Upload folder using huggingface_hub
Browse files- README.md +21 -30
- adapter_config.json +3 -3
- adapter_model.safetensors +1 -1
- all_results.json +10 -10
- checkpoint-100/README.md +202 -0
- checkpoint-100/adapter_config.json +34 -0
- checkpoint-100/adapter_model.safetensors +3 -0
- checkpoint-100/optimizer.pt +3 -0
- checkpoint-100/rng_state.pth +3 -0
- checkpoint-100/scheduler.pt +3 -0
- checkpoint-100/special_tokens_map.json +17 -0
- checkpoint-100/tokenizer.json +3 -0
- checkpoint-100/tokenizer_config.json +2065 -0
- checkpoint-100/trainer_state.json +893 -0
- checkpoint-100/training_args.bin +3 -0
- eval_results.json +5 -5
- train_results.json +6 -6
- trainer_log.jsonl +121 -298
- trainer_state.json +512 -899
- training_args.bin +1 -1
- training_eval_loss.png +0 -0
- training_loss.png +0 -0
README.md
CHANGED
|
@@ -19,7 +19,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 19 |
|
| 20 |
This model is a fine-tuned version of [meta-llama/Llama-3.2-3B-Instruct](https://huggingface.co/meta-llama/Llama-3.2-3B-Instruct) on the relianceV2 dataset.
|
| 21 |
It achieves the following results on the evaluation set:
|
| 22 |
-
- Loss: 0.
|
| 23 |
|
| 24 |
## Model description
|
| 25 |
|
|
@@ -53,35 +53,26 @@ The following hyperparameters were used during training:
|
|
| 53 |
|
| 54 |
| Training Loss | Epoch | Step | Validation Loss |
|
| 55 |
|:-------------:|:------:|:----:|:---------------:|
|
| 56 |
-
| 0.
|
| 57 |
-
| 0.
|
| 58 |
-
| 0.
|
| 59 |
-
| 0.
|
| 60 |
-
| 0.
|
| 61 |
-
| 0.
|
| 62 |
-
| 0.
|
| 63 |
-
| 0.
|
| 64 |
-
| 0.
|
| 65 |
-
| 0.
|
| 66 |
-
| 0.
|
| 67 |
-
| 0.
|
| 68 |
-
| 0.
|
| 69 |
-
| 0.
|
| 70 |
-
| 0.
|
| 71 |
-
| 0.
|
| 72 |
-
| 0.
|
| 73 |
-
| 0.
|
| 74 |
-
| 0.
|
| 75 |
-
| 0.
|
| 76 |
-
| 0.0071 | 3.5897 | 105 | 0.0108 |
|
| 77 |
-
| 0.006 | 3.7607 | 110 | 0.0107 |
|
| 78 |
-
| 0.0065 | 3.9316 | 115 | 0.0106 |
|
| 79 |
-
| 0.0076 | 4.1026 | 120 | 0.0106 |
|
| 80 |
-
| 0.0057 | 4.2735 | 125 | 0.0106 |
|
| 81 |
-
| 0.0071 | 4.4444 | 130 | 0.0106 |
|
| 82 |
-
| 0.0055 | 4.6154 | 135 | 0.0106 |
|
| 83 |
-
| 0.0053 | 4.7863 | 140 | 0.0106 |
|
| 84 |
-
| 0.0074 | 4.9573 | 145 | 0.0106 |
|
| 85 |
|
| 86 |
|
| 87 |
### Framework versions
|
|
|
|
| 19 |
|
| 20 |
This model is a fine-tuned version of [meta-llama/Llama-3.2-3B-Instruct](https://huggingface.co/meta-llama/Llama-3.2-3B-Instruct) on the relianceV2 dataset.
|
| 21 |
It achieves the following results on the evaluation set:
|
| 22 |
+
- Loss: 0.0118
|
| 23 |
|
| 24 |
## Model description
|
| 25 |
|
|
|
|
| 53 |
|
| 54 |
| Training Loss | Epoch | Step | Validation Loss |
|
| 55 |
|:-------------:|:------:|:----:|:---------------:|
|
| 56 |
+
| 0.0395 | 0.2424 | 5 | 0.0433 |
|
| 57 |
+
| 0.0324 | 0.4848 | 10 | 0.0300 |
|
| 58 |
+
| 0.024 | 0.7273 | 15 | 0.0244 |
|
| 59 |
+
| 0.0189 | 0.9697 | 20 | 0.0212 |
|
| 60 |
+
| 0.0171 | 1.2303 | 25 | 0.0190 |
|
| 61 |
+
| 0.0146 | 1.4727 | 30 | 0.0173 |
|
| 62 |
+
| 0.0144 | 1.7152 | 35 | 0.0161 |
|
| 63 |
+
| 0.0104 | 1.9576 | 40 | 0.0155 |
|
| 64 |
+
| 0.0143 | 2.2182 | 45 | 0.0152 |
|
| 65 |
+
| 0.0117 | 2.4606 | 50 | 0.0141 |
|
| 66 |
+
| 0.015 | 2.7030 | 55 | 0.0136 |
|
| 67 |
+
| 0.0092 | 2.9455 | 60 | 0.0131 |
|
| 68 |
+
| 0.008 | 3.2061 | 65 | 0.0127 |
|
| 69 |
+
| 0.0109 | 3.4485 | 70 | 0.0125 |
|
| 70 |
+
| 0.0085 | 3.6909 | 75 | 0.0122 |
|
| 71 |
+
| 0.0089 | 3.9333 | 80 | 0.0120 |
|
| 72 |
+
| 0.0074 | 4.1939 | 85 | 0.0118 |
|
| 73 |
+
| 0.0074 | 4.4364 | 90 | 0.0118 |
|
| 74 |
+
| 0.0066 | 4.6788 | 95 | 0.0118 |
|
| 75 |
+
| 0.0065 | 4.9212 | 100 | 0.0118 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 76 |
|
| 77 |
|
| 78 |
### Framework versions
|
adapter_config.json
CHANGED
|
@@ -22,11 +22,11 @@
|
|
| 22 |
"target_modules": [
|
| 23 |
"v_proj",
|
| 24 |
"k_proj",
|
| 25 |
-
"q_proj",
|
| 26 |
-
"o_proj",
|
| 27 |
"up_proj",
|
|
|
|
|
|
|
| 28 |
"gate_proj",
|
| 29 |
-
"
|
| 30 |
],
|
| 31 |
"task_type": "CAUSAL_LM",
|
| 32 |
"use_dora": false,
|
|
|
|
| 22 |
"target_modules": [
|
| 23 |
"v_proj",
|
| 24 |
"k_proj",
|
|
|
|
|
|
|
| 25 |
"up_proj",
|
| 26 |
+
"down_proj",
|
| 27 |
+
"o_proj",
|
| 28 |
"gate_proj",
|
| 29 |
+
"q_proj"
|
| 30 |
],
|
| 31 |
"task_type": "CAUSAL_LM",
|
| 32 |
"use_dora": false,
|
adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1556140392
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6845c47c00421880852ea09974a8ab569a317709f856b8fcfcf66e573fdb36ea
|
| 3 |
size 1556140392
|
all_results.json
CHANGED
|
@@ -1,12 +1,12 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch": 4.
|
| 3 |
-
"eval_loss": 0.
|
| 4 |
-
"eval_runtime":
|
| 5 |
-
"eval_samples_per_second":
|
| 6 |
-
"eval_steps_per_second": 1.
|
| 7 |
-
"total_flos":
|
| 8 |
-
"train_loss": 0.
|
| 9 |
-
"train_runtime":
|
| 10 |
-
"train_samples_per_second": 1.
|
| 11 |
-
"train_steps_per_second": 0.
|
| 12 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 4.921212121212121,
|
| 3 |
+
"eval_loss": 0.011823245324194431,
|
| 4 |
+
"eval_runtime": 10.3534,
|
| 5 |
+
"eval_samples_per_second": 4.829,
|
| 6 |
+
"eval_steps_per_second": 1.256,
|
| 7 |
+
"total_flos": 2.442632501894185e+17,
|
| 8 |
+
"train_loss": 0.016519791511818767,
|
| 9 |
+
"train_runtime": 2009.2463,
|
| 10 |
+
"train_samples_per_second": 1.637,
|
| 11 |
+
"train_steps_per_second": 0.05
|
| 12 |
}
|
checkpoint-100/README.md
ADDED
|
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: unsloth/Llama-3.2-3B-Instruct
|
| 3 |
+
library_name: peft
|
| 4 |
+
---
|
| 5 |
+
|
| 6 |
+
# Model Card for Model ID
|
| 7 |
+
|
| 8 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
| 9 |
+
|
| 10 |
+
|
| 11 |
+
|
| 12 |
+
## Model Details
|
| 13 |
+
|
| 14 |
+
### Model Description
|
| 15 |
+
|
| 16 |
+
<!-- Provide a longer summary of what this model is. -->
|
| 17 |
+
|
| 18 |
+
|
| 19 |
+
|
| 20 |
+
- **Developed by:** [More Information Needed]
|
| 21 |
+
- **Funded by [optional]:** [More Information Needed]
|
| 22 |
+
- **Shared by [optional]:** [More Information Needed]
|
| 23 |
+
- **Model type:** [More Information Needed]
|
| 24 |
+
- **Language(s) (NLP):** [More Information Needed]
|
| 25 |
+
- **License:** [More Information Needed]
|
| 26 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
| 27 |
+
|
| 28 |
+
### Model Sources [optional]
|
| 29 |
+
|
| 30 |
+
<!-- Provide the basic links for the model. -->
|
| 31 |
+
|
| 32 |
+
- **Repository:** [More Information Needed]
|
| 33 |
+
- **Paper [optional]:** [More Information Needed]
|
| 34 |
+
- **Demo [optional]:** [More Information Needed]
|
| 35 |
+
|
| 36 |
+
## Uses
|
| 37 |
+
|
| 38 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
| 39 |
+
|
| 40 |
+
### Direct Use
|
| 41 |
+
|
| 42 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
| 43 |
+
|
| 44 |
+
[More Information Needed]
|
| 45 |
+
|
| 46 |
+
### Downstream Use [optional]
|
| 47 |
+
|
| 48 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
| 49 |
+
|
| 50 |
+
[More Information Needed]
|
| 51 |
+
|
| 52 |
+
### Out-of-Scope Use
|
| 53 |
+
|
| 54 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
| 55 |
+
|
| 56 |
+
[More Information Needed]
|
| 57 |
+
|
| 58 |
+
## Bias, Risks, and Limitations
|
| 59 |
+
|
| 60 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
| 61 |
+
|
| 62 |
+
[More Information Needed]
|
| 63 |
+
|
| 64 |
+
### Recommendations
|
| 65 |
+
|
| 66 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
| 67 |
+
|
| 68 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
| 69 |
+
|
| 70 |
+
## How to Get Started with the Model
|
| 71 |
+
|
| 72 |
+
Use the code below to get started with the model.
|
| 73 |
+
|
| 74 |
+
[More Information Needed]
|
| 75 |
+
|
| 76 |
+
## Training Details
|
| 77 |
+
|
| 78 |
+
### Training Data
|
| 79 |
+
|
| 80 |
+
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
| 81 |
+
|
| 82 |
+
[More Information Needed]
|
| 83 |
+
|
| 84 |
+
### Training Procedure
|
| 85 |
+
|
| 86 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
| 87 |
+
|
| 88 |
+
#### Preprocessing [optional]
|
| 89 |
+
|
| 90 |
+
[More Information Needed]
|
| 91 |
+
|
| 92 |
+
|
| 93 |
+
#### Training Hyperparameters
|
| 94 |
+
|
| 95 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
| 96 |
+
|
| 97 |
+
#### Speeds, Sizes, Times [optional]
|
| 98 |
+
|
| 99 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
| 100 |
+
|
| 101 |
+
[More Information Needed]
|
| 102 |
+
|
| 103 |
+
## Evaluation
|
| 104 |
+
|
| 105 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
| 106 |
+
|
| 107 |
+
### Testing Data, Factors & Metrics
|
| 108 |
+
|
| 109 |
+
#### Testing Data
|
| 110 |
+
|
| 111 |
+
<!-- This should link to a Dataset Card if possible. -->
|
| 112 |
+
|
| 113 |
+
[More Information Needed]
|
| 114 |
+
|
| 115 |
+
#### Factors
|
| 116 |
+
|
| 117 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
| 118 |
+
|
| 119 |
+
[More Information Needed]
|
| 120 |
+
|
| 121 |
+
#### Metrics
|
| 122 |
+
|
| 123 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
| 124 |
+
|
| 125 |
+
[More Information Needed]
|
| 126 |
+
|
| 127 |
+
### Results
|
| 128 |
+
|
| 129 |
+
[More Information Needed]
|
| 130 |
+
|
| 131 |
+
#### Summary
|
| 132 |
+
|
| 133 |
+
|
| 134 |
+
|
| 135 |
+
## Model Examination [optional]
|
| 136 |
+
|
| 137 |
+
<!-- Relevant interpretability work for the model goes here -->
|
| 138 |
+
|
| 139 |
+
[More Information Needed]
|
| 140 |
+
|
| 141 |
+
## Environmental Impact
|
| 142 |
+
|
| 143 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
| 144 |
+
|
| 145 |
+
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
| 146 |
+
|
| 147 |
+
- **Hardware Type:** [More Information Needed]
|
| 148 |
+
- **Hours used:** [More Information Needed]
|
| 149 |
+
- **Cloud Provider:** [More Information Needed]
|
| 150 |
+
- **Compute Region:** [More Information Needed]
|
| 151 |
+
- **Carbon Emitted:** [More Information Needed]
|
| 152 |
+
|
| 153 |
+
## Technical Specifications [optional]
|
| 154 |
+
|
| 155 |
+
### Model Architecture and Objective
|
| 156 |
+
|
| 157 |
+
[More Information Needed]
|
| 158 |
+
|
| 159 |
+
### Compute Infrastructure
|
| 160 |
+
|
| 161 |
+
[More Information Needed]
|
| 162 |
+
|
| 163 |
+
#### Hardware
|
| 164 |
+
|
| 165 |
+
[More Information Needed]
|
| 166 |
+
|
| 167 |
+
#### Software
|
| 168 |
+
|
| 169 |
+
[More Information Needed]
|
| 170 |
+
|
| 171 |
+
## Citation [optional]
|
| 172 |
+
|
| 173 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
| 174 |
+
|
| 175 |
+
**BibTeX:**
|
| 176 |
+
|
| 177 |
+
[More Information Needed]
|
| 178 |
+
|
| 179 |
+
**APA:**
|
| 180 |
+
|
| 181 |
+
[More Information Needed]
|
| 182 |
+
|
| 183 |
+
## Glossary [optional]
|
| 184 |
+
|
| 185 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
| 186 |
+
|
| 187 |
+
[More Information Needed]
|
| 188 |
+
|
| 189 |
+
## More Information [optional]
|
| 190 |
+
|
| 191 |
+
[More Information Needed]
|
| 192 |
+
|
| 193 |
+
## Model Card Authors [optional]
|
| 194 |
+
|
| 195 |
+
[More Information Needed]
|
| 196 |
+
|
| 197 |
+
## Model Card Contact
|
| 198 |
+
|
| 199 |
+
[More Information Needed]
|
| 200 |
+
### Framework versions
|
| 201 |
+
|
| 202 |
+
- PEFT 0.12.0
|
checkpoint-100/adapter_config.json
ADDED
|
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "unsloth/Llama-3.2-3B-Instruct",
|
| 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": 256,
|
| 14 |
+
"lora_dropout": 0.0,
|
| 15 |
+
"megatron_config": null,
|
| 16 |
+
"megatron_core": "megatron.core",
|
| 17 |
+
"modules_to_save": null,
|
| 18 |
+
"peft_type": "LORA",
|
| 19 |
+
"r": 256,
|
| 20 |
+
"rank_pattern": {},
|
| 21 |
+
"revision": null,
|
| 22 |
+
"target_modules": [
|
| 23 |
+
"v_proj",
|
| 24 |
+
"k_proj",
|
| 25 |
+
"up_proj",
|
| 26 |
+
"down_proj",
|
| 27 |
+
"o_proj",
|
| 28 |
+
"gate_proj",
|
| 29 |
+
"q_proj"
|
| 30 |
+
],
|
| 31 |
+
"task_type": "CAUSAL_LM",
|
| 32 |
+
"use_dora": false,
|
| 33 |
+
"use_rslora": false
|
| 34 |
+
}
|
checkpoint-100/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6845c47c00421880852ea09974a8ab569a317709f856b8fcfcf66e573fdb36ea
|
| 3 |
+
size 1556140392
|
checkpoint-100/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8a52238644cbe63ae9918d88b607d79b3c3333c5c418abf08b7a2e09fccb737a
|
| 3 |
+
size 3112505578
|
checkpoint-100/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:564a22a315e885b2f6a58c1213c1f0a6568bc482fcf1ad0064e4eb5e0442ac6b
|
| 3 |
+
size 14308
|
checkpoint-100/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:49d60a69e2379be2053e816cbaff31e6c931b5922dd86c71c9eaf473299cbf62
|
| 3 |
+
size 1064
|
checkpoint-100/special_tokens_map.json
ADDED
|
@@ -0,0 +1,17 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<|begin_of_text|>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "<|eot_id|>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": "<|eot_id|>"
|
| 17 |
+
}
|
checkpoint-100/tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
|
| 3 |
+
size 17209920
|
checkpoint-100/tokenizer_config.json
ADDED
|
@@ -0,0 +1,2065 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"128000": {
|
| 4 |
+
"content": "<|begin_of_text|>",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"128001": {
|
| 12 |
+
"content": "<|end_of_text|>",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"128002": {
|
| 20 |
+
"content": "<|reserved_special_token_0|>",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"128003": {
|
| 28 |
+
"content": "<|reserved_special_token_1|>",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"128004": {
|
| 36 |
+
"content": "<|finetune_right_pad_id|>",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
},
|
| 43 |
+
"128005": {
|
| 44 |
+
"content": "<|reserved_special_token_2|>",
|
| 45 |
+
"lstrip": false,
|
| 46 |
+
"normalized": false,
|
| 47 |
+
"rstrip": false,
|
| 48 |
+
"single_word": false,
|
| 49 |
+
"special": true
|
| 50 |
+
},
|
| 51 |
+
"128006": {
|
| 52 |
+
"content": "<|start_header_id|>",
|
| 53 |
+
"lstrip": false,
|
| 54 |
+
"normalized": false,
|
| 55 |
+
"rstrip": false,
|
| 56 |
+
"single_word": false,
|
| 57 |
+
"special": true
|
| 58 |
+
},
|
| 59 |
+
"128007": {
|
| 60 |
+
"content": "<|end_header_id|>",
|
| 61 |
+
"lstrip": false,
|
| 62 |
+
"normalized": false,
|
| 63 |
+
"rstrip": false,
|
| 64 |
+
"single_word": false,
|
| 65 |
+
"special": true
|
| 66 |
+
},
|
| 67 |
+
"128008": {
|
| 68 |
+
"content": "<|eom_id|>",
|
| 69 |
+
"lstrip": false,
|
| 70 |
+
"normalized": false,
|
| 71 |
+
"rstrip": false,
|
| 72 |
+
"single_word": false,
|
| 73 |
+
"special": true
|
| 74 |
+
},
|
| 75 |
+
"128009": {
|
| 76 |
+
"content": "<|eot_id|>",
|
| 77 |
+
"lstrip": false,
|
| 78 |
+
"normalized": false,
|
| 79 |
+
"rstrip": false,
|
| 80 |
+
"single_word": false,
|
| 81 |
+
"special": true
|
| 82 |
+
},
|
| 83 |
+
"128010": {
|
| 84 |
+
"content": "<|python_tag|>",
|
| 85 |
+
"lstrip": false,
|
| 86 |
+
"normalized": false,
|
| 87 |
+
"rstrip": false,
|
| 88 |
+
"single_word": false,
|
| 89 |
+
"special": true
|
| 90 |
+
},
|
| 91 |
+
"128011": {
|
| 92 |
+
"content": "<|reserved_special_token_3|>",
|
| 93 |
+
"lstrip": false,
|
| 94 |
+
"normalized": false,
|
| 95 |
+
"rstrip": false,
|
| 96 |
+
"single_word": false,
|
| 97 |
+
"special": true
|
| 98 |
+
},
|
| 99 |
+
"128012": {
|
| 100 |
+
"content": "<|reserved_special_token_4|>",
|
| 101 |
+
"lstrip": false,
|
| 102 |
+
"normalized": false,
|
| 103 |
+
"rstrip": false,
|
| 104 |
+
"single_word": false,
|
| 105 |
+
"special": true
|
| 106 |
+
},
|
| 107 |
+
"128013": {
|
| 108 |
+
"content": "<|reserved_special_token_5|>",
|
| 109 |
+
"lstrip": false,
|
| 110 |
+
"normalized": false,
|
| 111 |
+
"rstrip": false,
|
| 112 |
+
"single_word": false,
|
| 113 |
+
"special": true
|
| 114 |
+
},
|
| 115 |
+
"128014": {
|
| 116 |
+
"content": "<|reserved_special_token_6|>",
|
| 117 |
+
"lstrip": false,
|
| 118 |
+
"normalized": false,
|
| 119 |
+
"rstrip": false,
|
| 120 |
+
"single_word": false,
|
| 121 |
+
"special": true
|
| 122 |
+
},
|
| 123 |
+
"128015": {
|
| 124 |
+
"content": "<|reserved_special_token_7|>",
|
| 125 |
+
"lstrip": false,
|
| 126 |
+
"normalized": false,
|
| 127 |
+
"rstrip": false,
|
| 128 |
+
"single_word": false,
|
| 129 |
+
"special": true
|
| 130 |
+
},
|
| 131 |
+
"128016": {
|
| 132 |
+
"content": "<|reserved_special_token_8|>",
|
| 133 |
+
"lstrip": false,
|
| 134 |
+
"normalized": false,
|
| 135 |
+
"rstrip": false,
|
| 136 |
+
"single_word": false,
|
| 137 |
+
"special": true
|
| 138 |
+
},
|
| 139 |
+
"128017": {
|
| 140 |
+
"content": "<|reserved_special_token_9|>",
|
| 141 |
+
"lstrip": false,
|
| 142 |
+
"normalized": false,
|
| 143 |
+
"rstrip": false,
|
| 144 |
+
"single_word": false,
|
| 145 |
+
"special": true
|
| 146 |
+
},
|
| 147 |
+
"128018": {
|
| 148 |
+
"content": "<|reserved_special_token_10|>",
|
| 149 |
+
"lstrip": false,
|
| 150 |
+
"normalized": false,
|
| 151 |
+
"rstrip": false,
|
| 152 |
+
"single_word": false,
|
| 153 |
+
"special": true
|
| 154 |
+
},
|
| 155 |
+
"128019": {
|
| 156 |
+
"content": "<|reserved_special_token_11|>",
|
| 157 |
+
"lstrip": false,
|
| 158 |
+
"normalized": false,
|
| 159 |
+
"rstrip": false,
|
| 160 |
+
"single_word": false,
|
| 161 |
+
"special": true
|
| 162 |
+
},
|
| 163 |
+
"128020": {
|
| 164 |
+
"content": "<|reserved_special_token_12|>",
|
| 165 |
+
"lstrip": false,
|
| 166 |
+
"normalized": false,
|
| 167 |
+
"rstrip": false,
|
| 168 |
+
"single_word": false,
|
| 169 |
+
"special": true
|
| 170 |
+
},
|
| 171 |
+
"128021": {
|
| 172 |
+
"content": "<|reserved_special_token_13|>",
|
| 173 |
+
"lstrip": false,
|
| 174 |
+
"normalized": false,
|
| 175 |
+
"rstrip": false,
|
| 176 |
+
"single_word": false,
|
| 177 |
+
"special": true
|
| 178 |
+
},
|
| 179 |
+
"128022": {
|
| 180 |
+
"content": "<|reserved_special_token_14|>",
|
| 181 |
+
"lstrip": false,
|
| 182 |
+
"normalized": false,
|
| 183 |
+
"rstrip": false,
|
| 184 |
+
"single_word": false,
|
| 185 |
+
"special": true
|
| 186 |
+
},
|
| 187 |
+
"128023": {
|
| 188 |
+
"content": "<|reserved_special_token_15|>",
|
| 189 |
+
"lstrip": false,
|
| 190 |
+
"normalized": false,
|
| 191 |
+
"rstrip": false,
|
| 192 |
+
"single_word": false,
|
| 193 |
+
"special": true
|
| 194 |
+
},
|
| 195 |
+
"128024": {
|
| 196 |
+
"content": "<|reserved_special_token_16|>",
|
| 197 |
+
"lstrip": false,
|
| 198 |
+
"normalized": false,
|
| 199 |
+
"rstrip": false,
|
| 200 |
+
"single_word": false,
|
| 201 |
+
"special": true
|
| 202 |
+
},
|
| 203 |
+
"128025": {
|
| 204 |
+
"content": "<|reserved_special_token_17|>",
|
| 205 |
+
"lstrip": false,
|
| 206 |
+
"normalized": false,
|
| 207 |
+
"rstrip": false,
|
| 208 |
+
"single_word": false,
|
| 209 |
+
"special": true
|
| 210 |
+
},
|
| 211 |
+
"128026": {
|
| 212 |
+
"content": "<|reserved_special_token_18|>",
|
| 213 |
+
"lstrip": false,
|
| 214 |
+
"normalized": false,
|
| 215 |
+
"rstrip": false,
|
| 216 |
+
"single_word": false,
|
| 217 |
+
"special": true
|
| 218 |
+
},
|
| 219 |
+
"128027": {
|
| 220 |
+
"content": "<|reserved_special_token_19|>",
|
| 221 |
+
"lstrip": false,
|
| 222 |
+
"normalized": false,
|
| 223 |
+
"rstrip": false,
|
| 224 |
+
"single_word": false,
|
| 225 |
+
"special": true
|
| 226 |
+
},
|
| 227 |
+
"128028": {
|
| 228 |
+
"content": "<|reserved_special_token_20|>",
|
| 229 |
+
"lstrip": false,
|
| 230 |
+
"normalized": false,
|
| 231 |
+
"rstrip": false,
|
| 232 |
+
"single_word": false,
|
| 233 |
+
"special": true
|
| 234 |
+
},
|
| 235 |
+
"128029": {
|
| 236 |
+
"content": "<|reserved_special_token_21|>",
|
| 237 |
+
"lstrip": false,
|
| 238 |
+
"normalized": false,
|
| 239 |
+
"rstrip": false,
|
| 240 |
+
"single_word": false,
|
| 241 |
+
"special": true
|
| 242 |
+
},
|
| 243 |
+
"128030": {
|
| 244 |
+
"content": "<|reserved_special_token_22|>",
|
| 245 |
+
"lstrip": false,
|
| 246 |
+
"normalized": false,
|
| 247 |
+
"rstrip": false,
|
| 248 |
+
"single_word": false,
|
| 249 |
+
"special": true
|
| 250 |
+
},
|
| 251 |
+
"128031": {
|
| 252 |
+
"content": "<|reserved_special_token_23|>",
|
| 253 |
+
"lstrip": false,
|
| 254 |
+
"normalized": false,
|
| 255 |
+
"rstrip": false,
|
| 256 |
+
"single_word": false,
|
| 257 |
+
"special": true
|
| 258 |
+
},
|
| 259 |
+
"128032": {
|
| 260 |
+
"content": "<|reserved_special_token_24|>",
|
| 261 |
+
"lstrip": false,
|
| 262 |
+
"normalized": false,
|
| 263 |
+
"rstrip": false,
|
| 264 |
+
"single_word": false,
|
| 265 |
+
"special": true
|
| 266 |
+
},
|
| 267 |
+
"128033": {
|
| 268 |
+
"content": "<|reserved_special_token_25|>",
|
| 269 |
+
"lstrip": false,
|
| 270 |
+
"normalized": false,
|
| 271 |
+
"rstrip": false,
|
| 272 |
+
"single_word": false,
|
| 273 |
+
"special": true
|
| 274 |
+
},
|
| 275 |
+
"128034": {
|
| 276 |
+
"content": "<|reserved_special_token_26|>",
|
| 277 |
+
"lstrip": false,
|
| 278 |
+
"normalized": false,
|
| 279 |
+
"rstrip": false,
|
| 280 |
+
"single_word": false,
|
| 281 |
+
"special": true
|
| 282 |
+
},
|
| 283 |
+
"128035": {
|
| 284 |
+
"content": "<|reserved_special_token_27|>",
|
| 285 |
+
"lstrip": false,
|
| 286 |
+
"normalized": false,
|
| 287 |
+
"rstrip": false,
|
| 288 |
+
"single_word": false,
|
| 289 |
+
"special": true
|
| 290 |
+
},
|
| 291 |
+
"128036": {
|
| 292 |
+
"content": "<|reserved_special_token_28|>",
|
| 293 |
+
"lstrip": false,
|
| 294 |
+
"normalized": false,
|
| 295 |
+
"rstrip": false,
|
| 296 |
+
"single_word": false,
|
| 297 |
+
"special": true
|
| 298 |
+
},
|
| 299 |
+
"128037": {
|
| 300 |
+
"content": "<|reserved_special_token_29|>",
|
| 301 |
+
"lstrip": false,
|
| 302 |
+
"normalized": false,
|
| 303 |
+
"rstrip": false,
|
| 304 |
+
"single_word": false,
|
| 305 |
+
"special": true
|
| 306 |
+
},
|
| 307 |
+
"128038": {
|
| 308 |
+
"content": "<|reserved_special_token_30|>",
|
| 309 |
+
"lstrip": false,
|
| 310 |
+
"normalized": false,
|
| 311 |
+
"rstrip": false,
|
| 312 |
+
"single_word": false,
|
| 313 |
+
"special": true
|
| 314 |
+
},
|
| 315 |
+
"128039": {
|
| 316 |
+
"content": "<|reserved_special_token_31|>",
|
| 317 |
+
"lstrip": false,
|
| 318 |
+
"normalized": false,
|
| 319 |
+
"rstrip": false,
|
| 320 |
+
"single_word": false,
|
| 321 |
+
"special": true
|
| 322 |
+
},
|
| 323 |
+
"128040": {
|
| 324 |
+
"content": "<|reserved_special_token_32|>",
|
| 325 |
+
"lstrip": false,
|
| 326 |
+
"normalized": false,
|
| 327 |
+
"rstrip": false,
|
| 328 |
+
"single_word": false,
|
| 329 |
+
"special": true
|
| 330 |
+
},
|
| 331 |
+
"128041": {
|
| 332 |
+
"content": "<|reserved_special_token_33|>",
|
| 333 |
+
"lstrip": false,
|
| 334 |
+
"normalized": false,
|
| 335 |
+
"rstrip": false,
|
| 336 |
+
"single_word": false,
|
| 337 |
+
"special": true
|
| 338 |
+
},
|
| 339 |
+
"128042": {
|
| 340 |
+
"content": "<|reserved_special_token_34|>",
|
| 341 |
+
"lstrip": false,
|
| 342 |
+
"normalized": false,
|
| 343 |
+
"rstrip": false,
|
| 344 |
+
"single_word": false,
|
| 345 |
+
"special": true
|
| 346 |
+
},
|
| 347 |
+
"128043": {
|
| 348 |
+
"content": "<|reserved_special_token_35|>",
|
| 349 |
+
"lstrip": false,
|
| 350 |
+
"normalized": false,
|
| 351 |
+
"rstrip": false,
|
| 352 |
+
"single_word": false,
|
| 353 |
+
"special": true
|
| 354 |
+
},
|
| 355 |
+
"128044": {
|
| 356 |
+
"content": "<|reserved_special_token_36|>",
|
| 357 |
+
"lstrip": false,
|
| 358 |
+
"normalized": false,
|
| 359 |
+
"rstrip": false,
|
| 360 |
+
"single_word": false,
|
| 361 |
+
"special": true
|
| 362 |
+
},
|
| 363 |
+
"128045": {
|
| 364 |
+
"content": "<|reserved_special_token_37|>",
|
| 365 |
+
"lstrip": false,
|
| 366 |
+
"normalized": false,
|
| 367 |
+
"rstrip": false,
|
| 368 |
+
"single_word": false,
|
| 369 |
+
"special": true
|
| 370 |
+
},
|
| 371 |
+
"128046": {
|
| 372 |
+
"content": "<|reserved_special_token_38|>",
|
| 373 |
+
"lstrip": false,
|
| 374 |
+
"normalized": false,
|
| 375 |
+
"rstrip": false,
|
| 376 |
+
"single_word": false,
|
| 377 |
+
"special": true
|
| 378 |
+
},
|
| 379 |
+
"128047": {
|
| 380 |
+
"content": "<|reserved_special_token_39|>",
|
| 381 |
+
"lstrip": false,
|
| 382 |
+
"normalized": false,
|
| 383 |
+
"rstrip": false,
|
| 384 |
+
"single_word": false,
|
| 385 |
+
"special": true
|
| 386 |
+
},
|
| 387 |
+
"128048": {
|
| 388 |
+
"content": "<|reserved_special_token_40|>",
|
| 389 |
+
"lstrip": false,
|
| 390 |
+
"normalized": false,
|
| 391 |
+
"rstrip": false,
|
| 392 |
+
"single_word": false,
|
| 393 |
+
"special": true
|
| 394 |
+
},
|
| 395 |
+
"128049": {
|
| 396 |
+
"content": "<|reserved_special_token_41|>",
|
| 397 |
+
"lstrip": false,
|
| 398 |
+
"normalized": false,
|
| 399 |
+
"rstrip": false,
|
| 400 |
+
"single_word": false,
|
| 401 |
+
"special": true
|
| 402 |
+
},
|
| 403 |
+
"128050": {
|
| 404 |
+
"content": "<|reserved_special_token_42|>",
|
| 405 |
+
"lstrip": false,
|
| 406 |
+
"normalized": false,
|
| 407 |
+
"rstrip": false,
|
| 408 |
+
"single_word": false,
|
| 409 |
+
"special": true
|
| 410 |
+
},
|
| 411 |
+
"128051": {
|
| 412 |
+
"content": "<|reserved_special_token_43|>",
|
| 413 |
+
"lstrip": false,
|
| 414 |
+
"normalized": false,
|
| 415 |
+
"rstrip": false,
|
| 416 |
+
"single_word": false,
|
| 417 |
+
"special": true
|
| 418 |
+
},
|
| 419 |
+
"128052": {
|
| 420 |
+
"content": "<|reserved_special_token_44|>",
|
| 421 |
+
"lstrip": false,
|
| 422 |
+
"normalized": false,
|
| 423 |
+
"rstrip": false,
|
| 424 |
+
"single_word": false,
|
| 425 |
+
"special": true
|
| 426 |
+
},
|
| 427 |
+
"128053": {
|
| 428 |
+
"content": "<|reserved_special_token_45|>",
|
| 429 |
+
"lstrip": false,
|
| 430 |
+
"normalized": false,
|
| 431 |
+
"rstrip": false,
|
| 432 |
+
"single_word": false,
|
| 433 |
+
"special": true
|
| 434 |
+
},
|
| 435 |
+
"128054": {
|
| 436 |
+
"content": "<|reserved_special_token_46|>",
|
| 437 |
+
"lstrip": false,
|
| 438 |
+
"normalized": false,
|
| 439 |
+
"rstrip": false,
|
| 440 |
+
"single_word": false,
|
| 441 |
+
"special": true
|
| 442 |
+
},
|
| 443 |
+
"128055": {
|
| 444 |
+
"content": "<|reserved_special_token_47|>",
|
| 445 |
+
"lstrip": false,
|
| 446 |
+
"normalized": false,
|
| 447 |
+
"rstrip": false,
|
| 448 |
+
"single_word": false,
|
| 449 |
+
"special": true
|
| 450 |
+
},
|
| 451 |
+
"128056": {
|
| 452 |
+
"content": "<|reserved_special_token_48|>",
|
| 453 |
+
"lstrip": false,
|
| 454 |
+
"normalized": false,
|
| 455 |
+
"rstrip": false,
|
| 456 |
+
"single_word": false,
|
| 457 |
+
"special": true
|
| 458 |
+
},
|
| 459 |
+
"128057": {
|
| 460 |
+
"content": "<|reserved_special_token_49|>",
|
| 461 |
+
"lstrip": false,
|
| 462 |
+
"normalized": false,
|
| 463 |
+
"rstrip": false,
|
| 464 |
+
"single_word": false,
|
| 465 |
+
"special": true
|
| 466 |
+
},
|
| 467 |
+
"128058": {
|
| 468 |
+
"content": "<|reserved_special_token_50|>",
|
| 469 |
+
"lstrip": false,
|
| 470 |
+
"normalized": false,
|
| 471 |
+
"rstrip": false,
|
| 472 |
+
"single_word": false,
|
| 473 |
+
"special": true
|
| 474 |
+
},
|
| 475 |
+
"128059": {
|
| 476 |
+
"content": "<|reserved_special_token_51|>",
|
| 477 |
+
"lstrip": false,
|
| 478 |
+
"normalized": false,
|
| 479 |
+
"rstrip": false,
|
| 480 |
+
"single_word": false,
|
| 481 |
+
"special": true
|
| 482 |
+
},
|
| 483 |
+
"128060": {
|
| 484 |
+
"content": "<|reserved_special_token_52|>",
|
| 485 |
+
"lstrip": false,
|
| 486 |
+
"normalized": false,
|
| 487 |
+
"rstrip": false,
|
| 488 |
+
"single_word": false,
|
| 489 |
+
"special": true
|
| 490 |
+
},
|
| 491 |
+
"128061": {
|
| 492 |
+
"content": "<|reserved_special_token_53|>",
|
| 493 |
+
"lstrip": false,
|
| 494 |
+
"normalized": false,
|
| 495 |
+
"rstrip": false,
|
| 496 |
+
"single_word": false,
|
| 497 |
+
"special": true
|
| 498 |
+
},
|
| 499 |
+
"128062": {
|
| 500 |
+
"content": "<|reserved_special_token_54|>",
|
| 501 |
+
"lstrip": false,
|
| 502 |
+
"normalized": false,
|
| 503 |
+
"rstrip": false,
|
| 504 |
+
"single_word": false,
|
| 505 |
+
"special": true
|
| 506 |
+
},
|
| 507 |
+
"128063": {
|
| 508 |
+
"content": "<|reserved_special_token_55|>",
|
| 509 |
+
"lstrip": false,
|
| 510 |
+
"normalized": false,
|
| 511 |
+
"rstrip": false,
|
| 512 |
+
"single_word": false,
|
| 513 |
+
"special": true
|
| 514 |
+
},
|
| 515 |
+
"128064": {
|
| 516 |
+
"content": "<|reserved_special_token_56|>",
|
| 517 |
+
"lstrip": false,
|
| 518 |
+
"normalized": false,
|
| 519 |
+
"rstrip": false,
|
| 520 |
+
"single_word": false,
|
| 521 |
+
"special": true
|
| 522 |
+
},
|
| 523 |
+
"128065": {
|
| 524 |
+
"content": "<|reserved_special_token_57|>",
|
| 525 |
+
"lstrip": false,
|
| 526 |
+
"normalized": false,
|
| 527 |
+
"rstrip": false,
|
| 528 |
+
"single_word": false,
|
| 529 |
+
"special": true
|
| 530 |
+
},
|
| 531 |
+
"128066": {
|
| 532 |
+
"content": "<|reserved_special_token_58|>",
|
| 533 |
+
"lstrip": false,
|
| 534 |
+
"normalized": false,
|
| 535 |
+
"rstrip": false,
|
| 536 |
+
"single_word": false,
|
| 537 |
+
"special": true
|
| 538 |
+
},
|
| 539 |
+
"128067": {
|
| 540 |
+
"content": "<|reserved_special_token_59|>",
|
| 541 |
+
"lstrip": false,
|
| 542 |
+
"normalized": false,
|
| 543 |
+
"rstrip": false,
|
| 544 |
+
"single_word": false,
|
| 545 |
+
"special": true
|
| 546 |
+
},
|
| 547 |
+
"128068": {
|
| 548 |
+
"content": "<|reserved_special_token_60|>",
|
| 549 |
+
"lstrip": false,
|
| 550 |
+
"normalized": false,
|
| 551 |
+
"rstrip": false,
|
| 552 |
+
"single_word": false,
|
| 553 |
+
"special": true
|
| 554 |
+
},
|
| 555 |
+
"128069": {
|
| 556 |
+
"content": "<|reserved_special_token_61|>",
|
| 557 |
+
"lstrip": false,
|
| 558 |
+
"normalized": false,
|
| 559 |
+
"rstrip": false,
|
| 560 |
+
"single_word": false,
|
| 561 |
+
"special": true
|
| 562 |
+
},
|
| 563 |
+
"128070": {
|
| 564 |
+
"content": "<|reserved_special_token_62|>",
|
| 565 |
+
"lstrip": false,
|
| 566 |
+
"normalized": false,
|
| 567 |
+
"rstrip": false,
|
| 568 |
+
"single_word": false,
|
| 569 |
+
"special": true
|
| 570 |
+
},
|
| 571 |
+
"128071": {
|
| 572 |
+
"content": "<|reserved_special_token_63|>",
|
| 573 |
+
"lstrip": false,
|
| 574 |
+
"normalized": false,
|
| 575 |
+
"rstrip": false,
|
| 576 |
+
"single_word": false,
|
| 577 |
+
"special": true
|
| 578 |
+
},
|
| 579 |
+
"128072": {
|
| 580 |
+
"content": "<|reserved_special_token_64|>",
|
| 581 |
+
"lstrip": false,
|
| 582 |
+
"normalized": false,
|
| 583 |
+
"rstrip": false,
|
| 584 |
+
"single_word": false,
|
| 585 |
+
"special": true
|
| 586 |
+
},
|
| 587 |
+
"128073": {
|
| 588 |
+
"content": "<|reserved_special_token_65|>",
|
| 589 |
+
"lstrip": false,
|
| 590 |
+
"normalized": false,
|
| 591 |
+
"rstrip": false,
|
| 592 |
+
"single_word": false,
|
| 593 |
+
"special": true
|
| 594 |
+
},
|
| 595 |
+
"128074": {
|
| 596 |
+
"content": "<|reserved_special_token_66|>",
|
| 597 |
+
"lstrip": false,
|
| 598 |
+
"normalized": false,
|
| 599 |
+
"rstrip": false,
|
| 600 |
+
"single_word": false,
|
| 601 |
+
"special": true
|
| 602 |
+
},
|
| 603 |
+
"128075": {
|
| 604 |
+
"content": "<|reserved_special_token_67|>",
|
| 605 |
+
"lstrip": false,
|
| 606 |
+
"normalized": false,
|
| 607 |
+
"rstrip": false,
|
| 608 |
+
"single_word": false,
|
| 609 |
+
"special": true
|
| 610 |
+
},
|
| 611 |
+
"128076": {
|
| 612 |
+
"content": "<|reserved_special_token_68|>",
|
| 613 |
+
"lstrip": false,
|
| 614 |
+
"normalized": false,
|
| 615 |
+
"rstrip": false,
|
| 616 |
+
"single_word": false,
|
| 617 |
+
"special": true
|
| 618 |
+
},
|
| 619 |
+
"128077": {
|
| 620 |
+
"content": "<|reserved_special_token_69|>",
|
| 621 |
+
"lstrip": false,
|
| 622 |
+
"normalized": false,
|
| 623 |
+
"rstrip": false,
|
| 624 |
+
"single_word": false,
|
| 625 |
+
"special": true
|
| 626 |
+
},
|
| 627 |
+
"128078": {
|
| 628 |
+
"content": "<|reserved_special_token_70|>",
|
| 629 |
+
"lstrip": false,
|
| 630 |
+
"normalized": false,
|
| 631 |
+
"rstrip": false,
|
| 632 |
+
"single_word": false,
|
| 633 |
+
"special": true
|
| 634 |
+
},
|
| 635 |
+
"128079": {
|
| 636 |
+
"content": "<|reserved_special_token_71|>",
|
| 637 |
+
"lstrip": false,
|
| 638 |
+
"normalized": false,
|
| 639 |
+
"rstrip": false,
|
| 640 |
+
"single_word": false,
|
| 641 |
+
"special": true
|
| 642 |
+
},
|
| 643 |
+
"128080": {
|
| 644 |
+
"content": "<|reserved_special_token_72|>",
|
| 645 |
+
"lstrip": false,
|
| 646 |
+
"normalized": false,
|
| 647 |
+
"rstrip": false,
|
| 648 |
+
"single_word": false,
|
| 649 |
+
"special": true
|
| 650 |
+
},
|
| 651 |
+
"128081": {
|
| 652 |
+
"content": "<|reserved_special_token_73|>",
|
| 653 |
+
"lstrip": false,
|
| 654 |
+
"normalized": false,
|
| 655 |
+
"rstrip": false,
|
| 656 |
+
"single_word": false,
|
| 657 |
+
"special": true
|
| 658 |
+
},
|
| 659 |
+
"128082": {
|
| 660 |
+
"content": "<|reserved_special_token_74|>",
|
| 661 |
+
"lstrip": false,
|
| 662 |
+
"normalized": false,
|
| 663 |
+
"rstrip": false,
|
| 664 |
+
"single_word": false,
|
| 665 |
+
"special": true
|
| 666 |
+
},
|
| 667 |
+
"128083": {
|
| 668 |
+
"content": "<|reserved_special_token_75|>",
|
| 669 |
+
"lstrip": false,
|
| 670 |
+
"normalized": false,
|
| 671 |
+
"rstrip": false,
|
| 672 |
+
"single_word": false,
|
| 673 |
+
"special": true
|
| 674 |
+
},
|
| 675 |
+
"128084": {
|
| 676 |
+
"content": "<|reserved_special_token_76|>",
|
| 677 |
+
"lstrip": false,
|
| 678 |
+
"normalized": false,
|
| 679 |
+
"rstrip": false,
|
| 680 |
+
"single_word": false,
|
| 681 |
+
"special": true
|
| 682 |
+
},
|
| 683 |
+
"128085": {
|
| 684 |
+
"content": "<|reserved_special_token_77|>",
|
| 685 |
+
"lstrip": false,
|
| 686 |
+
"normalized": false,
|
| 687 |
+
"rstrip": false,
|
| 688 |
+
"single_word": false,
|
| 689 |
+
"special": true
|
| 690 |
+
},
|
| 691 |
+
"128086": {
|
| 692 |
+
"content": "<|reserved_special_token_78|>",
|
| 693 |
+
"lstrip": false,
|
| 694 |
+
"normalized": false,
|
| 695 |
+
"rstrip": false,
|
| 696 |
+
"single_word": false,
|
| 697 |
+
"special": true
|
| 698 |
+
},
|
| 699 |
+
"128087": {
|
| 700 |
+
"content": "<|reserved_special_token_79|>",
|
| 701 |
+
"lstrip": false,
|
| 702 |
+
"normalized": false,
|
| 703 |
+
"rstrip": false,
|
| 704 |
+
"single_word": false,
|
| 705 |
+
"special": true
|
| 706 |
+
},
|
| 707 |
+
"128088": {
|
| 708 |
+
"content": "<|reserved_special_token_80|>",
|
| 709 |
+
"lstrip": false,
|
| 710 |
+
"normalized": false,
|
| 711 |
+
"rstrip": false,
|
| 712 |
+
"single_word": false,
|
| 713 |
+
"special": true
|
| 714 |
+
},
|
| 715 |
+
"128089": {
|
| 716 |
+
"content": "<|reserved_special_token_81|>",
|
| 717 |
+
"lstrip": false,
|
| 718 |
+
"normalized": false,
|
| 719 |
+
"rstrip": false,
|
| 720 |
+
"single_word": false,
|
| 721 |
+
"special": true
|
| 722 |
+
},
|
| 723 |
+
"128090": {
|
| 724 |
+
"content": "<|reserved_special_token_82|>",
|
| 725 |
+
"lstrip": false,
|
| 726 |
+
"normalized": false,
|
| 727 |
+
"rstrip": false,
|
| 728 |
+
"single_word": false,
|
| 729 |
+
"special": true
|
| 730 |
+
},
|
| 731 |
+
"128091": {
|
| 732 |
+
"content": "<|reserved_special_token_83|>",
|
| 733 |
+
"lstrip": false,
|
| 734 |
+
"normalized": false,
|
| 735 |
+
"rstrip": false,
|
| 736 |
+
"single_word": false,
|
| 737 |
+
"special": true
|
| 738 |
+
},
|
| 739 |
+
"128092": {
|
| 740 |
+
"content": "<|reserved_special_token_84|>",
|
| 741 |
+
"lstrip": false,
|
| 742 |
+
"normalized": false,
|
| 743 |
+
"rstrip": false,
|
| 744 |
+
"single_word": false,
|
| 745 |
+
"special": true
|
| 746 |
+
},
|
| 747 |
+
"128093": {
|
| 748 |
+
"content": "<|reserved_special_token_85|>",
|
| 749 |
+
"lstrip": false,
|
| 750 |
+
"normalized": false,
|
| 751 |
+
"rstrip": false,
|
| 752 |
+
"single_word": false,
|
| 753 |
+
"special": true
|
| 754 |
+
},
|
| 755 |
+
"128094": {
|
| 756 |
+
"content": "<|reserved_special_token_86|>",
|
| 757 |
+
"lstrip": false,
|
| 758 |
+
"normalized": false,
|
| 759 |
+
"rstrip": false,
|
| 760 |
+
"single_word": false,
|
| 761 |
+
"special": true
|
| 762 |
+
},
|
| 763 |
+
"128095": {
|
| 764 |
+
"content": "<|reserved_special_token_87|>",
|
| 765 |
+
"lstrip": false,
|
| 766 |
+
"normalized": false,
|
| 767 |
+
"rstrip": false,
|
| 768 |
+
"single_word": false,
|
| 769 |
+
"special": true
|
| 770 |
+
},
|
| 771 |
+
"128096": {
|
| 772 |
+
"content": "<|reserved_special_token_88|>",
|
| 773 |
+
"lstrip": false,
|
| 774 |
+
"normalized": false,
|
| 775 |
+
"rstrip": false,
|
| 776 |
+
"single_word": false,
|
| 777 |
+
"special": true
|
| 778 |
+
},
|
| 779 |
+
"128097": {
|
| 780 |
+
"content": "<|reserved_special_token_89|>",
|
| 781 |
+
"lstrip": false,
|
| 782 |
+
"normalized": false,
|
| 783 |
+
"rstrip": false,
|
| 784 |
+
"single_word": false,
|
| 785 |
+
"special": true
|
| 786 |
+
},
|
| 787 |
+
"128098": {
|
| 788 |
+
"content": "<|reserved_special_token_90|>",
|
| 789 |
+
"lstrip": false,
|
| 790 |
+
"normalized": false,
|
| 791 |
+
"rstrip": false,
|
| 792 |
+
"single_word": false,
|
| 793 |
+
"special": true
|
| 794 |
+
},
|
| 795 |
+
"128099": {
|
| 796 |
+
"content": "<|reserved_special_token_91|>",
|
| 797 |
+
"lstrip": false,
|
| 798 |
+
"normalized": false,
|
| 799 |
+
"rstrip": false,
|
| 800 |
+
"single_word": false,
|
| 801 |
+
"special": true
|
| 802 |
+
},
|
| 803 |
+
"128100": {
|
| 804 |
+
"content": "<|reserved_special_token_92|>",
|
| 805 |
+
"lstrip": false,
|
| 806 |
+
"normalized": false,
|
| 807 |
+
"rstrip": false,
|
| 808 |
+
"single_word": false,
|
| 809 |
+
"special": true
|
| 810 |
+
},
|
| 811 |
+
"128101": {
|
| 812 |
+
"content": "<|reserved_special_token_93|>",
|
| 813 |
+
"lstrip": false,
|
| 814 |
+
"normalized": false,
|
| 815 |
+
"rstrip": false,
|
| 816 |
+
"single_word": false,
|
| 817 |
+
"special": true
|
| 818 |
+
},
|
| 819 |
+
"128102": {
|
| 820 |
+
"content": "<|reserved_special_token_94|>",
|
| 821 |
+
"lstrip": false,
|
| 822 |
+
"normalized": false,
|
| 823 |
+
"rstrip": false,
|
| 824 |
+
"single_word": false,
|
| 825 |
+
"special": true
|
| 826 |
+
},
|
| 827 |
+
"128103": {
|
| 828 |
+
"content": "<|reserved_special_token_95|>",
|
| 829 |
+
"lstrip": false,
|
| 830 |
+
"normalized": false,
|
| 831 |
+
"rstrip": false,
|
| 832 |
+
"single_word": false,
|
| 833 |
+
"special": true
|
| 834 |
+
},
|
| 835 |
+
"128104": {
|
| 836 |
+
"content": "<|reserved_special_token_96|>",
|
| 837 |
+
"lstrip": false,
|
| 838 |
+
"normalized": false,
|
| 839 |
+
"rstrip": false,
|
| 840 |
+
"single_word": false,
|
| 841 |
+
"special": true
|
| 842 |
+
},
|
| 843 |
+
"128105": {
|
| 844 |
+
"content": "<|reserved_special_token_97|>",
|
| 845 |
+
"lstrip": false,
|
| 846 |
+
"normalized": false,
|
| 847 |
+
"rstrip": false,
|
| 848 |
+
"single_word": false,
|
| 849 |
+
"special": true
|
| 850 |
+
},
|
| 851 |
+
"128106": {
|
| 852 |
+
"content": "<|reserved_special_token_98|>",
|
| 853 |
+
"lstrip": false,
|
| 854 |
+
"normalized": false,
|
| 855 |
+
"rstrip": false,
|
| 856 |
+
"single_word": false,
|
| 857 |
+
"special": true
|
| 858 |
+
},
|
| 859 |
+
"128107": {
|
| 860 |
+
"content": "<|reserved_special_token_99|>",
|
| 861 |
+
"lstrip": false,
|
| 862 |
+
"normalized": false,
|
| 863 |
+
"rstrip": false,
|
| 864 |
+
"single_word": false,
|
| 865 |
+
"special": true
|
| 866 |
+
},
|
| 867 |
+
"128108": {
|
| 868 |
+
"content": "<|reserved_special_token_100|>",
|
| 869 |
+
"lstrip": false,
|
| 870 |
+
"normalized": false,
|
| 871 |
+
"rstrip": false,
|
| 872 |
+
"single_word": false,
|
| 873 |
+
"special": true
|
| 874 |
+
},
|
| 875 |
+
"128109": {
|
| 876 |
+
"content": "<|reserved_special_token_101|>",
|
| 877 |
+
"lstrip": false,
|
| 878 |
+
"normalized": false,
|
| 879 |
+
"rstrip": false,
|
| 880 |
+
"single_word": false,
|
| 881 |
+
"special": true
|
| 882 |
+
},
|
| 883 |
+
"128110": {
|
| 884 |
+
"content": "<|reserved_special_token_102|>",
|
| 885 |
+
"lstrip": false,
|
| 886 |
+
"normalized": false,
|
| 887 |
+
"rstrip": false,
|
| 888 |
+
"single_word": false,
|
| 889 |
+
"special": true
|
| 890 |
+
},
|
| 891 |
+
"128111": {
|
| 892 |
+
"content": "<|reserved_special_token_103|>",
|
| 893 |
+
"lstrip": false,
|
| 894 |
+
"normalized": false,
|
| 895 |
+
"rstrip": false,
|
| 896 |
+
"single_word": false,
|
| 897 |
+
"special": true
|
| 898 |
+
},
|
| 899 |
+
"128112": {
|
| 900 |
+
"content": "<|reserved_special_token_104|>",
|
| 901 |
+
"lstrip": false,
|
| 902 |
+
"normalized": false,
|
| 903 |
+
"rstrip": false,
|
| 904 |
+
"single_word": false,
|
| 905 |
+
"special": true
|
| 906 |
+
},
|
| 907 |
+
"128113": {
|
| 908 |
+
"content": "<|reserved_special_token_105|>",
|
| 909 |
+
"lstrip": false,
|
| 910 |
+
"normalized": false,
|
| 911 |
+
"rstrip": false,
|
| 912 |
+
"single_word": false,
|
| 913 |
+
"special": true
|
| 914 |
+
},
|
| 915 |
+
"128114": {
|
| 916 |
+
"content": "<|reserved_special_token_106|>",
|
| 917 |
+
"lstrip": false,
|
| 918 |
+
"normalized": false,
|
| 919 |
+
"rstrip": false,
|
| 920 |
+
"single_word": false,
|
| 921 |
+
"special": true
|
| 922 |
+
},
|
| 923 |
+
"128115": {
|
| 924 |
+
"content": "<|reserved_special_token_107|>",
|
| 925 |
+
"lstrip": false,
|
| 926 |
+
"normalized": false,
|
| 927 |
+
"rstrip": false,
|
| 928 |
+
"single_word": false,
|
| 929 |
+
"special": true
|
| 930 |
+
},
|
| 931 |
+
"128116": {
|
| 932 |
+
"content": "<|reserved_special_token_108|>",
|
| 933 |
+
"lstrip": false,
|
| 934 |
+
"normalized": false,
|
| 935 |
+
"rstrip": false,
|
| 936 |
+
"single_word": false,
|
| 937 |
+
"special": true
|
| 938 |
+
},
|
| 939 |
+
"128117": {
|
| 940 |
+
"content": "<|reserved_special_token_109|>",
|
| 941 |
+
"lstrip": false,
|
| 942 |
+
"normalized": false,
|
| 943 |
+
"rstrip": false,
|
| 944 |
+
"single_word": false,
|
| 945 |
+
"special": true
|
| 946 |
+
},
|
| 947 |
+
"128118": {
|
| 948 |
+
"content": "<|reserved_special_token_110|>",
|
| 949 |
+
"lstrip": false,
|
| 950 |
+
"normalized": false,
|
| 951 |
+
"rstrip": false,
|
| 952 |
+
"single_word": false,
|
| 953 |
+
"special": true
|
| 954 |
+
},
|
| 955 |
+
"128119": {
|
| 956 |
+
"content": "<|reserved_special_token_111|>",
|
| 957 |
+
"lstrip": false,
|
| 958 |
+
"normalized": false,
|
| 959 |
+
"rstrip": false,
|
| 960 |
+
"single_word": false,
|
| 961 |
+
"special": true
|
| 962 |
+
},
|
| 963 |
+
"128120": {
|
| 964 |
+
"content": "<|reserved_special_token_112|>",
|
| 965 |
+
"lstrip": false,
|
| 966 |
+
"normalized": false,
|
| 967 |
+
"rstrip": false,
|
| 968 |
+
"single_word": false,
|
| 969 |
+
"special": true
|
| 970 |
+
},
|
| 971 |
+
"128121": {
|
| 972 |
+
"content": "<|reserved_special_token_113|>",
|
| 973 |
+
"lstrip": false,
|
| 974 |
+
"normalized": false,
|
| 975 |
+
"rstrip": false,
|
| 976 |
+
"single_word": false,
|
| 977 |
+
"special": true
|
| 978 |
+
},
|
| 979 |
+
"128122": {
|
| 980 |
+
"content": "<|reserved_special_token_114|>",
|
| 981 |
+
"lstrip": false,
|
| 982 |
+
"normalized": false,
|
| 983 |
+
"rstrip": false,
|
| 984 |
+
"single_word": false,
|
| 985 |
+
"special": true
|
| 986 |
+
},
|
| 987 |
+
"128123": {
|
| 988 |
+
"content": "<|reserved_special_token_115|>",
|
| 989 |
+
"lstrip": false,
|
| 990 |
+
"normalized": false,
|
| 991 |
+
"rstrip": false,
|
| 992 |
+
"single_word": false,
|
| 993 |
+
"special": true
|
| 994 |
+
},
|
| 995 |
+
"128124": {
|
| 996 |
+
"content": "<|reserved_special_token_116|>",
|
| 997 |
+
"lstrip": false,
|
| 998 |
+
"normalized": false,
|
| 999 |
+
"rstrip": false,
|
| 1000 |
+
"single_word": false,
|
| 1001 |
+
"special": true
|
| 1002 |
+
},
|
| 1003 |
+
"128125": {
|
| 1004 |
+
"content": "<|reserved_special_token_117|>",
|
| 1005 |
+
"lstrip": false,
|
| 1006 |
+
"normalized": false,
|
| 1007 |
+
"rstrip": false,
|
| 1008 |
+
"single_word": false,
|
| 1009 |
+
"special": true
|
| 1010 |
+
},
|
| 1011 |
+
"128126": {
|
| 1012 |
+
"content": "<|reserved_special_token_118|>",
|
| 1013 |
+
"lstrip": false,
|
| 1014 |
+
"normalized": false,
|
| 1015 |
+
"rstrip": false,
|
| 1016 |
+
"single_word": false,
|
| 1017 |
+
"special": true
|
| 1018 |
+
},
|
| 1019 |
+
"128127": {
|
| 1020 |
+
"content": "<|reserved_special_token_119|>",
|
| 1021 |
+
"lstrip": false,
|
| 1022 |
+
"normalized": false,
|
| 1023 |
+
"rstrip": false,
|
| 1024 |
+
"single_word": false,
|
| 1025 |
+
"special": true
|
| 1026 |
+
},
|
| 1027 |
+
"128128": {
|
| 1028 |
+
"content": "<|reserved_special_token_120|>",
|
| 1029 |
+
"lstrip": false,
|
| 1030 |
+
"normalized": false,
|
| 1031 |
+
"rstrip": false,
|
| 1032 |
+
"single_word": false,
|
| 1033 |
+
"special": true
|
| 1034 |
+
},
|
| 1035 |
+
"128129": {
|
| 1036 |
+
"content": "<|reserved_special_token_121|>",
|
| 1037 |
+
"lstrip": false,
|
| 1038 |
+
"normalized": false,
|
| 1039 |
+
"rstrip": false,
|
| 1040 |
+
"single_word": false,
|
| 1041 |
+
"special": true
|
| 1042 |
+
},
|
| 1043 |
+
"128130": {
|
| 1044 |
+
"content": "<|reserved_special_token_122|>",
|
| 1045 |
+
"lstrip": false,
|
| 1046 |
+
"normalized": false,
|
| 1047 |
+
"rstrip": false,
|
| 1048 |
+
"single_word": false,
|
| 1049 |
+
"special": true
|
| 1050 |
+
},
|
| 1051 |
+
"128131": {
|
| 1052 |
+
"content": "<|reserved_special_token_123|>",
|
| 1053 |
+
"lstrip": false,
|
| 1054 |
+
"normalized": false,
|
| 1055 |
+
"rstrip": false,
|
| 1056 |
+
"single_word": false,
|
| 1057 |
+
"special": true
|
| 1058 |
+
},
|
| 1059 |
+
"128132": {
|
| 1060 |
+
"content": "<|reserved_special_token_124|>",
|
| 1061 |
+
"lstrip": false,
|
| 1062 |
+
"normalized": false,
|
| 1063 |
+
"rstrip": false,
|
| 1064 |
+
"single_word": false,
|
| 1065 |
+
"special": true
|
| 1066 |
+
},
|
| 1067 |
+
"128133": {
|
| 1068 |
+
"content": "<|reserved_special_token_125|>",
|
| 1069 |
+
"lstrip": false,
|
| 1070 |
+
"normalized": false,
|
| 1071 |
+
"rstrip": false,
|
| 1072 |
+
"single_word": false,
|
| 1073 |
+
"special": true
|
| 1074 |
+
},
|
| 1075 |
+
"128134": {
|
| 1076 |
+
"content": "<|reserved_special_token_126|>",
|
| 1077 |
+
"lstrip": false,
|
| 1078 |
+
"normalized": false,
|
| 1079 |
+
"rstrip": false,
|
| 1080 |
+
"single_word": false,
|
| 1081 |
+
"special": true
|
| 1082 |
+
},
|
| 1083 |
+
"128135": {
|
| 1084 |
+
"content": "<|reserved_special_token_127|>",
|
| 1085 |
+
"lstrip": false,
|
| 1086 |
+
"normalized": false,
|
| 1087 |
+
"rstrip": false,
|
| 1088 |
+
"single_word": false,
|
| 1089 |
+
"special": true
|
| 1090 |
+
},
|
| 1091 |
+
"128136": {
|
| 1092 |
+
"content": "<|reserved_special_token_128|>",
|
| 1093 |
+
"lstrip": false,
|
| 1094 |
+
"normalized": false,
|
| 1095 |
+
"rstrip": false,
|
| 1096 |
+
"single_word": false,
|
| 1097 |
+
"special": true
|
| 1098 |
+
},
|
| 1099 |
+
"128137": {
|
| 1100 |
+
"content": "<|reserved_special_token_129|>",
|
| 1101 |
+
"lstrip": false,
|
| 1102 |
+
"normalized": false,
|
| 1103 |
+
"rstrip": false,
|
| 1104 |
+
"single_word": false,
|
| 1105 |
+
"special": true
|
| 1106 |
+
},
|
| 1107 |
+
"128138": {
|
| 1108 |
+
"content": "<|reserved_special_token_130|>",
|
| 1109 |
+
"lstrip": false,
|
| 1110 |
+
"normalized": false,
|
| 1111 |
+
"rstrip": false,
|
| 1112 |
+
"single_word": false,
|
| 1113 |
+
"special": true
|
| 1114 |
+
},
|
| 1115 |
+
"128139": {
|
| 1116 |
+
"content": "<|reserved_special_token_131|>",
|
| 1117 |
+
"lstrip": false,
|
| 1118 |
+
"normalized": false,
|
| 1119 |
+
"rstrip": false,
|
| 1120 |
+
"single_word": false,
|
| 1121 |
+
"special": true
|
| 1122 |
+
},
|
| 1123 |
+
"128140": {
|
| 1124 |
+
"content": "<|reserved_special_token_132|>",
|
| 1125 |
+
"lstrip": false,
|
| 1126 |
+
"normalized": false,
|
| 1127 |
+
"rstrip": false,
|
| 1128 |
+
"single_word": false,
|
| 1129 |
+
"special": true
|
| 1130 |
+
},
|
| 1131 |
+
"128141": {
|
| 1132 |
+
"content": "<|reserved_special_token_133|>",
|
| 1133 |
+
"lstrip": false,
|
| 1134 |
+
"normalized": false,
|
| 1135 |
+
"rstrip": false,
|
| 1136 |
+
"single_word": false,
|
| 1137 |
+
"special": true
|
| 1138 |
+
},
|
| 1139 |
+
"128142": {
|
| 1140 |
+
"content": "<|reserved_special_token_134|>",
|
| 1141 |
+
"lstrip": false,
|
| 1142 |
+
"normalized": false,
|
| 1143 |
+
"rstrip": false,
|
| 1144 |
+
"single_word": false,
|
| 1145 |
+
"special": true
|
| 1146 |
+
},
|
| 1147 |
+
"128143": {
|
| 1148 |
+
"content": "<|reserved_special_token_135|>",
|
| 1149 |
+
"lstrip": false,
|
| 1150 |
+
"normalized": false,
|
| 1151 |
+
"rstrip": false,
|
| 1152 |
+
"single_word": false,
|
| 1153 |
+
"special": true
|
| 1154 |
+
},
|
| 1155 |
+
"128144": {
|
| 1156 |
+
"content": "<|reserved_special_token_136|>",
|
| 1157 |
+
"lstrip": false,
|
| 1158 |
+
"normalized": false,
|
| 1159 |
+
"rstrip": false,
|
| 1160 |
+
"single_word": false,
|
| 1161 |
+
"special": true
|
| 1162 |
+
},
|
| 1163 |
+
"128145": {
|
| 1164 |
+
"content": "<|reserved_special_token_137|>",
|
| 1165 |
+
"lstrip": false,
|
| 1166 |
+
"normalized": false,
|
| 1167 |
+
"rstrip": false,
|
| 1168 |
+
"single_word": false,
|
| 1169 |
+
"special": true
|
| 1170 |
+
},
|
| 1171 |
+
"128146": {
|
| 1172 |
+
"content": "<|reserved_special_token_138|>",
|
| 1173 |
+
"lstrip": false,
|
| 1174 |
+
"normalized": false,
|
| 1175 |
+
"rstrip": false,
|
| 1176 |
+
"single_word": false,
|
| 1177 |
+
"special": true
|
| 1178 |
+
},
|
| 1179 |
+
"128147": {
|
| 1180 |
+
"content": "<|reserved_special_token_139|>",
|
| 1181 |
+
"lstrip": false,
|
| 1182 |
+
"normalized": false,
|
| 1183 |
+
"rstrip": false,
|
| 1184 |
+
"single_word": false,
|
| 1185 |
+
"special": true
|
| 1186 |
+
},
|
| 1187 |
+
"128148": {
|
| 1188 |
+
"content": "<|reserved_special_token_140|>",
|
| 1189 |
+
"lstrip": false,
|
| 1190 |
+
"normalized": false,
|
| 1191 |
+
"rstrip": false,
|
| 1192 |
+
"single_word": false,
|
| 1193 |
+
"special": true
|
| 1194 |
+
},
|
| 1195 |
+
"128149": {
|
| 1196 |
+
"content": "<|reserved_special_token_141|>",
|
| 1197 |
+
"lstrip": false,
|
| 1198 |
+
"normalized": false,
|
| 1199 |
+
"rstrip": false,
|
| 1200 |
+
"single_word": false,
|
| 1201 |
+
"special": true
|
| 1202 |
+
},
|
| 1203 |
+
"128150": {
|
| 1204 |
+
"content": "<|reserved_special_token_142|>",
|
| 1205 |
+
"lstrip": false,
|
| 1206 |
+
"normalized": false,
|
| 1207 |
+
"rstrip": false,
|
| 1208 |
+
"single_word": false,
|
| 1209 |
+
"special": true
|
| 1210 |
+
},
|
| 1211 |
+
"128151": {
|
| 1212 |
+
"content": "<|reserved_special_token_143|>",
|
| 1213 |
+
"lstrip": false,
|
| 1214 |
+
"normalized": false,
|
| 1215 |
+
"rstrip": false,
|
| 1216 |
+
"single_word": false,
|
| 1217 |
+
"special": true
|
| 1218 |
+
},
|
| 1219 |
+
"128152": {
|
| 1220 |
+
"content": "<|reserved_special_token_144|>",
|
| 1221 |
+
"lstrip": false,
|
| 1222 |
+
"normalized": false,
|
| 1223 |
+
"rstrip": false,
|
| 1224 |
+
"single_word": false,
|
| 1225 |
+
"special": true
|
| 1226 |
+
},
|
| 1227 |
+
"128153": {
|
| 1228 |
+
"content": "<|reserved_special_token_145|>",
|
| 1229 |
+
"lstrip": false,
|
| 1230 |
+
"normalized": false,
|
| 1231 |
+
"rstrip": false,
|
| 1232 |
+
"single_word": false,
|
| 1233 |
+
"special": true
|
| 1234 |
+
},
|
| 1235 |
+
"128154": {
|
| 1236 |
+
"content": "<|reserved_special_token_146|>",
|
| 1237 |
+
"lstrip": false,
|
| 1238 |
+
"normalized": false,
|
| 1239 |
+
"rstrip": false,
|
| 1240 |
+
"single_word": false,
|
| 1241 |
+
"special": true
|
| 1242 |
+
},
|
| 1243 |
+
"128155": {
|
| 1244 |
+
"content": "<|reserved_special_token_147|>",
|
| 1245 |
+
"lstrip": false,
|
| 1246 |
+
"normalized": false,
|
| 1247 |
+
"rstrip": false,
|
| 1248 |
+
"single_word": false,
|
| 1249 |
+
"special": true
|
| 1250 |
+
},
|
| 1251 |
+
"128156": {
|
| 1252 |
+
"content": "<|reserved_special_token_148|>",
|
| 1253 |
+
"lstrip": false,
|
| 1254 |
+
"normalized": false,
|
| 1255 |
+
"rstrip": false,
|
| 1256 |
+
"single_word": false,
|
| 1257 |
+
"special": true
|
| 1258 |
+
},
|
| 1259 |
+
"128157": {
|
| 1260 |
+
"content": "<|reserved_special_token_149|>",
|
| 1261 |
+
"lstrip": false,
|
| 1262 |
+
"normalized": false,
|
| 1263 |
+
"rstrip": false,
|
| 1264 |
+
"single_word": false,
|
| 1265 |
+
"special": true
|
| 1266 |
+
},
|
| 1267 |
+
"128158": {
|
| 1268 |
+
"content": "<|reserved_special_token_150|>",
|
| 1269 |
+
"lstrip": false,
|
| 1270 |
+
"normalized": false,
|
| 1271 |
+
"rstrip": false,
|
| 1272 |
+
"single_word": false,
|
| 1273 |
+
"special": true
|
| 1274 |
+
},
|
| 1275 |
+
"128159": {
|
| 1276 |
+
"content": "<|reserved_special_token_151|>",
|
| 1277 |
+
"lstrip": false,
|
| 1278 |
+
"normalized": false,
|
| 1279 |
+
"rstrip": false,
|
| 1280 |
+
"single_word": false,
|
| 1281 |
+
"special": true
|
| 1282 |
+
},
|
| 1283 |
+
"128160": {
|
| 1284 |
+
"content": "<|reserved_special_token_152|>",
|
| 1285 |
+
"lstrip": false,
|
| 1286 |
+
"normalized": false,
|
| 1287 |
+
"rstrip": false,
|
| 1288 |
+
"single_word": false,
|
| 1289 |
+
"special": true
|
| 1290 |
+
},
|
| 1291 |
+
"128161": {
|
| 1292 |
+
"content": "<|reserved_special_token_153|>",
|
| 1293 |
+
"lstrip": false,
|
| 1294 |
+
"normalized": false,
|
| 1295 |
+
"rstrip": false,
|
| 1296 |
+
"single_word": false,
|
| 1297 |
+
"special": true
|
| 1298 |
+
},
|
| 1299 |
+
"128162": {
|
| 1300 |
+
"content": "<|reserved_special_token_154|>",
|
| 1301 |
+
"lstrip": false,
|
| 1302 |
+
"normalized": false,
|
| 1303 |
+
"rstrip": false,
|
| 1304 |
+
"single_word": false,
|
| 1305 |
+
"special": true
|
| 1306 |
+
},
|
| 1307 |
+
"128163": {
|
| 1308 |
+
"content": "<|reserved_special_token_155|>",
|
| 1309 |
+
"lstrip": false,
|
| 1310 |
+
"normalized": false,
|
| 1311 |
+
"rstrip": false,
|
| 1312 |
+
"single_word": false,
|
| 1313 |
+
"special": true
|
| 1314 |
+
},
|
| 1315 |
+
"128164": {
|
| 1316 |
+
"content": "<|reserved_special_token_156|>",
|
| 1317 |
+
"lstrip": false,
|
| 1318 |
+
"normalized": false,
|
| 1319 |
+
"rstrip": false,
|
| 1320 |
+
"single_word": false,
|
| 1321 |
+
"special": true
|
| 1322 |
+
},
|
| 1323 |
+
"128165": {
|
| 1324 |
+
"content": "<|reserved_special_token_157|>",
|
| 1325 |
+
"lstrip": false,
|
| 1326 |
+
"normalized": false,
|
| 1327 |
+
"rstrip": false,
|
| 1328 |
+
"single_word": false,
|
| 1329 |
+
"special": true
|
| 1330 |
+
},
|
| 1331 |
+
"128166": {
|
| 1332 |
+
"content": "<|reserved_special_token_158|>",
|
| 1333 |
+
"lstrip": false,
|
| 1334 |
+
"normalized": false,
|
| 1335 |
+
"rstrip": false,
|
| 1336 |
+
"single_word": false,
|
| 1337 |
+
"special": true
|
| 1338 |
+
},
|
| 1339 |
+
"128167": {
|
| 1340 |
+
"content": "<|reserved_special_token_159|>",
|
| 1341 |
+
"lstrip": false,
|
| 1342 |
+
"normalized": false,
|
| 1343 |
+
"rstrip": false,
|
| 1344 |
+
"single_word": false,
|
| 1345 |
+
"special": true
|
| 1346 |
+
},
|
| 1347 |
+
"128168": {
|
| 1348 |
+
"content": "<|reserved_special_token_160|>",
|
| 1349 |
+
"lstrip": false,
|
| 1350 |
+
"normalized": false,
|
| 1351 |
+
"rstrip": false,
|
| 1352 |
+
"single_word": false,
|
| 1353 |
+
"special": true
|
| 1354 |
+
},
|
| 1355 |
+
"128169": {
|
| 1356 |
+
"content": "<|reserved_special_token_161|>",
|
| 1357 |
+
"lstrip": false,
|
| 1358 |
+
"normalized": false,
|
| 1359 |
+
"rstrip": false,
|
| 1360 |
+
"single_word": false,
|
| 1361 |
+
"special": true
|
| 1362 |
+
},
|
| 1363 |
+
"128170": {
|
| 1364 |
+
"content": "<|reserved_special_token_162|>",
|
| 1365 |
+
"lstrip": false,
|
| 1366 |
+
"normalized": false,
|
| 1367 |
+
"rstrip": false,
|
| 1368 |
+
"single_word": false,
|
| 1369 |
+
"special": true
|
| 1370 |
+
},
|
| 1371 |
+
"128171": {
|
| 1372 |
+
"content": "<|reserved_special_token_163|>",
|
| 1373 |
+
"lstrip": false,
|
| 1374 |
+
"normalized": false,
|
| 1375 |
+
"rstrip": false,
|
| 1376 |
+
"single_word": false,
|
| 1377 |
+
"special": true
|
| 1378 |
+
},
|
| 1379 |
+
"128172": {
|
| 1380 |
+
"content": "<|reserved_special_token_164|>",
|
| 1381 |
+
"lstrip": false,
|
| 1382 |
+
"normalized": false,
|
| 1383 |
+
"rstrip": false,
|
| 1384 |
+
"single_word": false,
|
| 1385 |
+
"special": true
|
| 1386 |
+
},
|
| 1387 |
+
"128173": {
|
| 1388 |
+
"content": "<|reserved_special_token_165|>",
|
| 1389 |
+
"lstrip": false,
|
| 1390 |
+
"normalized": false,
|
| 1391 |
+
"rstrip": false,
|
| 1392 |
+
"single_word": false,
|
| 1393 |
+
"special": true
|
| 1394 |
+
},
|
| 1395 |
+
"128174": {
|
| 1396 |
+
"content": "<|reserved_special_token_166|>",
|
| 1397 |
+
"lstrip": false,
|
| 1398 |
+
"normalized": false,
|
| 1399 |
+
"rstrip": false,
|
| 1400 |
+
"single_word": false,
|
| 1401 |
+
"special": true
|
| 1402 |
+
},
|
| 1403 |
+
"128175": {
|
| 1404 |
+
"content": "<|reserved_special_token_167|>",
|
| 1405 |
+
"lstrip": false,
|
| 1406 |
+
"normalized": false,
|
| 1407 |
+
"rstrip": false,
|
| 1408 |
+
"single_word": false,
|
| 1409 |
+
"special": true
|
| 1410 |
+
},
|
| 1411 |
+
"128176": {
|
| 1412 |
+
"content": "<|reserved_special_token_168|>",
|
| 1413 |
+
"lstrip": false,
|
| 1414 |
+
"normalized": false,
|
| 1415 |
+
"rstrip": false,
|
| 1416 |
+
"single_word": false,
|
| 1417 |
+
"special": true
|
| 1418 |
+
},
|
| 1419 |
+
"128177": {
|
| 1420 |
+
"content": "<|reserved_special_token_169|>",
|
| 1421 |
+
"lstrip": false,
|
| 1422 |
+
"normalized": false,
|
| 1423 |
+
"rstrip": false,
|
| 1424 |
+
"single_word": false,
|
| 1425 |
+
"special": true
|
| 1426 |
+
},
|
| 1427 |
+
"128178": {
|
| 1428 |
+
"content": "<|reserved_special_token_170|>",
|
| 1429 |
+
"lstrip": false,
|
| 1430 |
+
"normalized": false,
|
| 1431 |
+
"rstrip": false,
|
| 1432 |
+
"single_word": false,
|
| 1433 |
+
"special": true
|
| 1434 |
+
},
|
| 1435 |
+
"128179": {
|
| 1436 |
+
"content": "<|reserved_special_token_171|>",
|
| 1437 |
+
"lstrip": false,
|
| 1438 |
+
"normalized": false,
|
| 1439 |
+
"rstrip": false,
|
| 1440 |
+
"single_word": false,
|
| 1441 |
+
"special": true
|
| 1442 |
+
},
|
| 1443 |
+
"128180": {
|
| 1444 |
+
"content": "<|reserved_special_token_172|>",
|
| 1445 |
+
"lstrip": false,
|
| 1446 |
+
"normalized": false,
|
| 1447 |
+
"rstrip": false,
|
| 1448 |
+
"single_word": false,
|
| 1449 |
+
"special": true
|
| 1450 |
+
},
|
| 1451 |
+
"128181": {
|
| 1452 |
+
"content": "<|reserved_special_token_173|>",
|
| 1453 |
+
"lstrip": false,
|
| 1454 |
+
"normalized": false,
|
| 1455 |
+
"rstrip": false,
|
| 1456 |
+
"single_word": false,
|
| 1457 |
+
"special": true
|
| 1458 |
+
},
|
| 1459 |
+
"128182": {
|
| 1460 |
+
"content": "<|reserved_special_token_174|>",
|
| 1461 |
+
"lstrip": false,
|
| 1462 |
+
"normalized": false,
|
| 1463 |
+
"rstrip": false,
|
| 1464 |
+
"single_word": false,
|
| 1465 |
+
"special": true
|
| 1466 |
+
},
|
| 1467 |
+
"128183": {
|
| 1468 |
+
"content": "<|reserved_special_token_175|>",
|
| 1469 |
+
"lstrip": false,
|
| 1470 |
+
"normalized": false,
|
| 1471 |
+
"rstrip": false,
|
| 1472 |
+
"single_word": false,
|
| 1473 |
+
"special": true
|
| 1474 |
+
},
|
| 1475 |
+
"128184": {
|
| 1476 |
+
"content": "<|reserved_special_token_176|>",
|
| 1477 |
+
"lstrip": false,
|
| 1478 |
+
"normalized": false,
|
| 1479 |
+
"rstrip": false,
|
| 1480 |
+
"single_word": false,
|
| 1481 |
+
"special": true
|
| 1482 |
+
},
|
| 1483 |
+
"128185": {
|
| 1484 |
+
"content": "<|reserved_special_token_177|>",
|
| 1485 |
+
"lstrip": false,
|
| 1486 |
+
"normalized": false,
|
| 1487 |
+
"rstrip": false,
|
| 1488 |
+
"single_word": false,
|
| 1489 |
+
"special": true
|
| 1490 |
+
},
|
| 1491 |
+
"128186": {
|
| 1492 |
+
"content": "<|reserved_special_token_178|>",
|
| 1493 |
+
"lstrip": false,
|
| 1494 |
+
"normalized": false,
|
| 1495 |
+
"rstrip": false,
|
| 1496 |
+
"single_word": false,
|
| 1497 |
+
"special": true
|
| 1498 |
+
},
|
| 1499 |
+
"128187": {
|
| 1500 |
+
"content": "<|reserved_special_token_179|>",
|
| 1501 |
+
"lstrip": false,
|
| 1502 |
+
"normalized": false,
|
| 1503 |
+
"rstrip": false,
|
| 1504 |
+
"single_word": false,
|
| 1505 |
+
"special": true
|
| 1506 |
+
},
|
| 1507 |
+
"128188": {
|
| 1508 |
+
"content": "<|reserved_special_token_180|>",
|
| 1509 |
+
"lstrip": false,
|
| 1510 |
+
"normalized": false,
|
| 1511 |
+
"rstrip": false,
|
| 1512 |
+
"single_word": false,
|
| 1513 |
+
"special": true
|
| 1514 |
+
},
|
| 1515 |
+
"128189": {
|
| 1516 |
+
"content": "<|reserved_special_token_181|>",
|
| 1517 |
+
"lstrip": false,
|
| 1518 |
+
"normalized": false,
|
| 1519 |
+
"rstrip": false,
|
| 1520 |
+
"single_word": false,
|
| 1521 |
+
"special": true
|
| 1522 |
+
},
|
| 1523 |
+
"128190": {
|
| 1524 |
+
"content": "<|reserved_special_token_182|>",
|
| 1525 |
+
"lstrip": false,
|
| 1526 |
+
"normalized": false,
|
| 1527 |
+
"rstrip": false,
|
| 1528 |
+
"single_word": false,
|
| 1529 |
+
"special": true
|
| 1530 |
+
},
|
| 1531 |
+
"128191": {
|
| 1532 |
+
"content": "<|reserved_special_token_183|>",
|
| 1533 |
+
"lstrip": false,
|
| 1534 |
+
"normalized": false,
|
| 1535 |
+
"rstrip": false,
|
| 1536 |
+
"single_word": false,
|
| 1537 |
+
"special": true
|
| 1538 |
+
},
|
| 1539 |
+
"128192": {
|
| 1540 |
+
"content": "<|reserved_special_token_184|>",
|
| 1541 |
+
"lstrip": false,
|
| 1542 |
+
"normalized": false,
|
| 1543 |
+
"rstrip": false,
|
| 1544 |
+
"single_word": false,
|
| 1545 |
+
"special": true
|
| 1546 |
+
},
|
| 1547 |
+
"128193": {
|
| 1548 |
+
"content": "<|reserved_special_token_185|>",
|
| 1549 |
+
"lstrip": false,
|
| 1550 |
+
"normalized": false,
|
| 1551 |
+
"rstrip": false,
|
| 1552 |
+
"single_word": false,
|
| 1553 |
+
"special": true
|
| 1554 |
+
},
|
| 1555 |
+
"128194": {
|
| 1556 |
+
"content": "<|reserved_special_token_186|>",
|
| 1557 |
+
"lstrip": false,
|
| 1558 |
+
"normalized": false,
|
| 1559 |
+
"rstrip": false,
|
| 1560 |
+
"single_word": false,
|
| 1561 |
+
"special": true
|
| 1562 |
+
},
|
| 1563 |
+
"128195": {
|
| 1564 |
+
"content": "<|reserved_special_token_187|>",
|
| 1565 |
+
"lstrip": false,
|
| 1566 |
+
"normalized": false,
|
| 1567 |
+
"rstrip": false,
|
| 1568 |
+
"single_word": false,
|
| 1569 |
+
"special": true
|
| 1570 |
+
},
|
| 1571 |
+
"128196": {
|
| 1572 |
+
"content": "<|reserved_special_token_188|>",
|
| 1573 |
+
"lstrip": false,
|
| 1574 |
+
"normalized": false,
|
| 1575 |
+
"rstrip": false,
|
| 1576 |
+
"single_word": false,
|
| 1577 |
+
"special": true
|
| 1578 |
+
},
|
| 1579 |
+
"128197": {
|
| 1580 |
+
"content": "<|reserved_special_token_189|>",
|
| 1581 |
+
"lstrip": false,
|
| 1582 |
+
"normalized": false,
|
| 1583 |
+
"rstrip": false,
|
| 1584 |
+
"single_word": false,
|
| 1585 |
+
"special": true
|
| 1586 |
+
},
|
| 1587 |
+
"128198": {
|
| 1588 |
+
"content": "<|reserved_special_token_190|>",
|
| 1589 |
+
"lstrip": false,
|
| 1590 |
+
"normalized": false,
|
| 1591 |
+
"rstrip": false,
|
| 1592 |
+
"single_word": false,
|
| 1593 |
+
"special": true
|
| 1594 |
+
},
|
| 1595 |
+
"128199": {
|
| 1596 |
+
"content": "<|reserved_special_token_191|>",
|
| 1597 |
+
"lstrip": false,
|
| 1598 |
+
"normalized": false,
|
| 1599 |
+
"rstrip": false,
|
| 1600 |
+
"single_word": false,
|
| 1601 |
+
"special": true
|
| 1602 |
+
},
|
| 1603 |
+
"128200": {
|
| 1604 |
+
"content": "<|reserved_special_token_192|>",
|
| 1605 |
+
"lstrip": false,
|
| 1606 |
+
"normalized": false,
|
| 1607 |
+
"rstrip": false,
|
| 1608 |
+
"single_word": false,
|
| 1609 |
+
"special": true
|
| 1610 |
+
},
|
| 1611 |
+
"128201": {
|
| 1612 |
+
"content": "<|reserved_special_token_193|>",
|
| 1613 |
+
"lstrip": false,
|
| 1614 |
+
"normalized": false,
|
| 1615 |
+
"rstrip": false,
|
| 1616 |
+
"single_word": false,
|
| 1617 |
+
"special": true
|
| 1618 |
+
},
|
| 1619 |
+
"128202": {
|
| 1620 |
+
"content": "<|reserved_special_token_194|>",
|
| 1621 |
+
"lstrip": false,
|
| 1622 |
+
"normalized": false,
|
| 1623 |
+
"rstrip": false,
|
| 1624 |
+
"single_word": false,
|
| 1625 |
+
"special": true
|
| 1626 |
+
},
|
| 1627 |
+
"128203": {
|
| 1628 |
+
"content": "<|reserved_special_token_195|>",
|
| 1629 |
+
"lstrip": false,
|
| 1630 |
+
"normalized": false,
|
| 1631 |
+
"rstrip": false,
|
| 1632 |
+
"single_word": false,
|
| 1633 |
+
"special": true
|
| 1634 |
+
},
|
| 1635 |
+
"128204": {
|
| 1636 |
+
"content": "<|reserved_special_token_196|>",
|
| 1637 |
+
"lstrip": false,
|
| 1638 |
+
"normalized": false,
|
| 1639 |
+
"rstrip": false,
|
| 1640 |
+
"single_word": false,
|
| 1641 |
+
"special": true
|
| 1642 |
+
},
|
| 1643 |
+
"128205": {
|
| 1644 |
+
"content": "<|reserved_special_token_197|>",
|
| 1645 |
+
"lstrip": false,
|
| 1646 |
+
"normalized": false,
|
| 1647 |
+
"rstrip": false,
|
| 1648 |
+
"single_word": false,
|
| 1649 |
+
"special": true
|
| 1650 |
+
},
|
| 1651 |
+
"128206": {
|
| 1652 |
+
"content": "<|reserved_special_token_198|>",
|
| 1653 |
+
"lstrip": false,
|
| 1654 |
+
"normalized": false,
|
| 1655 |
+
"rstrip": false,
|
| 1656 |
+
"single_word": false,
|
| 1657 |
+
"special": true
|
| 1658 |
+
},
|
| 1659 |
+
"128207": {
|
| 1660 |
+
"content": "<|reserved_special_token_199|>",
|
| 1661 |
+
"lstrip": false,
|
| 1662 |
+
"normalized": false,
|
| 1663 |
+
"rstrip": false,
|
| 1664 |
+
"single_word": false,
|
| 1665 |
+
"special": true
|
| 1666 |
+
},
|
| 1667 |
+
"128208": {
|
| 1668 |
+
"content": "<|reserved_special_token_200|>",
|
| 1669 |
+
"lstrip": false,
|
| 1670 |
+
"normalized": false,
|
| 1671 |
+
"rstrip": false,
|
| 1672 |
+
"single_word": false,
|
| 1673 |
+
"special": true
|
| 1674 |
+
},
|
| 1675 |
+
"128209": {
|
| 1676 |
+
"content": "<|reserved_special_token_201|>",
|
| 1677 |
+
"lstrip": false,
|
| 1678 |
+
"normalized": false,
|
| 1679 |
+
"rstrip": false,
|
| 1680 |
+
"single_word": false,
|
| 1681 |
+
"special": true
|
| 1682 |
+
},
|
| 1683 |
+
"128210": {
|
| 1684 |
+
"content": "<|reserved_special_token_202|>",
|
| 1685 |
+
"lstrip": false,
|
| 1686 |
+
"normalized": false,
|
| 1687 |
+
"rstrip": false,
|
| 1688 |
+
"single_word": false,
|
| 1689 |
+
"special": true
|
| 1690 |
+
},
|
| 1691 |
+
"128211": {
|
| 1692 |
+
"content": "<|reserved_special_token_203|>",
|
| 1693 |
+
"lstrip": false,
|
| 1694 |
+
"normalized": false,
|
| 1695 |
+
"rstrip": false,
|
| 1696 |
+
"single_word": false,
|
| 1697 |
+
"special": true
|
| 1698 |
+
},
|
| 1699 |
+
"128212": {
|
| 1700 |
+
"content": "<|reserved_special_token_204|>",
|
| 1701 |
+
"lstrip": false,
|
| 1702 |
+
"normalized": false,
|
| 1703 |
+
"rstrip": false,
|
| 1704 |
+
"single_word": false,
|
| 1705 |
+
"special": true
|
| 1706 |
+
},
|
| 1707 |
+
"128213": {
|
| 1708 |
+
"content": "<|reserved_special_token_205|>",
|
| 1709 |
+
"lstrip": false,
|
| 1710 |
+
"normalized": false,
|
| 1711 |
+
"rstrip": false,
|
| 1712 |
+
"single_word": false,
|
| 1713 |
+
"special": true
|
| 1714 |
+
},
|
| 1715 |
+
"128214": {
|
| 1716 |
+
"content": "<|reserved_special_token_206|>",
|
| 1717 |
+
"lstrip": false,
|
| 1718 |
+
"normalized": false,
|
| 1719 |
+
"rstrip": false,
|
| 1720 |
+
"single_word": false,
|
| 1721 |
+
"special": true
|
| 1722 |
+
},
|
| 1723 |
+
"128215": {
|
| 1724 |
+
"content": "<|reserved_special_token_207|>",
|
| 1725 |
+
"lstrip": false,
|
| 1726 |
+
"normalized": false,
|
| 1727 |
+
"rstrip": false,
|
| 1728 |
+
"single_word": false,
|
| 1729 |
+
"special": true
|
| 1730 |
+
},
|
| 1731 |
+
"128216": {
|
| 1732 |
+
"content": "<|reserved_special_token_208|>",
|
| 1733 |
+
"lstrip": false,
|
| 1734 |
+
"normalized": false,
|
| 1735 |
+
"rstrip": false,
|
| 1736 |
+
"single_word": false,
|
| 1737 |
+
"special": true
|
| 1738 |
+
},
|
| 1739 |
+
"128217": {
|
| 1740 |
+
"content": "<|reserved_special_token_209|>",
|
| 1741 |
+
"lstrip": false,
|
| 1742 |
+
"normalized": false,
|
| 1743 |
+
"rstrip": false,
|
| 1744 |
+
"single_word": false,
|
| 1745 |
+
"special": true
|
| 1746 |
+
},
|
| 1747 |
+
"128218": {
|
| 1748 |
+
"content": "<|reserved_special_token_210|>",
|
| 1749 |
+
"lstrip": false,
|
| 1750 |
+
"normalized": false,
|
| 1751 |
+
"rstrip": false,
|
| 1752 |
+
"single_word": false,
|
| 1753 |
+
"special": true
|
| 1754 |
+
},
|
| 1755 |
+
"128219": {
|
| 1756 |
+
"content": "<|reserved_special_token_211|>",
|
| 1757 |
+
"lstrip": false,
|
| 1758 |
+
"normalized": false,
|
| 1759 |
+
"rstrip": false,
|
| 1760 |
+
"single_word": false,
|
| 1761 |
+
"special": true
|
| 1762 |
+
},
|
| 1763 |
+
"128220": {
|
| 1764 |
+
"content": "<|reserved_special_token_212|>",
|
| 1765 |
+
"lstrip": false,
|
| 1766 |
+
"normalized": false,
|
| 1767 |
+
"rstrip": false,
|
| 1768 |
+
"single_word": false,
|
| 1769 |
+
"special": true
|
| 1770 |
+
},
|
| 1771 |
+
"128221": {
|
| 1772 |
+
"content": "<|reserved_special_token_213|>",
|
| 1773 |
+
"lstrip": false,
|
| 1774 |
+
"normalized": false,
|
| 1775 |
+
"rstrip": false,
|
| 1776 |
+
"single_word": false,
|
| 1777 |
+
"special": true
|
| 1778 |
+
},
|
| 1779 |
+
"128222": {
|
| 1780 |
+
"content": "<|reserved_special_token_214|>",
|
| 1781 |
+
"lstrip": false,
|
| 1782 |
+
"normalized": false,
|
| 1783 |
+
"rstrip": false,
|
| 1784 |
+
"single_word": false,
|
| 1785 |
+
"special": true
|
| 1786 |
+
},
|
| 1787 |
+
"128223": {
|
| 1788 |
+
"content": "<|reserved_special_token_215|>",
|
| 1789 |
+
"lstrip": false,
|
| 1790 |
+
"normalized": false,
|
| 1791 |
+
"rstrip": false,
|
| 1792 |
+
"single_word": false,
|
| 1793 |
+
"special": true
|
| 1794 |
+
},
|
| 1795 |
+
"128224": {
|
| 1796 |
+
"content": "<|reserved_special_token_216|>",
|
| 1797 |
+
"lstrip": false,
|
| 1798 |
+
"normalized": false,
|
| 1799 |
+
"rstrip": false,
|
| 1800 |
+
"single_word": false,
|
| 1801 |
+
"special": true
|
| 1802 |
+
},
|
| 1803 |
+
"128225": {
|
| 1804 |
+
"content": "<|reserved_special_token_217|>",
|
| 1805 |
+
"lstrip": false,
|
| 1806 |
+
"normalized": false,
|
| 1807 |
+
"rstrip": false,
|
| 1808 |
+
"single_word": false,
|
| 1809 |
+
"special": true
|
| 1810 |
+
},
|
| 1811 |
+
"128226": {
|
| 1812 |
+
"content": "<|reserved_special_token_218|>",
|
| 1813 |
+
"lstrip": false,
|
| 1814 |
+
"normalized": false,
|
| 1815 |
+
"rstrip": false,
|
| 1816 |
+
"single_word": false,
|
| 1817 |
+
"special": true
|
| 1818 |
+
},
|
| 1819 |
+
"128227": {
|
| 1820 |
+
"content": "<|reserved_special_token_219|>",
|
| 1821 |
+
"lstrip": false,
|
| 1822 |
+
"normalized": false,
|
| 1823 |
+
"rstrip": false,
|
| 1824 |
+
"single_word": false,
|
| 1825 |
+
"special": true
|
| 1826 |
+
},
|
| 1827 |
+
"128228": {
|
| 1828 |
+
"content": "<|reserved_special_token_220|>",
|
| 1829 |
+
"lstrip": false,
|
| 1830 |
+
"normalized": false,
|
| 1831 |
+
"rstrip": false,
|
| 1832 |
+
"single_word": false,
|
| 1833 |
+
"special": true
|
| 1834 |
+
},
|
| 1835 |
+
"128229": {
|
| 1836 |
+
"content": "<|reserved_special_token_221|>",
|
| 1837 |
+
"lstrip": false,
|
| 1838 |
+
"normalized": false,
|
| 1839 |
+
"rstrip": false,
|
| 1840 |
+
"single_word": false,
|
| 1841 |
+
"special": true
|
| 1842 |
+
},
|
| 1843 |
+
"128230": {
|
| 1844 |
+
"content": "<|reserved_special_token_222|>",
|
| 1845 |
+
"lstrip": false,
|
| 1846 |
+
"normalized": false,
|
| 1847 |
+
"rstrip": false,
|
| 1848 |
+
"single_word": false,
|
| 1849 |
+
"special": true
|
| 1850 |
+
},
|
| 1851 |
+
"128231": {
|
| 1852 |
+
"content": "<|reserved_special_token_223|>",
|
| 1853 |
+
"lstrip": false,
|
| 1854 |
+
"normalized": false,
|
| 1855 |
+
"rstrip": false,
|
| 1856 |
+
"single_word": false,
|
| 1857 |
+
"special": true
|
| 1858 |
+
},
|
| 1859 |
+
"128232": {
|
| 1860 |
+
"content": "<|reserved_special_token_224|>",
|
| 1861 |
+
"lstrip": false,
|
| 1862 |
+
"normalized": false,
|
| 1863 |
+
"rstrip": false,
|
| 1864 |
+
"single_word": false,
|
| 1865 |
+
"special": true
|
| 1866 |
+
},
|
| 1867 |
+
"128233": {
|
| 1868 |
+
"content": "<|reserved_special_token_225|>",
|
| 1869 |
+
"lstrip": false,
|
| 1870 |
+
"normalized": false,
|
| 1871 |
+
"rstrip": false,
|
| 1872 |
+
"single_word": false,
|
| 1873 |
+
"special": true
|
| 1874 |
+
},
|
| 1875 |
+
"128234": {
|
| 1876 |
+
"content": "<|reserved_special_token_226|>",
|
| 1877 |
+
"lstrip": false,
|
| 1878 |
+
"normalized": false,
|
| 1879 |
+
"rstrip": false,
|
| 1880 |
+
"single_word": false,
|
| 1881 |
+
"special": true
|
| 1882 |
+
},
|
| 1883 |
+
"128235": {
|
| 1884 |
+
"content": "<|reserved_special_token_227|>",
|
| 1885 |
+
"lstrip": false,
|
| 1886 |
+
"normalized": false,
|
| 1887 |
+
"rstrip": false,
|
| 1888 |
+
"single_word": false,
|
| 1889 |
+
"special": true
|
| 1890 |
+
},
|
| 1891 |
+
"128236": {
|
| 1892 |
+
"content": "<|reserved_special_token_228|>",
|
| 1893 |
+
"lstrip": false,
|
| 1894 |
+
"normalized": false,
|
| 1895 |
+
"rstrip": false,
|
| 1896 |
+
"single_word": false,
|
| 1897 |
+
"special": true
|
| 1898 |
+
},
|
| 1899 |
+
"128237": {
|
| 1900 |
+
"content": "<|reserved_special_token_229|>",
|
| 1901 |
+
"lstrip": false,
|
| 1902 |
+
"normalized": false,
|
| 1903 |
+
"rstrip": false,
|
| 1904 |
+
"single_word": false,
|
| 1905 |
+
"special": true
|
| 1906 |
+
},
|
| 1907 |
+
"128238": {
|
| 1908 |
+
"content": "<|reserved_special_token_230|>",
|
| 1909 |
+
"lstrip": false,
|
| 1910 |
+
"normalized": false,
|
| 1911 |
+
"rstrip": false,
|
| 1912 |
+
"single_word": false,
|
| 1913 |
+
"special": true
|
| 1914 |
+
},
|
| 1915 |
+
"128239": {
|
| 1916 |
+
"content": "<|reserved_special_token_231|>",
|
| 1917 |
+
"lstrip": false,
|
| 1918 |
+
"normalized": false,
|
| 1919 |
+
"rstrip": false,
|
| 1920 |
+
"single_word": false,
|
| 1921 |
+
"special": true
|
| 1922 |
+
},
|
| 1923 |
+
"128240": {
|
| 1924 |
+
"content": "<|reserved_special_token_232|>",
|
| 1925 |
+
"lstrip": false,
|
| 1926 |
+
"normalized": false,
|
| 1927 |
+
"rstrip": false,
|
| 1928 |
+
"single_word": false,
|
| 1929 |
+
"special": true
|
| 1930 |
+
},
|
| 1931 |
+
"128241": {
|
| 1932 |
+
"content": "<|reserved_special_token_233|>",
|
| 1933 |
+
"lstrip": false,
|
| 1934 |
+
"normalized": false,
|
| 1935 |
+
"rstrip": false,
|
| 1936 |
+
"single_word": false,
|
| 1937 |
+
"special": true
|
| 1938 |
+
},
|
| 1939 |
+
"128242": {
|
| 1940 |
+
"content": "<|reserved_special_token_234|>",
|
| 1941 |
+
"lstrip": false,
|
| 1942 |
+
"normalized": false,
|
| 1943 |
+
"rstrip": false,
|
| 1944 |
+
"single_word": false,
|
| 1945 |
+
"special": true
|
| 1946 |
+
},
|
| 1947 |
+
"128243": {
|
| 1948 |
+
"content": "<|reserved_special_token_235|>",
|
| 1949 |
+
"lstrip": false,
|
| 1950 |
+
"normalized": false,
|
| 1951 |
+
"rstrip": false,
|
| 1952 |
+
"single_word": false,
|
| 1953 |
+
"special": true
|
| 1954 |
+
},
|
| 1955 |
+
"128244": {
|
| 1956 |
+
"content": "<|reserved_special_token_236|>",
|
| 1957 |
+
"lstrip": false,
|
| 1958 |
+
"normalized": false,
|
| 1959 |
+
"rstrip": false,
|
| 1960 |
+
"single_word": false,
|
| 1961 |
+
"special": true
|
| 1962 |
+
},
|
| 1963 |
+
"128245": {
|
| 1964 |
+
"content": "<|reserved_special_token_237|>",
|
| 1965 |
+
"lstrip": false,
|
| 1966 |
+
"normalized": false,
|
| 1967 |
+
"rstrip": false,
|
| 1968 |
+
"single_word": false,
|
| 1969 |
+
"special": true
|
| 1970 |
+
},
|
| 1971 |
+
"128246": {
|
| 1972 |
+
"content": "<|reserved_special_token_238|>",
|
| 1973 |
+
"lstrip": false,
|
| 1974 |
+
"normalized": false,
|
| 1975 |
+
"rstrip": false,
|
| 1976 |
+
"single_word": false,
|
| 1977 |
+
"special": true
|
| 1978 |
+
},
|
| 1979 |
+
"128247": {
|
| 1980 |
+
"content": "<|reserved_special_token_239|>",
|
| 1981 |
+
"lstrip": false,
|
| 1982 |
+
"normalized": false,
|
| 1983 |
+
"rstrip": false,
|
| 1984 |
+
"single_word": false,
|
| 1985 |
+
"special": true
|
| 1986 |
+
},
|
| 1987 |
+
"128248": {
|
| 1988 |
+
"content": "<|reserved_special_token_240|>",
|
| 1989 |
+
"lstrip": false,
|
| 1990 |
+
"normalized": false,
|
| 1991 |
+
"rstrip": false,
|
| 1992 |
+
"single_word": false,
|
| 1993 |
+
"special": true
|
| 1994 |
+
},
|
| 1995 |
+
"128249": {
|
| 1996 |
+
"content": "<|reserved_special_token_241|>",
|
| 1997 |
+
"lstrip": false,
|
| 1998 |
+
"normalized": false,
|
| 1999 |
+
"rstrip": false,
|
| 2000 |
+
"single_word": false,
|
| 2001 |
+
"special": true
|
| 2002 |
+
},
|
| 2003 |
+
"128250": {
|
| 2004 |
+
"content": "<|reserved_special_token_242|>",
|
| 2005 |
+
"lstrip": false,
|
| 2006 |
+
"normalized": false,
|
| 2007 |
+
"rstrip": false,
|
| 2008 |
+
"single_word": false,
|
| 2009 |
+
"special": true
|
| 2010 |
+
},
|
| 2011 |
+
"128251": {
|
| 2012 |
+
"content": "<|reserved_special_token_243|>",
|
| 2013 |
+
"lstrip": false,
|
| 2014 |
+
"normalized": false,
|
| 2015 |
+
"rstrip": false,
|
| 2016 |
+
"single_word": false,
|
| 2017 |
+
"special": true
|
| 2018 |
+
},
|
| 2019 |
+
"128252": {
|
| 2020 |
+
"content": "<|reserved_special_token_244|>",
|
| 2021 |
+
"lstrip": false,
|
| 2022 |
+
"normalized": false,
|
| 2023 |
+
"rstrip": false,
|
| 2024 |
+
"single_word": false,
|
| 2025 |
+
"special": true
|
| 2026 |
+
},
|
| 2027 |
+
"128253": {
|
| 2028 |
+
"content": "<|reserved_special_token_245|>",
|
| 2029 |
+
"lstrip": false,
|
| 2030 |
+
"normalized": false,
|
| 2031 |
+
"rstrip": false,
|
| 2032 |
+
"single_word": false,
|
| 2033 |
+
"special": true
|
| 2034 |
+
},
|
| 2035 |
+
"128254": {
|
| 2036 |
+
"content": "<|reserved_special_token_246|>",
|
| 2037 |
+
"lstrip": false,
|
| 2038 |
+
"normalized": false,
|
| 2039 |
+
"rstrip": false,
|
| 2040 |
+
"single_word": false,
|
| 2041 |
+
"special": true
|
| 2042 |
+
},
|
| 2043 |
+
"128255": {
|
| 2044 |
+
"content": "<|reserved_special_token_247|>",
|
| 2045 |
+
"lstrip": false,
|
| 2046 |
+
"normalized": false,
|
| 2047 |
+
"rstrip": false,
|
| 2048 |
+
"single_word": false,
|
| 2049 |
+
"special": true
|
| 2050 |
+
}
|
| 2051 |
+
},
|
| 2052 |
+
"bos_token": "<|begin_of_text|>",
|
| 2053 |
+
"chat_template": "{{- bos_token }}\n{%- if custom_tools is defined %}\n {%- set tools = custom_tools %}\n{%- endif %}\n{%- if not tools_in_user_message is defined %}\n {%- set tools_in_user_message = true %}\n{%- endif %}\n{%- if not date_string is defined %}\n {%- if strftime_now is defined %}\n {%- set date_string = strftime_now(\"%d %b %Y\") %}\n {%- else %}\n {%- set date_string = \"26 Jul 2024\" %}\n {%- endif %}\n{%- endif %}\n{%- if not tools is defined %}\n {%- set tools = none %}\n{%- endif %}\n\n{#- This block extracts the system message, so we can slot it into the right place. #}\n{%- if messages[0]['role'] == 'system' %}\n {%- set system_message = messages[0]['content']|trim %}\n {%- set messages = messages[1:] %}\n{%- else %}\n {%- set system_message = \"\" %}\n{%- endif %}\n\n{#- System message #}\n{{- \"<|start_header_id|>system<|end_header_id|>\\n\\n\" }}\n{%- if tools is not none %}\n {{- \"Environment: ipython\\n\" }}\n{%- endif %}\n{{- \"Cutting Knowledge Date: December 2023\\n\" }}\n{{- \"Today Date: \" + date_string + \"\\n\\n\" }}\n{%- if tools is not none and not tools_in_user_message %}\n {{- \"You have access to the following functions. To call a function, please respond with JSON for a function call.\" }}\n {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n {{- \"Do not use variables.\\n\\n\" }}\n {%- for t in tools %}\n {{- t | tojson(indent=4) }}\n {{- \"\\n\\n\" }}\n {%- endfor %}\n{%- endif %}\n{{- system_message }}\n{{- \"<|eot_id|>\" }}\n\n{#- Custom tools are passed in a user message with some extra guidance #}\n{%- if tools_in_user_message and not tools is none %}\n {#- Extract the first user message so we can plug it in here #}\n {%- if messages | length != 0 %}\n {%- set first_user_message = messages[0]['content']|trim %}\n {%- set messages = messages[1:] %}\n {%- else %}\n {{- raise_exception(\"Cannot put tools in the first user message when there's no first user message!\") }}\n{%- endif %}\n {{- '<|start_header_id|>user<|end_header_id|>\\n\\n' -}}\n {{- \"Given the following functions, please respond with a JSON for a function call \" }}\n {{- \"with its proper arguments that best answers the given prompt.\\n\\n\" }}\n {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n {{- \"Do not use variables.\\n\\n\" }}\n {%- for t in tools %}\n {{- t | tojson(indent=4) }}\n {{- \"\\n\\n\" }}\n {%- endfor %}\n {{- first_user_message + \"<|eot_id|>\"}}\n{%- endif %}\n\n{%- for message in messages %}\n {%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %}\n {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\\n\\n'+ message['content'] | trim + '<|eot_id|>' }}\n {%- elif 'tool_calls' in message %}\n {%- if not message.tool_calls|length == 1 %}\n {{- raise_exception(\"This model only supports single tool-calls at once!\") }}\n {%- endif %}\n {%- set tool_call = message.tool_calls[0].function %}\n {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' -}}\n {{- '{\"name\": \"' + tool_call.name + '\", ' }}\n {{- '\"parameters\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- \"}\" }}\n {{- \"<|eot_id|>\" }}\n {%- elif message.role == \"tool\" or message.role == \"ipython\" %}\n {{- \"<|start_header_id|>ipython<|end_header_id|>\\n\\n\" }}\n {%- if message.content is mapping or message.content is iterable %}\n {{- message.content | tojson }}\n {%- else %}\n {{- message.content }}\n {%- endif %}\n {{- \"<|eot_id|>\" }}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' }}\n{%- endif %}\n",
|
| 2054 |
+
"clean_up_tokenization_spaces": true,
|
| 2055 |
+
"eos_token": "<|eot_id|>",
|
| 2056 |
+
"model_input_names": [
|
| 2057 |
+
"input_ids",
|
| 2058 |
+
"attention_mask"
|
| 2059 |
+
],
|
| 2060 |
+
"model_max_length": 131072,
|
| 2061 |
+
"pad_token": "<|eot_id|>",
|
| 2062 |
+
"padding_side": "right",
|
| 2063 |
+
"split_special_tokens": false,
|
| 2064 |
+
"tokenizer_class": "PreTrainedTokenizerFast"
|
| 2065 |
+
}
|
checkpoint-100/trainer_state.json
ADDED
|
@@ -0,0 +1,893 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.011823242530226707,
|
| 3 |
+
"best_model_checkpoint": "/home/paperspace/Data/models/relianceV2/llm3br256/checkpoint-100",
|
| 4 |
+
"epoch": 4.921212121212121,
|
| 5 |
+
"eval_steps": 5,
|
| 6 |
+
"global_step": 100,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.048484848484848485,
|
| 13 |
+
"grad_norm": 0.13376639783382416,
|
| 14 |
+
"learning_rate": 1e-05,
|
| 15 |
+
"loss": 0.063,
|
| 16 |
+
"step": 1
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.09696969696969697,
|
| 20 |
+
"grad_norm": 0.12203846871852875,
|
| 21 |
+
"learning_rate": 2e-05,
|
| 22 |
+
"loss": 0.0607,
|
| 23 |
+
"step": 2
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.14545454545454545,
|
| 27 |
+
"grad_norm": 0.13988564908504486,
|
| 28 |
+
"learning_rate": 3e-05,
|
| 29 |
+
"loss": 0.0615,
|
| 30 |
+
"step": 3
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.19393939393939394,
|
| 34 |
+
"grad_norm": 0.10985743254423141,
|
| 35 |
+
"learning_rate": 4e-05,
|
| 36 |
+
"loss": 0.0504,
|
| 37 |
+
"step": 4
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.24242424242424243,
|
| 41 |
+
"grad_norm": 0.07405027747154236,
|
| 42 |
+
"learning_rate": 5e-05,
|
| 43 |
+
"loss": 0.0395,
|
| 44 |
+
"step": 5
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.24242424242424243,
|
| 48 |
+
"eval_loss": 0.04326783865690231,
|
| 49 |
+
"eval_runtime": 11.3564,
|
| 50 |
+
"eval_samples_per_second": 4.403,
|
| 51 |
+
"eval_steps_per_second": 1.145,
|
| 52 |
+
"step": 5
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.2909090909090909,
|
| 56 |
+
"grad_norm": 0.09203900396823883,
|
| 57 |
+
"learning_rate": 6e-05,
|
| 58 |
+
"loss": 0.0419,
|
| 59 |
+
"step": 6
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.3393939393939394,
|
| 63 |
+
"grad_norm": 0.07265866547822952,
|
| 64 |
+
"learning_rate": 7e-05,
|
| 65 |
+
"loss": 0.0381,
|
| 66 |
+
"step": 7
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.3878787878787879,
|
| 70 |
+
"grad_norm": 0.04461047425866127,
|
| 71 |
+
"learning_rate": 8e-05,
|
| 72 |
+
"loss": 0.0341,
|
| 73 |
+
"step": 8
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.43636363636363634,
|
| 77 |
+
"grad_norm": 0.04746266454458237,
|
| 78 |
+
"learning_rate": 9e-05,
|
| 79 |
+
"loss": 0.0345,
|
| 80 |
+
"step": 9
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.48484848484848486,
|
| 84 |
+
"grad_norm": 0.040007542818784714,
|
| 85 |
+
"learning_rate": 0.0001,
|
| 86 |
+
"loss": 0.0324,
|
| 87 |
+
"step": 10
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.48484848484848486,
|
| 91 |
+
"eval_loss": 0.03000650927424431,
|
| 92 |
+
"eval_runtime": 10.3489,
|
| 93 |
+
"eval_samples_per_second": 4.831,
|
| 94 |
+
"eval_steps_per_second": 1.256,
|
| 95 |
+
"step": 10
|
| 96 |
+
},
|
| 97 |
+
{
|
| 98 |
+
"epoch": 0.5333333333333333,
|
| 99 |
+
"grad_norm": 0.03799016401171684,
|
| 100 |
+
"learning_rate": 9.99695413509548e-05,
|
| 101 |
+
"loss": 0.0331,
|
| 102 |
+
"step": 11
|
| 103 |
+
},
|
| 104 |
+
{
|
| 105 |
+
"epoch": 0.5818181818181818,
|
| 106 |
+
"grad_norm": 0.03196106478571892,
|
| 107 |
+
"learning_rate": 9.987820251299122e-05,
|
| 108 |
+
"loss": 0.029,
|
| 109 |
+
"step": 12
|
| 110 |
+
},
|
| 111 |
+
{
|
| 112 |
+
"epoch": 0.6303030303030303,
|
| 113 |
+
"grad_norm": 0.027229588478803635,
|
| 114 |
+
"learning_rate": 9.972609476841367e-05,
|
| 115 |
+
"loss": 0.0257,
|
| 116 |
+
"step": 13
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 0.6787878787878788,
|
| 120 |
+
"grad_norm": 0.02768268622457981,
|
| 121 |
+
"learning_rate": 9.951340343707852e-05,
|
| 122 |
+
"loss": 0.0215,
|
| 123 |
+
"step": 14
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 0.7272727272727273,
|
| 127 |
+
"grad_norm": 0.032983552664518356,
|
| 128 |
+
"learning_rate": 9.924038765061042e-05,
|
| 129 |
+
"loss": 0.024,
|
| 130 |
+
"step": 15
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"epoch": 0.7272727272727273,
|
| 134 |
+
"eval_loss": 0.024439169093966484,
|
| 135 |
+
"eval_runtime": 10.352,
|
| 136 |
+
"eval_samples_per_second": 4.83,
|
| 137 |
+
"eval_steps_per_second": 1.256,
|
| 138 |
+
"step": 15
|
| 139 |
+
},
|
| 140 |
+
{
|
| 141 |
+
"epoch": 0.7757575757575758,
|
| 142 |
+
"grad_norm": 0.03327898308634758,
|
| 143 |
+
"learning_rate": 9.890738003669029e-05,
|
| 144 |
+
"loss": 0.0321,
|
| 145 |
+
"step": 16
|
| 146 |
+
},
|
| 147 |
+
{
|
| 148 |
+
"epoch": 0.8242424242424242,
|
| 149 |
+
"grad_norm": 0.02506704442203045,
|
| 150 |
+
"learning_rate": 9.851478631379982e-05,
|
| 151 |
+
"loss": 0.0281,
|
| 152 |
+
"step": 17
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 0.8727272727272727,
|
| 156 |
+
"grad_norm": 0.023538140580058098,
|
| 157 |
+
"learning_rate": 9.806308479691595e-05,
|
| 158 |
+
"loss": 0.0202,
|
| 159 |
+
"step": 18
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 0.9212121212121213,
|
| 163 |
+
"grad_norm": 0.02581767924129963,
|
| 164 |
+
"learning_rate": 9.755282581475769e-05,
|
| 165 |
+
"loss": 0.0206,
|
| 166 |
+
"step": 19
|
| 167 |
+
},
|
| 168 |
+
{
|
| 169 |
+
"epoch": 0.9696969696969697,
|
| 170 |
+
"grad_norm": 0.021269701421260834,
|
| 171 |
+
"learning_rate": 9.698463103929542e-05,
|
| 172 |
+
"loss": 0.0189,
|
| 173 |
+
"step": 20
|
| 174 |
+
},
|
| 175 |
+
{
|
| 176 |
+
"epoch": 0.9696969696969697,
|
| 177 |
+
"eval_loss": 0.0212231557816267,
|
| 178 |
+
"eval_runtime": 10.4147,
|
| 179 |
+
"eval_samples_per_second": 4.801,
|
| 180 |
+
"eval_steps_per_second": 1.248,
|
| 181 |
+
"step": 20
|
| 182 |
+
},
|
| 183 |
+
{
|
| 184 |
+
"epoch": 1.0363636363636364,
|
| 185 |
+
"grad_norm": 0.037210095673799515,
|
| 186 |
+
"learning_rate": 9.635919272833938e-05,
|
| 187 |
+
"loss": 0.0317,
|
| 188 |
+
"step": 21
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 1.084848484848485,
|
| 192 |
+
"grad_norm": 0.02000698819756508,
|
| 193 |
+
"learning_rate": 9.567727288213005e-05,
|
| 194 |
+
"loss": 0.019,
|
| 195 |
+
"step": 22
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 1.1333333333333333,
|
| 199 |
+
"grad_norm": 0.020116321742534637,
|
| 200 |
+
"learning_rate": 9.493970231495835e-05,
|
| 201 |
+
"loss": 0.019,
|
| 202 |
+
"step": 23
|
| 203 |
+
},
|
| 204 |
+
{
|
| 205 |
+
"epoch": 1.1818181818181819,
|
| 206 |
+
"grad_norm": 0.022886989638209343,
|
| 207 |
+
"learning_rate": 9.414737964294636e-05,
|
| 208 |
+
"loss": 0.0181,
|
| 209 |
+
"step": 24
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 1.2303030303030302,
|
| 213 |
+
"grad_norm": 0.023031054064631462,
|
| 214 |
+
"learning_rate": 9.330127018922194e-05,
|
| 215 |
+
"loss": 0.0171,
|
| 216 |
+
"step": 25
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 1.2303030303030302,
|
| 220 |
+
"eval_loss": 0.019027845934033394,
|
| 221 |
+
"eval_runtime": 10.3362,
|
| 222 |
+
"eval_samples_per_second": 4.837,
|
| 223 |
+
"eval_steps_per_second": 1.258,
|
| 224 |
+
"step": 25
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 1.2787878787878788,
|
| 228 |
+
"grad_norm": 0.01873927377164364,
|
| 229 |
+
"learning_rate": 9.24024048078213e-05,
|
| 230 |
+
"loss": 0.0182,
|
| 231 |
+
"step": 26
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 1.3272727272727272,
|
| 235 |
+
"grad_norm": 0.018605511635541916,
|
| 236 |
+
"learning_rate": 9.145187862775209e-05,
|
| 237 |
+
"loss": 0.0163,
|
| 238 |
+
"step": 27
|
| 239 |
+
},
|
| 240 |
+
{
|
| 241 |
+
"epoch": 1.3757575757575757,
|
| 242 |
+
"grad_norm": 0.023363754153251648,
|
| 243 |
+
"learning_rate": 9.045084971874738e-05,
|
| 244 |
+
"loss": 0.0177,
|
| 245 |
+
"step": 28
|
| 246 |
+
},
|
| 247 |
+
{
|
| 248 |
+
"epoch": 1.4242424242424243,
|
| 249 |
+
"grad_norm": 0.017733635380864143,
|
| 250 |
+
"learning_rate": 8.940053768033609e-05,
|
| 251 |
+
"loss": 0.014,
|
| 252 |
+
"step": 29
|
| 253 |
+
},
|
| 254 |
+
{
|
| 255 |
+
"epoch": 1.4727272727272727,
|
| 256 |
+
"grad_norm": 0.0225802194327116,
|
| 257 |
+
"learning_rate": 8.83022221559489e-05,
|
| 258 |
+
"loss": 0.0146,
|
| 259 |
+
"step": 30
|
| 260 |
+
},
|
| 261 |
+
{
|
| 262 |
+
"epoch": 1.4727272727272727,
|
| 263 |
+
"eval_loss": 0.01733844168484211,
|
| 264 |
+
"eval_runtime": 10.3386,
|
| 265 |
+
"eval_samples_per_second": 4.836,
|
| 266 |
+
"eval_steps_per_second": 1.257,
|
| 267 |
+
"step": 30
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 1.5212121212121212,
|
| 271 |
+
"grad_norm": 0.018234577029943466,
|
| 272 |
+
"learning_rate": 8.715724127386972e-05,
|
| 273 |
+
"loss": 0.017,
|
| 274 |
+
"step": 31
|
| 275 |
+
},
|
| 276 |
+
{
|
| 277 |
+
"epoch": 1.5696969696969698,
|
| 278 |
+
"grad_norm": 0.024176109582185745,
|
| 279 |
+
"learning_rate": 8.596699001693255e-05,
|
| 280 |
+
"loss": 0.0155,
|
| 281 |
+
"step": 32
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 1.6181818181818182,
|
| 285 |
+
"grad_norm": 0.023358961567282677,
|
| 286 |
+
"learning_rate": 8.473291852294987e-05,
|
| 287 |
+
"loss": 0.0157,
|
| 288 |
+
"step": 33
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"epoch": 1.6666666666666665,
|
| 292 |
+
"grad_norm": 0.025254715234041214,
|
| 293 |
+
"learning_rate": 8.345653031794292e-05,
|
| 294 |
+
"loss": 0.0167,
|
| 295 |
+
"step": 34
|
| 296 |
+
},
|
| 297 |
+
{
|
| 298 |
+
"epoch": 1.7151515151515153,
|
| 299 |
+
"grad_norm": 0.021989861503243446,
|
| 300 |
+
"learning_rate": 8.213938048432697e-05,
|
| 301 |
+
"loss": 0.0144,
|
| 302 |
+
"step": 35
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 1.7151515151515153,
|
| 306 |
+
"eval_loss": 0.016134196892380714,
|
| 307 |
+
"eval_runtime": 10.3976,
|
| 308 |
+
"eval_samples_per_second": 4.809,
|
| 309 |
+
"eval_steps_per_second": 1.25,
|
| 310 |
+
"step": 35
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 1.7636363636363637,
|
| 314 |
+
"grad_norm": 0.018357617780566216,
|
| 315 |
+
"learning_rate": 8.07830737662829e-05,
|
| 316 |
+
"loss": 0.0162,
|
| 317 |
+
"step": 36
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 1.812121212121212,
|
| 321 |
+
"grad_norm": 0.021665558218955994,
|
| 322 |
+
"learning_rate": 7.938926261462366e-05,
|
| 323 |
+
"loss": 0.0194,
|
| 324 |
+
"step": 37
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 1.8606060606060606,
|
| 328 |
+
"grad_norm": 0.020184990018606186,
|
| 329 |
+
"learning_rate": 7.795964517353735e-05,
|
| 330 |
+
"loss": 0.0154,
|
| 331 |
+
"step": 38
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 1.9090909090909092,
|
| 335 |
+
"grad_norm": 0.016307702288031578,
|
| 336 |
+
"learning_rate": 7.649596321166024e-05,
|
| 337 |
+
"loss": 0.0134,
|
| 338 |
+
"step": 39
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 1.9575757575757575,
|
| 342 |
+
"grad_norm": 0.01873622089624405,
|
| 343 |
+
"learning_rate": 7.500000000000001e-05,
|
| 344 |
+
"loss": 0.0104,
|
| 345 |
+
"step": 40
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 1.9575757575757575,
|
| 349 |
+
"eval_loss": 0.015456685796380043,
|
| 350 |
+
"eval_runtime": 10.3404,
|
| 351 |
+
"eval_samples_per_second": 4.835,
|
| 352 |
+
"eval_steps_per_second": 1.257,
|
| 353 |
+
"step": 40
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 2.0242424242424244,
|
| 357 |
+
"grad_norm": 0.03928119316697121,
|
| 358 |
+
"learning_rate": 7.347357813929454e-05,
|
| 359 |
+
"loss": 0.0277,
|
| 360 |
+
"step": 41
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 2.0727272727272728,
|
| 364 |
+
"grad_norm": 0.01585806906223297,
|
| 365 |
+
"learning_rate": 7.191855733945387e-05,
|
| 366 |
+
"loss": 0.012,
|
| 367 |
+
"step": 42
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 2.121212121212121,
|
| 371 |
+
"grad_norm": 0.022943127900362015,
|
| 372 |
+
"learning_rate": 7.033683215379002e-05,
|
| 373 |
+
"loss": 0.0147,
|
| 374 |
+
"step": 43
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 2.16969696969697,
|
| 378 |
+
"grad_norm": 0.022961463779211044,
|
| 379 |
+
"learning_rate": 6.873032967079561e-05,
|
| 380 |
+
"loss": 0.014,
|
| 381 |
+
"step": 44
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 2.2181818181818183,
|
| 385 |
+
"grad_norm": 0.017532989382743835,
|
| 386 |
+
"learning_rate": 6.710100716628344e-05,
|
| 387 |
+
"loss": 0.0143,
|
| 388 |
+
"step": 45
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 2.2181818181818183,
|
| 392 |
+
"eval_loss": 0.01516613457351923,
|
| 393 |
+
"eval_runtime": 10.3353,
|
| 394 |
+
"eval_samples_per_second": 4.838,
|
| 395 |
+
"eval_steps_per_second": 1.258,
|
| 396 |
+
"step": 45
|
| 397 |
+
},
|
| 398 |
+
{
|
| 399 |
+
"epoch": 2.2666666666666666,
|
| 400 |
+
"grad_norm": 0.026267599314451218,
|
| 401 |
+
"learning_rate": 6.545084971874738e-05,
|
| 402 |
+
"loss": 0.0126,
|
| 403 |
+
"step": 46
|
| 404 |
+
},
|
| 405 |
+
{
|
| 406 |
+
"epoch": 2.315151515151515,
|
| 407 |
+
"grad_norm": 0.024150898680090904,
|
| 408 |
+
"learning_rate": 6.378186779084995e-05,
|
| 409 |
+
"loss": 0.0118,
|
| 410 |
+
"step": 47
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 2.3636363636363638,
|
| 414 |
+
"grad_norm": 0.019730910658836365,
|
| 415 |
+
"learning_rate": 6.209609477998338e-05,
|
| 416 |
+
"loss": 0.0121,
|
| 417 |
+
"step": 48
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 2.412121212121212,
|
| 421 |
+
"grad_norm": 0.02562836930155754,
|
| 422 |
+
"learning_rate": 6.0395584540887963e-05,
|
| 423 |
+
"loss": 0.0096,
|
| 424 |
+
"step": 49
|
| 425 |
+
},
|
| 426 |
+
{
|
| 427 |
+
"epoch": 2.4606060606060605,
|
| 428 |
+
"grad_norm": 0.01951598934829235,
|
| 429 |
+
"learning_rate": 5.868240888334653e-05,
|
| 430 |
+
"loss": 0.0117,
|
| 431 |
+
"step": 50
|
| 432 |
+
},
|
| 433 |
+
{
|
| 434 |
+
"epoch": 2.4606060606060605,
|
| 435 |
+
"eval_loss": 0.014072530902922153,
|
| 436 |
+
"eval_runtime": 10.3868,
|
| 437 |
+
"eval_samples_per_second": 4.814,
|
| 438 |
+
"eval_steps_per_second": 1.252,
|
| 439 |
+
"step": 50
|
| 440 |
+
},
|
| 441 |
+
{
|
| 442 |
+
"epoch": 2.509090909090909,
|
| 443 |
+
"grad_norm": 0.02022629976272583,
|
| 444 |
+
"learning_rate": 5.695865504800327e-05,
|
| 445 |
+
"loss": 0.0139,
|
| 446 |
+
"step": 51
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"epoch": 2.5575757575757576,
|
| 450 |
+
"grad_norm": 0.01750958524644375,
|
| 451 |
+
"learning_rate": 5.522642316338268e-05,
|
| 452 |
+
"loss": 0.0099,
|
| 453 |
+
"step": 52
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 2.606060606060606,
|
| 457 |
+
"grad_norm": 0.0212919432669878,
|
| 458 |
+
"learning_rate": 5.348782368720626e-05,
|
| 459 |
+
"loss": 0.013,
|
| 460 |
+
"step": 53
|
| 461 |
+
},
|
| 462 |
+
{
|
| 463 |
+
"epoch": 2.6545454545454543,
|
| 464 |
+
"grad_norm": 0.016065998002886772,
|
| 465 |
+
"learning_rate": 5.174497483512506e-05,
|
| 466 |
+
"loss": 0.0093,
|
| 467 |
+
"step": 54
|
| 468 |
+
},
|
| 469 |
+
{
|
| 470 |
+
"epoch": 2.703030303030303,
|
| 471 |
+
"grad_norm": 0.018324071541428566,
|
| 472 |
+
"learning_rate": 5e-05,
|
| 473 |
+
"loss": 0.015,
|
| 474 |
+
"step": 55
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 2.703030303030303,
|
| 478 |
+
"eval_loss": 0.013632840476930141,
|
| 479 |
+
"eval_runtime": 10.3292,
|
| 480 |
+
"eval_samples_per_second": 4.841,
|
| 481 |
+
"eval_steps_per_second": 1.259,
|
| 482 |
+
"step": 55
|
| 483 |
+
},
|
| 484 |
+
{
|
| 485 |
+
"epoch": 2.7515151515151515,
|
| 486 |
+
"grad_norm": 0.02191258780658245,
|
| 487 |
+
"learning_rate": 4.825502516487497e-05,
|
| 488 |
+
"loss": 0.0109,
|
| 489 |
+
"step": 56
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 2.8,
|
| 493 |
+
"grad_norm": 0.01748000457882881,
|
| 494 |
+
"learning_rate": 4.6512176312793736e-05,
|
| 495 |
+
"loss": 0.0104,
|
| 496 |
+
"step": 57
|
| 497 |
+
},
|
| 498 |
+
{
|
| 499 |
+
"epoch": 2.8484848484848486,
|
| 500 |
+
"grad_norm": 0.01487227063626051,
|
| 501 |
+
"learning_rate": 4.477357683661734e-05,
|
| 502 |
+
"loss": 0.0097,
|
| 503 |
+
"step": 58
|
| 504 |
+
},
|
| 505 |
+
{
|
| 506 |
+
"epoch": 2.896969696969697,
|
| 507 |
+
"grad_norm": 0.01992475800216198,
|
| 508 |
+
"learning_rate": 4.3041344951996746e-05,
|
| 509 |
+
"loss": 0.0108,
|
| 510 |
+
"step": 59
|
| 511 |
+
},
|
| 512 |
+
{
|
| 513 |
+
"epoch": 2.9454545454545453,
|
| 514 |
+
"grad_norm": 0.01630261354148388,
|
| 515 |
+
"learning_rate": 4.131759111665349e-05,
|
| 516 |
+
"loss": 0.0092,
|
| 517 |
+
"step": 60
|
| 518 |
+
},
|
| 519 |
+
{
|
| 520 |
+
"epoch": 2.9454545454545453,
|
| 521 |
+
"eval_loss": 0.013053460977971554,
|
| 522 |
+
"eval_runtime": 10.3658,
|
| 523 |
+
"eval_samples_per_second": 4.824,
|
| 524 |
+
"eval_steps_per_second": 1.254,
|
| 525 |
+
"step": 60
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"epoch": 3.012121212121212,
|
| 529 |
+
"grad_norm": 0.03835081681609154,
|
| 530 |
+
"learning_rate": 3.960441545911204e-05,
|
| 531 |
+
"loss": 0.0172,
|
| 532 |
+
"step": 61
|
| 533 |
+
},
|
| 534 |
+
{
|
| 535 |
+
"epoch": 3.0606060606060606,
|
| 536 |
+
"grad_norm": 0.017339400947093964,
|
| 537 |
+
"learning_rate": 3.790390522001662e-05,
|
| 538 |
+
"loss": 0.008,
|
| 539 |
+
"step": 62
|
| 540 |
+
},
|
| 541 |
+
{
|
| 542 |
+
"epoch": 3.109090909090909,
|
| 543 |
+
"grad_norm": 0.01646747626364231,
|
| 544 |
+
"learning_rate": 3.6218132209150045e-05,
|
| 545 |
+
"loss": 0.0121,
|
| 546 |
+
"step": 63
|
| 547 |
+
},
|
| 548 |
+
{
|
| 549 |
+
"epoch": 3.1575757575757577,
|
| 550 |
+
"grad_norm": 0.01738414168357849,
|
| 551 |
+
"learning_rate": 3.4549150281252636e-05,
|
| 552 |
+
"loss": 0.008,
|
| 553 |
+
"step": 64
|
| 554 |
+
},
|
| 555 |
+
{
|
| 556 |
+
"epoch": 3.206060606060606,
|
| 557 |
+
"grad_norm": 0.022966962307691574,
|
| 558 |
+
"learning_rate": 3.289899283371657e-05,
|
| 559 |
+
"loss": 0.008,
|
| 560 |
+
"step": 65
|
| 561 |
+
},
|
| 562 |
+
{
|
| 563 |
+
"epoch": 3.206060606060606,
|
| 564 |
+
"eval_loss": 0.012713730335235596,
|
| 565 |
+
"eval_runtime": 10.3449,
|
| 566 |
+
"eval_samples_per_second": 4.833,
|
| 567 |
+
"eval_steps_per_second": 1.257,
|
| 568 |
+
"step": 65
|
| 569 |
+
},
|
| 570 |
+
{
|
| 571 |
+
"epoch": 3.2545454545454544,
|
| 572 |
+
"grad_norm": 0.01976313628256321,
|
| 573 |
+
"learning_rate": 3.12696703292044e-05,
|
| 574 |
+
"loss": 0.0096,
|
| 575 |
+
"step": 66
|
| 576 |
+
},
|
| 577 |
+
{
|
| 578 |
+
"epoch": 3.303030303030303,
|
| 579 |
+
"grad_norm": 0.015671931207180023,
|
| 580 |
+
"learning_rate": 2.9663167846209998e-05,
|
| 581 |
+
"loss": 0.0071,
|
| 582 |
+
"step": 67
|
| 583 |
+
},
|
| 584 |
+
{
|
| 585 |
+
"epoch": 3.3515151515151516,
|
| 586 |
+
"grad_norm": 0.02184975892305374,
|
| 587 |
+
"learning_rate": 2.8081442660546125e-05,
|
| 588 |
+
"loss": 0.0092,
|
| 589 |
+
"step": 68
|
| 590 |
+
},
|
| 591 |
+
{
|
| 592 |
+
"epoch": 3.4,
|
| 593 |
+
"grad_norm": 0.021975932642817497,
|
| 594 |
+
"learning_rate": 2.6526421860705473e-05,
|
| 595 |
+
"loss": 0.009,
|
| 596 |
+
"step": 69
|
| 597 |
+
},
|
| 598 |
+
{
|
| 599 |
+
"epoch": 3.4484848484848483,
|
| 600 |
+
"grad_norm": 0.02743859961628914,
|
| 601 |
+
"learning_rate": 2.500000000000001e-05,
|
| 602 |
+
"loss": 0.0109,
|
| 603 |
+
"step": 70
|
| 604 |
+
},
|
| 605 |
+
{
|
| 606 |
+
"epoch": 3.4484848484848483,
|
| 607 |
+
"eval_loss": 0.012468294240534306,
|
| 608 |
+
"eval_runtime": 10.3407,
|
| 609 |
+
"eval_samples_per_second": 4.835,
|
| 610 |
+
"eval_steps_per_second": 1.257,
|
| 611 |
+
"step": 70
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 3.496969696969697,
|
| 615 |
+
"grad_norm": 0.02249360829591751,
|
| 616 |
+
"learning_rate": 2.350403678833976e-05,
|
| 617 |
+
"loss": 0.0123,
|
| 618 |
+
"step": 71
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 3.5454545454545454,
|
| 622 |
+
"grad_norm": 0.019340503960847855,
|
| 623 |
+
"learning_rate": 2.2040354826462668e-05,
|
| 624 |
+
"loss": 0.0072,
|
| 625 |
+
"step": 72
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 3.5939393939393938,
|
| 629 |
+
"grad_norm": 0.017731212079524994,
|
| 630 |
+
"learning_rate": 2.061073738537635e-05,
|
| 631 |
+
"loss": 0.009,
|
| 632 |
+
"step": 73
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 3.6424242424242426,
|
| 636 |
+
"grad_norm": 0.017661720514297485,
|
| 637 |
+
"learning_rate": 1.9216926233717085e-05,
|
| 638 |
+
"loss": 0.0078,
|
| 639 |
+
"step": 74
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 3.690909090909091,
|
| 643 |
+
"grad_norm": 0.01668357476592064,
|
| 644 |
+
"learning_rate": 1.7860619515673033e-05,
|
| 645 |
+
"loss": 0.0085,
|
| 646 |
+
"step": 75
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 3.690909090909091,
|
| 650 |
+
"eval_loss": 0.012197648175060749,
|
| 651 |
+
"eval_runtime": 10.3397,
|
| 652 |
+
"eval_samples_per_second": 4.836,
|
| 653 |
+
"eval_steps_per_second": 1.257,
|
| 654 |
+
"step": 75
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 3.7393939393939393,
|
| 658 |
+
"grad_norm": 0.019251663237810135,
|
| 659 |
+
"learning_rate": 1.6543469682057106e-05,
|
| 660 |
+
"loss": 0.0089,
|
| 661 |
+
"step": 76
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 3.787878787878788,
|
| 665 |
+
"grad_norm": 0.018358884379267693,
|
| 666 |
+
"learning_rate": 1.526708147705013e-05,
|
| 667 |
+
"loss": 0.0127,
|
| 668 |
+
"step": 77
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 3.8363636363636364,
|
| 672 |
+
"grad_norm": 0.018658000975847244,
|
| 673 |
+
"learning_rate": 1.4033009983067452e-05,
|
| 674 |
+
"loss": 0.0085,
|
| 675 |
+
"step": 78
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 3.8848484848484848,
|
| 679 |
+
"grad_norm": 0.01768352836370468,
|
| 680 |
+
"learning_rate": 1.2842758726130283e-05,
|
| 681 |
+
"loss": 0.0079,
|
| 682 |
+
"step": 79
|
| 683 |
+
},
|
| 684 |
+
{
|
| 685 |
+
"epoch": 3.9333333333333336,
|
| 686 |
+
"grad_norm": 0.017675764858722687,
|
| 687 |
+
"learning_rate": 1.1697777844051105e-05,
|
| 688 |
+
"loss": 0.0089,
|
| 689 |
+
"step": 80
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 3.9333333333333336,
|
| 693 |
+
"eval_loss": 0.011956109665334225,
|
| 694 |
+
"eval_runtime": 10.3374,
|
| 695 |
+
"eval_samples_per_second": 4.837,
|
| 696 |
+
"eval_steps_per_second": 1.258,
|
| 697 |
+
"step": 80
|
| 698 |
+
},
|
| 699 |
+
{
|
| 700 |
+
"epoch": 3.981818181818182,
|
| 701 |
+
"grad_norm": 0.04371407628059387,
|
| 702 |
+
"learning_rate": 1.0599462319663905e-05,
|
| 703 |
+
"loss": 0.013,
|
| 704 |
+
"step": 81
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 4.048484848484849,
|
| 708 |
+
"grad_norm": 0.01942707970738411,
|
| 709 |
+
"learning_rate": 9.549150281252633e-06,
|
| 710 |
+
"loss": 0.0092,
|
| 711 |
+
"step": 82
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 4.096969696969697,
|
| 715 |
+
"grad_norm": 0.014996436424553394,
|
| 716 |
+
"learning_rate": 8.548121372247918e-06,
|
| 717 |
+
"loss": 0.0064,
|
| 718 |
+
"step": 83
|
| 719 |
+
},
|
| 720 |
+
{
|
| 721 |
+
"epoch": 4.1454545454545455,
|
| 722 |
+
"grad_norm": 0.01869269274175167,
|
| 723 |
+
"learning_rate": 7.597595192178702e-06,
|
| 724 |
+
"loss": 0.0086,
|
| 725 |
+
"step": 84
|
| 726 |
+
},
|
| 727 |
+
{
|
| 728 |
+
"epoch": 4.193939393939394,
|
| 729 |
+
"grad_norm": 0.017618168145418167,
|
| 730 |
+
"learning_rate": 6.698729810778065e-06,
|
| 731 |
+
"loss": 0.0074,
|
| 732 |
+
"step": 85
|
| 733 |
+
},
|
| 734 |
+
{
|
| 735 |
+
"epoch": 4.193939393939394,
|
| 736 |
+
"eval_loss": 0.011830544099211693,
|
| 737 |
+
"eval_runtime": 10.3339,
|
| 738 |
+
"eval_samples_per_second": 4.838,
|
| 739 |
+
"eval_steps_per_second": 1.258,
|
| 740 |
+
"step": 85
|
| 741 |
+
},
|
| 742 |
+
{
|
| 743 |
+
"epoch": 4.242424242424242,
|
| 744 |
+
"grad_norm": 0.016551963984966278,
|
| 745 |
+
"learning_rate": 5.852620357053651e-06,
|
| 746 |
+
"loss": 0.009,
|
| 747 |
+
"step": 86
|
| 748 |
+
},
|
| 749 |
+
{
|
| 750 |
+
"epoch": 4.290909090909091,
|
| 751 |
+
"grad_norm": 0.01904563419520855,
|
| 752 |
+
"learning_rate": 5.060297685041659e-06,
|
| 753 |
+
"loss": 0.0074,
|
| 754 |
+
"step": 87
|
| 755 |
+
},
|
| 756 |
+
{
|
| 757 |
+
"epoch": 4.33939393939394,
|
| 758 |
+
"grad_norm": 0.02098240703344345,
|
| 759 |
+
"learning_rate": 4.322727117869951e-06,
|
| 760 |
+
"loss": 0.0094,
|
| 761 |
+
"step": 88
|
| 762 |
+
},
|
| 763 |
+
{
|
| 764 |
+
"epoch": 4.387878787878788,
|
| 765 |
+
"grad_norm": 0.015075408853590488,
|
| 766 |
+
"learning_rate": 3.6408072716606346e-06,
|
| 767 |
+
"loss": 0.0084,
|
| 768 |
+
"step": 89
|
| 769 |
+
},
|
| 770 |
+
{
|
| 771 |
+
"epoch": 4.4363636363636365,
|
| 772 |
+
"grad_norm": 0.016622379422187805,
|
| 773 |
+
"learning_rate": 3.0153689607045845e-06,
|
| 774 |
+
"loss": 0.0074,
|
| 775 |
+
"step": 90
|
| 776 |
+
},
|
| 777 |
+
{
|
| 778 |
+
"epoch": 4.4363636363636365,
|
| 779 |
+
"eval_loss": 0.011814383789896965,
|
| 780 |
+
"eval_runtime": 10.356,
|
| 781 |
+
"eval_samples_per_second": 4.828,
|
| 782 |
+
"eval_steps_per_second": 1.255,
|
| 783 |
+
"step": 90
|
| 784 |
+
},
|
| 785 |
+
{
|
| 786 |
+
"epoch": 4.484848484848484,
|
| 787 |
+
"grad_norm": 0.017493437975645065,
|
| 788 |
+
"learning_rate": 2.4471741852423237e-06,
|
| 789 |
+
"loss": 0.0087,
|
| 790 |
+
"step": 91
|
| 791 |
+
},
|
| 792 |
+
{
|
| 793 |
+
"epoch": 4.533333333333333,
|
| 794 |
+
"grad_norm": 0.01581619866192341,
|
| 795 |
+
"learning_rate": 1.9369152030840556e-06,
|
| 796 |
+
"loss": 0.0073,
|
| 797 |
+
"step": 92
|
| 798 |
+
},
|
| 799 |
+
{
|
| 800 |
+
"epoch": 4.581818181818182,
|
| 801 |
+
"grad_norm": 0.020205620676279068,
|
| 802 |
+
"learning_rate": 1.4852136862001764e-06,
|
| 803 |
+
"loss": 0.0075,
|
| 804 |
+
"step": 93
|
| 805 |
+
},
|
| 806 |
+
{
|
| 807 |
+
"epoch": 4.63030303030303,
|
| 808 |
+
"grad_norm": 0.016090713441371918,
|
| 809 |
+
"learning_rate": 1.0926199633097157e-06,
|
| 810 |
+
"loss": 0.0071,
|
| 811 |
+
"step": 94
|
| 812 |
+
},
|
| 813 |
+
{
|
| 814 |
+
"epoch": 4.678787878787879,
|
| 815 |
+
"grad_norm": 0.014329814352095127,
|
| 816 |
+
"learning_rate": 7.596123493895991e-07,
|
| 817 |
+
"loss": 0.0066,
|
| 818 |
+
"step": 95
|
| 819 |
+
},
|
| 820 |
+
{
|
| 821 |
+
"epoch": 4.678787878787879,
|
| 822 |
+
"eval_loss": 0.011838787235319614,
|
| 823 |
+
"eval_runtime": 10.3353,
|
| 824 |
+
"eval_samples_per_second": 4.838,
|
| 825 |
+
"eval_steps_per_second": 1.258,
|
| 826 |
+
"step": 95
|
| 827 |
+
},
|
| 828 |
+
{
|
| 829 |
+
"epoch": 4.7272727272727275,
|
| 830 |
+
"grad_norm": 0.015449507161974907,
|
| 831 |
+
"learning_rate": 4.865965629214819e-07,
|
| 832 |
+
"loss": 0.0063,
|
| 833 |
+
"step": 96
|
| 834 |
+
},
|
| 835 |
+
{
|
| 836 |
+
"epoch": 4.775757575757575,
|
| 837 |
+
"grad_norm": 0.016315339133143425,
|
| 838 |
+
"learning_rate": 2.7390523158633554e-07,
|
| 839 |
+
"loss": 0.0076,
|
| 840 |
+
"step": 97
|
| 841 |
+
},
|
| 842 |
+
{
|
| 843 |
+
"epoch": 4.824242424242424,
|
| 844 |
+
"grad_norm": 0.018415048718452454,
|
| 845 |
+
"learning_rate": 1.2179748700879012e-07,
|
| 846 |
+
"loss": 0.0103,
|
| 847 |
+
"step": 98
|
| 848 |
+
},
|
| 849 |
+
{
|
| 850 |
+
"epoch": 4.872727272727273,
|
| 851 |
+
"grad_norm": 0.014639717526733875,
|
| 852 |
+
"learning_rate": 3.04586490452119e-08,
|
| 853 |
+
"loss": 0.0057,
|
| 854 |
+
"step": 99
|
| 855 |
+
},
|
| 856 |
+
{
|
| 857 |
+
"epoch": 4.921212121212121,
|
| 858 |
+
"grad_norm": 0.018388710916042328,
|
| 859 |
+
"learning_rate": 0.0,
|
| 860 |
+
"loss": 0.0065,
|
| 861 |
+
"step": 100
|
| 862 |
+
},
|
| 863 |
+
{
|
| 864 |
+
"epoch": 4.921212121212121,
|
| 865 |
+
"eval_loss": 0.011823242530226707,
|
| 866 |
+
"eval_runtime": 10.3329,
|
| 867 |
+
"eval_samples_per_second": 4.839,
|
| 868 |
+
"eval_steps_per_second": 1.258,
|
| 869 |
+
"step": 100
|
| 870 |
+
}
|
| 871 |
+
],
|
| 872 |
+
"logging_steps": 1,
|
| 873 |
+
"max_steps": 100,
|
| 874 |
+
"num_input_tokens_seen": 0,
|
| 875 |
+
"num_train_epochs": 5,
|
| 876 |
+
"save_steps": 50,
|
| 877 |
+
"stateful_callbacks": {
|
| 878 |
+
"TrainerControl": {
|
| 879 |
+
"args": {
|
| 880 |
+
"should_epoch_stop": false,
|
| 881 |
+
"should_evaluate": false,
|
| 882 |
+
"should_log": false,
|
| 883 |
+
"should_save": true,
|
| 884 |
+
"should_training_stop": true
|
| 885 |
+
},
|
| 886 |
+
"attributes": {}
|
| 887 |
+
}
|
| 888 |
+
},
|
| 889 |
+
"total_flos": 2.442632501894185e+17,
|
| 890 |
+
"train_batch_size": 4,
|
| 891 |
+
"trial_name": null,
|
| 892 |
+
"trial_params": null
|
| 893 |
+
}
|
checkpoint-100/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f7621cfdd62b7b103ef94ad34fb8774ce9010f461047b0d903b32f12aae5046f
|
| 3 |
+
size 5432
|
eval_results.json
CHANGED
|
@@ -1,7 +1,7 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch": 4.
|
| 3 |
-
"eval_loss": 0.
|
| 4 |
-
"eval_runtime":
|
| 5 |
-
"eval_samples_per_second":
|
| 6 |
-
"eval_steps_per_second": 1.
|
| 7 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 4.921212121212121,
|
| 3 |
+
"eval_loss": 0.011823245324194431,
|
| 4 |
+
"eval_runtime": 10.3534,
|
| 5 |
+
"eval_samples_per_second": 4.829,
|
| 6 |
+
"eval_steps_per_second": 1.256
|
| 7 |
}
|
train_results.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch": 4.
|
| 3 |
-
"total_flos":
|
| 4 |
-
"train_loss": 0.
|
| 5 |
-
"train_runtime":
|
| 6 |
-
"train_samples_per_second": 1.
|
| 7 |
-
"train_steps_per_second": 0.
|
| 8 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 4.921212121212121,
|
| 3 |
+
"total_flos": 2.442632501894185e+17,
|
| 4 |
+
"train_loss": 0.016519791511818767,
|
| 5 |
+
"train_runtime": 2009.2463,
|
| 6 |
+
"train_samples_per_second": 1.637,
|
| 7 |
+
"train_steps_per_second": 0.05
|
| 8 |
}
|
trainer_log.jsonl
CHANGED
|
@@ -1,298 +1,121 @@
|
|
| 1 |
-
{"current_steps":
|
| 2 |
-
{"current_steps":
|
| 3 |
-
{"current_steps":
|
| 4 |
-
{"current_steps":
|
| 5 |
-
{"current_steps":
|
| 6 |
-
{"current_steps":
|
| 7 |
-
{"current_steps":
|
| 8 |
-
{"current_steps":
|
| 9 |
-
{"current_steps":
|
| 10 |
-
{"current_steps":
|
| 11 |
-
{"current_steps":
|
| 12 |
-
{"current_steps":
|
| 13 |
-
{"current_steps":
|
| 14 |
-
{"current_steps":
|
| 15 |
-
{"current_steps":
|
| 16 |
-
{"current_steps":
|
| 17 |
-
{"current_steps":
|
| 18 |
-
{"current_steps":
|
| 19 |
-
{"current_steps":
|
| 20 |
-
{"current_steps":
|
| 21 |
-
{"current_steps":
|
| 22 |
-
{"current_steps":
|
| 23 |
-
{"current_steps":
|
| 24 |
-
{"current_steps":
|
| 25 |
-
{"current_steps":
|
| 26 |
-
{"current_steps":
|
| 27 |
-
{"current_steps":
|
| 28 |
-
{"current_steps":
|
| 29 |
-
{"current_steps":
|
| 30 |
-
{"current_steps":
|
| 31 |
-
{"current_steps":
|
| 32 |
-
{"current_steps":
|
| 33 |
-
{"current_steps":
|
| 34 |
-
{"current_steps":
|
| 35 |
-
{"current_steps":
|
| 36 |
-
{"current_steps":
|
| 37 |
-
{"current_steps":
|
| 38 |
-
{"current_steps":
|
| 39 |
-
{"current_steps":
|
| 40 |
-
{"current_steps":
|
| 41 |
-
{"current_steps":
|
| 42 |
-
{"current_steps":
|
| 43 |
-
{"current_steps":
|
| 44 |
-
{"current_steps":
|
| 45 |
-
{"current_steps":
|
| 46 |
-
{"current_steps":
|
| 47 |
-
{"current_steps":
|
| 48 |
-
{"current_steps":
|
| 49 |
-
{"current_steps":
|
| 50 |
-
{"current_steps":
|
| 51 |
-
{"current_steps":
|
| 52 |
-
{"current_steps":
|
| 53 |
-
{"current_steps":
|
| 54 |
-
{"current_steps":
|
| 55 |
-
{"current_steps":
|
| 56 |
-
{"current_steps":
|
| 57 |
-
{"current_steps":
|
| 58 |
-
{"current_steps":
|
| 59 |
-
{"current_steps":
|
| 60 |
-
{"current_steps":
|
| 61 |
-
{"current_steps":
|
| 62 |
-
{"current_steps":
|
| 63 |
-
{"current_steps":
|
| 64 |
-
{"current_steps":
|
| 65 |
-
{"current_steps":
|
| 66 |
-
{"current_steps":
|
| 67 |
-
{"current_steps":
|
| 68 |
-
{"current_steps":
|
| 69 |
-
{"current_steps":
|
| 70 |
-
{"current_steps":
|
| 71 |
-
{"current_steps":
|
| 72 |
-
{"current_steps":
|
| 73 |
-
{"current_steps":
|
| 74 |
-
{"current_steps":
|
| 75 |
-
{"current_steps":
|
| 76 |
-
{"current_steps":
|
| 77 |
-
{"current_steps":
|
| 78 |
-
{"current_steps":
|
| 79 |
-
{"current_steps":
|
| 80 |
-
{"current_steps":
|
| 81 |
-
{"current_steps":
|
| 82 |
-
{"current_steps":
|
| 83 |
-
{"current_steps":
|
| 84 |
-
{"current_steps":
|
| 85 |
-
{"current_steps":
|
| 86 |
-
{"current_steps":
|
| 87 |
-
{"current_steps":
|
| 88 |
-
{"current_steps":
|
| 89 |
-
{"current_steps":
|
| 90 |
-
{"current_steps":
|
| 91 |
-
{"current_steps":
|
| 92 |
-
{"current_steps":
|
| 93 |
-
{"current_steps":
|
| 94 |
-
{"current_steps":
|
| 95 |
-
{"current_steps":
|
| 96 |
-
{"current_steps":
|
| 97 |
-
{"current_steps":
|
| 98 |
-
{"current_steps":
|
| 99 |
-
{"current_steps":
|
| 100 |
-
{"current_steps":
|
| 101 |
-
{"current_steps":
|
| 102 |
-
{"current_steps":
|
| 103 |
-
{"current_steps":
|
| 104 |
-
{"current_steps":
|
| 105 |
-
{"current_steps":
|
| 106 |
-
{"current_steps":
|
| 107 |
-
{"current_steps":
|
| 108 |
-
{"current_steps":
|
| 109 |
-
{"current_steps":
|
| 110 |
-
{"current_steps":
|
| 111 |
-
{"current_steps": 93, "total_steps":
|
| 112 |
-
{"current_steps":
|
| 113 |
-
{"current_steps":
|
| 114 |
-
{"current_steps":
|
| 115 |
-
{"current_steps":
|
| 116 |
-
{"current_steps":
|
| 117 |
-
{"current_steps":
|
| 118 |
-
{"current_steps":
|
| 119 |
-
{"current_steps":
|
| 120 |
-
{"current_steps":
|
| 121 |
-
{"current_steps":
|
| 122 |
-
{"current_steps": 49, "total_steps": 145, "loss": 0.0125, "lr": 8.405079293933986e-05, "epoch": 1.6752136752136753, "percentage": 33.79, "elapsed_time": "0:30:32", "remaining_time": "0:59:49"}
|
| 123 |
-
{"current_steps": 98, "total_steps": 145, "loss": 0.007, "lr": 2.8929944611373554e-05, "epoch": 3.3504273504273505, "percentage": 67.59, "elapsed_time": "0:44:00", "remaining_time": "0:21:06"}
|
| 124 |
-
{"current_steps": 50, "total_steps": 145, "loss": 0.0122, "lr": 8.315613291203976e-05, "epoch": 1.7094017094017095, "percentage": 34.48, "elapsed_time": "0:31:04", "remaining_time": "0:59:02"}
|
| 125 |
-
{"current_steps": 99, "total_steps": 145, "loss": 0.0069, "lr": 2.784042272003794e-05, "epoch": 3.3846153846153846, "percentage": 68.28, "elapsed_time": "0:44:33", "remaining_time": "0:20:42"}
|
| 126 |
-
{"current_steps": 50, "total_steps": 145, "eval_loss": 0.013878260739147663, "epoch": 1.7094017094017095, "percentage": 34.48, "elapsed_time": "0:31:24", "remaining_time": "0:59:41"}
|
| 127 |
-
{"current_steps": 100, "total_steps": 145, "loss": 0.0067, "lr": 2.6763841397811573e-05, "epoch": 3.4188034188034186, "percentage": 68.97, "elapsed_time": "0:44:52", "remaining_time": "0:20:11"}
|
| 128 |
-
{"current_steps": 100, "total_steps": 145, "eval_loss": 0.011121884919703007, "epoch": 3.4188034188034186, "percentage": 68.97, "elapsed_time": "0:45:06", "remaining_time": "0:20:18"}
|
| 129 |
-
{"current_steps": 51, "total_steps": 145, "loss": 0.0136, "lr": 8.224211063680853e-05, "epoch": 1.7435897435897436, "percentage": 35.17, "elapsed_time": "0:32:06", "remaining_time": "0:59:11"}
|
| 130 |
-
{"current_steps": 101, "total_steps": 145, "loss": 0.0089, "lr": 2.57008293378697e-05, "epoch": 3.452991452991453, "percentage": 69.66, "elapsed_time": "0:45:44", "remaining_time": "0:19:55"}
|
| 131 |
-
{"current_steps": 52, "total_steps": 145, "loss": 0.0125, "lr": 8.130925987691569e-05, "epoch": 1.7777777777777777, "percentage": 35.86, "elapsed_time": "0:32:38", "remaining_time": "0:58:23"}
|
| 132 |
-
{"current_steps": 102, "total_steps": 145, "loss": 0.0064, "lr": 2.4652007309320498e-05, "epoch": 3.4871794871794872, "percentage": 70.34, "elapsed_time": "0:46:14", "remaining_time": "0:19:29"}
|
| 133 |
-
{"current_steps": 53, "total_steps": 145, "loss": 0.0105, "lr": 8.035812539093557e-05, "epoch": 1.811965811965812, "percentage": 36.55, "elapsed_time": "0:33:09", "remaining_time": "0:57:32"}
|
| 134 |
-
{"current_steps": 103, "total_steps": 145, "loss": 0.0074, "lr": 2.361798779469336e-05, "epoch": 3.5213675213675213, "percentage": 71.03, "elapsed_time": "0:46:45", "remaining_time": "0:19:03"}
|
| 135 |
-
{"current_steps": 54, "total_steps": 145, "loss": 0.0122, "lr": 7.938926261462366e-05, "epoch": 1.8461538461538463, "percentage": 37.24, "elapsed_time": "0:33:42", "remaining_time": "0:56:47"}
|
| 136 |
-
{"current_steps": 104, "total_steps": 145, "loss": 0.0062, "lr": 2.259937463226651e-05, "epoch": 3.5555555555555554, "percentage": 71.72, "elapsed_time": "0:47:14", "remaining_time": "0:18:37"}
|
| 137 |
-
{"current_steps": 55, "total_steps": 145, "loss": 0.0136, "lr": 7.840323733655778e-05, "epoch": 1.8803418803418803, "percentage": 37.93, "elapsed_time": "0:34:13", "remaining_time": "0:56:00"}
|
| 138 |
-
{"current_steps": 105, "total_steps": 145, "loss": 0.0071, "lr": 2.1596762663442218e-05, "epoch": 3.58974358974359, "percentage": 72.41, "elapsed_time": "0:47:45", "remaining_time": "0:18:11"}
|
| 139 |
-
{"current_steps": 55, "total_steps": 145, "eval_loss": 0.013426054269075394, "epoch": 1.8803418803418803, "percentage": 37.93, "elapsed_time": "0:34:34", "remaining_time": "0:56:34"}
|
| 140 |
-
{"current_steps": 105, "total_steps": 145, "eval_loss": 0.010777024552226067, "epoch": 3.58974358974359, "percentage": 72.41, "elapsed_time": "0:48:04", "remaining_time": "0:18:18"}
|
| 141 |
-
{"current_steps": 56, "total_steps": 145, "loss": 0.0121, "lr": 7.740062536773352e-05, "epoch": 1.9145299145299144, "percentage": 38.62, "elapsed_time": "0:35:07", "remaining_time": "0:55:50"}
|
| 142 |
-
{"current_steps": 106, "total_steps": 145, "loss": 0.0079, "lr": 2.061073738537635e-05, "epoch": 3.623931623931624, "percentage": 73.1, "elapsed_time": "0:48:33", "remaining_time": "0:17:52"}
|
| 143 |
-
{"current_steps": 57, "total_steps": 145, "loss": 0.0124, "lr": 7.638201220530665e-05, "epoch": 1.9487179487179487, "percentage": 39.31, "elapsed_time": "0:35:38", "remaining_time": "0:55:02"}
|
| 144 |
-
{"current_steps": 107, "total_steps": 145, "loss": 0.0078, "lr": 1.9641874609064443e-05, "epoch": 3.658119658119658, "percentage": 73.79, "elapsed_time": "0:49:03", "remaining_time": "0:17:25"}
|
| 145 |
-
{"current_steps": 58, "total_steps": 145, "loss": 0.0125, "lr": 7.534799269067953e-05, "epoch": 1.982905982905983, "percentage": 40.0, "elapsed_time": "0:36:10", "remaining_time": "0:54:15"}
|
| 146 |
-
{"current_steps": 108, "total_steps": 145, "loss": 0.007, "lr": 1.8690740123084316e-05, "epoch": 3.6923076923076925, "percentage": 74.48, "elapsed_time": "0:49:33", "remaining_time": "0:16:58"}
|
| 147 |
-
{"current_steps": 59, "total_steps": 145, "loss": 0.0197, "lr": 7.42991706621303e-05, "epoch": 2.017094017094017, "percentage": 40.69, "elapsed_time": "0:36:40", "remaining_time": "0:53:27"}
|
| 148 |
-
{"current_steps": 109, "total_steps": 145, "loss": 0.0066, "lr": 1.7757889363191483e-05, "epoch": 3.7264957264957266, "percentage": 75.17, "elapsed_time": "0:50:05", "remaining_time": "0:16:32"}
|
| 149 |
-
{"current_steps": 60, "total_steps": 145, "loss": 0.011, "lr": 7.323615860218843e-05, "epoch": 2.051282051282051, "percentage": 41.38, "elapsed_time": "0:37:11", "remaining_time": "0:52:41"}
|
| 150 |
-
{"current_steps": 110, "total_steps": 145, "loss": 0.0061, "lr": 1.684386708796025e-05, "epoch": 3.7606837606837606, "percentage": 75.86, "elapsed_time": "0:50:34", "remaining_time": "0:16:05"}
|
| 151 |
-
{"current_steps": 60, "total_steps": 145, "eval_loss": 0.01329517550766468, "epoch": 2.051282051282051, "percentage": 41.38, "elapsed_time": "0:37:32", "remaining_time": "0:53:11"}
|
| 152 |
-
{"current_steps": 110, "total_steps": 145, "eval_loss": 0.010564588941633701, "epoch": 3.7606837606837606, "percentage": 75.86, "elapsed_time": "0:50:53", "remaining_time": "0:16:11"}
|
| 153 |
-
{"current_steps": 61, "total_steps": 145, "loss": 0.0107, "lr": 7.215957727996207e-05, "epoch": 2.0854700854700856, "percentage": 42.07, "elapsed_time": "0:38:03", "remaining_time": "0:52:24"}
|
| 154 |
-
{"current_steps": 111, "total_steps": 145, "loss": 0.0062, "lr": 1.5949207060660138e-05, "epoch": 3.7948717948717947, "percentage": 76.55, "elapsed_time": "0:51:23", "remaining_time": "0:15:44"}
|
| 155 |
-
{"current_steps": 62, "total_steps": 145, "loss": 0.0107, "lr": 7.107005538862646e-05, "epoch": 2.1196581196581197, "percentage": 42.76, "elapsed_time": "0:38:37", "remaining_time": "0:51:42"}
|
| 156 |
-
{"current_steps": 112, "total_steps": 145, "loss": 0.0074, "lr": 1.5074431737553157e-05, "epoch": 3.8290598290598292, "percentage": 77.24, "elapsed_time": "0:51:55", "remaining_time": "0:15:18"}
|
| 157 |
-
{"current_steps": 63, "total_steps": 145, "loss": 0.0115, "lr": 6.996822917828477e-05, "epoch": 2.1538461538461537, "percentage": 43.45, "elapsed_time": "0:39:08", "remaining_time": "0:50:57"}
|
| 158 |
-
{"current_steps": 113, "total_steps": 145, "loss": 0.0094, "lr": 1.422005196279395e-05, "epoch": 3.8632478632478633, "percentage": 77.93, "elapsed_time": "0:52:27", "remaining_time": "0:14:51"}
|
| 159 |
-
{"current_steps": 114, "total_steps": 145, "loss": 0.0071, "lr": 1.338656667011134e-05, "epoch": 3.8974358974358974, "percentage": 78.62, "elapsed_time": "0:52:57", "remaining_time": "0:14:24"}
|
| 160 |
-
{"current_steps": 64, "total_steps": 145, "loss": 0.0105, "lr": 6.885474208441603e-05, "epoch": 2.1880341880341883, "percentage": 44.14, "elapsed_time": "0:39:40", "remaining_time": "0:50:13"}
|
| 161 |
-
{"current_steps": 115, "total_steps": 145, "loss": 0.0064, "lr": 1.257446259144494e-05, "epoch": 3.931623931623932, "percentage": 79.31, "elapsed_time": "0:53:30", "remaining_time": "0:13:57"}
|
| 162 |
-
{"current_steps": 65, "total_steps": 145, "loss": 0.0098, "lr": 6.773024435212678e-05, "epoch": 2.2222222222222223, "percentage": 44.83, "elapsed_time": "0:40:15", "remaining_time": "0:49:33"}
|
| 163 |
-
{"current_steps": 115, "total_steps": 145, "eval_loss": 0.010578772984445095, "epoch": 3.931623931623932, "percentage": 79.31, "elapsed_time": "0:53:49", "remaining_time": "0:14:02"}
|
| 164 |
-
{"current_steps": 65, "total_steps": 145, "eval_loss": 0.012847676873207092, "epoch": 2.2222222222222223, "percentage": 44.83, "elapsed_time": "0:40:36", "remaining_time": "0:49:58"}
|
| 165 |
-
{"current_steps": 116, "total_steps": 145, "loss": 0.0059, "lr": 1.178421397270758e-05, "epoch": 3.965811965811966, "percentage": 80.0, "elapsed_time": "0:54:18", "remaining_time": "0:13:34"}
|
| 166 |
-
{"current_steps": 66, "total_steps": 145, "loss": 0.0105, "lr": 6.659539265642643e-05, "epoch": 2.2564102564102564, "percentage": 45.52, "elapsed_time": "0:41:11", "remaining_time": "0:49:17"}
|
| 167 |
-
{"current_steps": 117, "total_steps": 145, "loss": 0.0124, "lr": 1.1016282296838887e-05, "epoch": 4.0, "percentage": 80.69, "elapsed_time": "0:54:46", "remaining_time": "0:13:06"}
|
| 168 |
-
{"current_steps": 67, "total_steps": 145, "loss": 0.0083, "lr": 6.545084971874738e-05, "epoch": 2.2905982905982905, "percentage": 46.21, "elapsed_time": "0:41:45", "remaining_time": "0:48:36"}
|
| 169 |
-
{"current_steps": 118, "total_steps": 145, "loss": 0.005, "lr": 1.0271116014312293e-05, "epoch": 4.034188034188034, "percentage": 81.38, "elapsed_time": "0:55:18", "remaining_time": "0:12:39"}
|
| 170 |
-
{"current_steps": 68, "total_steps": 145, "loss": 0.0116, "lr": 6.429728391993446e-05, "epoch": 2.324786324786325, "percentage": 46.9, "elapsed_time": "0:42:17", "remaining_time": "0:47:53"}
|
| 171 |
-
{"current_steps": 119, "total_steps": 145, "loss": 0.0055, "lr": 9.549150281252633e-06, "epoch": 4.068376068376068, "percentage": 82.07, "elapsed_time": "0:55:50", "remaining_time": "0:12:11"}
|
| 172 |
-
{"current_steps": 69, "total_steps": 145, "loss": 0.0091, "lr": 6.313536890992935e-05, "epoch": 2.358974358974359, "percentage": 47.59, "elapsed_time": "0:42:50", "remaining_time": "0:47:11"}
|
| 173 |
-
{"current_steps": 120, "total_steps": 145, "loss": 0.0077, "lr": 8.850806705317183e-06, "epoch": 4.102564102564102, "percentage": 82.76, "elapsed_time": "0:56:20", "remaining_time": "0:11:44"}
|
| 174 |
-
{"current_steps": 120, "total_steps": 145, "eval_loss": 0.010579032823443413, "epoch": 4.102564102564102, "percentage": 82.76, "elapsed_time": "0:56:39", "remaining_time": "0:11:48"}
|
| 175 |
-
{"current_steps": 70, "total_steps": 145, "loss": 0.011, "lr": 6.19657832143779e-05, "epoch": 2.393162393162393, "percentage": 48.28, "elapsed_time": "0:43:25", "remaining_time": "0:46:31"}
|
| 176 |
-
{"current_steps": 70, "total_steps": 145, "eval_loss": 0.012613310478627682, "epoch": 2.393162393162393, "percentage": 48.28, "elapsed_time": "0:43:45", "remaining_time": "0:46:53"}
|
| 177 |
-
{"current_steps": 121, "total_steps": 145, "loss": 0.0068, "lr": 8.176493099488663e-06, "epoch": 4.136752136752137, "percentage": 83.45, "elapsed_time": "0:57:13", "remaining_time": "0:11:21"}
|
| 178 |
-
{"current_steps": 71, "total_steps": 145, "loss": 0.0105, "lr": 6.078920983839031e-05, "epoch": 2.427350427350427, "percentage": 48.97, "elapsed_time": "0:44:19", "remaining_time": "0:46:12"}
|
| 179 |
-
{"current_steps": 122, "total_steps": 145, "loss": 0.0063, "lr": 7.526603243923957e-06, "epoch": 4.170940170940171, "percentage": 84.14, "elapsed_time": "0:57:46", "remaining_time": "0:10:53"}
|
| 180 |
-
{"current_steps": 72, "total_steps": 145, "loss": 0.0105, "lr": 5.960633586768543e-05, "epoch": 2.4615384615384617, "percentage": 49.66, "elapsed_time": "0:44:52", "remaining_time": "0:45:30"}
|
| 181 |
-
{"current_steps": 123, "total_steps": 145, "loss": 0.006, "lr": 6.901516655997536e-06, "epoch": 4.205128205128205, "percentage": 84.83, "elapsed_time": "0:58:19", "remaining_time": "0:10:25"}
|
| 182 |
-
{"current_steps": 73, "total_steps": 145, "loss": 0.0106, "lr": 5.841785206735192e-05, "epoch": 2.4957264957264957, "percentage": 50.34, "elapsed_time": "0:45:25", "remaining_time": "0:44:48"}
|
| 183 |
-
{"current_steps": 124, "total_steps": 145, "loss": 0.0058, "lr": 6.301598368674105e-06, "epoch": 4.239316239316239, "percentage": 85.52, "elapsed_time": "0:58:48", "remaining_time": "0:09:57"}
|
| 184 |
-
{"current_steps": 74, "total_steps": 145, "loss": 0.0108, "lr": 5.7224452478461064e-05, "epoch": 2.52991452991453, "percentage": 51.03, "elapsed_time": "0:45:55", "remaining_time": "0:44:03"}
|
| 185 |
-
{"current_steps": 125, "total_steps": 145, "loss": 0.0056, "lr": 5.727198717339511e-06, "epoch": 4.273504273504273, "percentage": 86.21, "elapsed_time": "0:59:21", "remaining_time": "0:09:29"}
|
| 186 |
-
{"current_steps": 125, "total_steps": 145, "eval_loss": 0.010702351108193398, "epoch": 4.273504273504273, "percentage": 86.21, "elapsed_time": "0:59:40", "remaining_time": "0:09:32"}
|
| 187 |
-
{"current_steps": 75, "total_steps": 145, "loss": 0.0087, "lr": 5.602683401276615e-05, "epoch": 2.564102564102564, "percentage": 51.72, "elapsed_time": "0:46:27", "remaining_time": "0:43:21"}
|
| 188 |
-
{"current_steps": 75, "total_steps": 145, "eval_loss": 0.012018020264804363, "epoch": 2.564102564102564, "percentage": 51.72, "elapsed_time": "0:46:47", "remaining_time": "0:43:40"}
|
| 189 |
-
{"current_steps": 126, "total_steps": 145, "loss": 0.0051, "lr": 5.178653135214812e-06, "epoch": 4.3076923076923075, "percentage": 86.9, "elapsed_time": "1:00:11", "remaining_time": "0:09:04"}
|
| 190 |
-
{"current_steps": 76, "total_steps": 145, "loss": 0.0085, "lr": 5.482569604572576e-05, "epoch": 2.5982905982905984, "percentage": 52.41, "elapsed_time": "0:47:21", "remaining_time": "0:42:59"}
|
| 191 |
-
{"current_steps": 127, "total_steps": 145, "loss": 0.0055, "lr": 4.65628195747273e-06, "epoch": 4.3418803418803416, "percentage": 87.59, "elapsed_time": "1:00:42", "remaining_time": "0:08:36"}
|
| 192 |
-
{"current_steps": 77, "total_steps": 145, "loss": 0.0111, "lr": 5.3621740008088126e-05, "epoch": 2.6324786324786325, "percentage": 53.1, "elapsed_time": "0:47:56", "remaining_time": "0:42:20"}
|
| 193 |
-
{"current_steps": 128, "total_steps": 145, "loss": 0.005, "lr": 4.16039023417088e-06, "epoch": 4.3760683760683765, "percentage": 88.28, "elapsed_time": "1:01:14", "remaining_time": "0:08:08"}
|
| 194 |
-
{"current_steps": 129, "total_steps": 145, "loss": 0.0052, "lr": 3.691267552111183e-06, "epoch": 4.410256410256411, "percentage": 88.97, "elapsed_time": "1:01:47", "remaining_time": "0:07:39"}
|
| 195 |
-
{"current_steps": 78, "total_steps": 145, "loss": 0.0081, "lr": 5.2415668976275355e-05, "epoch": 2.6666666666666665, "percentage": 53.79, "elapsed_time": "0:48:29", "remaining_time": "0:41:39"}
|
| 196 |
-
{"current_steps": 130, "total_steps": 145, "loss": 0.0069, "lr": 3.249187865729264e-06, "epoch": 4.444444444444445, "percentage": 89.66, "elapsed_time": "1:02:18", "remaining_time": "0:07:11"}
|
| 197 |
-
{"current_steps": 79, "total_steps": 145, "loss": 0.0112, "lr": 5.1208187261806615e-05, "epoch": 2.700854700854701, "percentage": 54.48, "elapsed_time": "0:49:01", "remaining_time": "0:40:57"}
|
| 198 |
-
{"current_steps": 130, "total_steps": 145, "eval_loss": 0.010735642164945602, "epoch": 4.444444444444445, "percentage": 89.66, "elapsed_time": "1:02:37", "remaining_time": "0:07:13"}
|
| 199 |
-
{"current_steps": 80, "total_steps": 145, "loss": 0.0086, "lr": 5e-05, "epoch": 2.735042735042735, "percentage": 55.17, "elapsed_time": "0:49:33", "remaining_time": "0:40:16"}
|
| 200 |
-
{"current_steps": 131, "total_steps": 145, "loss": 0.0051, "lr": 2.8344093371128424e-06, "epoch": 4.478632478632479, "percentage": 90.34, "elapsed_time": "1:03:10", "remaining_time": "0:06:45"}
|
| 201 |
-
{"current_steps": 80, "total_steps": 145, "eval_loss": 0.011721721850335598, "epoch": 2.735042735042735, "percentage": 55.17, "elapsed_time": "0:49:53", "remaining_time": "0:40:32"}
|
| 202 |
-
{"current_steps": 132, "total_steps": 145, "loss": 0.0047, "lr": 2.4471741852423237e-06, "epoch": 4.512820512820513, "percentage": 91.03, "elapsed_time": "1:03:43", "remaining_time": "0:06:16"}
|
| 203 |
-
{"current_steps": 81, "total_steps": 145, "loss": 0.009, "lr": 4.87918127381934e-05, "epoch": 2.769230769230769, "percentage": 55.86, "elapsed_time": "0:50:26", "remaining_time": "0:39:51"}
|
| 204 |
-
{"current_steps": 133, "total_steps": 145, "loss": 0.0045, "lr": 2.087708544541689e-06, "epoch": 4.547008547008547, "percentage": 91.72, "elapsed_time": "1:04:13", "remaining_time": "0:05:47"}
|
| 205 |
-
{"current_steps": 82, "total_steps": 145, "loss": 0.01, "lr": 4.758433102372466e-05, "epoch": 2.8034188034188032, "percentage": 56.55, "elapsed_time": "0:50:59", "remaining_time": "0:39:10"}
|
| 206 |
-
{"current_steps": 134, "total_steps": 145, "loss": 0.0051, "lr": 1.7562223328224325e-06, "epoch": 4.581196581196581, "percentage": 92.41, "elapsed_time": "1:04:43", "remaining_time": "0:05:18"}
|
| 207 |
-
{"current_steps": 83, "total_steps": 145, "loss": 0.008, "lr": 4.6378259991911886e-05, "epoch": 2.8376068376068377, "percentage": 57.24, "elapsed_time": "0:51:30", "remaining_time": "0:38:28"}
|
| 208 |
-
{"current_steps": 135, "total_steps": 145, "loss": 0.0056, "lr": 1.4529091286973995e-06, "epoch": 4.615384615384615, "percentage": 93.1, "elapsed_time": "1:05:14", "remaining_time": "0:04:49"}
|
| 209 |
-
{"current_steps": 84, "total_steps": 145, "loss": 0.0093, "lr": 4.5174303954274244e-05, "epoch": 2.871794871794872, "percentage": 57.93, "elapsed_time": "0:52:04", "remaining_time": "0:37:49"}
|
| 210 |
-
{"current_steps": 135, "total_steps": 145, "eval_loss": 0.010704606771469116, "epoch": 4.615384615384615, "percentage": 93.1, "elapsed_time": "1:05:34", "remaining_time": "0:04:51"}
|
| 211 |
-
{"current_steps": 85, "total_steps": 145, "loss": 0.0091, "lr": 4.397316598723385e-05, "epoch": 2.905982905982906, "percentage": 58.62, "elapsed_time": "0:52:37", "remaining_time": "0:37:09"}
|
| 212 |
-
{"current_steps": 136, "total_steps": 145, "loss": 0.0054, "lr": 1.1779460585363944e-06, "epoch": 4.64957264957265, "percentage": 93.79, "elapsed_time": "1:06:07", "remaining_time": "0:04:22"}
|
| 213 |
-
{"current_steps": 85, "total_steps": 145, "eval_loss": 0.01138822827488184, "epoch": 2.905982905982906, "percentage": 58.62, "elapsed_time": "0:52:57", "remaining_time": "0:37:23"}
|
| 214 |
-
{"current_steps": 137, "total_steps": 145, "loss": 0.005, "lr": 9.314936930293283e-07, "epoch": 4.683760683760684, "percentage": 94.48, "elapsed_time": "1:06:39", "remaining_time": "0:03:53"}
|
| 215 |
-
{"current_steps": 86, "total_steps": 145, "loss": 0.0098, "lr": 4.277554752153895e-05, "epoch": 2.9401709401709404, "percentage": 59.31, "elapsed_time": "0:53:31", "remaining_time": "0:36:43"}
|
| 216 |
-
{"current_steps": 138, "total_steps": 145, "loss": 0.0057, "lr": 7.136959534174592e-07, "epoch": 4.717948717948718, "percentage": 95.17, "elapsed_time": "1:07:10", "remaining_time": "0:03:24"}
|
| 217 |
-
{"current_steps": 87, "total_steps": 145, "loss": 0.01, "lr": 4.1582147932648074e-05, "epoch": 2.9743589743589745, "percentage": 60.0, "elapsed_time": "0:54:05", "remaining_time": "0:36:03"}
|
| 218 |
-
{"current_steps": 139, "total_steps": 145, "loss": 0.0065, "lr": 5.246800274474439e-07, "epoch": 4.752136752136752, "percentage": 95.86, "elapsed_time": "1:07:38", "remaining_time": "0:02:55"}
|
| 219 |
-
{"current_steps": 88, "total_steps": 145, "loss": 0.0134, "lr": 4.039366413231458e-05, "epoch": 3.0085470085470085, "percentage": 60.69, "elapsed_time": "0:54:35", "remaining_time": "0:35:21"}
|
| 220 |
-
{"current_steps": 140, "total_steps": 145, "loss": 0.0057, "lr": 3.6455629509730136e-07, "epoch": 4.786324786324786, "percentage": 96.55, "elapsed_time": "1:08:09", "remaining_time": "0:02:26"}
|
| 221 |
-
{"current_steps": 89, "total_steps": 145, "loss": 0.0079, "lr": 3.92107901616097e-05, "epoch": 3.0427350427350426, "percentage": 61.38, "elapsed_time": "0:55:07", "remaining_time": "0:34:41"}
|
| 222 |
-
{"current_steps": 140, "total_steps": 145, "eval_loss": 0.010714489966630936, "epoch": 4.786324786324786, "percentage": 96.55, "elapsed_time": "1:08:28", "remaining_time": "0:02:26"}
|
| 223 |
-
{"current_steps": 141, "total_steps": 145, "loss": 0.0039, "lr": 2.334182641175686e-07, "epoch": 4.82051282051282, "percentage": 97.24, "elapsed_time": "1:08:57", "remaining_time": "0:01:57"}
|
| 224 |
-
{"current_steps": 90, "total_steps": 145, "loss": 0.009, "lr": 3.803421678562213e-05, "epoch": 3.076923076923077, "percentage": 62.07, "elapsed_time": "0:55:40", "remaining_time": "0:34:01"}
|
| 225 |
-
{"current_steps": 90, "total_steps": 145, "eval_loss": 0.011335253715515137, "epoch": 3.076923076923077, "percentage": 62.07, "elapsed_time": "0:56:01", "remaining_time": "0:34:14"}
|
| 226 |
-
{"current_steps": 142, "total_steps": 145, "loss": 0.0061, "lr": 1.3134251542544774e-07, "epoch": 4.854700854700854, "percentage": 97.93, "elapsed_time": "1:09:31", "remaining_time": "0:01:28"}
|
| 227 |
-
{"current_steps": 91, "total_steps": 145, "loss": 0.0077, "lr": 3.6864631090070655e-05, "epoch": 3.111111111111111, "percentage": 62.76, "elapsed_time": "0:56:33", "remaining_time": "0:33:33"}
|
| 228 |
-
{"current_steps": 143, "total_steps": 145, "loss": 0.0064, "lr": 5.838865838366792e-08, "epoch": 4.888888888888889, "percentage": 98.62, "elapsed_time": "1:10:02", "remaining_time": "0:00:58"}
|
| 229 |
-
{"current_steps": 92, "total_steps": 145, "loss": 0.0076, "lr": 3.570271608006555e-05, "epoch": 3.1452991452991452, "percentage": 63.45, "elapsed_time": "0:57:09", "remaining_time": "0:32:55"}
|
| 230 |
-
{"current_steps": 144, "total_steps": 145, "loss": 0.0071, "lr": 1.4599295990352924e-08, "epoch": 4.923076923076923, "percentage": 99.31, "elapsed_time": "1:10:31", "remaining_time": "0:00:29"}
|
| 231 |
-
{"current_steps": 93, "total_steps": 145, "loss": 0.007, "lr": 3.4549150281252636e-05, "epoch": 3.1794871794871793, "percentage": 64.14, "elapsed_time": "0:57:40", "remaining_time": "0:32:14"}
|
| 232 |
-
{"current_steps": 145, "total_steps": 145, "loss": 0.0075, "lr": 0.0, "epoch": 4.957264957264957, "percentage": 100.0, "elapsed_time": "1:11:02", "remaining_time": "0:00:00"}
|
| 233 |
-
{"current_steps": 145, "total_steps": 145, "eval_loss": 0.01070808432996273, "epoch": 4.957264957264957, "percentage": 100.0, "elapsed_time": "1:11:21", "remaining_time": "0:00:00"}
|
| 234 |
-
{"current_steps": 94, "total_steps": 145, "loss": 0.0072, "lr": 3.340460734357359e-05, "epoch": 3.213675213675214, "percentage": 64.83, "elapsed_time": "0:58:09", "remaining_time": "0:31:33"}
|
| 235 |
-
{"current_steps": 145, "total_steps": 145, "epoch": 4.957264957264957, "percentage": 100.0, "elapsed_time": "1:11:28", "remaining_time": "0:00:00"}
|
| 236 |
-
{"current_steps": 95, "total_steps": 145, "loss": 0.0062, "lr": 3.226975564787322e-05, "epoch": 3.247863247863248, "percentage": 65.52, "elapsed_time": "0:58:33", "remaining_time": "0:30:49"}
|
| 237 |
-
{"current_steps": 95, "total_steps": 145, "eval_loss": 0.011275053024291992, "epoch": 3.247863247863248, "percentage": 65.52, "elapsed_time": "0:58:45", "remaining_time": "0:30:55"}
|
| 238 |
-
{"current_steps": 96, "total_steps": 145, "loss": 0.0077, "lr": 3.114525791558398e-05, "epoch": 3.282051282051282, "percentage": 66.21, "elapsed_time": "0:59:03", "remaining_time": "0:30:08"}
|
| 239 |
-
{"current_steps": 97, "total_steps": 145, "loss": 0.0076, "lr": 3.003177082171523e-05, "epoch": 3.316239316239316, "percentage": 66.9, "elapsed_time": "0:59:19", "remaining_time": "0:29:21"}
|
| 240 |
-
{"current_steps": 98, "total_steps": 145, "loss": 0.0072, "lr": 2.8929944611373554e-05, "epoch": 3.3504273504273505, "percentage": 67.59, "elapsed_time": "0:59:37", "remaining_time": "0:28:35"}
|
| 241 |
-
{"current_steps": 99, "total_steps": 145, "loss": 0.0069, "lr": 2.784042272003794e-05, "epoch": 3.3846153846153846, "percentage": 68.28, "elapsed_time": "0:59:54", "remaining_time": "0:27:50"}
|
| 242 |
-
{"current_steps": 100, "total_steps": 145, "loss": 0.0069, "lr": 2.6763841397811573e-05, "epoch": 3.4188034188034186, "percentage": 68.97, "elapsed_time": "1:00:10", "remaining_time": "0:27:04"}
|
| 243 |
-
{"current_steps": 100, "total_steps": 145, "eval_loss": 0.011122054420411587, "epoch": 3.4188034188034186, "percentage": 68.97, "elapsed_time": "1:00:20", "remaining_time": "0:27:09"}
|
| 244 |
-
{"current_steps": 101, "total_steps": 145, "loss": 0.0094, "lr": 2.57008293378697e-05, "epoch": 3.452991452991453, "percentage": 69.66, "elapsed_time": "1:00:42", "remaining_time": "0:26:27"}
|
| 245 |
-
{"current_steps": 102, "total_steps": 145, "loss": 0.0064, "lr": 2.4652007309320498e-05, "epoch": 3.4871794871794872, "percentage": 70.34, "elapsed_time": "1:00:59", "remaining_time": "0:25:42"}
|
| 246 |
-
{"current_steps": 103, "total_steps": 145, "loss": 0.0074, "lr": 2.361798779469336e-05, "epoch": 3.5213675213675213, "percentage": 71.03, "elapsed_time": "1:01:15", "remaining_time": "0:24:58"}
|
| 247 |
-
{"current_steps": 104, "total_steps": 145, "loss": 0.0063, "lr": 2.259937463226651e-05, "epoch": 3.5555555555555554, "percentage": 71.72, "elapsed_time": "1:01:31", "remaining_time": "0:24:15"}
|
| 248 |
-
{"current_steps": 105, "total_steps": 145, "loss": 0.0071, "lr": 2.1596762663442218e-05, "epoch": 3.58974358974359, "percentage": 72.41, "elapsed_time": "1:01:47", "remaining_time": "0:23:32"}
|
| 249 |
-
{"current_steps": 105, "total_steps": 145, "eval_loss": 0.01076994277536869, "epoch": 3.58974358974359, "percentage": 72.41, "elapsed_time": "1:01:57", "remaining_time": "0:23:36"}
|
| 250 |
-
{"current_steps": 106, "total_steps": 145, "loss": 0.0078, "lr": 2.061073738537635e-05, "epoch": 3.623931623931624, "percentage": 73.1, "elapsed_time": "1:02:13", "remaining_time": "0:22:53"}
|
| 251 |
-
{"current_steps": 107, "total_steps": 145, "loss": 0.0079, "lr": 1.9641874609064443e-05, "epoch": 3.658119658119658, "percentage": 73.79, "elapsed_time": "1:02:29", "remaining_time": "0:22:11"}
|
| 252 |
-
{"current_steps": 108, "total_steps": 145, "loss": 0.0067, "lr": 1.8690740123084316e-05, "epoch": 3.6923076923076925, "percentage": 74.48, "elapsed_time": "1:02:45", "remaining_time": "0:21:29"}
|
| 253 |
-
{"current_steps": 109, "total_steps": 145, "loss": 0.0066, "lr": 1.7757889363191483e-05, "epoch": 3.7264957264957266, "percentage": 75.17, "elapsed_time": "1:03:02", "remaining_time": "0:20:49"}
|
| 254 |
-
{"current_steps": 110, "total_steps": 145, "loss": 0.006, "lr": 1.684386708796025e-05, "epoch": 3.7606837606837606, "percentage": 75.86, "elapsed_time": "1:03:17", "remaining_time": "0:20:08"}
|
| 255 |
-
{"current_steps": 110, "total_steps": 145, "eval_loss": 0.010681088082492352, "epoch": 3.7606837606837606, "percentage": 75.86, "elapsed_time": "1:03:27", "remaining_time": "0:20:11"}
|
| 256 |
-
{"current_steps": 111, "total_steps": 145, "loss": 0.0061, "lr": 1.5949207060660138e-05, "epoch": 3.7948717948717947, "percentage": 76.55, "elapsed_time": "1:03:43", "remaining_time": "0:19:31"}
|
| 257 |
-
{"current_steps": 112, "total_steps": 145, "loss": 0.0072, "lr": 1.5074431737553157e-05, "epoch": 3.8290598290598292, "percentage": 77.24, "elapsed_time": "1:04:00", "remaining_time": "0:18:51"}
|
| 258 |
-
{"current_steps": 113, "total_steps": 145, "loss": 0.0091, "lr": 1.422005196279395e-05, "epoch": 3.8632478632478633, "percentage": 77.93, "elapsed_time": "1:04:17", "remaining_time": "0:18:12"}
|
| 259 |
-
{"current_steps": 114, "total_steps": 145, "loss": 0.0071, "lr": 1.338656667011134e-05, "epoch": 3.8974358974358974, "percentage": 78.62, "elapsed_time": "1:04:33", "remaining_time": "0:17:33"}
|
| 260 |
-
{"current_steps": 115, "total_steps": 145, "loss": 0.0065, "lr": 1.257446259144494e-05, "epoch": 3.931623931623932, "percentage": 79.31, "elapsed_time": "1:04:50", "remaining_time": "0:16:54"}
|
| 261 |
-
{"current_steps": 115, "total_steps": 145, "eval_loss": 0.010614048689603806, "epoch": 3.931623931623932, "percentage": 79.31, "elapsed_time": "1:05:00", "remaining_time": "0:16:57"}
|
| 262 |
-
{"current_steps": 116, "total_steps": 145, "loss": 0.0059, "lr": 1.178421397270758e-05, "epoch": 3.965811965811966, "percentage": 80.0, "elapsed_time": "1:05:15", "remaining_time": "0:16:18"}
|
| 263 |
-
{"current_steps": 117, "total_steps": 145, "loss": 0.0121, "lr": 1.1016282296838887e-05, "epoch": 4.0, "percentage": 80.69, "elapsed_time": "1:05:30", "remaining_time": "0:15:40"}
|
| 264 |
-
{"current_steps": 118, "total_steps": 145, "loss": 0.005, "lr": 1.0271116014312293e-05, "epoch": 4.034188034188034, "percentage": 81.38, "elapsed_time": "1:05:47", "remaining_time": "0:15:03"}
|
| 265 |
-
{"current_steps": 119, "total_steps": 145, "loss": 0.0053, "lr": 9.549150281252633e-06, "epoch": 4.068376068376068, "percentage": 82.07, "elapsed_time": "1:06:04", "remaining_time": "0:14:26"}
|
| 266 |
-
{"current_steps": 120, "total_steps": 145, "loss": 0.0076, "lr": 8.850806705317183e-06, "epoch": 4.102564102564102, "percentage": 82.76, "elapsed_time": "1:06:20", "remaining_time": "0:13:49"}
|
| 267 |
-
{"current_steps": 120, "total_steps": 145, "eval_loss": 0.010566945187747478, "epoch": 4.102564102564102, "percentage": 82.76, "elapsed_time": "1:06:30", "remaining_time": "0:13:51"}
|
| 268 |
-
{"current_steps": 121, "total_steps": 145, "loss": 0.0072, "lr": 8.176493099488663e-06, "epoch": 4.136752136752137, "percentage": 83.45, "elapsed_time": "1:06:47", "remaining_time": "0:13:14"}
|
| 269 |
-
{"current_steps": 122, "total_steps": 145, "loss": 0.0061, "lr": 7.526603243923957e-06, "epoch": 4.170940170940171, "percentage": 84.14, "elapsed_time": "1:07:04", "remaining_time": "0:12:38"}
|
| 270 |
-
{"current_steps": 123, "total_steps": 145, "loss": 0.006, "lr": 6.901516655997536e-06, "epoch": 4.205128205128205, "percentage": 84.83, "elapsed_time": "1:07:21", "remaining_time": "0:12:02"}
|
| 271 |
-
{"current_steps": 124, "total_steps": 145, "loss": 0.0059, "lr": 6.301598368674105e-06, "epoch": 4.239316239316239, "percentage": 85.52, "elapsed_time": "1:07:38", "remaining_time": "0:11:27"}
|
| 272 |
-
{"current_steps": 125, "total_steps": 145, "loss": 0.0057, "lr": 5.727198717339511e-06, "epoch": 4.273504273504273, "percentage": 86.21, "elapsed_time": "1:07:55", "remaining_time": "0:10:52"}
|
| 273 |
-
{"current_steps": 125, "total_steps": 145, "eval_loss": 0.010598141700029373, "epoch": 4.273504273504273, "percentage": 86.21, "elapsed_time": "1:08:05", "remaining_time": "0:10:53"}
|
| 274 |
-
{"current_steps": 126, "total_steps": 145, "loss": 0.0051, "lr": 5.178653135214812e-06, "epoch": 4.3076923076923075, "percentage": 86.9, "elapsed_time": "1:08:21", "remaining_time": "0:10:18"}
|
| 275 |
-
{"current_steps": 127, "total_steps": 145, "loss": 0.0058, "lr": 4.65628195747273e-06, "epoch": 4.3418803418803416, "percentage": 87.59, "elapsed_time": "1:08:37", "remaining_time": "0:09:43"}
|
| 276 |
-
{"current_steps": 128, "total_steps": 145, "loss": 0.0051, "lr": 4.16039023417088e-06, "epoch": 4.3760683760683765, "percentage": 88.28, "elapsed_time": "1:08:54", "remaining_time": "0:09:09"}
|
| 277 |
-
{"current_steps": 129, "total_steps": 145, "loss": 0.0054, "lr": 3.691267552111183e-06, "epoch": 4.410256410256411, "percentage": 88.97, "elapsed_time": "1:09:12", "remaining_time": "0:08:34"}
|
| 278 |
-
{"current_steps": 130, "total_steps": 145, "loss": 0.0071, "lr": 3.249187865729264e-06, "epoch": 4.444444444444445, "percentage": 89.66, "elapsed_time": "1:09:29", "remaining_time": "0:08:01"}
|
| 279 |
-
{"current_steps": 130, "total_steps": 145, "eval_loss": 0.010587843134999275, "epoch": 4.444444444444445, "percentage": 89.66, "elapsed_time": "1:09:38", "remaining_time": "0:08:02"}
|
| 280 |
-
{"current_steps": 131, "total_steps": 145, "loss": 0.005, "lr": 2.8344093371128424e-06, "epoch": 4.478632478632479, "percentage": 90.34, "elapsed_time": "1:09:56", "remaining_time": "0:07:28"}
|
| 281 |
-
{"current_steps": 132, "total_steps": 145, "loss": 0.0048, "lr": 2.4471741852423237e-06, "epoch": 4.512820512820513, "percentage": 91.03, "elapsed_time": "1:10:13", "remaining_time": "0:06:54"}
|
| 282 |
-
{"current_steps": 133, "total_steps": 145, "loss": 0.0047, "lr": 2.087708544541689e-06, "epoch": 4.547008547008547, "percentage": 91.72, "elapsed_time": "1:10:29", "remaining_time": "0:06:21"}
|
| 283 |
-
{"current_steps": 134, "total_steps": 145, "loss": 0.0053, "lr": 1.7562223328224325e-06, "epoch": 4.581196581196581, "percentage": 92.41, "elapsed_time": "1:10:45", "remaining_time": "0:05:48"}
|
| 284 |
-
{"current_steps": 135, "total_steps": 145, "loss": 0.0055, "lr": 1.4529091286973995e-06, "epoch": 4.615384615384615, "percentage": 93.1, "elapsed_time": "1:11:02", "remaining_time": "0:05:15"}
|
| 285 |
-
{"current_steps": 135, "total_steps": 145, "eval_loss": 0.010594615712761879, "epoch": 4.615384615384615, "percentage": 93.1, "elapsed_time": "1:11:11", "remaining_time": "0:05:16"}
|
| 286 |
-
{"current_steps": 136, "total_steps": 145, "loss": 0.0053, "lr": 1.1779460585363944e-06, "epoch": 4.64957264957265, "percentage": 93.79, "elapsed_time": "1:11:29", "remaining_time": "0:04:43"}
|
| 287 |
-
{"current_steps": 137, "total_steps": 145, "loss": 0.0048, "lr": 9.314936930293283e-07, "epoch": 4.683760683760684, "percentage": 94.48, "elapsed_time": "1:11:46", "remaining_time": "0:04:11"}
|
| 288 |
-
{"current_steps": 138, "total_steps": 145, "loss": 0.0056, "lr": 7.136959534174592e-07, "epoch": 4.717948717948718, "percentage": 95.17, "elapsed_time": "1:12:03", "remaining_time": "0:03:39"}
|
| 289 |
-
{"current_steps": 139, "total_steps": 145, "loss": 0.0065, "lr": 5.246800274474439e-07, "epoch": 4.752136752136752, "percentage": 95.86, "elapsed_time": "1:12:18", "remaining_time": "0:03:07"}
|
| 290 |
-
{"current_steps": 140, "total_steps": 145, "loss": 0.0053, "lr": 3.6455629509730136e-07, "epoch": 4.786324786324786, "percentage": 96.55, "elapsed_time": "1:12:35", "remaining_time": "0:02:35"}
|
| 291 |
-
{"current_steps": 140, "total_steps": 145, "eval_loss": 0.010573416948318481, "epoch": 4.786324786324786, "percentage": 96.55, "elapsed_time": "1:12:44", "remaining_time": "0:02:35"}
|
| 292 |
-
{"current_steps": 141, "total_steps": 145, "loss": 0.0038, "lr": 2.334182641175686e-07, "epoch": 4.82051282051282, "percentage": 97.24, "elapsed_time": "1:13:00", "remaining_time": "0:02:04"}
|
| 293 |
-
{"current_steps": 142, "total_steps": 145, "loss": 0.006, "lr": 1.3134251542544774e-07, "epoch": 4.854700854700854, "percentage": 97.93, "elapsed_time": "1:13:18", "remaining_time": "0:01:32"}
|
| 294 |
-
{"current_steps": 143, "total_steps": 145, "loss": 0.0063, "lr": 5.838865838366792e-08, "epoch": 4.888888888888889, "percentage": 98.62, "elapsed_time": "1:13:34", "remaining_time": "0:01:01"}
|
| 295 |
-
{"current_steps": 144, "total_steps": 145, "loss": 0.0068, "lr": 1.4599295990352924e-08, "epoch": 4.923076923076923, "percentage": 99.31, "elapsed_time": "1:13:49", "remaining_time": "0:00:30"}
|
| 296 |
-
{"current_steps": 145, "total_steps": 145, "loss": 0.0074, "lr": 0.0, "epoch": 4.957264957264957, "percentage": 100.0, "elapsed_time": "1:14:06", "remaining_time": "0:00:00"}
|
| 297 |
-
{"current_steps": 145, "total_steps": 145, "eval_loss": 0.010564341209828854, "epoch": 4.957264957264957, "percentage": 100.0, "elapsed_time": "1:14:15", "remaining_time": "0:00:00"}
|
| 298 |
-
{"current_steps": 145, "total_steps": 145, "epoch": 4.957264957264957, "percentage": 100.0, "elapsed_time": "1:14:31", "remaining_time": "0:00:00"}
|
|
|
|
| 1 |
+
{"current_steps": 1, "total_steps": 100, "loss": 0.063, "lr": 1e-05, "epoch": 0.048484848484848485, "percentage": 1.0, "elapsed_time": "0:00:27", "remaining_time": "0:45:13"}
|
| 2 |
+
{"current_steps": 2, "total_steps": 100, "loss": 0.0607, "lr": 2e-05, "epoch": 0.09696969696969697, "percentage": 2.0, "elapsed_time": "0:00:45", "remaining_time": "0:37:02"}
|
| 3 |
+
{"current_steps": 3, "total_steps": 100, "loss": 0.0615, "lr": 3e-05, "epoch": 0.14545454545454545, "percentage": 3.0, "elapsed_time": "0:01:04", "remaining_time": "0:34:46"}
|
| 4 |
+
{"current_steps": 4, "total_steps": 100, "loss": 0.0504, "lr": 4e-05, "epoch": 0.19393939393939394, "percentage": 4.0, "elapsed_time": "0:01:25", "remaining_time": "0:34:03"}
|
| 5 |
+
{"current_steps": 5, "total_steps": 100, "loss": 0.0395, "lr": 5e-05, "epoch": 0.24242424242424243, "percentage": 5.0, "elapsed_time": "0:01:43", "remaining_time": "0:32:37"}
|
| 6 |
+
{"current_steps": 5, "total_steps": 100, "eval_loss": 0.04326783865690231, "epoch": 0.24242424242424243, "percentage": 5.0, "elapsed_time": "0:01:54", "remaining_time": "0:36:13"}
|
| 7 |
+
{"current_steps": 6, "total_steps": 100, "loss": 0.0419, "lr": 6e-05, "epoch": 0.2909090909090909, "percentage": 6.0, "elapsed_time": "0:02:12", "remaining_time": "0:34:37"}
|
| 8 |
+
{"current_steps": 7, "total_steps": 100, "loss": 0.0381, "lr": 7e-05, "epoch": 0.3393939393939394, "percentage": 7.0, "elapsed_time": "0:02:35", "remaining_time": "0:34:24"}
|
| 9 |
+
{"current_steps": 8, "total_steps": 100, "loss": 0.0341, "lr": 8e-05, "epoch": 0.3878787878787879, "percentage": 8.0, "elapsed_time": "0:02:52", "remaining_time": "0:33:09"}
|
| 10 |
+
{"current_steps": 9, "total_steps": 100, "loss": 0.0345, "lr": 9e-05, "epoch": 0.43636363636363634, "percentage": 9.0, "elapsed_time": "0:03:10", "remaining_time": "0:32:10"}
|
| 11 |
+
{"current_steps": 10, "total_steps": 100, "loss": 0.0324, "lr": 0.0001, "epoch": 0.48484848484848486, "percentage": 10.0, "elapsed_time": "0:03:28", "remaining_time": "0:31:13"}
|
| 12 |
+
{"current_steps": 10, "total_steps": 100, "eval_loss": 0.03000650927424431, "epoch": 0.48484848484848486, "percentage": 10.0, "elapsed_time": "0:03:38", "remaining_time": "0:32:47"}
|
| 13 |
+
{"current_steps": 11, "total_steps": 100, "loss": 0.0331, "lr": 9.99695413509548e-05, "epoch": 0.5333333333333333, "percentage": 11.0, "elapsed_time": "0:03:56", "remaining_time": "0:31:51"}
|
| 14 |
+
{"current_steps": 12, "total_steps": 100, "loss": 0.029, "lr": 9.987820251299122e-05, "epoch": 0.5818181818181818, "percentage": 12.0, "elapsed_time": "0:04:14", "remaining_time": "0:31:03"}
|
| 15 |
+
{"current_steps": 13, "total_steps": 100, "loss": 0.0257, "lr": 9.972609476841367e-05, "epoch": 0.6303030303030303, "percentage": 13.0, "elapsed_time": "0:04:32", "remaining_time": "0:30:20"}
|
| 16 |
+
{"current_steps": 14, "total_steps": 100, "loss": 0.0215, "lr": 9.951340343707852e-05, "epoch": 0.6787878787878788, "percentage": 14.0, "elapsed_time": "0:04:48", "remaining_time": "0:29:32"}
|
| 17 |
+
{"current_steps": 15, "total_steps": 100, "loss": 0.024, "lr": 9.924038765061042e-05, "epoch": 0.7272727272727273, "percentage": 15.0, "elapsed_time": "0:05:06", "remaining_time": "0:28:56"}
|
| 18 |
+
{"current_steps": 15, "total_steps": 100, "eval_loss": 0.024439169093966484, "epoch": 0.7272727272727273, "percentage": 15.0, "elapsed_time": "0:05:16", "remaining_time": "0:29:54"}
|
| 19 |
+
{"current_steps": 16, "total_steps": 100, "loss": 0.0321, "lr": 9.890738003669029e-05, "epoch": 0.7757575757575758, "percentage": 16.0, "elapsed_time": "0:05:34", "remaining_time": "0:29:17"}
|
| 20 |
+
{"current_steps": 17, "total_steps": 100, "loss": 0.0281, "lr": 9.851478631379982e-05, "epoch": 0.8242424242424242, "percentage": 17.0, "elapsed_time": "0:05:52", "remaining_time": "0:28:41"}
|
| 21 |
+
{"current_steps": 18, "total_steps": 100, "loss": 0.0202, "lr": 9.806308479691595e-05, "epoch": 0.8727272727272727, "percentage": 18.0, "elapsed_time": "0:06:11", "remaining_time": "0:28:11"}
|
| 22 |
+
{"current_steps": 19, "total_steps": 100, "loss": 0.0206, "lr": 9.755282581475769e-05, "epoch": 0.9212121212121213, "percentage": 19.0, "elapsed_time": "0:06:28", "remaining_time": "0:27:35"}
|
| 23 |
+
{"current_steps": 20, "total_steps": 100, "loss": 0.0189, "lr": 9.698463103929542e-05, "epoch": 0.9696969696969697, "percentage": 20.0, "elapsed_time": "0:06:45", "remaining_time": "0:27:01"}
|
| 24 |
+
{"current_steps": 20, "total_steps": 100, "eval_loss": 0.0212231557816267, "epoch": 0.9696969696969697, "percentage": 20.0, "elapsed_time": "0:06:55", "remaining_time": "0:27:43"}
|
| 25 |
+
{"current_steps": 21, "total_steps": 100, "loss": 0.0317, "lr": 9.635919272833938e-05, "epoch": 1.0363636363636364, "percentage": 21.0, "elapsed_time": "0:07:17", "remaining_time": "0:27:25"}
|
| 26 |
+
{"current_steps": 22, "total_steps": 100, "loss": 0.019, "lr": 9.567727288213005e-05, "epoch": 1.084848484848485, "percentage": 22.0, "elapsed_time": "0:07:34", "remaining_time": "0:26:52"}
|
| 27 |
+
{"current_steps": 23, "total_steps": 100, "loss": 0.019, "lr": 9.493970231495835e-05, "epoch": 1.1333333333333333, "percentage": 23.0, "elapsed_time": "0:07:52", "remaining_time": "0:26:22"}
|
| 28 |
+
{"current_steps": 24, "total_steps": 100, "loss": 0.0181, "lr": 9.414737964294636e-05, "epoch": 1.1818181818181819, "percentage": 24.0, "elapsed_time": "0:08:10", "remaining_time": "0:25:53"}
|
| 29 |
+
{"current_steps": 25, "total_steps": 100, "loss": 0.0171, "lr": 9.330127018922194e-05, "epoch": 1.2303030303030302, "percentage": 25.0, "elapsed_time": "0:08:27", "remaining_time": "0:25:23"}
|
| 30 |
+
{"current_steps": 25, "total_steps": 100, "eval_loss": 0.019027845934033394, "epoch": 1.2303030303030302, "percentage": 25.0, "elapsed_time": "0:08:38", "remaining_time": "0:25:54"}
|
| 31 |
+
{"current_steps": 26, "total_steps": 100, "loss": 0.0182, "lr": 9.24024048078213e-05, "epoch": 1.2787878787878788, "percentage": 26.0, "elapsed_time": "0:08:55", "remaining_time": "0:25:24"}
|
| 32 |
+
{"current_steps": 27, "total_steps": 100, "loss": 0.0163, "lr": 9.145187862775209e-05, "epoch": 1.3272727272727272, "percentage": 27.0, "elapsed_time": "0:09:13", "remaining_time": "0:24:56"}
|
| 33 |
+
{"current_steps": 28, "total_steps": 100, "loss": 0.0177, "lr": 9.045084971874738e-05, "epoch": 1.3757575757575757, "percentage": 28.0, "elapsed_time": "0:09:31", "remaining_time": "0:24:28"}
|
| 34 |
+
{"current_steps": 29, "total_steps": 100, "loss": 0.014, "lr": 8.940053768033609e-05, "epoch": 1.4242424242424243, "percentage": 29.0, "elapsed_time": "0:09:47", "remaining_time": "0:23:59"}
|
| 35 |
+
{"current_steps": 30, "total_steps": 100, "loss": 0.0146, "lr": 8.83022221559489e-05, "epoch": 1.4727272727272727, "percentage": 30.0, "elapsed_time": "0:10:05", "remaining_time": "0:23:32"}
|
| 36 |
+
{"current_steps": 30, "total_steps": 100, "eval_loss": 0.01733844168484211, "epoch": 1.4727272727272727, "percentage": 30.0, "elapsed_time": "0:10:15", "remaining_time": "0:23:56"}
|
| 37 |
+
{"current_steps": 31, "total_steps": 100, "loss": 0.017, "lr": 8.715724127386972e-05, "epoch": 1.5212121212121212, "percentage": 31.0, "elapsed_time": "0:10:33", "remaining_time": "0:23:30"}
|
| 38 |
+
{"current_steps": 32, "total_steps": 100, "loss": 0.0155, "lr": 8.596699001693255e-05, "epoch": 1.5696969696969698, "percentage": 32.0, "elapsed_time": "0:10:51", "remaining_time": "0:23:04"}
|
| 39 |
+
{"current_steps": 33, "total_steps": 100, "loss": 0.0157, "lr": 8.473291852294987e-05, "epoch": 1.6181818181818182, "percentage": 33.0, "elapsed_time": "0:11:08", "remaining_time": "0:22:37"}
|
| 40 |
+
{"current_steps": 34, "total_steps": 100, "loss": 0.0167, "lr": 8.345653031794292e-05, "epoch": 1.6666666666666665, "percentage": 34.0, "elapsed_time": "0:11:26", "remaining_time": "0:22:12"}
|
| 41 |
+
{"current_steps": 35, "total_steps": 100, "loss": 0.0144, "lr": 8.213938048432697e-05, "epoch": 1.7151515151515153, "percentage": 35.0, "elapsed_time": "0:11:44", "remaining_time": "0:21:48"}
|
| 42 |
+
{"current_steps": 35, "total_steps": 100, "eval_loss": 0.016134196892380714, "epoch": 1.7151515151515153, "percentage": 35.0, "elapsed_time": "0:11:54", "remaining_time": "0:22:07"}
|
| 43 |
+
{"current_steps": 36, "total_steps": 100, "loss": 0.0162, "lr": 8.07830737662829e-05, "epoch": 1.7636363636363637, "percentage": 36.0, "elapsed_time": "0:12:12", "remaining_time": "0:21:41"}
|
| 44 |
+
{"current_steps": 37, "total_steps": 100, "loss": 0.0194, "lr": 7.938926261462366e-05, "epoch": 1.812121212121212, "percentage": 37.0, "elapsed_time": "0:12:29", "remaining_time": "0:21:16"}
|
| 45 |
+
{"current_steps": 38, "total_steps": 100, "loss": 0.0154, "lr": 7.795964517353735e-05, "epoch": 1.8606060606060606, "percentage": 38.0, "elapsed_time": "0:12:46", "remaining_time": "0:20:50"}
|
| 46 |
+
{"current_steps": 39, "total_steps": 100, "loss": 0.0134, "lr": 7.649596321166024e-05, "epoch": 1.9090909090909092, "percentage": 39.0, "elapsed_time": "0:13:03", "remaining_time": "0:20:25"}
|
| 47 |
+
{"current_steps": 40, "total_steps": 100, "loss": 0.0104, "lr": 7.500000000000001e-05, "epoch": 1.9575757575757575, "percentage": 40.0, "elapsed_time": "0:13:21", "remaining_time": "0:20:01"}
|
| 48 |
+
{"current_steps": 40, "total_steps": 100, "eval_loss": 0.015456685796380043, "epoch": 1.9575757575757575, "percentage": 40.0, "elapsed_time": "0:13:31", "remaining_time": "0:20:17"}
|
| 49 |
+
{"current_steps": 41, "total_steps": 100, "loss": 0.0277, "lr": 7.347357813929454e-05, "epoch": 2.0242424242424244, "percentage": 41.0, "elapsed_time": "0:13:49", "remaining_time": "0:19:54"}
|
| 50 |
+
{"current_steps": 42, "total_steps": 100, "loss": 0.012, "lr": 7.191855733945387e-05, "epoch": 2.0727272727272728, "percentage": 42.0, "elapsed_time": "0:14:07", "remaining_time": "0:19:30"}
|
| 51 |
+
{"current_steps": 43, "total_steps": 100, "loss": 0.0147, "lr": 7.033683215379002e-05, "epoch": 2.121212121212121, "percentage": 43.0, "elapsed_time": "0:14:25", "remaining_time": "0:19:06"}
|
| 52 |
+
{"current_steps": 44, "total_steps": 100, "loss": 0.014, "lr": 6.873032967079561e-05, "epoch": 2.16969696969697, "percentage": 44.0, "elapsed_time": "0:14:41", "remaining_time": "0:18:42"}
|
| 53 |
+
{"current_steps": 45, "total_steps": 100, "loss": 0.0143, "lr": 6.710100716628344e-05, "epoch": 2.2181818181818183, "percentage": 45.0, "elapsed_time": "0:14:59", "remaining_time": "0:18:19"}
|
| 54 |
+
{"current_steps": 45, "total_steps": 100, "eval_loss": 0.01516613457351923, "epoch": 2.2181818181818183, "percentage": 45.0, "elapsed_time": "0:15:09", "remaining_time": "0:18:31"}
|
| 55 |
+
{"current_steps": 46, "total_steps": 100, "loss": 0.0126, "lr": 6.545084971874738e-05, "epoch": 2.2666666666666666, "percentage": 46.0, "elapsed_time": "0:15:27", "remaining_time": "0:18:08"}
|
| 56 |
+
{"current_steps": 47, "total_steps": 100, "loss": 0.0118, "lr": 6.378186779084995e-05, "epoch": 2.315151515151515, "percentage": 47.0, "elapsed_time": "0:15:45", "remaining_time": "0:17:46"}
|
| 57 |
+
{"current_steps": 48, "total_steps": 100, "loss": 0.0121, "lr": 6.209609477998338e-05, "epoch": 2.3636363636363638, "percentage": 48.0, "elapsed_time": "0:16:03", "remaining_time": "0:17:23"}
|
| 58 |
+
{"current_steps": 49, "total_steps": 100, "loss": 0.0096, "lr": 6.0395584540887963e-05, "epoch": 2.412121212121212, "percentage": 49.0, "elapsed_time": "0:16:20", "remaining_time": "0:17:00"}
|
| 59 |
+
{"current_steps": 50, "total_steps": 100, "loss": 0.0117, "lr": 5.868240888334653e-05, "epoch": 2.4606060606060605, "percentage": 50.0, "elapsed_time": "0:16:38", "remaining_time": "0:16:38"}
|
| 60 |
+
{"current_steps": 50, "total_steps": 100, "eval_loss": 0.014072530902922153, "epoch": 2.4606060606060605, "percentage": 50.0, "elapsed_time": "0:16:48", "remaining_time": "0:16:48"}
|
| 61 |
+
{"current_steps": 51, "total_steps": 100, "loss": 0.0139, "lr": 5.695865504800327e-05, "epoch": 2.509090909090909, "percentage": 51.0, "elapsed_time": "0:17:12", "remaining_time": "0:16:32"}
|
| 62 |
+
{"current_steps": 52, "total_steps": 100, "loss": 0.0099, "lr": 5.522642316338268e-05, "epoch": 2.5575757575757576, "percentage": 52.0, "elapsed_time": "0:17:30", "remaining_time": "0:16:09"}
|
| 63 |
+
{"current_steps": 53, "total_steps": 100, "loss": 0.013, "lr": 5.348782368720626e-05, "epoch": 2.606060606060606, "percentage": 53.0, "elapsed_time": "0:17:49", "remaining_time": "0:15:47"}
|
| 64 |
+
{"current_steps": 54, "total_steps": 100, "loss": 0.0093, "lr": 5.174497483512506e-05, "epoch": 2.6545454545454543, "percentage": 54.0, "elapsed_time": "0:18:06", "remaining_time": "0:15:25"}
|
| 65 |
+
{"current_steps": 55, "total_steps": 100, "loss": 0.015, "lr": 5e-05, "epoch": 2.703030303030303, "percentage": 55.0, "elapsed_time": "0:18:24", "remaining_time": "0:15:03"}
|
| 66 |
+
{"current_steps": 55, "total_steps": 100, "eval_loss": 0.013632840476930141, "epoch": 2.703030303030303, "percentage": 55.0, "elapsed_time": "0:18:34", "remaining_time": "0:15:12"}
|
| 67 |
+
{"current_steps": 56, "total_steps": 100, "loss": 0.0109, "lr": 4.825502516487497e-05, "epoch": 2.7515151515151515, "percentage": 56.0, "elapsed_time": "0:18:52", "remaining_time": "0:14:49"}
|
| 68 |
+
{"current_steps": 57, "total_steps": 100, "loss": 0.0104, "lr": 4.6512176312793736e-05, "epoch": 2.8, "percentage": 57.0, "elapsed_time": "0:19:10", "remaining_time": "0:14:27"}
|
| 69 |
+
{"current_steps": 58, "total_steps": 100, "loss": 0.0097, "lr": 4.477357683661734e-05, "epoch": 2.8484848484848486, "percentage": 58.0, "elapsed_time": "0:19:26", "remaining_time": "0:14:04"}
|
| 70 |
+
{"current_steps": 59, "total_steps": 100, "loss": 0.0108, "lr": 4.3041344951996746e-05, "epoch": 2.896969696969697, "percentage": 59.0, "elapsed_time": "0:19:43", "remaining_time": "0:13:42"}
|
| 71 |
+
{"current_steps": 60, "total_steps": 100, "loss": 0.0092, "lr": 4.131759111665349e-05, "epoch": 2.9454545454545453, "percentage": 60.0, "elapsed_time": "0:20:01", "remaining_time": "0:13:20"}
|
| 72 |
+
{"current_steps": 60, "total_steps": 100, "eval_loss": 0.013053460977971554, "epoch": 2.9454545454545453, "percentage": 60.0, "elapsed_time": "0:20:11", "remaining_time": "0:13:27"}
|
| 73 |
+
{"current_steps": 61, "total_steps": 100, "loss": 0.0172, "lr": 3.960441545911204e-05, "epoch": 3.012121212121212, "percentage": 61.0, "elapsed_time": "0:20:29", "remaining_time": "0:13:06"}
|
| 74 |
+
{"current_steps": 62, "total_steps": 100, "loss": 0.008, "lr": 3.790390522001662e-05, "epoch": 3.0606060606060606, "percentage": 62.0, "elapsed_time": "0:20:47", "remaining_time": "0:12:44"}
|
| 75 |
+
{"current_steps": 63, "total_steps": 100, "loss": 0.0121, "lr": 3.6218132209150045e-05, "epoch": 3.109090909090909, "percentage": 63.0, "elapsed_time": "0:21:05", "remaining_time": "0:12:23"}
|
| 76 |
+
{"current_steps": 64, "total_steps": 100, "loss": 0.008, "lr": 3.4549150281252636e-05, "epoch": 3.1575757575757577, "percentage": 64.0, "elapsed_time": "0:21:22", "remaining_time": "0:12:01"}
|
| 77 |
+
{"current_steps": 65, "total_steps": 100, "loss": 0.008, "lr": 3.289899283371657e-05, "epoch": 3.206060606060606, "percentage": 65.0, "elapsed_time": "0:21:40", "remaining_time": "0:11:40"}
|
| 78 |
+
{"current_steps": 65, "total_steps": 100, "eval_loss": 0.012713730335235596, "epoch": 3.206060606060606, "percentage": 65.0, "elapsed_time": "0:21:50", "remaining_time": "0:11:45"}
|
| 79 |
+
{"current_steps": 66, "total_steps": 100, "loss": 0.0096, "lr": 3.12696703292044e-05, "epoch": 3.2545454545454544, "percentage": 66.0, "elapsed_time": "0:22:08", "remaining_time": "0:11:24"}
|
| 80 |
+
{"current_steps": 67, "total_steps": 100, "loss": 0.0071, "lr": 2.9663167846209998e-05, "epoch": 3.303030303030303, "percentage": 67.0, "elapsed_time": "0:22:26", "remaining_time": "0:11:03"}
|
| 81 |
+
{"current_steps": 68, "total_steps": 100, "loss": 0.0092, "lr": 2.8081442660546125e-05, "epoch": 3.3515151515151516, "percentage": 68.0, "elapsed_time": "0:22:44", "remaining_time": "0:10:41"}
|
| 82 |
+
{"current_steps": 69, "total_steps": 100, "loss": 0.009, "lr": 2.6526421860705473e-05, "epoch": 3.4, "percentage": 69.0, "elapsed_time": "0:23:01", "remaining_time": "0:10:20"}
|
| 83 |
+
{"current_steps": 70, "total_steps": 100, "loss": 0.0109, "lr": 2.500000000000001e-05, "epoch": 3.4484848484848483, "percentage": 70.0, "elapsed_time": "0:23:19", "remaining_time": "0:09:59"}
|
| 84 |
+
{"current_steps": 70, "total_steps": 100, "eval_loss": 0.012468294240534306, "epoch": 3.4484848484848483, "percentage": 70.0, "elapsed_time": "0:23:29", "remaining_time": "0:10:04"}
|
| 85 |
+
{"current_steps": 71, "total_steps": 100, "loss": 0.0123, "lr": 2.350403678833976e-05, "epoch": 3.496969696969697, "percentage": 71.0, "elapsed_time": "0:23:47", "remaining_time": "0:09:43"}
|
| 86 |
+
{"current_steps": 72, "total_steps": 100, "loss": 0.0072, "lr": 2.2040354826462668e-05, "epoch": 3.5454545454545454, "percentage": 72.0, "elapsed_time": "0:24:05", "remaining_time": "0:09:22"}
|
| 87 |
+
{"current_steps": 73, "total_steps": 100, "loss": 0.009, "lr": 2.061073738537635e-05, "epoch": 3.5939393939393938, "percentage": 73.0, "elapsed_time": "0:24:23", "remaining_time": "0:09:01"}
|
| 88 |
+
{"current_steps": 74, "total_steps": 100, "loss": 0.0078, "lr": 1.9216926233717085e-05, "epoch": 3.6424242424242426, "percentage": 74.0, "elapsed_time": "0:24:41", "remaining_time": "0:08:40"}
|
| 89 |
+
{"current_steps": 75, "total_steps": 100, "loss": 0.0085, "lr": 1.7860619515673033e-05, "epoch": 3.690909090909091, "percentage": 75.0, "elapsed_time": "0:24:58", "remaining_time": "0:08:19"}
|
| 90 |
+
{"current_steps": 75, "total_steps": 100, "eval_loss": 0.012197648175060749, "epoch": 3.690909090909091, "percentage": 75.0, "elapsed_time": "0:25:08", "remaining_time": "0:08:22"}
|
| 91 |
+
{"current_steps": 76, "total_steps": 100, "loss": 0.0089, "lr": 1.6543469682057106e-05, "epoch": 3.7393939393939393, "percentage": 76.0, "elapsed_time": "0:25:26", "remaining_time": "0:08:02"}
|
| 92 |
+
{"current_steps": 77, "total_steps": 100, "loss": 0.0127, "lr": 1.526708147705013e-05, "epoch": 3.787878787878788, "percentage": 77.0, "elapsed_time": "0:25:44", "remaining_time": "0:07:41"}
|
| 93 |
+
{"current_steps": 78, "total_steps": 100, "loss": 0.0085, "lr": 1.4033009983067452e-05, "epoch": 3.8363636363636364, "percentage": 78.0, "elapsed_time": "0:26:01", "remaining_time": "0:07:20"}
|
| 94 |
+
{"current_steps": 79, "total_steps": 100, "loss": 0.0079, "lr": 1.2842758726130283e-05, "epoch": 3.8848484848484848, "percentage": 79.0, "elapsed_time": "0:26:18", "remaining_time": "0:06:59"}
|
| 95 |
+
{"current_steps": 80, "total_steps": 100, "loss": 0.0089, "lr": 1.1697777844051105e-05, "epoch": 3.9333333333333336, "percentage": 80.0, "elapsed_time": "0:26:36", "remaining_time": "0:06:39"}
|
| 96 |
+
{"current_steps": 80, "total_steps": 100, "eval_loss": 0.011956109665334225, "epoch": 3.9333333333333336, "percentage": 80.0, "elapsed_time": "0:26:47", "remaining_time": "0:06:41"}
|
| 97 |
+
{"current_steps": 81, "total_steps": 100, "loss": 0.013, "lr": 1.0599462319663905e-05, "epoch": 3.981818181818182, "percentage": 81.0, "elapsed_time": "0:27:03", "remaining_time": "0:06:20"}
|
| 98 |
+
{"current_steps": 82, "total_steps": 100, "loss": 0.0092, "lr": 9.549150281252633e-06, "epoch": 4.048484848484849, "percentage": 82.0, "elapsed_time": "0:27:21", "remaining_time": "0:06:00"}
|
| 99 |
+
{"current_steps": 83, "total_steps": 100, "loss": 0.0064, "lr": 8.548121372247918e-06, "epoch": 4.096969696969697, "percentage": 83.0, "elapsed_time": "0:27:39", "remaining_time": "0:05:39"}
|
| 100 |
+
{"current_steps": 84, "total_steps": 100, "loss": 0.0086, "lr": 7.597595192178702e-06, "epoch": 4.1454545454545455, "percentage": 84.0, "elapsed_time": "0:27:57", "remaining_time": "0:05:19"}
|
| 101 |
+
{"current_steps": 85, "total_steps": 100, "loss": 0.0074, "lr": 6.698729810778065e-06, "epoch": 4.193939393939394, "percentage": 85.0, "elapsed_time": "0:28:14", "remaining_time": "0:04:59"}
|
| 102 |
+
{"current_steps": 85, "total_steps": 100, "eval_loss": 0.011830544099211693, "epoch": 4.193939393939394, "percentage": 85.0, "elapsed_time": "0:28:24", "remaining_time": "0:05:00"}
|
| 103 |
+
{"current_steps": 86, "total_steps": 100, "loss": 0.009, "lr": 5.852620357053651e-06, "epoch": 4.242424242424242, "percentage": 86.0, "elapsed_time": "0:28:42", "remaining_time": "0:04:40"}
|
| 104 |
+
{"current_steps": 87, "total_steps": 100, "loss": 0.0074, "lr": 5.060297685041659e-06, "epoch": 4.290909090909091, "percentage": 87.0, "elapsed_time": "0:28:59", "remaining_time": "0:04:19"}
|
| 105 |
+
{"current_steps": 88, "total_steps": 100, "loss": 0.0094, "lr": 4.322727117869951e-06, "epoch": 4.33939393939394, "percentage": 88.0, "elapsed_time": "0:29:18", "remaining_time": "0:03:59"}
|
| 106 |
+
{"current_steps": 89, "total_steps": 100, "loss": 0.0084, "lr": 3.6408072716606346e-06, "epoch": 4.387878787878788, "percentage": 89.0, "elapsed_time": "0:29:35", "remaining_time": "0:03:39"}
|
| 107 |
+
{"current_steps": 90, "total_steps": 100, "loss": 0.0074, "lr": 3.0153689607045845e-06, "epoch": 4.4363636363636365, "percentage": 90.0, "elapsed_time": "0:29:53", "remaining_time": "0:03:19"}
|
| 108 |
+
{"current_steps": 90, "total_steps": 100, "eval_loss": 0.011814383789896965, "epoch": 4.4363636363636365, "percentage": 90.0, "elapsed_time": "0:30:03", "remaining_time": "0:03:20"}
|
| 109 |
+
{"current_steps": 91, "total_steps": 100, "loss": 0.0087, "lr": 2.4471741852423237e-06, "epoch": 4.484848484848484, "percentage": 91.0, "elapsed_time": "0:30:21", "remaining_time": "0:03:00"}
|
| 110 |
+
{"current_steps": 92, "total_steps": 100, "loss": 0.0073, "lr": 1.9369152030840556e-06, "epoch": 4.533333333333333, "percentage": 92.0, "elapsed_time": "0:30:38", "remaining_time": "0:02:39"}
|
| 111 |
+
{"current_steps": 93, "total_steps": 100, "loss": 0.0075, "lr": 1.4852136862001764e-06, "epoch": 4.581818181818182, "percentage": 93.0, "elapsed_time": "0:30:56", "remaining_time": "0:02:19"}
|
| 112 |
+
{"current_steps": 94, "total_steps": 100, "loss": 0.0071, "lr": 1.0926199633097157e-06, "epoch": 4.63030303030303, "percentage": 94.0, "elapsed_time": "0:31:13", "remaining_time": "0:01:59"}
|
| 113 |
+
{"current_steps": 95, "total_steps": 100, "loss": 0.0066, "lr": 7.596123493895991e-07, "epoch": 4.678787878787879, "percentage": 95.0, "elapsed_time": "0:31:31", "remaining_time": "0:01:39"}
|
| 114 |
+
{"current_steps": 95, "total_steps": 100, "eval_loss": 0.011838787235319614, "epoch": 4.678787878787879, "percentage": 95.0, "elapsed_time": "0:31:41", "remaining_time": "0:01:40"}
|
| 115 |
+
{"current_steps": 96, "total_steps": 100, "loss": 0.0063, "lr": 4.865965629214819e-07, "epoch": 4.7272727272727275, "percentage": 96.0, "elapsed_time": "0:31:59", "remaining_time": "0:01:19"}
|
| 116 |
+
{"current_steps": 97, "total_steps": 100, "loss": 0.0076, "lr": 2.7390523158633554e-07, "epoch": 4.775757575757575, "percentage": 97.0, "elapsed_time": "0:32:17", "remaining_time": "0:00:59"}
|
| 117 |
+
{"current_steps": 98, "total_steps": 100, "loss": 0.0103, "lr": 1.2179748700879012e-07, "epoch": 4.824242424242424, "percentage": 98.0, "elapsed_time": "0:32:35", "remaining_time": "0:00:39"}
|
| 118 |
+
{"current_steps": 99, "total_steps": 100, "loss": 0.0057, "lr": 3.04586490452119e-08, "epoch": 4.872727272727273, "percentage": 99.0, "elapsed_time": "0:32:52", "remaining_time": "0:00:19"}
|
| 119 |
+
{"current_steps": 100, "total_steps": 100, "loss": 0.0065, "lr": 0.0, "epoch": 4.921212121212121, "percentage": 100.0, "elapsed_time": "0:33:10", "remaining_time": "0:00:00"}
|
| 120 |
+
{"current_steps": 100, "total_steps": 100, "eval_loss": 0.011823242530226707, "epoch": 4.921212121212121, "percentage": 100.0, "elapsed_time": "0:33:20", "remaining_time": "0:00:00"}
|
| 121 |
+
{"current_steps": 100, "total_steps": 100, "epoch": 4.921212121212121, "percentage": 100.0, "elapsed_time": "0:33:27", "remaining_time": "0:00:00"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
trainer_state.json
CHANGED
|
@@ -1,1272 +1,885 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric": 0.
|
| 3 |
-
"best_model_checkpoint": "/home/paperspace/Data/models/relianceV2/llm3br256/checkpoint-
|
| 4 |
-
"epoch": 4.
|
| 5 |
"eval_steps": 5,
|
| 6 |
-
"global_step":
|
| 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.
|
| 13 |
-
"grad_norm": 0.
|
| 14 |
-
"learning_rate":
|
| 15 |
-
"loss": 0.
|
| 16 |
"step": 1
|
| 17 |
},
|
| 18 |
{
|
| 19 |
-
"epoch": 0.
|
| 20 |
-
"grad_norm": 0.
|
| 21 |
-
"learning_rate":
|
| 22 |
-
"loss": 0.
|
| 23 |
"step": 2
|
| 24 |
},
|
| 25 |
{
|
| 26 |
-
"epoch": 0.
|
| 27 |
-
"grad_norm": 0.
|
| 28 |
-
"learning_rate":
|
| 29 |
-
"loss": 0.
|
| 30 |
"step": 3
|
| 31 |
},
|
| 32 |
{
|
| 33 |
-
"epoch": 0.
|
| 34 |
-
"grad_norm": 0.
|
| 35 |
-
"learning_rate":
|
| 36 |
-
"loss": 0.
|
| 37 |
"step": 4
|
| 38 |
},
|
| 39 |
{
|
| 40 |
-
"epoch": 0.
|
| 41 |
-
"grad_norm": 0.
|
| 42 |
-
"learning_rate":
|
| 43 |
-
"loss": 0.
|
| 44 |
"step": 5
|
| 45 |
},
|
| 46 |
{
|
| 47 |
-
"epoch": 0.
|
| 48 |
-
"eval_loss": 0.
|
| 49 |
-
"eval_runtime":
|
| 50 |
-
"eval_samples_per_second":
|
| 51 |
-
"eval_steps_per_second":
|
| 52 |
"step": 5
|
| 53 |
},
|
| 54 |
{
|
| 55 |
-
"epoch": 0.
|
| 56 |
-
"grad_norm": 0.
|
| 57 |
-
"learning_rate":
|
| 58 |
-
"loss": 0.
|
| 59 |
"step": 6
|
| 60 |
},
|
| 61 |
{
|
| 62 |
-
"epoch": 0.
|
| 63 |
-
"grad_norm": 0.
|
| 64 |
-
"learning_rate":
|
| 65 |
-
"loss": 0.
|
| 66 |
"step": 7
|
| 67 |
},
|
| 68 |
{
|
| 69 |
-
"epoch": 0.
|
| 70 |
-
"grad_norm": 0.
|
| 71 |
-
"learning_rate":
|
| 72 |
-
"loss": 0.
|
| 73 |
"step": 8
|
| 74 |
},
|
| 75 |
{
|
| 76 |
-
"epoch": 0.
|
| 77 |
-
"grad_norm": 0.
|
| 78 |
-
"learning_rate":
|
| 79 |
-
"loss": 0.
|
| 80 |
"step": 9
|
| 81 |
},
|
| 82 |
{
|
| 83 |
-
"epoch": 0.
|
| 84 |
-
"grad_norm": 0.
|
| 85 |
-
"learning_rate":
|
| 86 |
-
"loss": 0.
|
| 87 |
"step": 10
|
| 88 |
},
|
| 89 |
{
|
| 90 |
-
"epoch": 0.
|
| 91 |
-
"eval_loss": 0.
|
| 92 |
-
"eval_runtime":
|
| 93 |
-
"eval_samples_per_second":
|
| 94 |
-
"eval_steps_per_second":
|
| 95 |
"step": 10
|
| 96 |
},
|
| 97 |
{
|
| 98 |
-
"epoch": 0.
|
| 99 |
-
"grad_norm": 0.
|
| 100 |
-
"learning_rate":
|
| 101 |
-
"loss": 0.
|
| 102 |
"step": 11
|
| 103 |
},
|
| 104 |
{
|
| 105 |
-
"epoch": 0.
|
| 106 |
-
"grad_norm": 0.
|
| 107 |
-
"learning_rate":
|
| 108 |
-
"loss": 0.
|
| 109 |
"step": 12
|
| 110 |
},
|
| 111 |
{
|
| 112 |
-
"epoch": 0.
|
| 113 |
-
"grad_norm": 0.
|
| 114 |
-
"learning_rate":
|
| 115 |
-
"loss": 0.
|
| 116 |
"step": 13
|
| 117 |
},
|
| 118 |
{
|
| 119 |
-
"epoch": 0.
|
| 120 |
-
"grad_norm": 0.
|
| 121 |
-
"learning_rate": 9.
|
| 122 |
-
"loss": 0.
|
| 123 |
"step": 14
|
| 124 |
},
|
| 125 |
{
|
| 126 |
-
"epoch": 0.
|
| 127 |
-
"grad_norm": 0.
|
| 128 |
-
"learning_rate":
|
| 129 |
-
"loss": 0.
|
| 130 |
"step": 15
|
| 131 |
},
|
| 132 |
{
|
| 133 |
-
"epoch": 0.
|
| 134 |
-
"eval_loss": 0.
|
| 135 |
-
"eval_runtime":
|
| 136 |
-
"eval_samples_per_second":
|
| 137 |
-
"eval_steps_per_second":
|
| 138 |
"step": 15
|
| 139 |
},
|
| 140 |
{
|
| 141 |
-
"epoch": 0.
|
| 142 |
-
"grad_norm": 0.
|
| 143 |
-
"learning_rate": 9.
|
| 144 |
-
"loss": 0.
|
| 145 |
"step": 16
|
| 146 |
},
|
| 147 |
{
|
| 148 |
-
"epoch": 0.
|
| 149 |
-
"grad_norm": 0.
|
| 150 |
-
"learning_rate": 9.
|
| 151 |
-
"loss": 0.
|
| 152 |
"step": 17
|
| 153 |
},
|
| 154 |
{
|
| 155 |
-
"epoch": 0.
|
| 156 |
-
"grad_norm": 0.
|
| 157 |
-
"learning_rate": 9.
|
| 158 |
-
"loss": 0.
|
| 159 |
"step": 18
|
| 160 |
},
|
| 161 |
{
|
| 162 |
-
"epoch": 0.
|
| 163 |
-
"grad_norm": 0.
|
| 164 |
-
"learning_rate": 9.
|
| 165 |
-
"loss": 0.
|
| 166 |
"step": 19
|
| 167 |
},
|
| 168 |
{
|
| 169 |
-
"epoch": 0.
|
| 170 |
-
"grad_norm": 0.
|
| 171 |
-
"learning_rate": 9.
|
| 172 |
-
"loss": 0.
|
| 173 |
"step": 20
|
| 174 |
},
|
| 175 |
{
|
| 176 |
-
"epoch": 0.
|
| 177 |
-
"eval_loss": 0.
|
| 178 |
-
"eval_runtime":
|
| 179 |
-
"eval_samples_per_second":
|
| 180 |
-
"eval_steps_per_second":
|
| 181 |
"step": 20
|
| 182 |
},
|
| 183 |
{
|
| 184 |
-
"epoch":
|
| 185 |
-
"grad_norm": 0.
|
| 186 |
-
"learning_rate": 9.
|
| 187 |
-
"loss": 0.
|
| 188 |
"step": 21
|
| 189 |
},
|
| 190 |
{
|
| 191 |
-
"epoch":
|
| 192 |
-
"grad_norm": 0.
|
| 193 |
-
"learning_rate": 9.
|
| 194 |
-
"loss": 0.
|
| 195 |
"step": 22
|
| 196 |
},
|
| 197 |
{
|
| 198 |
-
"epoch":
|
| 199 |
-
"grad_norm": 0.
|
| 200 |
-
"learning_rate": 9.
|
| 201 |
-
"loss": 0.
|
| 202 |
"step": 23
|
| 203 |
},
|
| 204 |
{
|
| 205 |
-
"epoch":
|
| 206 |
-
"grad_norm": 0.
|
| 207 |
-
"learning_rate": 9.
|
| 208 |
-
"loss": 0.
|
| 209 |
"step": 24
|
| 210 |
},
|
| 211 |
{
|
| 212 |
-
"epoch":
|
| 213 |
-
"grad_norm": 0.
|
| 214 |
-
"learning_rate": 9.
|
| 215 |
-
"loss": 0.
|
| 216 |
"step": 25
|
| 217 |
},
|
| 218 |
{
|
| 219 |
-
"epoch":
|
| 220 |
-
"eval_loss": 0.
|
| 221 |
-
"eval_runtime":
|
| 222 |
-
"eval_samples_per_second":
|
| 223 |
-
"eval_steps_per_second":
|
| 224 |
"step": 25
|
| 225 |
},
|
| 226 |
{
|
| 227 |
-
"epoch":
|
| 228 |
-
"grad_norm": 0.
|
| 229 |
-
"learning_rate": 9.
|
| 230 |
-
"loss": 0.
|
| 231 |
"step": 26
|
| 232 |
},
|
| 233 |
{
|
| 234 |
-
"epoch":
|
| 235 |
-
"grad_norm": 0.
|
| 236 |
-
"learning_rate": 9.
|
| 237 |
-
"loss": 0.
|
| 238 |
"step": 27
|
| 239 |
},
|
| 240 |
{
|
| 241 |
-
"epoch":
|
| 242 |
-
"grad_norm": 0.
|
| 243 |
-
"learning_rate": 9.
|
| 244 |
-
"loss": 0.
|
| 245 |
"step": 28
|
| 246 |
},
|
| 247 |
{
|
| 248 |
-
"epoch":
|
| 249 |
-
"grad_norm": 0.
|
| 250 |
-
"learning_rate":
|
| 251 |
-
"loss": 0.
|
| 252 |
"step": 29
|
| 253 |
},
|
| 254 |
{
|
| 255 |
-
"epoch": 1.
|
| 256 |
-
"grad_norm": 0.
|
| 257 |
-
"learning_rate":
|
| 258 |
-
"loss": 0.
|
| 259 |
"step": 30
|
| 260 |
},
|
| 261 |
{
|
| 262 |
-
"epoch": 1.
|
| 263 |
-
"eval_loss": 0.
|
| 264 |
-
"eval_runtime":
|
| 265 |
-
"eval_samples_per_second":
|
| 266 |
-
"eval_steps_per_second":
|
| 267 |
"step": 30
|
| 268 |
},
|
| 269 |
{
|
| 270 |
-
"epoch": 1.
|
| 271 |
-
"grad_norm": 0.
|
| 272 |
-
"learning_rate":
|
| 273 |
-
"loss": 0.
|
| 274 |
"step": 31
|
| 275 |
},
|
| 276 |
{
|
| 277 |
-
"epoch": 1.
|
| 278 |
-
"grad_norm": 0.
|
| 279 |
-
"learning_rate":
|
| 280 |
-
"loss": 0.
|
| 281 |
"step": 32
|
| 282 |
},
|
| 283 |
{
|
| 284 |
-
"epoch": 1.
|
| 285 |
-
"grad_norm": 0.
|
| 286 |
-
"learning_rate":
|
| 287 |
-
"loss": 0.
|
| 288 |
"step": 33
|
| 289 |
},
|
| 290 |
{
|
| 291 |
-
"epoch": 1.
|
| 292 |
-
"grad_norm": 0.
|
| 293 |
-
"learning_rate":
|
| 294 |
-
"loss": 0.
|
| 295 |
"step": 34
|
| 296 |
},
|
| 297 |
{
|
| 298 |
-
"epoch": 1.
|
| 299 |
-
"grad_norm": 0.
|
| 300 |
-
"learning_rate":
|
| 301 |
-
"loss": 0.
|
| 302 |
"step": 35
|
| 303 |
},
|
| 304 |
{
|
| 305 |
-
"epoch": 1.
|
| 306 |
-
"eval_loss": 0.
|
| 307 |
-
"eval_runtime":
|
| 308 |
-
"eval_samples_per_second":
|
| 309 |
-
"eval_steps_per_second":
|
| 310 |
"step": 35
|
| 311 |
},
|
| 312 |
{
|
| 313 |
-
"epoch": 1.
|
| 314 |
-
"grad_norm": 0.
|
| 315 |
-
"learning_rate":
|
| 316 |
-
"loss": 0.
|
| 317 |
"step": 36
|
| 318 |
},
|
| 319 |
{
|
| 320 |
-
"epoch": 1.
|
| 321 |
-
"grad_norm": 0.
|
| 322 |
-
"learning_rate":
|
| 323 |
-
"loss": 0.
|
| 324 |
"step": 37
|
| 325 |
},
|
| 326 |
{
|
| 327 |
-
"epoch": 1.
|
| 328 |
-
"grad_norm": 0.
|
| 329 |
-
"learning_rate":
|
| 330 |
-
"loss": 0.
|
| 331 |
"step": 38
|
| 332 |
},
|
| 333 |
{
|
| 334 |
-
"epoch": 1.
|
| 335 |
-
"grad_norm": 0.
|
| 336 |
-
"learning_rate":
|
| 337 |
-
"loss": 0.
|
| 338 |
"step": 39
|
| 339 |
},
|
| 340 |
{
|
| 341 |
-
"epoch": 1.
|
| 342 |
-
"grad_norm": 0.
|
| 343 |
-
"learning_rate":
|
| 344 |
-
"loss": 0.
|
| 345 |
"step": 40
|
| 346 |
},
|
| 347 |
{
|
| 348 |
-
"epoch": 1.
|
| 349 |
-
"eval_loss": 0.
|
| 350 |
-
"eval_runtime":
|
| 351 |
-
"eval_samples_per_second":
|
| 352 |
-
"eval_steps_per_second":
|
| 353 |
"step": 40
|
| 354 |
},
|
| 355 |
{
|
| 356 |
-
"epoch":
|
| 357 |
-
"grad_norm": 0.
|
| 358 |
-
"learning_rate":
|
| 359 |
-
"loss": 0.
|
| 360 |
"step": 41
|
| 361 |
},
|
| 362 |
{
|
| 363 |
-
"epoch":
|
| 364 |
-
"grad_norm": 0.
|
| 365 |
-
"learning_rate":
|
| 366 |
-
"loss": 0.
|
| 367 |
"step": 42
|
| 368 |
},
|
| 369 |
{
|
| 370 |
-
"epoch":
|
| 371 |
-
"grad_norm": 0.
|
| 372 |
-
"learning_rate":
|
| 373 |
-
"loss": 0.
|
| 374 |
"step": 43
|
| 375 |
},
|
| 376 |
{
|
| 377 |
-
"epoch":
|
| 378 |
-
"grad_norm": 0.
|
| 379 |
-
"learning_rate":
|
| 380 |
-
"loss": 0.
|
| 381 |
"step": 44
|
| 382 |
},
|
| 383 |
{
|
| 384 |
-
"epoch":
|
| 385 |
-
"grad_norm": 0.
|
| 386 |
-
"learning_rate":
|
| 387 |
-
"loss": 0.
|
| 388 |
"step": 45
|
| 389 |
},
|
| 390 |
{
|
| 391 |
-
"epoch":
|
| 392 |
-
"eval_loss": 0.
|
| 393 |
-
"eval_runtime":
|
| 394 |
-
"eval_samples_per_second":
|
| 395 |
-
"eval_steps_per_second":
|
| 396 |
"step": 45
|
| 397 |
},
|
| 398 |
{
|
| 399 |
-
"epoch":
|
| 400 |
-
"grad_norm": 0.
|
| 401 |
-
"learning_rate":
|
| 402 |
-
"loss": 0.
|
| 403 |
"step": 46
|
| 404 |
},
|
| 405 |
{
|
| 406 |
-
"epoch":
|
| 407 |
-
"grad_norm": 0.
|
| 408 |
-
"learning_rate":
|
| 409 |
-
"loss": 0.
|
| 410 |
"step": 47
|
| 411 |
},
|
| 412 |
{
|
| 413 |
-
"epoch":
|
| 414 |
-
"grad_norm": 0.
|
| 415 |
-
"learning_rate":
|
| 416 |
-
"loss": 0.
|
| 417 |
"step": 48
|
| 418 |
},
|
| 419 |
{
|
| 420 |
-
"epoch":
|
| 421 |
-
"grad_norm": 0.
|
| 422 |
-
"learning_rate":
|
| 423 |
-
"loss": 0.
|
| 424 |
"step": 49
|
| 425 |
},
|
| 426 |
{
|
| 427 |
-
"epoch":
|
| 428 |
-
"grad_norm": 0.
|
| 429 |
-
"learning_rate":
|
| 430 |
-
"loss": 0.
|
| 431 |
"step": 50
|
| 432 |
},
|
| 433 |
{
|
| 434 |
-
"epoch":
|
| 435 |
-
"eval_loss": 0.
|
| 436 |
-
"eval_runtime":
|
| 437 |
-
"eval_samples_per_second":
|
| 438 |
-
"eval_steps_per_second":
|
| 439 |
"step": 50
|
| 440 |
},
|
| 441 |
{
|
| 442 |
-
"epoch":
|
| 443 |
-
"grad_norm": 0.
|
| 444 |
-
"learning_rate":
|
| 445 |
-
"loss": 0.
|
| 446 |
"step": 51
|
| 447 |
},
|
| 448 |
{
|
| 449 |
-
"epoch":
|
| 450 |
-
"grad_norm": 0.
|
| 451 |
-
"learning_rate":
|
| 452 |
-
"loss": 0.
|
| 453 |
"step": 52
|
| 454 |
},
|
| 455 |
{
|
| 456 |
-
"epoch":
|
| 457 |
-
"grad_norm": 0.
|
| 458 |
-
"learning_rate":
|
| 459 |
-
"loss": 0.
|
| 460 |
"step": 53
|
| 461 |
},
|
| 462 |
{
|
| 463 |
-
"epoch":
|
| 464 |
-
"grad_norm": 0.
|
| 465 |
-
"learning_rate":
|
| 466 |
-
"loss": 0.
|
| 467 |
"step": 54
|
| 468 |
},
|
| 469 |
{
|
| 470 |
-
"epoch":
|
| 471 |
-
"grad_norm": 0.
|
| 472 |
-
"learning_rate":
|
| 473 |
-
"loss": 0.
|
| 474 |
"step": 55
|
| 475 |
},
|
| 476 |
{
|
| 477 |
-
"epoch":
|
| 478 |
-
"eval_loss": 0.
|
| 479 |
-
"eval_runtime":
|
| 480 |
-
"eval_samples_per_second":
|
| 481 |
-
"eval_steps_per_second":
|
| 482 |
"step": 55
|
| 483 |
},
|
| 484 |
{
|
| 485 |
-
"epoch":
|
| 486 |
-
"grad_norm": 0.
|
| 487 |
-
"learning_rate":
|
| 488 |
-
"loss": 0.
|
| 489 |
"step": 56
|
| 490 |
},
|
| 491 |
{
|
| 492 |
-
"epoch":
|
| 493 |
-
"grad_norm": 0.
|
| 494 |
-
"learning_rate":
|
| 495 |
-
"loss": 0.
|
| 496 |
"step": 57
|
| 497 |
},
|
| 498 |
{
|
| 499 |
-
"epoch":
|
| 500 |
-
"grad_norm": 0.
|
| 501 |
-
"learning_rate":
|
| 502 |
-
"loss": 0.
|
| 503 |
"step": 58
|
| 504 |
},
|
| 505 |
{
|
| 506 |
-
"epoch": 2.
|
| 507 |
-
"grad_norm": 0.
|
| 508 |
-
"learning_rate":
|
| 509 |
-
"loss": 0.
|
| 510 |
"step": 59
|
| 511 |
},
|
| 512 |
{
|
| 513 |
-
"epoch": 2.
|
| 514 |
-
"grad_norm": 0.
|
| 515 |
-
"learning_rate":
|
| 516 |
-
"loss": 0.
|
| 517 |
"step": 60
|
| 518 |
},
|
| 519 |
{
|
| 520 |
-
"epoch": 2.
|
| 521 |
-
"eval_loss": 0.
|
| 522 |
-
"eval_runtime":
|
| 523 |
-
"eval_samples_per_second":
|
| 524 |
-
"eval_steps_per_second":
|
| 525 |
"step": 60
|
| 526 |
},
|
| 527 |
{
|
| 528 |
-
"epoch":
|
| 529 |
-
"grad_norm": 0.
|
| 530 |
-
"learning_rate":
|
| 531 |
-
"loss": 0.
|
| 532 |
"step": 61
|
| 533 |
},
|
| 534 |
{
|
| 535 |
-
"epoch":
|
| 536 |
-
"grad_norm": 0.
|
| 537 |
-
"learning_rate":
|
| 538 |
-
"loss": 0.
|
| 539 |
"step": 62
|
| 540 |
},
|
| 541 |
{
|
| 542 |
-
"epoch":
|
| 543 |
-
"grad_norm": 0.
|
| 544 |
-
"learning_rate":
|
| 545 |
-
"loss": 0.
|
| 546 |
"step": 63
|
| 547 |
},
|
| 548 |
{
|
| 549 |
-
"epoch":
|
| 550 |
-
"grad_norm": 0.
|
| 551 |
-
"learning_rate":
|
| 552 |
-
"loss": 0.
|
| 553 |
"step": 64
|
| 554 |
},
|
| 555 |
{
|
| 556 |
-
"epoch":
|
| 557 |
-
"grad_norm": 0.
|
| 558 |
-
"learning_rate":
|
| 559 |
-
"loss": 0.
|
| 560 |
"step": 65
|
| 561 |
},
|
| 562 |
{
|
| 563 |
-
"epoch":
|
| 564 |
-
"eval_loss": 0.
|
| 565 |
-
"eval_runtime":
|
| 566 |
-
"eval_samples_per_second":
|
| 567 |
-
"eval_steps_per_second":
|
| 568 |
"step": 65
|
| 569 |
},
|
| 570 |
{
|
| 571 |
-
"epoch":
|
| 572 |
-
"grad_norm": 0.
|
| 573 |
-
"learning_rate":
|
| 574 |
-
"loss": 0.
|
| 575 |
"step": 66
|
| 576 |
},
|
| 577 |
{
|
| 578 |
-
"epoch":
|
| 579 |
-
"grad_norm": 0.
|
| 580 |
-
"learning_rate":
|
| 581 |
-
"loss": 0.
|
| 582 |
"step": 67
|
| 583 |
},
|
| 584 |
{
|
| 585 |
-
"epoch":
|
| 586 |
-
"grad_norm": 0.
|
| 587 |
-
"learning_rate":
|
| 588 |
-
"loss": 0.
|
| 589 |
"step": 68
|
| 590 |
},
|
| 591 |
{
|
| 592 |
-
"epoch":
|
| 593 |
-
"grad_norm": 0.
|
| 594 |
-
"learning_rate":
|
| 595 |
-
"loss": 0.
|
| 596 |
"step": 69
|
| 597 |
},
|
| 598 |
{
|
| 599 |
-
"epoch":
|
| 600 |
-
"grad_norm": 0.
|
| 601 |
-
"learning_rate":
|
| 602 |
-
"loss": 0.
|
| 603 |
"step": 70
|
| 604 |
},
|
| 605 |
{
|
| 606 |
-
"epoch":
|
| 607 |
-
"eval_loss": 0.
|
| 608 |
-
"eval_runtime":
|
| 609 |
-
"eval_samples_per_second":
|
| 610 |
-
"eval_steps_per_second":
|
| 611 |
"step": 70
|
| 612 |
},
|
| 613 |
{
|
| 614 |
-
"epoch":
|
| 615 |
-
"grad_norm": 0.
|
| 616 |
-
"learning_rate":
|
| 617 |
-
"loss": 0.
|
| 618 |
"step": 71
|
| 619 |
},
|
| 620 |
{
|
| 621 |
-
"epoch":
|
| 622 |
-
"grad_norm": 0.
|
| 623 |
-
"learning_rate":
|
| 624 |
-
"loss": 0.
|
| 625 |
"step": 72
|
| 626 |
},
|
| 627 |
{
|
| 628 |
-
"epoch":
|
| 629 |
-
"grad_norm": 0.
|
| 630 |
-
"learning_rate":
|
| 631 |
-
"loss": 0.
|
| 632 |
"step": 73
|
| 633 |
},
|
| 634 |
{
|
| 635 |
-
"epoch":
|
| 636 |
-
"grad_norm": 0.
|
| 637 |
-
"learning_rate":
|
| 638 |
-
"loss": 0.
|
| 639 |
"step": 74
|
| 640 |
},
|
| 641 |
{
|
| 642 |
-
"epoch":
|
| 643 |
-
"grad_norm": 0.
|
| 644 |
-
"learning_rate":
|
| 645 |
-
"loss": 0.
|
| 646 |
"step": 75
|
| 647 |
},
|
| 648 |
{
|
| 649 |
-
"epoch":
|
| 650 |
-
"eval_loss": 0.
|
| 651 |
-
"eval_runtime":
|
| 652 |
-
"eval_samples_per_second":
|
| 653 |
-
"eval_steps_per_second":
|
| 654 |
"step": 75
|
| 655 |
},
|
| 656 |
{
|
| 657 |
-
"epoch":
|
| 658 |
-
"grad_norm": 0.
|
| 659 |
-
"learning_rate":
|
| 660 |
-
"loss": 0.
|
| 661 |
"step": 76
|
| 662 |
},
|
| 663 |
{
|
| 664 |
-
"epoch":
|
| 665 |
-
"grad_norm": 0.
|
| 666 |
-
"learning_rate":
|
| 667 |
-
"loss": 0.
|
| 668 |
"step": 77
|
| 669 |
},
|
| 670 |
{
|
| 671 |
-
"epoch":
|
| 672 |
-
"grad_norm": 0.
|
| 673 |
-
"learning_rate":
|
| 674 |
-
"loss": 0.
|
| 675 |
"step": 78
|
| 676 |
},
|
| 677 |
{
|
| 678 |
-
"epoch":
|
| 679 |
-
"grad_norm": 0.
|
| 680 |
-
"learning_rate":
|
| 681 |
-
"loss": 0.
|
| 682 |
"step": 79
|
| 683 |
},
|
| 684 |
{
|
| 685 |
-
"epoch":
|
| 686 |
-
"grad_norm": 0.
|
| 687 |
-
"learning_rate":
|
| 688 |
-
"loss": 0.
|
| 689 |
"step": 80
|
| 690 |
},
|
| 691 |
{
|
| 692 |
-
"epoch":
|
| 693 |
-
"eval_loss": 0.
|
| 694 |
-
"eval_runtime":
|
| 695 |
-
"eval_samples_per_second":
|
| 696 |
-
"eval_steps_per_second":
|
| 697 |
"step": 80
|
| 698 |
},
|
| 699 |
{
|
| 700 |
-
"epoch":
|
| 701 |
-
"grad_norm": 0.
|
| 702 |
-
"learning_rate":
|
| 703 |
-
"loss": 0.
|
| 704 |
"step": 81
|
| 705 |
},
|
| 706 |
{
|
| 707 |
-
"epoch":
|
| 708 |
-
"grad_norm": 0.
|
| 709 |
-
"learning_rate":
|
| 710 |
-
"loss": 0.
|
| 711 |
"step": 82
|
| 712 |
},
|
| 713 |
{
|
| 714 |
-
"epoch":
|
| 715 |
-
"grad_norm": 0.
|
| 716 |
-
"learning_rate":
|
| 717 |
-
"loss": 0.
|
| 718 |
"step": 83
|
| 719 |
},
|
| 720 |
{
|
| 721 |
-
"epoch":
|
| 722 |
-
"grad_norm": 0.
|
| 723 |
-
"learning_rate":
|
| 724 |
-
"loss": 0.
|
| 725 |
"step": 84
|
| 726 |
},
|
| 727 |
{
|
| 728 |
-
"epoch":
|
| 729 |
-
"grad_norm": 0.
|
| 730 |
-
"learning_rate":
|
| 731 |
-
"loss": 0.
|
| 732 |
"step": 85
|
| 733 |
},
|
| 734 |
{
|
| 735 |
-
"epoch":
|
| 736 |
-
"eval_loss": 0.
|
| 737 |
-
"eval_runtime":
|
| 738 |
-
"eval_samples_per_second":
|
| 739 |
-
"eval_steps_per_second":
|
| 740 |
"step": 85
|
| 741 |
},
|
| 742 |
{
|
| 743 |
-
"epoch":
|
| 744 |
-
"grad_norm": 0.
|
| 745 |
-
"learning_rate":
|
| 746 |
-
"loss": 0.
|
| 747 |
"step": 86
|
| 748 |
},
|
| 749 |
{
|
| 750 |
-
"epoch":
|
| 751 |
-
"grad_norm": 0.
|
| 752 |
-
"learning_rate":
|
| 753 |
-
"loss": 0.
|
| 754 |
"step": 87
|
| 755 |
},
|
| 756 |
{
|
| 757 |
-
"epoch":
|
| 758 |
-
"grad_norm": 0.
|
| 759 |
-
"learning_rate": 4.
|
| 760 |
-
"loss": 0.
|
| 761 |
"step": 88
|
| 762 |
},
|
| 763 |
{
|
| 764 |
-
"epoch":
|
| 765 |
-
"grad_norm": 0.
|
| 766 |
-
"learning_rate": 3.
|
| 767 |
-
"loss": 0.
|
| 768 |
"step": 89
|
| 769 |
},
|
| 770 |
{
|
| 771 |
-
"epoch":
|
| 772 |
-
"grad_norm": 0.
|
| 773 |
-
"learning_rate": 3.
|
| 774 |
-
"loss": 0.
|
| 775 |
"step": 90
|
| 776 |
},
|
| 777 |
{
|
| 778 |
-
"epoch":
|
| 779 |
-
"eval_loss": 0.
|
| 780 |
-
"eval_runtime":
|
| 781 |
-
"eval_samples_per_second":
|
| 782 |
-
"eval_steps_per_second":
|
| 783 |
"step": 90
|
| 784 |
},
|
| 785 |
{
|
| 786 |
-
"epoch":
|
| 787 |
-
"grad_norm": 0.
|
| 788 |
-
"learning_rate":
|
| 789 |
-
"loss": 0.
|
| 790 |
"step": 91
|
| 791 |
},
|
| 792 |
{
|
| 793 |
-
"epoch":
|
| 794 |
-
"grad_norm": 0.
|
| 795 |
-
"learning_rate":
|
| 796 |
-
"loss": 0.
|
| 797 |
"step": 92
|
| 798 |
},
|
| 799 |
{
|
| 800 |
-
"epoch":
|
| 801 |
-
"grad_norm": 0.
|
| 802 |
-
"learning_rate":
|
| 803 |
-
"loss": 0.
|
| 804 |
"step": 93
|
| 805 |
},
|
| 806 |
{
|
| 807 |
-
"epoch":
|
| 808 |
-
"grad_norm": 0.
|
| 809 |
-
"learning_rate":
|
| 810 |
-
"loss": 0.
|
| 811 |
"step": 94
|
| 812 |
},
|
| 813 |
{
|
| 814 |
-
"epoch":
|
| 815 |
-
"grad_norm": 0.
|
| 816 |
-
"learning_rate":
|
| 817 |
-
"loss": 0.
|
| 818 |
"step": 95
|
| 819 |
},
|
| 820 |
{
|
| 821 |
-
"epoch":
|
| 822 |
-
"eval_loss": 0.
|
| 823 |
-
"eval_runtime":
|
| 824 |
-
"eval_samples_per_second": 4.
|
| 825 |
-
"eval_steps_per_second": 1.
|
| 826 |
"step": 95
|
| 827 |
},
|
| 828 |
{
|
| 829 |
-
"epoch":
|
| 830 |
-
"grad_norm": 0.
|
| 831 |
-
"learning_rate":
|
| 832 |
-
"loss": 0.
|
| 833 |
"step": 96
|
| 834 |
},
|
| 835 |
{
|
| 836 |
-
"epoch":
|
| 837 |
-
"grad_norm": 0.
|
| 838 |
-
"learning_rate":
|
| 839 |
"loss": 0.0076,
|
| 840 |
"step": 97
|
| 841 |
},
|
| 842 |
{
|
| 843 |
-
"epoch":
|
| 844 |
-
"grad_norm": 0.
|
| 845 |
-
"learning_rate":
|
| 846 |
-
"loss": 0.
|
| 847 |
"step": 98
|
| 848 |
},
|
| 849 |
{
|
| 850 |
-
"epoch":
|
| 851 |
-
"grad_norm": 0.
|
| 852 |
-
"learning_rate":
|
| 853 |
-
"loss": 0.
|
| 854 |
"step": 99
|
| 855 |
},
|
| 856 |
{
|
| 857 |
-
"epoch":
|
| 858 |
-
"grad_norm": 0.
|
| 859 |
-
"learning_rate":
|
| 860 |
-
"loss": 0.
|
| 861 |
"step": 100
|
| 862 |
},
|
| 863 |
{
|
| 864 |
-
"epoch":
|
| 865 |
-
"eval_loss": 0.
|
| 866 |
-
"eval_runtime":
|
| 867 |
-
"eval_samples_per_second":
|
| 868 |
-
"eval_steps_per_second": 1.
|
| 869 |
"step": 100
|
| 870 |
},
|
| 871 |
{
|
| 872 |
-
"epoch":
|
| 873 |
-
"
|
| 874 |
-
"
|
| 875 |
-
"
|
| 876 |
-
"
|
| 877 |
-
|
| 878 |
-
|
| 879 |
-
"epoch": 3.4871794871794872,
|
| 880 |
-
"grad_norm": 0.021239478141069412,
|
| 881 |
-
"learning_rate": 2.4652007309320498e-05,
|
| 882 |
-
"loss": 0.0064,
|
| 883 |
-
"step": 102
|
| 884 |
-
},
|
| 885 |
-
{
|
| 886 |
-
"epoch": 3.5213675213675213,
|
| 887 |
-
"grad_norm": 0.017512433230876923,
|
| 888 |
-
"learning_rate": 2.361798779469336e-05,
|
| 889 |
-
"loss": 0.0074,
|
| 890 |
-
"step": 103
|
| 891 |
-
},
|
| 892 |
-
{
|
| 893 |
-
"epoch": 3.5555555555555554,
|
| 894 |
-
"grad_norm": 0.018754741176962852,
|
| 895 |
-
"learning_rate": 2.259937463226651e-05,
|
| 896 |
-
"loss": 0.0063,
|
| 897 |
-
"step": 104
|
| 898 |
-
},
|
| 899 |
-
{
|
| 900 |
-
"epoch": 3.58974358974359,
|
| 901 |
-
"grad_norm": 0.019357949495315552,
|
| 902 |
-
"learning_rate": 2.1596762663442218e-05,
|
| 903 |
-
"loss": 0.0071,
|
| 904 |
-
"step": 105
|
| 905 |
-
},
|
| 906 |
-
{
|
| 907 |
-
"epoch": 3.58974358974359,
|
| 908 |
-
"eval_loss": 0.01076994277536869,
|
| 909 |
-
"eval_runtime": 9.7069,
|
| 910 |
-
"eval_samples_per_second": 5.151,
|
| 911 |
-
"eval_steps_per_second": 1.339,
|
| 912 |
-
"step": 105
|
| 913 |
-
},
|
| 914 |
-
{
|
| 915 |
-
"epoch": 3.623931623931624,
|
| 916 |
-
"grad_norm": 0.02121426723897457,
|
| 917 |
-
"learning_rate": 2.061073738537635e-05,
|
| 918 |
-
"loss": 0.0078,
|
| 919 |
-
"step": 106
|
| 920 |
-
},
|
| 921 |
-
{
|
| 922 |
-
"epoch": 3.658119658119658,
|
| 923 |
-
"grad_norm": 0.020560307428240776,
|
| 924 |
-
"learning_rate": 1.9641874609064443e-05,
|
| 925 |
-
"loss": 0.0079,
|
| 926 |
-
"step": 107
|
| 927 |
-
},
|
| 928 |
-
{
|
| 929 |
-
"epoch": 3.6923076923076925,
|
| 930 |
-
"grad_norm": 0.024254970252513885,
|
| 931 |
-
"learning_rate": 1.8690740123084316e-05,
|
| 932 |
-
"loss": 0.0067,
|
| 933 |
-
"step": 108
|
| 934 |
-
},
|
| 935 |
-
{
|
| 936 |
-
"epoch": 3.7264957264957266,
|
| 937 |
-
"grad_norm": 0.020139144733548164,
|
| 938 |
-
"learning_rate": 1.7757889363191483e-05,
|
| 939 |
-
"loss": 0.0066,
|
| 940 |
-
"step": 109
|
| 941 |
-
},
|
| 942 |
-
{
|
| 943 |
-
"epoch": 3.7606837606837606,
|
| 944 |
-
"grad_norm": 0.01883375644683838,
|
| 945 |
-
"learning_rate": 1.684386708796025e-05,
|
| 946 |
-
"loss": 0.006,
|
| 947 |
-
"step": 110
|
| 948 |
-
},
|
| 949 |
-
{
|
| 950 |
-
"epoch": 3.7606837606837606,
|
| 951 |
-
"eval_loss": 0.010681088082492352,
|
| 952 |
-
"eval_runtime": 9.7636,
|
| 953 |
-
"eval_samples_per_second": 5.121,
|
| 954 |
-
"eval_steps_per_second": 1.331,
|
| 955 |
-
"step": 110
|
| 956 |
-
},
|
| 957 |
-
{
|
| 958 |
-
"epoch": 3.7948717948717947,
|
| 959 |
-
"grad_norm": 0.017693698406219482,
|
| 960 |
-
"learning_rate": 1.5949207060660138e-05,
|
| 961 |
-
"loss": 0.0061,
|
| 962 |
-
"step": 111
|
| 963 |
-
},
|
| 964 |
-
{
|
| 965 |
-
"epoch": 3.8290598290598292,
|
| 966 |
-
"grad_norm": 0.020463695749640465,
|
| 967 |
-
"learning_rate": 1.5074431737553157e-05,
|
| 968 |
-
"loss": 0.0072,
|
| 969 |
-
"step": 112
|
| 970 |
-
},
|
| 971 |
-
{
|
| 972 |
-
"epoch": 3.8632478632478633,
|
| 973 |
-
"grad_norm": 0.020722465589642525,
|
| 974 |
-
"learning_rate": 1.422005196279395e-05,
|
| 975 |
-
"loss": 0.0091,
|
| 976 |
-
"step": 113
|
| 977 |
-
},
|
| 978 |
-
{
|
| 979 |
-
"epoch": 3.8974358974358974,
|
| 980 |
-
"grad_norm": 0.020328683778643608,
|
| 981 |
-
"learning_rate": 1.338656667011134e-05,
|
| 982 |
-
"loss": 0.0071,
|
| 983 |
-
"step": 114
|
| 984 |
-
},
|
| 985 |
-
{
|
| 986 |
-
"epoch": 3.931623931623932,
|
| 987 |
-
"grad_norm": 0.0204046331346035,
|
| 988 |
-
"learning_rate": 1.257446259144494e-05,
|
| 989 |
-
"loss": 0.0065,
|
| 990 |
-
"step": 115
|
| 991 |
-
},
|
| 992 |
-
{
|
| 993 |
-
"epoch": 3.931623931623932,
|
| 994 |
-
"eval_loss": 0.010614048689603806,
|
| 995 |
-
"eval_runtime": 9.7105,
|
| 996 |
-
"eval_samples_per_second": 5.149,
|
| 997 |
-
"eval_steps_per_second": 1.339,
|
| 998 |
-
"step": 115
|
| 999 |
-
},
|
| 1000 |
-
{
|
| 1001 |
-
"epoch": 3.965811965811966,
|
| 1002 |
-
"grad_norm": 0.018496442586183548,
|
| 1003 |
-
"learning_rate": 1.178421397270758e-05,
|
| 1004 |
-
"loss": 0.0059,
|
| 1005 |
-
"step": 116
|
| 1006 |
-
},
|
| 1007 |
-
{
|
| 1008 |
-
"epoch": 4.0,
|
| 1009 |
-
"grad_norm": 0.04243512079119682,
|
| 1010 |
-
"learning_rate": 1.1016282296838887e-05,
|
| 1011 |
-
"loss": 0.0121,
|
| 1012 |
-
"step": 117
|
| 1013 |
-
},
|
| 1014 |
-
{
|
| 1015 |
-
"epoch": 4.034188034188034,
|
| 1016 |
-
"grad_norm": 0.01636839285492897,
|
| 1017 |
-
"learning_rate": 1.0271116014312293e-05,
|
| 1018 |
-
"loss": 0.005,
|
| 1019 |
-
"step": 118
|
| 1020 |
-
},
|
| 1021 |
-
{
|
| 1022 |
-
"epoch": 4.068376068376068,
|
| 1023 |
-
"grad_norm": 0.016252394765615463,
|
| 1024 |
-
"learning_rate": 9.549150281252633e-06,
|
| 1025 |
-
"loss": 0.0053,
|
| 1026 |
-
"step": 119
|
| 1027 |
-
},
|
| 1028 |
-
{
|
| 1029 |
-
"epoch": 4.102564102564102,
|
| 1030 |
-
"grad_norm": 0.016149073839187622,
|
| 1031 |
-
"learning_rate": 8.850806705317183e-06,
|
| 1032 |
-
"loss": 0.0076,
|
| 1033 |
-
"step": 120
|
| 1034 |
-
},
|
| 1035 |
-
{
|
| 1036 |
-
"epoch": 4.102564102564102,
|
| 1037 |
-
"eval_loss": 0.010566945187747478,
|
| 1038 |
-
"eval_runtime": 9.7295,
|
| 1039 |
-
"eval_samples_per_second": 5.139,
|
| 1040 |
-
"eval_steps_per_second": 1.336,
|
| 1041 |
-
"step": 120
|
| 1042 |
-
},
|
| 1043 |
-
{
|
| 1044 |
-
"epoch": 4.136752136752137,
|
| 1045 |
-
"grad_norm": 0.01633269712328911,
|
| 1046 |
-
"learning_rate": 8.176493099488663e-06,
|
| 1047 |
-
"loss": 0.0072,
|
| 1048 |
-
"step": 121
|
| 1049 |
-
},
|
| 1050 |
-
{
|
| 1051 |
-
"epoch": 4.170940170940171,
|
| 1052 |
-
"grad_norm": 0.018178582191467285,
|
| 1053 |
-
"learning_rate": 7.526603243923957e-06,
|
| 1054 |
-
"loss": 0.0061,
|
| 1055 |
-
"step": 122
|
| 1056 |
-
},
|
| 1057 |
-
{
|
| 1058 |
-
"epoch": 4.205128205128205,
|
| 1059 |
-
"grad_norm": 0.017663611099123955,
|
| 1060 |
-
"learning_rate": 6.901516655997536e-06,
|
| 1061 |
-
"loss": 0.006,
|
| 1062 |
-
"step": 123
|
| 1063 |
-
},
|
| 1064 |
-
{
|
| 1065 |
-
"epoch": 4.239316239316239,
|
| 1066 |
-
"grad_norm": 0.01672632433474064,
|
| 1067 |
-
"learning_rate": 6.301598368674105e-06,
|
| 1068 |
-
"loss": 0.0059,
|
| 1069 |
-
"step": 124
|
| 1070 |
-
},
|
| 1071 |
-
{
|
| 1072 |
-
"epoch": 4.273504273504273,
|
| 1073 |
-
"grad_norm": 0.01625417172908783,
|
| 1074 |
-
"learning_rate": 5.727198717339511e-06,
|
| 1075 |
-
"loss": 0.0057,
|
| 1076 |
-
"step": 125
|
| 1077 |
-
},
|
| 1078 |
-
{
|
| 1079 |
-
"epoch": 4.273504273504273,
|
| 1080 |
-
"eval_loss": 0.010598141700029373,
|
| 1081 |
-
"eval_runtime": 9.7399,
|
| 1082 |
-
"eval_samples_per_second": 5.133,
|
| 1083 |
-
"eval_steps_per_second": 1.335,
|
| 1084 |
-
"step": 125
|
| 1085 |
-
},
|
| 1086 |
-
{
|
| 1087 |
-
"epoch": 4.3076923076923075,
|
| 1088 |
-
"grad_norm": 0.016820693388581276,
|
| 1089 |
-
"learning_rate": 5.178653135214812e-06,
|
| 1090 |
-
"loss": 0.0051,
|
| 1091 |
-
"step": 126
|
| 1092 |
-
},
|
| 1093 |
-
{
|
| 1094 |
-
"epoch": 4.3418803418803416,
|
| 1095 |
-
"grad_norm": 0.017715787515044212,
|
| 1096 |
-
"learning_rate": 4.65628195747273e-06,
|
| 1097 |
-
"loss": 0.0058,
|
| 1098 |
-
"step": 127
|
| 1099 |
-
},
|
| 1100 |
-
{
|
| 1101 |
-
"epoch": 4.3760683760683765,
|
| 1102 |
-
"grad_norm": 0.01836553029716015,
|
| 1103 |
-
"learning_rate": 4.16039023417088e-06,
|
| 1104 |
-
"loss": 0.0051,
|
| 1105 |
-
"step": 128
|
| 1106 |
-
},
|
| 1107 |
-
{
|
| 1108 |
-
"epoch": 4.410256410256411,
|
| 1109 |
-
"grad_norm": 0.02160499058663845,
|
| 1110 |
-
"learning_rate": 3.691267552111183e-06,
|
| 1111 |
-
"loss": 0.0054,
|
| 1112 |
-
"step": 129
|
| 1113 |
-
},
|
| 1114 |
-
{
|
| 1115 |
-
"epoch": 4.444444444444445,
|
| 1116 |
-
"grad_norm": 0.019846314564347267,
|
| 1117 |
-
"learning_rate": 3.249187865729264e-06,
|
| 1118 |
-
"loss": 0.0071,
|
| 1119 |
-
"step": 130
|
| 1120 |
-
},
|
| 1121 |
-
{
|
| 1122 |
-
"epoch": 4.444444444444445,
|
| 1123 |
-
"eval_loss": 0.010587843134999275,
|
| 1124 |
-
"eval_runtime": 9.707,
|
| 1125 |
-
"eval_samples_per_second": 5.151,
|
| 1126 |
-
"eval_steps_per_second": 1.339,
|
| 1127 |
-
"step": 130
|
| 1128 |
-
},
|
| 1129 |
-
{
|
| 1130 |
-
"epoch": 4.478632478632479,
|
| 1131 |
-
"grad_norm": 0.01771419309079647,
|
| 1132 |
-
"learning_rate": 2.8344093371128424e-06,
|
| 1133 |
-
"loss": 0.005,
|
| 1134 |
-
"step": 131
|
| 1135 |
-
},
|
| 1136 |
-
{
|
| 1137 |
-
"epoch": 4.512820512820513,
|
| 1138 |
-
"grad_norm": 0.015574207529425621,
|
| 1139 |
-
"learning_rate": 2.4471741852423237e-06,
|
| 1140 |
-
"loss": 0.0048,
|
| 1141 |
-
"step": 132
|
| 1142 |
-
},
|
| 1143 |
-
{
|
| 1144 |
-
"epoch": 4.547008547008547,
|
| 1145 |
-
"grad_norm": 0.01756260357797146,
|
| 1146 |
-
"learning_rate": 2.087708544541689e-06,
|
| 1147 |
-
"loss": 0.0047,
|
| 1148 |
-
"step": 133
|
| 1149 |
-
},
|
| 1150 |
-
{
|
| 1151 |
-
"epoch": 4.581196581196581,
|
| 1152 |
-
"grad_norm": 0.02206473983824253,
|
| 1153 |
-
"learning_rate": 1.7562223328224325e-06,
|
| 1154 |
-
"loss": 0.0053,
|
| 1155 |
-
"step": 134
|
| 1156 |
-
},
|
| 1157 |
-
{
|
| 1158 |
-
"epoch": 4.615384615384615,
|
| 1159 |
-
"grad_norm": 0.017151422798633575,
|
| 1160 |
-
"learning_rate": 1.4529091286973995e-06,
|
| 1161 |
-
"loss": 0.0055,
|
| 1162 |
-
"step": 135
|
| 1163 |
-
},
|
| 1164 |
-
{
|
| 1165 |
-
"epoch": 4.615384615384615,
|
| 1166 |
-
"eval_loss": 0.010594615712761879,
|
| 1167 |
-
"eval_runtime": 9.7136,
|
| 1168 |
-
"eval_samples_per_second": 5.147,
|
| 1169 |
-
"eval_steps_per_second": 1.338,
|
| 1170 |
-
"step": 135
|
| 1171 |
-
},
|
| 1172 |
-
{
|
| 1173 |
-
"epoch": 4.64957264957265,
|
| 1174 |
-
"grad_norm": 0.018389733508229256,
|
| 1175 |
-
"learning_rate": 1.1779460585363944e-06,
|
| 1176 |
-
"loss": 0.0053,
|
| 1177 |
-
"step": 136
|
| 1178 |
-
},
|
| 1179 |
-
{
|
| 1180 |
-
"epoch": 4.683760683760684,
|
| 1181 |
-
"grad_norm": 0.016087768599390984,
|
| 1182 |
-
"learning_rate": 9.314936930293283e-07,
|
| 1183 |
-
"loss": 0.0048,
|
| 1184 |
-
"step": 137
|
| 1185 |
-
},
|
| 1186 |
-
{
|
| 1187 |
-
"epoch": 4.717948717948718,
|
| 1188 |
-
"grad_norm": 0.019610892981290817,
|
| 1189 |
-
"learning_rate": 7.136959534174592e-07,
|
| 1190 |
-
"loss": 0.0056,
|
| 1191 |
-
"step": 138
|
| 1192 |
-
},
|
| 1193 |
-
{
|
| 1194 |
-
"epoch": 4.752136752136752,
|
| 1195 |
-
"grad_norm": 0.018921220675110817,
|
| 1196 |
-
"learning_rate": 5.246800274474439e-07,
|
| 1197 |
-
"loss": 0.0065,
|
| 1198 |
-
"step": 139
|
| 1199 |
-
},
|
| 1200 |
-
{
|
| 1201 |
-
"epoch": 4.786324786324786,
|
| 1202 |
-
"grad_norm": 0.020553983747959137,
|
| 1203 |
-
"learning_rate": 3.6455629509730136e-07,
|
| 1204 |
-
"loss": 0.0053,
|
| 1205 |
-
"step": 140
|
| 1206 |
-
},
|
| 1207 |
-
{
|
| 1208 |
-
"epoch": 4.786324786324786,
|
| 1209 |
-
"eval_loss": 0.010573416948318481,
|
| 1210 |
-
"eval_runtime": 9.7174,
|
| 1211 |
-
"eval_samples_per_second": 5.145,
|
| 1212 |
-
"eval_steps_per_second": 1.338,
|
| 1213 |
-
"step": 140
|
| 1214 |
-
},
|
| 1215 |
-
{
|
| 1216 |
-
"epoch": 4.82051282051282,
|
| 1217 |
-
"grad_norm": 0.015205741859972477,
|
| 1218 |
-
"learning_rate": 2.334182641175686e-07,
|
| 1219 |
-
"loss": 0.0038,
|
| 1220 |
-
"step": 141
|
| 1221 |
-
},
|
| 1222 |
-
{
|
| 1223 |
-
"epoch": 4.854700854700854,
|
| 1224 |
-
"grad_norm": 0.017062170431017876,
|
| 1225 |
-
"learning_rate": 1.3134251542544774e-07,
|
| 1226 |
-
"loss": 0.006,
|
| 1227 |
-
"step": 142
|
| 1228 |
-
},
|
| 1229 |
-
{
|
| 1230 |
-
"epoch": 4.888888888888889,
|
| 1231 |
-
"grad_norm": 0.01831440068781376,
|
| 1232 |
-
"learning_rate": 5.838865838366792e-08,
|
| 1233 |
-
"loss": 0.0063,
|
| 1234 |
-
"step": 143
|
| 1235 |
-
},
|
| 1236 |
-
{
|
| 1237 |
-
"epoch": 4.923076923076923,
|
| 1238 |
-
"grad_norm": 0.019888985902071,
|
| 1239 |
-
"learning_rate": 1.4599295990352924e-08,
|
| 1240 |
-
"loss": 0.0068,
|
| 1241 |
-
"step": 144
|
| 1242 |
-
},
|
| 1243 |
-
{
|
| 1244 |
-
"epoch": 4.957264957264957,
|
| 1245 |
-
"grad_norm": 0.01834353245794773,
|
| 1246 |
-
"learning_rate": 0.0,
|
| 1247 |
-
"loss": 0.0074,
|
| 1248 |
-
"step": 145
|
| 1249 |
-
},
|
| 1250 |
-
{
|
| 1251 |
-
"epoch": 4.957264957264957,
|
| 1252 |
-
"eval_loss": 0.010564341209828854,
|
| 1253 |
-
"eval_runtime": 9.7196,
|
| 1254 |
-
"eval_samples_per_second": 5.144,
|
| 1255 |
-
"eval_steps_per_second": 1.338,
|
| 1256 |
-
"step": 145
|
| 1257 |
-
},
|
| 1258 |
-
{
|
| 1259 |
-
"epoch": 4.957264957264957,
|
| 1260 |
-
"step": 145,
|
| 1261 |
-
"total_flos": 3.332736073022669e+17,
|
| 1262 |
-
"train_loss": 0.014139376566263621,
|
| 1263 |
-
"train_runtime": 4477.1315,
|
| 1264 |
-
"train_samples_per_second": 1.042,
|
| 1265 |
-
"train_steps_per_second": 0.032
|
| 1266 |
}
|
| 1267 |
],
|
| 1268 |
"logging_steps": 1,
|
| 1269 |
-
"max_steps":
|
| 1270 |
"num_input_tokens_seen": 0,
|
| 1271 |
"num_train_epochs": 5,
|
| 1272 |
"save_steps": 50,
|
|
@@ -1282,7 +895,7 @@
|
|
| 1282 |
"attributes": {}
|
| 1283 |
}
|
| 1284 |
},
|
| 1285 |
-
"total_flos":
|
| 1286 |
"train_batch_size": 4,
|
| 1287 |
"trial_name": null,
|
| 1288 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 0.011823242530226707,
|
| 3 |
+
"best_model_checkpoint": "/home/paperspace/Data/models/relianceV2/llm3br256/checkpoint-100",
|
| 4 |
+
"epoch": 4.921212121212121,
|
| 5 |
"eval_steps": 5,
|
| 6 |
+
"global_step": 100,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
+
"epoch": 0.048484848484848485,
|
| 13 |
+
"grad_norm": 0.13376639783382416,
|
| 14 |
+
"learning_rate": 1e-05,
|
| 15 |
+
"loss": 0.063,
|
| 16 |
"step": 1
|
| 17 |
},
|
| 18 |
{
|
| 19 |
+
"epoch": 0.09696969696969697,
|
| 20 |
+
"grad_norm": 0.12203846871852875,
|
| 21 |
+
"learning_rate": 2e-05,
|
| 22 |
+
"loss": 0.0607,
|
| 23 |
"step": 2
|
| 24 |
},
|
| 25 |
{
|
| 26 |
+
"epoch": 0.14545454545454545,
|
| 27 |
+
"grad_norm": 0.13988564908504486,
|
| 28 |
+
"learning_rate": 3e-05,
|
| 29 |
+
"loss": 0.0615,
|
| 30 |
"step": 3
|
| 31 |
},
|
| 32 |
{
|
| 33 |
+
"epoch": 0.19393939393939394,
|
| 34 |
+
"grad_norm": 0.10985743254423141,
|
| 35 |
+
"learning_rate": 4e-05,
|
| 36 |
+
"loss": 0.0504,
|
| 37 |
"step": 4
|
| 38 |
},
|
| 39 |
{
|
| 40 |
+
"epoch": 0.24242424242424243,
|
| 41 |
+
"grad_norm": 0.07405027747154236,
|
| 42 |
+
"learning_rate": 5e-05,
|
| 43 |
+
"loss": 0.0395,
|
| 44 |
"step": 5
|
| 45 |
},
|
| 46 |
{
|
| 47 |
+
"epoch": 0.24242424242424243,
|
| 48 |
+
"eval_loss": 0.04326783865690231,
|
| 49 |
+
"eval_runtime": 11.3564,
|
| 50 |
+
"eval_samples_per_second": 4.403,
|
| 51 |
+
"eval_steps_per_second": 1.145,
|
| 52 |
"step": 5
|
| 53 |
},
|
| 54 |
{
|
| 55 |
+
"epoch": 0.2909090909090909,
|
| 56 |
+
"grad_norm": 0.09203900396823883,
|
| 57 |
+
"learning_rate": 6e-05,
|
| 58 |
+
"loss": 0.0419,
|
| 59 |
"step": 6
|
| 60 |
},
|
| 61 |
{
|
| 62 |
+
"epoch": 0.3393939393939394,
|
| 63 |
+
"grad_norm": 0.07265866547822952,
|
| 64 |
+
"learning_rate": 7e-05,
|
| 65 |
+
"loss": 0.0381,
|
| 66 |
"step": 7
|
| 67 |
},
|
| 68 |
{
|
| 69 |
+
"epoch": 0.3878787878787879,
|
| 70 |
+
"grad_norm": 0.04461047425866127,
|
| 71 |
+
"learning_rate": 8e-05,
|
| 72 |
+
"loss": 0.0341,
|
| 73 |
"step": 8
|
| 74 |
},
|
| 75 |
{
|
| 76 |
+
"epoch": 0.43636363636363634,
|
| 77 |
+
"grad_norm": 0.04746266454458237,
|
| 78 |
+
"learning_rate": 9e-05,
|
| 79 |
+
"loss": 0.0345,
|
| 80 |
"step": 9
|
| 81 |
},
|
| 82 |
{
|
| 83 |
+
"epoch": 0.48484848484848486,
|
| 84 |
+
"grad_norm": 0.040007542818784714,
|
| 85 |
+
"learning_rate": 0.0001,
|
| 86 |
+
"loss": 0.0324,
|
| 87 |
"step": 10
|
| 88 |
},
|
| 89 |
{
|
| 90 |
+
"epoch": 0.48484848484848486,
|
| 91 |
+
"eval_loss": 0.03000650927424431,
|
| 92 |
+
"eval_runtime": 10.3489,
|
| 93 |
+
"eval_samples_per_second": 4.831,
|
| 94 |
+
"eval_steps_per_second": 1.256,
|
| 95 |
"step": 10
|
| 96 |
},
|
| 97 |
{
|
| 98 |
+
"epoch": 0.5333333333333333,
|
| 99 |
+
"grad_norm": 0.03799016401171684,
|
| 100 |
+
"learning_rate": 9.99695413509548e-05,
|
| 101 |
+
"loss": 0.0331,
|
| 102 |
"step": 11
|
| 103 |
},
|
| 104 |
{
|
| 105 |
+
"epoch": 0.5818181818181818,
|
| 106 |
+
"grad_norm": 0.03196106478571892,
|
| 107 |
+
"learning_rate": 9.987820251299122e-05,
|
| 108 |
+
"loss": 0.029,
|
| 109 |
"step": 12
|
| 110 |
},
|
| 111 |
{
|
| 112 |
+
"epoch": 0.6303030303030303,
|
| 113 |
+
"grad_norm": 0.027229588478803635,
|
| 114 |
+
"learning_rate": 9.972609476841367e-05,
|
| 115 |
+
"loss": 0.0257,
|
| 116 |
"step": 13
|
| 117 |
},
|
| 118 |
{
|
| 119 |
+
"epoch": 0.6787878787878788,
|
| 120 |
+
"grad_norm": 0.02768268622457981,
|
| 121 |
+
"learning_rate": 9.951340343707852e-05,
|
| 122 |
+
"loss": 0.0215,
|
| 123 |
"step": 14
|
| 124 |
},
|
| 125 |
{
|
| 126 |
+
"epoch": 0.7272727272727273,
|
| 127 |
+
"grad_norm": 0.032983552664518356,
|
| 128 |
+
"learning_rate": 9.924038765061042e-05,
|
| 129 |
+
"loss": 0.024,
|
| 130 |
"step": 15
|
| 131 |
},
|
| 132 |
{
|
| 133 |
+
"epoch": 0.7272727272727273,
|
| 134 |
+
"eval_loss": 0.024439169093966484,
|
| 135 |
+
"eval_runtime": 10.352,
|
| 136 |
+
"eval_samples_per_second": 4.83,
|
| 137 |
+
"eval_steps_per_second": 1.256,
|
| 138 |
"step": 15
|
| 139 |
},
|
| 140 |
{
|
| 141 |
+
"epoch": 0.7757575757575758,
|
| 142 |
+
"grad_norm": 0.03327898308634758,
|
| 143 |
+
"learning_rate": 9.890738003669029e-05,
|
| 144 |
+
"loss": 0.0321,
|
| 145 |
"step": 16
|
| 146 |
},
|
| 147 |
{
|
| 148 |
+
"epoch": 0.8242424242424242,
|
| 149 |
+
"grad_norm": 0.02506704442203045,
|
| 150 |
+
"learning_rate": 9.851478631379982e-05,
|
| 151 |
+
"loss": 0.0281,
|
| 152 |
"step": 17
|
| 153 |
},
|
| 154 |
{
|
| 155 |
+
"epoch": 0.8727272727272727,
|
| 156 |
+
"grad_norm": 0.023538140580058098,
|
| 157 |
+
"learning_rate": 9.806308479691595e-05,
|
| 158 |
+
"loss": 0.0202,
|
| 159 |
"step": 18
|
| 160 |
},
|
| 161 |
{
|
| 162 |
+
"epoch": 0.9212121212121213,
|
| 163 |
+
"grad_norm": 0.02581767924129963,
|
| 164 |
+
"learning_rate": 9.755282581475769e-05,
|
| 165 |
+
"loss": 0.0206,
|
| 166 |
"step": 19
|
| 167 |
},
|
| 168 |
{
|
| 169 |
+
"epoch": 0.9696969696969697,
|
| 170 |
+
"grad_norm": 0.021269701421260834,
|
| 171 |
+
"learning_rate": 9.698463103929542e-05,
|
| 172 |
+
"loss": 0.0189,
|
| 173 |
"step": 20
|
| 174 |
},
|
| 175 |
{
|
| 176 |
+
"epoch": 0.9696969696969697,
|
| 177 |
+
"eval_loss": 0.0212231557816267,
|
| 178 |
+
"eval_runtime": 10.4147,
|
| 179 |
+
"eval_samples_per_second": 4.801,
|
| 180 |
+
"eval_steps_per_second": 1.248,
|
| 181 |
"step": 20
|
| 182 |
},
|
| 183 |
{
|
| 184 |
+
"epoch": 1.0363636363636364,
|
| 185 |
+
"grad_norm": 0.037210095673799515,
|
| 186 |
+
"learning_rate": 9.635919272833938e-05,
|
| 187 |
+
"loss": 0.0317,
|
| 188 |
"step": 21
|
| 189 |
},
|
| 190 |
{
|
| 191 |
+
"epoch": 1.084848484848485,
|
| 192 |
+
"grad_norm": 0.02000698819756508,
|
| 193 |
+
"learning_rate": 9.567727288213005e-05,
|
| 194 |
+
"loss": 0.019,
|
| 195 |
"step": 22
|
| 196 |
},
|
| 197 |
{
|
| 198 |
+
"epoch": 1.1333333333333333,
|
| 199 |
+
"grad_norm": 0.020116321742534637,
|
| 200 |
+
"learning_rate": 9.493970231495835e-05,
|
| 201 |
+
"loss": 0.019,
|
| 202 |
"step": 23
|
| 203 |
},
|
| 204 |
{
|
| 205 |
+
"epoch": 1.1818181818181819,
|
| 206 |
+
"grad_norm": 0.022886989638209343,
|
| 207 |
+
"learning_rate": 9.414737964294636e-05,
|
| 208 |
+
"loss": 0.0181,
|
| 209 |
"step": 24
|
| 210 |
},
|
| 211 |
{
|
| 212 |
+
"epoch": 1.2303030303030302,
|
| 213 |
+
"grad_norm": 0.023031054064631462,
|
| 214 |
+
"learning_rate": 9.330127018922194e-05,
|
| 215 |
+
"loss": 0.0171,
|
| 216 |
"step": 25
|
| 217 |
},
|
| 218 |
{
|
| 219 |
+
"epoch": 1.2303030303030302,
|
| 220 |
+
"eval_loss": 0.019027845934033394,
|
| 221 |
+
"eval_runtime": 10.3362,
|
| 222 |
+
"eval_samples_per_second": 4.837,
|
| 223 |
+
"eval_steps_per_second": 1.258,
|
| 224 |
"step": 25
|
| 225 |
},
|
| 226 |
{
|
| 227 |
+
"epoch": 1.2787878787878788,
|
| 228 |
+
"grad_norm": 0.01873927377164364,
|
| 229 |
+
"learning_rate": 9.24024048078213e-05,
|
| 230 |
+
"loss": 0.0182,
|
| 231 |
"step": 26
|
| 232 |
},
|
| 233 |
{
|
| 234 |
+
"epoch": 1.3272727272727272,
|
| 235 |
+
"grad_norm": 0.018605511635541916,
|
| 236 |
+
"learning_rate": 9.145187862775209e-05,
|
| 237 |
+
"loss": 0.0163,
|
| 238 |
"step": 27
|
| 239 |
},
|
| 240 |
{
|
| 241 |
+
"epoch": 1.3757575757575757,
|
| 242 |
+
"grad_norm": 0.023363754153251648,
|
| 243 |
+
"learning_rate": 9.045084971874738e-05,
|
| 244 |
+
"loss": 0.0177,
|
| 245 |
"step": 28
|
| 246 |
},
|
| 247 |
{
|
| 248 |
+
"epoch": 1.4242424242424243,
|
| 249 |
+
"grad_norm": 0.017733635380864143,
|
| 250 |
+
"learning_rate": 8.940053768033609e-05,
|
| 251 |
+
"loss": 0.014,
|
| 252 |
"step": 29
|
| 253 |
},
|
| 254 |
{
|
| 255 |
+
"epoch": 1.4727272727272727,
|
| 256 |
+
"grad_norm": 0.0225802194327116,
|
| 257 |
+
"learning_rate": 8.83022221559489e-05,
|
| 258 |
+
"loss": 0.0146,
|
| 259 |
"step": 30
|
| 260 |
},
|
| 261 |
{
|
| 262 |
+
"epoch": 1.4727272727272727,
|
| 263 |
+
"eval_loss": 0.01733844168484211,
|
| 264 |
+
"eval_runtime": 10.3386,
|
| 265 |
+
"eval_samples_per_second": 4.836,
|
| 266 |
+
"eval_steps_per_second": 1.257,
|
| 267 |
"step": 30
|
| 268 |
},
|
| 269 |
{
|
| 270 |
+
"epoch": 1.5212121212121212,
|
| 271 |
+
"grad_norm": 0.018234577029943466,
|
| 272 |
+
"learning_rate": 8.715724127386972e-05,
|
| 273 |
+
"loss": 0.017,
|
| 274 |
"step": 31
|
| 275 |
},
|
| 276 |
{
|
| 277 |
+
"epoch": 1.5696969696969698,
|
| 278 |
+
"grad_norm": 0.024176109582185745,
|
| 279 |
+
"learning_rate": 8.596699001693255e-05,
|
| 280 |
+
"loss": 0.0155,
|
| 281 |
"step": 32
|
| 282 |
},
|
| 283 |
{
|
| 284 |
+
"epoch": 1.6181818181818182,
|
| 285 |
+
"grad_norm": 0.023358961567282677,
|
| 286 |
+
"learning_rate": 8.473291852294987e-05,
|
| 287 |
+
"loss": 0.0157,
|
| 288 |
"step": 33
|
| 289 |
},
|
| 290 |
{
|
| 291 |
+
"epoch": 1.6666666666666665,
|
| 292 |
+
"grad_norm": 0.025254715234041214,
|
| 293 |
+
"learning_rate": 8.345653031794292e-05,
|
| 294 |
+
"loss": 0.0167,
|
| 295 |
"step": 34
|
| 296 |
},
|
| 297 |
{
|
| 298 |
+
"epoch": 1.7151515151515153,
|
| 299 |
+
"grad_norm": 0.021989861503243446,
|
| 300 |
+
"learning_rate": 8.213938048432697e-05,
|
| 301 |
+
"loss": 0.0144,
|
| 302 |
"step": 35
|
| 303 |
},
|
| 304 |
{
|
| 305 |
+
"epoch": 1.7151515151515153,
|
| 306 |
+
"eval_loss": 0.016134196892380714,
|
| 307 |
+
"eval_runtime": 10.3976,
|
| 308 |
+
"eval_samples_per_second": 4.809,
|
| 309 |
+
"eval_steps_per_second": 1.25,
|
| 310 |
"step": 35
|
| 311 |
},
|
| 312 |
{
|
| 313 |
+
"epoch": 1.7636363636363637,
|
| 314 |
+
"grad_norm": 0.018357617780566216,
|
| 315 |
+
"learning_rate": 8.07830737662829e-05,
|
| 316 |
+
"loss": 0.0162,
|
| 317 |
"step": 36
|
| 318 |
},
|
| 319 |
{
|
| 320 |
+
"epoch": 1.812121212121212,
|
| 321 |
+
"grad_norm": 0.021665558218955994,
|
| 322 |
+
"learning_rate": 7.938926261462366e-05,
|
| 323 |
+
"loss": 0.0194,
|
| 324 |
"step": 37
|
| 325 |
},
|
| 326 |
{
|
| 327 |
+
"epoch": 1.8606060606060606,
|
| 328 |
+
"grad_norm": 0.020184990018606186,
|
| 329 |
+
"learning_rate": 7.795964517353735e-05,
|
| 330 |
+
"loss": 0.0154,
|
| 331 |
"step": 38
|
| 332 |
},
|
| 333 |
{
|
| 334 |
+
"epoch": 1.9090909090909092,
|
| 335 |
+
"grad_norm": 0.016307702288031578,
|
| 336 |
+
"learning_rate": 7.649596321166024e-05,
|
| 337 |
+
"loss": 0.0134,
|
| 338 |
"step": 39
|
| 339 |
},
|
| 340 |
{
|
| 341 |
+
"epoch": 1.9575757575757575,
|
| 342 |
+
"grad_norm": 0.01873622089624405,
|
| 343 |
+
"learning_rate": 7.500000000000001e-05,
|
| 344 |
+
"loss": 0.0104,
|
| 345 |
"step": 40
|
| 346 |
},
|
| 347 |
{
|
| 348 |
+
"epoch": 1.9575757575757575,
|
| 349 |
+
"eval_loss": 0.015456685796380043,
|
| 350 |
+
"eval_runtime": 10.3404,
|
| 351 |
+
"eval_samples_per_second": 4.835,
|
| 352 |
+
"eval_steps_per_second": 1.257,
|
| 353 |
"step": 40
|
| 354 |
},
|
| 355 |
{
|
| 356 |
+
"epoch": 2.0242424242424244,
|
| 357 |
+
"grad_norm": 0.03928119316697121,
|
| 358 |
+
"learning_rate": 7.347357813929454e-05,
|
| 359 |
+
"loss": 0.0277,
|
| 360 |
"step": 41
|
| 361 |
},
|
| 362 |
{
|
| 363 |
+
"epoch": 2.0727272727272728,
|
| 364 |
+
"grad_norm": 0.01585806906223297,
|
| 365 |
+
"learning_rate": 7.191855733945387e-05,
|
| 366 |
+
"loss": 0.012,
|
| 367 |
"step": 42
|
| 368 |
},
|
| 369 |
{
|
| 370 |
+
"epoch": 2.121212121212121,
|
| 371 |
+
"grad_norm": 0.022943127900362015,
|
| 372 |
+
"learning_rate": 7.033683215379002e-05,
|
| 373 |
+
"loss": 0.0147,
|
| 374 |
"step": 43
|
| 375 |
},
|
| 376 |
{
|
| 377 |
+
"epoch": 2.16969696969697,
|
| 378 |
+
"grad_norm": 0.022961463779211044,
|
| 379 |
+
"learning_rate": 6.873032967079561e-05,
|
| 380 |
+
"loss": 0.014,
|
| 381 |
"step": 44
|
| 382 |
},
|
| 383 |
{
|
| 384 |
+
"epoch": 2.2181818181818183,
|
| 385 |
+
"grad_norm": 0.017532989382743835,
|
| 386 |
+
"learning_rate": 6.710100716628344e-05,
|
| 387 |
+
"loss": 0.0143,
|
| 388 |
"step": 45
|
| 389 |
},
|
| 390 |
{
|
| 391 |
+
"epoch": 2.2181818181818183,
|
| 392 |
+
"eval_loss": 0.01516613457351923,
|
| 393 |
+
"eval_runtime": 10.3353,
|
| 394 |
+
"eval_samples_per_second": 4.838,
|
| 395 |
+
"eval_steps_per_second": 1.258,
|
| 396 |
"step": 45
|
| 397 |
},
|
| 398 |
{
|
| 399 |
+
"epoch": 2.2666666666666666,
|
| 400 |
+
"grad_norm": 0.026267599314451218,
|
| 401 |
+
"learning_rate": 6.545084971874738e-05,
|
| 402 |
+
"loss": 0.0126,
|
| 403 |
"step": 46
|
| 404 |
},
|
| 405 |
{
|
| 406 |
+
"epoch": 2.315151515151515,
|
| 407 |
+
"grad_norm": 0.024150898680090904,
|
| 408 |
+
"learning_rate": 6.378186779084995e-05,
|
| 409 |
+
"loss": 0.0118,
|
| 410 |
"step": 47
|
| 411 |
},
|
| 412 |
{
|
| 413 |
+
"epoch": 2.3636363636363638,
|
| 414 |
+
"grad_norm": 0.019730910658836365,
|
| 415 |
+
"learning_rate": 6.209609477998338e-05,
|
| 416 |
+
"loss": 0.0121,
|
| 417 |
"step": 48
|
| 418 |
},
|
| 419 |
{
|
| 420 |
+
"epoch": 2.412121212121212,
|
| 421 |
+
"grad_norm": 0.02562836930155754,
|
| 422 |
+
"learning_rate": 6.0395584540887963e-05,
|
| 423 |
+
"loss": 0.0096,
|
| 424 |
"step": 49
|
| 425 |
},
|
| 426 |
{
|
| 427 |
+
"epoch": 2.4606060606060605,
|
| 428 |
+
"grad_norm": 0.01951598934829235,
|
| 429 |
+
"learning_rate": 5.868240888334653e-05,
|
| 430 |
+
"loss": 0.0117,
|
| 431 |
"step": 50
|
| 432 |
},
|
| 433 |
{
|
| 434 |
+
"epoch": 2.4606060606060605,
|
| 435 |
+
"eval_loss": 0.014072530902922153,
|
| 436 |
+
"eval_runtime": 10.3868,
|
| 437 |
+
"eval_samples_per_second": 4.814,
|
| 438 |
+
"eval_steps_per_second": 1.252,
|
| 439 |
"step": 50
|
| 440 |
},
|
| 441 |
{
|
| 442 |
+
"epoch": 2.509090909090909,
|
| 443 |
+
"grad_norm": 0.02022629976272583,
|
| 444 |
+
"learning_rate": 5.695865504800327e-05,
|
| 445 |
+
"loss": 0.0139,
|
| 446 |
"step": 51
|
| 447 |
},
|
| 448 |
{
|
| 449 |
+
"epoch": 2.5575757575757576,
|
| 450 |
+
"grad_norm": 0.01750958524644375,
|
| 451 |
+
"learning_rate": 5.522642316338268e-05,
|
| 452 |
+
"loss": 0.0099,
|
| 453 |
"step": 52
|
| 454 |
},
|
| 455 |
{
|
| 456 |
+
"epoch": 2.606060606060606,
|
| 457 |
+
"grad_norm": 0.0212919432669878,
|
| 458 |
+
"learning_rate": 5.348782368720626e-05,
|
| 459 |
+
"loss": 0.013,
|
| 460 |
"step": 53
|
| 461 |
},
|
| 462 |
{
|
| 463 |
+
"epoch": 2.6545454545454543,
|
| 464 |
+
"grad_norm": 0.016065998002886772,
|
| 465 |
+
"learning_rate": 5.174497483512506e-05,
|
| 466 |
+
"loss": 0.0093,
|
| 467 |
"step": 54
|
| 468 |
},
|
| 469 |
{
|
| 470 |
+
"epoch": 2.703030303030303,
|
| 471 |
+
"grad_norm": 0.018324071541428566,
|
| 472 |
+
"learning_rate": 5e-05,
|
| 473 |
+
"loss": 0.015,
|
| 474 |
"step": 55
|
| 475 |
},
|
| 476 |
{
|
| 477 |
+
"epoch": 2.703030303030303,
|
| 478 |
+
"eval_loss": 0.013632840476930141,
|
| 479 |
+
"eval_runtime": 10.3292,
|
| 480 |
+
"eval_samples_per_second": 4.841,
|
| 481 |
+
"eval_steps_per_second": 1.259,
|
| 482 |
"step": 55
|
| 483 |
},
|
| 484 |
{
|
| 485 |
+
"epoch": 2.7515151515151515,
|
| 486 |
+
"grad_norm": 0.02191258780658245,
|
| 487 |
+
"learning_rate": 4.825502516487497e-05,
|
| 488 |
+
"loss": 0.0109,
|
| 489 |
"step": 56
|
| 490 |
},
|
| 491 |
{
|
| 492 |
+
"epoch": 2.8,
|
| 493 |
+
"grad_norm": 0.01748000457882881,
|
| 494 |
+
"learning_rate": 4.6512176312793736e-05,
|
| 495 |
+
"loss": 0.0104,
|
| 496 |
"step": 57
|
| 497 |
},
|
| 498 |
{
|
| 499 |
+
"epoch": 2.8484848484848486,
|
| 500 |
+
"grad_norm": 0.01487227063626051,
|
| 501 |
+
"learning_rate": 4.477357683661734e-05,
|
| 502 |
+
"loss": 0.0097,
|
| 503 |
"step": 58
|
| 504 |
},
|
| 505 |
{
|
| 506 |
+
"epoch": 2.896969696969697,
|
| 507 |
+
"grad_norm": 0.01992475800216198,
|
| 508 |
+
"learning_rate": 4.3041344951996746e-05,
|
| 509 |
+
"loss": 0.0108,
|
| 510 |
"step": 59
|
| 511 |
},
|
| 512 |
{
|
| 513 |
+
"epoch": 2.9454545454545453,
|
| 514 |
+
"grad_norm": 0.01630261354148388,
|
| 515 |
+
"learning_rate": 4.131759111665349e-05,
|
| 516 |
+
"loss": 0.0092,
|
| 517 |
"step": 60
|
| 518 |
},
|
| 519 |
{
|
| 520 |
+
"epoch": 2.9454545454545453,
|
| 521 |
+
"eval_loss": 0.013053460977971554,
|
| 522 |
+
"eval_runtime": 10.3658,
|
| 523 |
+
"eval_samples_per_second": 4.824,
|
| 524 |
+
"eval_steps_per_second": 1.254,
|
| 525 |
"step": 60
|
| 526 |
},
|
| 527 |
{
|
| 528 |
+
"epoch": 3.012121212121212,
|
| 529 |
+
"grad_norm": 0.03835081681609154,
|
| 530 |
+
"learning_rate": 3.960441545911204e-05,
|
| 531 |
+
"loss": 0.0172,
|
| 532 |
"step": 61
|
| 533 |
},
|
| 534 |
{
|
| 535 |
+
"epoch": 3.0606060606060606,
|
| 536 |
+
"grad_norm": 0.017339400947093964,
|
| 537 |
+
"learning_rate": 3.790390522001662e-05,
|
| 538 |
+
"loss": 0.008,
|
| 539 |
"step": 62
|
| 540 |
},
|
| 541 |
{
|
| 542 |
+
"epoch": 3.109090909090909,
|
| 543 |
+
"grad_norm": 0.01646747626364231,
|
| 544 |
+
"learning_rate": 3.6218132209150045e-05,
|
| 545 |
+
"loss": 0.0121,
|
| 546 |
"step": 63
|
| 547 |
},
|
| 548 |
{
|
| 549 |
+
"epoch": 3.1575757575757577,
|
| 550 |
+
"grad_norm": 0.01738414168357849,
|
| 551 |
+
"learning_rate": 3.4549150281252636e-05,
|
| 552 |
+
"loss": 0.008,
|
| 553 |
"step": 64
|
| 554 |
},
|
| 555 |
{
|
| 556 |
+
"epoch": 3.206060606060606,
|
| 557 |
+
"grad_norm": 0.022966962307691574,
|
| 558 |
+
"learning_rate": 3.289899283371657e-05,
|
| 559 |
+
"loss": 0.008,
|
| 560 |
"step": 65
|
| 561 |
},
|
| 562 |
{
|
| 563 |
+
"epoch": 3.206060606060606,
|
| 564 |
+
"eval_loss": 0.012713730335235596,
|
| 565 |
+
"eval_runtime": 10.3449,
|
| 566 |
+
"eval_samples_per_second": 4.833,
|
| 567 |
+
"eval_steps_per_second": 1.257,
|
| 568 |
"step": 65
|
| 569 |
},
|
| 570 |
{
|
| 571 |
+
"epoch": 3.2545454545454544,
|
| 572 |
+
"grad_norm": 0.01976313628256321,
|
| 573 |
+
"learning_rate": 3.12696703292044e-05,
|
| 574 |
+
"loss": 0.0096,
|
| 575 |
"step": 66
|
| 576 |
},
|
| 577 |
{
|
| 578 |
+
"epoch": 3.303030303030303,
|
| 579 |
+
"grad_norm": 0.015671931207180023,
|
| 580 |
+
"learning_rate": 2.9663167846209998e-05,
|
| 581 |
+
"loss": 0.0071,
|
| 582 |
"step": 67
|
| 583 |
},
|
| 584 |
{
|
| 585 |
+
"epoch": 3.3515151515151516,
|
| 586 |
+
"grad_norm": 0.02184975892305374,
|
| 587 |
+
"learning_rate": 2.8081442660546125e-05,
|
| 588 |
+
"loss": 0.0092,
|
| 589 |
"step": 68
|
| 590 |
},
|
| 591 |
{
|
| 592 |
+
"epoch": 3.4,
|
| 593 |
+
"grad_norm": 0.021975932642817497,
|
| 594 |
+
"learning_rate": 2.6526421860705473e-05,
|
| 595 |
+
"loss": 0.009,
|
| 596 |
"step": 69
|
| 597 |
},
|
| 598 |
{
|
| 599 |
+
"epoch": 3.4484848484848483,
|
| 600 |
+
"grad_norm": 0.02743859961628914,
|
| 601 |
+
"learning_rate": 2.500000000000001e-05,
|
| 602 |
+
"loss": 0.0109,
|
| 603 |
"step": 70
|
| 604 |
},
|
| 605 |
{
|
| 606 |
+
"epoch": 3.4484848484848483,
|
| 607 |
+
"eval_loss": 0.012468294240534306,
|
| 608 |
+
"eval_runtime": 10.3407,
|
| 609 |
+
"eval_samples_per_second": 4.835,
|
| 610 |
+
"eval_steps_per_second": 1.257,
|
| 611 |
"step": 70
|
| 612 |
},
|
| 613 |
{
|
| 614 |
+
"epoch": 3.496969696969697,
|
| 615 |
+
"grad_norm": 0.02249360829591751,
|
| 616 |
+
"learning_rate": 2.350403678833976e-05,
|
| 617 |
+
"loss": 0.0123,
|
| 618 |
"step": 71
|
| 619 |
},
|
| 620 |
{
|
| 621 |
+
"epoch": 3.5454545454545454,
|
| 622 |
+
"grad_norm": 0.019340503960847855,
|
| 623 |
+
"learning_rate": 2.2040354826462668e-05,
|
| 624 |
+
"loss": 0.0072,
|
| 625 |
"step": 72
|
| 626 |
},
|
| 627 |
{
|
| 628 |
+
"epoch": 3.5939393939393938,
|
| 629 |
+
"grad_norm": 0.017731212079524994,
|
| 630 |
+
"learning_rate": 2.061073738537635e-05,
|
| 631 |
+
"loss": 0.009,
|
| 632 |
"step": 73
|
| 633 |
},
|
| 634 |
{
|
| 635 |
+
"epoch": 3.6424242424242426,
|
| 636 |
+
"grad_norm": 0.017661720514297485,
|
| 637 |
+
"learning_rate": 1.9216926233717085e-05,
|
| 638 |
+
"loss": 0.0078,
|
| 639 |
"step": 74
|
| 640 |
},
|
| 641 |
{
|
| 642 |
+
"epoch": 3.690909090909091,
|
| 643 |
+
"grad_norm": 0.01668357476592064,
|
| 644 |
+
"learning_rate": 1.7860619515673033e-05,
|
| 645 |
+
"loss": 0.0085,
|
| 646 |
"step": 75
|
| 647 |
},
|
| 648 |
{
|
| 649 |
+
"epoch": 3.690909090909091,
|
| 650 |
+
"eval_loss": 0.012197648175060749,
|
| 651 |
+
"eval_runtime": 10.3397,
|
| 652 |
+
"eval_samples_per_second": 4.836,
|
| 653 |
+
"eval_steps_per_second": 1.257,
|
| 654 |
"step": 75
|
| 655 |
},
|
| 656 |
{
|
| 657 |
+
"epoch": 3.7393939393939393,
|
| 658 |
+
"grad_norm": 0.019251663237810135,
|
| 659 |
+
"learning_rate": 1.6543469682057106e-05,
|
| 660 |
+
"loss": 0.0089,
|
| 661 |
"step": 76
|
| 662 |
},
|
| 663 |
{
|
| 664 |
+
"epoch": 3.787878787878788,
|
| 665 |
+
"grad_norm": 0.018358884379267693,
|
| 666 |
+
"learning_rate": 1.526708147705013e-05,
|
| 667 |
+
"loss": 0.0127,
|
| 668 |
"step": 77
|
| 669 |
},
|
| 670 |
{
|
| 671 |
+
"epoch": 3.8363636363636364,
|
| 672 |
+
"grad_norm": 0.018658000975847244,
|
| 673 |
+
"learning_rate": 1.4033009983067452e-05,
|
| 674 |
+
"loss": 0.0085,
|
| 675 |
"step": 78
|
| 676 |
},
|
| 677 |
{
|
| 678 |
+
"epoch": 3.8848484848484848,
|
| 679 |
+
"grad_norm": 0.01768352836370468,
|
| 680 |
+
"learning_rate": 1.2842758726130283e-05,
|
| 681 |
+
"loss": 0.0079,
|
| 682 |
"step": 79
|
| 683 |
},
|
| 684 |
{
|
| 685 |
+
"epoch": 3.9333333333333336,
|
| 686 |
+
"grad_norm": 0.017675764858722687,
|
| 687 |
+
"learning_rate": 1.1697777844051105e-05,
|
| 688 |
+
"loss": 0.0089,
|
| 689 |
"step": 80
|
| 690 |
},
|
| 691 |
{
|
| 692 |
+
"epoch": 3.9333333333333336,
|
| 693 |
+
"eval_loss": 0.011956109665334225,
|
| 694 |
+
"eval_runtime": 10.3374,
|
| 695 |
+
"eval_samples_per_second": 4.837,
|
| 696 |
+
"eval_steps_per_second": 1.258,
|
| 697 |
"step": 80
|
| 698 |
},
|
| 699 |
{
|
| 700 |
+
"epoch": 3.981818181818182,
|
| 701 |
+
"grad_norm": 0.04371407628059387,
|
| 702 |
+
"learning_rate": 1.0599462319663905e-05,
|
| 703 |
+
"loss": 0.013,
|
| 704 |
"step": 81
|
| 705 |
},
|
| 706 |
{
|
| 707 |
+
"epoch": 4.048484848484849,
|
| 708 |
+
"grad_norm": 0.01942707970738411,
|
| 709 |
+
"learning_rate": 9.549150281252633e-06,
|
| 710 |
+
"loss": 0.0092,
|
| 711 |
"step": 82
|
| 712 |
},
|
| 713 |
{
|
| 714 |
+
"epoch": 4.096969696969697,
|
| 715 |
+
"grad_norm": 0.014996436424553394,
|
| 716 |
+
"learning_rate": 8.548121372247918e-06,
|
| 717 |
+
"loss": 0.0064,
|
| 718 |
"step": 83
|
| 719 |
},
|
| 720 |
{
|
| 721 |
+
"epoch": 4.1454545454545455,
|
| 722 |
+
"grad_norm": 0.01869269274175167,
|
| 723 |
+
"learning_rate": 7.597595192178702e-06,
|
| 724 |
+
"loss": 0.0086,
|
| 725 |
"step": 84
|
| 726 |
},
|
| 727 |
{
|
| 728 |
+
"epoch": 4.193939393939394,
|
| 729 |
+
"grad_norm": 0.017618168145418167,
|
| 730 |
+
"learning_rate": 6.698729810778065e-06,
|
| 731 |
+
"loss": 0.0074,
|
| 732 |
"step": 85
|
| 733 |
},
|
| 734 |
{
|
| 735 |
+
"epoch": 4.193939393939394,
|
| 736 |
+
"eval_loss": 0.011830544099211693,
|
| 737 |
+
"eval_runtime": 10.3339,
|
| 738 |
+
"eval_samples_per_second": 4.838,
|
| 739 |
+
"eval_steps_per_second": 1.258,
|
| 740 |
"step": 85
|
| 741 |
},
|
| 742 |
{
|
| 743 |
+
"epoch": 4.242424242424242,
|
| 744 |
+
"grad_norm": 0.016551963984966278,
|
| 745 |
+
"learning_rate": 5.852620357053651e-06,
|
| 746 |
+
"loss": 0.009,
|
| 747 |
"step": 86
|
| 748 |
},
|
| 749 |
{
|
| 750 |
+
"epoch": 4.290909090909091,
|
| 751 |
+
"grad_norm": 0.01904563419520855,
|
| 752 |
+
"learning_rate": 5.060297685041659e-06,
|
| 753 |
+
"loss": 0.0074,
|
| 754 |
"step": 87
|
| 755 |
},
|
| 756 |
{
|
| 757 |
+
"epoch": 4.33939393939394,
|
| 758 |
+
"grad_norm": 0.02098240703344345,
|
| 759 |
+
"learning_rate": 4.322727117869951e-06,
|
| 760 |
+
"loss": 0.0094,
|
| 761 |
"step": 88
|
| 762 |
},
|
| 763 |
{
|
| 764 |
+
"epoch": 4.387878787878788,
|
| 765 |
+
"grad_norm": 0.015075408853590488,
|
| 766 |
+
"learning_rate": 3.6408072716606346e-06,
|
| 767 |
+
"loss": 0.0084,
|
| 768 |
"step": 89
|
| 769 |
},
|
| 770 |
{
|
| 771 |
+
"epoch": 4.4363636363636365,
|
| 772 |
+
"grad_norm": 0.016622379422187805,
|
| 773 |
+
"learning_rate": 3.0153689607045845e-06,
|
| 774 |
+
"loss": 0.0074,
|
| 775 |
"step": 90
|
| 776 |
},
|
| 777 |
{
|
| 778 |
+
"epoch": 4.4363636363636365,
|
| 779 |
+
"eval_loss": 0.011814383789896965,
|
| 780 |
+
"eval_runtime": 10.356,
|
| 781 |
+
"eval_samples_per_second": 4.828,
|
| 782 |
+
"eval_steps_per_second": 1.255,
|
| 783 |
"step": 90
|
| 784 |
},
|
| 785 |
{
|
| 786 |
+
"epoch": 4.484848484848484,
|
| 787 |
+
"grad_norm": 0.017493437975645065,
|
| 788 |
+
"learning_rate": 2.4471741852423237e-06,
|
| 789 |
+
"loss": 0.0087,
|
| 790 |
"step": 91
|
| 791 |
},
|
| 792 |
{
|
| 793 |
+
"epoch": 4.533333333333333,
|
| 794 |
+
"grad_norm": 0.01581619866192341,
|
| 795 |
+
"learning_rate": 1.9369152030840556e-06,
|
| 796 |
+
"loss": 0.0073,
|
| 797 |
"step": 92
|
| 798 |
},
|
| 799 |
{
|
| 800 |
+
"epoch": 4.581818181818182,
|
| 801 |
+
"grad_norm": 0.020205620676279068,
|
| 802 |
+
"learning_rate": 1.4852136862001764e-06,
|
| 803 |
+
"loss": 0.0075,
|
| 804 |
"step": 93
|
| 805 |
},
|
| 806 |
{
|
| 807 |
+
"epoch": 4.63030303030303,
|
| 808 |
+
"grad_norm": 0.016090713441371918,
|
| 809 |
+
"learning_rate": 1.0926199633097157e-06,
|
| 810 |
+
"loss": 0.0071,
|
| 811 |
"step": 94
|
| 812 |
},
|
| 813 |
{
|
| 814 |
+
"epoch": 4.678787878787879,
|
| 815 |
+
"grad_norm": 0.014329814352095127,
|
| 816 |
+
"learning_rate": 7.596123493895991e-07,
|
| 817 |
+
"loss": 0.0066,
|
| 818 |
"step": 95
|
| 819 |
},
|
| 820 |
{
|
| 821 |
+
"epoch": 4.678787878787879,
|
| 822 |
+
"eval_loss": 0.011838787235319614,
|
| 823 |
+
"eval_runtime": 10.3353,
|
| 824 |
+
"eval_samples_per_second": 4.838,
|
| 825 |
+
"eval_steps_per_second": 1.258,
|
| 826 |
"step": 95
|
| 827 |
},
|
| 828 |
{
|
| 829 |
+
"epoch": 4.7272727272727275,
|
| 830 |
+
"grad_norm": 0.015449507161974907,
|
| 831 |
+
"learning_rate": 4.865965629214819e-07,
|
| 832 |
+
"loss": 0.0063,
|
| 833 |
"step": 96
|
| 834 |
},
|
| 835 |
{
|
| 836 |
+
"epoch": 4.775757575757575,
|
| 837 |
+
"grad_norm": 0.016315339133143425,
|
| 838 |
+
"learning_rate": 2.7390523158633554e-07,
|
| 839 |
"loss": 0.0076,
|
| 840 |
"step": 97
|
| 841 |
},
|
| 842 |
{
|
| 843 |
+
"epoch": 4.824242424242424,
|
| 844 |
+
"grad_norm": 0.018415048718452454,
|
| 845 |
+
"learning_rate": 1.2179748700879012e-07,
|
| 846 |
+
"loss": 0.0103,
|
| 847 |
"step": 98
|
| 848 |
},
|
| 849 |
{
|
| 850 |
+
"epoch": 4.872727272727273,
|
| 851 |
+
"grad_norm": 0.014639717526733875,
|
| 852 |
+
"learning_rate": 3.04586490452119e-08,
|
| 853 |
+
"loss": 0.0057,
|
| 854 |
"step": 99
|
| 855 |
},
|
| 856 |
{
|
| 857 |
+
"epoch": 4.921212121212121,
|
| 858 |
+
"grad_norm": 0.018388710916042328,
|
| 859 |
+
"learning_rate": 0.0,
|
| 860 |
+
"loss": 0.0065,
|
| 861 |
"step": 100
|
| 862 |
},
|
| 863 |
{
|
| 864 |
+
"epoch": 4.921212121212121,
|
| 865 |
+
"eval_loss": 0.011823242530226707,
|
| 866 |
+
"eval_runtime": 10.3329,
|
| 867 |
+
"eval_samples_per_second": 4.839,
|
| 868 |
+
"eval_steps_per_second": 1.258,
|
| 869 |
"step": 100
|
| 870 |
},
|
| 871 |
{
|
| 872 |
+
"epoch": 4.921212121212121,
|
| 873 |
+
"step": 100,
|
| 874 |
+
"total_flos": 2.442632501894185e+17,
|
| 875 |
+
"train_loss": 0.016519791511818767,
|
| 876 |
+
"train_runtime": 2009.2463,
|
| 877 |
+
"train_samples_per_second": 1.637,
|
| 878 |
+
"train_steps_per_second": 0.05
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 879 |
}
|
| 880 |
],
|
| 881 |
"logging_steps": 1,
|
| 882 |
+
"max_steps": 100,
|
| 883 |
"num_input_tokens_seen": 0,
|
| 884 |
"num_train_epochs": 5,
|
| 885 |
"save_steps": 50,
|
|
|
|
| 895 |
"attributes": {}
|
| 896 |
}
|
| 897 |
},
|
| 898 |
+
"total_flos": 2.442632501894185e+17,
|
| 899 |
"train_batch_size": 4,
|
| 900 |
"trial_name": null,
|
| 901 |
"trial_params": null
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 5432
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f7621cfdd62b7b103ef94ad34fb8774ce9010f461047b0d903b32f12aae5046f
|
| 3 |
size 5432
|
training_eval_loss.png
CHANGED
|
|
training_loss.png
CHANGED
|
|