Upload 8 files
Browse files- README.md +202 -0
- adapter_config.json +30 -0
- adapter_model.safetensors +3 -0
- optimizer.pt +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- trainer_state.json +3021 -0
- training_args.bin +3 -0
README.md
ADDED
|
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: TianlaiChen/PepMLM-650M
|
| 3 |
+
library_name: peft
|
| 4 |
+
---
|
| 5 |
+
|
| 6 |
+
# Model Card for Model ID
|
| 7 |
+
|
| 8 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
| 9 |
+
|
| 10 |
+
|
| 11 |
+
|
| 12 |
+
## Model Details
|
| 13 |
+
|
| 14 |
+
### Model Description
|
| 15 |
+
|
| 16 |
+
<!-- Provide a longer summary of what this model is. -->
|
| 17 |
+
|
| 18 |
+
|
| 19 |
+
|
| 20 |
+
- **Developed by:** [More Information Needed]
|
| 21 |
+
- **Funded by [optional]:** [More Information Needed]
|
| 22 |
+
- **Shared by [optional]:** [More Information Needed]
|
| 23 |
+
- **Model type:** [More Information Needed]
|
| 24 |
+
- **Language(s) (NLP):** [More Information Needed]
|
| 25 |
+
- **License:** [More Information Needed]
|
| 26 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
| 27 |
+
|
| 28 |
+
### Model Sources [optional]
|
| 29 |
+
|
| 30 |
+
<!-- Provide the basic links for the model. -->
|
| 31 |
+
|
| 32 |
+
- **Repository:** [More Information Needed]
|
| 33 |
+
- **Paper [optional]:** [More Information Needed]
|
| 34 |
+
- **Demo [optional]:** [More Information Needed]
|
| 35 |
+
|
| 36 |
+
## Uses
|
| 37 |
+
|
| 38 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
| 39 |
+
|
| 40 |
+
### Direct Use
|
| 41 |
+
|
| 42 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
| 43 |
+
|
| 44 |
+
[More Information Needed]
|
| 45 |
+
|
| 46 |
+
### Downstream Use [optional]
|
| 47 |
+
|
| 48 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
| 49 |
+
|
| 50 |
+
[More Information Needed]
|
| 51 |
+
|
| 52 |
+
### Out-of-Scope Use
|
| 53 |
+
|
| 54 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
| 55 |
+
|
| 56 |
+
[More Information Needed]
|
| 57 |
+
|
| 58 |
+
## Bias, Risks, and Limitations
|
| 59 |
+
|
| 60 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
| 61 |
+
|
| 62 |
+
[More Information Needed]
|
| 63 |
+
|
| 64 |
+
### Recommendations
|
| 65 |
+
|
| 66 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
| 67 |
+
|
| 68 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
| 69 |
+
|
| 70 |
+
## How to Get Started with the Model
|
| 71 |
+
|
| 72 |
+
Use the code below to get started with the model.
|
| 73 |
+
|
| 74 |
+
[More Information Needed]
|
| 75 |
+
|
| 76 |
+
## Training Details
|
| 77 |
+
|
| 78 |
+
### Training Data
|
| 79 |
+
|
| 80 |
+
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
| 81 |
+
|
| 82 |
+
[More Information Needed]
|
| 83 |
+
|
| 84 |
+
### Training Procedure
|
| 85 |
+
|
| 86 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
| 87 |
+
|
| 88 |
+
#### Preprocessing [optional]
|
| 89 |
+
|
| 90 |
+
[More Information Needed]
|
| 91 |
+
|
| 92 |
+
|
| 93 |
+
#### Training Hyperparameters
|
| 94 |
+
|
| 95 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
| 96 |
+
|
| 97 |
+
#### Speeds, Sizes, Times [optional]
|
| 98 |
+
|
| 99 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
| 100 |
+
|
| 101 |
+
[More Information Needed]
|
| 102 |
+
|
| 103 |
+
## Evaluation
|
| 104 |
+
|
| 105 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
| 106 |
+
|
| 107 |
+
### Testing Data, Factors & Metrics
|
| 108 |
+
|
| 109 |
+
#### Testing Data
|
| 110 |
+
|
| 111 |
+
<!-- This should link to a Dataset Card if possible. -->
|
| 112 |
+
|
| 113 |
+
[More Information Needed]
|
| 114 |
+
|
| 115 |
+
#### Factors
|
| 116 |
+
|
| 117 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
| 118 |
+
|
| 119 |
+
[More Information Needed]
|
| 120 |
+
|
| 121 |
+
#### Metrics
|
| 122 |
+
|
| 123 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
| 124 |
+
|
| 125 |
+
[More Information Needed]
|
| 126 |
+
|
| 127 |
+
### Results
|
| 128 |
+
|
| 129 |
+
[More Information Needed]
|
| 130 |
+
|
| 131 |
+
#### Summary
|
| 132 |
+
|
| 133 |
+
|
| 134 |
+
|
| 135 |
+
## Model Examination [optional]
|
| 136 |
+
|
| 137 |
+
<!-- Relevant interpretability work for the model goes here -->
|
| 138 |
+
|
| 139 |
+
[More Information Needed]
|
| 140 |
+
|
| 141 |
+
## Environmental Impact
|
| 142 |
+
|
| 143 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
| 144 |
+
|
| 145 |
+
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
| 146 |
+
|
| 147 |
+
- **Hardware Type:** [More Information Needed]
|
| 148 |
+
- **Hours used:** [More Information Needed]
|
| 149 |
+
- **Cloud Provider:** [More Information Needed]
|
| 150 |
+
- **Compute Region:** [More Information Needed]
|
| 151 |
+
- **Carbon Emitted:** [More Information Needed]
|
| 152 |
+
|
| 153 |
+
## Technical Specifications [optional]
|
| 154 |
+
|
| 155 |
+
### Model Architecture and Objective
|
| 156 |
+
|
| 157 |
+
[More Information Needed]
|
| 158 |
+
|
| 159 |
+
### Compute Infrastructure
|
| 160 |
+
|
| 161 |
+
[More Information Needed]
|
| 162 |
+
|
| 163 |
+
#### Hardware
|
| 164 |
+
|
| 165 |
+
[More Information Needed]
|
| 166 |
+
|
| 167 |
+
#### Software
|
| 168 |
+
|
| 169 |
+
[More Information Needed]
|
| 170 |
+
|
| 171 |
+
## Citation [optional]
|
| 172 |
+
|
| 173 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
| 174 |
+
|
| 175 |
+
**BibTeX:**
|
| 176 |
+
|
| 177 |
+
[More Information Needed]
|
| 178 |
+
|
| 179 |
+
**APA:**
|
| 180 |
+
|
| 181 |
+
[More Information Needed]
|
| 182 |
+
|
| 183 |
+
## Glossary [optional]
|
| 184 |
+
|
| 185 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
| 186 |
+
|
| 187 |
+
[More Information Needed]
|
| 188 |
+
|
| 189 |
+
## More Information [optional]
|
| 190 |
+
|
| 191 |
+
[More Information Needed]
|
| 192 |
+
|
| 193 |
+
## Model Card Authors [optional]
|
| 194 |
+
|
| 195 |
+
[More Information Needed]
|
| 196 |
+
|
| 197 |
+
## Model Card Contact
|
| 198 |
+
|
| 199 |
+
[More Information Needed]
|
| 200 |
+
### Framework versions
|
| 201 |
+
|
| 202 |
+
- PEFT 0.10.0
|
adapter_config.json
ADDED
|
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "TianlaiChen/PepMLM-650M",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"fan_in_fan_out": false,
|
| 7 |
+
"inference_mode": true,
|
| 8 |
+
"init_lora_weights": true,
|
| 9 |
+
"layer_replication": null,
|
| 10 |
+
"layers_pattern": null,
|
| 11 |
+
"layers_to_transform": null,
|
| 12 |
+
"loftq_config": {},
|
| 13 |
+
"lora_alpha": 32,
|
| 14 |
+
"lora_dropout": 0.1,
|
| 15 |
+
"megatron_config": null,
|
| 16 |
+
"megatron_core": "megatron.core",
|
| 17 |
+
"modules_to_save": null,
|
| 18 |
+
"peft_type": "LORA",
|
| 19 |
+
"r": 8,
|
| 20 |
+
"rank_pattern": {},
|
| 21 |
+
"revision": null,
|
| 22 |
+
"target_modules": [
|
| 23 |
+
"key",
|
| 24 |
+
"query",
|
| 25 |
+
"value"
|
| 26 |
+
],
|
| 27 |
+
"task_type": "SEQ_CLS",
|
| 28 |
+
"use_dora": false,
|
| 29 |
+
"use_rslora": false
|
| 30 |
+
}
|
adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:631051c680e34d63ab0d16b716ebec487e255134babd4b72a18edaa907a8027b
|
| 3 |
+
size 14707472
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7622b3d0137ae949b6ee2797c9c97718fedb4ad59e2af29bd44ff704f98ef762
|
| 3 |
+
size 29479290
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:40f33dd295aab577c830fa7c40c25eef11385d54fadaa6f9877fb50a6df60eb3
|
| 3 |
+
size 14244
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:41ebb633099a186053f06b548bfd7a7a2393922f44951adfcfebad6ea4d2e895
|
| 3 |
+
size 1000
|
trainer_state.json
ADDED
|
@@ -0,0 +1,3021 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 2.995008319467554,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 18000,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.008319467554076539,
|
| 13 |
+
"grad_norm": 0.5583499073982239,
|
| 14 |
+
"learning_rate": 0.0004999994583628932,
|
| 15 |
+
"loss": 0.7169,
|
| 16 |
+
"step": 50
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.016638935108153077,
|
| 20 |
+
"grad_norm": 0.19315695762634277,
|
| 21 |
+
"learning_rate": 0.0004999989167257863,
|
| 22 |
+
"loss": 0.6946,
|
| 23 |
+
"step": 100
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.024958402662229616,
|
| 27 |
+
"grad_norm": 0.2500464618206024,
|
| 28 |
+
"learning_rate": 0.0004999983750886796,
|
| 29 |
+
"loss": 0.6934,
|
| 30 |
+
"step": 150
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.033277870216306155,
|
| 34 |
+
"grad_norm": 0.10472989827394485,
|
| 35 |
+
"learning_rate": 0.0004999978334515727,
|
| 36 |
+
"loss": 0.6922,
|
| 37 |
+
"step": 200
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.04159733777038269,
|
| 41 |
+
"grad_norm": 0.08617454022169113,
|
| 42 |
+
"learning_rate": 0.0004999972918144659,
|
| 43 |
+
"loss": 0.6891,
|
| 44 |
+
"step": 250
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.04991680532445923,
|
| 48 |
+
"grad_norm": 0.25109192728996277,
|
| 49 |
+
"learning_rate": 0.0004999967501773591,
|
| 50 |
+
"loss": 0.687,
|
| 51 |
+
"step": 300
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.05823627287853577,
|
| 55 |
+
"grad_norm": 0.06475350260734558,
|
| 56 |
+
"learning_rate": 0.0004999962085402523,
|
| 57 |
+
"loss": 0.6854,
|
| 58 |
+
"step": 350
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.06655574043261231,
|
| 62 |
+
"grad_norm": 0.5543227791786194,
|
| 63 |
+
"learning_rate": 0.0004999956669031455,
|
| 64 |
+
"loss": 0.6836,
|
| 65 |
+
"step": 400
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.07487520798668885,
|
| 69 |
+
"grad_norm": 0.39940813183784485,
|
| 70 |
+
"learning_rate": 0.0004999951252660387,
|
| 71 |
+
"loss": 0.6808,
|
| 72 |
+
"step": 450
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.08319467554076539,
|
| 76 |
+
"grad_norm": 0.3018794655799866,
|
| 77 |
+
"learning_rate": 0.0004999945836289318,
|
| 78 |
+
"loss": 0.6762,
|
| 79 |
+
"step": 500
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.08319467554076539,
|
| 83 |
+
"eval_accuracy": 0.5590276660651246,
|
| 84 |
+
"eval_auc": 0.5967892656129481,
|
| 85 |
+
"eval_f1": 0.4315189357947604,
|
| 86 |
+
"eval_loss": 0.6786146759986877,
|
| 87 |
+
"eval_precision": 0.6065314861727951,
|
| 88 |
+
"eval_recall": 0.3348881306732058,
|
| 89 |
+
"eval_runtime": 3130.7158,
|
| 90 |
+
"eval_samples_per_second": 109.208,
|
| 91 |
+
"eval_steps_per_second": 13.651,
|
| 92 |
+
"step": 500
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 0.09151414309484193,
|
| 96 |
+
"grad_norm": 0.2409348487854004,
|
| 97 |
+
"learning_rate": 0.000499994041991825,
|
| 98 |
+
"loss": 0.6738,
|
| 99 |
+
"step": 550
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 0.09983361064891846,
|
| 103 |
+
"grad_norm": 0.292751282453537,
|
| 104 |
+
"learning_rate": 0.0004999935003547182,
|
| 105 |
+
"loss": 0.6718,
|
| 106 |
+
"step": 600
|
| 107 |
+
},
|
| 108 |
+
{
|
| 109 |
+
"epoch": 0.10815307820299501,
|
| 110 |
+
"grad_norm": 0.4114605486392975,
|
| 111 |
+
"learning_rate": 0.0004999929587176114,
|
| 112 |
+
"loss": 0.6691,
|
| 113 |
+
"step": 650
|
| 114 |
+
},
|
| 115 |
+
{
|
| 116 |
+
"epoch": 0.11647254575707154,
|
| 117 |
+
"grad_norm": 0.30100876092910767,
|
| 118 |
+
"learning_rate": 0.0004999924170805046,
|
| 119 |
+
"loss": 0.6691,
|
| 120 |
+
"step": 700
|
| 121 |
+
},
|
| 122 |
+
{
|
| 123 |
+
"epoch": 0.12479201331114809,
|
| 124 |
+
"grad_norm": 0.20736241340637207,
|
| 125 |
+
"learning_rate": 0.0004999918754433977,
|
| 126 |
+
"loss": 0.6653,
|
| 127 |
+
"step": 750
|
| 128 |
+
},
|
| 129 |
+
{
|
| 130 |
+
"epoch": 0.13311148086522462,
|
| 131 |
+
"grad_norm": 0.11416225880384445,
|
| 132 |
+
"learning_rate": 0.0004999913338062909,
|
| 133 |
+
"loss": 0.6629,
|
| 134 |
+
"step": 800
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 0.14143094841930118,
|
| 138 |
+
"grad_norm": 0.23378710448741913,
|
| 139 |
+
"learning_rate": 0.000499990792169184,
|
| 140 |
+
"loss": 0.66,
|
| 141 |
+
"step": 850
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 0.1497504159733777,
|
| 145 |
+
"grad_norm": 0.3658539652824402,
|
| 146 |
+
"learning_rate": 0.0004999902505320771,
|
| 147 |
+
"loss": 0.6538,
|
| 148 |
+
"step": 900
|
| 149 |
+
},
|
| 150 |
+
{
|
| 151 |
+
"epoch": 0.15806988352745424,
|
| 152 |
+
"grad_norm": 0.23335859179496765,
|
| 153 |
+
"learning_rate": 0.0004999897088949704,
|
| 154 |
+
"loss": 0.6572,
|
| 155 |
+
"step": 950
|
| 156 |
+
},
|
| 157 |
+
{
|
| 158 |
+
"epoch": 0.16638935108153077,
|
| 159 |
+
"grad_norm": 0.11527813971042633,
|
| 160 |
+
"learning_rate": 0.0004999891672578635,
|
| 161 |
+
"loss": 0.6559,
|
| 162 |
+
"step": 1000
|
| 163 |
+
},
|
| 164 |
+
{
|
| 165 |
+
"epoch": 0.16638935108153077,
|
| 166 |
+
"eval_accuracy": 0.6038917926054186,
|
| 167 |
+
"eval_auc": 0.6553736533116105,
|
| 168 |
+
"eval_f1": 0.5857262157127257,
|
| 169 |
+
"eval_loss": 0.650829017162323,
|
| 170 |
+
"eval_precision": 0.6135620810315436,
|
| 171 |
+
"eval_recall": 0.5603064335836225,
|
| 172 |
+
"eval_runtime": 3082.7349,
|
| 173 |
+
"eval_samples_per_second": 110.908,
|
| 174 |
+
"eval_steps_per_second": 13.864,
|
| 175 |
+
"step": 1000
|
| 176 |
+
},
|
| 177 |
+
{
|
| 178 |
+
"epoch": 0.17470881863560733,
|
| 179 |
+
"grad_norm": 0.12938088178634644,
|
| 180 |
+
"learning_rate": 0.0004999886256207567,
|
| 181 |
+
"loss": 0.6453,
|
| 182 |
+
"step": 1050
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 0.18302828618968386,
|
| 186 |
+
"grad_norm": 0.16796837747097015,
|
| 187 |
+
"learning_rate": 0.0004999880839836499,
|
| 188 |
+
"loss": 0.6459,
|
| 189 |
+
"step": 1100
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 0.1913477537437604,
|
| 193 |
+
"grad_norm": 0.31427496671676636,
|
| 194 |
+
"learning_rate": 0.0004999875423465431,
|
| 195 |
+
"loss": 0.6404,
|
| 196 |
+
"step": 1150
|
| 197 |
+
},
|
| 198 |
+
{
|
| 199 |
+
"epoch": 0.19966722129783693,
|
| 200 |
+
"grad_norm": 0.24732699990272522,
|
| 201 |
+
"learning_rate": 0.0004999870007094363,
|
| 202 |
+
"loss": 0.638,
|
| 203 |
+
"step": 1200
|
| 204 |
+
},
|
| 205 |
+
{
|
| 206 |
+
"epoch": 0.2079866888519135,
|
| 207 |
+
"grad_norm": 0.19166573882102966,
|
| 208 |
+
"learning_rate": 0.0004999864590723295,
|
| 209 |
+
"loss": 0.6316,
|
| 210 |
+
"step": 1250
|
| 211 |
+
},
|
| 212 |
+
{
|
| 213 |
+
"epoch": 0.21630615640599002,
|
| 214 |
+
"grad_norm": 0.23063616454601288,
|
| 215 |
+
"learning_rate": 0.0004999859174352226,
|
| 216 |
+
"loss": 0.6243,
|
| 217 |
+
"step": 1300
|
| 218 |
+
},
|
| 219 |
+
{
|
| 220 |
+
"epoch": 0.22462562396006655,
|
| 221 |
+
"grad_norm": 0.21349310874938965,
|
| 222 |
+
"learning_rate": 0.0004999853757981158,
|
| 223 |
+
"loss": 0.6229,
|
| 224 |
+
"step": 1350
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 0.23294509151414308,
|
| 228 |
+
"grad_norm": 0.21778538823127747,
|
| 229 |
+
"learning_rate": 0.000499984834161009,
|
| 230 |
+
"loss": 0.6173,
|
| 231 |
+
"step": 1400
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 0.24126455906821964,
|
| 235 |
+
"grad_norm": 0.3121509850025177,
|
| 236 |
+
"learning_rate": 0.0004999842925239022,
|
| 237 |
+
"loss": 0.6061,
|
| 238 |
+
"step": 1450
|
| 239 |
+
},
|
| 240 |
+
{
|
| 241 |
+
"epoch": 0.24958402662229617,
|
| 242 |
+
"grad_norm": 0.30077889561653137,
|
| 243 |
+
"learning_rate": 0.0004999837508867954,
|
| 244 |
+
"loss": 0.597,
|
| 245 |
+
"step": 1500
|
| 246 |
+
},
|
| 247 |
+
{
|
| 248 |
+
"epoch": 0.24958402662229617,
|
| 249 |
+
"eval_accuracy": 0.6591010795585831,
|
| 250 |
+
"eval_auc": 0.7267389932367714,
|
| 251 |
+
"eval_f1": 0.6891016322077618,
|
| 252 |
+
"eval_loss": 0.5957785844802856,
|
| 253 |
+
"eval_precision": 0.6331130956465479,
|
| 254 |
+
"eval_recall": 0.7559533911944238,
|
| 255 |
+
"eval_runtime": 3116.4637,
|
| 256 |
+
"eval_samples_per_second": 109.707,
|
| 257 |
+
"eval_steps_per_second": 13.714,
|
| 258 |
+
"step": 1500
|
| 259 |
+
},
|
| 260 |
+
{
|
| 261 |
+
"epoch": 0.2579034941763727,
|
| 262 |
+
"grad_norm": 0.29947781562805176,
|
| 263 |
+
"learning_rate": 0.0004999832092496885,
|
| 264 |
+
"loss": 0.594,
|
| 265 |
+
"step": 1550
|
| 266 |
+
},
|
| 267 |
+
{
|
| 268 |
+
"epoch": 0.26622296173044924,
|
| 269 |
+
"grad_norm": 0.35637083649635315,
|
| 270 |
+
"learning_rate": 0.0004999826676125817,
|
| 271 |
+
"loss": 0.5865,
|
| 272 |
+
"step": 1600
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 0.27454242928452577,
|
| 276 |
+
"grad_norm": 0.4300802946090698,
|
| 277 |
+
"learning_rate": 0.0004999821259754749,
|
| 278 |
+
"loss": 0.5795,
|
| 279 |
+
"step": 1650
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 0.28286189683860236,
|
| 283 |
+
"grad_norm": 0.37862110137939453,
|
| 284 |
+
"learning_rate": 0.0004999815843383681,
|
| 285 |
+
"loss": 0.5767,
|
| 286 |
+
"step": 1700
|
| 287 |
+
},
|
| 288 |
+
{
|
| 289 |
+
"epoch": 0.2911813643926789,
|
| 290 |
+
"grad_norm": 0.5083811283111572,
|
| 291 |
+
"learning_rate": 0.0004999810427012613,
|
| 292 |
+
"loss": 0.5665,
|
| 293 |
+
"step": 1750
|
| 294 |
+
},
|
| 295 |
+
{
|
| 296 |
+
"epoch": 0.2995008319467554,
|
| 297 |
+
"grad_norm": 0.4686565399169922,
|
| 298 |
+
"learning_rate": 0.0004999805010641545,
|
| 299 |
+
"loss": 0.5628,
|
| 300 |
+
"step": 1800
|
| 301 |
+
},
|
| 302 |
+
{
|
| 303 |
+
"epoch": 0.30782029950083195,
|
| 304 |
+
"grad_norm": 0.6207341551780701,
|
| 305 |
+
"learning_rate": 0.0004999799594270476,
|
| 306 |
+
"loss": 0.5612,
|
| 307 |
+
"step": 1850
|
| 308 |
+
},
|
| 309 |
+
{
|
| 310 |
+
"epoch": 0.3161397670549085,
|
| 311 |
+
"grad_norm": 0.400837779045105,
|
| 312 |
+
"learning_rate": 0.0004999794177899408,
|
| 313 |
+
"loss": 0.5546,
|
| 314 |
+
"step": 1900
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 0.324459234608985,
|
| 318 |
+
"grad_norm": 0.3956456184387207,
|
| 319 |
+
"learning_rate": 0.000499978876152834,
|
| 320 |
+
"loss": 0.5522,
|
| 321 |
+
"step": 1950
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 0.33277870216306155,
|
| 325 |
+
"grad_norm": 0.39825043082237244,
|
| 326 |
+
"learning_rate": 0.0004999783345157272,
|
| 327 |
+
"loss": 0.547,
|
| 328 |
+
"step": 2000
|
| 329 |
+
},
|
| 330 |
+
{
|
| 331 |
+
"epoch": 0.33277870216306155,
|
| 332 |
+
"eval_accuracy": 0.696047663198781,
|
| 333 |
+
"eval_auc": 0.7729761853730717,
|
| 334 |
+
"eval_f1": 0.7419938676961655,
|
| 335 |
+
"eval_loss": 0.5397406220436096,
|
| 336 |
+
"eval_precision": 0.644336742613705,
|
| 337 |
+
"eval_recall": 0.8745413152766154,
|
| 338 |
+
"eval_runtime": 3213.3641,
|
| 339 |
+
"eval_samples_per_second": 106.399,
|
| 340 |
+
"eval_steps_per_second": 13.3,
|
| 341 |
+
"step": 2000
|
| 342 |
+
},
|
| 343 |
+
{
|
| 344 |
+
"epoch": 0.3410981697171381,
|
| 345 |
+
"grad_norm": 0.4658432900905609,
|
| 346 |
+
"learning_rate": 0.0004999777928786204,
|
| 347 |
+
"loss": 0.5417,
|
| 348 |
+
"step": 2050
|
| 349 |
+
},
|
| 350 |
+
{
|
| 351 |
+
"epoch": 0.34941763727121466,
|
| 352 |
+
"grad_norm": 0.3485628664493561,
|
| 353 |
+
"learning_rate": 0.0004999772512415135,
|
| 354 |
+
"loss": 0.5391,
|
| 355 |
+
"step": 2100
|
| 356 |
+
},
|
| 357 |
+
{
|
| 358 |
+
"epoch": 0.3577371048252912,
|
| 359 |
+
"grad_norm": 0.3111945390701294,
|
| 360 |
+
"learning_rate": 0.0004999767096044067,
|
| 361 |
+
"loss": 0.5395,
|
| 362 |
+
"step": 2150
|
| 363 |
+
},
|
| 364 |
+
{
|
| 365 |
+
"epoch": 0.36605657237936773,
|
| 366 |
+
"grad_norm": 0.33330038189888,
|
| 367 |
+
"learning_rate": 0.0004999761679672999,
|
| 368 |
+
"loss": 0.5341,
|
| 369 |
+
"step": 2200
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 0.37437603993344426,
|
| 373 |
+
"grad_norm": 0.6060266494750977,
|
| 374 |
+
"learning_rate": 0.0004999756263301931,
|
| 375 |
+
"loss": 0.5348,
|
| 376 |
+
"step": 2250
|
| 377 |
+
},
|
| 378 |
+
{
|
| 379 |
+
"epoch": 0.3826955074875208,
|
| 380 |
+
"grad_norm": 0.38933542370796204,
|
| 381 |
+
"learning_rate": 0.0004999750846930863,
|
| 382 |
+
"loss": 0.5346,
|
| 383 |
+
"step": 2300
|
| 384 |
+
},
|
| 385 |
+
{
|
| 386 |
+
"epoch": 0.3910149750415973,
|
| 387 |
+
"grad_norm": 0.30752280354499817,
|
| 388 |
+
"learning_rate": 0.0004999745430559793,
|
| 389 |
+
"loss": 0.5292,
|
| 390 |
+
"step": 2350
|
| 391 |
+
},
|
| 392 |
+
{
|
| 393 |
+
"epoch": 0.39933444259567386,
|
| 394 |
+
"grad_norm": 0.3584199845790863,
|
| 395 |
+
"learning_rate": 0.0004999740014188725,
|
| 396 |
+
"loss": 0.528,
|
| 397 |
+
"step": 2400
|
| 398 |
+
},
|
| 399 |
+
{
|
| 400 |
+
"epoch": 0.40765391014975044,
|
| 401 |
+
"grad_norm": 0.34107691049575806,
|
| 402 |
+
"learning_rate": 0.0004999734597817657,
|
| 403 |
+
"loss": 0.5255,
|
| 404 |
+
"step": 2450
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"epoch": 0.415973377703827,
|
| 408 |
+
"grad_norm": 0.33743101358413696,
|
| 409 |
+
"learning_rate": 0.0004999729181446589,
|
| 410 |
+
"loss": 0.5241,
|
| 411 |
+
"step": 2500
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 0.415973377703827,
|
| 415 |
+
"eval_accuracy": 0.7029268877651003,
|
| 416 |
+
"eval_auc": 0.7850390034483034,
|
| 417 |
+
"eval_f1": 0.7599834583801028,
|
| 418 |
+
"eval_loss": 0.5229647755622864,
|
| 419 |
+
"eval_precision": 0.6373332382107441,
|
| 420 |
+
"eval_recall": 0.9410893725602655,
|
| 421 |
+
"eval_runtime": 3103.5803,
|
| 422 |
+
"eval_samples_per_second": 110.163,
|
| 423 |
+
"eval_steps_per_second": 13.771,
|
| 424 |
+
"step": 2500
|
| 425 |
+
},
|
| 426 |
+
{
|
| 427 |
+
"epoch": 0.4242928452579035,
|
| 428 |
+
"grad_norm": 0.43357181549072266,
|
| 429 |
+
"learning_rate": 0.0004999723765075521,
|
| 430 |
+
"loss": 0.526,
|
| 431 |
+
"step": 2550
|
| 432 |
+
},
|
| 433 |
+
{
|
| 434 |
+
"epoch": 0.43261231281198004,
|
| 435 |
+
"grad_norm": 0.536624550819397,
|
| 436 |
+
"learning_rate": 0.0004999718348704453,
|
| 437 |
+
"loss": 0.5235,
|
| 438 |
+
"step": 2600
|
| 439 |
+
},
|
| 440 |
+
{
|
| 441 |
+
"epoch": 0.44093178036605657,
|
| 442 |
+
"grad_norm": 0.26722005009651184,
|
| 443 |
+
"learning_rate": 0.0004999712932333384,
|
| 444 |
+
"loss": 0.5238,
|
| 445 |
+
"step": 2650
|
| 446 |
+
},
|
| 447 |
+
{
|
| 448 |
+
"epoch": 0.4492512479201331,
|
| 449 |
+
"grad_norm": 0.29940328001976013,
|
| 450 |
+
"learning_rate": 0.0004999707515962316,
|
| 451 |
+
"loss": 0.5127,
|
| 452 |
+
"step": 2700
|
| 453 |
+
},
|
| 454 |
+
{
|
| 455 |
+
"epoch": 0.45757071547420963,
|
| 456 |
+
"grad_norm": 0.27166950702667236,
|
| 457 |
+
"learning_rate": 0.0004999702099591248,
|
| 458 |
+
"loss": 0.5167,
|
| 459 |
+
"step": 2750
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 0.46589018302828616,
|
| 463 |
+
"grad_norm": 0.5428174138069153,
|
| 464 |
+
"learning_rate": 0.000499969668322018,
|
| 465 |
+
"loss": 0.5148,
|
| 466 |
+
"step": 2800
|
| 467 |
+
},
|
| 468 |
+
{
|
| 469 |
+
"epoch": 0.47420965058236275,
|
| 470 |
+
"grad_norm": 0.37499845027923584,
|
| 471 |
+
"learning_rate": 0.0004999691266849112,
|
| 472 |
+
"loss": 0.5135,
|
| 473 |
+
"step": 2850
|
| 474 |
+
},
|
| 475 |
+
{
|
| 476 |
+
"epoch": 0.4825291181364393,
|
| 477 |
+
"grad_norm": 0.5476682186126709,
|
| 478 |
+
"learning_rate": 0.0004999685850478043,
|
| 479 |
+
"loss": 0.5127,
|
| 480 |
+
"step": 2900
|
| 481 |
+
},
|
| 482 |
+
{
|
| 483 |
+
"epoch": 0.4908485856905158,
|
| 484 |
+
"grad_norm": 0.24501897394657135,
|
| 485 |
+
"learning_rate": 0.0004999680434106975,
|
| 486 |
+
"loss": 0.5098,
|
| 487 |
+
"step": 2950
|
| 488 |
+
},
|
| 489 |
+
{
|
| 490 |
+
"epoch": 0.49916805324459235,
|
| 491 |
+
"grad_norm": 0.3694550395011902,
|
| 492 |
+
"learning_rate": 0.0004999675017735907,
|
| 493 |
+
"loss": 0.5138,
|
| 494 |
+
"step": 3000
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 0.49916805324459235,
|
| 498 |
+
"eval_accuracy": 0.7139476863050199,
|
| 499 |
+
"eval_auc": 0.794041583180005,
|
| 500 |
+
"eval_f1": 0.7427284708283901,
|
| 501 |
+
"eval_loss": 0.5122376084327698,
|
| 502 |
+
"eval_precision": 0.6745716224352297,
|
| 503 |
+
"eval_recall": 0.8262060408851225,
|
| 504 |
+
"eval_runtime": 3072.5721,
|
| 505 |
+
"eval_samples_per_second": 111.275,
|
| 506 |
+
"eval_steps_per_second": 13.91,
|
| 507 |
+
"step": 3000
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 0.5074875207986689,
|
| 511 |
+
"grad_norm": 0.2761985957622528,
|
| 512 |
+
"learning_rate": 0.0004999669601364839,
|
| 513 |
+
"loss": 0.5187,
|
| 514 |
+
"step": 3050
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 0.5158069883527454,
|
| 518 |
+
"grad_norm": 0.23015080392360687,
|
| 519 |
+
"learning_rate": 0.0004999664184993771,
|
| 520 |
+
"loss": 0.5117,
|
| 521 |
+
"step": 3100
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 0.5241264559068219,
|
| 525 |
+
"grad_norm": 0.26510143280029297,
|
| 526 |
+
"learning_rate": 0.0004999658768622703,
|
| 527 |
+
"loss": 0.5124,
|
| 528 |
+
"step": 3150
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 0.5324459234608985,
|
| 532 |
+
"grad_norm": 0.6037235260009766,
|
| 533 |
+
"learning_rate": 0.0004999653352251634,
|
| 534 |
+
"loss": 0.5111,
|
| 535 |
+
"step": 3200
|
| 536 |
+
},
|
| 537 |
+
{
|
| 538 |
+
"epoch": 0.540765391014975,
|
| 539 |
+
"grad_norm": 0.4400153160095215,
|
| 540 |
+
"learning_rate": 0.0004999647935880566,
|
| 541 |
+
"loss": 0.5167,
|
| 542 |
+
"step": 3250
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 0.5490848585690515,
|
| 546 |
+
"grad_norm": 0.33088386058807373,
|
| 547 |
+
"learning_rate": 0.0004999642519509498,
|
| 548 |
+
"loss": 0.5103,
|
| 549 |
+
"step": 3300
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 0.5574043261231281,
|
| 553 |
+
"grad_norm": 0.45530447363853455,
|
| 554 |
+
"learning_rate": 0.000499963710313843,
|
| 555 |
+
"loss": 0.5136,
|
| 556 |
+
"step": 3350
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 0.5657237936772047,
|
| 560 |
+
"grad_norm": 0.38819849491119385,
|
| 561 |
+
"learning_rate": 0.0004999631686767362,
|
| 562 |
+
"loss": 0.5094,
|
| 563 |
+
"step": 3400
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 0.5740432612312812,
|
| 567 |
+
"grad_norm": 0.2275410294532776,
|
| 568 |
+
"learning_rate": 0.0004999626270396293,
|
| 569 |
+
"loss": 0.5095,
|
| 570 |
+
"step": 3450
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 0.5823627287853578,
|
| 574 |
+
"grad_norm": 0.25340116024017334,
|
| 575 |
+
"learning_rate": 0.0004999620854025226,
|
| 576 |
+
"loss": 0.5109,
|
| 577 |
+
"step": 3500
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 0.5823627287853578,
|
| 581 |
+
"eval_accuracy": 0.7234504926893615,
|
| 582 |
+
"eval_auc": 0.8032986510196456,
|
| 583 |
+
"eval_f1": 0.7607974094312893,
|
| 584 |
+
"eval_loss": 0.5012865662574768,
|
| 585 |
+
"eval_precision": 0.6700384562254078,
|
| 586 |
+
"eval_recall": 0.8799957862456034,
|
| 587 |
+
"eval_runtime": 3072.7802,
|
| 588 |
+
"eval_samples_per_second": 111.267,
|
| 589 |
+
"eval_steps_per_second": 13.909,
|
| 590 |
+
"step": 3500
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 0.5906821963394343,
|
| 594 |
+
"grad_norm": 0.2851439416408539,
|
| 595 |
+
"learning_rate": 0.0004999615437654157,
|
| 596 |
+
"loss": 0.5072,
|
| 597 |
+
"step": 3550
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 0.5990016638935108,
|
| 601 |
+
"grad_norm": 0.2701944410800934,
|
| 602 |
+
"learning_rate": 0.0004999610021283089,
|
| 603 |
+
"loss": 0.5013,
|
| 604 |
+
"step": 3600
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 0.6073211314475874,
|
| 608 |
+
"grad_norm": 0.3663853704929352,
|
| 609 |
+
"learning_rate": 0.0004999604604912021,
|
| 610 |
+
"loss": 0.509,
|
| 611 |
+
"step": 3650
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 0.6156405990016639,
|
| 615 |
+
"grad_norm": 0.3946699798107147,
|
| 616 |
+
"learning_rate": 0.0004999599188540951,
|
| 617 |
+
"loss": 0.5073,
|
| 618 |
+
"step": 3700
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 0.6239600665557404,
|
| 622 |
+
"grad_norm": 0.20986106991767883,
|
| 623 |
+
"learning_rate": 0.0004999593772169885,
|
| 624 |
+
"loss": 0.5032,
|
| 625 |
+
"step": 3750
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 0.632279534109817,
|
| 629 |
+
"grad_norm": 0.44309139251708984,
|
| 630 |
+
"learning_rate": 0.0004999588355798815,
|
| 631 |
+
"loss": 0.5062,
|
| 632 |
+
"step": 3800
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 0.6405990016638935,
|
| 636 |
+
"grad_norm": 0.3160322904586792,
|
| 637 |
+
"learning_rate": 0.0004999582939427747,
|
| 638 |
+
"loss": 0.5003,
|
| 639 |
+
"step": 3850
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 0.64891846921797,
|
| 643 |
+
"grad_norm": 0.36600473523139954,
|
| 644 |
+
"learning_rate": 0.0004999577523056679,
|
| 645 |
+
"loss": 0.5047,
|
| 646 |
+
"step": 3900
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 0.6572379367720466,
|
| 650 |
+
"grad_norm": 0.4690772593021393,
|
| 651 |
+
"learning_rate": 0.0004999572106685611,
|
| 652 |
+
"loss": 0.504,
|
| 653 |
+
"step": 3950
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 0.6655574043261231,
|
| 657 |
+
"grad_norm": 0.2607940137386322,
|
| 658 |
+
"learning_rate": 0.0004999566690314542,
|
| 659 |
+
"loss": 0.5039,
|
| 660 |
+
"step": 4000
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 0.6655574043261231,
|
| 664 |
+
"eval_accuracy": 0.7287415289310586,
|
| 665 |
+
"eval_auc": 0.8093233697055171,
|
| 666 |
+
"eval_f1": 0.7662815165757343,
|
| 667 |
+
"eval_loss": 0.49741330742836,
|
| 668 |
+
"eval_precision": 0.6728864418931957,
|
| 669 |
+
"eval_recall": 0.8897810603444745,
|
| 670 |
+
"eval_runtime": 3108.812,
|
| 671 |
+
"eval_samples_per_second": 109.977,
|
| 672 |
+
"eval_steps_per_second": 13.747,
|
| 673 |
+
"step": 4000
|
| 674 |
+
},
|
| 675 |
+
{
|
| 676 |
+
"epoch": 0.6738768718801996,
|
| 677 |
+
"grad_norm": 0.4410100281238556,
|
| 678 |
+
"learning_rate": 0.0004999561273943475,
|
| 679 |
+
"loss": 0.5004,
|
| 680 |
+
"step": 4050
|
| 681 |
+
},
|
| 682 |
+
{
|
| 683 |
+
"epoch": 0.6821963394342762,
|
| 684 |
+
"grad_norm": 0.3221227824687958,
|
| 685 |
+
"learning_rate": 0.0004999555857572406,
|
| 686 |
+
"loss": 0.4987,
|
| 687 |
+
"step": 4100
|
| 688 |
+
},
|
| 689 |
+
{
|
| 690 |
+
"epoch": 0.6905158069883528,
|
| 691 |
+
"grad_norm": 0.3825673460960388,
|
| 692 |
+
"learning_rate": 0.0004999550441201338,
|
| 693 |
+
"loss": 0.5006,
|
| 694 |
+
"step": 4150
|
| 695 |
+
},
|
| 696 |
+
{
|
| 697 |
+
"epoch": 0.6988352745424293,
|
| 698 |
+
"grad_norm": 0.4332997798919678,
|
| 699 |
+
"learning_rate": 0.000499954502483027,
|
| 700 |
+
"loss": 0.498,
|
| 701 |
+
"step": 4200
|
| 702 |
+
},
|
| 703 |
+
{
|
| 704 |
+
"epoch": 0.7071547420965059,
|
| 705 |
+
"grad_norm": 0.4402281939983368,
|
| 706 |
+
"learning_rate": 0.0004999539608459201,
|
| 707 |
+
"loss": 0.497,
|
| 708 |
+
"step": 4250
|
| 709 |
+
},
|
| 710 |
+
{
|
| 711 |
+
"epoch": 0.7154742096505824,
|
| 712 |
+
"grad_norm": 0.2534608840942383,
|
| 713 |
+
"learning_rate": 0.0004999534192088134,
|
| 714 |
+
"loss": 0.4959,
|
| 715 |
+
"step": 4300
|
| 716 |
+
},
|
| 717 |
+
{
|
| 718 |
+
"epoch": 0.7237936772046589,
|
| 719 |
+
"grad_norm": 0.43906906247138977,
|
| 720 |
+
"learning_rate": 0.0004999528775717065,
|
| 721 |
+
"loss": 0.4923,
|
| 722 |
+
"step": 4350
|
| 723 |
+
},
|
| 724 |
+
{
|
| 725 |
+
"epoch": 0.7321131447587355,
|
| 726 |
+
"grad_norm": 0.3567379117012024,
|
| 727 |
+
"learning_rate": 0.0004999523359345997,
|
| 728 |
+
"loss": 0.497,
|
| 729 |
+
"step": 4400
|
| 730 |
+
},
|
| 731 |
+
{
|
| 732 |
+
"epoch": 0.740432612312812,
|
| 733 |
+
"grad_norm": 0.26709049940109253,
|
| 734 |
+
"learning_rate": 0.0004999517942974929,
|
| 735 |
+
"loss": 0.494,
|
| 736 |
+
"step": 4450
|
| 737 |
+
},
|
| 738 |
+
{
|
| 739 |
+
"epoch": 0.7487520798668885,
|
| 740 |
+
"grad_norm": 0.3749837577342987,
|
| 741 |
+
"learning_rate": 0.0004999512526603861,
|
| 742 |
+
"loss": 0.4954,
|
| 743 |
+
"step": 4500
|
| 744 |
+
},
|
| 745 |
+
{
|
| 746 |
+
"epoch": 0.7487520798668885,
|
| 747 |
+
"eval_accuracy": 0.7357143483894366,
|
| 748 |
+
"eval_auc": 0.8154262901262641,
|
| 749 |
+
"eval_f1": 0.7617121262865868,
|
| 750 |
+
"eval_loss": 0.48994818329811096,
|
| 751 |
+
"eval_precision": 0.6932252366415145,
|
| 752 |
+
"eval_recall": 0.8452147551633122,
|
| 753 |
+
"eval_runtime": 3064.0111,
|
| 754 |
+
"eval_samples_per_second": 111.585,
|
| 755 |
+
"eval_steps_per_second": 13.948,
|
| 756 |
+
"step": 4500
|
| 757 |
+
},
|
| 758 |
+
{
|
| 759 |
+
"epoch": 0.757071547420965,
|
| 760 |
+
"grad_norm": 0.34779804944992065,
|
| 761 |
+
"learning_rate": 0.0004999507110232793,
|
| 762 |
+
"loss": 0.4947,
|
| 763 |
+
"step": 4550
|
| 764 |
+
},
|
| 765 |
+
{
|
| 766 |
+
"epoch": 0.7653910149750416,
|
| 767 |
+
"grad_norm": 0.48780205845832825,
|
| 768 |
+
"learning_rate": 0.0004999501693861724,
|
| 769 |
+
"loss": 0.5003,
|
| 770 |
+
"step": 4600
|
| 771 |
+
},
|
| 772 |
+
{
|
| 773 |
+
"epoch": 0.7737104825291181,
|
| 774 |
+
"grad_norm": 0.25045379996299744,
|
| 775 |
+
"learning_rate": 0.0004999496277490656,
|
| 776 |
+
"loss": 0.4922,
|
| 777 |
+
"step": 4650
|
| 778 |
+
},
|
| 779 |
+
{
|
| 780 |
+
"epoch": 0.7820299500831946,
|
| 781 |
+
"grad_norm": 0.29499462246894836,
|
| 782 |
+
"learning_rate": 0.0004999490861119588,
|
| 783 |
+
"loss": 0.4891,
|
| 784 |
+
"step": 4700
|
| 785 |
+
},
|
| 786 |
+
{
|
| 787 |
+
"epoch": 0.7903494176372712,
|
| 788 |
+
"grad_norm": 0.34115445613861084,
|
| 789 |
+
"learning_rate": 0.000499948544474852,
|
| 790 |
+
"loss": 0.4984,
|
| 791 |
+
"step": 4750
|
| 792 |
+
},
|
| 793 |
+
{
|
| 794 |
+
"epoch": 0.7986688851913477,
|
| 795 |
+
"grad_norm": 0.5018367171287537,
|
| 796 |
+
"learning_rate": 0.0004999480028377452,
|
| 797 |
+
"loss": 0.4935,
|
| 798 |
+
"step": 4800
|
| 799 |
+
},
|
| 800 |
+
{
|
| 801 |
+
"epoch": 0.8069883527454242,
|
| 802 |
+
"grad_norm": 0.492158442735672,
|
| 803 |
+
"learning_rate": 0.0004999474612006384,
|
| 804 |
+
"loss": 0.4914,
|
| 805 |
+
"step": 4850
|
| 806 |
+
},
|
| 807 |
+
{
|
| 808 |
+
"epoch": 0.8153078202995009,
|
| 809 |
+
"grad_norm": 0.3154297173023224,
|
| 810 |
+
"learning_rate": 0.0004999469195635315,
|
| 811 |
+
"loss": 0.4946,
|
| 812 |
+
"step": 4900
|
| 813 |
+
},
|
| 814 |
+
{
|
| 815 |
+
"epoch": 0.8236272878535774,
|
| 816 |
+
"grad_norm": 0.27449771761894226,
|
| 817 |
+
"learning_rate": 0.0004999463779264247,
|
| 818 |
+
"loss": 0.4906,
|
| 819 |
+
"step": 4950
|
| 820 |
+
},
|
| 821 |
+
{
|
| 822 |
+
"epoch": 0.831946755407654,
|
| 823 |
+
"grad_norm": 0.37241068482398987,
|
| 824 |
+
"learning_rate": 0.0004999458362893179,
|
| 825 |
+
"loss": 0.4906,
|
| 826 |
+
"step": 5000
|
| 827 |
+
},
|
| 828 |
+
{
|
| 829 |
+
"epoch": 0.831946755407654,
|
| 830 |
+
"eval_accuracy": 0.7396014612502523,
|
| 831 |
+
"eval_auc": 0.8197279172699253,
|
| 832 |
+
"eval_f1": 0.7709238179535209,
|
| 833 |
+
"eval_loss": 0.48505428433418274,
|
| 834 |
+
"eval_precision": 0.6878946087547468,
|
| 835 |
+
"eval_recall": 0.876747683898191,
|
| 836 |
+
"eval_runtime": 3075.4729,
|
| 837 |
+
"eval_samples_per_second": 111.17,
|
| 838 |
+
"eval_steps_per_second": 13.896,
|
| 839 |
+
"step": 5000
|
| 840 |
+
},
|
| 841 |
+
{
|
| 842 |
+
"epoch": 0.8402662229617305,
|
| 843 |
+
"grad_norm": 0.2525058090686798,
|
| 844 |
+
"learning_rate": 0.0004999452946522111,
|
| 845 |
+
"loss": 0.4907,
|
| 846 |
+
"step": 5050
|
| 847 |
+
},
|
| 848 |
+
{
|
| 849 |
+
"epoch": 0.848585690515807,
|
| 850 |
+
"grad_norm": 0.3323892056941986,
|
| 851 |
+
"learning_rate": 0.0004999447530151043,
|
| 852 |
+
"loss": 0.4914,
|
| 853 |
+
"step": 5100
|
| 854 |
+
},
|
| 855 |
+
{
|
| 856 |
+
"epoch": 0.8569051580698835,
|
| 857 |
+
"grad_norm": 0.28021496534347534,
|
| 858 |
+
"learning_rate": 0.0004999442113779973,
|
| 859 |
+
"loss": 0.4891,
|
| 860 |
+
"step": 5150
|
| 861 |
+
},
|
| 862 |
+
{
|
| 863 |
+
"epoch": 0.8652246256239601,
|
| 864 |
+
"grad_norm": 0.2550656497478485,
|
| 865 |
+
"learning_rate": 0.0004999436697408905,
|
| 866 |
+
"loss": 0.4866,
|
| 867 |
+
"step": 5200
|
| 868 |
+
},
|
| 869 |
+
{
|
| 870 |
+
"epoch": 0.8735440931780366,
|
| 871 |
+
"grad_norm": 0.27683132886886597,
|
| 872 |
+
"learning_rate": 0.0004999431281037837,
|
| 873 |
+
"loss": 0.4867,
|
| 874 |
+
"step": 5250
|
| 875 |
+
},
|
| 876 |
+
{
|
| 877 |
+
"epoch": 0.8818635607321131,
|
| 878 |
+
"grad_norm": 0.3277775049209595,
|
| 879 |
+
"learning_rate": 0.0004999425864666769,
|
| 880 |
+
"loss": 0.4897,
|
| 881 |
+
"step": 5300
|
| 882 |
+
},
|
| 883 |
+
{
|
| 884 |
+
"epoch": 0.8901830282861897,
|
| 885 |
+
"grad_norm": 0.29307055473327637,
|
| 886 |
+
"learning_rate": 0.0004999420448295701,
|
| 887 |
+
"loss": 0.4861,
|
| 888 |
+
"step": 5350
|
| 889 |
+
},
|
| 890 |
+
{
|
| 891 |
+
"epoch": 0.8985024958402662,
|
| 892 |
+
"grad_norm": 0.4498750865459442,
|
| 893 |
+
"learning_rate": 0.0004999415031924633,
|
| 894 |
+
"loss": 0.4839,
|
| 895 |
+
"step": 5400
|
| 896 |
+
},
|
| 897 |
+
{
|
| 898 |
+
"epoch": 0.9068219633943427,
|
| 899 |
+
"grad_norm": 0.2954080104827881,
|
| 900 |
+
"learning_rate": 0.0004999409615553564,
|
| 901 |
+
"loss": 0.4857,
|
| 902 |
+
"step": 5450
|
| 903 |
+
},
|
| 904 |
+
{
|
| 905 |
+
"epoch": 0.9151414309484193,
|
| 906 |
+
"grad_norm": 0.35260140895843506,
|
| 907 |
+
"learning_rate": 0.0004999404199182496,
|
| 908 |
+
"loss": 0.487,
|
| 909 |
+
"step": 5500
|
| 910 |
+
},
|
| 911 |
+
{
|
| 912 |
+
"epoch": 0.9151414309484193,
|
| 913 |
+
"eval_accuracy": 0.7438073817121431,
|
| 914 |
+
"eval_auc": 0.8241829377605762,
|
| 915 |
+
"eval_f1": 0.7730318561781915,
|
| 916 |
+
"eval_loss": 0.4809417724609375,
|
| 917 |
+
"eval_precision": 0.6936197123499789,
|
| 918 |
+
"eval_recall": 0.8729787146878603,
|
| 919 |
+
"eval_runtime": 3075.8035,
|
| 920 |
+
"eval_samples_per_second": 111.158,
|
| 921 |
+
"eval_steps_per_second": 13.895,
|
| 922 |
+
"step": 5500
|
| 923 |
+
},
|
| 924 |
+
{
|
| 925 |
+
"epoch": 0.9234608985024958,
|
| 926 |
+
"grad_norm": 0.353834867477417,
|
| 927 |
+
"learning_rate": 0.0004999398782811428,
|
| 928 |
+
"loss": 0.4848,
|
| 929 |
+
"step": 5550
|
| 930 |
+
},
|
| 931 |
+
{
|
| 932 |
+
"epoch": 0.9317803660565723,
|
| 933 |
+
"grad_norm": 0.47889459133148193,
|
| 934 |
+
"learning_rate": 0.000499939336644036,
|
| 935 |
+
"loss": 0.4862,
|
| 936 |
+
"step": 5600
|
| 937 |
+
},
|
| 938 |
+
{
|
| 939 |
+
"epoch": 0.940099833610649,
|
| 940 |
+
"grad_norm": 0.24000470340251923,
|
| 941 |
+
"learning_rate": 0.0004999387950069292,
|
| 942 |
+
"loss": 0.4807,
|
| 943 |
+
"step": 5650
|
| 944 |
+
},
|
| 945 |
+
{
|
| 946 |
+
"epoch": 0.9484193011647255,
|
| 947 |
+
"grad_norm": 0.34989428520202637,
|
| 948 |
+
"learning_rate": 0.0004999382533698223,
|
| 949 |
+
"loss": 0.4862,
|
| 950 |
+
"step": 5700
|
| 951 |
+
},
|
| 952 |
+
{
|
| 953 |
+
"epoch": 0.956738768718802,
|
| 954 |
+
"grad_norm": 0.3731101155281067,
|
| 955 |
+
"learning_rate": 0.0004999377117327155,
|
| 956 |
+
"loss": 0.4875,
|
| 957 |
+
"step": 5750
|
| 958 |
+
},
|
| 959 |
+
{
|
| 960 |
+
"epoch": 0.9650582362728786,
|
| 961 |
+
"grad_norm": 0.26715531945228577,
|
| 962 |
+
"learning_rate": 0.0004999371700956087,
|
| 963 |
+
"loss": 0.4824,
|
| 964 |
+
"step": 5800
|
| 965 |
+
},
|
| 966 |
+
{
|
| 967 |
+
"epoch": 0.9733777038269551,
|
| 968 |
+
"grad_norm": 0.25930115580558777,
|
| 969 |
+
"learning_rate": 0.0004999366284585019,
|
| 970 |
+
"loss": 0.4805,
|
| 971 |
+
"step": 5850
|
| 972 |
+
},
|
| 973 |
+
{
|
| 974 |
+
"epoch": 0.9816971713810316,
|
| 975 |
+
"grad_norm": 0.3994530439376831,
|
| 976 |
+
"learning_rate": 0.0004999360868213951,
|
| 977 |
+
"loss": 0.4848,
|
| 978 |
+
"step": 5900
|
| 979 |
+
},
|
| 980 |
+
{
|
| 981 |
+
"epoch": 0.9900166389351082,
|
| 982 |
+
"grad_norm": 0.3294505178928375,
|
| 983 |
+
"learning_rate": 0.0004999355451842882,
|
| 984 |
+
"loss": 0.4848,
|
| 985 |
+
"step": 5950
|
| 986 |
+
},
|
| 987 |
+
{
|
| 988 |
+
"epoch": 0.9983361064891847,
|
| 989 |
+
"grad_norm": 0.3712209165096283,
|
| 990 |
+
"learning_rate": 0.0004999350035471814,
|
| 991 |
+
"loss": 0.4819,
|
| 992 |
+
"step": 6000
|
| 993 |
+
},
|
| 994 |
+
{
|
| 995 |
+
"epoch": 0.9983361064891847,
|
| 996 |
+
"eval_accuracy": 0.7473610627699994,
|
| 997 |
+
"eval_auc": 0.827144023087403,
|
| 998 |
+
"eval_f1": 0.7763430113178821,
|
| 999 |
+
"eval_loss": 0.4787616729736328,
|
| 1000 |
+
"eval_precision": 0.6961882470952102,
|
| 1001 |
+
"eval_recall": 0.8773563373110395,
|
| 1002 |
+
"eval_runtime": 3107.0522,
|
| 1003 |
+
"eval_samples_per_second": 110.04,
|
| 1004 |
+
"eval_steps_per_second": 13.755,
|
| 1005 |
+
"step": 6000
|
| 1006 |
+
},
|
| 1007 |
+
{
|
| 1008 |
+
"epoch": 1.0066555740432612,
|
| 1009 |
+
"grad_norm": 0.4111676812171936,
|
| 1010 |
+
"learning_rate": 0.0004999344619100746,
|
| 1011 |
+
"loss": 0.4793,
|
| 1012 |
+
"step": 6050
|
| 1013 |
+
},
|
| 1014 |
+
{
|
| 1015 |
+
"epoch": 1.0149750415973378,
|
| 1016 |
+
"grad_norm": 0.28988873958587646,
|
| 1017 |
+
"learning_rate": 0.0004999339202729678,
|
| 1018 |
+
"loss": 0.4809,
|
| 1019 |
+
"step": 6100
|
| 1020 |
+
},
|
| 1021 |
+
{
|
| 1022 |
+
"epoch": 1.0232945091514143,
|
| 1023 |
+
"grad_norm": 0.4895919859409332,
|
| 1024 |
+
"learning_rate": 0.000499933378635861,
|
| 1025 |
+
"loss": 0.4774,
|
| 1026 |
+
"step": 6150
|
| 1027 |
+
},
|
| 1028 |
+
{
|
| 1029 |
+
"epoch": 1.0316139767054908,
|
| 1030 |
+
"grad_norm": 0.40186378359794617,
|
| 1031 |
+
"learning_rate": 0.0004999328369987542,
|
| 1032 |
+
"loss": 0.4783,
|
| 1033 |
+
"step": 6200
|
| 1034 |
+
},
|
| 1035 |
+
{
|
| 1036 |
+
"epoch": 1.0399334442595674,
|
| 1037 |
+
"grad_norm": 0.31091171503067017,
|
| 1038 |
+
"learning_rate": 0.0004999322953616473,
|
| 1039 |
+
"loss": 0.472,
|
| 1040 |
+
"step": 6250
|
| 1041 |
+
},
|
| 1042 |
+
{
|
| 1043 |
+
"epoch": 1.0482529118136439,
|
| 1044 |
+
"grad_norm": 0.4297674000263214,
|
| 1045 |
+
"learning_rate": 0.0004999317645572826,
|
| 1046 |
+
"loss": 0.4755,
|
| 1047 |
+
"step": 6300
|
| 1048 |
+
},
|
| 1049 |
+
{
|
| 1050 |
+
"epoch": 1.0565723793677204,
|
| 1051 |
+
"grad_norm": 0.5054673552513123,
|
| 1052 |
+
"learning_rate": 0.0004999312229201758,
|
| 1053 |
+
"loss": 0.4715,
|
| 1054 |
+
"step": 6350
|
| 1055 |
+
},
|
| 1056 |
+
{
|
| 1057 |
+
"epoch": 1.064891846921797,
|
| 1058 |
+
"grad_norm": 0.3952338993549347,
|
| 1059 |
+
"learning_rate": 0.000499930681283069,
|
| 1060 |
+
"loss": 0.4742,
|
| 1061 |
+
"step": 6400
|
| 1062 |
+
},
|
| 1063 |
+
{
|
| 1064 |
+
"epoch": 1.0732113144758735,
|
| 1065 |
+
"grad_norm": 0.2842634320259094,
|
| 1066 |
+
"learning_rate": 0.0004999301396459622,
|
| 1067 |
+
"loss": 0.4772,
|
| 1068 |
+
"step": 6450
|
| 1069 |
+
},
|
| 1070 |
+
{
|
| 1071 |
+
"epoch": 1.08153078202995,
|
| 1072 |
+
"grad_norm": 0.3358585238456726,
|
| 1073 |
+
"learning_rate": 0.0004999295980088553,
|
| 1074 |
+
"loss": 0.4709,
|
| 1075 |
+
"step": 6500
|
| 1076 |
+
},
|
| 1077 |
+
{
|
| 1078 |
+
"epoch": 1.08153078202995,
|
| 1079 |
+
"eval_accuracy": 0.7469252615538508,
|
| 1080 |
+
"eval_auc": 0.8303769212813772,
|
| 1081 |
+
"eval_f1": 0.759462915601023,
|
| 1082 |
+
"eval_loss": 0.47938379645347595,
|
| 1083 |
+
"eval_precision": 0.7233056748441893,
|
| 1084 |
+
"eval_recall": 0.7994252907197912,
|
| 1085 |
+
"eval_runtime": 3090.922,
|
| 1086 |
+
"eval_samples_per_second": 110.614,
|
| 1087 |
+
"eval_steps_per_second": 13.827,
|
| 1088 |
+
"step": 6500
|
| 1089 |
+
},
|
| 1090 |
+
{
|
| 1091 |
+
"epoch": 1.0898502495840265,
|
| 1092 |
+
"grad_norm": 0.33011338114738464,
|
| 1093 |
+
"learning_rate": 0.0004999290563717485,
|
| 1094 |
+
"loss": 0.4741,
|
| 1095 |
+
"step": 6550
|
| 1096 |
+
},
|
| 1097 |
+
{
|
| 1098 |
+
"epoch": 1.098169717138103,
|
| 1099 |
+
"grad_norm": 0.3731289207935333,
|
| 1100 |
+
"learning_rate": 0.0004999285147346417,
|
| 1101 |
+
"loss": 0.4797,
|
| 1102 |
+
"step": 6600
|
| 1103 |
+
},
|
| 1104 |
+
{
|
| 1105 |
+
"epoch": 1.1064891846921796,
|
| 1106 |
+
"grad_norm": 0.3975057601928711,
|
| 1107 |
+
"learning_rate": 0.0004999279730975349,
|
| 1108 |
+
"loss": 0.4768,
|
| 1109 |
+
"step": 6650
|
| 1110 |
+
},
|
| 1111 |
+
{
|
| 1112 |
+
"epoch": 1.1148086522462561,
|
| 1113 |
+
"grad_norm": 0.37461864948272705,
|
| 1114 |
+
"learning_rate": 0.0004999274314604281,
|
| 1115 |
+
"loss": 0.4715,
|
| 1116 |
+
"step": 6700
|
| 1117 |
+
},
|
| 1118 |
+
{
|
| 1119 |
+
"epoch": 1.1231281198003327,
|
| 1120 |
+
"grad_norm": 0.4079597294330597,
|
| 1121 |
+
"learning_rate": 0.0004999268898233213,
|
| 1122 |
+
"loss": 0.4738,
|
| 1123 |
+
"step": 6750
|
| 1124 |
+
},
|
| 1125 |
+
{
|
| 1126 |
+
"epoch": 1.1314475873544092,
|
| 1127 |
+
"grad_norm": 0.25766322016716003,
|
| 1128 |
+
"learning_rate": 0.0004999263481862144,
|
| 1129 |
+
"loss": 0.4749,
|
| 1130 |
+
"step": 6800
|
| 1131 |
+
},
|
| 1132 |
+
{
|
| 1133 |
+
"epoch": 1.1397670549084857,
|
| 1134 |
+
"grad_norm": 0.32334184646606445,
|
| 1135 |
+
"learning_rate": 0.0004999258065491076,
|
| 1136 |
+
"loss": 0.4753,
|
| 1137 |
+
"step": 6850
|
| 1138 |
+
},
|
| 1139 |
+
{
|
| 1140 |
+
"epoch": 1.1480865224625625,
|
| 1141 |
+
"grad_norm": 0.3726251423358917,
|
| 1142 |
+
"learning_rate": 0.0004999252649120008,
|
| 1143 |
+
"loss": 0.4706,
|
| 1144 |
+
"step": 6900
|
| 1145 |
+
},
|
| 1146 |
+
{
|
| 1147 |
+
"epoch": 1.156405990016639,
|
| 1148 |
+
"grad_norm": 0.2608793079853058,
|
| 1149 |
+
"learning_rate": 0.000499924723274894,
|
| 1150 |
+
"loss": 0.4758,
|
| 1151 |
+
"step": 6950
|
| 1152 |
+
},
|
| 1153 |
+
{
|
| 1154 |
+
"epoch": 1.1647254575707155,
|
| 1155 |
+
"grad_norm": 0.2321689873933792,
|
| 1156 |
+
"learning_rate": 0.0004999241816377872,
|
| 1157 |
+
"loss": 0.4775,
|
| 1158 |
+
"step": 7000
|
| 1159 |
+
},
|
| 1160 |
+
{
|
| 1161 |
+
"epoch": 1.1647254575707155,
|
| 1162 |
+
"eval_accuracy": 0.7482034167985282,
|
| 1163 |
+
"eval_auc": 0.8299646263747171,
|
| 1164 |
+
"eval_f1": 0.7817299037815499,
|
| 1165 |
+
"eval_loss": 0.4775802195072174,
|
| 1166 |
+
"eval_precision": 0.6896254014833636,
|
| 1167 |
+
"eval_recall": 0.9022291931245574,
|
| 1168 |
+
"eval_runtime": 3102.1713,
|
| 1169 |
+
"eval_samples_per_second": 110.213,
|
| 1170 |
+
"eval_steps_per_second": 13.777,
|
| 1171 |
+
"step": 7000
|
| 1172 |
+
},
|
| 1173 |
+
{
|
| 1174 |
+
"epoch": 1.173044925124792,
|
| 1175 |
+
"grad_norm": 0.4716586172580719,
|
| 1176 |
+
"learning_rate": 0.0004999236400006803,
|
| 1177 |
+
"loss": 0.4688,
|
| 1178 |
+
"step": 7050
|
| 1179 |
+
},
|
| 1180 |
+
{
|
| 1181 |
+
"epoch": 1.1813643926788686,
|
| 1182 |
+
"grad_norm": 0.3553094267845154,
|
| 1183 |
+
"learning_rate": 0.0004999230983635735,
|
| 1184 |
+
"loss": 0.4699,
|
| 1185 |
+
"step": 7100
|
| 1186 |
+
},
|
| 1187 |
+
{
|
| 1188 |
+
"epoch": 1.1896838602329451,
|
| 1189 |
+
"grad_norm": 0.5420466065406799,
|
| 1190 |
+
"learning_rate": 0.0004999225567264667,
|
| 1191 |
+
"loss": 0.4742,
|
| 1192 |
+
"step": 7150
|
| 1193 |
+
},
|
| 1194 |
+
{
|
| 1195 |
+
"epoch": 1.1980033277870217,
|
| 1196 |
+
"grad_norm": 0.26752716302871704,
|
| 1197 |
+
"learning_rate": 0.0004999220150893599,
|
| 1198 |
+
"loss": 0.4725,
|
| 1199 |
+
"step": 7200
|
| 1200 |
+
},
|
| 1201 |
+
{
|
| 1202 |
+
"epoch": 1.2063227953410982,
|
| 1203 |
+
"grad_norm": 0.2967946529388428,
|
| 1204 |
+
"learning_rate": 0.0004999214734522531,
|
| 1205 |
+
"loss": 0.4671,
|
| 1206 |
+
"step": 7250
|
| 1207 |
+
},
|
| 1208 |
+
{
|
| 1209 |
+
"epoch": 1.2146422628951747,
|
| 1210 |
+
"grad_norm": 0.24301719665527344,
|
| 1211 |
+
"learning_rate": 0.0004999209318151461,
|
| 1212 |
+
"loss": 0.4741,
|
| 1213 |
+
"step": 7300
|
| 1214 |
+
},
|
| 1215 |
+
{
|
| 1216 |
+
"epoch": 1.2229617304492513,
|
| 1217 |
+
"grad_norm": 0.3372076451778412,
|
| 1218 |
+
"learning_rate": 0.0004999203901780393,
|
| 1219 |
+
"loss": 0.4718,
|
| 1220 |
+
"step": 7350
|
| 1221 |
+
},
|
| 1222 |
+
{
|
| 1223 |
+
"epoch": 1.2312811980033278,
|
| 1224 |
+
"grad_norm": 0.28806430101394653,
|
| 1225 |
+
"learning_rate": 0.0004999198485409325,
|
| 1226 |
+
"loss": 0.4751,
|
| 1227 |
+
"step": 7400
|
| 1228 |
+
},
|
| 1229 |
+
{
|
| 1230 |
+
"epoch": 1.2396006655574043,
|
| 1231 |
+
"grad_norm": 0.28929972648620605,
|
| 1232 |
+
"learning_rate": 0.0004999193069038257,
|
| 1233 |
+
"loss": 0.4748,
|
| 1234 |
+
"step": 7450
|
| 1235 |
+
},
|
| 1236 |
+
{
|
| 1237 |
+
"epoch": 1.2479201331114809,
|
| 1238 |
+
"grad_norm": 0.5165761113166809,
|
| 1239 |
+
"learning_rate": 0.0004999187652667189,
|
| 1240 |
+
"loss": 0.4738,
|
| 1241 |
+
"step": 7500
|
| 1242 |
+
},
|
| 1243 |
+
{
|
| 1244 |
+
"epoch": 1.2479201331114809,
|
| 1245 |
+
"eval_accuracy": 0.7527018212981027,
|
| 1246 |
+
"eval_auc": 0.8341791803614174,
|
| 1247 |
+
"eval_f1": 0.7692807265047057,
|
| 1248 |
+
"eval_loss": 0.4720609784126282,
|
| 1249 |
+
"eval_precision": 0.7206515404042986,
|
| 1250 |
+
"eval_recall": 0.8249477670027916,
|
| 1251 |
+
"eval_runtime": 3117.7578,
|
| 1252 |
+
"eval_samples_per_second": 109.662,
|
| 1253 |
+
"eval_steps_per_second": 13.708,
|
| 1254 |
+
"step": 7500
|
| 1255 |
+
},
|
| 1256 |
+
{
|
| 1257 |
+
"epoch": 1.2562396006655574,
|
| 1258 |
+
"grad_norm": 0.3871491551399231,
|
| 1259 |
+
"learning_rate": 0.0004999182236296121,
|
| 1260 |
+
"loss": 0.4749,
|
| 1261 |
+
"step": 7550
|
| 1262 |
+
},
|
| 1263 |
+
{
|
| 1264 |
+
"epoch": 1.264559068219634,
|
| 1265 |
+
"grad_norm": 0.34656795859336853,
|
| 1266 |
+
"learning_rate": 0.0004999176819925052,
|
| 1267 |
+
"loss": 0.4729,
|
| 1268 |
+
"step": 7600
|
| 1269 |
+
},
|
| 1270 |
+
{
|
| 1271 |
+
"epoch": 1.2728785357737105,
|
| 1272 |
+
"grad_norm": 0.4117598533630371,
|
| 1273 |
+
"learning_rate": 0.0004999171403553984,
|
| 1274 |
+
"loss": 0.4677,
|
| 1275 |
+
"step": 7650
|
| 1276 |
+
},
|
| 1277 |
+
{
|
| 1278 |
+
"epoch": 1.281198003327787,
|
| 1279 |
+
"grad_norm": 0.25794079899787903,
|
| 1280 |
+
"learning_rate": 0.0004999165987182916,
|
| 1281 |
+
"loss": 0.4723,
|
| 1282 |
+
"step": 7700
|
| 1283 |
+
},
|
| 1284 |
+
{
|
| 1285 |
+
"epoch": 1.2895174708818635,
|
| 1286 |
+
"grad_norm": 0.33428308367729187,
|
| 1287 |
+
"learning_rate": 0.0004999160570811848,
|
| 1288 |
+
"loss": 0.471,
|
| 1289 |
+
"step": 7750
|
| 1290 |
+
},
|
| 1291 |
+
{
|
| 1292 |
+
"epoch": 1.29783693843594,
|
| 1293 |
+
"grad_norm": 0.3722244203090668,
|
| 1294 |
+
"learning_rate": 0.000499915515444078,
|
| 1295 |
+
"loss": 0.4695,
|
| 1296 |
+
"step": 7800
|
| 1297 |
+
},
|
| 1298 |
+
{
|
| 1299 |
+
"epoch": 1.3061564059900166,
|
| 1300 |
+
"grad_norm": 0.34326881170272827,
|
| 1301 |
+
"learning_rate": 0.0004999149738069711,
|
| 1302 |
+
"loss": 0.4693,
|
| 1303 |
+
"step": 7850
|
| 1304 |
+
},
|
| 1305 |
+
{
|
| 1306 |
+
"epoch": 1.3144758735440931,
|
| 1307 |
+
"grad_norm": 0.473015695810318,
|
| 1308 |
+
"learning_rate": 0.0004999144321698643,
|
| 1309 |
+
"loss": 0.4773,
|
| 1310 |
+
"step": 7900
|
| 1311 |
+
},
|
| 1312 |
+
{
|
| 1313 |
+
"epoch": 1.3227953410981697,
|
| 1314 |
+
"grad_norm": 0.39536336064338684,
|
| 1315 |
+
"learning_rate": 0.0004999138905327575,
|
| 1316 |
+
"loss": 0.4633,
|
| 1317 |
+
"step": 7950
|
| 1318 |
+
},
|
| 1319 |
+
{
|
| 1320 |
+
"epoch": 1.3311148086522462,
|
| 1321 |
+
"grad_norm": 0.24282647669315338,
|
| 1322 |
+
"learning_rate": 0.0004999133488956507,
|
| 1323 |
+
"loss": 0.4704,
|
| 1324 |
+
"step": 8000
|
| 1325 |
+
},
|
| 1326 |
+
{
|
| 1327 |
+
"epoch": 1.3311148086522462,
|
| 1328 |
+
"eval_accuracy": 0.7551382133320074,
|
| 1329 |
+
"eval_auc": 0.8357908200441471,
|
| 1330 |
+
"eval_f1": 0.7845750840156658,
|
| 1331 |
+
"eval_loss": 0.46888816356658936,
|
| 1332 |
+
"eval_precision": 0.7001180258003481,
|
| 1333 |
+
"eval_recall": 0.8922039691225442,
|
| 1334 |
+
"eval_runtime": 3128.319,
|
| 1335 |
+
"eval_samples_per_second": 109.292,
|
| 1336 |
+
"eval_steps_per_second": 13.662,
|
| 1337 |
+
"step": 8000
|
| 1338 |
+
},
|
| 1339 |
+
{
|
| 1340 |
+
"epoch": 1.3394342762063227,
|
| 1341 |
+
"grad_norm": 0.46165645122528076,
|
| 1342 |
+
"learning_rate": 0.0004999128072585439,
|
| 1343 |
+
"loss": 0.4677,
|
| 1344 |
+
"step": 8050
|
| 1345 |
+
},
|
| 1346 |
+
{
|
| 1347 |
+
"epoch": 1.3477537437603995,
|
| 1348 |
+
"grad_norm": 0.2814394235610962,
|
| 1349 |
+
"learning_rate": 0.0004999122656214371,
|
| 1350 |
+
"loss": 0.4655,
|
| 1351 |
+
"step": 8100
|
| 1352 |
+
},
|
| 1353 |
+
{
|
| 1354 |
+
"epoch": 1.356073211314476,
|
| 1355 |
+
"grad_norm": 0.24799716472625732,
|
| 1356 |
+
"learning_rate": 0.0004999117239843302,
|
| 1357 |
+
"loss": 0.4705,
|
| 1358 |
+
"step": 8150
|
| 1359 |
+
},
|
| 1360 |
+
{
|
| 1361 |
+
"epoch": 1.3643926788685525,
|
| 1362 |
+
"grad_norm": 0.3806433379650116,
|
| 1363 |
+
"learning_rate": 0.0004999111823472234,
|
| 1364 |
+
"loss": 0.4689,
|
| 1365 |
+
"step": 8200
|
| 1366 |
+
},
|
| 1367 |
+
{
|
| 1368 |
+
"epoch": 1.372712146422629,
|
| 1369 |
+
"grad_norm": 0.3523135185241699,
|
| 1370 |
+
"learning_rate": 0.0004999106407101166,
|
| 1371 |
+
"loss": 0.4695,
|
| 1372 |
+
"step": 8250
|
| 1373 |
+
},
|
| 1374 |
+
{
|
| 1375 |
+
"epoch": 1.3810316139767056,
|
| 1376 |
+
"grad_norm": 0.2665747106075287,
|
| 1377 |
+
"learning_rate": 0.0004999100990730098,
|
| 1378 |
+
"loss": 0.4737,
|
| 1379 |
+
"step": 8300
|
| 1380 |
+
},
|
| 1381 |
+
{
|
| 1382 |
+
"epoch": 1.3893510815307821,
|
| 1383 |
+
"grad_norm": 0.28612571954727173,
|
| 1384 |
+
"learning_rate": 0.000499909557435903,
|
| 1385 |
+
"loss": 0.4686,
|
| 1386 |
+
"step": 8350
|
| 1387 |
+
},
|
| 1388 |
+
{
|
| 1389 |
+
"epoch": 1.3976705490848587,
|
| 1390 |
+
"grad_norm": 0.2960534691810608,
|
| 1391 |
+
"learning_rate": 0.0004999090157987961,
|
| 1392 |
+
"loss": 0.4696,
|
| 1393 |
+
"step": 8400
|
| 1394 |
+
},
|
| 1395 |
+
{
|
| 1396 |
+
"epoch": 1.4059900166389352,
|
| 1397 |
+
"grad_norm": 0.34513574838638306,
|
| 1398 |
+
"learning_rate": 0.0004999084741616894,
|
| 1399 |
+
"loss": 0.4694,
|
| 1400 |
+
"step": 8450
|
| 1401 |
+
},
|
| 1402 |
+
{
|
| 1403 |
+
"epoch": 1.4143094841930117,
|
| 1404 |
+
"grad_norm": 0.3929885923862457,
|
| 1405 |
+
"learning_rate": 0.0004999079325245825,
|
| 1406 |
+
"loss": 0.4687,
|
| 1407 |
+
"step": 8500
|
| 1408 |
+
},
|
| 1409 |
+
{
|
| 1410 |
+
"epoch": 1.4143094841930117,
|
| 1411 |
+
"eval_accuracy": 0.7571154054267488,
|
| 1412 |
+
"eval_auc": 0.8376226439602212,
|
| 1413 |
+
"eval_f1": 0.7821289144488288,
|
| 1414 |
+
"eval_loss": 0.4663051962852478,
|
| 1415 |
+
"eval_precision": 0.7088304808282172,
|
| 1416 |
+
"eval_recall": 0.8723349466550399,
|
| 1417 |
+
"eval_runtime": 3128.487,
|
| 1418 |
+
"eval_samples_per_second": 109.286,
|
| 1419 |
+
"eval_steps_per_second": 13.661,
|
| 1420 |
+
"step": 8500
|
| 1421 |
+
},
|
| 1422 |
+
{
|
| 1423 |
+
"epoch": 1.4226289517470883,
|
| 1424 |
+
"grad_norm": 0.667980968952179,
|
| 1425 |
+
"learning_rate": 0.0004999074017202178,
|
| 1426 |
+
"loss": 0.4712,
|
| 1427 |
+
"step": 8550
|
| 1428 |
+
},
|
| 1429 |
+
{
|
| 1430 |
+
"epoch": 1.4309484193011648,
|
| 1431 |
+
"grad_norm": 0.27172645926475525,
|
| 1432 |
+
"learning_rate": 0.000499906860083111,
|
| 1433 |
+
"loss": 0.4713,
|
| 1434 |
+
"step": 8600
|
| 1435 |
+
},
|
| 1436 |
+
{
|
| 1437 |
+
"epoch": 1.4392678868552413,
|
| 1438 |
+
"grad_norm": 0.4408021569252014,
|
| 1439 |
+
"learning_rate": 0.0004999063184460041,
|
| 1440 |
+
"loss": 0.4706,
|
| 1441 |
+
"step": 8650
|
| 1442 |
+
},
|
| 1443 |
+
{
|
| 1444 |
+
"epoch": 1.4475873544093179,
|
| 1445 |
+
"grad_norm": 0.25165098905563354,
|
| 1446 |
+
"learning_rate": 0.0004999057768088973,
|
| 1447 |
+
"loss": 0.4699,
|
| 1448 |
+
"step": 8700
|
| 1449 |
+
},
|
| 1450 |
+
{
|
| 1451 |
+
"epoch": 1.4559068219633944,
|
| 1452 |
+
"grad_norm": 0.35004204511642456,
|
| 1453 |
+
"learning_rate": 0.0004999052351717905,
|
| 1454 |
+
"loss": 0.4708,
|
| 1455 |
+
"step": 8750
|
| 1456 |
+
},
|
| 1457 |
+
{
|
| 1458 |
+
"epoch": 1.464226289517471,
|
| 1459 |
+
"grad_norm": 0.33756914734840393,
|
| 1460 |
+
"learning_rate": 0.0004999046935346837,
|
| 1461 |
+
"loss": 0.4665,
|
| 1462 |
+
"step": 8800
|
| 1463 |
+
},
|
| 1464 |
+
{
|
| 1465 |
+
"epoch": 1.4725457570715474,
|
| 1466 |
+
"grad_norm": 0.4379380941390991,
|
| 1467 |
+
"learning_rate": 0.0004999041518975769,
|
| 1468 |
+
"loss": 0.4671,
|
| 1469 |
+
"step": 8850
|
| 1470 |
+
},
|
| 1471 |
+
{
|
| 1472 |
+
"epoch": 1.480865224625624,
|
| 1473 |
+
"grad_norm": 0.450702965259552,
|
| 1474 |
+
"learning_rate": 0.0004999036102604701,
|
| 1475 |
+
"loss": 0.4682,
|
| 1476 |
+
"step": 8900
|
| 1477 |
+
},
|
| 1478 |
+
{
|
| 1479 |
+
"epoch": 1.4891846921797005,
|
| 1480 |
+
"grad_norm": 0.429463654756546,
|
| 1481 |
+
"learning_rate": 0.0004999030686233632,
|
| 1482 |
+
"loss": 0.4657,
|
| 1483 |
+
"step": 8950
|
| 1484 |
+
},
|
| 1485 |
+
{
|
| 1486 |
+
"epoch": 1.497504159733777,
|
| 1487 |
+
"grad_norm": 0.26801300048828125,
|
| 1488 |
+
"learning_rate": 0.0004999025269862564,
|
| 1489 |
+
"loss": 0.4663,
|
| 1490 |
+
"step": 9000
|
| 1491 |
+
},
|
| 1492 |
+
{
|
| 1493 |
+
"epoch": 1.497504159733777,
|
| 1494 |
+
"eval_accuracy": 0.7582911912582371,
|
| 1495 |
+
"eval_auc": 0.839204544655265,
|
| 1496 |
+
"eval_f1": 0.7839499717650011,
|
| 1497 |
+
"eval_loss": 0.4652154743671417,
|
| 1498 |
+
"eval_precision": 0.7084461454863326,
|
| 1499 |
+
"eval_recall": 0.8774675336076175,
|
| 1500 |
+
"eval_runtime": 3125.7976,
|
| 1501 |
+
"eval_samples_per_second": 109.38,
|
| 1502 |
+
"eval_steps_per_second": 13.673,
|
| 1503 |
+
"step": 9000
|
| 1504 |
+
},
|
| 1505 |
+
{
|
| 1506 |
+
"epoch": 1.5058236272878536,
|
| 1507 |
+
"grad_norm": 0.41154783964157104,
|
| 1508 |
+
"learning_rate": 0.0004999019853491496,
|
| 1509 |
+
"loss": 0.4675,
|
| 1510 |
+
"step": 9050
|
| 1511 |
+
},
|
| 1512 |
+
{
|
| 1513 |
+
"epoch": 1.51414309484193,
|
| 1514 |
+
"grad_norm": 0.5559844374656677,
|
| 1515 |
+
"learning_rate": 0.0004999014437120428,
|
| 1516 |
+
"loss": 0.4668,
|
| 1517 |
+
"step": 9100
|
| 1518 |
+
},
|
| 1519 |
+
{
|
| 1520 |
+
"epoch": 1.5224625623960066,
|
| 1521 |
+
"grad_norm": 0.2977549135684967,
|
| 1522 |
+
"learning_rate": 0.000499900902074936,
|
| 1523 |
+
"loss": 0.4652,
|
| 1524 |
+
"step": 9150
|
| 1525 |
+
},
|
| 1526 |
+
{
|
| 1527 |
+
"epoch": 1.5307820299500832,
|
| 1528 |
+
"grad_norm": 0.24874624609947205,
|
| 1529 |
+
"learning_rate": 0.0004999003604378291,
|
| 1530 |
+
"loss": 0.465,
|
| 1531 |
+
"step": 9200
|
| 1532 |
+
},
|
| 1533 |
+
{
|
| 1534 |
+
"epoch": 1.5391014975041597,
|
| 1535 |
+
"grad_norm": 0.7150341868400574,
|
| 1536 |
+
"learning_rate": 0.0004998998188007223,
|
| 1537 |
+
"loss": 0.468,
|
| 1538 |
+
"step": 9250
|
| 1539 |
+
},
|
| 1540 |
+
{
|
| 1541 |
+
"epoch": 1.5474209650582362,
|
| 1542 |
+
"grad_norm": 0.2461651861667633,
|
| 1543 |
+
"learning_rate": 0.0004998992771636155,
|
| 1544 |
+
"loss": 0.4664,
|
| 1545 |
+
"step": 9300
|
| 1546 |
+
},
|
| 1547 |
+
{
|
| 1548 |
+
"epoch": 1.5557404326123128,
|
| 1549 |
+
"grad_norm": 0.4250808358192444,
|
| 1550 |
+
"learning_rate": 0.0004998987355265087,
|
| 1551 |
+
"loss": 0.4641,
|
| 1552 |
+
"step": 9350
|
| 1553 |
+
},
|
| 1554 |
+
{
|
| 1555 |
+
"epoch": 1.5640599001663893,
|
| 1556 |
+
"grad_norm": 0.3863760530948639,
|
| 1557 |
+
"learning_rate": 0.0004998981938894019,
|
| 1558 |
+
"loss": 0.4675,
|
| 1559 |
+
"step": 9400
|
| 1560 |
+
},
|
| 1561 |
+
{
|
| 1562 |
+
"epoch": 1.5723793677204658,
|
| 1563 |
+
"grad_norm": 0.31154608726501465,
|
| 1564 |
+
"learning_rate": 0.000499897652252295,
|
| 1565 |
+
"loss": 0.4639,
|
| 1566 |
+
"step": 9450
|
| 1567 |
+
},
|
| 1568 |
+
{
|
| 1569 |
+
"epoch": 1.5806988352745424,
|
| 1570 |
+
"grad_norm": 0.3062475323677063,
|
| 1571 |
+
"learning_rate": 0.0004998971106151881,
|
| 1572 |
+
"loss": 0.4667,
|
| 1573 |
+
"step": 9500
|
| 1574 |
+
},
|
| 1575 |
+
{
|
| 1576 |
+
"epoch": 1.5806988352745424,
|
| 1577 |
+
"eval_accuracy": 0.7589258816200106,
|
| 1578 |
+
"eval_auc": 0.840721603017736,
|
| 1579 |
+
"eval_f1": 0.7787355473290578,
|
| 1580 |
+
"eval_loss": 0.46345818042755127,
|
| 1581 |
+
"eval_precision": 0.7193166038484428,
|
| 1582 |
+
"eval_recall": 0.8488549707670788,
|
| 1583 |
+
"eval_runtime": 3071.5791,
|
| 1584 |
+
"eval_samples_per_second": 111.31,
|
| 1585 |
+
"eval_steps_per_second": 13.914,
|
| 1586 |
+
"step": 9500
|
| 1587 |
+
},
|
| 1588 |
+
{
|
| 1589 |
+
"epoch": 1.589018302828619,
|
| 1590 |
+
"grad_norm": 0.2855340838432312,
|
| 1591 |
+
"learning_rate": 0.0004998965689780813,
|
| 1592 |
+
"loss": 0.4682,
|
| 1593 |
+
"step": 9550
|
| 1594 |
+
},
|
| 1595 |
+
{
|
| 1596 |
+
"epoch": 1.5973377703826954,
|
| 1597 |
+
"grad_norm": 0.309037983417511,
|
| 1598 |
+
"learning_rate": 0.0004998960273409745,
|
| 1599 |
+
"loss": 0.464,
|
| 1600 |
+
"step": 9600
|
| 1601 |
+
},
|
| 1602 |
+
{
|
| 1603 |
+
"epoch": 1.605657237936772,
|
| 1604 |
+
"grad_norm": 0.4070012867450714,
|
| 1605 |
+
"learning_rate": 0.0004998954857038677,
|
| 1606 |
+
"loss": 0.4652,
|
| 1607 |
+
"step": 9650
|
| 1608 |
+
},
|
| 1609 |
+
{
|
| 1610 |
+
"epoch": 1.6139767054908485,
|
| 1611 |
+
"grad_norm": 0.4464728534221649,
|
| 1612 |
+
"learning_rate": 0.0004998949440667609,
|
| 1613 |
+
"loss": 0.4655,
|
| 1614 |
+
"step": 9700
|
| 1615 |
+
},
|
| 1616 |
+
{
|
| 1617 |
+
"epoch": 1.622296173044925,
|
| 1618 |
+
"grad_norm": 0.2548810541629791,
|
| 1619 |
+
"learning_rate": 0.000499894402429654,
|
| 1620 |
+
"loss": 0.4694,
|
| 1621 |
+
"step": 9750
|
| 1622 |
+
},
|
| 1623 |
+
{
|
| 1624 |
+
"epoch": 1.6306156405990015,
|
| 1625 |
+
"grad_norm": 0.2812168002128601,
|
| 1626 |
+
"learning_rate": 0.0004998938607925473,
|
| 1627 |
+
"loss": 0.4618,
|
| 1628 |
+
"step": 9800
|
| 1629 |
+
},
|
| 1630 |
+
{
|
| 1631 |
+
"epoch": 1.638935108153078,
|
| 1632 |
+
"grad_norm": 0.28069692850112915,
|
| 1633 |
+
"learning_rate": 0.0004998933191554404,
|
| 1634 |
+
"loss": 0.4669,
|
| 1635 |
+
"step": 9850
|
| 1636 |
+
},
|
| 1637 |
+
{
|
| 1638 |
+
"epoch": 1.6472545757071546,
|
| 1639 |
+
"grad_norm": 0.2677462100982666,
|
| 1640 |
+
"learning_rate": 0.0004998927775183336,
|
| 1641 |
+
"loss": 0.469,
|
| 1642 |
+
"step": 9900
|
| 1643 |
+
},
|
| 1644 |
+
{
|
| 1645 |
+
"epoch": 1.6555740432612311,
|
| 1646 |
+
"grad_norm": 0.3109247386455536,
|
| 1647 |
+
"learning_rate": 0.0004998922358812268,
|
| 1648 |
+
"loss": 0.4621,
|
| 1649 |
+
"step": 9950
|
| 1650 |
+
},
|
| 1651 |
+
{
|
| 1652 |
+
"epoch": 1.6638935108153077,
|
| 1653 |
+
"grad_norm": 0.3598281741142273,
|
| 1654 |
+
"learning_rate": 0.0004998916942441199,
|
| 1655 |
+
"loss": 0.4614,
|
| 1656 |
+
"step": 10000
|
| 1657 |
+
},
|
| 1658 |
+
{
|
| 1659 |
+
"epoch": 1.6638935108153077,
|
| 1660 |
+
"eval_accuracy": 0.7620525359828487,
|
| 1661 |
+
"eval_auc": 0.8427547777707038,
|
| 1662 |
+
"eval_f1": 0.7841862883458367,
|
| 1663 |
+
"eval_loss": 0.460246205329895,
|
| 1664 |
+
"eval_precision": 0.7171692666003542,
|
| 1665 |
+
"eval_recall": 0.8650194008275346,
|
| 1666 |
+
"eval_runtime": 3091.9645,
|
| 1667 |
+
"eval_samples_per_second": 110.577,
|
| 1668 |
+
"eval_steps_per_second": 13.822,
|
| 1669 |
+
"step": 10000
|
| 1670 |
+
},
|
| 1671 |
+
{
|
| 1672 |
+
"epoch": 1.6722129783693842,
|
| 1673 |
+
"grad_norm": 0.5699976682662964,
|
| 1674 |
+
"learning_rate": 0.0004998911526070131,
|
| 1675 |
+
"loss": 0.4668,
|
| 1676 |
+
"step": 10050
|
| 1677 |
+
},
|
| 1678 |
+
{
|
| 1679 |
+
"epoch": 1.6805324459234607,
|
| 1680 |
+
"grad_norm": 0.3142874538898468,
|
| 1681 |
+
"learning_rate": 0.0004998906109699063,
|
| 1682 |
+
"loss": 0.4634,
|
| 1683 |
+
"step": 10100
|
| 1684 |
+
},
|
| 1685 |
+
{
|
| 1686 |
+
"epoch": 1.6888519134775375,
|
| 1687 |
+
"grad_norm": 0.3907163441181183,
|
| 1688 |
+
"learning_rate": 0.0004998900693327995,
|
| 1689 |
+
"loss": 0.4686,
|
| 1690 |
+
"step": 10150
|
| 1691 |
+
},
|
| 1692 |
+
{
|
| 1693 |
+
"epoch": 1.697171381031614,
|
| 1694 |
+
"grad_norm": 0.39660388231277466,
|
| 1695 |
+
"learning_rate": 0.0004998895276956927,
|
| 1696 |
+
"loss": 0.465,
|
| 1697 |
+
"step": 10200
|
| 1698 |
+
},
|
| 1699 |
+
{
|
| 1700 |
+
"epoch": 1.7054908485856906,
|
| 1701 |
+
"grad_norm": 0.6148430705070496,
|
| 1702 |
+
"learning_rate": 0.0004998889860585859,
|
| 1703 |
+
"loss": 0.4654,
|
| 1704 |
+
"step": 10250
|
| 1705 |
+
},
|
| 1706 |
+
{
|
| 1707 |
+
"epoch": 1.713810316139767,
|
| 1708 |
+
"grad_norm": 0.2848416864871979,
|
| 1709 |
+
"learning_rate": 0.000499888444421479,
|
| 1710 |
+
"loss": 0.4617,
|
| 1711 |
+
"step": 10300
|
| 1712 |
+
},
|
| 1713 |
+
{
|
| 1714 |
+
"epoch": 1.7221297836938436,
|
| 1715 |
+
"grad_norm": 0.4551065266132355,
|
| 1716 |
+
"learning_rate": 0.0004998879027843723,
|
| 1717 |
+
"loss": 0.4622,
|
| 1718 |
+
"step": 10350
|
| 1719 |
+
},
|
| 1720 |
+
{
|
| 1721 |
+
"epoch": 1.7304492512479202,
|
| 1722 |
+
"grad_norm": 0.24504904448986053,
|
| 1723 |
+
"learning_rate": 0.0004998873611472654,
|
| 1724 |
+
"loss": 0.4558,
|
| 1725 |
+
"step": 10400
|
| 1726 |
+
},
|
| 1727 |
+
{
|
| 1728 |
+
"epoch": 1.7387687188019967,
|
| 1729 |
+
"grad_norm": 0.2634543776512146,
|
| 1730 |
+
"learning_rate": 0.0004998868195101586,
|
| 1731 |
+
"loss": 0.4621,
|
| 1732 |
+
"step": 10450
|
| 1733 |
+
},
|
| 1734 |
+
{
|
| 1735 |
+
"epoch": 1.7470881863560732,
|
| 1736 |
+
"grad_norm": 0.3404432237148285,
|
| 1737 |
+
"learning_rate": 0.0004998862778730518,
|
| 1738 |
+
"loss": 0.465,
|
| 1739 |
+
"step": 10500
|
| 1740 |
+
},
|
| 1741 |
+
{
|
| 1742 |
+
"epoch": 1.7470881863560732,
|
| 1743 |
+
"eval_accuracy": 0.7618653461987313,
|
| 1744 |
+
"eval_auc": 0.8441348324318876,
|
| 1745 |
+
"eval_f1": 0.7790148521301081,
|
| 1746 |
+
"eval_loss": 0.45925500988960266,
|
| 1747 |
+
"eval_precision": 0.7263860135754164,
|
| 1748 |
+
"eval_recall": 0.8398656280542404,
|
| 1749 |
+
"eval_runtime": 3075.9859,
|
| 1750 |
+
"eval_samples_per_second": 111.151,
|
| 1751 |
+
"eval_steps_per_second": 13.894,
|
| 1752 |
+
"step": 10500
|
| 1753 |
+
},
|
| 1754 |
+
{
|
| 1755 |
+
"epoch": 1.7554076539101497,
|
| 1756 |
+
"grad_norm": 0.35343432426452637,
|
| 1757 |
+
"learning_rate": 0.0004998857362359449,
|
| 1758 |
+
"loss": 0.4592,
|
| 1759 |
+
"step": 10550
|
| 1760 |
+
},
|
| 1761 |
+
{
|
| 1762 |
+
"epoch": 1.7637271214642263,
|
| 1763 |
+
"grad_norm": 0.3516612648963928,
|
| 1764 |
+
"learning_rate": 0.0004998851945988382,
|
| 1765 |
+
"loss": 0.464,
|
| 1766 |
+
"step": 10600
|
| 1767 |
+
},
|
| 1768 |
+
{
|
| 1769 |
+
"epoch": 1.7720465890183028,
|
| 1770 |
+
"grad_norm": 0.295074462890625,
|
| 1771 |
+
"learning_rate": 0.0004998846529617313,
|
| 1772 |
+
"loss": 0.4642,
|
| 1773 |
+
"step": 10650
|
| 1774 |
+
},
|
| 1775 |
+
{
|
| 1776 |
+
"epoch": 1.7803660565723793,
|
| 1777 |
+
"grad_norm": 0.3098844885826111,
|
| 1778 |
+
"learning_rate": 0.0004998841113246245,
|
| 1779 |
+
"loss": 0.463,
|
| 1780 |
+
"step": 10700
|
| 1781 |
+
},
|
| 1782 |
+
{
|
| 1783 |
+
"epoch": 1.7886855241264559,
|
| 1784 |
+
"grad_norm": 0.3475278317928314,
|
| 1785 |
+
"learning_rate": 0.0004998835696875177,
|
| 1786 |
+
"loss": 0.4593,
|
| 1787 |
+
"step": 10750
|
| 1788 |
+
},
|
| 1789 |
+
{
|
| 1790 |
+
"epoch": 1.7970049916805324,
|
| 1791 |
+
"grad_norm": 0.2945404350757599,
|
| 1792 |
+
"learning_rate": 0.0004998830280504109,
|
| 1793 |
+
"loss": 0.4663,
|
| 1794 |
+
"step": 10800
|
| 1795 |
+
},
|
| 1796 |
+
{
|
| 1797 |
+
"epoch": 1.805324459234609,
|
| 1798 |
+
"grad_norm": 0.3487035632133484,
|
| 1799 |
+
"learning_rate": 0.000499882486413304,
|
| 1800 |
+
"loss": 0.4637,
|
| 1801 |
+
"step": 10850
|
| 1802 |
+
},
|
| 1803 |
+
{
|
| 1804 |
+
"epoch": 1.8136439267886857,
|
| 1805 |
+
"grad_norm": 0.3474220931529999,
|
| 1806 |
+
"learning_rate": 0.0004998819447761971,
|
| 1807 |
+
"loss": 0.4639,
|
| 1808 |
+
"step": 10900
|
| 1809 |
+
},
|
| 1810 |
+
{
|
| 1811 |
+
"epoch": 1.8219633943427622,
|
| 1812 |
+
"grad_norm": 0.5383617877960205,
|
| 1813 |
+
"learning_rate": 0.0004998814031390903,
|
| 1814 |
+
"loss": 0.4615,
|
| 1815 |
+
"step": 10950
|
| 1816 |
+
},
|
| 1817 |
+
{
|
| 1818 |
+
"epoch": 1.8302828618968388,
|
| 1819 |
+
"grad_norm": 0.30488741397857666,
|
| 1820 |
+
"learning_rate": 0.0004998808615019835,
|
| 1821 |
+
"loss": 0.4602,
|
| 1822 |
+
"step": 11000
|
| 1823 |
+
},
|
| 1824 |
+
{
|
| 1825 |
+
"epoch": 1.8302828618968388,
|
| 1826 |
+
"eval_accuracy": 0.7627603473540432,
|
| 1827 |
+
"eval_auc": 0.8444230596164721,
|
| 1828 |
+
"eval_f1": 0.7833894140896224,
|
| 1829 |
+
"eval_loss": 0.4582211673259735,
|
| 1830 |
+
"eval_precision": 0.720434596814201,
|
| 1831 |
+
"eval_recall": 0.8584002949628078,
|
| 1832 |
+
"eval_runtime": 3088.1236,
|
| 1833 |
+
"eval_samples_per_second": 110.714,
|
| 1834 |
+
"eval_steps_per_second": 13.839,
|
| 1835 |
+
"step": 11000
|
| 1836 |
+
},
|
| 1837 |
+
{
|
| 1838 |
+
"epoch": 1.8386023294509153,
|
| 1839 |
+
"grad_norm": 0.3203362822532654,
|
| 1840 |
+
"learning_rate": 0.0004998803198648767,
|
| 1841 |
+
"loss": 0.461,
|
| 1842 |
+
"step": 11050
|
| 1843 |
+
},
|
| 1844 |
+
{
|
| 1845 |
+
"epoch": 1.8469217970049918,
|
| 1846 |
+
"grad_norm": 0.272316038608551,
|
| 1847 |
+
"learning_rate": 0.0004998797782277699,
|
| 1848 |
+
"loss": 0.4634,
|
| 1849 |
+
"step": 11100
|
| 1850 |
+
},
|
| 1851 |
+
{
|
| 1852 |
+
"epoch": 1.8552412645590683,
|
| 1853 |
+
"grad_norm": 0.3532938063144684,
|
| 1854 |
+
"learning_rate": 0.0004998792365906631,
|
| 1855 |
+
"loss": 0.4616,
|
| 1856 |
+
"step": 11150
|
| 1857 |
+
},
|
| 1858 |
+
{
|
| 1859 |
+
"epoch": 1.8635607321131449,
|
| 1860 |
+
"grad_norm": 0.32843783497810364,
|
| 1861 |
+
"learning_rate": 0.0004998786949535562,
|
| 1862 |
+
"loss": 0.4698,
|
| 1863 |
+
"step": 11200
|
| 1864 |
+
},
|
| 1865 |
+
{
|
| 1866 |
+
"epoch": 1.8718801996672214,
|
| 1867 |
+
"grad_norm": 0.43027517199516296,
|
| 1868 |
+
"learning_rate": 0.0004998781533164494,
|
| 1869 |
+
"loss": 0.4561,
|
| 1870 |
+
"step": 11250
|
| 1871 |
+
},
|
| 1872 |
+
{
|
| 1873 |
+
"epoch": 1.880199667221298,
|
| 1874 |
+
"grad_norm": 0.7312646508216858,
|
| 1875 |
+
"learning_rate": 0.0004998776116793426,
|
| 1876 |
+
"loss": 0.4621,
|
| 1877 |
+
"step": 11300
|
| 1878 |
+
},
|
| 1879 |
+
{
|
| 1880 |
+
"epoch": 1.8885191347753745,
|
| 1881 |
+
"grad_norm": 0.33167243003845215,
|
| 1882 |
+
"learning_rate": 0.0004998770700422358,
|
| 1883 |
+
"loss": 0.4587,
|
| 1884 |
+
"step": 11350
|
| 1885 |
+
},
|
| 1886 |
+
{
|
| 1887 |
+
"epoch": 1.896838602329451,
|
| 1888 |
+
"grad_norm": 0.25895464420318604,
|
| 1889 |
+
"learning_rate": 0.000499876528405129,
|
| 1890 |
+
"loss": 0.4629,
|
| 1891 |
+
"step": 11400
|
| 1892 |
+
},
|
| 1893 |
+
{
|
| 1894 |
+
"epoch": 1.9051580698835275,
|
| 1895 |
+
"grad_norm": 0.34123238921165466,
|
| 1896 |
+
"learning_rate": 0.0004998759867680221,
|
| 1897 |
+
"loss": 0.4603,
|
| 1898 |
+
"step": 11450
|
| 1899 |
+
},
|
| 1900 |
+
{
|
| 1901 |
+
"epoch": 1.913477537437604,
|
| 1902 |
+
"grad_norm": 0.3420165479183197,
|
| 1903 |
+
"learning_rate": 0.0004998754451309153,
|
| 1904 |
+
"loss": 0.4611,
|
| 1905 |
+
"step": 11500
|
| 1906 |
+
},
|
| 1907 |
+
{
|
| 1908 |
+
"epoch": 1.913477537437604,
|
| 1909 |
+
"eval_accuracy": 0.7647872617351908,
|
| 1910 |
+
"eval_auc": 0.8470155046356656,
|
| 1911 |
+
"eval_f1": 0.7896492104554169,
|
| 1912 |
+
"eval_loss": 0.4563252329826355,
|
| 1913 |
+
"eval_precision": 0.7138904653802497,
|
| 1914 |
+
"eval_recall": 0.8833960519462278,
|
| 1915 |
+
"eval_runtime": 3116.3735,
|
| 1916 |
+
"eval_samples_per_second": 109.711,
|
| 1917 |
+
"eval_steps_per_second": 13.714,
|
| 1918 |
+
"step": 11500
|
| 1919 |
+
},
|
| 1920 |
+
{
|
| 1921 |
+
"epoch": 1.9217970049916806,
|
| 1922 |
+
"grad_norm": 0.31535664200782776,
|
| 1923 |
+
"learning_rate": 0.0004998749034938085,
|
| 1924 |
+
"loss": 0.454,
|
| 1925 |
+
"step": 11550
|
| 1926 |
+
},
|
| 1927 |
+
{
|
| 1928 |
+
"epoch": 1.9301164725457571,
|
| 1929 |
+
"grad_norm": 0.3028728663921356,
|
| 1930 |
+
"learning_rate": 0.0004998743618567017,
|
| 1931 |
+
"loss": 0.4655,
|
| 1932 |
+
"step": 11600
|
| 1933 |
+
},
|
| 1934 |
+
{
|
| 1935 |
+
"epoch": 1.9384359400998337,
|
| 1936 |
+
"grad_norm": 0.35277822613716125,
|
| 1937 |
+
"learning_rate": 0.0004998738202195949,
|
| 1938 |
+
"loss": 0.4579,
|
| 1939 |
+
"step": 11650
|
| 1940 |
+
},
|
| 1941 |
+
{
|
| 1942 |
+
"epoch": 1.9467554076539102,
|
| 1943 |
+
"grad_norm": 0.2921321988105774,
|
| 1944 |
+
"learning_rate": 0.0004998732785824881,
|
| 1945 |
+
"loss": 0.4597,
|
| 1946 |
+
"step": 11700
|
| 1947 |
+
},
|
| 1948 |
+
{
|
| 1949 |
+
"epoch": 1.9550748752079867,
|
| 1950 |
+
"grad_norm": 0.49088171124458313,
|
| 1951 |
+
"learning_rate": 0.0004998727369453812,
|
| 1952 |
+
"loss": 0.454,
|
| 1953 |
+
"step": 11750
|
| 1954 |
+
},
|
| 1955 |
+
{
|
| 1956 |
+
"epoch": 1.9633943427620633,
|
| 1957 |
+
"grad_norm": 0.37039515376091003,
|
| 1958 |
+
"learning_rate": 0.0004998721953082744,
|
| 1959 |
+
"loss": 0.463,
|
| 1960 |
+
"step": 11800
|
| 1961 |
+
},
|
| 1962 |
+
{
|
| 1963 |
+
"epoch": 1.9717138103161398,
|
| 1964 |
+
"grad_norm": 0.3478553295135498,
|
| 1965 |
+
"learning_rate": 0.0004998716536711676,
|
| 1966 |
+
"loss": 0.4596,
|
| 1967 |
+
"step": 11850
|
| 1968 |
+
},
|
| 1969 |
+
{
|
| 1970 |
+
"epoch": 1.9800332778702163,
|
| 1971 |
+
"grad_norm": 0.31678304076194763,
|
| 1972 |
+
"learning_rate": 0.0004998711120340608,
|
| 1973 |
+
"loss": 0.4627,
|
| 1974 |
+
"step": 11900
|
| 1975 |
+
},
|
| 1976 |
+
{
|
| 1977 |
+
"epoch": 1.9883527454242929,
|
| 1978 |
+
"grad_norm": 0.2272387593984604,
|
| 1979 |
+
"learning_rate": 0.000499870570396954,
|
| 1980 |
+
"loss": 0.4627,
|
| 1981 |
+
"step": 11950
|
| 1982 |
+
},
|
| 1983 |
+
{
|
| 1984 |
+
"epoch": 1.9966722129783694,
|
| 1985 |
+
"grad_norm": 0.26735177636146545,
|
| 1986 |
+
"learning_rate": 0.0004998700287598471,
|
| 1987 |
+
"loss": 0.4614,
|
| 1988 |
+
"step": 12000
|
| 1989 |
+
},
|
| 1990 |
+
{
|
| 1991 |
+
"epoch": 1.9966722129783694,
|
| 1992 |
+
"eval_accuracy": 0.7641379471715332,
|
| 1993 |
+
"eval_auc": 0.8468346428705298,
|
| 1994 |
+
"eval_f1": 0.7830218885794621,
|
| 1995 |
+
"eval_loss": 0.45656195282936096,
|
| 1996 |
+
"eval_precision": 0.72468698016794,
|
| 1997 |
+
"eval_recall": 0.8515705013782489,
|
| 1998 |
+
"eval_runtime": 3066.5927,
|
| 1999 |
+
"eval_samples_per_second": 111.491,
|
| 2000 |
+
"eval_steps_per_second": 13.937,
|
| 2001 |
+
"step": 12000
|
| 2002 |
+
},
|
| 2003 |
+
{
|
| 2004 |
+
"epoch": 2.004991680532446,
|
| 2005 |
+
"grad_norm": 0.4045884907245636,
|
| 2006 |
+
"learning_rate": 0.0004998694871227403,
|
| 2007 |
+
"loss": 0.457,
|
| 2008 |
+
"step": 12050
|
| 2009 |
+
},
|
| 2010 |
+
{
|
| 2011 |
+
"epoch": 2.0133111480865225,
|
| 2012 |
+
"grad_norm": 0.3358103036880493,
|
| 2013 |
+
"learning_rate": 0.0004998689454856335,
|
| 2014 |
+
"loss": 0.4457,
|
| 2015 |
+
"step": 12100
|
| 2016 |
+
},
|
| 2017 |
+
{
|
| 2018 |
+
"epoch": 2.021630615640599,
|
| 2019 |
+
"grad_norm": 0.4295903742313385,
|
| 2020 |
+
"learning_rate": 0.0004998684038485267,
|
| 2021 |
+
"loss": 0.4526,
|
| 2022 |
+
"step": 12150
|
| 2023 |
+
},
|
| 2024 |
+
{
|
| 2025 |
+
"epoch": 2.0299500831946755,
|
| 2026 |
+
"grad_norm": 0.30707797408103943,
|
| 2027 |
+
"learning_rate": 0.0004998678622114199,
|
| 2028 |
+
"loss": 0.4523,
|
| 2029 |
+
"step": 12200
|
| 2030 |
+
},
|
| 2031 |
+
{
|
| 2032 |
+
"epoch": 2.038269550748752,
|
| 2033 |
+
"grad_norm": 0.30385756492614746,
|
| 2034 |
+
"learning_rate": 0.000499867320574313,
|
| 2035 |
+
"loss": 0.4529,
|
| 2036 |
+
"step": 12250
|
| 2037 |
+
},
|
| 2038 |
+
{
|
| 2039 |
+
"epoch": 2.0465890183028286,
|
| 2040 |
+
"grad_norm": 0.25600412487983704,
|
| 2041 |
+
"learning_rate": 0.0004998667897699483,
|
| 2042 |
+
"loss": 0.4551,
|
| 2043 |
+
"step": 12300
|
| 2044 |
+
},
|
| 2045 |
+
{
|
| 2046 |
+
"epoch": 2.054908485856905,
|
| 2047 |
+
"grad_norm": 0.4305065870285034,
|
| 2048 |
+
"learning_rate": 0.0004998662481328415,
|
| 2049 |
+
"loss": 0.4545,
|
| 2050 |
+
"step": 12350
|
| 2051 |
+
},
|
| 2052 |
+
{
|
| 2053 |
+
"epoch": 2.0632279534109816,
|
| 2054 |
+
"grad_norm": 0.49212226271629333,
|
| 2055 |
+
"learning_rate": 0.0004998657064957347,
|
| 2056 |
+
"loss": 0.4561,
|
| 2057 |
+
"step": 12400
|
| 2058 |
+
},
|
| 2059 |
+
{
|
| 2060 |
+
"epoch": 2.071547420965058,
|
| 2061 |
+
"grad_norm": 0.2785611152648926,
|
| 2062 |
+
"learning_rate": 0.0004998651648586279,
|
| 2063 |
+
"loss": 0.457,
|
| 2064 |
+
"step": 12450
|
| 2065 |
+
},
|
| 2066 |
+
{
|
| 2067 |
+
"epoch": 2.0798668885191347,
|
| 2068 |
+
"grad_norm": 0.37156569957733154,
|
| 2069 |
+
"learning_rate": 0.0004998646232215211,
|
| 2070 |
+
"loss": 0.4543,
|
| 2071 |
+
"step": 12500
|
| 2072 |
+
},
|
| 2073 |
+
{
|
| 2074 |
+
"epoch": 2.0798668885191347,
|
| 2075 |
+
"eval_accuracy": 0.7628480925653482,
|
| 2076 |
+
"eval_auc": 0.847242187715394,
|
| 2077 |
+
"eval_f1": 0.791982226053404,
|
| 2078 |
+
"eval_loss": 0.45966818928718567,
|
| 2079 |
+
"eval_precision": 0.7050727451293881,
|
| 2080 |
+
"eval_recall": 0.9033294512170142,
|
| 2081 |
+
"eval_runtime": 3110.1977,
|
| 2082 |
+
"eval_samples_per_second": 109.928,
|
| 2083 |
+
"eval_steps_per_second": 13.741,
|
| 2084 |
+
"step": 12500
|
| 2085 |
+
},
|
| 2086 |
+
{
|
| 2087 |
+
"epoch": 2.0881863560732112,
|
| 2088 |
+
"grad_norm": 0.3126935660839081,
|
| 2089 |
+
"learning_rate": 0.0004998640815844142,
|
| 2090 |
+
"loss": 0.4533,
|
| 2091 |
+
"step": 12550
|
| 2092 |
+
},
|
| 2093 |
+
{
|
| 2094 |
+
"epoch": 2.0965058236272878,
|
| 2095 |
+
"grad_norm": 0.2464996725320816,
|
| 2096 |
+
"learning_rate": 0.0004998635399473074,
|
| 2097 |
+
"loss": 0.4572,
|
| 2098 |
+
"step": 12600
|
| 2099 |
+
},
|
| 2100 |
+
{
|
| 2101 |
+
"epoch": 2.1048252911813643,
|
| 2102 |
+
"grad_norm": 0.5269837379455566,
|
| 2103 |
+
"learning_rate": 0.0004998629983102006,
|
| 2104 |
+
"loss": 0.4573,
|
| 2105 |
+
"step": 12650
|
| 2106 |
+
},
|
| 2107 |
+
{
|
| 2108 |
+
"epoch": 2.113144758735441,
|
| 2109 |
+
"grad_norm": 0.3495631217956543,
|
| 2110 |
+
"learning_rate": 0.0004998624566730938,
|
| 2111 |
+
"loss": 0.4509,
|
| 2112 |
+
"step": 12700
|
| 2113 |
+
},
|
| 2114 |
+
{
|
| 2115 |
+
"epoch": 2.1214642262895174,
|
| 2116 |
+
"grad_norm": 0.24060170352458954,
|
| 2117 |
+
"learning_rate": 0.000499861915035987,
|
| 2118 |
+
"loss": 0.4542,
|
| 2119 |
+
"step": 12750
|
| 2120 |
+
},
|
| 2121 |
+
{
|
| 2122 |
+
"epoch": 2.129783693843594,
|
| 2123 |
+
"grad_norm": 0.43895021080970764,
|
| 2124 |
+
"learning_rate": 0.0004998613733988801,
|
| 2125 |
+
"loss": 0.4528,
|
| 2126 |
+
"step": 12800
|
| 2127 |
+
},
|
| 2128 |
+
{
|
| 2129 |
+
"epoch": 2.1381031613976704,
|
| 2130 |
+
"grad_norm": 0.30949124693870544,
|
| 2131 |
+
"learning_rate": 0.0004998608317617733,
|
| 2132 |
+
"loss": 0.4481,
|
| 2133 |
+
"step": 12850
|
| 2134 |
+
},
|
| 2135 |
+
{
|
| 2136 |
+
"epoch": 2.146422628951747,
|
| 2137 |
+
"grad_norm": 0.3358418345451355,
|
| 2138 |
+
"learning_rate": 0.0004998602901246665,
|
| 2139 |
+
"loss": 0.4504,
|
| 2140 |
+
"step": 12900
|
| 2141 |
+
},
|
| 2142 |
+
{
|
| 2143 |
+
"epoch": 2.1547420965058235,
|
| 2144 |
+
"grad_norm": 0.40767422318458557,
|
| 2145 |
+
"learning_rate": 0.0004998597484875597,
|
| 2146 |
+
"loss": 0.4583,
|
| 2147 |
+
"step": 12950
|
| 2148 |
+
},
|
| 2149 |
+
{
|
| 2150 |
+
"epoch": 2.1630615640599,
|
| 2151 |
+
"grad_norm": 0.3742935061454773,
|
| 2152 |
+
"learning_rate": 0.0004998592068504528,
|
| 2153 |
+
"loss": 0.4574,
|
| 2154 |
+
"step": 13000
|
| 2155 |
+
},
|
| 2156 |
+
{
|
| 2157 |
+
"epoch": 2.1630615640599,
|
| 2158 |
+
"eval_accuracy": 0.7631610504856697,
|
| 2159 |
+
"eval_auc": 0.8489359071807063,
|
| 2160 |
+
"eval_f1": 0.794699065212045,
|
| 2161 |
+
"eval_loss": 0.45762190222740173,
|
| 2162 |
+
"eval_precision": 0.7010583667334669,
|
| 2163 |
+
"eval_recall": 0.9172114309792883,
|
| 2164 |
+
"eval_runtime": 3073.781,
|
| 2165 |
+
"eval_samples_per_second": 111.231,
|
| 2166 |
+
"eval_steps_per_second": 13.904,
|
| 2167 |
+
"step": 13000
|
| 2168 |
+
},
|
| 2169 |
+
{
|
| 2170 |
+
"epoch": 2.1713810316139766,
|
| 2171 |
+
"grad_norm": 0.3705851137638092,
|
| 2172 |
+
"learning_rate": 0.000499858665213346,
|
| 2173 |
+
"loss": 0.4513,
|
| 2174 |
+
"step": 13050
|
| 2175 |
+
},
|
| 2176 |
+
{
|
| 2177 |
+
"epoch": 2.179700499168053,
|
| 2178 |
+
"grad_norm": 0.222339928150177,
|
| 2179 |
+
"learning_rate": 0.0004998581235762391,
|
| 2180 |
+
"loss": 0.4536,
|
| 2181 |
+
"step": 13100
|
| 2182 |
+
},
|
| 2183 |
+
{
|
| 2184 |
+
"epoch": 2.1880199667221296,
|
| 2185 |
+
"grad_norm": 0.3179910182952881,
|
| 2186 |
+
"learning_rate": 0.0004998575819391323,
|
| 2187 |
+
"loss": 0.4527,
|
| 2188 |
+
"step": 13150
|
| 2189 |
+
},
|
| 2190 |
+
{
|
| 2191 |
+
"epoch": 2.196339434276206,
|
| 2192 |
+
"grad_norm": 0.43729254603385925,
|
| 2193 |
+
"learning_rate": 0.0004998570403020255,
|
| 2194 |
+
"loss": 0.4521,
|
| 2195 |
+
"step": 13200
|
| 2196 |
+
},
|
| 2197 |
+
{
|
| 2198 |
+
"epoch": 2.2046589018302827,
|
| 2199 |
+
"grad_norm": 0.31573063135147095,
|
| 2200 |
+
"learning_rate": 0.0004998564986649187,
|
| 2201 |
+
"loss": 0.4573,
|
| 2202 |
+
"step": 13250
|
| 2203 |
+
},
|
| 2204 |
+
{
|
| 2205 |
+
"epoch": 2.212978369384359,
|
| 2206 |
+
"grad_norm": 0.34133201837539673,
|
| 2207 |
+
"learning_rate": 0.0004998559570278119,
|
| 2208 |
+
"loss": 0.4547,
|
| 2209 |
+
"step": 13300
|
| 2210 |
+
},
|
| 2211 |
+
{
|
| 2212 |
+
"epoch": 2.2212978369384357,
|
| 2213 |
+
"grad_norm": 0.32229501008987427,
|
| 2214 |
+
"learning_rate": 0.000499855415390705,
|
| 2215 |
+
"loss": 0.4552,
|
| 2216 |
+
"step": 13350
|
| 2217 |
+
},
|
| 2218 |
+
{
|
| 2219 |
+
"epoch": 2.2296173044925123,
|
| 2220 |
+
"grad_norm": 0.25182995200157166,
|
| 2221 |
+
"learning_rate": 0.0004998548737535982,
|
| 2222 |
+
"loss": 0.4519,
|
| 2223 |
+
"step": 13400
|
| 2224 |
+
},
|
| 2225 |
+
{
|
| 2226 |
+
"epoch": 2.237936772046589,
|
| 2227 |
+
"grad_norm": 0.38632023334503174,
|
| 2228 |
+
"learning_rate": 0.0004998543321164914,
|
| 2229 |
+
"loss": 0.4549,
|
| 2230 |
+
"step": 13450
|
| 2231 |
+
},
|
| 2232 |
+
{
|
| 2233 |
+
"epoch": 2.2462562396006653,
|
| 2234 |
+
"grad_norm": 0.4629928469657898,
|
| 2235 |
+
"learning_rate": 0.0004998537904793846,
|
| 2236 |
+
"loss": 0.4532,
|
| 2237 |
+
"step": 13500
|
| 2238 |
+
},
|
| 2239 |
+
{
|
| 2240 |
+
"epoch": 2.2462562396006653,
|
| 2241 |
+
"eval_accuracy": 0.7667761531914395,
|
| 2242 |
+
"eval_auc": 0.8491075200735866,
|
| 2243 |
+
"eval_f1": 0.7892359376528085,
|
| 2244 |
+
"eval_loss": 0.4522622525691986,
|
| 2245 |
+
"eval_precision": 0.7196284656615124,
|
| 2246 |
+
"eval_recall": 0.8737512363272448,
|
| 2247 |
+
"eval_runtime": 3076.782,
|
| 2248 |
+
"eval_samples_per_second": 111.122,
|
| 2249 |
+
"eval_steps_per_second": 13.89,
|
| 2250 |
+
"step": 13500
|
| 2251 |
+
},
|
| 2252 |
+
{
|
| 2253 |
+
"epoch": 2.254575707154742,
|
| 2254 |
+
"grad_norm": 0.3204486668109894,
|
| 2255 |
+
"learning_rate": 0.0004998532488422778,
|
| 2256 |
+
"loss": 0.4549,
|
| 2257 |
+
"step": 13550
|
| 2258 |
+
},
|
| 2259 |
+
{
|
| 2260 |
+
"epoch": 2.2628951747088184,
|
| 2261 |
+
"grad_norm": 0.2668420076370239,
|
| 2262 |
+
"learning_rate": 0.0004998527072051709,
|
| 2263 |
+
"loss": 0.4498,
|
| 2264 |
+
"step": 13600
|
| 2265 |
+
},
|
| 2266 |
+
{
|
| 2267 |
+
"epoch": 2.271214642262895,
|
| 2268 |
+
"grad_norm": 0.34950193762779236,
|
| 2269 |
+
"learning_rate": 0.0004998521655680641,
|
| 2270 |
+
"loss": 0.4492,
|
| 2271 |
+
"step": 13650
|
| 2272 |
+
},
|
| 2273 |
+
{
|
| 2274 |
+
"epoch": 2.2795341098169715,
|
| 2275 |
+
"grad_norm": 0.39468878507614136,
|
| 2276 |
+
"learning_rate": 0.0004998516239309573,
|
| 2277 |
+
"loss": 0.4572,
|
| 2278 |
+
"step": 13700
|
| 2279 |
+
},
|
| 2280 |
+
{
|
| 2281 |
+
"epoch": 2.2878535773710484,
|
| 2282 |
+
"grad_norm": 0.40462568402290344,
|
| 2283 |
+
"learning_rate": 0.0004998510822938505,
|
| 2284 |
+
"loss": 0.4521,
|
| 2285 |
+
"step": 13750
|
| 2286 |
+
},
|
| 2287 |
+
{
|
| 2288 |
+
"epoch": 2.296173044925125,
|
| 2289 |
+
"grad_norm": 0.3331548571586609,
|
| 2290 |
+
"learning_rate": 0.0004998505406567437,
|
| 2291 |
+
"loss": 0.4473,
|
| 2292 |
+
"step": 13800
|
| 2293 |
+
},
|
| 2294 |
+
{
|
| 2295 |
+
"epoch": 2.3044925124792015,
|
| 2296 |
+
"grad_norm": 0.2660551965236664,
|
| 2297 |
+
"learning_rate": 0.0004998499990196369,
|
| 2298 |
+
"loss": 0.4534,
|
| 2299 |
+
"step": 13850
|
| 2300 |
+
},
|
| 2301 |
+
{
|
| 2302 |
+
"epoch": 2.312811980033278,
|
| 2303 |
+
"grad_norm": 0.311027854681015,
|
| 2304 |
+
"learning_rate": 0.00049984945738253,
|
| 2305 |
+
"loss": 0.45,
|
| 2306 |
+
"step": 13900
|
| 2307 |
+
},
|
| 2308 |
+
{
|
| 2309 |
+
"epoch": 2.3211314475873546,
|
| 2310 |
+
"grad_norm": 0.5009548664093018,
|
| 2311 |
+
"learning_rate": 0.0004998489157454232,
|
| 2312 |
+
"loss": 0.4558,
|
| 2313 |
+
"step": 13950
|
| 2314 |
+
},
|
| 2315 |
+
{
|
| 2316 |
+
"epoch": 2.329450915141431,
|
| 2317 |
+
"grad_norm": 0.28578829765319824,
|
| 2318 |
+
"learning_rate": 0.0004998483741083164,
|
| 2319 |
+
"loss": 0.4472,
|
| 2320 |
+
"step": 14000
|
| 2321 |
+
},
|
| 2322 |
+
{
|
| 2323 |
+
"epoch": 2.329450915141431,
|
| 2324 |
+
"eval_accuracy": 0.7664251723462192,
|
| 2325 |
+
"eval_auc": 0.8494449173929353,
|
| 2326 |
+
"eval_f1": 0.7848782550838166,
|
| 2327 |
+
"eval_loss": 0.452217161655426,
|
| 2328 |
+
"eval_precision": 0.7271184579602511,
|
| 2329 |
+
"eval_recall": 0.8526063826674236,
|
| 2330 |
+
"eval_runtime": 3063.8475,
|
| 2331 |
+
"eval_samples_per_second": 111.591,
|
| 2332 |
+
"eval_steps_per_second": 13.949,
|
| 2333 |
+
"step": 14000
|
| 2334 |
+
},
|
| 2335 |
+
{
|
| 2336 |
+
"epoch": 2.3377703826955076,
|
| 2337 |
+
"grad_norm": 0.351082444190979,
|
| 2338 |
+
"learning_rate": 0.0004998478324712096,
|
| 2339 |
+
"loss": 0.4548,
|
| 2340 |
+
"step": 14050
|
| 2341 |
+
},
|
| 2342 |
+
{
|
| 2343 |
+
"epoch": 2.346089850249584,
|
| 2344 |
+
"grad_norm": 0.35973915457725525,
|
| 2345 |
+
"learning_rate": 0.0004998472908341028,
|
| 2346 |
+
"loss": 0.4514,
|
| 2347 |
+
"step": 14100
|
| 2348 |
+
},
|
| 2349 |
+
{
|
| 2350 |
+
"epoch": 2.3544093178036607,
|
| 2351 |
+
"grad_norm": 0.4456665515899658,
|
| 2352 |
+
"learning_rate": 0.0004998467491969959,
|
| 2353 |
+
"loss": 0.4553,
|
| 2354 |
+
"step": 14150
|
| 2355 |
+
},
|
| 2356 |
+
{
|
| 2357 |
+
"epoch": 2.3627287853577372,
|
| 2358 |
+
"grad_norm": 0.34595686197280884,
|
| 2359 |
+
"learning_rate": 0.0004998462075598891,
|
| 2360 |
+
"loss": 0.4559,
|
| 2361 |
+
"step": 14200
|
| 2362 |
+
},
|
| 2363 |
+
{
|
| 2364 |
+
"epoch": 2.3710482529118138,
|
| 2365 |
+
"grad_norm": 0.3657195270061493,
|
| 2366 |
+
"learning_rate": 0.0004998456659227823,
|
| 2367 |
+
"loss": 0.4499,
|
| 2368 |
+
"step": 14250
|
| 2369 |
+
},
|
| 2370 |
+
{
|
| 2371 |
+
"epoch": 2.3793677204658903,
|
| 2372 |
+
"grad_norm": 0.398843377828598,
|
| 2373 |
+
"learning_rate": 0.0004998451242856755,
|
| 2374 |
+
"loss": 0.4523,
|
| 2375 |
+
"step": 14300
|
| 2376 |
+
},
|
| 2377 |
+
{
|
| 2378 |
+
"epoch": 2.387687188019967,
|
| 2379 |
+
"grad_norm": 0.44224244356155396,
|
| 2380 |
+
"learning_rate": 0.0004998445826485687,
|
| 2381 |
+
"loss": 0.4479,
|
| 2382 |
+
"step": 14350
|
| 2383 |
+
},
|
| 2384 |
+
{
|
| 2385 |
+
"epoch": 2.3960066555740434,
|
| 2386 |
+
"grad_norm": 0.4334554374217987,
|
| 2387 |
+
"learning_rate": 0.0004998440410114619,
|
| 2388 |
+
"loss": 0.452,
|
| 2389 |
+
"step": 14400
|
| 2390 |
+
},
|
| 2391 |
+
{
|
| 2392 |
+
"epoch": 2.40432612312812,
|
| 2393 |
+
"grad_norm": 0.36450016498565674,
|
| 2394 |
+
"learning_rate": 0.0004998434993743549,
|
| 2395 |
+
"loss": 0.4517,
|
| 2396 |
+
"step": 14450
|
| 2397 |
+
},
|
| 2398 |
+
{
|
| 2399 |
+
"epoch": 2.4126455906821964,
|
| 2400 |
+
"grad_norm": 0.37175169587135315,
|
| 2401 |
+
"learning_rate": 0.0004998429577372481,
|
| 2402 |
+
"loss": 0.4505,
|
| 2403 |
+
"step": 14500
|
| 2404 |
+
},
|
| 2405 |
+
{
|
| 2406 |
+
"epoch": 2.4126455906821964,
|
| 2407 |
+
"eval_accuracy": 0.7648048107774518,
|
| 2408 |
+
"eval_auc": 0.8497144763208656,
|
| 2409 |
+
"eval_f1": 0.7768245941722891,
|
| 2410 |
+
"eval_loss": 0.45364442467689514,
|
| 2411 |
+
"eval_precision": 0.7387407360486477,
|
| 2412 |
+
"eval_recall": 0.8190485108474913,
|
| 2413 |
+
"eval_runtime": 3069.7075,
|
| 2414 |
+
"eval_samples_per_second": 111.378,
|
| 2415 |
+
"eval_steps_per_second": 13.922,
|
| 2416 |
+
"step": 14500
|
| 2417 |
+
},
|
| 2418 |
+
{
|
| 2419 |
+
"epoch": 2.420965058236273,
|
| 2420 |
+
"grad_norm": 0.4115402102470398,
|
| 2421 |
+
"learning_rate": 0.0004998424161001413,
|
| 2422 |
+
"loss": 0.4522,
|
| 2423 |
+
"step": 14550
|
| 2424 |
+
},
|
| 2425 |
+
{
|
| 2426 |
+
"epoch": 2.4292845257903495,
|
| 2427 |
+
"grad_norm": 0.33581915497779846,
|
| 2428 |
+
"learning_rate": 0.0004998418744630345,
|
| 2429 |
+
"loss": 0.4546,
|
| 2430 |
+
"step": 14600
|
| 2431 |
+
},
|
| 2432 |
+
{
|
| 2433 |
+
"epoch": 2.437603993344426,
|
| 2434 |
+
"grad_norm": 0.26651909947395325,
|
| 2435 |
+
"learning_rate": 0.0004998413328259277,
|
| 2436 |
+
"loss": 0.4527,
|
| 2437 |
+
"step": 14650
|
| 2438 |
+
},
|
| 2439 |
+
{
|
| 2440 |
+
"epoch": 2.4459234608985025,
|
| 2441 |
+
"grad_norm": 0.3490288555622101,
|
| 2442 |
+
"learning_rate": 0.0004998407911888208,
|
| 2443 |
+
"loss": 0.4479,
|
| 2444 |
+
"step": 14700
|
| 2445 |
+
},
|
| 2446 |
+
{
|
| 2447 |
+
"epoch": 2.454242928452579,
|
| 2448 |
+
"grad_norm": 0.3200080990791321,
|
| 2449 |
+
"learning_rate": 0.000499840249551714,
|
| 2450 |
+
"loss": 0.4471,
|
| 2451 |
+
"step": 14750
|
| 2452 |
+
},
|
| 2453 |
+
{
|
| 2454 |
+
"epoch": 2.4625623960066556,
|
| 2455 |
+
"grad_norm": 0.31173649430274963,
|
| 2456 |
+
"learning_rate": 0.0004998397079146072,
|
| 2457 |
+
"loss": 0.4488,
|
| 2458 |
+
"step": 14800
|
| 2459 |
+
},
|
| 2460 |
+
{
|
| 2461 |
+
"epoch": 2.470881863560732,
|
| 2462 |
+
"grad_norm": 0.431302934885025,
|
| 2463 |
+
"learning_rate": 0.0004998391662775004,
|
| 2464 |
+
"loss": 0.4509,
|
| 2465 |
+
"step": 14850
|
| 2466 |
+
},
|
| 2467 |
+
{
|
| 2468 |
+
"epoch": 2.4792013311148087,
|
| 2469 |
+
"grad_norm": 0.37330421805381775,
|
| 2470 |
+
"learning_rate": 0.0004998386246403936,
|
| 2471 |
+
"loss": 0.4537,
|
| 2472 |
+
"step": 14900
|
| 2473 |
+
},
|
| 2474 |
+
{
|
| 2475 |
+
"epoch": 2.487520798668885,
|
| 2476 |
+
"grad_norm": 0.2857615649700165,
|
| 2477 |
+
"learning_rate": 0.0004998380830032867,
|
| 2478 |
+
"loss": 0.4469,
|
| 2479 |
+
"step": 14950
|
| 2480 |
+
},
|
| 2481 |
+
{
|
| 2482 |
+
"epoch": 2.4958402662229617,
|
| 2483 |
+
"grad_norm": 0.3119502365589142,
|
| 2484 |
+
"learning_rate": 0.0004998375413661799,
|
| 2485 |
+
"loss": 0.4506,
|
| 2486 |
+
"step": 15000
|
| 2487 |
+
},
|
| 2488 |
+
{
|
| 2489 |
+
"epoch": 2.4958402662229617,
|
| 2490 |
+
"eval_accuracy": 0.7662789303273774,
|
| 2491 |
+
"eval_auc": 0.8515752861892085,
|
| 2492 |
+
"eval_f1": 0.7784029616893832,
|
| 2493 |
+
"eval_loss": 0.45170241594314575,
|
| 2494 |
+
"eval_precision": 0.7397014799510899,
|
| 2495 |
+
"eval_recall": 0.821377780638969,
|
| 2496 |
+
"eval_runtime": 3072.2397,
|
| 2497 |
+
"eval_samples_per_second": 111.287,
|
| 2498 |
+
"eval_steps_per_second": 13.911,
|
| 2499 |
+
"step": 15000
|
| 2500 |
+
},
|
| 2501 |
+
{
|
| 2502 |
+
"epoch": 2.5041597337770383,
|
| 2503 |
+
"grad_norm": 0.31348904967308044,
|
| 2504 |
+
"learning_rate": 0.0004998369997290731,
|
| 2505 |
+
"loss": 0.4502,
|
| 2506 |
+
"step": 15050
|
| 2507 |
+
},
|
| 2508 |
+
{
|
| 2509 |
+
"epoch": 2.512479201331115,
|
| 2510 |
+
"grad_norm": 0.280769020318985,
|
| 2511 |
+
"learning_rate": 0.0004998364580919663,
|
| 2512 |
+
"loss": 0.4507,
|
| 2513 |
+
"step": 15100
|
| 2514 |
+
},
|
| 2515 |
+
{
|
| 2516 |
+
"epoch": 2.5207986688851913,
|
| 2517 |
+
"grad_norm": 0.3579796850681305,
|
| 2518 |
+
"learning_rate": 0.0004998359164548595,
|
| 2519 |
+
"loss": 0.45,
|
| 2520 |
+
"step": 15150
|
| 2521 |
+
},
|
| 2522 |
+
{
|
| 2523 |
+
"epoch": 2.529118136439268,
|
| 2524 |
+
"grad_norm": 0.4033232629299164,
|
| 2525 |
+
"learning_rate": 0.0004998353748177527,
|
| 2526 |
+
"loss": 0.4506,
|
| 2527 |
+
"step": 15200
|
| 2528 |
+
},
|
| 2529 |
+
{
|
| 2530 |
+
"epoch": 2.5374376039933444,
|
| 2531 |
+
"grad_norm": 0.3025188148021698,
|
| 2532 |
+
"learning_rate": 0.0004998348331806458,
|
| 2533 |
+
"loss": 0.4515,
|
| 2534 |
+
"step": 15250
|
| 2535 |
+
},
|
| 2536 |
+
{
|
| 2537 |
+
"epoch": 2.545757071547421,
|
| 2538 |
+
"grad_norm": 0.28588080406188965,
|
| 2539 |
+
"learning_rate": 0.0004998342915435391,
|
| 2540 |
+
"loss": 0.4502,
|
| 2541 |
+
"step": 15300
|
| 2542 |
+
},
|
| 2543 |
+
{
|
| 2544 |
+
"epoch": 2.5540765391014975,
|
| 2545 |
+
"grad_norm": 0.36141297221183777,
|
| 2546 |
+
"learning_rate": 0.0004998337499064322,
|
| 2547 |
+
"loss": 0.446,
|
| 2548 |
+
"step": 15350
|
| 2549 |
+
},
|
| 2550 |
+
{
|
| 2551 |
+
"epoch": 2.562396006655574,
|
| 2552 |
+
"grad_norm": 0.5286752581596375,
|
| 2553 |
+
"learning_rate": 0.0004998332082693254,
|
| 2554 |
+
"loss": 0.4511,
|
| 2555 |
+
"step": 15400
|
| 2556 |
+
},
|
| 2557 |
+
{
|
| 2558 |
+
"epoch": 2.5707154742096505,
|
| 2559 |
+
"grad_norm": 0.3852572441101074,
|
| 2560 |
+
"learning_rate": 0.0004998326666322186,
|
| 2561 |
+
"loss": 0.455,
|
| 2562 |
+
"step": 15450
|
| 2563 |
+
},
|
| 2564 |
+
{
|
| 2565 |
+
"epoch": 2.579034941763727,
|
| 2566 |
+
"grad_norm": 0.3271165192127228,
|
| 2567 |
+
"learning_rate": 0.0004998321249951117,
|
| 2568 |
+
"loss": 0.4562,
|
| 2569 |
+
"step": 15500
|
| 2570 |
+
},
|
| 2571 |
+
{
|
| 2572 |
+
"epoch": 2.579034941763727,
|
| 2573 |
+
"eval_accuracy": 0.7698033629814652,
|
| 2574 |
+
"eval_auc": 0.8525774850851346,
|
| 2575 |
+
"eval_f1": 0.7916979853693137,
|
| 2576 |
+
"eval_loss": 0.447857141494751,
|
| 2577 |
+
"eval_precision": 0.7226562688737818,
|
| 2578 |
+
"eval_recall": 0.875325541789324,
|
| 2579 |
+
"eval_runtime": 3063.8515,
|
| 2580 |
+
"eval_samples_per_second": 111.591,
|
| 2581 |
+
"eval_steps_per_second": 13.949,
|
| 2582 |
+
"step": 15500
|
| 2583 |
+
},
|
| 2584 |
+
{
|
| 2585 |
+
"epoch": 2.5873544093178036,
|
| 2586 |
+
"grad_norm": 0.29755738377571106,
|
| 2587 |
+
"learning_rate": 0.000499831583358005,
|
| 2588 |
+
"loss": 0.4446,
|
| 2589 |
+
"step": 15550
|
| 2590 |
+
},
|
| 2591 |
+
{
|
| 2592 |
+
"epoch": 2.59567387687188,
|
| 2593 |
+
"grad_norm": 0.3373735547065735,
|
| 2594 |
+
"learning_rate": 0.0004998310417208981,
|
| 2595 |
+
"loss": 0.4515,
|
| 2596 |
+
"step": 15600
|
| 2597 |
+
},
|
| 2598 |
+
{
|
| 2599 |
+
"epoch": 2.6039933444259566,
|
| 2600 |
+
"grad_norm": 0.33765482902526855,
|
| 2601 |
+
"learning_rate": 0.0004998305000837913,
|
| 2602 |
+
"loss": 0.4488,
|
| 2603 |
+
"step": 15650
|
| 2604 |
+
},
|
| 2605 |
+
{
|
| 2606 |
+
"epoch": 2.612312811980033,
|
| 2607 |
+
"grad_norm": 0.4411982595920563,
|
| 2608 |
+
"learning_rate": 0.0004998299584466845,
|
| 2609 |
+
"loss": 0.4498,
|
| 2610 |
+
"step": 15700
|
| 2611 |
+
},
|
| 2612 |
+
{
|
| 2613 |
+
"epoch": 2.6206322795341097,
|
| 2614 |
+
"grad_norm": 0.3372790217399597,
|
| 2615 |
+
"learning_rate": 0.0004998294168095777,
|
| 2616 |
+
"loss": 0.4496,
|
| 2617 |
+
"step": 15750
|
| 2618 |
+
},
|
| 2619 |
+
{
|
| 2620 |
+
"epoch": 2.6289517470881862,
|
| 2621 |
+
"grad_norm": 0.2755867540836334,
|
| 2622 |
+
"learning_rate": 0.0004998288751724709,
|
| 2623 |
+
"loss": 0.4504,
|
| 2624 |
+
"step": 15800
|
| 2625 |
+
},
|
| 2626 |
+
{
|
| 2627 |
+
"epoch": 2.6372712146422628,
|
| 2628 |
+
"grad_norm": 0.33905473351478577,
|
| 2629 |
+
"learning_rate": 0.0004998283335353639,
|
| 2630 |
+
"loss": 0.4549,
|
| 2631 |
+
"step": 15850
|
| 2632 |
+
},
|
| 2633 |
+
{
|
| 2634 |
+
"epoch": 2.6455906821963393,
|
| 2635 |
+
"grad_norm": 0.38283759355545044,
|
| 2636 |
+
"learning_rate": 0.0004998277918982571,
|
| 2637 |
+
"loss": 0.445,
|
| 2638 |
+
"step": 15900
|
| 2639 |
+
},
|
| 2640 |
+
{
|
| 2641 |
+
"epoch": 2.653910149750416,
|
| 2642 |
+
"grad_norm": 0.3542182743549347,
|
| 2643 |
+
"learning_rate": 0.0004998272502611503,
|
| 2644 |
+
"loss": 0.448,
|
| 2645 |
+
"step": 15950
|
| 2646 |
+
},
|
| 2647 |
+
{
|
| 2648 |
+
"epoch": 2.6622296173044924,
|
| 2649 |
+
"grad_norm": 0.42483657598495483,
|
| 2650 |
+
"learning_rate": 0.0004998267086240435,
|
| 2651 |
+
"loss": 0.4434,
|
| 2652 |
+
"step": 16000
|
| 2653 |
+
},
|
| 2654 |
+
{
|
| 2655 |
+
"epoch": 2.6622296173044924,
|
| 2656 |
+
"eval_accuracy": 0.769505029263028,
|
| 2657 |
+
"eval_auc": 0.8523741424932588,
|
| 2658 |
+
"eval_f1": 0.7897149627226103,
|
| 2659 |
+
"eval_loss": 0.4486808776855469,
|
| 2660 |
+
"eval_precision": 0.7257674518978464,
|
| 2661 |
+
"eval_recall": 0.8660201674967373,
|
| 2662 |
+
"eval_runtime": 3076.2646,
|
| 2663 |
+
"eval_samples_per_second": 111.141,
|
| 2664 |
+
"eval_steps_per_second": 13.893,
|
| 2665 |
+
"step": 16000
|
| 2666 |
+
},
|
| 2667 |
+
{
|
| 2668 |
+
"epoch": 2.670549084858569,
|
| 2669 |
+
"grad_norm": 0.2930859327316284,
|
| 2670 |
+
"learning_rate": 0.0004998261669869367,
|
| 2671 |
+
"loss": 0.4467,
|
| 2672 |
+
"step": 16050
|
| 2673 |
+
},
|
| 2674 |
+
{
|
| 2675 |
+
"epoch": 2.6788685524126454,
|
| 2676 |
+
"grad_norm": 0.4802510142326355,
|
| 2677 |
+
"learning_rate": 0.0004998256253498299,
|
| 2678 |
+
"loss": 0.4472,
|
| 2679 |
+
"step": 16100
|
| 2680 |
+
},
|
| 2681 |
+
{
|
| 2682 |
+
"epoch": 2.687188019966722,
|
| 2683 |
+
"grad_norm": 0.30784839391708374,
|
| 2684 |
+
"learning_rate": 0.000499825083712723,
|
| 2685 |
+
"loss": 0.4489,
|
| 2686 |
+
"step": 16150
|
| 2687 |
+
},
|
| 2688 |
+
{
|
| 2689 |
+
"epoch": 2.695507487520799,
|
| 2690 |
+
"grad_norm": 0.27913177013397217,
|
| 2691 |
+
"learning_rate": 0.0004998245420756162,
|
| 2692 |
+
"loss": 0.451,
|
| 2693 |
+
"step": 16200
|
| 2694 |
+
},
|
| 2695 |
+
{
|
| 2696 |
+
"epoch": 2.7038269550748755,
|
| 2697 |
+
"grad_norm": 0.3060939311981201,
|
| 2698 |
+
"learning_rate": 0.0004998240004385094,
|
| 2699 |
+
"loss": 0.446,
|
| 2700 |
+
"step": 16250
|
| 2701 |
+
},
|
| 2702 |
+
{
|
| 2703 |
+
"epoch": 2.712146422628952,
|
| 2704 |
+
"grad_norm": 0.3916643261909485,
|
| 2705 |
+
"learning_rate": 0.0004998234696341447,
|
| 2706 |
+
"loss": 0.449,
|
| 2707 |
+
"step": 16300
|
| 2708 |
+
},
|
| 2709 |
+
{
|
| 2710 |
+
"epoch": 2.7204658901830285,
|
| 2711 |
+
"grad_norm": 0.3149168789386749,
|
| 2712 |
+
"learning_rate": 0.0004998229279970379,
|
| 2713 |
+
"loss": 0.4484,
|
| 2714 |
+
"step": 16350
|
| 2715 |
+
},
|
| 2716 |
+
{
|
| 2717 |
+
"epoch": 2.728785357737105,
|
| 2718 |
+
"grad_norm": 0.3204551339149475,
|
| 2719 |
+
"learning_rate": 0.000499822386359931,
|
| 2720 |
+
"loss": 0.4467,
|
| 2721 |
+
"step": 16400
|
| 2722 |
+
},
|
| 2723 |
+
{
|
| 2724 |
+
"epoch": 2.7371048252911816,
|
| 2725 |
+
"grad_norm": 0.4137204885482788,
|
| 2726 |
+
"learning_rate": 0.0004998218447228243,
|
| 2727 |
+
"loss": 0.4503,
|
| 2728 |
+
"step": 16450
|
| 2729 |
+
},
|
| 2730 |
+
{
|
| 2731 |
+
"epoch": 2.745424292845258,
|
| 2732 |
+
"grad_norm": 0.34219491481781006,
|
| 2733 |
+
"learning_rate": 0.0004998213030857175,
|
| 2734 |
+
"loss": 0.4482,
|
| 2735 |
+
"step": 16500
|
| 2736 |
+
},
|
| 2737 |
+
{
|
| 2738 |
+
"epoch": 2.745424292845258,
|
| 2739 |
+
"eval_accuracy": 0.7704673017470072,
|
| 2740 |
+
"eval_auc": 0.8527454649367189,
|
| 2741 |
+
"eval_f1": 0.7930540722281555,
|
| 2742 |
+
"eval_loss": 0.4480786919593811,
|
| 2743 |
+
"eval_precision": 0.7217273189790061,
|
| 2744 |
+
"eval_recall": 0.8800250484289134,
|
| 2745 |
+
"eval_runtime": 3081.5516,
|
| 2746 |
+
"eval_samples_per_second": 110.95,
|
| 2747 |
+
"eval_steps_per_second": 13.869,
|
| 2748 |
+
"step": 16500
|
| 2749 |
+
},
|
| 2750 |
+
{
|
| 2751 |
+
"epoch": 2.7537437603993347,
|
| 2752 |
+
"grad_norm": 0.38494977355003357,
|
| 2753 |
+
"learning_rate": 0.0004998207614486106,
|
| 2754 |
+
"loss": 0.4491,
|
| 2755 |
+
"step": 16550
|
| 2756 |
+
},
|
| 2757 |
+
{
|
| 2758 |
+
"epoch": 2.762063227953411,
|
| 2759 |
+
"grad_norm": 0.3267413079738617,
|
| 2760 |
+
"learning_rate": 0.0004998202198115037,
|
| 2761 |
+
"loss": 0.4502,
|
| 2762 |
+
"step": 16600
|
| 2763 |
+
},
|
| 2764 |
+
{
|
| 2765 |
+
"epoch": 2.7703826955074877,
|
| 2766 |
+
"grad_norm": 0.39887621998786926,
|
| 2767 |
+
"learning_rate": 0.000499819678174397,
|
| 2768 |
+
"loss": 0.4529,
|
| 2769 |
+
"step": 16650
|
| 2770 |
+
},
|
| 2771 |
+
{
|
| 2772 |
+
"epoch": 2.7787021630615643,
|
| 2773 |
+
"grad_norm": 0.4172428548336029,
|
| 2774 |
+
"learning_rate": 0.0004998191365372901,
|
| 2775 |
+
"loss": 0.4517,
|
| 2776 |
+
"step": 16700
|
| 2777 |
+
},
|
| 2778 |
+
{
|
| 2779 |
+
"epoch": 2.787021630615641,
|
| 2780 |
+
"grad_norm": 0.3547029197216034,
|
| 2781 |
+
"learning_rate": 0.0004998185949001833,
|
| 2782 |
+
"loss": 0.4471,
|
| 2783 |
+
"step": 16750
|
| 2784 |
+
},
|
| 2785 |
+
{
|
| 2786 |
+
"epoch": 2.7953410981697173,
|
| 2787 |
+
"grad_norm": 0.31628596782684326,
|
| 2788 |
+
"learning_rate": 0.0004998180532630765,
|
| 2789 |
+
"loss": 0.4472,
|
| 2790 |
+
"step": 16800
|
| 2791 |
+
},
|
| 2792 |
+
{
|
| 2793 |
+
"epoch": 2.803660565723794,
|
| 2794 |
+
"grad_norm": 0.29753875732421875,
|
| 2795 |
+
"learning_rate": 0.0004998175116259696,
|
| 2796 |
+
"loss": 0.4506,
|
| 2797 |
+
"step": 16850
|
| 2798 |
+
},
|
| 2799 |
+
{
|
| 2800 |
+
"epoch": 2.8119800332778704,
|
| 2801 |
+
"grad_norm": 0.48493313789367676,
|
| 2802 |
+
"learning_rate": 0.0004998169699888629,
|
| 2803 |
+
"loss": 0.4502,
|
| 2804 |
+
"step": 16900
|
| 2805 |
+
},
|
| 2806 |
+
{
|
| 2807 |
+
"epoch": 2.820299500831947,
|
| 2808 |
+
"grad_norm": 0.36175137758255005,
|
| 2809 |
+
"learning_rate": 0.000499816428351756,
|
| 2810 |
+
"loss": 0.4504,
|
| 2811 |
+
"step": 16950
|
| 2812 |
+
},
|
| 2813 |
+
{
|
| 2814 |
+
"epoch": 2.8286189683860234,
|
| 2815 |
+
"grad_norm": 0.3172094523906708,
|
| 2816 |
+
"learning_rate": 0.0004998158867146492,
|
| 2817 |
+
"loss": 0.4455,
|
| 2818 |
+
"step": 17000
|
| 2819 |
+
},
|
| 2820 |
+
{
|
| 2821 |
+
"epoch": 2.8286189683860234,
|
| 2822 |
+
"eval_accuracy": 0.770005176967467,
|
| 2823 |
+
"eval_auc": 0.85512334595064,
|
| 2824 |
+
"eval_f1": 0.782045916288558,
|
| 2825 |
+
"eval_loss": 0.4468492567539215,
|
| 2826 |
+
"eval_precision": 0.7428258511568151,
|
| 2827 |
+
"eval_recall": 0.8256383545289081,
|
| 2828 |
+
"eval_runtime": 3103.5745,
|
| 2829 |
+
"eval_samples_per_second": 110.163,
|
| 2830 |
+
"eval_steps_per_second": 13.771,
|
| 2831 |
+
"step": 17000
|
| 2832 |
+
},
|
| 2833 |
+
{
|
| 2834 |
+
"epoch": 2.8369384359401,
|
| 2835 |
+
"grad_norm": 0.49940770864486694,
|
| 2836 |
+
"learning_rate": 0.0004998153450775424,
|
| 2837 |
+
"loss": 0.4467,
|
| 2838 |
+
"step": 17050
|
| 2839 |
+
},
|
| 2840 |
+
{
|
| 2841 |
+
"epoch": 2.8452579034941765,
|
| 2842 |
+
"grad_norm": 0.3779182434082031,
|
| 2843 |
+
"learning_rate": 0.0004998148034404356,
|
| 2844 |
+
"loss": 0.4427,
|
| 2845 |
+
"step": 17100
|
| 2846 |
+
},
|
| 2847 |
+
{
|
| 2848 |
+
"epoch": 2.853577371048253,
|
| 2849 |
+
"grad_norm": 0.3529649078845978,
|
| 2850 |
+
"learning_rate": 0.0004998142726360708,
|
| 2851 |
+
"loss": 0.4469,
|
| 2852 |
+
"step": 17150
|
| 2853 |
+
},
|
| 2854 |
+
{
|
| 2855 |
+
"epoch": 2.8618968386023296,
|
| 2856 |
+
"grad_norm": 0.421783447265625,
|
| 2857 |
+
"learning_rate": 0.0004998137309989642,
|
| 2858 |
+
"loss": 0.4449,
|
| 2859 |
+
"step": 17200
|
| 2860 |
+
},
|
| 2861 |
+
{
|
| 2862 |
+
"epoch": 2.870216306156406,
|
| 2863 |
+
"grad_norm": 0.38324880599975586,
|
| 2864 |
+
"learning_rate": 0.0004998131893618572,
|
| 2865 |
+
"loss": 0.4446,
|
| 2866 |
+
"step": 17250
|
| 2867 |
+
},
|
| 2868 |
+
{
|
| 2869 |
+
"epoch": 2.8785357737104826,
|
| 2870 |
+
"grad_norm": 0.43824031949043274,
|
| 2871 |
+
"learning_rate": 0.0004998126477247504,
|
| 2872 |
+
"loss": 0.4465,
|
| 2873 |
+
"step": 17300
|
| 2874 |
+
},
|
| 2875 |
+
{
|
| 2876 |
+
"epoch": 2.886855241264559,
|
| 2877 |
+
"grad_norm": 0.3818030059337616,
|
| 2878 |
+
"learning_rate": 0.0004998121060876436,
|
| 2879 |
+
"loss": 0.4459,
|
| 2880 |
+
"step": 17350
|
| 2881 |
+
},
|
| 2882 |
+
{
|
| 2883 |
+
"epoch": 2.8951747088186357,
|
| 2884 |
+
"grad_norm": 0.30165761709213257,
|
| 2885 |
+
"learning_rate": 0.0004998115644505367,
|
| 2886 |
+
"loss": 0.4505,
|
| 2887 |
+
"step": 17400
|
| 2888 |
+
},
|
| 2889 |
+
{
|
| 2890 |
+
"epoch": 2.9034941763727122,
|
| 2891 |
+
"grad_norm": 0.28733378648757935,
|
| 2892 |
+
"learning_rate": 0.00049981102281343,
|
| 2893 |
+
"loss": 0.4526,
|
| 2894 |
+
"step": 17450
|
| 2895 |
+
},
|
| 2896 |
+
{
|
| 2897 |
+
"epoch": 2.9118136439267888,
|
| 2898 |
+
"grad_norm": 0.3203652799129486,
|
| 2899 |
+
"learning_rate": 0.0004998104811763231,
|
| 2900 |
+
"loss": 0.4428,
|
| 2901 |
+
"step": 17500
|
| 2902 |
+
},
|
| 2903 |
+
{
|
| 2904 |
+
"epoch": 2.9118136439267888,
|
| 2905 |
+
"eval_accuracy": 0.7715377933249293,
|
| 2906 |
+
"eval_auc": 0.8548695984738128,
|
| 2907 |
+
"eval_f1": 0.7888806302958228,
|
| 2908 |
+
"eval_loss": 0.44894230365753174,
|
| 2909 |
+
"eval_precision": 0.7329245264067177,
|
| 2910 |
+
"eval_recall": 0.8540870491429107,
|
| 2911 |
+
"eval_runtime": 3097.7551,
|
| 2912 |
+
"eval_samples_per_second": 110.37,
|
| 2913 |
+
"eval_steps_per_second": 13.796,
|
| 2914 |
+
"step": 17500
|
| 2915 |
+
},
|
| 2916 |
+
{
|
| 2917 |
+
"epoch": 2.9201331114808653,
|
| 2918 |
+
"grad_norm": 0.2848743498325348,
|
| 2919 |
+
"learning_rate": 0.0004998099395392163,
|
| 2920 |
+
"loss": 0.4506,
|
| 2921 |
+
"step": 17550
|
| 2922 |
+
},
|
| 2923 |
+
{
|
| 2924 |
+
"epoch": 2.928452579034942,
|
| 2925 |
+
"grad_norm": 0.3639114499092102,
|
| 2926 |
+
"learning_rate": 0.0004998093979021095,
|
| 2927 |
+
"loss": 0.45,
|
| 2928 |
+
"step": 17600
|
| 2929 |
+
},
|
| 2930 |
+
{
|
| 2931 |
+
"epoch": 2.9367720465890184,
|
| 2932 |
+
"grad_norm": 0.35603734850883484,
|
| 2933 |
+
"learning_rate": 0.0004998088562650027,
|
| 2934 |
+
"loss": 0.4445,
|
| 2935 |
+
"step": 17650
|
| 2936 |
+
},
|
| 2937 |
+
{
|
| 2938 |
+
"epoch": 2.945091514143095,
|
| 2939 |
+
"grad_norm": 0.3066865801811218,
|
| 2940 |
+
"learning_rate": 0.0004998083146278958,
|
| 2941 |
+
"loss": 0.4486,
|
| 2942 |
+
"step": 17700
|
| 2943 |
+
},
|
| 2944 |
+
{
|
| 2945 |
+
"epoch": 2.9534109816971714,
|
| 2946 |
+
"grad_norm": 0.30339953303337097,
|
| 2947 |
+
"learning_rate": 0.000499807772990789,
|
| 2948 |
+
"loss": 0.4523,
|
| 2949 |
+
"step": 17750
|
| 2950 |
+
},
|
| 2951 |
+
{
|
| 2952 |
+
"epoch": 2.961730449251248,
|
| 2953 |
+
"grad_norm": 0.2876887917518616,
|
| 2954 |
+
"learning_rate": 0.0004998072313536822,
|
| 2955 |
+
"loss": 0.4506,
|
| 2956 |
+
"step": 17800
|
| 2957 |
+
},
|
| 2958 |
+
{
|
| 2959 |
+
"epoch": 2.9700499168053245,
|
| 2960 |
+
"grad_norm": 0.32773932814598083,
|
| 2961 |
+
"learning_rate": 0.0004998066897165754,
|
| 2962 |
+
"loss": 0.4459,
|
| 2963 |
+
"step": 17850
|
| 2964 |
+
},
|
| 2965 |
+
{
|
| 2966 |
+
"epoch": 2.978369384359401,
|
| 2967 |
+
"grad_norm": 0.2950334846973419,
|
| 2968 |
+
"learning_rate": 0.0004998061480794686,
|
| 2969 |
+
"loss": 0.4454,
|
| 2970 |
+
"step": 17900
|
| 2971 |
+
},
|
| 2972 |
+
{
|
| 2973 |
+
"epoch": 2.9866888519134775,
|
| 2974 |
+
"grad_norm": 0.4425393044948578,
|
| 2975 |
+
"learning_rate": 0.0004998056064423617,
|
| 2976 |
+
"loss": 0.4434,
|
| 2977 |
+
"step": 17950
|
| 2978 |
+
},
|
| 2979 |
+
{
|
| 2980 |
+
"epoch": 2.995008319467554,
|
| 2981 |
+
"grad_norm": 0.2697887718677521,
|
| 2982 |
+
"learning_rate": 0.000499805064805255,
|
| 2983 |
+
"loss": 0.4465,
|
| 2984 |
+
"step": 18000
|
| 2985 |
+
},
|
| 2986 |
+
{
|
| 2987 |
+
"epoch": 2.995008319467554,
|
| 2988 |
+
"eval_accuracy": 0.773348269518191,
|
| 2989 |
+
"eval_auc": 0.8564303811560599,
|
| 2990 |
+
"eval_f1": 0.7921942795235261,
|
| 2991 |
+
"eval_loss": 0.4447154104709625,
|
| 2992 |
+
"eval_precision": 0.7310888599612942,
|
| 2993 |
+
"eval_recall": 0.8644458620346581,
|
| 2994 |
+
"eval_runtime": 3118.3883,
|
| 2995 |
+
"eval_samples_per_second": 109.64,
|
| 2996 |
+
"eval_steps_per_second": 13.705,
|
| 2997 |
+
"step": 18000
|
| 2998 |
+
}
|
| 2999 |
+
],
|
| 3000 |
+
"logging_steps": 50,
|
| 3001 |
+
"max_steps": 90150,
|
| 3002 |
+
"num_input_tokens_seen": 0,
|
| 3003 |
+
"num_train_epochs": 15,
|
| 3004 |
+
"save_steps": 500,
|
| 3005 |
+
"stateful_callbacks": {
|
| 3006 |
+
"TrainerControl": {
|
| 3007 |
+
"args": {
|
| 3008 |
+
"should_epoch_stop": false,
|
| 3009 |
+
"should_evaluate": false,
|
| 3010 |
+
"should_log": false,
|
| 3011 |
+
"should_save": true,
|
| 3012 |
+
"should_training_stop": false
|
| 3013 |
+
},
|
| 3014 |
+
"attributes": {}
|
| 3015 |
+
}
|
| 3016 |
+
},
|
| 3017 |
+
"total_flos": 9.267314096665788e+18,
|
| 3018 |
+
"train_batch_size": 512,
|
| 3019 |
+
"trial_name": null,
|
| 3020 |
+
"trial_params": null
|
| 3021 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e75980e262b6c0c19f65e1b1e28a8eefd3ed3d9eca42533bb813424fdd742137
|
| 3 |
+
size 5368
|