Commit
·
150e2df
1
Parent(s):
66397bb
Upload folder using huggingface_hub
Browse files- README.md +204 -0
- adapter_config.json +29 -0
- optimizer.pt +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- trainer_state.json +2483 -0
- training_args.bin +3 -0
README.md
ADDED
|
@@ -0,0 +1,204 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: peft
|
| 3 |
+
base_model: Salesforce/codegen-350M-mono
|
| 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 |
+
|
| 201 |
+
|
| 202 |
+
### Framework versions
|
| 203 |
+
|
| 204 |
+
- PEFT 0.7.1
|
adapter_config.json
ADDED
|
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "Salesforce/codegen-350M-mono",
|
| 5 |
+
"bias": "all",
|
| 6 |
+
"fan_in_fan_out": false,
|
| 7 |
+
"inference_mode": true,
|
| 8 |
+
"init_lora_weights": true,
|
| 9 |
+
"layers_pattern": null,
|
| 10 |
+
"layers_to_transform": null,
|
| 11 |
+
"loftq_config": {},
|
| 12 |
+
"lora_alpha": 128,
|
| 13 |
+
"lora_dropout": 0.05,
|
| 14 |
+
"megatron_config": null,
|
| 15 |
+
"megatron_core": "megatron.core",
|
| 16 |
+
"modules_to_save": null,
|
| 17 |
+
"peft_type": "LORA",
|
| 18 |
+
"r": 64,
|
| 19 |
+
"rank_pattern": {},
|
| 20 |
+
"revision": null,
|
| 21 |
+
"target_modules": [
|
| 22 |
+
"fc_out",
|
| 23 |
+
"qkv_proj",
|
| 24 |
+
"lm_head",
|
| 25 |
+
"out_proj",
|
| 26 |
+
"fc_in"
|
| 27 |
+
],
|
| 28 |
+
"task_type": "CAUSAL_LM"
|
| 29 |
+
}
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:13e53dd1b6bf9b97fa8657fe76f43c33b02003925b116dac3f71ef422dbb1f83
|
| 3 |
+
size 196099770
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a8f037b1bc0d160d86fab5da09aa2dd8683f9e916a04e84a2669baeda6833cce
|
| 3 |
+
size 14244
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3eb2314d3932639e8b7bcafd8f07745559d4397334d657a32bf5310d54057bee
|
| 3 |
+
size 1064
|
trainer_state.json
ADDED
|
@@ -0,0 +1,2483 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.04,
|
| 5 |
+
"eval_steps": 50,
|
| 6 |
+
"global_step": 400,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.0,
|
| 13 |
+
"learning_rate": 5.000000000000001e-07,
|
| 14 |
+
"loss": 1.424,
|
| 15 |
+
"step": 1
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.0,
|
| 19 |
+
"learning_rate": 1.0000000000000002e-06,
|
| 20 |
+
"loss": 0.9593,
|
| 21 |
+
"step": 2
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.0,
|
| 25 |
+
"learning_rate": 1.5e-06,
|
| 26 |
+
"loss": 0.8636,
|
| 27 |
+
"step": 3
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 0.0,
|
| 31 |
+
"learning_rate": 2.0000000000000003e-06,
|
| 32 |
+
"loss": 1.0751,
|
| 33 |
+
"step": 4
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 0.0,
|
| 37 |
+
"learning_rate": 2.5e-06,
|
| 38 |
+
"loss": 1.0284,
|
| 39 |
+
"step": 5
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.0,
|
| 43 |
+
"learning_rate": 3e-06,
|
| 44 |
+
"loss": 1.0424,
|
| 45 |
+
"step": 6
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.0,
|
| 49 |
+
"learning_rate": 3.5000000000000004e-06,
|
| 50 |
+
"loss": 1.154,
|
| 51 |
+
"step": 7
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.0,
|
| 55 |
+
"learning_rate": 4.000000000000001e-06,
|
| 56 |
+
"loss": 1.4715,
|
| 57 |
+
"step": 8
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 0.0,
|
| 61 |
+
"learning_rate": 4.5e-06,
|
| 62 |
+
"loss": 1.5074,
|
| 63 |
+
"step": 9
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 0.0,
|
| 67 |
+
"learning_rate": 5e-06,
|
| 68 |
+
"loss": 0.9633,
|
| 69 |
+
"step": 10
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 0.0,
|
| 73 |
+
"learning_rate": 5.500000000000001e-06,
|
| 74 |
+
"loss": 0.7885,
|
| 75 |
+
"step": 11
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 0.0,
|
| 79 |
+
"learning_rate": 6e-06,
|
| 80 |
+
"loss": 0.9121,
|
| 81 |
+
"step": 12
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 0.0,
|
| 85 |
+
"learning_rate": 6.5000000000000004e-06,
|
| 86 |
+
"loss": 1.0456,
|
| 87 |
+
"step": 13
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.0,
|
| 91 |
+
"learning_rate": 7.000000000000001e-06,
|
| 92 |
+
"loss": 0.8722,
|
| 93 |
+
"step": 14
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.0,
|
| 97 |
+
"learning_rate": 7.5e-06,
|
| 98 |
+
"loss": 1.0264,
|
| 99 |
+
"step": 15
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 0.0,
|
| 103 |
+
"learning_rate": 8.000000000000001e-06,
|
| 104 |
+
"loss": 1.2709,
|
| 105 |
+
"step": 16
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 0.0,
|
| 109 |
+
"learning_rate": 8.500000000000002e-06,
|
| 110 |
+
"loss": 1.1519,
|
| 111 |
+
"step": 17
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 0.0,
|
| 115 |
+
"learning_rate": 9e-06,
|
| 116 |
+
"loss": 0.9543,
|
| 117 |
+
"step": 18
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 0.0,
|
| 121 |
+
"learning_rate": 9.5e-06,
|
| 122 |
+
"loss": 0.7449,
|
| 123 |
+
"step": 19
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 0.0,
|
| 127 |
+
"learning_rate": 1e-05,
|
| 128 |
+
"loss": 1.0338,
|
| 129 |
+
"step": 20
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.0,
|
| 133 |
+
"learning_rate": 1.05e-05,
|
| 134 |
+
"loss": 1.3037,
|
| 135 |
+
"step": 21
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.0,
|
| 139 |
+
"learning_rate": 1.1000000000000001e-05,
|
| 140 |
+
"loss": 1.0368,
|
| 141 |
+
"step": 22
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 0.0,
|
| 145 |
+
"learning_rate": 1.1500000000000002e-05,
|
| 146 |
+
"loss": 1.076,
|
| 147 |
+
"step": 23
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 0.0,
|
| 151 |
+
"learning_rate": 1.2e-05,
|
| 152 |
+
"loss": 1.4172,
|
| 153 |
+
"step": 24
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 0.0,
|
| 157 |
+
"learning_rate": 1.25e-05,
|
| 158 |
+
"loss": 0.7517,
|
| 159 |
+
"step": 25
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 0.0,
|
| 163 |
+
"learning_rate": 1.3000000000000001e-05,
|
| 164 |
+
"loss": 1.0805,
|
| 165 |
+
"step": 26
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 0.0,
|
| 169 |
+
"learning_rate": 1.3500000000000001e-05,
|
| 170 |
+
"loss": 0.9719,
|
| 171 |
+
"step": 27
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.0,
|
| 175 |
+
"learning_rate": 1.4000000000000001e-05,
|
| 176 |
+
"loss": 0.8599,
|
| 177 |
+
"step": 28
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.0,
|
| 181 |
+
"learning_rate": 1.45e-05,
|
| 182 |
+
"loss": 1.0069,
|
| 183 |
+
"step": 29
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 0.0,
|
| 187 |
+
"learning_rate": 1.5e-05,
|
| 188 |
+
"loss": 0.8821,
|
| 189 |
+
"step": 30
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 0.0,
|
| 193 |
+
"learning_rate": 1.55e-05,
|
| 194 |
+
"loss": 1.324,
|
| 195 |
+
"step": 31
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 0.0,
|
| 199 |
+
"learning_rate": 1.6000000000000003e-05,
|
| 200 |
+
"loss": 0.7325,
|
| 201 |
+
"step": 32
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 0.0,
|
| 205 |
+
"learning_rate": 1.65e-05,
|
| 206 |
+
"loss": 0.9195,
|
| 207 |
+
"step": 33
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 0.0,
|
| 211 |
+
"learning_rate": 1.7000000000000003e-05,
|
| 212 |
+
"loss": 1.0733,
|
| 213 |
+
"step": 34
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.0,
|
| 217 |
+
"learning_rate": 1.75e-05,
|
| 218 |
+
"loss": 1.0441,
|
| 219 |
+
"step": 35
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.0,
|
| 223 |
+
"learning_rate": 1.8e-05,
|
| 224 |
+
"loss": 0.9961,
|
| 225 |
+
"step": 36
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 0.0,
|
| 229 |
+
"learning_rate": 1.85e-05,
|
| 230 |
+
"loss": 1.0976,
|
| 231 |
+
"step": 37
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 0.0,
|
| 235 |
+
"learning_rate": 1.9e-05,
|
| 236 |
+
"loss": 0.7981,
|
| 237 |
+
"step": 38
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 0.0,
|
| 241 |
+
"learning_rate": 1.9500000000000003e-05,
|
| 242 |
+
"loss": 0.9183,
|
| 243 |
+
"step": 39
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 0.0,
|
| 247 |
+
"learning_rate": 2e-05,
|
| 248 |
+
"loss": 1.2273,
|
| 249 |
+
"step": 40
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 0.0,
|
| 253 |
+
"learning_rate": 2.05e-05,
|
| 254 |
+
"loss": 1.0005,
|
| 255 |
+
"step": 41
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.0,
|
| 259 |
+
"learning_rate": 2.1e-05,
|
| 260 |
+
"loss": 1.2448,
|
| 261 |
+
"step": 42
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.0,
|
| 265 |
+
"learning_rate": 2.15e-05,
|
| 266 |
+
"loss": 1.4173,
|
| 267 |
+
"step": 43
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 0.0,
|
| 271 |
+
"learning_rate": 2.2000000000000003e-05,
|
| 272 |
+
"loss": 0.6956,
|
| 273 |
+
"step": 44
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 0.0,
|
| 277 |
+
"learning_rate": 2.25e-05,
|
| 278 |
+
"loss": 0.7313,
|
| 279 |
+
"step": 45
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 0.0,
|
| 283 |
+
"learning_rate": 2.3000000000000003e-05,
|
| 284 |
+
"loss": 0.9992,
|
| 285 |
+
"step": 46
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 0.0,
|
| 289 |
+
"learning_rate": 2.35e-05,
|
| 290 |
+
"loss": 1.0287,
|
| 291 |
+
"step": 47
|
| 292 |
+
},
|
| 293 |
+
{
|
| 294 |
+
"epoch": 0.0,
|
| 295 |
+
"learning_rate": 2.4e-05,
|
| 296 |
+
"loss": 1.3604,
|
| 297 |
+
"step": 48
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.0,
|
| 301 |
+
"learning_rate": 2.45e-05,
|
| 302 |
+
"loss": 0.7198,
|
| 303 |
+
"step": 49
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.01,
|
| 307 |
+
"learning_rate": 2.5e-05,
|
| 308 |
+
"loss": 0.2974,
|
| 309 |
+
"step": 50
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 0.01,
|
| 313 |
+
"eval_loss": 1.1389975547790527,
|
| 314 |
+
"eval_runtime": 71.831,
|
| 315 |
+
"eval_samples_per_second": 2.77,
|
| 316 |
+
"eval_steps_per_second": 0.696,
|
| 317 |
+
"step": 50
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.01,
|
| 321 |
+
"learning_rate": 2.5500000000000003e-05,
|
| 322 |
+
"loss": 0.5533,
|
| 323 |
+
"step": 51
|
| 324 |
+
},
|
| 325 |
+
{
|
| 326 |
+
"epoch": 0.01,
|
| 327 |
+
"learning_rate": 2.6000000000000002e-05,
|
| 328 |
+
"loss": 1.2819,
|
| 329 |
+
"step": 52
|
| 330 |
+
},
|
| 331 |
+
{
|
| 332 |
+
"epoch": 0.01,
|
| 333 |
+
"learning_rate": 2.6500000000000004e-05,
|
| 334 |
+
"loss": 1.4542,
|
| 335 |
+
"step": 53
|
| 336 |
+
},
|
| 337 |
+
{
|
| 338 |
+
"epoch": 0.01,
|
| 339 |
+
"learning_rate": 2.7000000000000002e-05,
|
| 340 |
+
"loss": 1.5254,
|
| 341 |
+
"step": 54
|
| 342 |
+
},
|
| 343 |
+
{
|
| 344 |
+
"epoch": 0.01,
|
| 345 |
+
"learning_rate": 2.7500000000000004e-05,
|
| 346 |
+
"loss": 1.1699,
|
| 347 |
+
"step": 55
|
| 348 |
+
},
|
| 349 |
+
{
|
| 350 |
+
"epoch": 0.01,
|
| 351 |
+
"learning_rate": 2.8000000000000003e-05,
|
| 352 |
+
"loss": 1.3209,
|
| 353 |
+
"step": 56
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 0.01,
|
| 357 |
+
"learning_rate": 2.8499999999999998e-05,
|
| 358 |
+
"loss": 0.659,
|
| 359 |
+
"step": 57
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 0.01,
|
| 363 |
+
"learning_rate": 2.9e-05,
|
| 364 |
+
"loss": 1.0342,
|
| 365 |
+
"step": 58
|
| 366 |
+
},
|
| 367 |
+
{
|
| 368 |
+
"epoch": 0.01,
|
| 369 |
+
"learning_rate": 2.95e-05,
|
| 370 |
+
"loss": 1.1414,
|
| 371 |
+
"step": 59
|
| 372 |
+
},
|
| 373 |
+
{
|
| 374 |
+
"epoch": 0.01,
|
| 375 |
+
"learning_rate": 3e-05,
|
| 376 |
+
"loss": 1.2102,
|
| 377 |
+
"step": 60
|
| 378 |
+
},
|
| 379 |
+
{
|
| 380 |
+
"epoch": 0.01,
|
| 381 |
+
"learning_rate": 3.05e-05,
|
| 382 |
+
"loss": 1.0656,
|
| 383 |
+
"step": 61
|
| 384 |
+
},
|
| 385 |
+
{
|
| 386 |
+
"epoch": 0.01,
|
| 387 |
+
"learning_rate": 3.1e-05,
|
| 388 |
+
"loss": 1.0089,
|
| 389 |
+
"step": 62
|
| 390 |
+
},
|
| 391 |
+
{
|
| 392 |
+
"epoch": 0.01,
|
| 393 |
+
"learning_rate": 3.15e-05,
|
| 394 |
+
"loss": 1.2177,
|
| 395 |
+
"step": 63
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 0.01,
|
| 399 |
+
"learning_rate": 3.2000000000000005e-05,
|
| 400 |
+
"loss": 0.965,
|
| 401 |
+
"step": 64
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 0.01,
|
| 405 |
+
"learning_rate": 3.2500000000000004e-05,
|
| 406 |
+
"loss": 0.8526,
|
| 407 |
+
"step": 65
|
| 408 |
+
},
|
| 409 |
+
{
|
| 410 |
+
"epoch": 0.01,
|
| 411 |
+
"learning_rate": 3.3e-05,
|
| 412 |
+
"loss": 0.9656,
|
| 413 |
+
"step": 66
|
| 414 |
+
},
|
| 415 |
+
{
|
| 416 |
+
"epoch": 0.01,
|
| 417 |
+
"learning_rate": 3.35e-05,
|
| 418 |
+
"loss": 1.0447,
|
| 419 |
+
"step": 67
|
| 420 |
+
},
|
| 421 |
+
{
|
| 422 |
+
"epoch": 0.01,
|
| 423 |
+
"learning_rate": 3.4000000000000007e-05,
|
| 424 |
+
"loss": 0.7947,
|
| 425 |
+
"step": 68
|
| 426 |
+
},
|
| 427 |
+
{
|
| 428 |
+
"epoch": 0.01,
|
| 429 |
+
"learning_rate": 3.45e-05,
|
| 430 |
+
"loss": 0.7962,
|
| 431 |
+
"step": 69
|
| 432 |
+
},
|
| 433 |
+
{
|
| 434 |
+
"epoch": 0.01,
|
| 435 |
+
"learning_rate": 3.5e-05,
|
| 436 |
+
"loss": 0.5062,
|
| 437 |
+
"step": 70
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 0.01,
|
| 441 |
+
"learning_rate": 3.55e-05,
|
| 442 |
+
"loss": 0.9352,
|
| 443 |
+
"step": 71
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 0.01,
|
| 447 |
+
"learning_rate": 3.6e-05,
|
| 448 |
+
"loss": 1.8548,
|
| 449 |
+
"step": 72
|
| 450 |
+
},
|
| 451 |
+
{
|
| 452 |
+
"epoch": 0.01,
|
| 453 |
+
"learning_rate": 3.65e-05,
|
| 454 |
+
"loss": 2.0769,
|
| 455 |
+
"step": 73
|
| 456 |
+
},
|
| 457 |
+
{
|
| 458 |
+
"epoch": 0.01,
|
| 459 |
+
"learning_rate": 3.7e-05,
|
| 460 |
+
"loss": 0.8846,
|
| 461 |
+
"step": 74
|
| 462 |
+
},
|
| 463 |
+
{
|
| 464 |
+
"epoch": 0.01,
|
| 465 |
+
"learning_rate": 3.7500000000000003e-05,
|
| 466 |
+
"loss": 0.864,
|
| 467 |
+
"step": 75
|
| 468 |
+
},
|
| 469 |
+
{
|
| 470 |
+
"epoch": 0.01,
|
| 471 |
+
"learning_rate": 3.8e-05,
|
| 472 |
+
"loss": 0.8684,
|
| 473 |
+
"step": 76
|
| 474 |
+
},
|
| 475 |
+
{
|
| 476 |
+
"epoch": 0.01,
|
| 477 |
+
"learning_rate": 3.85e-05,
|
| 478 |
+
"loss": 1.0395,
|
| 479 |
+
"step": 77
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 0.01,
|
| 483 |
+
"learning_rate": 3.9000000000000006e-05,
|
| 484 |
+
"loss": 1.1751,
|
| 485 |
+
"step": 78
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 0.01,
|
| 489 |
+
"learning_rate": 3.9500000000000005e-05,
|
| 490 |
+
"loss": 0.7136,
|
| 491 |
+
"step": 79
|
| 492 |
+
},
|
| 493 |
+
{
|
| 494 |
+
"epoch": 0.01,
|
| 495 |
+
"learning_rate": 4e-05,
|
| 496 |
+
"loss": 0.5699,
|
| 497 |
+
"step": 80
|
| 498 |
+
},
|
| 499 |
+
{
|
| 500 |
+
"epoch": 0.01,
|
| 501 |
+
"learning_rate": 4.05e-05,
|
| 502 |
+
"loss": 0.782,
|
| 503 |
+
"step": 81
|
| 504 |
+
},
|
| 505 |
+
{
|
| 506 |
+
"epoch": 0.01,
|
| 507 |
+
"learning_rate": 4.1e-05,
|
| 508 |
+
"loss": 1.4756,
|
| 509 |
+
"step": 82
|
| 510 |
+
},
|
| 511 |
+
{
|
| 512 |
+
"epoch": 0.01,
|
| 513 |
+
"learning_rate": 4.15e-05,
|
| 514 |
+
"loss": 1.3176,
|
| 515 |
+
"step": 83
|
| 516 |
+
},
|
| 517 |
+
{
|
| 518 |
+
"epoch": 0.01,
|
| 519 |
+
"learning_rate": 4.2e-05,
|
| 520 |
+
"loss": 1.2823,
|
| 521 |
+
"step": 84
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 0.01,
|
| 525 |
+
"learning_rate": 4.25e-05,
|
| 526 |
+
"loss": 1.3336,
|
| 527 |
+
"step": 85
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 0.01,
|
| 531 |
+
"learning_rate": 4.3e-05,
|
| 532 |
+
"loss": 1.3062,
|
| 533 |
+
"step": 86
|
| 534 |
+
},
|
| 535 |
+
{
|
| 536 |
+
"epoch": 0.01,
|
| 537 |
+
"learning_rate": 4.35e-05,
|
| 538 |
+
"loss": 1.2965,
|
| 539 |
+
"step": 87
|
| 540 |
+
},
|
| 541 |
+
{
|
| 542 |
+
"epoch": 0.01,
|
| 543 |
+
"learning_rate": 4.4000000000000006e-05,
|
| 544 |
+
"loss": 1.7232,
|
| 545 |
+
"step": 88
|
| 546 |
+
},
|
| 547 |
+
{
|
| 548 |
+
"epoch": 0.01,
|
| 549 |
+
"learning_rate": 4.4500000000000004e-05,
|
| 550 |
+
"loss": 1.0913,
|
| 551 |
+
"step": 89
|
| 552 |
+
},
|
| 553 |
+
{
|
| 554 |
+
"epoch": 0.01,
|
| 555 |
+
"learning_rate": 4.5e-05,
|
| 556 |
+
"loss": 1.3334,
|
| 557 |
+
"step": 90
|
| 558 |
+
},
|
| 559 |
+
{
|
| 560 |
+
"epoch": 0.01,
|
| 561 |
+
"learning_rate": 4.55e-05,
|
| 562 |
+
"loss": 1.1843,
|
| 563 |
+
"step": 91
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 0.01,
|
| 567 |
+
"learning_rate": 4.600000000000001e-05,
|
| 568 |
+
"loss": 0.9398,
|
| 569 |
+
"step": 92
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 0.01,
|
| 573 |
+
"learning_rate": 4.6500000000000005e-05,
|
| 574 |
+
"loss": 0.7859,
|
| 575 |
+
"step": 93
|
| 576 |
+
},
|
| 577 |
+
{
|
| 578 |
+
"epoch": 0.01,
|
| 579 |
+
"learning_rate": 4.7e-05,
|
| 580 |
+
"loss": 1.2015,
|
| 581 |
+
"step": 94
|
| 582 |
+
},
|
| 583 |
+
{
|
| 584 |
+
"epoch": 0.01,
|
| 585 |
+
"learning_rate": 4.75e-05,
|
| 586 |
+
"loss": 1.1383,
|
| 587 |
+
"step": 95
|
| 588 |
+
},
|
| 589 |
+
{
|
| 590 |
+
"epoch": 0.01,
|
| 591 |
+
"learning_rate": 4.8e-05,
|
| 592 |
+
"loss": 0.9095,
|
| 593 |
+
"step": 96
|
| 594 |
+
},
|
| 595 |
+
{
|
| 596 |
+
"epoch": 0.01,
|
| 597 |
+
"learning_rate": 4.85e-05,
|
| 598 |
+
"loss": 0.9644,
|
| 599 |
+
"step": 97
|
| 600 |
+
},
|
| 601 |
+
{
|
| 602 |
+
"epoch": 0.01,
|
| 603 |
+
"learning_rate": 4.9e-05,
|
| 604 |
+
"loss": 1.2399,
|
| 605 |
+
"step": 98
|
| 606 |
+
},
|
| 607 |
+
{
|
| 608 |
+
"epoch": 0.01,
|
| 609 |
+
"learning_rate": 4.9500000000000004e-05,
|
| 610 |
+
"loss": 0.8818,
|
| 611 |
+
"step": 99
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 0.01,
|
| 615 |
+
"learning_rate": 5e-05,
|
| 616 |
+
"loss": 0.9184,
|
| 617 |
+
"step": 100
|
| 618 |
+
},
|
| 619 |
+
{
|
| 620 |
+
"epoch": 0.01,
|
| 621 |
+
"eval_loss": 1.1290233135223389,
|
| 622 |
+
"eval_runtime": 72.0275,
|
| 623 |
+
"eval_samples_per_second": 2.763,
|
| 624 |
+
"eval_steps_per_second": 0.694,
|
| 625 |
+
"step": 100
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 0.01,
|
| 629 |
+
"learning_rate": 4.999999874125034e-05,
|
| 630 |
+
"loss": 0.4027,
|
| 631 |
+
"step": 101
|
| 632 |
+
},
|
| 633 |
+
{
|
| 634 |
+
"epoch": 0.01,
|
| 635 |
+
"learning_rate": 4.9999994965001495e-05,
|
| 636 |
+
"loss": 0.0226,
|
| 637 |
+
"step": 102
|
| 638 |
+
},
|
| 639 |
+
{
|
| 640 |
+
"epoch": 0.01,
|
| 641 |
+
"learning_rate": 4.999998867125384e-05,
|
| 642 |
+
"loss": 0.0269,
|
| 643 |
+
"step": 103
|
| 644 |
+
},
|
| 645 |
+
{
|
| 646 |
+
"epoch": 0.01,
|
| 647 |
+
"learning_rate": 4.9999979860008006e-05,
|
| 648 |
+
"loss": 0.025,
|
| 649 |
+
"step": 104
|
| 650 |
+
},
|
| 651 |
+
{
|
| 652 |
+
"epoch": 0.01,
|
| 653 |
+
"learning_rate": 4.999996853126489e-05,
|
| 654 |
+
"loss": 0.0204,
|
| 655 |
+
"step": 105
|
| 656 |
+
},
|
| 657 |
+
{
|
| 658 |
+
"epoch": 0.01,
|
| 659 |
+
"learning_rate": 4.999995468502562e-05,
|
| 660 |
+
"loss": 0.0263,
|
| 661 |
+
"step": 106
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 0.01,
|
| 665 |
+
"learning_rate": 4.9999938321291604e-05,
|
| 666 |
+
"loss": 0.0248,
|
| 667 |
+
"step": 107
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 0.01,
|
| 671 |
+
"learning_rate": 4.999991944006448e-05,
|
| 672 |
+
"loss": 0.0274,
|
| 673 |
+
"step": 108
|
| 674 |
+
},
|
| 675 |
+
{
|
| 676 |
+
"epoch": 0.01,
|
| 677 |
+
"learning_rate": 4.9999898041346155e-05,
|
| 678 |
+
"loss": 0.0218,
|
| 679 |
+
"step": 109
|
| 680 |
+
},
|
| 681 |
+
{
|
| 682 |
+
"epoch": 0.01,
|
| 683 |
+
"learning_rate": 4.999987412513878e-05,
|
| 684 |
+
"loss": 0.0182,
|
| 685 |
+
"step": 110
|
| 686 |
+
},
|
| 687 |
+
{
|
| 688 |
+
"epoch": 0.01,
|
| 689 |
+
"learning_rate": 4.999984769144476e-05,
|
| 690 |
+
"loss": 0.0205,
|
| 691 |
+
"step": 111
|
| 692 |
+
},
|
| 693 |
+
{
|
| 694 |
+
"epoch": 0.01,
|
| 695 |
+
"learning_rate": 4.9999818740266766e-05,
|
| 696 |
+
"loss": 0.0229,
|
| 697 |
+
"step": 112
|
| 698 |
+
},
|
| 699 |
+
{
|
| 700 |
+
"epoch": 0.01,
|
| 701 |
+
"learning_rate": 4.9999787271607714e-05,
|
| 702 |
+
"loss": 0.0416,
|
| 703 |
+
"step": 113
|
| 704 |
+
},
|
| 705 |
+
{
|
| 706 |
+
"epoch": 0.01,
|
| 707 |
+
"learning_rate": 4.999975328547076e-05,
|
| 708 |
+
"loss": 0.0191,
|
| 709 |
+
"step": 114
|
| 710 |
+
},
|
| 711 |
+
{
|
| 712 |
+
"epoch": 0.01,
|
| 713 |
+
"learning_rate": 4.999971678185933e-05,
|
| 714 |
+
"loss": 0.0205,
|
| 715 |
+
"step": 115
|
| 716 |
+
},
|
| 717 |
+
{
|
| 718 |
+
"epoch": 0.01,
|
| 719 |
+
"learning_rate": 4.9999677760777114e-05,
|
| 720 |
+
"loss": 0.0184,
|
| 721 |
+
"step": 116
|
| 722 |
+
},
|
| 723 |
+
{
|
| 724 |
+
"epoch": 0.01,
|
| 725 |
+
"learning_rate": 4.999963622222803e-05,
|
| 726 |
+
"loss": 0.018,
|
| 727 |
+
"step": 117
|
| 728 |
+
},
|
| 729 |
+
{
|
| 730 |
+
"epoch": 0.01,
|
| 731 |
+
"learning_rate": 4.9999592166216256e-05,
|
| 732 |
+
"loss": 0.0242,
|
| 733 |
+
"step": 118
|
| 734 |
+
},
|
| 735 |
+
{
|
| 736 |
+
"epoch": 0.01,
|
| 737 |
+
"learning_rate": 4.999954559274624e-05,
|
| 738 |
+
"loss": 0.4053,
|
| 739 |
+
"step": 119
|
| 740 |
+
},
|
| 741 |
+
{
|
| 742 |
+
"epoch": 0.01,
|
| 743 |
+
"learning_rate": 4.999949650182266e-05,
|
| 744 |
+
"loss": 0.5058,
|
| 745 |
+
"step": 120
|
| 746 |
+
},
|
| 747 |
+
{
|
| 748 |
+
"epoch": 0.01,
|
| 749 |
+
"learning_rate": 4.9999444893450476e-05,
|
| 750 |
+
"loss": 0.9192,
|
| 751 |
+
"step": 121
|
| 752 |
+
},
|
| 753 |
+
{
|
| 754 |
+
"epoch": 0.01,
|
| 755 |
+
"learning_rate": 4.999939076763487e-05,
|
| 756 |
+
"loss": 1.1211,
|
| 757 |
+
"step": 122
|
| 758 |
+
},
|
| 759 |
+
{
|
| 760 |
+
"epoch": 0.01,
|
| 761 |
+
"learning_rate": 4.99993341243813e-05,
|
| 762 |
+
"loss": 0.7105,
|
| 763 |
+
"step": 123
|
| 764 |
+
},
|
| 765 |
+
{
|
| 766 |
+
"epoch": 0.01,
|
| 767 |
+
"learning_rate": 4.999927496369547e-05,
|
| 768 |
+
"loss": 0.851,
|
| 769 |
+
"step": 124
|
| 770 |
+
},
|
| 771 |
+
{
|
| 772 |
+
"epoch": 0.01,
|
| 773 |
+
"learning_rate": 4.999921328558333e-05,
|
| 774 |
+
"loss": 0.763,
|
| 775 |
+
"step": 125
|
| 776 |
+
},
|
| 777 |
+
{
|
| 778 |
+
"epoch": 0.01,
|
| 779 |
+
"learning_rate": 4.99991490900511e-05,
|
| 780 |
+
"loss": 1.1325,
|
| 781 |
+
"step": 126
|
| 782 |
+
},
|
| 783 |
+
{
|
| 784 |
+
"epoch": 0.01,
|
| 785 |
+
"learning_rate": 4.999908237710523e-05,
|
| 786 |
+
"loss": 1.1006,
|
| 787 |
+
"step": 127
|
| 788 |
+
},
|
| 789 |
+
{
|
| 790 |
+
"epoch": 0.01,
|
| 791 |
+
"learning_rate": 4.999901314675246e-05,
|
| 792 |
+
"loss": 0.9444,
|
| 793 |
+
"step": 128
|
| 794 |
+
},
|
| 795 |
+
{
|
| 796 |
+
"epoch": 0.01,
|
| 797 |
+
"learning_rate": 4.9998941398999754e-05,
|
| 798 |
+
"loss": 1.0285,
|
| 799 |
+
"step": 129
|
| 800 |
+
},
|
| 801 |
+
{
|
| 802 |
+
"epoch": 0.01,
|
| 803 |
+
"learning_rate": 4.999886713385432e-05,
|
| 804 |
+
"loss": 0.9176,
|
| 805 |
+
"step": 130
|
| 806 |
+
},
|
| 807 |
+
{
|
| 808 |
+
"epoch": 0.01,
|
| 809 |
+
"learning_rate": 4.999879035132366e-05,
|
| 810 |
+
"loss": 1.2408,
|
| 811 |
+
"step": 131
|
| 812 |
+
},
|
| 813 |
+
{
|
| 814 |
+
"epoch": 0.01,
|
| 815 |
+
"learning_rate": 4.999871105141549e-05,
|
| 816 |
+
"loss": 1.0897,
|
| 817 |
+
"step": 132
|
| 818 |
+
},
|
| 819 |
+
{
|
| 820 |
+
"epoch": 0.01,
|
| 821 |
+
"learning_rate": 4.999862923413781e-05,
|
| 822 |
+
"loss": 0.6091,
|
| 823 |
+
"step": 133
|
| 824 |
+
},
|
| 825 |
+
{
|
| 826 |
+
"epoch": 0.01,
|
| 827 |
+
"learning_rate": 4.999854489949884e-05,
|
| 828 |
+
"loss": 1.1689,
|
| 829 |
+
"step": 134
|
| 830 |
+
},
|
| 831 |
+
{
|
| 832 |
+
"epoch": 0.01,
|
| 833 |
+
"learning_rate": 4.999845804750709e-05,
|
| 834 |
+
"loss": 1.5978,
|
| 835 |
+
"step": 135
|
| 836 |
+
},
|
| 837 |
+
{
|
| 838 |
+
"epoch": 0.01,
|
| 839 |
+
"learning_rate": 4.999836867817129e-05,
|
| 840 |
+
"loss": 1.4423,
|
| 841 |
+
"step": 136
|
| 842 |
+
},
|
| 843 |
+
{
|
| 844 |
+
"epoch": 0.01,
|
| 845 |
+
"learning_rate": 4.999827679150045e-05,
|
| 846 |
+
"loss": 0.9095,
|
| 847 |
+
"step": 137
|
| 848 |
+
},
|
| 849 |
+
{
|
| 850 |
+
"epoch": 0.01,
|
| 851 |
+
"learning_rate": 4.999818238750382e-05,
|
| 852 |
+
"loss": 0.7459,
|
| 853 |
+
"step": 138
|
| 854 |
+
},
|
| 855 |
+
{
|
| 856 |
+
"epoch": 0.01,
|
| 857 |
+
"learning_rate": 4.999808546619091e-05,
|
| 858 |
+
"loss": 0.8685,
|
| 859 |
+
"step": 139
|
| 860 |
+
},
|
| 861 |
+
{
|
| 862 |
+
"epoch": 0.01,
|
| 863 |
+
"learning_rate": 4.9997986027571485e-05,
|
| 864 |
+
"loss": 1.1481,
|
| 865 |
+
"step": 140
|
| 866 |
+
},
|
| 867 |
+
{
|
| 868 |
+
"epoch": 0.01,
|
| 869 |
+
"learning_rate": 4.9997884071655546e-05,
|
| 870 |
+
"loss": 2.5944,
|
| 871 |
+
"step": 141
|
| 872 |
+
},
|
| 873 |
+
{
|
| 874 |
+
"epoch": 0.01,
|
| 875 |
+
"learning_rate": 4.999777959845336e-05,
|
| 876 |
+
"loss": 0.8284,
|
| 877 |
+
"step": 142
|
| 878 |
+
},
|
| 879 |
+
{
|
| 880 |
+
"epoch": 0.01,
|
| 881 |
+
"learning_rate": 4.999767260797546e-05,
|
| 882 |
+
"loss": 1.0722,
|
| 883 |
+
"step": 143
|
| 884 |
+
},
|
| 885 |
+
{
|
| 886 |
+
"epoch": 0.01,
|
| 887 |
+
"learning_rate": 4.999756310023261e-05,
|
| 888 |
+
"loss": 1.0372,
|
| 889 |
+
"step": 144
|
| 890 |
+
},
|
| 891 |
+
{
|
| 892 |
+
"epoch": 0.01,
|
| 893 |
+
"learning_rate": 4.9997451075235834e-05,
|
| 894 |
+
"loss": 1.1565,
|
| 895 |
+
"step": 145
|
| 896 |
+
},
|
| 897 |
+
{
|
| 898 |
+
"epoch": 0.01,
|
| 899 |
+
"learning_rate": 4.9997336532996426e-05,
|
| 900 |
+
"loss": 1.1735,
|
| 901 |
+
"step": 146
|
| 902 |
+
},
|
| 903 |
+
{
|
| 904 |
+
"epoch": 0.01,
|
| 905 |
+
"learning_rate": 4.999721947352591e-05,
|
| 906 |
+
"loss": 0.861,
|
| 907 |
+
"step": 147
|
| 908 |
+
},
|
| 909 |
+
{
|
| 910 |
+
"epoch": 0.01,
|
| 911 |
+
"learning_rate": 4.999709989683607e-05,
|
| 912 |
+
"loss": 0.7458,
|
| 913 |
+
"step": 148
|
| 914 |
+
},
|
| 915 |
+
{
|
| 916 |
+
"epoch": 0.01,
|
| 917 |
+
"learning_rate": 4.999697780293897e-05,
|
| 918 |
+
"loss": 1.1438,
|
| 919 |
+
"step": 149
|
| 920 |
+
},
|
| 921 |
+
{
|
| 922 |
+
"epoch": 0.01,
|
| 923 |
+
"learning_rate": 4.9996853191846885e-05,
|
| 924 |
+
"loss": 0.8448,
|
| 925 |
+
"step": 150
|
| 926 |
+
},
|
| 927 |
+
{
|
| 928 |
+
"epoch": 0.01,
|
| 929 |
+
"eval_loss": 1.1207772493362427,
|
| 930 |
+
"eval_runtime": 72.9183,
|
| 931 |
+
"eval_samples_per_second": 2.729,
|
| 932 |
+
"eval_steps_per_second": 0.686,
|
| 933 |
+
"step": 150
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 0.02,
|
| 937 |
+
"learning_rate": 4.999672606357236e-05,
|
| 938 |
+
"loss": 0.4995,
|
| 939 |
+
"step": 151
|
| 940 |
+
},
|
| 941 |
+
{
|
| 942 |
+
"epoch": 0.02,
|
| 943 |
+
"learning_rate": 4.99965964181282e-05,
|
| 944 |
+
"loss": 0.2793,
|
| 945 |
+
"step": 152
|
| 946 |
+
},
|
| 947 |
+
{
|
| 948 |
+
"epoch": 0.02,
|
| 949 |
+
"learning_rate": 4.9996464255527475e-05,
|
| 950 |
+
"loss": 0.5865,
|
| 951 |
+
"step": 153
|
| 952 |
+
},
|
| 953 |
+
{
|
| 954 |
+
"epoch": 0.02,
|
| 955 |
+
"learning_rate": 4.999632957578349e-05,
|
| 956 |
+
"loss": 0.7137,
|
| 957 |
+
"step": 154
|
| 958 |
+
},
|
| 959 |
+
{
|
| 960 |
+
"epoch": 0.02,
|
| 961 |
+
"learning_rate": 4.9996192378909786e-05,
|
| 962 |
+
"loss": 0.495,
|
| 963 |
+
"step": 155
|
| 964 |
+
},
|
| 965 |
+
{
|
| 966 |
+
"epoch": 0.02,
|
| 967 |
+
"learning_rate": 4.9996052664920195e-05,
|
| 968 |
+
"loss": 0.9241,
|
| 969 |
+
"step": 156
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 0.02,
|
| 973 |
+
"learning_rate": 4.999591043382878e-05,
|
| 974 |
+
"loss": 2.3316,
|
| 975 |
+
"step": 157
|
| 976 |
+
},
|
| 977 |
+
{
|
| 978 |
+
"epoch": 0.02,
|
| 979 |
+
"learning_rate": 4.9995765685649885e-05,
|
| 980 |
+
"loss": 1.1994,
|
| 981 |
+
"step": 158
|
| 982 |
+
},
|
| 983 |
+
{
|
| 984 |
+
"epoch": 0.02,
|
| 985 |
+
"learning_rate": 4.999561842039806e-05,
|
| 986 |
+
"loss": 0.6486,
|
| 987 |
+
"step": 159
|
| 988 |
+
},
|
| 989 |
+
{
|
| 990 |
+
"epoch": 0.02,
|
| 991 |
+
"learning_rate": 4.999546863808815e-05,
|
| 992 |
+
"loss": 0.6252,
|
| 993 |
+
"step": 160
|
| 994 |
+
},
|
| 995 |
+
{
|
| 996 |
+
"epoch": 0.02,
|
| 997 |
+
"learning_rate": 4.999531633873522e-05,
|
| 998 |
+
"loss": 1.0976,
|
| 999 |
+
"step": 161
|
| 1000 |
+
},
|
| 1001 |
+
{
|
| 1002 |
+
"epoch": 0.02,
|
| 1003 |
+
"learning_rate": 4.9995161522354626e-05,
|
| 1004 |
+
"loss": 0.8763,
|
| 1005 |
+
"step": 162
|
| 1006 |
+
},
|
| 1007 |
+
{
|
| 1008 |
+
"epoch": 0.02,
|
| 1009 |
+
"learning_rate": 4.9995004188961954e-05,
|
| 1010 |
+
"loss": 0.4891,
|
| 1011 |
+
"step": 163
|
| 1012 |
+
},
|
| 1013 |
+
{
|
| 1014 |
+
"epoch": 0.02,
|
| 1015 |
+
"learning_rate": 4.9994844338573047e-05,
|
| 1016 |
+
"loss": 0.7395,
|
| 1017 |
+
"step": 164
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 0.02,
|
| 1021 |
+
"learning_rate": 4.9994681971203985e-05,
|
| 1022 |
+
"loss": 0.9335,
|
| 1023 |
+
"step": 165
|
| 1024 |
+
},
|
| 1025 |
+
{
|
| 1026 |
+
"epoch": 0.02,
|
| 1027 |
+
"learning_rate": 4.999451708687114e-05,
|
| 1028 |
+
"loss": 0.8835,
|
| 1029 |
+
"step": 166
|
| 1030 |
+
},
|
| 1031 |
+
{
|
| 1032 |
+
"epoch": 0.02,
|
| 1033 |
+
"learning_rate": 4.999434968559111e-05,
|
| 1034 |
+
"loss": 0.7375,
|
| 1035 |
+
"step": 167
|
| 1036 |
+
},
|
| 1037 |
+
{
|
| 1038 |
+
"epoch": 0.02,
|
| 1039 |
+
"learning_rate": 4.9994179767380746e-05,
|
| 1040 |
+
"loss": 1.1447,
|
| 1041 |
+
"step": 168
|
| 1042 |
+
},
|
| 1043 |
+
{
|
| 1044 |
+
"epoch": 0.02,
|
| 1045 |
+
"learning_rate": 4.9994007332257166e-05,
|
| 1046 |
+
"loss": 1.0092,
|
| 1047 |
+
"step": 169
|
| 1048 |
+
},
|
| 1049 |
+
{
|
| 1050 |
+
"epoch": 0.02,
|
| 1051 |
+
"learning_rate": 4.9993832380237735e-05,
|
| 1052 |
+
"loss": 1.2002,
|
| 1053 |
+
"step": 170
|
| 1054 |
+
},
|
| 1055 |
+
{
|
| 1056 |
+
"epoch": 0.02,
|
| 1057 |
+
"learning_rate": 4.999365491134006e-05,
|
| 1058 |
+
"loss": 1.1527,
|
| 1059 |
+
"step": 171
|
| 1060 |
+
},
|
| 1061 |
+
{
|
| 1062 |
+
"epoch": 0.02,
|
| 1063 |
+
"learning_rate": 4.999347492558202e-05,
|
| 1064 |
+
"loss": 0.8259,
|
| 1065 |
+
"step": 172
|
| 1066 |
+
},
|
| 1067 |
+
{
|
| 1068 |
+
"epoch": 0.02,
|
| 1069 |
+
"learning_rate": 4.9993292422981744e-05,
|
| 1070 |
+
"loss": 0.7446,
|
| 1071 |
+
"step": 173
|
| 1072 |
+
},
|
| 1073 |
+
{
|
| 1074 |
+
"epoch": 0.02,
|
| 1075 |
+
"learning_rate": 4.9993107403557606e-05,
|
| 1076 |
+
"loss": 0.8483,
|
| 1077 |
+
"step": 174
|
| 1078 |
+
},
|
| 1079 |
+
{
|
| 1080 |
+
"epoch": 0.02,
|
| 1081 |
+
"learning_rate": 4.999291986732823e-05,
|
| 1082 |
+
"loss": 0.9139,
|
| 1083 |
+
"step": 175
|
| 1084 |
+
},
|
| 1085 |
+
{
|
| 1086 |
+
"epoch": 0.02,
|
| 1087 |
+
"learning_rate": 4.999272981431251e-05,
|
| 1088 |
+
"loss": 1.1312,
|
| 1089 |
+
"step": 176
|
| 1090 |
+
},
|
| 1091 |
+
{
|
| 1092 |
+
"epoch": 0.02,
|
| 1093 |
+
"learning_rate": 4.999253724452958e-05,
|
| 1094 |
+
"loss": 1.0392,
|
| 1095 |
+
"step": 177
|
| 1096 |
+
},
|
| 1097 |
+
{
|
| 1098 |
+
"epoch": 0.02,
|
| 1099 |
+
"learning_rate": 4.999234215799884e-05,
|
| 1100 |
+
"loss": 0.9711,
|
| 1101 |
+
"step": 178
|
| 1102 |
+
},
|
| 1103 |
+
{
|
| 1104 |
+
"epoch": 0.02,
|
| 1105 |
+
"learning_rate": 4.9992144554739915e-05,
|
| 1106 |
+
"loss": 0.0736,
|
| 1107 |
+
"step": 179
|
| 1108 |
+
},
|
| 1109 |
+
{
|
| 1110 |
+
"epoch": 0.02,
|
| 1111 |
+
"learning_rate": 4.9991944434772734e-05,
|
| 1112 |
+
"loss": 0.0228,
|
| 1113 |
+
"step": 180
|
| 1114 |
+
},
|
| 1115 |
+
{
|
| 1116 |
+
"epoch": 0.02,
|
| 1117 |
+
"learning_rate": 4.999174179811742e-05,
|
| 1118 |
+
"loss": 0.0183,
|
| 1119 |
+
"step": 181
|
| 1120 |
+
},
|
| 1121 |
+
{
|
| 1122 |
+
"epoch": 0.02,
|
| 1123 |
+
"learning_rate": 4.9991536644794394e-05,
|
| 1124 |
+
"loss": 0.0135,
|
| 1125 |
+
"step": 182
|
| 1126 |
+
},
|
| 1127 |
+
{
|
| 1128 |
+
"epoch": 0.02,
|
| 1129 |
+
"learning_rate": 4.9991328974824314e-05,
|
| 1130 |
+
"loss": 0.0189,
|
| 1131 |
+
"step": 183
|
| 1132 |
+
},
|
| 1133 |
+
{
|
| 1134 |
+
"epoch": 0.02,
|
| 1135 |
+
"learning_rate": 4.9991118788228084e-05,
|
| 1136 |
+
"loss": 0.0138,
|
| 1137 |
+
"step": 184
|
| 1138 |
+
},
|
| 1139 |
+
{
|
| 1140 |
+
"epoch": 0.02,
|
| 1141 |
+
"learning_rate": 4.999090608502688e-05,
|
| 1142 |
+
"loss": 0.0177,
|
| 1143 |
+
"step": 185
|
| 1144 |
+
},
|
| 1145 |
+
{
|
| 1146 |
+
"epoch": 0.02,
|
| 1147 |
+
"learning_rate": 4.999069086524212e-05,
|
| 1148 |
+
"loss": 0.0161,
|
| 1149 |
+
"step": 186
|
| 1150 |
+
},
|
| 1151 |
+
{
|
| 1152 |
+
"epoch": 0.02,
|
| 1153 |
+
"learning_rate": 4.999047312889547e-05,
|
| 1154 |
+
"loss": 0.0227,
|
| 1155 |
+
"step": 187
|
| 1156 |
+
},
|
| 1157 |
+
{
|
| 1158 |
+
"epoch": 0.02,
|
| 1159 |
+
"learning_rate": 4.999025287600886e-05,
|
| 1160 |
+
"loss": 0.0161,
|
| 1161 |
+
"step": 188
|
| 1162 |
+
},
|
| 1163 |
+
{
|
| 1164 |
+
"epoch": 0.02,
|
| 1165 |
+
"learning_rate": 4.9990030106604466e-05,
|
| 1166 |
+
"loss": 0.0178,
|
| 1167 |
+
"step": 189
|
| 1168 |
+
},
|
| 1169 |
+
{
|
| 1170 |
+
"epoch": 0.02,
|
| 1171 |
+
"learning_rate": 4.9989804820704735e-05,
|
| 1172 |
+
"loss": 0.0351,
|
| 1173 |
+
"step": 190
|
| 1174 |
+
},
|
| 1175 |
+
{
|
| 1176 |
+
"epoch": 0.02,
|
| 1177 |
+
"learning_rate": 4.998957701833233e-05,
|
| 1178 |
+
"loss": 0.0169,
|
| 1179 |
+
"step": 191
|
| 1180 |
+
},
|
| 1181 |
+
{
|
| 1182 |
+
"epoch": 0.02,
|
| 1183 |
+
"learning_rate": 4.998934669951021e-05,
|
| 1184 |
+
"loss": 0.0152,
|
| 1185 |
+
"step": 192
|
| 1186 |
+
},
|
| 1187 |
+
{
|
| 1188 |
+
"epoch": 0.02,
|
| 1189 |
+
"learning_rate": 4.998911386426156e-05,
|
| 1190 |
+
"loss": 0.0116,
|
| 1191 |
+
"step": 193
|
| 1192 |
+
},
|
| 1193 |
+
{
|
| 1194 |
+
"epoch": 0.02,
|
| 1195 |
+
"learning_rate": 4.998887851260983e-05,
|
| 1196 |
+
"loss": 0.015,
|
| 1197 |
+
"step": 194
|
| 1198 |
+
},
|
| 1199 |
+
{
|
| 1200 |
+
"epoch": 0.02,
|
| 1201 |
+
"learning_rate": 4.998864064457871e-05,
|
| 1202 |
+
"loss": 0.021,
|
| 1203 |
+
"step": 195
|
| 1204 |
+
},
|
| 1205 |
+
{
|
| 1206 |
+
"epoch": 0.02,
|
| 1207 |
+
"learning_rate": 4.998840026019217e-05,
|
| 1208 |
+
"loss": 0.017,
|
| 1209 |
+
"step": 196
|
| 1210 |
+
},
|
| 1211 |
+
{
|
| 1212 |
+
"epoch": 0.02,
|
| 1213 |
+
"learning_rate": 4.99881573594744e-05,
|
| 1214 |
+
"loss": 0.4376,
|
| 1215 |
+
"step": 197
|
| 1216 |
+
},
|
| 1217 |
+
{
|
| 1218 |
+
"epoch": 0.02,
|
| 1219 |
+
"learning_rate": 4.9987911942449874e-05,
|
| 1220 |
+
"loss": 0.5764,
|
| 1221 |
+
"step": 198
|
| 1222 |
+
},
|
| 1223 |
+
{
|
| 1224 |
+
"epoch": 0.02,
|
| 1225 |
+
"learning_rate": 4.998766400914329e-05,
|
| 1226 |
+
"loss": 1.0406,
|
| 1227 |
+
"step": 199
|
| 1228 |
+
},
|
| 1229 |
+
{
|
| 1230 |
+
"epoch": 0.02,
|
| 1231 |
+
"learning_rate": 4.9987413559579636e-05,
|
| 1232 |
+
"loss": 1.2413,
|
| 1233 |
+
"step": 200
|
| 1234 |
+
},
|
| 1235 |
+
{
|
| 1236 |
+
"epoch": 0.02,
|
| 1237 |
+
"eval_loss": 1.1171025037765503,
|
| 1238 |
+
"eval_runtime": 71.816,
|
| 1239 |
+
"eval_samples_per_second": 2.771,
|
| 1240 |
+
"eval_steps_per_second": 0.696,
|
| 1241 |
+
"step": 200
|
| 1242 |
+
},
|
| 1243 |
+
{
|
| 1244 |
+
"epoch": 0.02,
|
| 1245 |
+
"learning_rate": 4.998716059378411e-05,
|
| 1246 |
+
"loss": 0.9615,
|
| 1247 |
+
"step": 201
|
| 1248 |
+
},
|
| 1249 |
+
{
|
| 1250 |
+
"epoch": 0.02,
|
| 1251 |
+
"learning_rate": 4.99869051117822e-05,
|
| 1252 |
+
"loss": 0.9232,
|
| 1253 |
+
"step": 202
|
| 1254 |
+
},
|
| 1255 |
+
{
|
| 1256 |
+
"epoch": 0.02,
|
| 1257 |
+
"learning_rate": 4.998664711359963e-05,
|
| 1258 |
+
"loss": 1.3542,
|
| 1259 |
+
"step": 203
|
| 1260 |
+
},
|
| 1261 |
+
{
|
| 1262 |
+
"epoch": 0.02,
|
| 1263 |
+
"learning_rate": 4.9986386599262374e-05,
|
| 1264 |
+
"loss": 0.7679,
|
| 1265 |
+
"step": 204
|
| 1266 |
+
},
|
| 1267 |
+
{
|
| 1268 |
+
"epoch": 0.02,
|
| 1269 |
+
"learning_rate": 4.998612356879667e-05,
|
| 1270 |
+
"loss": 0.9539,
|
| 1271 |
+
"step": 205
|
| 1272 |
+
},
|
| 1273 |
+
{
|
| 1274 |
+
"epoch": 0.02,
|
| 1275 |
+
"learning_rate": 4.9985858022229015e-05,
|
| 1276 |
+
"loss": 1.3759,
|
| 1277 |
+
"step": 206
|
| 1278 |
+
},
|
| 1279 |
+
{
|
| 1280 |
+
"epoch": 0.02,
|
| 1281 |
+
"learning_rate": 4.998558995958614e-05,
|
| 1282 |
+
"loss": 0.9567,
|
| 1283 |
+
"step": 207
|
| 1284 |
+
},
|
| 1285 |
+
{
|
| 1286 |
+
"epoch": 0.02,
|
| 1287 |
+
"learning_rate": 4.998531938089503e-05,
|
| 1288 |
+
"loss": 0.8245,
|
| 1289 |
+
"step": 208
|
| 1290 |
+
},
|
| 1291 |
+
{
|
| 1292 |
+
"epoch": 0.02,
|
| 1293 |
+
"learning_rate": 4.998504628618296e-05,
|
| 1294 |
+
"loss": 0.8987,
|
| 1295 |
+
"step": 209
|
| 1296 |
+
},
|
| 1297 |
+
{
|
| 1298 |
+
"epoch": 0.02,
|
| 1299 |
+
"learning_rate": 4.99847706754774e-05,
|
| 1300 |
+
"loss": 0.9503,
|
| 1301 |
+
"step": 210
|
| 1302 |
+
},
|
| 1303 |
+
{
|
| 1304 |
+
"epoch": 0.02,
|
| 1305 |
+
"learning_rate": 4.998449254880612e-05,
|
| 1306 |
+
"loss": 0.9907,
|
| 1307 |
+
"step": 211
|
| 1308 |
+
},
|
| 1309 |
+
{
|
| 1310 |
+
"epoch": 0.02,
|
| 1311 |
+
"learning_rate": 4.998421190619711e-05,
|
| 1312 |
+
"loss": 1.1336,
|
| 1313 |
+
"step": 212
|
| 1314 |
+
},
|
| 1315 |
+
{
|
| 1316 |
+
"epoch": 0.02,
|
| 1317 |
+
"learning_rate": 4.9983928747678663e-05,
|
| 1318 |
+
"loss": 1.3901,
|
| 1319 |
+
"step": 213
|
| 1320 |
+
},
|
| 1321 |
+
{
|
| 1322 |
+
"epoch": 0.02,
|
| 1323 |
+
"learning_rate": 4.998364307327927e-05,
|
| 1324 |
+
"loss": 1.5705,
|
| 1325 |
+
"step": 214
|
| 1326 |
+
},
|
| 1327 |
+
{
|
| 1328 |
+
"epoch": 0.02,
|
| 1329 |
+
"learning_rate": 4.99833548830277e-05,
|
| 1330 |
+
"loss": 0.8125,
|
| 1331 |
+
"step": 215
|
| 1332 |
+
},
|
| 1333 |
+
{
|
| 1334 |
+
"epoch": 0.02,
|
| 1335 |
+
"learning_rate": 4.9983064176952976e-05,
|
| 1336 |
+
"loss": 0.82,
|
| 1337 |
+
"step": 216
|
| 1338 |
+
},
|
| 1339 |
+
{
|
| 1340 |
+
"epoch": 0.02,
|
| 1341 |
+
"learning_rate": 4.9982770955084376e-05,
|
| 1342 |
+
"loss": 0.7146,
|
| 1343 |
+
"step": 217
|
| 1344 |
+
},
|
| 1345 |
+
{
|
| 1346 |
+
"epoch": 0.02,
|
| 1347 |
+
"learning_rate": 4.9982475217451426e-05,
|
| 1348 |
+
"loss": 1.0612,
|
| 1349 |
+
"step": 218
|
| 1350 |
+
},
|
| 1351 |
+
{
|
| 1352 |
+
"epoch": 0.02,
|
| 1353 |
+
"learning_rate": 4.998217696408391e-05,
|
| 1354 |
+
"loss": 0.7297,
|
| 1355 |
+
"step": 219
|
| 1356 |
+
},
|
| 1357 |
+
{
|
| 1358 |
+
"epoch": 0.02,
|
| 1359 |
+
"learning_rate": 4.9981876195011844e-05,
|
| 1360 |
+
"loss": 0.9502,
|
| 1361 |
+
"step": 220
|
| 1362 |
+
},
|
| 1363 |
+
{
|
| 1364 |
+
"epoch": 0.02,
|
| 1365 |
+
"learning_rate": 4.998157291026553e-05,
|
| 1366 |
+
"loss": 1.1155,
|
| 1367 |
+
"step": 221
|
| 1368 |
+
},
|
| 1369 |
+
{
|
| 1370 |
+
"epoch": 0.02,
|
| 1371 |
+
"learning_rate": 4.998126710987552e-05,
|
| 1372 |
+
"loss": 1.1281,
|
| 1373 |
+
"step": 222
|
| 1374 |
+
},
|
| 1375 |
+
{
|
| 1376 |
+
"epoch": 0.02,
|
| 1377 |
+
"learning_rate": 4.9980958793872577e-05,
|
| 1378 |
+
"loss": 0.848,
|
| 1379 |
+
"step": 223
|
| 1380 |
+
},
|
| 1381 |
+
{
|
| 1382 |
+
"epoch": 0.02,
|
| 1383 |
+
"learning_rate": 4.998064796228779e-05,
|
| 1384 |
+
"loss": 0.6496,
|
| 1385 |
+
"step": 224
|
| 1386 |
+
},
|
| 1387 |
+
{
|
| 1388 |
+
"epoch": 0.02,
|
| 1389 |
+
"learning_rate": 4.998033461515242e-05,
|
| 1390 |
+
"loss": 0.9489,
|
| 1391 |
+
"step": 225
|
| 1392 |
+
},
|
| 1393 |
+
{
|
| 1394 |
+
"epoch": 0.02,
|
| 1395 |
+
"learning_rate": 4.9980018752498035e-05,
|
| 1396 |
+
"loss": 1.1667,
|
| 1397 |
+
"step": 226
|
| 1398 |
+
},
|
| 1399 |
+
{
|
| 1400 |
+
"epoch": 0.02,
|
| 1401 |
+
"learning_rate": 4.9979700374356455e-05,
|
| 1402 |
+
"loss": 1.0077,
|
| 1403 |
+
"step": 227
|
| 1404 |
+
},
|
| 1405 |
+
{
|
| 1406 |
+
"epoch": 0.02,
|
| 1407 |
+
"learning_rate": 4.997937948075973e-05,
|
| 1408 |
+
"loss": 0.8891,
|
| 1409 |
+
"step": 228
|
| 1410 |
+
},
|
| 1411 |
+
{
|
| 1412 |
+
"epoch": 0.02,
|
| 1413 |
+
"learning_rate": 4.997905607174017e-05,
|
| 1414 |
+
"loss": 1.2342,
|
| 1415 |
+
"step": 229
|
| 1416 |
+
},
|
| 1417 |
+
{
|
| 1418 |
+
"epoch": 0.02,
|
| 1419 |
+
"learning_rate": 4.9978730147330355e-05,
|
| 1420 |
+
"loss": 0.7439,
|
| 1421 |
+
"step": 230
|
| 1422 |
+
},
|
| 1423 |
+
{
|
| 1424 |
+
"epoch": 0.02,
|
| 1425 |
+
"learning_rate": 4.9978401707563096e-05,
|
| 1426 |
+
"loss": 0.8864,
|
| 1427 |
+
"step": 231
|
| 1428 |
+
},
|
| 1429 |
+
{
|
| 1430 |
+
"epoch": 0.02,
|
| 1431 |
+
"learning_rate": 4.997807075247146e-05,
|
| 1432 |
+
"loss": 0.8909,
|
| 1433 |
+
"step": 232
|
| 1434 |
+
},
|
| 1435 |
+
{
|
| 1436 |
+
"epoch": 0.02,
|
| 1437 |
+
"learning_rate": 4.997773728208879e-05,
|
| 1438 |
+
"loss": 0.928,
|
| 1439 |
+
"step": 233
|
| 1440 |
+
},
|
| 1441 |
+
{
|
| 1442 |
+
"epoch": 0.02,
|
| 1443 |
+
"learning_rate": 4.997740129644865e-05,
|
| 1444 |
+
"loss": 0.8764,
|
| 1445 |
+
"step": 234
|
| 1446 |
+
},
|
| 1447 |
+
{
|
| 1448 |
+
"epoch": 0.02,
|
| 1449 |
+
"learning_rate": 4.9977062795584893e-05,
|
| 1450 |
+
"loss": 0.8078,
|
| 1451 |
+
"step": 235
|
| 1452 |
+
},
|
| 1453 |
+
{
|
| 1454 |
+
"epoch": 0.02,
|
| 1455 |
+
"learning_rate": 4.99767217795316e-05,
|
| 1456 |
+
"loss": 1.2065,
|
| 1457 |
+
"step": 236
|
| 1458 |
+
},
|
| 1459 |
+
{
|
| 1460 |
+
"epoch": 0.02,
|
| 1461 |
+
"learning_rate": 4.9976378248323095e-05,
|
| 1462 |
+
"loss": 0.6946,
|
| 1463 |
+
"step": 237
|
| 1464 |
+
},
|
| 1465 |
+
{
|
| 1466 |
+
"epoch": 0.02,
|
| 1467 |
+
"learning_rate": 4.997603220199399e-05,
|
| 1468 |
+
"loss": 0.8255,
|
| 1469 |
+
"step": 238
|
| 1470 |
+
},
|
| 1471 |
+
{
|
| 1472 |
+
"epoch": 0.02,
|
| 1473 |
+
"learning_rate": 4.9975683640579126e-05,
|
| 1474 |
+
"loss": 0.9762,
|
| 1475 |
+
"step": 239
|
| 1476 |
+
},
|
| 1477 |
+
{
|
| 1478 |
+
"epoch": 0.02,
|
| 1479 |
+
"learning_rate": 4.99753325641136e-05,
|
| 1480 |
+
"loss": 0.9771,
|
| 1481 |
+
"step": 240
|
| 1482 |
+
},
|
| 1483 |
+
{
|
| 1484 |
+
"epoch": 0.02,
|
| 1485 |
+
"learning_rate": 4.997497897263277e-05,
|
| 1486 |
+
"loss": 0.8766,
|
| 1487 |
+
"step": 241
|
| 1488 |
+
},
|
| 1489 |
+
{
|
| 1490 |
+
"epoch": 0.02,
|
| 1491 |
+
"learning_rate": 4.997462286617224e-05,
|
| 1492 |
+
"loss": 1.03,
|
| 1493 |
+
"step": 242
|
| 1494 |
+
},
|
| 1495 |
+
{
|
| 1496 |
+
"epoch": 0.02,
|
| 1497 |
+
"learning_rate": 4.997426424476787e-05,
|
| 1498 |
+
"loss": 0.7792,
|
| 1499 |
+
"step": 243
|
| 1500 |
+
},
|
| 1501 |
+
{
|
| 1502 |
+
"epoch": 0.02,
|
| 1503 |
+
"learning_rate": 4.997390310845578e-05,
|
| 1504 |
+
"loss": 0.7772,
|
| 1505 |
+
"step": 244
|
| 1506 |
+
},
|
| 1507 |
+
{
|
| 1508 |
+
"epoch": 0.02,
|
| 1509 |
+
"learning_rate": 4.997353945727232e-05,
|
| 1510 |
+
"loss": 0.9822,
|
| 1511 |
+
"step": 245
|
| 1512 |
+
},
|
| 1513 |
+
{
|
| 1514 |
+
"epoch": 0.02,
|
| 1515 |
+
"learning_rate": 4.9973173291254126e-05,
|
| 1516 |
+
"loss": 0.9403,
|
| 1517 |
+
"step": 246
|
| 1518 |
+
},
|
| 1519 |
+
{
|
| 1520 |
+
"epoch": 0.02,
|
| 1521 |
+
"learning_rate": 4.997280461043806e-05,
|
| 1522 |
+
"loss": 1.117,
|
| 1523 |
+
"step": 247
|
| 1524 |
+
},
|
| 1525 |
+
{
|
| 1526 |
+
"epoch": 0.02,
|
| 1527 |
+
"learning_rate": 4.997243341486127e-05,
|
| 1528 |
+
"loss": 1.3156,
|
| 1529 |
+
"step": 248
|
| 1530 |
+
},
|
| 1531 |
+
{
|
| 1532 |
+
"epoch": 0.02,
|
| 1533 |
+
"learning_rate": 4.9972059704561094e-05,
|
| 1534 |
+
"loss": 0.7289,
|
| 1535 |
+
"step": 249
|
| 1536 |
+
},
|
| 1537 |
+
{
|
| 1538 |
+
"epoch": 0.03,
|
| 1539 |
+
"learning_rate": 4.99716834795752e-05,
|
| 1540 |
+
"loss": 0.7193,
|
| 1541 |
+
"step": 250
|
| 1542 |
+
},
|
| 1543 |
+
{
|
| 1544 |
+
"epoch": 0.03,
|
| 1545 |
+
"eval_loss": 1.108275294303894,
|
| 1546 |
+
"eval_runtime": 72.6609,
|
| 1547 |
+
"eval_samples_per_second": 2.739,
|
| 1548 |
+
"eval_steps_per_second": 0.688,
|
| 1549 |
+
"step": 250
|
| 1550 |
+
},
|
| 1551 |
+
{
|
| 1552 |
+
"epoch": 0.03,
|
| 1553 |
+
"learning_rate": 4.9971304739941465e-05,
|
| 1554 |
+
"loss": 0.8273,
|
| 1555 |
+
"step": 251
|
| 1556 |
+
},
|
| 1557 |
+
{
|
| 1558 |
+
"epoch": 0.03,
|
| 1559 |
+
"learning_rate": 4.9970923485698025e-05,
|
| 1560 |
+
"loss": 0.8979,
|
| 1561 |
+
"step": 252
|
| 1562 |
+
},
|
| 1563 |
+
{
|
| 1564 |
+
"epoch": 0.03,
|
| 1565 |
+
"learning_rate": 4.997053971688327e-05,
|
| 1566 |
+
"loss": 1.1935,
|
| 1567 |
+
"step": 253
|
| 1568 |
+
},
|
| 1569 |
+
{
|
| 1570 |
+
"epoch": 0.03,
|
| 1571 |
+
"learning_rate": 4.997015343353585e-05,
|
| 1572 |
+
"loss": 0.6769,
|
| 1573 |
+
"step": 254
|
| 1574 |
+
},
|
| 1575 |
+
{
|
| 1576 |
+
"epoch": 0.03,
|
| 1577 |
+
"learning_rate": 4.996976463569467e-05,
|
| 1578 |
+
"loss": 0.1888,
|
| 1579 |
+
"step": 255
|
| 1580 |
+
},
|
| 1581 |
+
{
|
| 1582 |
+
"epoch": 0.03,
|
| 1583 |
+
"learning_rate": 4.996937332339887e-05,
|
| 1584 |
+
"loss": 0.6274,
|
| 1585 |
+
"step": 256
|
| 1586 |
+
},
|
| 1587 |
+
{
|
| 1588 |
+
"epoch": 0.03,
|
| 1589 |
+
"learning_rate": 4.996897949668785e-05,
|
| 1590 |
+
"loss": 1.1241,
|
| 1591 |
+
"step": 257
|
| 1592 |
+
},
|
| 1593 |
+
{
|
| 1594 |
+
"epoch": 0.03,
|
| 1595 |
+
"learning_rate": 4.996858315560129e-05,
|
| 1596 |
+
"loss": 1.4104,
|
| 1597 |
+
"step": 258
|
| 1598 |
+
},
|
| 1599 |
+
{
|
| 1600 |
+
"epoch": 0.03,
|
| 1601 |
+
"learning_rate": 4.996818430017908e-05,
|
| 1602 |
+
"loss": 1.5033,
|
| 1603 |
+
"step": 259
|
| 1604 |
+
},
|
| 1605 |
+
{
|
| 1606 |
+
"epoch": 0.03,
|
| 1607 |
+
"learning_rate": 4.996778293046141e-05,
|
| 1608 |
+
"loss": 0.9864,
|
| 1609 |
+
"step": 260
|
| 1610 |
+
},
|
| 1611 |
+
{
|
| 1612 |
+
"epoch": 0.03,
|
| 1613 |
+
"learning_rate": 4.996737904648866e-05,
|
| 1614 |
+
"loss": 1.2575,
|
| 1615 |
+
"step": 261
|
| 1616 |
+
},
|
| 1617 |
+
{
|
| 1618 |
+
"epoch": 0.03,
|
| 1619 |
+
"learning_rate": 4.9966972648301536e-05,
|
| 1620 |
+
"loss": 0.4235,
|
| 1621 |
+
"step": 262
|
| 1622 |
+
},
|
| 1623 |
+
{
|
| 1624 |
+
"epoch": 0.03,
|
| 1625 |
+
"learning_rate": 4.996656373594095e-05,
|
| 1626 |
+
"loss": 0.9705,
|
| 1627 |
+
"step": 263
|
| 1628 |
+
},
|
| 1629 |
+
{
|
| 1630 |
+
"epoch": 0.03,
|
| 1631 |
+
"learning_rate": 4.9966152309448076e-05,
|
| 1632 |
+
"loss": 1.1265,
|
| 1633 |
+
"step": 264
|
| 1634 |
+
},
|
| 1635 |
+
{
|
| 1636 |
+
"epoch": 0.03,
|
| 1637 |
+
"learning_rate": 4.996573836886435e-05,
|
| 1638 |
+
"loss": 1.0598,
|
| 1639 |
+
"step": 265
|
| 1640 |
+
},
|
| 1641 |
+
{
|
| 1642 |
+
"epoch": 0.03,
|
| 1643 |
+
"learning_rate": 4.996532191423145e-05,
|
| 1644 |
+
"loss": 0.9536,
|
| 1645 |
+
"step": 266
|
| 1646 |
+
},
|
| 1647 |
+
{
|
| 1648 |
+
"epoch": 0.03,
|
| 1649 |
+
"learning_rate": 4.996490294559132e-05,
|
| 1650 |
+
"loss": 0.936,
|
| 1651 |
+
"step": 267
|
| 1652 |
+
},
|
| 1653 |
+
{
|
| 1654 |
+
"epoch": 0.03,
|
| 1655 |
+
"learning_rate": 4.996448146298614e-05,
|
| 1656 |
+
"loss": 1.1793,
|
| 1657 |
+
"step": 268
|
| 1658 |
+
},
|
| 1659 |
+
{
|
| 1660 |
+
"epoch": 0.03,
|
| 1661 |
+
"learning_rate": 4.996405746645837e-05,
|
| 1662 |
+
"loss": 0.8472,
|
| 1663 |
+
"step": 269
|
| 1664 |
+
},
|
| 1665 |
+
{
|
| 1666 |
+
"epoch": 0.03,
|
| 1667 |
+
"learning_rate": 4.996363095605069e-05,
|
| 1668 |
+
"loss": 0.861,
|
| 1669 |
+
"step": 270
|
| 1670 |
+
},
|
| 1671 |
+
{
|
| 1672 |
+
"epoch": 0.03,
|
| 1673 |
+
"learning_rate": 4.996320193180606e-05,
|
| 1674 |
+
"loss": 0.7457,
|
| 1675 |
+
"step": 271
|
| 1676 |
+
},
|
| 1677 |
+
{
|
| 1678 |
+
"epoch": 0.03,
|
| 1679 |
+
"learning_rate": 4.996277039376767e-05,
|
| 1680 |
+
"loss": 0.9936,
|
| 1681 |
+
"step": 272
|
| 1682 |
+
},
|
| 1683 |
+
{
|
| 1684 |
+
"epoch": 0.03,
|
| 1685 |
+
"learning_rate": 4.996233634197899e-05,
|
| 1686 |
+
"loss": 0.6526,
|
| 1687 |
+
"step": 273
|
| 1688 |
+
},
|
| 1689 |
+
{
|
| 1690 |
+
"epoch": 0.03,
|
| 1691 |
+
"learning_rate": 4.996189977648372e-05,
|
| 1692 |
+
"loss": 0.6052,
|
| 1693 |
+
"step": 274
|
| 1694 |
+
},
|
| 1695 |
+
{
|
| 1696 |
+
"epoch": 0.03,
|
| 1697 |
+
"learning_rate": 4.996146069732583e-05,
|
| 1698 |
+
"loss": 0.3457,
|
| 1699 |
+
"step": 275
|
| 1700 |
+
},
|
| 1701 |
+
{
|
| 1702 |
+
"epoch": 0.03,
|
| 1703 |
+
"learning_rate": 4.996101910454953e-05,
|
| 1704 |
+
"loss": 0.8991,
|
| 1705 |
+
"step": 276
|
| 1706 |
+
},
|
| 1707 |
+
{
|
| 1708 |
+
"epoch": 0.03,
|
| 1709 |
+
"learning_rate": 4.9960574998199285e-05,
|
| 1710 |
+
"loss": 2.1928,
|
| 1711 |
+
"step": 277
|
| 1712 |
+
},
|
| 1713 |
+
{
|
| 1714 |
+
"epoch": 0.03,
|
| 1715 |
+
"learning_rate": 4.9960128378319825e-05,
|
| 1716 |
+
"loss": 1.5278,
|
| 1717 |
+
"step": 278
|
| 1718 |
+
},
|
| 1719 |
+
{
|
| 1720 |
+
"epoch": 0.03,
|
| 1721 |
+
"learning_rate": 4.995967924495611e-05,
|
| 1722 |
+
"loss": 0.7869,
|
| 1723 |
+
"step": 279
|
| 1724 |
+
},
|
| 1725 |
+
{
|
| 1726 |
+
"epoch": 0.03,
|
| 1727 |
+
"learning_rate": 4.995922759815339e-05,
|
| 1728 |
+
"loss": 0.75,
|
| 1729 |
+
"step": 280
|
| 1730 |
+
},
|
| 1731 |
+
{
|
| 1732 |
+
"epoch": 0.03,
|
| 1733 |
+
"learning_rate": 4.995877343795714e-05,
|
| 1734 |
+
"loss": 0.8104,
|
| 1735 |
+
"step": 281
|
| 1736 |
+
},
|
| 1737 |
+
{
|
| 1738 |
+
"epoch": 0.03,
|
| 1739 |
+
"learning_rate": 4.995831676441307e-05,
|
| 1740 |
+
"loss": 0.9529,
|
| 1741 |
+
"step": 282
|
| 1742 |
+
},
|
| 1743 |
+
{
|
| 1744 |
+
"epoch": 0.03,
|
| 1745 |
+
"learning_rate": 4.9957857577567197e-05,
|
| 1746 |
+
"loss": 0.9996,
|
| 1747 |
+
"step": 283
|
| 1748 |
+
},
|
| 1749 |
+
{
|
| 1750 |
+
"epoch": 0.03,
|
| 1751 |
+
"learning_rate": 4.995739587746574e-05,
|
| 1752 |
+
"loss": 0.6799,
|
| 1753 |
+
"step": 284
|
| 1754 |
+
},
|
| 1755 |
+
{
|
| 1756 |
+
"epoch": 0.03,
|
| 1757 |
+
"learning_rate": 4.995693166415521e-05,
|
| 1758 |
+
"loss": 0.3521,
|
| 1759 |
+
"step": 285
|
| 1760 |
+
},
|
| 1761 |
+
{
|
| 1762 |
+
"epoch": 0.03,
|
| 1763 |
+
"learning_rate": 4.995646493768234e-05,
|
| 1764 |
+
"loss": 0.7761,
|
| 1765 |
+
"step": 286
|
| 1766 |
+
},
|
| 1767 |
+
{
|
| 1768 |
+
"epoch": 0.03,
|
| 1769 |
+
"learning_rate": 4.995599569809414e-05,
|
| 1770 |
+
"loss": 1.4368,
|
| 1771 |
+
"step": 287
|
| 1772 |
+
},
|
| 1773 |
+
{
|
| 1774 |
+
"epoch": 0.03,
|
| 1775 |
+
"learning_rate": 4.995552394543784e-05,
|
| 1776 |
+
"loss": 1.2596,
|
| 1777 |
+
"step": 288
|
| 1778 |
+
},
|
| 1779 |
+
{
|
| 1780 |
+
"epoch": 0.03,
|
| 1781 |
+
"learning_rate": 4.995504967976098e-05,
|
| 1782 |
+
"loss": 1.2384,
|
| 1783 |
+
"step": 289
|
| 1784 |
+
},
|
| 1785 |
+
{
|
| 1786 |
+
"epoch": 0.03,
|
| 1787 |
+
"learning_rate": 4.9954572901111286e-05,
|
| 1788 |
+
"loss": 1.2618,
|
| 1789 |
+
"step": 290
|
| 1790 |
+
},
|
| 1791 |
+
{
|
| 1792 |
+
"epoch": 0.03,
|
| 1793 |
+
"learning_rate": 4.995409360953679e-05,
|
| 1794 |
+
"loss": 1.1813,
|
| 1795 |
+
"step": 291
|
| 1796 |
+
},
|
| 1797 |
+
{
|
| 1798 |
+
"epoch": 0.03,
|
| 1799 |
+
"learning_rate": 4.995361180508575e-05,
|
| 1800 |
+
"loss": 1.2225,
|
| 1801 |
+
"step": 292
|
| 1802 |
+
},
|
| 1803 |
+
{
|
| 1804 |
+
"epoch": 0.03,
|
| 1805 |
+
"learning_rate": 4.995312748780668e-05,
|
| 1806 |
+
"loss": 1.6035,
|
| 1807 |
+
"step": 293
|
| 1808 |
+
},
|
| 1809 |
+
{
|
| 1810 |
+
"epoch": 0.03,
|
| 1811 |
+
"learning_rate": 4.995264065774836e-05,
|
| 1812 |
+
"loss": 1.0326,
|
| 1813 |
+
"step": 294
|
| 1814 |
+
},
|
| 1815 |
+
{
|
| 1816 |
+
"epoch": 0.03,
|
| 1817 |
+
"learning_rate": 4.995215131495981e-05,
|
| 1818 |
+
"loss": 1.1068,
|
| 1819 |
+
"step": 295
|
| 1820 |
+
},
|
| 1821 |
+
{
|
| 1822 |
+
"epoch": 0.03,
|
| 1823 |
+
"learning_rate": 4.9951659459490294e-05,
|
| 1824 |
+
"loss": 1.1749,
|
| 1825 |
+
"step": 296
|
| 1826 |
+
},
|
| 1827 |
+
{
|
| 1828 |
+
"epoch": 0.03,
|
| 1829 |
+
"learning_rate": 4.995116509138936e-05,
|
| 1830 |
+
"loss": 0.7934,
|
| 1831 |
+
"step": 297
|
| 1832 |
+
},
|
| 1833 |
+
{
|
| 1834 |
+
"epoch": 0.03,
|
| 1835 |
+
"learning_rate": 4.995066821070679e-05,
|
| 1836 |
+
"loss": 0.7168,
|
| 1837 |
+
"step": 298
|
| 1838 |
+
},
|
| 1839 |
+
{
|
| 1840 |
+
"epoch": 0.03,
|
| 1841 |
+
"learning_rate": 4.995016881749261e-05,
|
| 1842 |
+
"loss": 1.1443,
|
| 1843 |
+
"step": 299
|
| 1844 |
+
},
|
| 1845 |
+
{
|
| 1846 |
+
"epoch": 0.03,
|
| 1847 |
+
"learning_rate": 4.994966691179711e-05,
|
| 1848 |
+
"loss": 1.0016,
|
| 1849 |
+
"step": 300
|
| 1850 |
+
},
|
| 1851 |
+
{
|
| 1852 |
+
"epoch": 0.03,
|
| 1853 |
+
"eval_loss": 1.1079908609390259,
|
| 1854 |
+
"eval_runtime": 72.0399,
|
| 1855 |
+
"eval_samples_per_second": 2.762,
|
| 1856 |
+
"eval_steps_per_second": 0.694,
|
| 1857 |
+
"step": 300
|
| 1858 |
+
},
|
| 1859 |
+
{
|
| 1860 |
+
"epoch": 0.03,
|
| 1861 |
+
"learning_rate": 4.994916249367084e-05,
|
| 1862 |
+
"loss": 0.8799,
|
| 1863 |
+
"step": 301
|
| 1864 |
+
},
|
| 1865 |
+
{
|
| 1866 |
+
"epoch": 0.03,
|
| 1867 |
+
"learning_rate": 4.994865556316458e-05,
|
| 1868 |
+
"loss": 0.7981,
|
| 1869 |
+
"step": 302
|
| 1870 |
+
},
|
| 1871 |
+
{
|
| 1872 |
+
"epoch": 0.03,
|
| 1873 |
+
"learning_rate": 4.9948146120329395e-05,
|
| 1874 |
+
"loss": 1.1415,
|
| 1875 |
+
"step": 303
|
| 1876 |
+
},
|
| 1877 |
+
{
|
| 1878 |
+
"epoch": 0.03,
|
| 1879 |
+
"learning_rate": 4.9947634165216584e-05,
|
| 1880 |
+
"loss": 0.7678,
|
| 1881 |
+
"step": 304
|
| 1882 |
+
},
|
| 1883 |
+
{
|
| 1884 |
+
"epoch": 0.03,
|
| 1885 |
+
"learning_rate": 4.994711969787769e-05,
|
| 1886 |
+
"loss": 0.6894,
|
| 1887 |
+
"step": 305
|
| 1888 |
+
},
|
| 1889 |
+
{
|
| 1890 |
+
"epoch": 0.03,
|
| 1891 |
+
"learning_rate": 4.9946602718364515e-05,
|
| 1892 |
+
"loss": 0.2112,
|
| 1893 |
+
"step": 306
|
| 1894 |
+
},
|
| 1895 |
+
{
|
| 1896 |
+
"epoch": 0.03,
|
| 1897 |
+
"learning_rate": 4.994608322672914e-05,
|
| 1898 |
+
"loss": 0.0144,
|
| 1899 |
+
"step": 307
|
| 1900 |
+
},
|
| 1901 |
+
{
|
| 1902 |
+
"epoch": 0.03,
|
| 1903 |
+
"learning_rate": 4.994556122302386e-05,
|
| 1904 |
+
"loss": 0.0126,
|
| 1905 |
+
"step": 308
|
| 1906 |
+
},
|
| 1907 |
+
{
|
| 1908 |
+
"epoch": 0.03,
|
| 1909 |
+
"learning_rate": 4.994503670730125e-05,
|
| 1910 |
+
"loss": 0.0285,
|
| 1911 |
+
"step": 309
|
| 1912 |
+
},
|
| 1913 |
+
{
|
| 1914 |
+
"epoch": 0.03,
|
| 1915 |
+
"learning_rate": 4.994450967961413e-05,
|
| 1916 |
+
"loss": 0.0182,
|
| 1917 |
+
"step": 310
|
| 1918 |
+
},
|
| 1919 |
+
{
|
| 1920 |
+
"epoch": 0.03,
|
| 1921 |
+
"learning_rate": 4.994398014001557e-05,
|
| 1922 |
+
"loss": 0.0169,
|
| 1923 |
+
"step": 311
|
| 1924 |
+
},
|
| 1925 |
+
{
|
| 1926 |
+
"epoch": 0.03,
|
| 1927 |
+
"learning_rate": 4.994344808855888e-05,
|
| 1928 |
+
"loss": 0.0094,
|
| 1929 |
+
"step": 312
|
| 1930 |
+
},
|
| 1931 |
+
{
|
| 1932 |
+
"epoch": 0.03,
|
| 1933 |
+
"learning_rate": 4.9942913525297655e-05,
|
| 1934 |
+
"loss": 0.0169,
|
| 1935 |
+
"step": 313
|
| 1936 |
+
},
|
| 1937 |
+
{
|
| 1938 |
+
"epoch": 0.03,
|
| 1939 |
+
"learning_rate": 4.994237645028572e-05,
|
| 1940 |
+
"loss": 0.0135,
|
| 1941 |
+
"step": 314
|
| 1942 |
+
},
|
| 1943 |
+
{
|
| 1944 |
+
"epoch": 0.03,
|
| 1945 |
+
"learning_rate": 4.994183686357717e-05,
|
| 1946 |
+
"loss": 0.0131,
|
| 1947 |
+
"step": 315
|
| 1948 |
+
},
|
| 1949 |
+
{
|
| 1950 |
+
"epoch": 0.03,
|
| 1951 |
+
"learning_rate": 4.994129476522632e-05,
|
| 1952 |
+
"loss": 0.0138,
|
| 1953 |
+
"step": 316
|
| 1954 |
+
},
|
| 1955 |
+
{
|
| 1956 |
+
"epoch": 0.03,
|
| 1957 |
+
"learning_rate": 4.9940750155287775e-05,
|
| 1958 |
+
"loss": 0.0172,
|
| 1959 |
+
"step": 317
|
| 1960 |
+
},
|
| 1961 |
+
{
|
| 1962 |
+
"epoch": 0.03,
|
| 1963 |
+
"learning_rate": 4.994020303381636e-05,
|
| 1964 |
+
"loss": 0.0196,
|
| 1965 |
+
"step": 318
|
| 1966 |
+
},
|
| 1967 |
+
{
|
| 1968 |
+
"epoch": 0.03,
|
| 1969 |
+
"learning_rate": 4.993965340086719e-05,
|
| 1970 |
+
"loss": 0.0103,
|
| 1971 |
+
"step": 319
|
| 1972 |
+
},
|
| 1973 |
+
{
|
| 1974 |
+
"epoch": 0.03,
|
| 1975 |
+
"learning_rate": 4.993910125649561e-05,
|
| 1976 |
+
"loss": 0.018,
|
| 1977 |
+
"step": 320
|
| 1978 |
+
},
|
| 1979 |
+
{
|
| 1980 |
+
"epoch": 0.03,
|
| 1981 |
+
"learning_rate": 4.9938546600757205e-05,
|
| 1982 |
+
"loss": 0.0128,
|
| 1983 |
+
"step": 321
|
| 1984 |
+
},
|
| 1985 |
+
{
|
| 1986 |
+
"epoch": 0.03,
|
| 1987 |
+
"learning_rate": 4.993798943370785e-05,
|
| 1988 |
+
"loss": 0.0112,
|
| 1989 |
+
"step": 322
|
| 1990 |
+
},
|
| 1991 |
+
{
|
| 1992 |
+
"epoch": 0.03,
|
| 1993 |
+
"learning_rate": 4.9937429755403634e-05,
|
| 1994 |
+
"loss": 0.0176,
|
| 1995 |
+
"step": 323
|
| 1996 |
+
},
|
| 1997 |
+
{
|
| 1998 |
+
"epoch": 0.03,
|
| 1999 |
+
"learning_rate": 4.993686756590093e-05,
|
| 2000 |
+
"loss": 0.371,
|
| 2001 |
+
"step": 324
|
| 2002 |
+
},
|
| 2003 |
+
{
|
| 2004 |
+
"epoch": 0.03,
|
| 2005 |
+
"learning_rate": 4.993630286525634e-05,
|
| 2006 |
+
"loss": 0.5097,
|
| 2007 |
+
"step": 325
|
| 2008 |
+
},
|
| 2009 |
+
{
|
| 2010 |
+
"epoch": 0.03,
|
| 2011 |
+
"learning_rate": 4.993573565352674e-05,
|
| 2012 |
+
"loss": 0.8996,
|
| 2013 |
+
"step": 326
|
| 2014 |
+
},
|
| 2015 |
+
{
|
| 2016 |
+
"epoch": 0.03,
|
| 2017 |
+
"learning_rate": 4.9935165930769235e-05,
|
| 2018 |
+
"loss": 0.9685,
|
| 2019 |
+
"step": 327
|
| 2020 |
+
},
|
| 2021 |
+
{
|
| 2022 |
+
"epoch": 0.03,
|
| 2023 |
+
"learning_rate": 4.99345936970412e-05,
|
| 2024 |
+
"loss": 0.5462,
|
| 2025 |
+
"step": 328
|
| 2026 |
+
},
|
| 2027 |
+
{
|
| 2028 |
+
"epoch": 0.03,
|
| 2029 |
+
"learning_rate": 4.993401895240027e-05,
|
| 2030 |
+
"loss": 0.8048,
|
| 2031 |
+
"step": 329
|
| 2032 |
+
},
|
| 2033 |
+
{
|
| 2034 |
+
"epoch": 0.03,
|
| 2035 |
+
"learning_rate": 4.993344169690431e-05,
|
| 2036 |
+
"loss": 0.7428,
|
| 2037 |
+
"step": 330
|
| 2038 |
+
},
|
| 2039 |
+
{
|
| 2040 |
+
"epoch": 0.03,
|
| 2041 |
+
"learning_rate": 4.9932861930611454e-05,
|
| 2042 |
+
"loss": 0.9778,
|
| 2043 |
+
"step": 331
|
| 2044 |
+
},
|
| 2045 |
+
{
|
| 2046 |
+
"epoch": 0.03,
|
| 2047 |
+
"learning_rate": 4.993227965358008e-05,
|
| 2048 |
+
"loss": 0.9751,
|
| 2049 |
+
"step": 332
|
| 2050 |
+
},
|
| 2051 |
+
{
|
| 2052 |
+
"epoch": 0.03,
|
| 2053 |
+
"learning_rate": 4.993169486586884e-05,
|
| 2054 |
+
"loss": 0.8585,
|
| 2055 |
+
"step": 333
|
| 2056 |
+
},
|
| 2057 |
+
{
|
| 2058 |
+
"epoch": 0.03,
|
| 2059 |
+
"learning_rate": 4.99311075675366e-05,
|
| 2060 |
+
"loss": 1.0175,
|
| 2061 |
+
"step": 334
|
| 2062 |
+
},
|
| 2063 |
+
{
|
| 2064 |
+
"epoch": 0.03,
|
| 2065 |
+
"learning_rate": 4.9930517758642503e-05,
|
| 2066 |
+
"loss": 0.7355,
|
| 2067 |
+
"step": 335
|
| 2068 |
+
},
|
| 2069 |
+
{
|
| 2070 |
+
"epoch": 0.03,
|
| 2071 |
+
"learning_rate": 4.992992543924596e-05,
|
| 2072 |
+
"loss": 1.1919,
|
| 2073 |
+
"step": 336
|
| 2074 |
+
},
|
| 2075 |
+
{
|
| 2076 |
+
"epoch": 0.03,
|
| 2077 |
+
"learning_rate": 4.992933060940661e-05,
|
| 2078 |
+
"loss": 0.9677,
|
| 2079 |
+
"step": 337
|
| 2080 |
+
},
|
| 2081 |
+
{
|
| 2082 |
+
"epoch": 0.03,
|
| 2083 |
+
"learning_rate": 4.992873326918434e-05,
|
| 2084 |
+
"loss": 0.4328,
|
| 2085 |
+
"step": 338
|
| 2086 |
+
},
|
| 2087 |
+
{
|
| 2088 |
+
"epoch": 0.03,
|
| 2089 |
+
"learning_rate": 4.9928133418639316e-05,
|
| 2090 |
+
"loss": 1.2334,
|
| 2091 |
+
"step": 339
|
| 2092 |
+
},
|
| 2093 |
+
{
|
| 2094 |
+
"epoch": 0.03,
|
| 2095 |
+
"learning_rate": 4.992753105783194e-05,
|
| 2096 |
+
"loss": 1.3437,
|
| 2097 |
+
"step": 340
|
| 2098 |
+
},
|
| 2099 |
+
{
|
| 2100 |
+
"epoch": 0.03,
|
| 2101 |
+
"learning_rate": 4.992692618682286e-05,
|
| 2102 |
+
"loss": 1.3923,
|
| 2103 |
+
"step": 341
|
| 2104 |
+
},
|
| 2105 |
+
{
|
| 2106 |
+
"epoch": 0.03,
|
| 2107 |
+
"learning_rate": 4.992631880567301e-05,
|
| 2108 |
+
"loss": 0.747,
|
| 2109 |
+
"step": 342
|
| 2110 |
+
},
|
| 2111 |
+
{
|
| 2112 |
+
"epoch": 0.03,
|
| 2113 |
+
"learning_rate": 4.9925708914443526e-05,
|
| 2114 |
+
"loss": 0.7077,
|
| 2115 |
+
"step": 343
|
| 2116 |
+
},
|
| 2117 |
+
{
|
| 2118 |
+
"epoch": 0.03,
|
| 2119 |
+
"learning_rate": 4.9925096513195846e-05,
|
| 2120 |
+
"loss": 0.8386,
|
| 2121 |
+
"step": 344
|
| 2122 |
+
},
|
| 2123 |
+
{
|
| 2124 |
+
"epoch": 0.03,
|
| 2125 |
+
"learning_rate": 4.992448160199162e-05,
|
| 2126 |
+
"loss": 1.0766,
|
| 2127 |
+
"step": 345
|
| 2128 |
+
},
|
| 2129 |
+
{
|
| 2130 |
+
"epoch": 0.03,
|
| 2131 |
+
"learning_rate": 4.992386418089279e-05,
|
| 2132 |
+
"loss": 2.5327,
|
| 2133 |
+
"step": 346
|
| 2134 |
+
},
|
| 2135 |
+
{
|
| 2136 |
+
"epoch": 0.03,
|
| 2137 |
+
"learning_rate": 4.992324424996151e-05,
|
| 2138 |
+
"loss": 0.669,
|
| 2139 |
+
"step": 347
|
| 2140 |
+
},
|
| 2141 |
+
{
|
| 2142 |
+
"epoch": 0.03,
|
| 2143 |
+
"learning_rate": 4.992262180926022e-05,
|
| 2144 |
+
"loss": 1.1023,
|
| 2145 |
+
"step": 348
|
| 2146 |
+
},
|
| 2147 |
+
{
|
| 2148 |
+
"epoch": 0.03,
|
| 2149 |
+
"learning_rate": 4.992199685885159e-05,
|
| 2150 |
+
"loss": 0.9316,
|
| 2151 |
+
"step": 349
|
| 2152 |
+
},
|
| 2153 |
+
{
|
| 2154 |
+
"epoch": 0.04,
|
| 2155 |
+
"learning_rate": 4.992136939879856e-05,
|
| 2156 |
+
"loss": 1.0181,
|
| 2157 |
+
"step": 350
|
| 2158 |
+
},
|
| 2159 |
+
{
|
| 2160 |
+
"epoch": 0.04,
|
| 2161 |
+
"eval_loss": 1.1037520170211792,
|
| 2162 |
+
"eval_runtime": 72.8274,
|
| 2163 |
+
"eval_samples_per_second": 2.732,
|
| 2164 |
+
"eval_steps_per_second": 0.687,
|
| 2165 |
+
"step": 350
|
| 2166 |
+
},
|
| 2167 |
+
{
|
| 2168 |
+
"epoch": 0.04,
|
| 2169 |
+
"learning_rate": 4.992073942916432e-05,
|
| 2170 |
+
"loss": 1.1855,
|
| 2171 |
+
"step": 351
|
| 2172 |
+
},
|
| 2173 |
+
{
|
| 2174 |
+
"epoch": 0.04,
|
| 2175 |
+
"learning_rate": 4.992010695001229e-05,
|
| 2176 |
+
"loss": 0.7205,
|
| 2177 |
+
"step": 352
|
| 2178 |
+
},
|
| 2179 |
+
{
|
| 2180 |
+
"epoch": 0.04,
|
| 2181 |
+
"learning_rate": 4.991947196140618e-05,
|
| 2182 |
+
"loss": 0.7094,
|
| 2183 |
+
"step": 353
|
| 2184 |
+
},
|
| 2185 |
+
{
|
| 2186 |
+
"epoch": 0.04,
|
| 2187 |
+
"learning_rate": 4.991883446340992e-05,
|
| 2188 |
+
"loss": 1.0553,
|
| 2189 |
+
"step": 354
|
| 2190 |
+
},
|
| 2191 |
+
{
|
| 2192 |
+
"epoch": 0.04,
|
| 2193 |
+
"learning_rate": 4.991819445608772e-05,
|
| 2194 |
+
"loss": 0.8234,
|
| 2195 |
+
"step": 355
|
| 2196 |
+
},
|
| 2197 |
+
{
|
| 2198 |
+
"epoch": 0.04,
|
| 2199 |
+
"learning_rate": 4.991755193950401e-05,
|
| 2200 |
+
"loss": 0.3084,
|
| 2201 |
+
"step": 356
|
| 2202 |
+
},
|
| 2203 |
+
{
|
| 2204 |
+
"epoch": 0.04,
|
| 2205 |
+
"learning_rate": 4.991690691372352e-05,
|
| 2206 |
+
"loss": 0.1456,
|
| 2207 |
+
"step": 357
|
| 2208 |
+
},
|
| 2209 |
+
{
|
| 2210 |
+
"epoch": 0.04,
|
| 2211 |
+
"learning_rate": 4.991625937881116e-05,
|
| 2212 |
+
"loss": 0.5623,
|
| 2213 |
+
"step": 358
|
| 2214 |
+
},
|
| 2215 |
+
{
|
| 2216 |
+
"epoch": 0.04,
|
| 2217 |
+
"learning_rate": 4.991560933483218e-05,
|
| 2218 |
+
"loss": 0.5258,
|
| 2219 |
+
"step": 359
|
| 2220 |
+
},
|
| 2221 |
+
{
|
| 2222 |
+
"epoch": 0.04,
|
| 2223 |
+
"learning_rate": 4.991495678185202e-05,
|
| 2224 |
+
"loss": 0.5237,
|
| 2225 |
+
"step": 360
|
| 2226 |
+
},
|
| 2227 |
+
{
|
| 2228 |
+
"epoch": 0.04,
|
| 2229 |
+
"learning_rate": 4.9914301719936386e-05,
|
| 2230 |
+
"loss": 0.9311,
|
| 2231 |
+
"step": 361
|
| 2232 |
+
},
|
| 2233 |
+
{
|
| 2234 |
+
"epoch": 0.04,
|
| 2235 |
+
"learning_rate": 4.9913644149151256e-05,
|
| 2236 |
+
"loss": 2.1465,
|
| 2237 |
+
"step": 362
|
| 2238 |
+
},
|
| 2239 |
+
{
|
| 2240 |
+
"epoch": 0.04,
|
| 2241 |
+
"learning_rate": 4.991298406956284e-05,
|
| 2242 |
+
"loss": 1.0485,
|
| 2243 |
+
"step": 363
|
| 2244 |
+
},
|
| 2245 |
+
{
|
| 2246 |
+
"epoch": 0.04,
|
| 2247 |
+
"learning_rate": 4.991232148123761e-05,
|
| 2248 |
+
"loss": 0.5495,
|
| 2249 |
+
"step": 364
|
| 2250 |
+
},
|
| 2251 |
+
{
|
| 2252 |
+
"epoch": 0.04,
|
| 2253 |
+
"learning_rate": 4.991165638424229e-05,
|
| 2254 |
+
"loss": 0.5886,
|
| 2255 |
+
"step": 365
|
| 2256 |
+
},
|
| 2257 |
+
{
|
| 2258 |
+
"epoch": 0.04,
|
| 2259 |
+
"learning_rate": 4.991098877864385e-05,
|
| 2260 |
+
"loss": 0.9717,
|
| 2261 |
+
"step": 366
|
| 2262 |
+
},
|
| 2263 |
+
{
|
| 2264 |
+
"epoch": 0.04,
|
| 2265 |
+
"learning_rate": 4.991031866450953e-05,
|
| 2266 |
+
"loss": 0.6979,
|
| 2267 |
+
"step": 367
|
| 2268 |
+
},
|
| 2269 |
+
{
|
| 2270 |
+
"epoch": 0.04,
|
| 2271 |
+
"learning_rate": 4.990964604190679e-05,
|
| 2272 |
+
"loss": 0.3933,
|
| 2273 |
+
"step": 368
|
| 2274 |
+
},
|
| 2275 |
+
{
|
| 2276 |
+
"epoch": 0.04,
|
| 2277 |
+
"learning_rate": 4.990897091090338e-05,
|
| 2278 |
+
"loss": 0.7745,
|
| 2279 |
+
"step": 369
|
| 2280 |
+
},
|
| 2281 |
+
{
|
| 2282 |
+
"epoch": 0.04,
|
| 2283 |
+
"learning_rate": 4.9908293271567286e-05,
|
| 2284 |
+
"loss": 0.7866,
|
| 2285 |
+
"step": 370
|
| 2286 |
+
},
|
| 2287 |
+
{
|
| 2288 |
+
"epoch": 0.04,
|
| 2289 |
+
"learning_rate": 4.990761312396673e-05,
|
| 2290 |
+
"loss": 0.7686,
|
| 2291 |
+
"step": 371
|
| 2292 |
+
},
|
| 2293 |
+
{
|
| 2294 |
+
"epoch": 0.04,
|
| 2295 |
+
"learning_rate": 4.990693046817023e-05,
|
| 2296 |
+
"loss": 0.7124,
|
| 2297 |
+
"step": 372
|
| 2298 |
+
},
|
| 2299 |
+
{
|
| 2300 |
+
"epoch": 0.04,
|
| 2301 |
+
"learning_rate": 4.99062453042465e-05,
|
| 2302 |
+
"loss": 1.1124,
|
| 2303 |
+
"step": 373
|
| 2304 |
+
},
|
| 2305 |
+
{
|
| 2306 |
+
"epoch": 0.04,
|
| 2307 |
+
"learning_rate": 4.990555763226455e-05,
|
| 2308 |
+
"loss": 0.8905,
|
| 2309 |
+
"step": 374
|
| 2310 |
+
},
|
| 2311 |
+
{
|
| 2312 |
+
"epoch": 0.04,
|
| 2313 |
+
"learning_rate": 4.990486745229364e-05,
|
| 2314 |
+
"loss": 1.0419,
|
| 2315 |
+
"step": 375
|
| 2316 |
+
},
|
| 2317 |
+
{
|
| 2318 |
+
"epoch": 0.04,
|
| 2319 |
+
"learning_rate": 4.9904174764403255e-05,
|
| 2320 |
+
"loss": 1.1019,
|
| 2321 |
+
"step": 376
|
| 2322 |
+
},
|
| 2323 |
+
{
|
| 2324 |
+
"epoch": 0.04,
|
| 2325 |
+
"learning_rate": 4.990347956866315e-05,
|
| 2326 |
+
"loss": 0.6797,
|
| 2327 |
+
"step": 377
|
| 2328 |
+
},
|
| 2329 |
+
{
|
| 2330 |
+
"epoch": 0.04,
|
| 2331 |
+
"learning_rate": 4.9902781865143326e-05,
|
| 2332 |
+
"loss": 0.522,
|
| 2333 |
+
"step": 378
|
| 2334 |
+
},
|
| 2335 |
+
{
|
| 2336 |
+
"epoch": 0.04,
|
| 2337 |
+
"learning_rate": 4.9902081653914056e-05,
|
| 2338 |
+
"loss": 0.8258,
|
| 2339 |
+
"step": 379
|
| 2340 |
+
},
|
| 2341 |
+
{
|
| 2342 |
+
"epoch": 0.04,
|
| 2343 |
+
"learning_rate": 4.990137893504585e-05,
|
| 2344 |
+
"loss": 0.8358,
|
| 2345 |
+
"step": 380
|
| 2346 |
+
},
|
| 2347 |
+
{
|
| 2348 |
+
"epoch": 0.04,
|
| 2349 |
+
"learning_rate": 4.9900673708609455e-05,
|
| 2350 |
+
"loss": 1.0822,
|
| 2351 |
+
"step": 381
|
| 2352 |
+
},
|
| 2353 |
+
{
|
| 2354 |
+
"epoch": 0.04,
|
| 2355 |
+
"learning_rate": 4.989996597467591e-05,
|
| 2356 |
+
"loss": 0.8717,
|
| 2357 |
+
"step": 382
|
| 2358 |
+
},
|
| 2359 |
+
{
|
| 2360 |
+
"epoch": 0.04,
|
| 2361 |
+
"learning_rate": 4.9899255733316465e-05,
|
| 2362 |
+
"loss": 0.8567,
|
| 2363 |
+
"step": 383
|
| 2364 |
+
},
|
| 2365 |
+
{
|
| 2366 |
+
"epoch": 0.04,
|
| 2367 |
+
"learning_rate": 4.9898542984602656e-05,
|
| 2368 |
+
"loss": 0.0489,
|
| 2369 |
+
"step": 384
|
| 2370 |
+
},
|
| 2371 |
+
{
|
| 2372 |
+
"epoch": 0.04,
|
| 2373 |
+
"learning_rate": 4.989782772860624e-05,
|
| 2374 |
+
"loss": 0.0117,
|
| 2375 |
+
"step": 385
|
| 2376 |
+
},
|
| 2377 |
+
{
|
| 2378 |
+
"epoch": 0.04,
|
| 2379 |
+
"learning_rate": 4.989710996539926e-05,
|
| 2380 |
+
"loss": 0.0183,
|
| 2381 |
+
"step": 386
|
| 2382 |
+
},
|
| 2383 |
+
{
|
| 2384 |
+
"epoch": 0.04,
|
| 2385 |
+
"learning_rate": 4.989638969505399e-05,
|
| 2386 |
+
"loss": 0.0143,
|
| 2387 |
+
"step": 387
|
| 2388 |
+
},
|
| 2389 |
+
{
|
| 2390 |
+
"epoch": 0.04,
|
| 2391 |
+
"learning_rate": 4.989566691764295e-05,
|
| 2392 |
+
"loss": 0.0117,
|
| 2393 |
+
"step": 388
|
| 2394 |
+
},
|
| 2395 |
+
{
|
| 2396 |
+
"epoch": 0.04,
|
| 2397 |
+
"learning_rate": 4.989494163323894e-05,
|
| 2398 |
+
"loss": 0.0188,
|
| 2399 |
+
"step": 389
|
| 2400 |
+
},
|
| 2401 |
+
{
|
| 2402 |
+
"epoch": 0.04,
|
| 2403 |
+
"learning_rate": 4.989421384191499e-05,
|
| 2404 |
+
"loss": 0.0138,
|
| 2405 |
+
"step": 390
|
| 2406 |
+
},
|
| 2407 |
+
{
|
| 2408 |
+
"epoch": 0.04,
|
| 2409 |
+
"learning_rate": 4.989348354374438e-05,
|
| 2410 |
+
"loss": 0.0138,
|
| 2411 |
+
"step": 391
|
| 2412 |
+
},
|
| 2413 |
+
{
|
| 2414 |
+
"epoch": 0.04,
|
| 2415 |
+
"learning_rate": 4.9892750738800664e-05,
|
| 2416 |
+
"loss": 0.0121,
|
| 2417 |
+
"step": 392
|
| 2418 |
+
},
|
| 2419 |
+
{
|
| 2420 |
+
"epoch": 0.04,
|
| 2421 |
+
"learning_rate": 4.989201542715762e-05,
|
| 2422 |
+
"loss": 0.014,
|
| 2423 |
+
"step": 393
|
| 2424 |
+
},
|
| 2425 |
+
{
|
| 2426 |
+
"epoch": 0.04,
|
| 2427 |
+
"learning_rate": 4.989127760888932e-05,
|
| 2428 |
+
"loss": 0.0112,
|
| 2429 |
+
"step": 394
|
| 2430 |
+
},
|
| 2431 |
+
{
|
| 2432 |
+
"epoch": 0.04,
|
| 2433 |
+
"learning_rate": 4.9890537284070037e-05,
|
| 2434 |
+
"loss": 0.0236,
|
| 2435 |
+
"step": 395
|
| 2436 |
+
},
|
| 2437 |
+
{
|
| 2438 |
+
"epoch": 0.04,
|
| 2439 |
+
"learning_rate": 4.988979445277433e-05,
|
| 2440 |
+
"loss": 0.0129,
|
| 2441 |
+
"step": 396
|
| 2442 |
+
},
|
| 2443 |
+
{
|
| 2444 |
+
"epoch": 0.04,
|
| 2445 |
+
"learning_rate": 4.9889049115077005e-05,
|
| 2446 |
+
"loss": 0.0129,
|
| 2447 |
+
"step": 397
|
| 2448 |
+
},
|
| 2449 |
+
{
|
| 2450 |
+
"epoch": 0.04,
|
| 2451 |
+
"learning_rate": 4.988830127105311e-05,
|
| 2452 |
+
"loss": 0.0204,
|
| 2453 |
+
"step": 398
|
| 2454 |
+
},
|
| 2455 |
+
{
|
| 2456 |
+
"epoch": 0.04,
|
| 2457 |
+
"learning_rate": 4.9887550920777956e-05,
|
| 2458 |
+
"loss": 0.02,
|
| 2459 |
+
"step": 399
|
| 2460 |
+
},
|
| 2461 |
+
{
|
| 2462 |
+
"epoch": 0.04,
|
| 2463 |
+
"learning_rate": 4.988679806432712e-05,
|
| 2464 |
+
"loss": 0.0099,
|
| 2465 |
+
"step": 400
|
| 2466 |
+
},
|
| 2467 |
+
{
|
| 2468 |
+
"epoch": 0.04,
|
| 2469 |
+
"eval_loss": 1.1065870523452759,
|
| 2470 |
+
"eval_runtime": 71.8543,
|
| 2471 |
+
"eval_samples_per_second": 2.769,
|
| 2472 |
+
"eval_steps_per_second": 0.696,
|
| 2473 |
+
"step": 400
|
| 2474 |
+
}
|
| 2475 |
+
],
|
| 2476 |
+
"logging_steps": 1,
|
| 2477 |
+
"max_steps": 10000,
|
| 2478 |
+
"num_train_epochs": 9223372036854775807,
|
| 2479 |
+
"save_steps": 100,
|
| 2480 |
+
"total_flos": 6460489806643200.0,
|
| 2481 |
+
"trial_name": null,
|
| 2482 |
+
"trial_params": null
|
| 2483 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5a87f7bc738b1ba0679e4bc919ec2c7b708e16bc585561e76f9d112c47941171
|
| 3 |
+
size 4664
|