
| 1729 |
+
"learning_rate": 4.679474985733309e-06,
|
| 1730 |
+
"loss": 1.1366,
|
| 1731 |
+
"step": 2460
|
| 1732 |
+
},
|
| 1733 |
+
{
|
| 1734 |
+
"epoch": 0.046985866194905745,
|
| 1735 |
+
"grad_norm": 2.538586139678955,
|
| 1736 |
+
"learning_rate": 4.698497241772875e-06,
|
| 1737 |
+
"loss": 1.0307,
|
| 1738 |
+
"step": 2470
|
| 1739 |
+
},
|
| 1740 |
+
{
|
| 1741 |
+
"epoch": 0.04717609237383249,
|
| 1742 |
+
"grad_norm": 3.817042589187622,
|
| 1743 |
+
"learning_rate": 4.717519497812441e-06,
|
| 1744 |
+
"loss": 0.9,
|
| 1745 |
+
"step": 2480
|
| 1746 |
+
},
|
| 1747 |
+
{
|
| 1748 |
+
"epoch": 0.04736631855275923,
|
| 1749 |
+
"grad_norm": 5.339418888092041,
|
| 1750 |
+
"learning_rate": 4.736541753852007e-06,
|
| 1751 |
+
"loss": 0.9951,
|
| 1752 |
+
"step": 2490
|
| 1753 |
+
},
|
| 1754 |
+
{
|
| 1755 |
+
"epoch": 0.047556544731685975,
|
| 1756 |
+
"grad_norm": 12.489927291870117,
|
| 1757 |
+
"learning_rate": 4.755564009891573e-06,
|
| 1758 |
+
"loss": 1.1541,
|
| 1759 |
+
"step": 2500
|
| 1760 |
+
},
|
| 1761 |
+
{
|
| 1762 |
+
"epoch": 0.04774677091061272,
|
| 1763 |
+
"grad_norm": 2.1420531272888184,
|
| 1764 |
+
"learning_rate": 4.7745862659311395e-06,
|
| 1765 |
+
"loss": 1.1063,
|
| 1766 |
+
"step": 2510
|
| 1767 |
+
},
|
| 1768 |
+
{
|
| 1769 |
+
"epoch": 0.04793699708953946,
|
| 1770 |
+
"grad_norm": 2.2218401432037354,
|
| 1771 |
+
"learning_rate": 4.7936085219707066e-06,
|
| 1772 |
+
"loss": 1.0871,
|
| 1773 |
+
"step": 2520
|
| 1774 |
+
},
|
| 1775 |
+
{
|
| 1776 |
+
"epoch": 0.048127223268466204,
|
| 1777 |
+
"grad_norm": 3.700441360473633,
|
| 1778 |
+
"learning_rate": 4.812630778010273e-06,
|
| 1779 |
+
"loss": 0.873,
|
| 1780 |
+
"step": 2530
|
| 1781 |
+
},
|
| 1782 |
+
{
|
| 1783 |
+
"epoch": 0.04831744944739295,
|
| 1784 |
+
"grad_norm": 5.405223369598389,
|
| 1785 |
+
"learning_rate": 4.831653034049839e-06,
|
| 1786 |
+
"loss": 0.985,
|
| 1787 |
+
"step": 2540
|
| 1788 |
+
},
|
| 1789 |
+
{
|
| 1790 |
+
"epoch": 0.04850767562631969,
|
| 1791 |
+
"grad_norm": 11.029736518859863,
|
| 1792 |
+
"learning_rate": 4.850675290089405e-06,
|
| 1793 |
+
"loss": 1.2141,
|
| 1794 |
+
"step": 2550
|
| 1795 |
+
},
|
| 1796 |
+
{
|
| 1797 |
+
"epoch": 0.04869790180524644,
|
| 1798 |
+
"grad_norm": 2.7142674922943115,
|
| 1799 |
+
"learning_rate": 4.869697546128971e-06,
|
| 1800 |
+
"loss": 1.1559,
|
| 1801 |
+
"step": 2560
|
| 1802 |
+
},
|
| 1803 |
+
{
|
| 1804 |
+
"epoch": 0.048888127984173184,
|
| 1805 |
+
"grad_norm": 2.459038734436035,
|
| 1806 |
+
"learning_rate": 4.8887198021685375e-06,
|
| 1807 |
+
"loss": 1.1262,
|
| 1808 |
+
"step": 2570
|
| 1809 |
+
},
|
| 1810 |
+
{
|
| 1811 |
+
"epoch": 0.04907835416309993,
|
| 1812 |
+
"grad_norm": 3.2301881313323975,
|
| 1813 |
+
"learning_rate": 4.907742058208104e-06,
|
| 1814 |
+
"loss": 0.9321,
|
| 1815 |
+
"step": 2580
|
| 1816 |
+
},
|
| 1817 |
+
{
|
| 1818 |
+
"epoch": 0.04926858034202667,
|
| 1819 |
+
"grad_norm": 5.523041248321533,
|
| 1820 |
+
"learning_rate": 4.92676431424767e-06,
|
| 1821 |
+
"loss": 0.9226,
|
| 1822 |
+
"step": 2590
|
| 1823 |
+
},
|
| 1824 |
+
{
|
| 1825 |
+
"epoch": 0.04945880652095341,
|
| 1826 |
+
"grad_norm": 10.131287574768066,
|
| 1827 |
+
"learning_rate": 4.945786570287237e-06,
|
| 1828 |
+
"loss": 1.1409,
|
| 1829 |
+
"step": 2600
|
| 1830 |
+
},
|
| 1831 |
+
{
|
| 1832 |
+
"epoch": 0.049649032699880156,
|
| 1833 |
+
"grad_norm": 2.8806002140045166,
|
| 1834 |
+
"learning_rate": 4.964808826326803e-06,
|
| 1835 |
+
"loss": 1.1364,
|
| 1836 |
+
"step": 2610
|
| 1837 |
+
},
|
| 1838 |
+
{
|
| 1839 |
+
"epoch": 0.0498392588788069,
|
| 1840 |
+
"grad_norm": 2.400009870529175,
|
| 1841 |
+
"learning_rate": 4.983831082366369e-06,
|
| 1842 |
+
"loss": 1.0847,
|
| 1843 |
+
"step": 2620
|
| 1844 |
+
},
|
| 1845 |
+
{
|
| 1846 |
+
"epoch": 0.05002948505773364,
|
| 1847 |
+
"grad_norm": 4.137524604797363,
|
| 1848 |
+
"learning_rate": 5.002853338405935e-06,
|
| 1849 |
+
"loss": 0.9026,
|
| 1850 |
+
"step": 2630
|
| 1851 |
+
},
|
| 1852 |
+
{
|
| 1853 |
+
"epoch": 0.050219711236660386,
|
| 1854 |
+
"grad_norm": 4.834102153778076,
|
| 1855 |
+
"learning_rate": 5.021875594445501e-06,
|
| 1856 |
+
"loss": 0.936,
|
| 1857 |
+
"step": 2640
|
| 1858 |
+
},
|
| 1859 |
+
{
|
| 1860 |
+
"epoch": 0.050409937415587136,
|
| 1861 |
+
"grad_norm": 10.480986595153809,
|
| 1862 |
+
"learning_rate": 5.040897850485068e-06,
|
| 1863 |
+
"loss": 1.1391,
|
| 1864 |
+
"step": 2650
|
| 1865 |
+
},
|
| 1866 |
+
{
|
| 1867 |
+
"epoch": 0.05060016359451388,
|
| 1868 |
+
"grad_norm": 2.876462697982788,
|
| 1869 |
+
"learning_rate": 5.059920106524634e-06,
|
| 1870 |
+
"loss": 1.1186,
|
| 1871 |
+
"step": 2660
|
| 1872 |
+
},
|
| 1873 |
+
{
|
| 1874 |
+
"epoch": 0.05079038977344062,
|
| 1875 |
+
"grad_norm": 3.254173755645752,
|
| 1876 |
+
"learning_rate": 5.078942362564201e-06,
|
| 1877 |
+
"loss": 1.0468,
|
| 1878 |
+
"step": 2670
|
| 1879 |
+
},
|
| 1880 |
+
{
|
| 1881 |
+
"epoch": 0.050980615952367365,
|
| 1882 |
+
"grad_norm": 3.5466344356536865,
|
| 1883 |
+
"learning_rate": 5.097964618603767e-06,
|
| 1884 |
+
"loss": 0.8944,
|
| 1885 |
+
"step": 2680
|
| 1886 |
+
},
|
| 1887 |
+
{
|
| 1888 |
+
"epoch": 0.05117084213129411,
|
| 1889 |
+
"grad_norm": 4.0647382736206055,
|
| 1890 |
+
"learning_rate": 5.1169868746433324e-06,
|
| 1891 |
+
"loss": 0.8855,
|
| 1892 |
+
"step": 2690
|
| 1893 |
+
},
|
| 1894 |
+
{
|
| 1895 |
+
"epoch": 0.05136106831022085,
|
| 1896 |
+
"grad_norm": 12.590734481811523,
|
| 1897 |
+
"learning_rate": 5.1360091306828995e-06,
|
| 1898 |
+
"loss": 1.1354,
|
| 1899 |
+
"step": 2700
|
| 1900 |
+
},
|
| 1901 |
+
{
|
| 1902 |
+
"epoch": 0.051551294489147595,
|
| 1903 |
+
"grad_norm": 2.858893632888794,
|
| 1904 |
+
"learning_rate": 5.155031386722466e-06,
|
| 1905 |
+
"loss": 1.1345,
|
| 1906 |
+
"step": 2710
|
| 1907 |
+
},
|
| 1908 |
+
{
|
| 1909 |
+
"epoch": 0.05174152066807434,
|
| 1910 |
+
"grad_norm": 2.8196043968200684,
|
| 1911 |
+
"learning_rate": 5.174053642762033e-06,
|
| 1912 |
+
"loss": 1.0826,
|
| 1913 |
+
"step": 2720
|
| 1914 |
+
},
|
| 1915 |
+
{
|
| 1916 |
+
"epoch": 0.05193174684700108,
|
| 1917 |
+
"grad_norm": 3.493431806564331,
|
| 1918 |
+
"learning_rate": 5.193075898801598e-06,
|
| 1919 |
+
"loss": 0.8708,
|
| 1920 |
+
"step": 2730
|
| 1921 |
+
},
|
| 1922 |
+
{
|
| 1923 |
+
"epoch": 0.05212197302592783,
|
| 1924 |
+
"grad_norm": 5.68046236038208,
|
| 1925 |
+
"learning_rate": 5.212098154841164e-06,
|
| 1926 |
+
"loss": 0.937,
|
| 1927 |
+
"step": 2740
|
| 1928 |
+
},
|
| 1929 |
+
{
|
| 1930 |
+
"epoch": 0.052312199204854574,
|
| 1931 |
+
"grad_norm": 13.049890518188477,
|
| 1932 |
+
"learning_rate": 5.231120410880731e-06,
|
| 1933 |
+
"loss": 1.1392,
|
| 1934 |
+
"step": 2750
|
| 1935 |
+
},
|
| 1936 |
+
{
|
| 1937 |
+
"epoch": 0.05250242538378132,
|
| 1938 |
+
"grad_norm": 4.613514423370361,
|
| 1939 |
+
"learning_rate": 5.250142666920297e-06,
|
| 1940 |
+
"loss": 1.1284,
|
| 1941 |
+
"step": 2760
|
| 1942 |
+
},
|
| 1943 |
+
{
|
| 1944 |
+
"epoch": 0.05269265156270806,
|
| 1945 |
+
"grad_norm": 2.3258795738220215,
|
| 1946 |
+
"learning_rate": 5.269164922959863e-06,
|
| 1947 |
+
"loss": 1.0144,
|
| 1948 |
+
"step": 2770
|
| 1949 |
+
},
|
| 1950 |
+
{
|
| 1951 |
+
"epoch": 0.052882877741634804,
|
| 1952 |
+
"grad_norm": 3.8380930423736572,
|
| 1953 |
+
"learning_rate": 5.28818717899943e-06,
|
| 1954 |
+
"loss": 0.9067,
|
| 1955 |
+
"step": 2780
|
| 1956 |
+
},
|
| 1957 |
+
{
|
| 1958 |
+
"epoch": 0.05307310392056155,
|
| 1959 |
+
"grad_norm": 5.028414249420166,
|
| 1960 |
+
"learning_rate": 5.307209435038996e-06,
|
| 1961 |
+
"loss": 0.9445,
|
| 1962 |
+
"step": 2790
|
| 1963 |
+
},
|
| 1964 |
+
{
|
| 1965 |
+
"epoch": 0.05326333009948829,
|
| 1966 |
+
"grad_norm": 9.695432662963867,
|
| 1967 |
+
"learning_rate": 5.326231691078563e-06,
|
| 1968 |
+
"loss": 1.0988,
|
| 1969 |
+
"step": 2800
|
| 1970 |
+
},
|
| 1971 |
+
{
|
| 1972 |
+
"epoch": 0.05345355627841503,
|
| 1973 |
+
"grad_norm": 3.135622262954712,
|
| 1974 |
+
"learning_rate": 5.345253947118128e-06,
|
| 1975 |
+
"loss": 1.1195,
|
| 1976 |
+
"step": 2810
|
| 1977 |
+
},
|
| 1978 |
+
{
|
| 1979 |
+
"epoch": 0.053643782457341777,
|
| 1980 |
+
"grad_norm": 3.463083505630493,
|
| 1981 |
+
"learning_rate": 5.3642762031576945e-06,
|
| 1982 |
+
"loss": 1.0298,
|
| 1983 |
+
"step": 2820
|
| 1984 |
+
},
|
| 1985 |
+
{
|
| 1986 |
+
"epoch": 0.05383400863626853,
|
| 1987 |
+
"grad_norm": 2.976191997528076,
|
| 1988 |
+
"learning_rate": 5.3832984591972615e-06,
|
| 1989 |
+
"loss": 0.8963,
|
| 1990 |
+
"step": 2830
|
| 1991 |
+
},
|
| 1992 |
+
{
|
| 1993 |
+
"epoch": 0.05402423481519527,
|
| 1994 |
+
"grad_norm": 5.485313892364502,
|
| 1995 |
+
"learning_rate": 5.402320715236828e-06,
|
| 1996 |
+
"loss": 0.9498,
|
| 1997 |
+
"step": 2840
|
| 1998 |
+
},
|
| 1999 |
+
{
|
| 2000 |
+
"epoch": 0.05421446099412201,
|
| 2001 |
+
"grad_norm": 12.000988006591797,
|
| 2002 |
+
"learning_rate": 5.421342971276395e-06,
|
| 2003 |
+
"loss": 1.1117,
|
| 2004 |
+
"step": 2850
|
| 2005 |
+
},
|
| 2006 |
+
{
|
| 2007 |
+
"epoch": 0.054404687173048756,
|
| 2008 |
+
"grad_norm": 3.293025493621826,
|
| 2009 |
+
"learning_rate": 5.44036522731596e-06,
|
| 2010 |
+
"loss": 1.1391,
|
| 2011 |
+
"step": 2860
|
| 2012 |
+
},
|
| 2013 |
+
{
|
| 2014 |
+
"epoch": 0.0545949133519755,
|
| 2015 |
+
"grad_norm": 3.216097354888916,
|
| 2016 |
+
"learning_rate": 5.459387483355526e-06,
|
| 2017 |
+
"loss": 1.0316,
|
| 2018 |
+
"step": 2870
|
| 2019 |
+
},
|
| 2020 |
+
{
|
| 2021 |
+
"epoch": 0.05478513953090224,
|
| 2022 |
+
"grad_norm": 3.772177219390869,
|
| 2023 |
+
"learning_rate": 5.478409739395093e-06,
|
| 2024 |
+
"loss": 0.8565,
|
| 2025 |
+
"step": 2880
|
| 2026 |
+
},
|
| 2027 |
+
{
|
| 2028 |
+
"epoch": 0.054975365709828986,
|
| 2029 |
+
"grad_norm": 4.893718242645264,
|
| 2030 |
+
"learning_rate": 5.4974319954346586e-06,
|
| 2031 |
+
"loss": 0.8826,
|
| 2032 |
+
"step": 2890
|
| 2033 |
+
},
|
| 2034 |
+
{
|
| 2035 |
+
"epoch": 0.05516559188875573,
|
| 2036 |
+
"grad_norm": 12.316627502441406,
|
| 2037 |
+
"learning_rate": 5.516454251474225e-06,
|
| 2038 |
+
"loss": 1.1345,
|
| 2039 |
+
"step": 2900
|
| 2040 |
+
},
|
| 2041 |
+
{
|
| 2042 |
+
"epoch": 0.05535581806768247,
|
| 2043 |
+
"grad_norm": 2.428457021713257,
|
| 2044 |
+
"learning_rate": 5.535476507513792e-06,
|
| 2045 |
+
"loss": 1.1332,
|
| 2046 |
+
"step": 2910
|
| 2047 |
+
},
|
| 2048 |
+
{
|
| 2049 |
+
"epoch": 0.055546044246609215,
|
| 2050 |
+
"grad_norm": 2.9872822761535645,
|
| 2051 |
+
"learning_rate": 5.554498763553358e-06,
|
| 2052 |
+
"loss": 1.0649,
|
| 2053 |
+
"step": 2920
|
| 2054 |
+
},
|
| 2055 |
+
{
|
| 2056 |
+
"epoch": 0.055736270425535965,
|
| 2057 |
+
"grad_norm": 3.698500156402588,
|
| 2058 |
+
"learning_rate": 5.573521019592925e-06,
|
| 2059 |
+
"loss": 0.9102,
|
| 2060 |
+
"step": 2930
|
| 2061 |
+
},
|
| 2062 |
+
{
|
| 2063 |
+
"epoch": 0.05592649660446271,
|
| 2064 |
+
"grad_norm": 5.477416515350342,
|
| 2065 |
+
"learning_rate": 5.59254327563249e-06,
|
| 2066 |
+
"loss": 0.9307,
|
| 2067 |
+
"step": 2940
|
| 2068 |
+
},
|
| 2069 |
+
{
|
| 2070 |
+
"epoch": 0.05611672278338945,
|
| 2071 |
+
"grad_norm": 13.570015907287598,
|
| 2072 |
+
"learning_rate": 5.6115655316720565e-06,
|
| 2073 |
+
"loss": 1.1574,
|
| 2074 |
+
"step": 2950
|
| 2075 |
+
},
|
| 2076 |
+
{
|
| 2077 |
+
"epoch": 0.056306948962316195,
|
| 2078 |
+
"grad_norm": 4.1514434814453125,
|
| 2079 |
+
"learning_rate": 5.6305877877116235e-06,
|
| 2080 |
+
"loss": 1.0952,
|
| 2081 |
+
"step": 2960
|
| 2082 |
+
},
|
| 2083 |
+
{
|
| 2084 |
+
"epoch": 0.05649717514124294,
|
| 2085 |
+
"grad_norm": 2.7112059593200684,
|
| 2086 |
+
"learning_rate": 5.649610043751189e-06,
|
| 2087 |
+
"loss": 1.1087,
|
| 2088 |
+
"step": 2970
|
| 2089 |
+
},
|
| 2090 |
+
{
|
| 2091 |
+
"epoch": 0.05668740132016968,
|
| 2092 |
+
"grad_norm": 3.348348617553711,
|
| 2093 |
+
"learning_rate": 5.668632299790756e-06,
|
| 2094 |
+
"loss": 0.893,
|
| 2095 |
+
"step": 2980
|
| 2096 |
+
},
|
| 2097 |
+
{
|
| 2098 |
+
"epoch": 0.056877627499096424,
|
| 2099 |
+
"grad_norm": 5.3222126960754395,
|
| 2100 |
+
"learning_rate": 5.687654555830322e-06,
|
| 2101 |
+
"loss": 0.9064,
|
| 2102 |
+
"step": 2990
|
| 2103 |
+
},
|
| 2104 |
+
{
|
| 2105 |
+
"epoch": 0.05706785367802317,
|
| 2106 |
+
"grad_norm": 11.816397666931152,
|
| 2107 |
+
"learning_rate": 5.706676811869888e-06,
|
| 2108 |
+
"loss": 1.0827,
|
| 2109 |
+
"step": 3000
|
| 2110 |
+
},
|
| 2111 |
+
{
|
| 2112 |
+
"epoch": 0.05725807985694991,
|
| 2113 |
+
"grad_norm": 2.0702426433563232,
|
| 2114 |
+
"learning_rate": 5.725699067909455e-06,
|
| 2115 |
+
"loss": 1.144,
|
| 2116 |
+
"step": 3010
|
| 2117 |
+
},
|
| 2118 |
+
{
|
| 2119 |
+
"epoch": 0.05744830603587666,
|
| 2120 |
+
"grad_norm": 3.0293846130371094,
|
| 2121 |
+
"learning_rate": 5.7447213239490206e-06,
|
| 2122 |
+
"loss": 1.0186,
|
| 2123 |
+
"step": 3020
|
| 2124 |
+
},
|
| 2125 |
+
{
|
| 2126 |
+
"epoch": 0.057638532214803403,
|
| 2127 |
+
"grad_norm": 3.4096548557281494,
|
| 2128 |
+
"learning_rate": 5.763743579988587e-06,
|
| 2129 |
+
"loss": 0.8879,
|
| 2130 |
+
"step": 3030
|
| 2131 |
+
},
|
| 2132 |
+
{
|
| 2133 |
+
"epoch": 0.05782875839373015,
|
| 2134 |
+
"grad_norm": 6.768439769744873,
|
| 2135 |
+
"learning_rate": 5.782765836028154e-06,
|
| 2136 |
+
"loss": 0.8991,
|
| 2137 |
+
"step": 3040
|
| 2138 |
+
},
|
| 2139 |
+
{
|
| 2140 |
+
"epoch": 0.05801898457265689,
|
| 2141 |
+
"grad_norm": 14.614982604980469,
|
| 2142 |
+
"learning_rate": 5.801788092067719e-06,
|
| 2143 |
+
"loss": 1.0877,
|
| 2144 |
+
"step": 3050
|
| 2145 |
+
},
|
| 2146 |
+
{
|
| 2147 |
+
"epoch": 0.05820921075158363,
|
| 2148 |
+
"grad_norm": 2.3279948234558105,
|
| 2149 |
+
"learning_rate": 5.820810348107286e-06,
|
| 2150 |
+
"loss": 1.081,
|
| 2151 |
+
"step": 3060
|
| 2152 |
+
},
|
| 2153 |
+
{
|
| 2154 |
+
"epoch": 0.058399436930510376,
|
| 2155 |
+
"grad_norm": 3.4593429565429688,
|
| 2156 |
+
"learning_rate": 5.839832604146852e-06,
|
| 2157 |
+
"loss": 1.0231,
|
| 2158 |
+
"step": 3070
|
| 2159 |
+
},
|
| 2160 |
+
{
|
| 2161 |
+
"epoch": 0.05858966310943712,
|
| 2162 |
+
"grad_norm": 3.165771484375,
|
| 2163 |
+
"learning_rate": 5.8588548601864185e-06,
|
| 2164 |
+
"loss": 0.8792,
|
| 2165 |
+
"step": 3080
|
| 2166 |
+
},
|
| 2167 |
+
{
|
| 2168 |
+
"epoch": 0.05877988928836386,
|
| 2169 |
+
"grad_norm": 5.759438991546631,
|
| 2170 |
+
"learning_rate": 5.8778771162259855e-06,
|
| 2171 |
+
"loss": 0.9131,
|
| 2172 |
+
"step": 3090
|
| 2173 |
+
},
|
| 2174 |
+
{
|
| 2175 |
+
"epoch": 0.058970115467290606,
|
| 2176 |
+
"grad_norm": 10.794733047485352,
|
| 2177 |
+
"learning_rate": 5.896899372265551e-06,
|
| 2178 |
+
"loss": 1.0556,
|
| 2179 |
+
"step": 3100
|
| 2180 |
+
},
|
| 2181 |
+
{
|
| 2182 |
+
"epoch": 0.059160341646217356,
|
| 2183 |
+
"grad_norm": 2.0568151473999023,
|
| 2184 |
+
"learning_rate": 5.915921628305118e-06,
|
| 2185 |
+
"loss": 1.0646,
|
| 2186 |
+
"step": 3110
|
| 2187 |
+
},
|
| 2188 |
+
{
|
| 2189 |
+
"epoch": 0.0593505678251441,
|
| 2190 |
+
"grad_norm": 3.4895856380462646,
|
| 2191 |
+
"learning_rate": 5.934943884344684e-06,
|
| 2192 |
+
"loss": 1.0352,
|
| 2193 |
+
"step": 3120
|
| 2194 |
+
},
|
| 2195 |
+
{
|
| 2196 |
+
"epoch": 0.05954079400407084,
|
| 2197 |
+
"grad_norm": 3.709806442260742,
|
| 2198 |
+
"learning_rate": 5.953966140384249e-06,
|
| 2199 |
+
"loss": 0.8928,
|
| 2200 |
+
"step": 3130
|
| 2201 |
+
},
|
| 2202 |
+
{
|
| 2203 |
+
"epoch": 0.059731020182997585,
|
| 2204 |
+
"grad_norm": 4.89426326751709,
|
| 2205 |
+
"learning_rate": 5.972988396423816e-06,
|
| 2206 |
+
"loss": 0.881,
|
| 2207 |
+
"step": 3140
|
| 2208 |
+
},
|
| 2209 |
+
{
|
| 2210 |
+
"epoch": 0.05992124636192433,
|
| 2211 |
+
"grad_norm": 13.595807075500488,
|
| 2212 |
+
"learning_rate": 5.992010652463383e-06,
|
| 2213 |
+
"loss": 1.0825,
|
| 2214 |
+
"step": 3150
|
| 2215 |
+
},
|
| 2216 |
+
{
|
| 2217 |
+
"epoch": 0.06011147254085107,
|
| 2218 |
+
"grad_norm": 3.318986177444458,
|
| 2219 |
+
"learning_rate": 6.011032908502949e-06,
|
| 2220 |
+
"loss": 1.1474,
|
| 2221 |
+
"step": 3160
|
| 2222 |
+
},
|
| 2223 |
+
{
|
| 2224 |
+
"epoch": 0.060301698719777815,
|
| 2225 |
+
"grad_norm": 3.450166940689087,
|
| 2226 |
+
"learning_rate": 6.030055164542516e-06,
|
| 2227 |
+
"loss": 1.0437,
|
| 2228 |
+
"step": 3170
|
| 2229 |
+
},
|
| 2230 |
+
{
|
| 2231 |
+
"epoch": 0.06049192489870456,
|
| 2232 |
+
"grad_norm": 3.8872604370117188,
|
| 2233 |
+
"learning_rate": 6.049077420582081e-06,
|
| 2234 |
+
"loss": 0.8966,
|
| 2235 |
+
"step": 3180
|
| 2236 |
+
},
|
| 2237 |
+
{
|
| 2238 |
+
"epoch": 0.0606821510776313,
|
| 2239 |
+
"grad_norm": 4.919650554656982,
|
| 2240 |
+
"learning_rate": 6.068099676621648e-06,
|
| 2241 |
+
"loss": 0.9155,
|
| 2242 |
+
"step": 3190
|
| 2243 |
+
},
|
| 2244 |
+
{
|
| 2245 |
+
"epoch": 0.06087237725655805,
|
| 2246 |
+
"grad_norm": 12.513046264648438,
|
| 2247 |
+
"learning_rate": 6.087121932661214e-06,
|
| 2248 |
+
"loss": 1.0846,
|
| 2249 |
+
"step": 3200
|
| 2250 |
+
},
|
| 2251 |
+
{
|
| 2252 |
+
"epoch": 0.061062603435484794,
|
| 2253 |
+
"grad_norm": 3.5747430324554443,
|
| 2254 |
+
"learning_rate": 6.10614418870078e-06,
|
| 2255 |
+
"loss": 1.1239,
|
| 2256 |
+
"step": 3210
|
| 2257 |
+
},
|
| 2258 |
+
{
|
| 2259 |
+
"epoch": 0.06125282961441154,
|
| 2260 |
+
"grad_norm": 2.480370044708252,
|
| 2261 |
+
"learning_rate": 6.125166444740347e-06,
|
| 2262 |
+
"loss": 1.0142,
|
| 2263 |
+
"step": 3220
|
| 2264 |
+
},
|
| 2265 |
+
{
|
| 2266 |
+
"epoch": 0.06144305579333828,
|
| 2267 |
+
"grad_norm": 3.4333581924438477,
|
| 2268 |
+
"learning_rate": 6.144188700779913e-06,
|
| 2269 |
+
"loss": 0.9134,
|
| 2270 |
+
"step": 3230
|
| 2271 |
+
},
|
| 2272 |
+
{
|
| 2273 |
+
"epoch": 0.061633281972265024,
|
| 2274 |
+
"grad_norm": 5.920953750610352,
|
| 2275 |
+
"learning_rate": 6.16321095681948e-06,
|
| 2276 |
+
"loss": 0.9426,
|
| 2277 |
+
"step": 3240
|
| 2278 |
+
},
|
| 2279 |
+
{
|
| 2280 |
+
"epoch": 0.06182350815119177,
|
| 2281 |
+
"grad_norm": 11.068296432495117,
|
| 2282 |
+
"learning_rate": 6.182233212859046e-06,
|
| 2283 |
+
"loss": 0.9753,
|
| 2284 |
+
"step": 3250
|
| 2285 |
+
},
|
| 2286 |
+
{
|
| 2287 |
+
"epoch": 0.06201373433011851,
|
| 2288 |
+
"grad_norm": 2.670910120010376,
|
| 2289 |
+
"learning_rate": 6.201255468898611e-06,
|
| 2290 |
+
"loss": 1.0863,
|
| 2291 |
+
"step": 3260
|
| 2292 |
+
},
|
| 2293 |
+
{
|
| 2294 |
+
"epoch": 0.06220396050904525,
|
| 2295 |
+
"grad_norm": 2.3734078407287598,
|
| 2296 |
+
"learning_rate": 6.220277724938178e-06,
|
| 2297 |
+
"loss": 1.0623,
|
| 2298 |
+
"step": 3270
|
| 2299 |
+
},
|
| 2300 |
+
{
|
| 2301 |
+
"epoch": 0.062394186687971996,
|
| 2302 |
+
"grad_norm": 5.874599933624268,
|
| 2303 |
+
"learning_rate": 6.239299980977745e-06,
|
| 2304 |
+
"loss": 0.8873,
|
| 2305 |
+
"step": 3280
|
| 2306 |
+
},
|
| 2307 |
+
{
|
| 2308 |
+
"epoch": 0.06258441286689874,
|
| 2309 |
+
"grad_norm": 6.023142337799072,
|
| 2310 |
+
"learning_rate": 6.25832223701731e-06,
|
| 2311 |
+
"loss": 0.8765,
|
| 2312 |
+
"step": 3290
|
| 2313 |
+
},
|
| 2314 |
+
{
|
| 2315 |
+
"epoch": 0.06277463904582549,
|
| 2316 |
+
"grad_norm": 12.106161117553711,
|
| 2317 |
+
"learning_rate": 6.277344493056877e-06,
|
| 2318 |
+
"loss": 1.0472,
|
| 2319 |
+
"step": 3300
|
| 2320 |
+
},
|
| 2321 |
+
{
|
| 2322 |
+
"epoch": 0.06296486522475223,
|
| 2323 |
+
"grad_norm": 2.7873780727386475,
|
| 2324 |
+
"learning_rate": 6.296366749096443e-06,
|
| 2325 |
+
"loss": 1.0871,
|
| 2326 |
+
"step": 3310
|
| 2327 |
+
},
|
| 2328 |
+
{
|
| 2329 |
+
"epoch": 0.06315509140367898,
|
| 2330 |
+
"grad_norm": 2.410355806350708,
|
| 2331 |
+
"learning_rate": 6.31538900513601e-06,
|
| 2332 |
+
"loss": 1.0264,
|
| 2333 |
+
"step": 3320
|
| 2334 |
+
},
|
| 2335 |
+
{
|
| 2336 |
+
"epoch": 0.06334531758260571,
|
| 2337 |
+
"grad_norm": 3.43695068359375,
|
| 2338 |
+
"learning_rate": 6.334411261175576e-06,
|
| 2339 |
+
"loss": 0.8591,
|
| 2340 |
+
"step": 3330
|
| 2341 |
+
},
|
| 2342 |
+
{
|
| 2343 |
+
"epoch": 0.06353554376153246,
|
| 2344 |
+
"grad_norm": 5.210920810699463,
|
| 2345 |
+
"learning_rate": 6.353433517215142e-06,
|
| 2346 |
+
"loss": 0.9006,
|
| 2347 |
+
"step": 3340
|
| 2348 |
+
},
|
| 2349 |
+
{
|
| 2350 |
+
"epoch": 0.06372576994045921,
|
| 2351 |
+
"grad_norm": 13.646373748779297,
|
| 2352 |
+
"learning_rate": 6.372455773254709e-06,
|
| 2353 |
+
"loss": 1.039,
|
| 2354 |
+
"step": 3350
|
| 2355 |
+
},
|
| 2356 |
+
{
|
| 2357 |
+
"epoch": 0.06391599611938595,
|
| 2358 |
+
"grad_norm": 3.9488167762756348,
|
| 2359 |
+
"learning_rate": 6.391478029294275e-06,
|
| 2360 |
+
"loss": 1.1264,
|
| 2361 |
+
"step": 3360
|
| 2362 |
+
},
|
| 2363 |
+
{
|
| 2364 |
+
"epoch": 0.0641062222983127,
|
| 2365 |
+
"grad_norm": 2.9603095054626465,
|
| 2366 |
+
"learning_rate": 6.410500285333842e-06,
|
| 2367 |
+
"loss": 1.0785,
|
| 2368 |
+
"step": 3370
|
| 2369 |
+
},
|
| 2370 |
+
{
|
| 2371 |
+
"epoch": 0.06429644847723943,
|
| 2372 |
+
"grad_norm": 6.125018119812012,
|
| 2373 |
+
"learning_rate": 6.429522541373407e-06,
|
| 2374 |
+
"loss": 0.8835,
|
| 2375 |
+
"step": 3380
|
| 2376 |
+
},
|
| 2377 |
+
{
|
| 2378 |
+
"epoch": 0.06448667465616618,
|
| 2379 |
+
"grad_norm": 6.037325382232666,
|
| 2380 |
+
"learning_rate": 6.448544797412973e-06,
|
| 2381 |
+
"loss": 0.9131,
|
| 2382 |
+
"step": 3390
|
| 2383 |
+
},
|
| 2384 |
+
{
|
| 2385 |
+
"epoch": 0.06467690083509292,
|
| 2386 |
+
"grad_norm": 16.08112144470215,
|
| 2387 |
+
"learning_rate": 6.46756705345254e-06,
|
| 2388 |
+
"loss": 1.111,
|
| 2389 |
+
"step": 3400
|
| 2390 |
+
},
|
| 2391 |
+
{
|
| 2392 |
+
"epoch": 0.06486712701401967,
|
| 2393 |
+
"grad_norm": 2.1979708671569824,
|
| 2394 |
+
"learning_rate": 6.486589309492107e-06,
|
| 2395 |
+
"loss": 1.0869,
|
| 2396 |
+
"step": 3410
|
| 2397 |
+
},
|
| 2398 |
+
{
|
| 2399 |
+
"epoch": 0.06505735319294641,
|
| 2400 |
+
"grad_norm": 3.191075086593628,
|
| 2401 |
+
"learning_rate": 6.505611565531672e-06,
|
| 2402 |
+
"loss": 1.0359,
|
| 2403 |
+
"step": 3420
|
| 2404 |
+
},
|
| 2405 |
+
{
|
| 2406 |
+
"epoch": 0.06524757937187316,
|
| 2407 |
+
"grad_norm": 4.361050128936768,
|
| 2408 |
+
"learning_rate": 6.524633821571239e-06,
|
| 2409 |
+
"loss": 0.8945,
|
| 2410 |
+
"step": 3430
|
| 2411 |
+
},
|
| 2412 |
+
{
|
| 2413 |
+
"epoch": 0.06543780555079991,
|
| 2414 |
+
"grad_norm": 5.246515274047852,
|
| 2415 |
+
"learning_rate": 6.543656077610805e-06,
|
| 2416 |
+
"loss": 0.898,
|
| 2417 |
+
"step": 3440
|
| 2418 |
+
},
|
| 2419 |
+
{
|
| 2420 |
+
"epoch": 0.06562803172972664,
|
| 2421 |
+
"grad_norm": 11.343035697937012,
|
| 2422 |
+
"learning_rate": 6.562678333650372e-06,
|
| 2423 |
+
"loss": 1.0329,
|
| 2424 |
+
"step": 3450
|
| 2425 |
+
},
|
| 2426 |
+
{
|
| 2427 |
+
"epoch": 0.0658182579086534,
|
| 2428 |
+
"grad_norm": 3.319098711013794,
|
| 2429 |
+
"learning_rate": 6.5817005896899375e-06,
|
| 2430 |
+
"loss": 1.1156,
|
| 2431 |
+
"step": 3460
|
| 2432 |
+
},
|
| 2433 |
+
{
|
| 2434 |
+
"epoch": 0.06600848408758013,
|
| 2435 |
+
"grad_norm": 2.946639060974121,
|
| 2436 |
+
"learning_rate": 6.600722845729504e-06,
|
| 2437 |
+
"loss": 1.018,
|
| 2438 |
+
"step": 3470
|
| 2439 |
+
},
|
| 2440 |
+
{
|
| 2441 |
+
"epoch": 0.06619871026650688,
|
| 2442 |
+
"grad_norm": 2.6161160469055176,
|
| 2443 |
+
"learning_rate": 6.619745101769071e-06,
|
| 2444 |
+
"loss": 0.8507,
|
| 2445 |
+
"step": 3480
|
| 2446 |
+
},
|
| 2447 |
+
{
|
| 2448 |
+
"epoch": 0.06638893644543362,
|
| 2449 |
+
"grad_norm": 5.574872970581055,
|
| 2450 |
+
"learning_rate": 6.638767357808637e-06,
|
| 2451 |
+
"loss": 0.9083,
|
| 2452 |
+
"step": 3490
|
| 2453 |
+
},
|
| 2454 |
+
{
|
| 2455 |
+
"epoch": 0.06657916262436037,
|
| 2456 |
+
"grad_norm": 13.42422866821289,
|
| 2457 |
+
"learning_rate": 6.657789613848203e-06,
|
| 2458 |
+
"loss": 1.0902,
|
| 2459 |
+
"step": 3500
|
| 2460 |
+
},
|
| 2461 |
+
{
|
| 2462 |
+
"epoch": 0.0667693888032871,
|
| 2463 |
+
"grad_norm": 2.8455140590667725,
|
| 2464 |
+
"learning_rate": 6.676811869887769e-06,
|
| 2465 |
+
"loss": 1.06,
|
| 2466 |
+
"step": 3510
|
| 2467 |
+
},
|
| 2468 |
+
{
|
| 2469 |
+
"epoch": 0.06695961498221385,
|
| 2470 |
+
"grad_norm": 2.6613621711730957,
|
| 2471 |
+
"learning_rate": 6.695834125927335e-06,
|
| 2472 |
+
"loss": 0.989,
|
| 2473 |
+
"step": 3520
|
| 2474 |
+
},
|
| 2475 |
+
{
|
| 2476 |
+
"epoch": 0.0671498411611406,
|
| 2477 |
+
"grad_norm": 3.7422332763671875,
|
| 2478 |
+
"learning_rate": 6.7148563819669024e-06,
|
| 2479 |
+
"loss": 0.8448,
|
| 2480 |
+
"step": 3530
|
| 2481 |
+
},
|
| 2482 |
+
{
|
| 2483 |
+
"epoch": 0.06734006734006734,
|
| 2484 |
+
"grad_norm": 5.147526264190674,
|
| 2485 |
+
"learning_rate": 6.733878638006468e-06,
|
| 2486 |
+
"loss": 0.8717,
|
| 2487 |
+
"step": 3540
|
| 2488 |
+
},
|
| 2489 |
+
{
|
| 2490 |
+
"epoch": 0.06753029351899409,
|
| 2491 |
+
"grad_norm": 12.03034782409668,
|
| 2492 |
+
"learning_rate": 6.752900894046034e-06,
|
| 2493 |
+
"loss": 1.048,
|
| 2494 |
+
"step": 3550
|
| 2495 |
+
},
|
| 2496 |
+
{
|
| 2497 |
+
"epoch": 0.06772051969792083,
|
| 2498 |
+
"grad_norm": 3.214045763015747,
|
| 2499 |
+
"learning_rate": 6.771923150085601e-06,
|
| 2500 |
+
"loss": 1.0937,
|
| 2501 |
+
"step": 3560
|
| 2502 |
+
},
|
| 2503 |
+
{
|
| 2504 |
+
"epoch": 0.06791074587684758,
|
| 2505 |
+
"grad_norm": 2.7989227771759033,
|
| 2506 |
+
"learning_rate": 6.790945406125167e-06,
|
| 2507 |
+
"loss": 1.0337,
|
| 2508 |
+
"step": 3570
|
| 2509 |
+
},
|
| 2510 |
+
{
|
| 2511 |
+
"epoch": 0.06810097205577431,
|
| 2512 |
+
"grad_norm": 4.597136497497559,
|
| 2513 |
+
"learning_rate": 6.809967662164733e-06,
|
| 2514 |
+
"loss": 0.8806,
|
| 2515 |
+
"step": 3580
|
| 2516 |
+
},
|
| 2517 |
+
{
|
| 2518 |
+
"epoch": 0.06829119823470106,
|
| 2519 |
+
"grad_norm": 4.616443634033203,
|
| 2520 |
+
"learning_rate": 6.8289899182042995e-06,
|
| 2521 |
+
"loss": 0.8547,
|
| 2522 |
+
"step": 3590
|
| 2523 |
+
},
|
| 2524 |
+
{
|
| 2525 |
+
"epoch": 0.0684814244136278,
|
| 2526 |
+
"grad_norm": 11.670774459838867,
|
| 2527 |
+
"learning_rate": 6.848012174243866e-06,
|
| 2528 |
+
"loss": 1.0259,
|
| 2529 |
+
"step": 3600
|
| 2530 |
+
},
|
| 2531 |
+
{
|
| 2532 |
+
"epoch": 0.06867165059255455,
|
| 2533 |
+
"grad_norm": 2.3249611854553223,
|
| 2534 |
+
"learning_rate": 6.867034430283433e-06,
|
| 2535 |
+
"loss": 1.045,
|
| 2536 |
+
"step": 3610
|
| 2537 |
+
},
|
| 2538 |
+
{
|
| 2539 |
+
"epoch": 0.0688618767714813,
|
| 2540 |
+
"grad_norm": 4.721532344818115,
|
| 2541 |
+
"learning_rate": 6.886056686322998e-06,
|
| 2542 |
+
"loss": 1.0629,
|
| 2543 |
+
"step": 3620
|
| 2544 |
+
},
|
| 2545 |
+
{
|
| 2546 |
+
"epoch": 0.06905210295040803,
|
| 2547 |
+
"grad_norm": 3.195577621459961,
|
| 2548 |
+
"learning_rate": 6.905078942362565e-06,
|
| 2549 |
+
"loss": 0.8311,
|
| 2550 |
+
"step": 3630
|
| 2551 |
+
},
|
| 2552 |
+
{
|
| 2553 |
+
"epoch": 0.06924232912933478,
|
| 2554 |
+
"grad_norm": 5.499499320983887,
|
| 2555 |
+
"learning_rate": 6.924101198402131e-06,
|
| 2556 |
+
"loss": 0.8811,
|
| 2557 |
+
"step": 3640
|
| 2558 |
+
},
|
| 2559 |
+
{
|
| 2560 |
+
"epoch": 0.06943255530826152,
|
| 2561 |
+
"grad_norm": 12.689728736877441,
|
| 2562 |
+
"learning_rate": 6.943123454441697e-06,
|
| 2563 |
+
"loss": 1.0668,
|
| 2564 |
+
"step": 3650
|
| 2565 |
+
},
|
| 2566 |
+
{
|
| 2567 |
+
"epoch": 0.06962278148718827,
|
| 2568 |
+
"grad_norm": 2.8369383811950684,
|
| 2569 |
+
"learning_rate": 6.962145710481264e-06,
|
| 2570 |
+
"loss": 1.066,
|
| 2571 |
+
"step": 3660
|
| 2572 |
+
},
|
| 2573 |
+
{
|
| 2574 |
+
"epoch": 0.069813007666115,
|
| 2575 |
+
"grad_norm": 5.4221415519714355,
|
| 2576 |
+
"learning_rate": 6.98116796652083e-06,
|
| 2577 |
+
"loss": 1.0518,
|
| 2578 |
+
"step": 3670
|
| 2579 |
+
},
|
| 2580 |
+
{
|
| 2581 |
+
"epoch": 0.07000323384504176,
|
| 2582 |
+
"grad_norm": 2.920156717300415,
|
| 2583 |
+
"learning_rate": 7.000190222560396e-06,
|
| 2584 |
+
"loss": 0.8456,
|
| 2585 |
+
"step": 3680
|
| 2586 |
+
},
|
| 2587 |
+
{
|
| 2588 |
+
"epoch": 0.07019346002396849,
|
| 2589 |
+
"grad_norm": 6.14293909072876,
|
| 2590 |
+
"learning_rate": 7.019212478599963e-06,
|
| 2591 |
+
"loss": 0.8598,
|
| 2592 |
+
"step": 3690
|
| 2593 |
+
},
|
| 2594 |
+
{
|
| 2595 |
+
"epoch": 0.07038368620289524,
|
| 2596 |
+
"grad_norm": 14.368626594543457,
|
| 2597 |
+
"learning_rate": 7.038234734639528e-06,
|
| 2598 |
+
"loss": 1.0146,
|
| 2599 |
+
"step": 3700
|
| 2600 |
+
},
|
| 2601 |
+
{
|
| 2602 |
+
"epoch": 0.070573912381822,
|
| 2603 |
+
"grad_norm": 3.4393813610076904,
|
| 2604 |
+
"learning_rate": 7.057256990679095e-06,
|
| 2605 |
+
"loss": 1.1011,
|
| 2606 |
+
"step": 3710
|
| 2607 |
+
},
|
| 2608 |
+
{
|
| 2609 |
+
"epoch": 0.07076413856074873,
|
| 2610 |
+
"grad_norm": 2.811824083328247,
|
| 2611 |
+
"learning_rate": 7.0762792467186615e-06,
|
| 2612 |
+
"loss": 1.0224,
|
| 2613 |
+
"step": 3720
|
| 2614 |
+
},
|
| 2615 |
+
{
|
| 2616 |
+
"epoch": 0.07095436473967548,
|
| 2617 |
+
"grad_norm": 3.577205181121826,
|
| 2618 |
+
"learning_rate": 7.095301502758227e-06,
|
| 2619 |
+
"loss": 0.8828,
|
| 2620 |
+
"step": 3730
|
| 2621 |
+
},
|
| 2622 |
+
{
|
| 2623 |
+
"epoch": 0.07114459091860222,
|
| 2624 |
+
"grad_norm": 5.109273910522461,
|
| 2625 |
+
"learning_rate": 7.114323758797794e-06,
|
| 2626 |
+
"loss": 0.8378,
|
| 2627 |
+
"step": 3740
|
| 2628 |
+
},
|
| 2629 |
+
{
|
| 2630 |
+
"epoch": 0.07133481709752897,
|
| 2631 |
+
"grad_norm": 12.113494873046875,
|
| 2632 |
+
"learning_rate": 7.13334601483736e-06,
|
| 2633 |
+
"loss": 1.0819,
|
| 2634 |
+
"step": 3750
|
| 2635 |
+
},
|
| 2636 |
+
{
|
| 2637 |
+
"epoch": 0.0715250432764557,
|
| 2638 |
+
"grad_norm": 2.632756471633911,
|
| 2639 |
+
"learning_rate": 7.152368270876927e-06,
|
| 2640 |
+
"loss": 1.0574,
|
| 2641 |
+
"step": 3760
|
| 2642 |
+
},
|
| 2643 |
+
{
|
| 2644 |
+
"epoch": 0.07171526945538245,
|
| 2645 |
+
"grad_norm": 2.616201162338257,
|
| 2646 |
+
"learning_rate": 7.171390526916493e-06,
|
| 2647 |
+
"loss": 1.0205,
|
| 2648 |
+
"step": 3770
|
| 2649 |
+
},
|
| 2650 |
+
{
|
| 2651 |
+
"epoch": 0.07190549563430919,
|
| 2652 |
+
"grad_norm": 4.030309200286865,
|
| 2653 |
+
"learning_rate": 7.190412782956059e-06,
|
| 2654 |
+
"loss": 0.8747,
|
| 2655 |
+
"step": 3780
|
| 2656 |
+
},
|
| 2657 |
+
{
|
| 2658 |
+
"epoch": 0.07209572181323594,
|
| 2659 |
+
"grad_norm": 5.87321138381958,
|
| 2660 |
+
"learning_rate": 7.209435038995626e-06,
|
| 2661 |
+
"loss": 0.9093,
|
| 2662 |
+
"step": 3790
|
| 2663 |
+
},
|
| 2664 |
+
{
|
| 2665 |
+
"epoch": 0.07228594799216267,
|
| 2666 |
+
"grad_norm": 13.199514389038086,
|
| 2667 |
+
"learning_rate": 7.228457295035192e-06,
|
| 2668 |
+
"loss": 1.0841,
|
| 2669 |
+
"step": 3800
|
| 2670 |
+
},
|
| 2671 |
+
{
|
| 2672 |
+
"epoch": 0.07247617417108942,
|
| 2673 |
+
"grad_norm": 3.2827208042144775,
|
| 2674 |
+
"learning_rate": 7.247479551074757e-06,
|
| 2675 |
+
"loss": 1.0602,
|
| 2676 |
+
"step": 3810
|
| 2677 |
+
},
|
| 2678 |
+
{
|
| 2679 |
+
"epoch": 0.07266640035001617,
|
| 2680 |
+
"grad_norm": 2.744004726409912,
|
| 2681 |
+
"learning_rate": 7.266501807114324e-06,
|
| 2682 |
+
"loss": 0.9903,
|
| 2683 |
+
"step": 3820
|
| 2684 |
+
},
|
| 2685 |
+
{
|
| 2686 |
+
"epoch": 0.07285662652894291,
|
| 2687 |
+
"grad_norm": 4.373607635498047,
|
| 2688 |
+
"learning_rate": 7.28552406315389e-06,
|
| 2689 |
+
"loss": 0.8325,
|
| 2690 |
+
"step": 3830
|
| 2691 |
+
},
|
| 2692 |
+
{
|
| 2693 |
+
"epoch": 0.07304685270786966,
|
| 2694 |
+
"grad_norm": 5.0198140144348145,
|
| 2695 |
+
"learning_rate": 7.304546319193457e-06,
|
| 2696 |
+
"loss": 0.9334,
|
| 2697 |
+
"step": 3840
|
| 2698 |
+
},
|
| 2699 |
+
{
|
| 2700 |
+
"epoch": 0.0732370788867964,
|
| 2701 |
+
"grad_norm": 13.514430046081543,
|
| 2702 |
+
"learning_rate": 7.3235685752330235e-06,
|
| 2703 |
+
"loss": 1.1131,
|
| 2704 |
+
"step": 3850
|
| 2705 |
+
},
|
| 2706 |
+
{
|
| 2707 |
+
"epoch": 0.07342730506572315,
|
| 2708 |
+
"grad_norm": 2.1664793491363525,
|
| 2709 |
+
"learning_rate": 7.342590831272589e-06,
|
| 2710 |
+
"loss": 1.0527,
|
| 2711 |
+
"step": 3860
|
| 2712 |
+
},
|
| 2713 |
+
{
|
| 2714 |
+
"epoch": 0.07361753124464988,
|
| 2715 |
+
"grad_norm": 6.562690258026123,
|
| 2716 |
+
"learning_rate": 7.361613087312156e-06,
|
| 2717 |
+
"loss": 0.9892,
|
| 2718 |
+
"step": 3870
|
| 2719 |
+
},
|
| 2720 |
+
{
|
| 2721 |
+
"epoch": 0.07380775742357663,
|
| 2722 |
+
"grad_norm": 3.725823163986206,
|
| 2723 |
+
"learning_rate": 7.380635343351722e-06,
|
| 2724 |
+
"loss": 0.8403,
|
| 2725 |
+
"step": 3880
|
| 2726 |
+
},
|
| 2727 |
+
{
|
| 2728 |
+
"epoch": 0.07399798360250337,
|
| 2729 |
+
"grad_norm": 5.953464031219482,
|
| 2730 |
+
"learning_rate": 7.399657599391289e-06,
|
| 2731 |
+
"loss": 0.8569,
|
| 2732 |
+
"step": 3890
|
| 2733 |
+
},
|
| 2734 |
+
{
|
| 2735 |
+
"epoch": 0.07418820978143012,
|
| 2736 |
+
"grad_norm": 10.803670883178711,
|
| 2737 |
+
"learning_rate": 7.418679855430854e-06,
|
| 2738 |
+
"loss": 1.0628,
|
| 2739 |
+
"step": 3900
|
| 2740 |
+
},
|
| 2741 |
+
{
|
| 2742 |
+
"epoch": 0.07437843596035687,
|
| 2743 |
+
"grad_norm": 2.3450770378112793,
|
| 2744 |
+
"learning_rate": 7.437702111470421e-06,
|
| 2745 |
+
"loss": 1.0782,
|
| 2746 |
+
"step": 3910
|
| 2747 |
+
},
|
| 2748 |
+
{
|
| 2749 |
+
"epoch": 0.0745686621392836,
|
| 2750 |
+
"grad_norm": 2.5900728702545166,
|
| 2751 |
+
"learning_rate": 7.456724367509988e-06,
|
| 2752 |
+
"loss": 0.9397,
|
| 2753 |
+
"step": 3920
|
| 2754 |
+
},
|
| 2755 |
+
{
|
| 2756 |
+
"epoch": 0.07475888831821036,
|
| 2757 |
+
"grad_norm": 3.811370849609375,
|
| 2758 |
+
"learning_rate": 7.475746623549554e-06,
|
| 2759 |
+
"loss": 0.8472,
|
| 2760 |
+
"step": 3930
|
| 2761 |
+
},
|
| 2762 |
+
{
|
| 2763 |
+
"epoch": 0.07494911449713709,
|
| 2764 |
+
"grad_norm": 8.507999420166016,
|
| 2765 |
+
"learning_rate": 7.494768879589119e-06,
|
| 2766 |
+
"loss": 0.8761,
|
| 2767 |
+
"step": 3940
|
| 2768 |
+
},
|
| 2769 |
+
{
|
| 2770 |
+
"epoch": 0.07513934067606384,
|
| 2771 |
+
"grad_norm": 11.520349502563477,
|
| 2772 |
+
"learning_rate": 7.513791135628686e-06,
|
| 2773 |
+
"loss": 1.0814,
|
| 2774 |
+
"step": 3950
|
| 2775 |
+
},
|
| 2776 |
+
{
|
| 2777 |
+
"epoch": 0.07532956685499058,
|
| 2778 |
+
"grad_norm": 2.7183773517608643,
|
| 2779 |
+
"learning_rate": 7.532813391668252e-06,
|
| 2780 |
+
"loss": 1.0746,
|
| 2781 |
+
"step": 3960
|
| 2782 |
+
},
|
| 2783 |
+
{
|
| 2784 |
+
"epoch": 0.07551979303391733,
|
| 2785 |
+
"grad_norm": 2.7066807746887207,
|
| 2786 |
+
"learning_rate": 7.551835647707819e-06,
|
| 2787 |
+
"loss": 0.9913,
|
| 2788 |
+
"step": 3970
|
| 2789 |
+
},
|
| 2790 |
+
{
|
| 2791 |
+
"epoch": 0.07571001921284407,
|
| 2792 |
+
"grad_norm": 2.972797393798828,
|
| 2793 |
+
"learning_rate": 7.570857903747385e-06,
|
| 2794 |
+
"loss": 0.8899,
|
| 2795 |
+
"step": 3980
|
| 2796 |
+
},
|
| 2797 |
+
{
|
| 2798 |
+
"epoch": 0.07590024539177082,
|
| 2799 |
+
"grad_norm": 5.18887996673584,
|
| 2800 |
+
"learning_rate": 7.589880159786951e-06,
|
| 2801 |
+
"loss": 0.8659,
|
| 2802 |
+
"step": 3990
|
| 2803 |
+
},
|
| 2804 |
+
{
|
| 2805 |
+
"epoch": 0.07609047157069757,
|
| 2806 |
+
"grad_norm": 13.543824195861816,
|
| 2807 |
+
"learning_rate": 7.608902415826518e-06,
|
| 2808 |
+
"loss": 1.003,
|
| 2809 |
+
"step": 4000
|
| 2810 |
+
}
|
| 2811 |
+
],
|
| 2812 |
+
"logging_steps": 10,
|
| 2813 |
+
"max_steps": 105138,
|
| 2814 |
+
"num_input_tokens_seen": 0,
|
| 2815 |
+
"num_train_epochs": 2,
|
| 2816 |
+
"save_steps": 2000,
|
| 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": 5.400871388028125e+18,
|
| 2830 |
+
"train_batch_size": 7,
|
| 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 sha256:50eef3897db5e724787ac3792e964d67c93ce813c03af7872a4e7a74143fbdc0
|
| 3 |
+
size 5240
|