Upload folder using huggingface_hub
Browse files- prior_attributer_polymarket_4b_2900/README.md +202 -0
- prior_attributer_polymarket_4b_2900/adapter_config.json +34 -0
- prior_attributer_polymarket_4b_2900/adapter_model.safetensors +3 -0
- prior_attributer_polymarket_4b_2900/config.json +6 -0
- prior_attributer_polymarket_4b_2900/optimizer.pt +3 -0
- prior_attributer_polymarket_4b_2900/regression_head.bin +3 -0
- prior_attributer_polymarket_4b_2900/rng_state.pth +3 -0
- prior_attributer_polymarket_4b_2900/scheduler.pt +3 -0
- prior_attributer_polymarket_4b_2900/trainer_state.json +2111 -0
- prior_attributer_polymarket_4b_2900/training_args.bin +3 -0
prior_attributer_polymarket_4b_2900/README.md
ADDED
|
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: Qwen/Qwen3-4B
|
| 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 0.14.0
|
prior_attributer_polymarket_4b_2900/adapter_config.json
ADDED
|
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "/mnt/tidal-alsh-share2/usr/wangshanyong/models/Qwen/Qwen3-4B",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"eva_config": null,
|
| 7 |
+
"exclude_modules": null,
|
| 8 |
+
"fan_in_fan_out": false,
|
| 9 |
+
"inference_mode": true,
|
| 10 |
+
"init_lora_weights": true,
|
| 11 |
+
"layer_replication": null,
|
| 12 |
+
"layers_pattern": null,
|
| 13 |
+
"layers_to_transform": null,
|
| 14 |
+
"loftq_config": {},
|
| 15 |
+
"lora_alpha": 32,
|
| 16 |
+
"lora_bias": false,
|
| 17 |
+
"lora_dropout": 0.1,
|
| 18 |
+
"megatron_config": null,
|
| 19 |
+
"megatron_core": "megatron.core",
|
| 20 |
+
"modules_to_save": null,
|
| 21 |
+
"peft_type": "LORA",
|
| 22 |
+
"r": 32,
|
| 23 |
+
"rank_pattern": {},
|
| 24 |
+
"revision": null,
|
| 25 |
+
"target_modules": [
|
| 26 |
+
"q_proj",
|
| 27 |
+
"v_proj",
|
| 28 |
+
"k_proj",
|
| 29 |
+
"o_proj"
|
| 30 |
+
],
|
| 31 |
+
"task_type": "CAUSAL_LM",
|
| 32 |
+
"use_dora": false,
|
| 33 |
+
"use_rslora": false
|
| 34 |
+
}
|
prior_attributer_polymarket_4b_2900/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a1c95c58a7689dda030b9276202475a2afbb73e119f3d812310656643dd27cce
|
| 3 |
+
size 94410616
|
prior_attributer_polymarket_4b_2900/config.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"base_model_name_or_path": "/mnt/tidal-alsh-share2/usr/wangshanyong/models/Qwen/Qwen3-4B",
|
| 3 |
+
"max_length": 1024,
|
| 4 |
+
"model_type": "llm_regressor",
|
| 5 |
+
"transformers_version": "4.57.6"
|
| 6 |
+
}
|
prior_attributer_polymarket_4b_2900/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e0b93a35e03123d129d72dcdf397070f52b61132a7e654dfa0a8731eef520cda
|
| 3 |
+
size 194410810
|
prior_attributer_polymarket_4b_2900/regression_head.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:06b6ceed8307b14b48e48f074c3babf963c647c3b2384c2d6869ef8cf77dde8d
|
| 3 |
+
size 2712352
|
prior_attributer_polymarket_4b_2900/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3b7a17cd060e6c3d3ffdf9501d645843cb62c9cdb5d8741f86c19f6e2c0bd74a
|
| 3 |
+
size 14244
|
prior_attributer_polymarket_4b_2900/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:faa8d11a452b0f628fb0fa1a6874024ca1271dc9684e0052fc10457b7bae9b0d
|
| 3 |
+
size 1064
|
prior_attributer_polymarket_4b_2900/trainer_state.json
ADDED
|
@@ -0,0 +1,2111 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": 2500,
|
| 3 |
+
"best_metric": 0.15810872614383698,
|
| 4 |
+
"best_model_checkpoint": "../saves/prior_attributer_polymarket_4b/checkpoint-2500",
|
| 5 |
+
"epoch": 1.1832092216668366,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 2900,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.0004080383556054269,
|
| 14 |
+
"grad_norm": 1.197115421295166,
|
| 15 |
+
"learning_rate": 2e-05,
|
| 16 |
+
"loss": 0.115,
|
| 17 |
+
"step": 1
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.004080383556054269,
|
| 21 |
+
"grad_norm": 0.062769815325737,
|
| 22 |
+
"learning_rate": 1.9992656058751532e-05,
|
| 23 |
+
"loss": 0.1976,
|
| 24 |
+
"step": 10
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.008160767112108539,
|
| 28 |
+
"grad_norm": 2.5398786067962646,
|
| 29 |
+
"learning_rate": 1.998449612403101e-05,
|
| 30 |
+
"loss": 0.1798,
|
| 31 |
+
"step": 20
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.012241150668162807,
|
| 35 |
+
"grad_norm": 1.748403549194336,
|
| 36 |
+
"learning_rate": 1.9976336189310487e-05,
|
| 37 |
+
"loss": 0.3736,
|
| 38 |
+
"step": 30
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.016321534224217078,
|
| 42 |
+
"grad_norm": 1.7297178506851196,
|
| 43 |
+
"learning_rate": 1.9968176254589966e-05,
|
| 44 |
+
"loss": 0.2225,
|
| 45 |
+
"step": 40
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.020401917780271346,
|
| 49 |
+
"grad_norm": 1.073101282119751,
|
| 50 |
+
"learning_rate": 1.9960016319869442e-05,
|
| 51 |
+
"loss": 0.2245,
|
| 52 |
+
"step": 50
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.024482301336325615,
|
| 56 |
+
"grad_norm": 2.884895086288452,
|
| 57 |
+
"learning_rate": 1.995185638514892e-05,
|
| 58 |
+
"loss": 0.3386,
|
| 59 |
+
"step": 60
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.028562684892379883,
|
| 63 |
+
"grad_norm": 0.4594326913356781,
|
| 64 |
+
"learning_rate": 1.9943696450428397e-05,
|
| 65 |
+
"loss": 0.1972,
|
| 66 |
+
"step": 70
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.032643068448434155,
|
| 70 |
+
"grad_norm": 2.303440809249878,
|
| 71 |
+
"learning_rate": 1.9935536515707876e-05,
|
| 72 |
+
"loss": 0.2936,
|
| 73 |
+
"step": 80
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.03672345200448842,
|
| 77 |
+
"grad_norm": 0.6495940089225769,
|
| 78 |
+
"learning_rate": 1.9927376580987355e-05,
|
| 79 |
+
"loss": 0.2015,
|
| 80 |
+
"step": 90
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.04080383556054269,
|
| 84 |
+
"grad_norm": 0.44108060002326965,
|
| 85 |
+
"learning_rate": 1.991921664626683e-05,
|
| 86 |
+
"loss": 0.1682,
|
| 87 |
+
"step": 100
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.04488421911659696,
|
| 91 |
+
"grad_norm": 0.8983336687088013,
|
| 92 |
+
"learning_rate": 1.9911056711546307e-05,
|
| 93 |
+
"loss": 0.2188,
|
| 94 |
+
"step": 110
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.04896460267265123,
|
| 98 |
+
"grad_norm": 0.804106593132019,
|
| 99 |
+
"learning_rate": 1.9902896776825786e-05,
|
| 100 |
+
"loss": 0.1468,
|
| 101 |
+
"step": 120
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.0530449862287055,
|
| 105 |
+
"grad_norm": 1.6065974235534668,
|
| 106 |
+
"learning_rate": 1.9894736842105265e-05,
|
| 107 |
+
"loss": 0.2299,
|
| 108 |
+
"step": 130
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.057125369784759766,
|
| 112 |
+
"grad_norm": 2.307762622833252,
|
| 113 |
+
"learning_rate": 1.9886576907384744e-05,
|
| 114 |
+
"loss": 0.2235,
|
| 115 |
+
"step": 140
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.06120575334081404,
|
| 119 |
+
"grad_norm": 2.0962867736816406,
|
| 120 |
+
"learning_rate": 1.987841697266422e-05,
|
| 121 |
+
"loss": 0.1584,
|
| 122 |
+
"step": 150
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.06528613689686831,
|
| 126 |
+
"grad_norm": 1.4618809223175049,
|
| 127 |
+
"learning_rate": 1.98702570379437e-05,
|
| 128 |
+
"loss": 0.1578,
|
| 129 |
+
"step": 160
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.06936652045292258,
|
| 133 |
+
"grad_norm": 1.4815113544464111,
|
| 134 |
+
"learning_rate": 1.9862097103223178e-05,
|
| 135 |
+
"loss": 0.1921,
|
| 136 |
+
"step": 170
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.07344690400897684,
|
| 140 |
+
"grad_norm": 1.9700915813446045,
|
| 141 |
+
"learning_rate": 1.9853937168502654e-05,
|
| 142 |
+
"loss": 0.2035,
|
| 143 |
+
"step": 180
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.07752728756503112,
|
| 147 |
+
"grad_norm": 1.9198737144470215,
|
| 148 |
+
"learning_rate": 1.984577723378213e-05,
|
| 149 |
+
"loss": 0.1231,
|
| 150 |
+
"step": 190
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.08160767112108538,
|
| 154 |
+
"grad_norm": 1.500857949256897,
|
| 155 |
+
"learning_rate": 1.983761729906161e-05,
|
| 156 |
+
"loss": 0.2042,
|
| 157 |
+
"step": 200
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 0.08568805467713965,
|
| 161 |
+
"grad_norm": 2.8167471885681152,
|
| 162 |
+
"learning_rate": 1.9829457364341088e-05,
|
| 163 |
+
"loss": 0.2765,
|
| 164 |
+
"step": 210
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.08976843823319391,
|
| 168 |
+
"grad_norm": 1.9542330503463745,
|
| 169 |
+
"learning_rate": 1.9821297429620564e-05,
|
| 170 |
+
"loss": 0.1445,
|
| 171 |
+
"step": 220
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.0938488217892482,
|
| 175 |
+
"grad_norm": 1.3737446069717407,
|
| 176 |
+
"learning_rate": 1.9813137494900043e-05,
|
| 177 |
+
"loss": 0.0898,
|
| 178 |
+
"step": 230
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.09792920534530246,
|
| 182 |
+
"grad_norm": 0.0,
|
| 183 |
+
"learning_rate": 1.980497756017952e-05,
|
| 184 |
+
"loss": 0.1711,
|
| 185 |
+
"step": 240
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.10200958890135672,
|
| 189 |
+
"grad_norm": 0.0,
|
| 190 |
+
"learning_rate": 1.9796817625458998e-05,
|
| 191 |
+
"loss": 0.1336,
|
| 192 |
+
"step": 250
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.106089972457411,
|
| 196 |
+
"grad_norm": 1.6241754293441772,
|
| 197 |
+
"learning_rate": 1.9788657690738477e-05,
|
| 198 |
+
"loss": 0.223,
|
| 199 |
+
"step": 260
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 0.11017035601346527,
|
| 203 |
+
"grad_norm": 0.8505207300186157,
|
| 204 |
+
"learning_rate": 1.9780497756017953e-05,
|
| 205 |
+
"loss": 0.1421,
|
| 206 |
+
"step": 270
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.11425073956951953,
|
| 210 |
+
"grad_norm": 1.3087742328643799,
|
| 211 |
+
"learning_rate": 1.977233782129743e-05,
|
| 212 |
+
"loss": 0.2088,
|
| 213 |
+
"step": 280
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.1183311231255738,
|
| 217 |
+
"grad_norm": 1.7539215087890625,
|
| 218 |
+
"learning_rate": 1.976417788657691e-05,
|
| 219 |
+
"loss": 0.2385,
|
| 220 |
+
"step": 290
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 0.12241150668162808,
|
| 224 |
+
"grad_norm": 1.763391137123108,
|
| 225 |
+
"learning_rate": 1.9756017951856387e-05,
|
| 226 |
+
"loss": 0.2221,
|
| 227 |
+
"step": 300
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 0.12649189023768234,
|
| 231 |
+
"grad_norm": 1.7321321964263916,
|
| 232 |
+
"learning_rate": 1.9747858017135862e-05,
|
| 233 |
+
"loss": 0.0796,
|
| 234 |
+
"step": 310
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.13057227379373662,
|
| 238 |
+
"grad_norm": 0.850107729434967,
|
| 239 |
+
"learning_rate": 1.973969808241534e-05,
|
| 240 |
+
"loss": 0.116,
|
| 241 |
+
"step": 320
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 0.13465265734979087,
|
| 245 |
+
"grad_norm": 0.14039260149002075,
|
| 246 |
+
"learning_rate": 1.973153814769482e-05,
|
| 247 |
+
"loss": 0.1679,
|
| 248 |
+
"step": 330
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.13873304090584515,
|
| 252 |
+
"grad_norm": 0.44985684752464294,
|
| 253 |
+
"learning_rate": 1.9723378212974296e-05,
|
| 254 |
+
"loss": 0.0986,
|
| 255 |
+
"step": 340
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.14281342446189943,
|
| 259 |
+
"grad_norm": 1.0865625143051147,
|
| 260 |
+
"learning_rate": 1.9715218278253775e-05,
|
| 261 |
+
"loss": 0.2011,
|
| 262 |
+
"step": 350
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 0.14689380801795368,
|
| 266 |
+
"grad_norm": 2.6993794441223145,
|
| 267 |
+
"learning_rate": 1.9707058343533255e-05,
|
| 268 |
+
"loss": 0.2065,
|
| 269 |
+
"step": 360
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 0.15097419157400796,
|
| 273 |
+
"grad_norm": 0.0,
|
| 274 |
+
"learning_rate": 1.9698898408812734e-05,
|
| 275 |
+
"loss": 0.2226,
|
| 276 |
+
"step": 370
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 0.15505457513006224,
|
| 280 |
+
"grad_norm": 1.9446637630462646,
|
| 281 |
+
"learning_rate": 1.969073847409221e-05,
|
| 282 |
+
"loss": 0.1792,
|
| 283 |
+
"step": 380
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 0.1591349586861165,
|
| 287 |
+
"grad_norm": 0.0,
|
| 288 |
+
"learning_rate": 1.9682578539371685e-05,
|
| 289 |
+
"loss": 0.1589,
|
| 290 |
+
"step": 390
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.16321534224217077,
|
| 294 |
+
"grad_norm": 3.4847676753997803,
|
| 295 |
+
"learning_rate": 1.9674418604651164e-05,
|
| 296 |
+
"loss": 0.2231,
|
| 297 |
+
"step": 400
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.16729572579822502,
|
| 301 |
+
"grad_norm": 2.1196365356445312,
|
| 302 |
+
"learning_rate": 1.9666258669930644e-05,
|
| 303 |
+
"loss": 0.2105,
|
| 304 |
+
"step": 410
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 0.1713761093542793,
|
| 308 |
+
"grad_norm": 2.080935478210449,
|
| 309 |
+
"learning_rate": 1.965809873521012e-05,
|
| 310 |
+
"loss": 0.1893,
|
| 311 |
+
"step": 420
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 0.17545649291033358,
|
| 315 |
+
"grad_norm": 0.0,
|
| 316 |
+
"learning_rate": 1.96499388004896e-05,
|
| 317 |
+
"loss": 0.1518,
|
| 318 |
+
"step": 430
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 0.17953687646638783,
|
| 322 |
+
"grad_norm": 1.2432128190994263,
|
| 323 |
+
"learning_rate": 1.9641778865769074e-05,
|
| 324 |
+
"loss": 0.1305,
|
| 325 |
+
"step": 440
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 0.1836172600224421,
|
| 329 |
+
"grad_norm": 1.5672948360443115,
|
| 330 |
+
"learning_rate": 1.9633618931048553e-05,
|
| 331 |
+
"loss": 0.1938,
|
| 332 |
+
"step": 450
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 0.1876976435784964,
|
| 336 |
+
"grad_norm": 0.0,
|
| 337 |
+
"learning_rate": 1.962545899632803e-05,
|
| 338 |
+
"loss": 0.1269,
|
| 339 |
+
"step": 460
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.19177802713455064,
|
| 343 |
+
"grad_norm": 0.7028200626373291,
|
| 344 |
+
"learning_rate": 1.9617299061607508e-05,
|
| 345 |
+
"loss": 0.1078,
|
| 346 |
+
"step": 470
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.19585841069060492,
|
| 350 |
+
"grad_norm": 0.5177062749862671,
|
| 351 |
+
"learning_rate": 1.9609139126886987e-05,
|
| 352 |
+
"loss": 0.1291,
|
| 353 |
+
"step": 480
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 0.1999387942466592,
|
| 357 |
+
"grad_norm": 1.3655359745025635,
|
| 358 |
+
"learning_rate": 1.9600979192166466e-05,
|
| 359 |
+
"loss": 0.2066,
|
| 360 |
+
"step": 490
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 0.20401917780271345,
|
| 364 |
+
"grad_norm": 1.7469329833984375,
|
| 365 |
+
"learning_rate": 1.9592819257445942e-05,
|
| 366 |
+
"loss": 0.1059,
|
| 367 |
+
"step": 500
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 0.20401917780271345,
|
| 371 |
+
"eval_loss": 0.1709977239370346,
|
| 372 |
+
"eval_runtime": 5717.6231,
|
| 373 |
+
"eval_samples_per_second": 0.646,
|
| 374 |
+
"eval_steps_per_second": 0.323,
|
| 375 |
+
"step": 500
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 0.20809956135876773,
|
| 379 |
+
"grad_norm": 0.0,
|
| 380 |
+
"learning_rate": 1.9584659322725418e-05,
|
| 381 |
+
"loss": 0.1062,
|
| 382 |
+
"step": 510
|
| 383 |
+
},
|
| 384 |
+
{
|
| 385 |
+
"epoch": 0.212179944914822,
|
| 386 |
+
"grad_norm": 1.9649909734725952,
|
| 387 |
+
"learning_rate": 1.9576499388004897e-05,
|
| 388 |
+
"loss": 0.2056,
|
| 389 |
+
"step": 520
|
| 390 |
+
},
|
| 391 |
+
{
|
| 392 |
+
"epoch": 0.21626032847087626,
|
| 393 |
+
"grad_norm": 0.9991185069084167,
|
| 394 |
+
"learning_rate": 1.9568339453284376e-05,
|
| 395 |
+
"loss": 0.1863,
|
| 396 |
+
"step": 530
|
| 397 |
+
},
|
| 398 |
+
{
|
| 399 |
+
"epoch": 0.22034071202693054,
|
| 400 |
+
"grad_norm": 1.955867052078247,
|
| 401 |
+
"learning_rate": 1.9560179518563852e-05,
|
| 402 |
+
"loss": 0.1804,
|
| 403 |
+
"step": 540
|
| 404 |
+
},
|
| 405 |
+
{
|
| 406 |
+
"epoch": 0.22442109558298481,
|
| 407 |
+
"grad_norm": 1.5744529962539673,
|
| 408 |
+
"learning_rate": 1.955201958384333e-05,
|
| 409 |
+
"loss": 0.1147,
|
| 410 |
+
"step": 550
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 0.22850147913903907,
|
| 414 |
+
"grad_norm": 0.8454556465148926,
|
| 415 |
+
"learning_rate": 1.954385964912281e-05,
|
| 416 |
+
"loss": 0.1995,
|
| 417 |
+
"step": 560
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 0.23258186269509334,
|
| 421 |
+
"grad_norm": 1.5379407405853271,
|
| 422 |
+
"learning_rate": 1.9535699714402286e-05,
|
| 423 |
+
"loss": 0.2056,
|
| 424 |
+
"step": 570
|
| 425 |
+
},
|
| 426 |
+
{
|
| 427 |
+
"epoch": 0.2366622462511476,
|
| 428 |
+
"grad_norm": 1.6168546676635742,
|
| 429 |
+
"learning_rate": 1.9527539779681762e-05,
|
| 430 |
+
"loss": 0.1991,
|
| 431 |
+
"step": 580
|
| 432 |
+
},
|
| 433 |
+
{
|
| 434 |
+
"epoch": 0.24074262980720187,
|
| 435 |
+
"grad_norm": 0.9494819045066833,
|
| 436 |
+
"learning_rate": 1.951937984496124e-05,
|
| 437 |
+
"loss": 0.1712,
|
| 438 |
+
"step": 590
|
| 439 |
+
},
|
| 440 |
+
{
|
| 441 |
+
"epoch": 0.24482301336325615,
|
| 442 |
+
"grad_norm": 1.0418027639389038,
|
| 443 |
+
"learning_rate": 1.951121991024072e-05,
|
| 444 |
+
"loss": 0.1218,
|
| 445 |
+
"step": 600
|
| 446 |
+
},
|
| 447 |
+
{
|
| 448 |
+
"epoch": 0.2489033969193104,
|
| 449 |
+
"grad_norm": 1.579040288925171,
|
| 450 |
+
"learning_rate": 1.95030599755202e-05,
|
| 451 |
+
"loss": 0.1568,
|
| 452 |
+
"step": 610
|
| 453 |
+
},
|
| 454 |
+
{
|
| 455 |
+
"epoch": 0.2529837804753647,
|
| 456 |
+
"grad_norm": 1.290714144706726,
|
| 457 |
+
"learning_rate": 1.9494900040799675e-05,
|
| 458 |
+
"loss": 0.2278,
|
| 459 |
+
"step": 620
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 0.25706416403141896,
|
| 463 |
+
"grad_norm": 0.5078051686286926,
|
| 464 |
+
"learning_rate": 1.9486740106079154e-05,
|
| 465 |
+
"loss": 0.167,
|
| 466 |
+
"step": 630
|
| 467 |
+
},
|
| 468 |
+
{
|
| 469 |
+
"epoch": 0.26114454758747324,
|
| 470 |
+
"grad_norm": 0.5044044256210327,
|
| 471 |
+
"learning_rate": 1.947858017135863e-05,
|
| 472 |
+
"loss": 0.1019,
|
| 473 |
+
"step": 640
|
| 474 |
+
},
|
| 475 |
+
{
|
| 476 |
+
"epoch": 0.26522493114352746,
|
| 477 |
+
"grad_norm": 0.38573765754699707,
|
| 478 |
+
"learning_rate": 1.947042023663811e-05,
|
| 479 |
+
"loss": 0.1564,
|
| 480 |
+
"step": 650
|
| 481 |
+
},
|
| 482 |
+
{
|
| 483 |
+
"epoch": 0.26930531469958174,
|
| 484 |
+
"grad_norm": 1.4927674531936646,
|
| 485 |
+
"learning_rate": 1.9462260301917585e-05,
|
| 486 |
+
"loss": 0.2518,
|
| 487 |
+
"step": 660
|
| 488 |
+
},
|
| 489 |
+
{
|
| 490 |
+
"epoch": 0.273385698255636,
|
| 491 |
+
"grad_norm": 1.397609829902649,
|
| 492 |
+
"learning_rate": 1.9454100367197064e-05,
|
| 493 |
+
"loss": 0.1117,
|
| 494 |
+
"step": 670
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 0.2774660818116903,
|
| 498 |
+
"grad_norm": 1.1881047487258911,
|
| 499 |
+
"learning_rate": 1.9445940432476543e-05,
|
| 500 |
+
"loss": 0.0951,
|
| 501 |
+
"step": 680
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 0.2815464653677446,
|
| 505 |
+
"grad_norm": 1.1354044675827026,
|
| 506 |
+
"learning_rate": 1.943778049775602e-05,
|
| 507 |
+
"loss": 0.0996,
|
| 508 |
+
"step": 690
|
| 509 |
+
},
|
| 510 |
+
{
|
| 511 |
+
"epoch": 0.28562684892379886,
|
| 512 |
+
"grad_norm": 0.7019430994987488,
|
| 513 |
+
"learning_rate": 1.9429620563035498e-05,
|
| 514 |
+
"loss": 0.1364,
|
| 515 |
+
"step": 700
|
| 516 |
+
},
|
| 517 |
+
{
|
| 518 |
+
"epoch": 0.2897072324798531,
|
| 519 |
+
"grad_norm": 1.2556483745574951,
|
| 520 |
+
"learning_rate": 1.9421460628314974e-05,
|
| 521 |
+
"loss": 0.1707,
|
| 522 |
+
"step": 710
|
| 523 |
+
},
|
| 524 |
+
{
|
| 525 |
+
"epoch": 0.29378761603590736,
|
| 526 |
+
"grad_norm": 0.5789899230003357,
|
| 527 |
+
"learning_rate": 1.9413300693594453e-05,
|
| 528 |
+
"loss": 0.0999,
|
| 529 |
+
"step": 720
|
| 530 |
+
},
|
| 531 |
+
{
|
| 532 |
+
"epoch": 0.29786799959196164,
|
| 533 |
+
"grad_norm": 1.1356525421142578,
|
| 534 |
+
"learning_rate": 1.9405140758873932e-05,
|
| 535 |
+
"loss": 0.1767,
|
| 536 |
+
"step": 730
|
| 537 |
+
},
|
| 538 |
+
{
|
| 539 |
+
"epoch": 0.3019483831480159,
|
| 540 |
+
"grad_norm": 1.6264972686767578,
|
| 541 |
+
"learning_rate": 1.9396980824153408e-05,
|
| 542 |
+
"loss": 0.1597,
|
| 543 |
+
"step": 740
|
| 544 |
+
},
|
| 545 |
+
{
|
| 546 |
+
"epoch": 0.3060287667040702,
|
| 547 |
+
"grad_norm": 3.7391366958618164,
|
| 548 |
+
"learning_rate": 1.9388820889432887e-05,
|
| 549 |
+
"loss": 0.2732,
|
| 550 |
+
"step": 750
|
| 551 |
+
},
|
| 552 |
+
{
|
| 553 |
+
"epoch": 0.3101091502601245,
|
| 554 |
+
"grad_norm": 1.7408511638641357,
|
| 555 |
+
"learning_rate": 1.9380660954712366e-05,
|
| 556 |
+
"loss": 0.1474,
|
| 557 |
+
"step": 760
|
| 558 |
+
},
|
| 559 |
+
{
|
| 560 |
+
"epoch": 0.3141895338161787,
|
| 561 |
+
"grad_norm": 1.4884685277938843,
|
| 562 |
+
"learning_rate": 1.9372501019991842e-05,
|
| 563 |
+
"loss": 0.1737,
|
| 564 |
+
"step": 770
|
| 565 |
+
},
|
| 566 |
+
{
|
| 567 |
+
"epoch": 0.318269917372233,
|
| 568 |
+
"grad_norm": 0.45126017928123474,
|
| 569 |
+
"learning_rate": 1.9364341085271317e-05,
|
| 570 |
+
"loss": 0.179,
|
| 571 |
+
"step": 780
|
| 572 |
+
},
|
| 573 |
+
{
|
| 574 |
+
"epoch": 0.32235030092828726,
|
| 575 |
+
"grad_norm": 0.9976311326026917,
|
| 576 |
+
"learning_rate": 1.9356181150550797e-05,
|
| 577 |
+
"loss": 0.1212,
|
| 578 |
+
"step": 790
|
| 579 |
+
},
|
| 580 |
+
{
|
| 581 |
+
"epoch": 0.32643068448434154,
|
| 582 |
+
"grad_norm": 1.568253517150879,
|
| 583 |
+
"learning_rate": 1.9348021215830276e-05,
|
| 584 |
+
"loss": 0.1096,
|
| 585 |
+
"step": 800
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 0.3305110680403958,
|
| 589 |
+
"grad_norm": 0.0,
|
| 590 |
+
"learning_rate": 1.933986128110975e-05,
|
| 591 |
+
"loss": 0.1105,
|
| 592 |
+
"step": 810
|
| 593 |
+
},
|
| 594 |
+
{
|
| 595 |
+
"epoch": 0.33459145159645004,
|
| 596 |
+
"grad_norm": 3.553971290588379,
|
| 597 |
+
"learning_rate": 1.933170134638923e-05,
|
| 598 |
+
"loss": 0.1685,
|
| 599 |
+
"step": 820
|
| 600 |
+
},
|
| 601 |
+
{
|
| 602 |
+
"epoch": 0.3386718351525043,
|
| 603 |
+
"grad_norm": 0.37956804037094116,
|
| 604 |
+
"learning_rate": 1.932354141166871e-05,
|
| 605 |
+
"loss": 0.0832,
|
| 606 |
+
"step": 830
|
| 607 |
+
},
|
| 608 |
+
{
|
| 609 |
+
"epoch": 0.3427522187085586,
|
| 610 |
+
"grad_norm": 0.9464099407196045,
|
| 611 |
+
"learning_rate": 1.9315381476948186e-05,
|
| 612 |
+
"loss": 0.1784,
|
| 613 |
+
"step": 840
|
| 614 |
+
},
|
| 615 |
+
{
|
| 616 |
+
"epoch": 0.3468326022646129,
|
| 617 |
+
"grad_norm": 2.282661199569702,
|
| 618 |
+
"learning_rate": 1.9307221542227665e-05,
|
| 619 |
+
"loss": 0.1712,
|
| 620 |
+
"step": 850
|
| 621 |
+
},
|
| 622 |
+
{
|
| 623 |
+
"epoch": 0.35091298582066716,
|
| 624 |
+
"grad_norm": 1.1713647842407227,
|
| 625 |
+
"learning_rate": 1.929906160750714e-05,
|
| 626 |
+
"loss": 0.1147,
|
| 627 |
+
"step": 860
|
| 628 |
+
},
|
| 629 |
+
{
|
| 630 |
+
"epoch": 0.35499336937672143,
|
| 631 |
+
"grad_norm": 1.503341555595398,
|
| 632 |
+
"learning_rate": 1.929090167278662e-05,
|
| 633 |
+
"loss": 0.1052,
|
| 634 |
+
"step": 870
|
| 635 |
+
},
|
| 636 |
+
{
|
| 637 |
+
"epoch": 0.35907375293277566,
|
| 638 |
+
"grad_norm": 0.6751163005828857,
|
| 639 |
+
"learning_rate": 1.92827417380661e-05,
|
| 640 |
+
"loss": 0.2266,
|
| 641 |
+
"step": 880
|
| 642 |
+
},
|
| 643 |
+
{
|
| 644 |
+
"epoch": 0.36315413648882994,
|
| 645 |
+
"grad_norm": 0.8894637823104858,
|
| 646 |
+
"learning_rate": 1.9274581803345574e-05,
|
| 647 |
+
"loss": 0.1487,
|
| 648 |
+
"step": 890
|
| 649 |
+
},
|
| 650 |
+
{
|
| 651 |
+
"epoch": 0.3672345200448842,
|
| 652 |
+
"grad_norm": 1.1354976892471313,
|
| 653 |
+
"learning_rate": 1.926642186862505e-05,
|
| 654 |
+
"loss": 0.2175,
|
| 655 |
+
"step": 900
|
| 656 |
+
},
|
| 657 |
+
{
|
| 658 |
+
"epoch": 0.3713149036009385,
|
| 659 |
+
"grad_norm": 1.0130964517593384,
|
| 660 |
+
"learning_rate": 1.925826193390453e-05,
|
| 661 |
+
"loss": 0.2418,
|
| 662 |
+
"step": 910
|
| 663 |
+
},
|
| 664 |
+
{
|
| 665 |
+
"epoch": 0.3753952871569928,
|
| 666 |
+
"grad_norm": 0.5899848341941833,
|
| 667 |
+
"learning_rate": 1.925010199918401e-05,
|
| 668 |
+
"loss": 0.1668,
|
| 669 |
+
"step": 920
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 0.37947567071304705,
|
| 673 |
+
"grad_norm": 0.2949761748313904,
|
| 674 |
+
"learning_rate": 1.9241942064463484e-05,
|
| 675 |
+
"loss": 0.1446,
|
| 676 |
+
"step": 930
|
| 677 |
+
},
|
| 678 |
+
{
|
| 679 |
+
"epoch": 0.3835560542691013,
|
| 680 |
+
"grad_norm": 1.4031494855880737,
|
| 681 |
+
"learning_rate": 1.9233782129742963e-05,
|
| 682 |
+
"loss": 0.0917,
|
| 683 |
+
"step": 940
|
| 684 |
+
},
|
| 685 |
+
{
|
| 686 |
+
"epoch": 0.38763643782515556,
|
| 687 |
+
"grad_norm": 0.0,
|
| 688 |
+
"learning_rate": 1.9225622195022442e-05,
|
| 689 |
+
"loss": 0.0876,
|
| 690 |
+
"step": 950
|
| 691 |
+
},
|
| 692 |
+
{
|
| 693 |
+
"epoch": 0.39171682138120983,
|
| 694 |
+
"grad_norm": 1.1788252592086792,
|
| 695 |
+
"learning_rate": 1.921746226030192e-05,
|
| 696 |
+
"loss": 0.1019,
|
| 697 |
+
"step": 960
|
| 698 |
+
},
|
| 699 |
+
{
|
| 700 |
+
"epoch": 0.3957972049372641,
|
| 701 |
+
"grad_norm": 1.3211113214492798,
|
| 702 |
+
"learning_rate": 1.9209302325581397e-05,
|
| 703 |
+
"loss": 0.1199,
|
| 704 |
+
"step": 970
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 0.3998775884933184,
|
| 708 |
+
"grad_norm": 2.4007322788238525,
|
| 709 |
+
"learning_rate": 1.9201142390860873e-05,
|
| 710 |
+
"loss": 0.2123,
|
| 711 |
+
"step": 980
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 0.4039579720493726,
|
| 715 |
+
"grad_norm": 0.7072489857673645,
|
| 716 |
+
"learning_rate": 1.9192982456140352e-05,
|
| 717 |
+
"loss": 0.2355,
|
| 718 |
+
"step": 990
|
| 719 |
+
},
|
| 720 |
+
{
|
| 721 |
+
"epoch": 0.4080383556054269,
|
| 722 |
+
"grad_norm": 0.9034311771392822,
|
| 723 |
+
"learning_rate": 1.918482252141983e-05,
|
| 724 |
+
"loss": 0.2086,
|
| 725 |
+
"step": 1000
|
| 726 |
+
},
|
| 727 |
+
{
|
| 728 |
+
"epoch": 0.4080383556054269,
|
| 729 |
+
"eval_loss": 0.16534732282161713,
|
| 730 |
+
"eval_runtime": 5717.6716,
|
| 731 |
+
"eval_samples_per_second": 0.646,
|
| 732 |
+
"eval_steps_per_second": 0.323,
|
| 733 |
+
"step": 1000
|
| 734 |
+
},
|
| 735 |
+
{
|
| 736 |
+
"epoch": 0.4121187391614812,
|
| 737 |
+
"grad_norm": 0.7085575461387634,
|
| 738 |
+
"learning_rate": 1.9176662586699307e-05,
|
| 739 |
+
"loss": 0.136,
|
| 740 |
+
"step": 1010
|
| 741 |
+
},
|
| 742 |
+
{
|
| 743 |
+
"epoch": 0.41619912271753545,
|
| 744 |
+
"grad_norm": 0.7955109477043152,
|
| 745 |
+
"learning_rate": 1.9168502651978786e-05,
|
| 746 |
+
"loss": 0.0829,
|
| 747 |
+
"step": 1020
|
| 748 |
+
},
|
| 749 |
+
{
|
| 750 |
+
"epoch": 0.42027950627358973,
|
| 751 |
+
"grad_norm": 0.4781329929828644,
|
| 752 |
+
"learning_rate": 1.9160342717258265e-05,
|
| 753 |
+
"loss": 0.2112,
|
| 754 |
+
"step": 1030
|
| 755 |
+
},
|
| 756 |
+
{
|
| 757 |
+
"epoch": 0.424359889829644,
|
| 758 |
+
"grad_norm": 0.0,
|
| 759 |
+
"learning_rate": 1.915218278253774e-05,
|
| 760 |
+
"loss": 0.1665,
|
| 761 |
+
"step": 1040
|
| 762 |
+
},
|
| 763 |
+
{
|
| 764 |
+
"epoch": 0.42844027338569823,
|
| 765 |
+
"grad_norm": 0.8854587078094482,
|
| 766 |
+
"learning_rate": 1.9144022847817217e-05,
|
| 767 |
+
"loss": 0.0929,
|
| 768 |
+
"step": 1050
|
| 769 |
+
},
|
| 770 |
+
{
|
| 771 |
+
"epoch": 0.4325206569417525,
|
| 772 |
+
"grad_norm": 0.7086293697357178,
|
| 773 |
+
"learning_rate": 1.9135862913096696e-05,
|
| 774 |
+
"loss": 0.1342,
|
| 775 |
+
"step": 1060
|
| 776 |
+
},
|
| 777 |
+
{
|
| 778 |
+
"epoch": 0.4366010404978068,
|
| 779 |
+
"grad_norm": 0.0,
|
| 780 |
+
"learning_rate": 1.9127702978376175e-05,
|
| 781 |
+
"loss": 0.1739,
|
| 782 |
+
"step": 1070
|
| 783 |
+
},
|
| 784 |
+
{
|
| 785 |
+
"epoch": 0.44068142405386107,
|
| 786 |
+
"grad_norm": 1.0532270669937134,
|
| 787 |
+
"learning_rate": 1.9119543043655654e-05,
|
| 788 |
+
"loss": 0.1093,
|
| 789 |
+
"step": 1080
|
| 790 |
+
},
|
| 791 |
+
{
|
| 792 |
+
"epoch": 0.44476180760991535,
|
| 793 |
+
"grad_norm": 0.0,
|
| 794 |
+
"learning_rate": 1.911138310893513e-05,
|
| 795 |
+
"loss": 0.1425,
|
| 796 |
+
"step": 1090
|
| 797 |
+
},
|
| 798 |
+
{
|
| 799 |
+
"epoch": 0.44884219116596963,
|
| 800 |
+
"grad_norm": 0.38894256949424744,
|
| 801 |
+
"learning_rate": 1.9103223174214606e-05,
|
| 802 |
+
"loss": 0.0964,
|
| 803 |
+
"step": 1100
|
| 804 |
+
},
|
| 805 |
+
{
|
| 806 |
+
"epoch": 0.45292257472202385,
|
| 807 |
+
"grad_norm": 0.0,
|
| 808 |
+
"learning_rate": 1.9095063239494085e-05,
|
| 809 |
+
"loss": 0.0769,
|
| 810 |
+
"step": 1110
|
| 811 |
+
},
|
| 812 |
+
{
|
| 813 |
+
"epoch": 0.45700295827807813,
|
| 814 |
+
"grad_norm": 2.1243956089019775,
|
| 815 |
+
"learning_rate": 1.9086903304773564e-05,
|
| 816 |
+
"loss": 0.1549,
|
| 817 |
+
"step": 1120
|
| 818 |
+
},
|
| 819 |
+
{
|
| 820 |
+
"epoch": 0.4610833418341324,
|
| 821 |
+
"grad_norm": 0.37033727765083313,
|
| 822 |
+
"learning_rate": 1.907874337005304e-05,
|
| 823 |
+
"loss": 0.1836,
|
| 824 |
+
"step": 1130
|
| 825 |
+
},
|
| 826 |
+
{
|
| 827 |
+
"epoch": 0.4651637253901867,
|
| 828 |
+
"grad_norm": 0.05899756774306297,
|
| 829 |
+
"learning_rate": 1.907058343533252e-05,
|
| 830 |
+
"loss": 0.1451,
|
| 831 |
+
"step": 1140
|
| 832 |
+
},
|
| 833 |
+
{
|
| 834 |
+
"epoch": 0.46924410894624097,
|
| 835 |
+
"grad_norm": 1.3318108320236206,
|
| 836 |
+
"learning_rate": 1.9062423500611998e-05,
|
| 837 |
+
"loss": 0.1424,
|
| 838 |
+
"step": 1150
|
| 839 |
+
},
|
| 840 |
+
{
|
| 841 |
+
"epoch": 0.4733244925022952,
|
| 842 |
+
"grad_norm": 0.5499687790870667,
|
| 843 |
+
"learning_rate": 1.9054263565891474e-05,
|
| 844 |
+
"loss": 0.1343,
|
| 845 |
+
"step": 1160
|
| 846 |
+
},
|
| 847 |
+
{
|
| 848 |
+
"epoch": 0.47740487605834947,
|
| 849 |
+
"grad_norm": 0.7460530996322632,
|
| 850 |
+
"learning_rate": 1.904610363117095e-05,
|
| 851 |
+
"loss": 0.1318,
|
| 852 |
+
"step": 1170
|
| 853 |
+
},
|
| 854 |
+
{
|
| 855 |
+
"epoch": 0.48148525961440375,
|
| 856 |
+
"grad_norm": 0.18631018698215485,
|
| 857 |
+
"learning_rate": 1.903794369645043e-05,
|
| 858 |
+
"loss": 0.1335,
|
| 859 |
+
"step": 1180
|
| 860 |
+
},
|
| 861 |
+
{
|
| 862 |
+
"epoch": 0.48556564317045803,
|
| 863 |
+
"grad_norm": 1.2286078929901123,
|
| 864 |
+
"learning_rate": 1.9029783761729908e-05,
|
| 865 |
+
"loss": 0.1599,
|
| 866 |
+
"step": 1190
|
| 867 |
+
},
|
| 868 |
+
{
|
| 869 |
+
"epoch": 0.4896460267265123,
|
| 870 |
+
"grad_norm": 0.456785649061203,
|
| 871 |
+
"learning_rate": 1.9021623827009387e-05,
|
| 872 |
+
"loss": 0.0534,
|
| 873 |
+
"step": 1200
|
| 874 |
+
},
|
| 875 |
+
{
|
| 876 |
+
"epoch": 0.4937264102825666,
|
| 877 |
+
"grad_norm": 1.5648113489151,
|
| 878 |
+
"learning_rate": 1.9013463892288863e-05,
|
| 879 |
+
"loss": 0.1173,
|
| 880 |
+
"step": 1210
|
| 881 |
+
},
|
| 882 |
+
{
|
| 883 |
+
"epoch": 0.4978067938386208,
|
| 884 |
+
"grad_norm": 1.4287240505218506,
|
| 885 |
+
"learning_rate": 1.9005303957568342e-05,
|
| 886 |
+
"loss": 0.1784,
|
| 887 |
+
"step": 1220
|
| 888 |
+
},
|
| 889 |
+
{
|
| 890 |
+
"epoch": 0.5018871773946751,
|
| 891 |
+
"grad_norm": 0.4237353205680847,
|
| 892 |
+
"learning_rate": 1.8997144022847818e-05,
|
| 893 |
+
"loss": 0.0898,
|
| 894 |
+
"step": 1230
|
| 895 |
+
},
|
| 896 |
+
{
|
| 897 |
+
"epoch": 0.5059675609507294,
|
| 898 |
+
"grad_norm": 1.7313411235809326,
|
| 899 |
+
"learning_rate": 1.8988984088127297e-05,
|
| 900 |
+
"loss": 0.1186,
|
| 901 |
+
"step": 1240
|
| 902 |
+
},
|
| 903 |
+
{
|
| 904 |
+
"epoch": 0.5100479445067836,
|
| 905 |
+
"grad_norm": 0.0,
|
| 906 |
+
"learning_rate": 1.8980824153406773e-05,
|
| 907 |
+
"loss": 0.2331,
|
| 908 |
+
"step": 1250
|
| 909 |
+
},
|
| 910 |
+
{
|
| 911 |
+
"epoch": 0.5141283280628379,
|
| 912 |
+
"grad_norm": 1.2604000568389893,
|
| 913 |
+
"learning_rate": 1.8972664218686252e-05,
|
| 914 |
+
"loss": 0.1924,
|
| 915 |
+
"step": 1260
|
| 916 |
+
},
|
| 917 |
+
{
|
| 918 |
+
"epoch": 0.5182087116188921,
|
| 919 |
+
"grad_norm": 0.24087439477443695,
|
| 920 |
+
"learning_rate": 1.896450428396573e-05,
|
| 921 |
+
"loss": 0.0633,
|
| 922 |
+
"step": 1270
|
| 923 |
+
},
|
| 924 |
+
{
|
| 925 |
+
"epoch": 0.5222890951749465,
|
| 926 |
+
"grad_norm": 0.14195257425308228,
|
| 927 |
+
"learning_rate": 1.8956344349245207e-05,
|
| 928 |
+
"loss": 0.0914,
|
| 929 |
+
"step": 1280
|
| 930 |
+
},
|
| 931 |
+
{
|
| 932 |
+
"epoch": 0.5263694787310007,
|
| 933 |
+
"grad_norm": 1.0728325843811035,
|
| 934 |
+
"learning_rate": 1.8948184414524686e-05,
|
| 935 |
+
"loss": 0.1142,
|
| 936 |
+
"step": 1290
|
| 937 |
+
},
|
| 938 |
+
{
|
| 939 |
+
"epoch": 0.5304498622870549,
|
| 940 |
+
"grad_norm": 2.187006711959839,
|
| 941 |
+
"learning_rate": 1.894002447980416e-05,
|
| 942 |
+
"loss": 0.162,
|
| 943 |
+
"step": 1300
|
| 944 |
+
},
|
| 945 |
+
{
|
| 946 |
+
"epoch": 0.5345302458431093,
|
| 947 |
+
"grad_norm": 2.7703022956848145,
|
| 948 |
+
"learning_rate": 1.893186454508364e-05,
|
| 949 |
+
"loss": 0.2188,
|
| 950 |
+
"step": 1310
|
| 951 |
+
},
|
| 952 |
+
{
|
| 953 |
+
"epoch": 0.5386106293991635,
|
| 954 |
+
"grad_norm": 1.2225255966186523,
|
| 955 |
+
"learning_rate": 1.892370461036312e-05,
|
| 956 |
+
"loss": 0.1318,
|
| 957 |
+
"step": 1320
|
| 958 |
+
},
|
| 959 |
+
{
|
| 960 |
+
"epoch": 0.5426910129552178,
|
| 961 |
+
"grad_norm": 1.5350176095962524,
|
| 962 |
+
"learning_rate": 1.8915544675642596e-05,
|
| 963 |
+
"loss": 0.1786,
|
| 964 |
+
"step": 1330
|
| 965 |
+
},
|
| 966 |
+
{
|
| 967 |
+
"epoch": 0.546771396511272,
|
| 968 |
+
"grad_norm": 1.9391083717346191,
|
| 969 |
+
"learning_rate": 1.8907384740922075e-05,
|
| 970 |
+
"loss": 0.1432,
|
| 971 |
+
"step": 1340
|
| 972 |
+
},
|
| 973 |
+
{
|
| 974 |
+
"epoch": 0.5508517800673264,
|
| 975 |
+
"grad_norm": 0.9705495834350586,
|
| 976 |
+
"learning_rate": 1.8899224806201554e-05,
|
| 977 |
+
"loss": 0.1274,
|
| 978 |
+
"step": 1350
|
| 979 |
+
},
|
| 980 |
+
{
|
| 981 |
+
"epoch": 0.5549321636233806,
|
| 982 |
+
"grad_norm": 0.8046002984046936,
|
| 983 |
+
"learning_rate": 1.889106487148103e-05,
|
| 984 |
+
"loss": 0.1206,
|
| 985 |
+
"step": 1360
|
| 986 |
+
},
|
| 987 |
+
{
|
| 988 |
+
"epoch": 0.5590125471794348,
|
| 989 |
+
"grad_norm": 1.8676600456237793,
|
| 990 |
+
"learning_rate": 1.8882904936760505e-05,
|
| 991 |
+
"loss": 0.2011,
|
| 992 |
+
"step": 1370
|
| 993 |
+
},
|
| 994 |
+
{
|
| 995 |
+
"epoch": 0.5630929307354892,
|
| 996 |
+
"grad_norm": 2.2367093563079834,
|
| 997 |
+
"learning_rate": 1.8874745002039984e-05,
|
| 998 |
+
"loss": 0.1716,
|
| 999 |
+
"step": 1380
|
| 1000 |
+
},
|
| 1001 |
+
{
|
| 1002 |
+
"epoch": 0.5671733142915434,
|
| 1003 |
+
"grad_norm": 0.0,
|
| 1004 |
+
"learning_rate": 1.8866585067319464e-05,
|
| 1005 |
+
"loss": 0.155,
|
| 1006 |
+
"step": 1390
|
| 1007 |
+
},
|
| 1008 |
+
{
|
| 1009 |
+
"epoch": 0.5712536978475977,
|
| 1010 |
+
"grad_norm": 0.0836629867553711,
|
| 1011 |
+
"learning_rate": 1.885842513259894e-05,
|
| 1012 |
+
"loss": 0.0718,
|
| 1013 |
+
"step": 1400
|
| 1014 |
+
},
|
| 1015 |
+
{
|
| 1016 |
+
"epoch": 0.5753340814036519,
|
| 1017 |
+
"grad_norm": 2.3889925479888916,
|
| 1018 |
+
"learning_rate": 1.885026519787842e-05,
|
| 1019 |
+
"loss": 0.2362,
|
| 1020 |
+
"step": 1410
|
| 1021 |
+
},
|
| 1022 |
+
{
|
| 1023 |
+
"epoch": 0.5794144649597062,
|
| 1024 |
+
"grad_norm": 2.2786920070648193,
|
| 1025 |
+
"learning_rate": 1.8842105263157898e-05,
|
| 1026 |
+
"loss": 0.1976,
|
| 1027 |
+
"step": 1420
|
| 1028 |
+
},
|
| 1029 |
+
{
|
| 1030 |
+
"epoch": 0.5834948485157605,
|
| 1031 |
+
"grad_norm": 1.596222996711731,
|
| 1032 |
+
"learning_rate": 1.8833945328437373e-05,
|
| 1033 |
+
"loss": 0.1621,
|
| 1034 |
+
"step": 1430
|
| 1035 |
+
},
|
| 1036 |
+
{
|
| 1037 |
+
"epoch": 0.5875752320718147,
|
| 1038 |
+
"grad_norm": 1.5035650730133057,
|
| 1039 |
+
"learning_rate": 1.8825785393716853e-05,
|
| 1040 |
+
"loss": 0.1539,
|
| 1041 |
+
"step": 1440
|
| 1042 |
+
},
|
| 1043 |
+
{
|
| 1044 |
+
"epoch": 0.5916556156278691,
|
| 1045 |
+
"grad_norm": 1.4773615598678589,
|
| 1046 |
+
"learning_rate": 1.8817625458996328e-05,
|
| 1047 |
+
"loss": 0.1193,
|
| 1048 |
+
"step": 1450
|
| 1049 |
+
},
|
| 1050 |
+
{
|
| 1051 |
+
"epoch": 0.5957359991839233,
|
| 1052 |
+
"grad_norm": 3.1149489879608154,
|
| 1053 |
+
"learning_rate": 1.8809465524275807e-05,
|
| 1054 |
+
"loss": 0.163,
|
| 1055 |
+
"step": 1460
|
| 1056 |
+
},
|
| 1057 |
+
{
|
| 1058 |
+
"epoch": 0.5998163827399775,
|
| 1059 |
+
"grad_norm": 0.0,
|
| 1060 |
+
"learning_rate": 1.8801305589555287e-05,
|
| 1061 |
+
"loss": 0.1259,
|
| 1062 |
+
"step": 1470
|
| 1063 |
+
},
|
| 1064 |
+
{
|
| 1065 |
+
"epoch": 0.6038967662960318,
|
| 1066 |
+
"grad_norm": 1.1338975429534912,
|
| 1067 |
+
"learning_rate": 1.8793145654834762e-05,
|
| 1068 |
+
"loss": 0.1926,
|
| 1069 |
+
"step": 1480
|
| 1070 |
+
},
|
| 1071 |
+
{
|
| 1072 |
+
"epoch": 0.6079771498520861,
|
| 1073 |
+
"grad_norm": 2.367356300354004,
|
| 1074 |
+
"learning_rate": 1.878498572011424e-05,
|
| 1075 |
+
"loss": 0.087,
|
| 1076 |
+
"step": 1490
|
| 1077 |
+
},
|
| 1078 |
+
{
|
| 1079 |
+
"epoch": 0.6120575334081404,
|
| 1080 |
+
"grad_norm": 0.7989845275878906,
|
| 1081 |
+
"learning_rate": 1.8776825785393717e-05,
|
| 1082 |
+
"loss": 0.164,
|
| 1083 |
+
"step": 1500
|
| 1084 |
+
},
|
| 1085 |
+
{
|
| 1086 |
+
"epoch": 0.6120575334081404,
|
| 1087 |
+
"eval_loss": 0.1599983274936676,
|
| 1088 |
+
"eval_runtime": 5718.9834,
|
| 1089 |
+
"eval_samples_per_second": 0.646,
|
| 1090 |
+
"eval_steps_per_second": 0.323,
|
| 1091 |
+
"step": 1500
|
| 1092 |
+
},
|
| 1093 |
+
{
|
| 1094 |
+
"epoch": 0.6161379169641946,
|
| 1095 |
+
"grad_norm": 0.7103864550590515,
|
| 1096 |
+
"learning_rate": 1.8768665850673196e-05,
|
| 1097 |
+
"loss": 0.1737,
|
| 1098 |
+
"step": 1510
|
| 1099 |
+
},
|
| 1100 |
+
{
|
| 1101 |
+
"epoch": 0.620218300520249,
|
| 1102 |
+
"grad_norm": 1.410314679145813,
|
| 1103 |
+
"learning_rate": 1.8760505915952672e-05,
|
| 1104 |
+
"loss": 0.1538,
|
| 1105 |
+
"step": 1520
|
| 1106 |
+
},
|
| 1107 |
+
{
|
| 1108 |
+
"epoch": 0.6242986840763032,
|
| 1109 |
+
"grad_norm": 2.189002275466919,
|
| 1110 |
+
"learning_rate": 1.875234598123215e-05,
|
| 1111 |
+
"loss": 0.1662,
|
| 1112 |
+
"step": 1530
|
| 1113 |
+
},
|
| 1114 |
+
{
|
| 1115 |
+
"epoch": 0.6283790676323574,
|
| 1116 |
+
"grad_norm": 2.2174313068389893,
|
| 1117 |
+
"learning_rate": 1.874418604651163e-05,
|
| 1118 |
+
"loss": 0.1765,
|
| 1119 |
+
"step": 1540
|
| 1120 |
+
},
|
| 1121 |
+
{
|
| 1122 |
+
"epoch": 0.6324594511884117,
|
| 1123 |
+
"grad_norm": 0.0,
|
| 1124 |
+
"learning_rate": 1.873602611179111e-05,
|
| 1125 |
+
"loss": 0.1565,
|
| 1126 |
+
"step": 1550
|
| 1127 |
+
},
|
| 1128 |
+
{
|
| 1129 |
+
"epoch": 0.636539834744466,
|
| 1130 |
+
"grad_norm": 2.8284146785736084,
|
| 1131 |
+
"learning_rate": 1.8727866177070585e-05,
|
| 1132 |
+
"loss": 0.2672,
|
| 1133 |
+
"step": 1560
|
| 1134 |
+
},
|
| 1135 |
+
{
|
| 1136 |
+
"epoch": 0.6406202183005203,
|
| 1137 |
+
"grad_norm": 0.0,
|
| 1138 |
+
"learning_rate": 1.871970624235006e-05,
|
| 1139 |
+
"loss": 0.0889,
|
| 1140 |
+
"step": 1570
|
| 1141 |
+
},
|
| 1142 |
+
{
|
| 1143 |
+
"epoch": 0.6447006018565745,
|
| 1144 |
+
"grad_norm": 1.36979341506958,
|
| 1145 |
+
"learning_rate": 1.871154630762954e-05,
|
| 1146 |
+
"loss": 0.0965,
|
| 1147 |
+
"step": 1580
|
| 1148 |
+
},
|
| 1149 |
+
{
|
| 1150 |
+
"epoch": 0.6487809854126287,
|
| 1151 |
+
"grad_norm": 2.8368990421295166,
|
| 1152 |
+
"learning_rate": 1.870338637290902e-05,
|
| 1153 |
+
"loss": 0.1882,
|
| 1154 |
+
"step": 1590
|
| 1155 |
+
},
|
| 1156 |
+
{
|
| 1157 |
+
"epoch": 0.6528613689686831,
|
| 1158 |
+
"grad_norm": 1.439751148223877,
|
| 1159 |
+
"learning_rate": 1.8695226438188495e-05,
|
| 1160 |
+
"loss": 0.1345,
|
| 1161 |
+
"step": 1600
|
| 1162 |
+
},
|
| 1163 |
+
{
|
| 1164 |
+
"epoch": 0.6569417525247373,
|
| 1165 |
+
"grad_norm": 1.7981996536254883,
|
| 1166 |
+
"learning_rate": 1.8687066503467974e-05,
|
| 1167 |
+
"loss": 0.2021,
|
| 1168 |
+
"step": 1610
|
| 1169 |
+
},
|
| 1170 |
+
{
|
| 1171 |
+
"epoch": 0.6610221360807916,
|
| 1172 |
+
"grad_norm": 2.474820375442505,
|
| 1173 |
+
"learning_rate": 1.8678906568747453e-05,
|
| 1174 |
+
"loss": 0.2709,
|
| 1175 |
+
"step": 1620
|
| 1176 |
+
},
|
| 1177 |
+
{
|
| 1178 |
+
"epoch": 0.6651025196368459,
|
| 1179 |
+
"grad_norm": 0.5656393766403198,
|
| 1180 |
+
"learning_rate": 1.867074663402693e-05,
|
| 1181 |
+
"loss": 0.1114,
|
| 1182 |
+
"step": 1630
|
| 1183 |
+
},
|
| 1184 |
+
{
|
| 1185 |
+
"epoch": 0.6691829031929001,
|
| 1186 |
+
"grad_norm": 2.1718122959136963,
|
| 1187 |
+
"learning_rate": 1.8662586699306405e-05,
|
| 1188 |
+
"loss": 0.1922,
|
| 1189 |
+
"step": 1640
|
| 1190 |
+
},
|
| 1191 |
+
{
|
| 1192 |
+
"epoch": 0.6732632867489544,
|
| 1193 |
+
"grad_norm": 1.9503840208053589,
|
| 1194 |
+
"learning_rate": 1.8654426764585884e-05,
|
| 1195 |
+
"loss": 0.1791,
|
| 1196 |
+
"step": 1650
|
| 1197 |
+
},
|
| 1198 |
+
{
|
| 1199 |
+
"epoch": 0.6773436703050086,
|
| 1200 |
+
"grad_norm": 0.5494780540466309,
|
| 1201 |
+
"learning_rate": 1.8646266829865363e-05,
|
| 1202 |
+
"loss": 0.1891,
|
| 1203 |
+
"step": 1660
|
| 1204 |
+
},
|
| 1205 |
+
{
|
| 1206 |
+
"epoch": 0.681424053861063,
|
| 1207 |
+
"grad_norm": 2.120107650756836,
|
| 1208 |
+
"learning_rate": 1.8638106895144842e-05,
|
| 1209 |
+
"loss": 0.1791,
|
| 1210 |
+
"step": 1670
|
| 1211 |
+
},
|
| 1212 |
+
{
|
| 1213 |
+
"epoch": 0.6855044374171172,
|
| 1214 |
+
"grad_norm": 1.1772249937057495,
|
| 1215 |
+
"learning_rate": 1.8629946960424318e-05,
|
| 1216 |
+
"loss": 0.1071,
|
| 1217 |
+
"step": 1680
|
| 1218 |
+
},
|
| 1219 |
+
{
|
| 1220 |
+
"epoch": 0.6895848209731715,
|
| 1221 |
+
"grad_norm": 0.5621774792671204,
|
| 1222 |
+
"learning_rate": 1.8621787025703797e-05,
|
| 1223 |
+
"loss": 0.1136,
|
| 1224 |
+
"step": 1690
|
| 1225 |
+
},
|
| 1226 |
+
{
|
| 1227 |
+
"epoch": 0.6936652045292258,
|
| 1228 |
+
"grad_norm": 1.0332114696502686,
|
| 1229 |
+
"learning_rate": 1.8613627090983273e-05,
|
| 1230 |
+
"loss": 0.2104,
|
| 1231 |
+
"step": 1700
|
| 1232 |
+
},
|
| 1233 |
+
{
|
| 1234 |
+
"epoch": 0.69774558808528,
|
| 1235 |
+
"grad_norm": 0.27499428391456604,
|
| 1236 |
+
"learning_rate": 1.8605467156262752e-05,
|
| 1237 |
+
"loss": 0.169,
|
| 1238 |
+
"step": 1710
|
| 1239 |
+
},
|
| 1240 |
+
{
|
| 1241 |
+
"epoch": 0.7018259716413343,
|
| 1242 |
+
"grad_norm": 2.5944690704345703,
|
| 1243 |
+
"learning_rate": 1.8597307221542228e-05,
|
| 1244 |
+
"loss": 0.1507,
|
| 1245 |
+
"step": 1720
|
| 1246 |
+
},
|
| 1247 |
+
{
|
| 1248 |
+
"epoch": 0.7059063551973885,
|
| 1249 |
+
"grad_norm": 1.3817540407180786,
|
| 1250 |
+
"learning_rate": 1.8589147286821707e-05,
|
| 1251 |
+
"loss": 0.1391,
|
| 1252 |
+
"step": 1730
|
| 1253 |
+
},
|
| 1254 |
+
{
|
| 1255 |
+
"epoch": 0.7099867387534429,
|
| 1256 |
+
"grad_norm": 1.1489579677581787,
|
| 1257 |
+
"learning_rate": 1.8580987352101186e-05,
|
| 1258 |
+
"loss": 0.0891,
|
| 1259 |
+
"step": 1740
|
| 1260 |
+
},
|
| 1261 |
+
{
|
| 1262 |
+
"epoch": 0.7140671223094971,
|
| 1263 |
+
"grad_norm": 1.933108925819397,
|
| 1264 |
+
"learning_rate": 1.8572827417380662e-05,
|
| 1265 |
+
"loss": 0.2514,
|
| 1266 |
+
"step": 1750
|
| 1267 |
+
},
|
| 1268 |
+
{
|
| 1269 |
+
"epoch": 0.7181475058655513,
|
| 1270 |
+
"grad_norm": 1.160273551940918,
|
| 1271 |
+
"learning_rate": 1.8564667482660138e-05,
|
| 1272 |
+
"loss": 0.1934,
|
| 1273 |
+
"step": 1760
|
| 1274 |
+
},
|
| 1275 |
+
{
|
| 1276 |
+
"epoch": 0.7222278894216057,
|
| 1277 |
+
"grad_norm": 0.7756880521774292,
|
| 1278 |
+
"learning_rate": 1.8556507547939617e-05,
|
| 1279 |
+
"loss": 0.1565,
|
| 1280 |
+
"step": 1770
|
| 1281 |
+
},
|
| 1282 |
+
{
|
| 1283 |
+
"epoch": 0.7263082729776599,
|
| 1284 |
+
"grad_norm": 0.7927201390266418,
|
| 1285 |
+
"learning_rate": 1.8548347613219096e-05,
|
| 1286 |
+
"loss": 0.1851,
|
| 1287 |
+
"step": 1780
|
| 1288 |
+
},
|
| 1289 |
+
{
|
| 1290 |
+
"epoch": 0.7303886565337142,
|
| 1291 |
+
"grad_norm": 1.8288319110870361,
|
| 1292 |
+
"learning_rate": 1.8540187678498575e-05,
|
| 1293 |
+
"loss": 0.1792,
|
| 1294 |
+
"step": 1790
|
| 1295 |
+
},
|
| 1296 |
+
{
|
| 1297 |
+
"epoch": 0.7344690400897684,
|
| 1298 |
+
"grad_norm": 0.6128740310668945,
|
| 1299 |
+
"learning_rate": 1.853202774377805e-05,
|
| 1300 |
+
"loss": 0.1863,
|
| 1301 |
+
"step": 1800
|
| 1302 |
+
},
|
| 1303 |
+
{
|
| 1304 |
+
"epoch": 0.7385494236458227,
|
| 1305 |
+
"grad_norm": 0.41025951504707336,
|
| 1306 |
+
"learning_rate": 1.852386780905753e-05,
|
| 1307 |
+
"loss": 0.1634,
|
| 1308 |
+
"step": 1810
|
| 1309 |
+
},
|
| 1310 |
+
{
|
| 1311 |
+
"epoch": 0.742629807201877,
|
| 1312 |
+
"grad_norm": 0.1404421627521515,
|
| 1313 |
+
"learning_rate": 1.851570787433701e-05,
|
| 1314 |
+
"loss": 0.1592,
|
| 1315 |
+
"step": 1820
|
| 1316 |
+
},
|
| 1317 |
+
{
|
| 1318 |
+
"epoch": 0.7467101907579312,
|
| 1319 |
+
"grad_norm": 0.4112943410873413,
|
| 1320 |
+
"learning_rate": 1.8507547939616485e-05,
|
| 1321 |
+
"loss": 0.1009,
|
| 1322 |
+
"step": 1830
|
| 1323 |
+
},
|
| 1324 |
+
{
|
| 1325 |
+
"epoch": 0.7507905743139855,
|
| 1326 |
+
"grad_norm": 1.8249828815460205,
|
| 1327 |
+
"learning_rate": 1.849938800489596e-05,
|
| 1328 |
+
"loss": 0.142,
|
| 1329 |
+
"step": 1840
|
| 1330 |
+
},
|
| 1331 |
+
{
|
| 1332 |
+
"epoch": 0.7548709578700398,
|
| 1333 |
+
"grad_norm": 1.3493293523788452,
|
| 1334 |
+
"learning_rate": 1.849122807017544e-05,
|
| 1335 |
+
"loss": 0.1564,
|
| 1336 |
+
"step": 1850
|
| 1337 |
+
},
|
| 1338 |
+
{
|
| 1339 |
+
"epoch": 0.7589513414260941,
|
| 1340 |
+
"grad_norm": 1.402621865272522,
|
| 1341 |
+
"learning_rate": 1.848306813545492e-05,
|
| 1342 |
+
"loss": 0.1766,
|
| 1343 |
+
"step": 1860
|
| 1344 |
+
},
|
| 1345 |
+
{
|
| 1346 |
+
"epoch": 0.7630317249821483,
|
| 1347 |
+
"grad_norm": 0.939300000667572,
|
| 1348 |
+
"learning_rate": 1.8474908200734395e-05,
|
| 1349 |
+
"loss": 0.1089,
|
| 1350 |
+
"step": 1870
|
| 1351 |
+
},
|
| 1352 |
+
{
|
| 1353 |
+
"epoch": 0.7671121085382026,
|
| 1354 |
+
"grad_norm": 1.1979037523269653,
|
| 1355 |
+
"learning_rate": 1.8466748266013874e-05,
|
| 1356 |
+
"loss": 0.1941,
|
| 1357 |
+
"step": 1880
|
| 1358 |
+
},
|
| 1359 |
+
{
|
| 1360 |
+
"epoch": 0.7711924920942569,
|
| 1361 |
+
"grad_norm": 0.6373042464256287,
|
| 1362 |
+
"learning_rate": 1.8458588331293353e-05,
|
| 1363 |
+
"loss": 0.1585,
|
| 1364 |
+
"step": 1890
|
| 1365 |
+
},
|
| 1366 |
+
{
|
| 1367 |
+
"epoch": 0.7752728756503111,
|
| 1368 |
+
"grad_norm": 0.9635875225067139,
|
| 1369 |
+
"learning_rate": 1.845042839657283e-05,
|
| 1370 |
+
"loss": 0.1157,
|
| 1371 |
+
"step": 1900
|
| 1372 |
+
},
|
| 1373 |
+
{
|
| 1374 |
+
"epoch": 0.7793532592063654,
|
| 1375 |
+
"grad_norm": 1.4881830215454102,
|
| 1376 |
+
"learning_rate": 1.8442268461852308e-05,
|
| 1377 |
+
"loss": 0.1192,
|
| 1378 |
+
"step": 1910
|
| 1379 |
+
},
|
| 1380 |
+
{
|
| 1381 |
+
"epoch": 0.7834336427624197,
|
| 1382 |
+
"grad_norm": 0.6800144910812378,
|
| 1383 |
+
"learning_rate": 1.8434108527131783e-05,
|
| 1384 |
+
"loss": 0.0905,
|
| 1385 |
+
"step": 1920
|
| 1386 |
+
},
|
| 1387 |
+
{
|
| 1388 |
+
"epoch": 0.7875140263184739,
|
| 1389 |
+
"grad_norm": 0.3224925398826599,
|
| 1390 |
+
"learning_rate": 1.8425948592411263e-05,
|
| 1391 |
+
"loss": 0.1117,
|
| 1392 |
+
"step": 1930
|
| 1393 |
+
},
|
| 1394 |
+
{
|
| 1395 |
+
"epoch": 0.7915944098745282,
|
| 1396 |
+
"grad_norm": 2.013815402984619,
|
| 1397 |
+
"learning_rate": 1.8417788657690742e-05,
|
| 1398 |
+
"loss": 0.1974,
|
| 1399 |
+
"step": 1940
|
| 1400 |
+
},
|
| 1401 |
+
{
|
| 1402 |
+
"epoch": 0.7956747934305824,
|
| 1403 |
+
"grad_norm": 2.8408901691436768,
|
| 1404 |
+
"learning_rate": 1.8409628722970217e-05,
|
| 1405 |
+
"loss": 0.1484,
|
| 1406 |
+
"step": 1950
|
| 1407 |
+
},
|
| 1408 |
+
{
|
| 1409 |
+
"epoch": 0.7997551769866368,
|
| 1410 |
+
"grad_norm": 1.5153237581253052,
|
| 1411 |
+
"learning_rate": 1.8401468788249693e-05,
|
| 1412 |
+
"loss": 0.2739,
|
| 1413 |
+
"step": 1960
|
| 1414 |
+
},
|
| 1415 |
+
{
|
| 1416 |
+
"epoch": 0.803835560542691,
|
| 1417 |
+
"grad_norm": 0.0,
|
| 1418 |
+
"learning_rate": 1.8393308853529172e-05,
|
| 1419 |
+
"loss": 0.093,
|
| 1420 |
+
"step": 1970
|
| 1421 |
+
},
|
| 1422 |
+
{
|
| 1423 |
+
"epoch": 0.8079159440987452,
|
| 1424 |
+
"grad_norm": 3.2609169483184814,
|
| 1425 |
+
"learning_rate": 1.838514891880865e-05,
|
| 1426 |
+
"loss": 0.1349,
|
| 1427 |
+
"step": 1980
|
| 1428 |
+
},
|
| 1429 |
+
{
|
| 1430 |
+
"epoch": 0.8119963276547996,
|
| 1431 |
+
"grad_norm": 1.1488144397735596,
|
| 1432 |
+
"learning_rate": 1.8376988984088127e-05,
|
| 1433 |
+
"loss": 0.1121,
|
| 1434 |
+
"step": 1990
|
| 1435 |
+
},
|
| 1436 |
+
{
|
| 1437 |
+
"epoch": 0.8160767112108538,
|
| 1438 |
+
"grad_norm": 0.609579861164093,
|
| 1439 |
+
"learning_rate": 1.8368829049367606e-05,
|
| 1440 |
+
"loss": 0.1625,
|
| 1441 |
+
"step": 2000
|
| 1442 |
+
},
|
| 1443 |
+
{
|
| 1444 |
+
"epoch": 0.8160767112108538,
|
| 1445 |
+
"eval_loss": 0.16013823449611664,
|
| 1446 |
+
"eval_runtime": 5718.8002,
|
| 1447 |
+
"eval_samples_per_second": 0.646,
|
| 1448 |
+
"eval_steps_per_second": 0.323,
|
| 1449 |
+
"step": 2000
|
| 1450 |
+
},
|
| 1451 |
+
{
|
| 1452 |
+
"epoch": 0.8201570947669081,
|
| 1453 |
+
"grad_norm": 0.7778828144073486,
|
| 1454 |
+
"learning_rate": 1.8360669114647086e-05,
|
| 1455 |
+
"loss": 0.1858,
|
| 1456 |
+
"step": 2010
|
| 1457 |
+
},
|
| 1458 |
+
{
|
| 1459 |
+
"epoch": 0.8242374783229623,
|
| 1460 |
+
"grad_norm": 1.5061280727386475,
|
| 1461 |
+
"learning_rate": 1.8352509179926565e-05,
|
| 1462 |
+
"loss": 0.1961,
|
| 1463 |
+
"step": 2020
|
| 1464 |
+
},
|
| 1465 |
+
{
|
| 1466 |
+
"epoch": 0.8283178618790167,
|
| 1467 |
+
"grad_norm": 1.2525917291641235,
|
| 1468 |
+
"learning_rate": 1.834434924520604e-05,
|
| 1469 |
+
"loss": 0.2311,
|
| 1470 |
+
"step": 2030
|
| 1471 |
+
},
|
| 1472 |
+
{
|
| 1473 |
+
"epoch": 0.8323982454350709,
|
| 1474 |
+
"grad_norm": 0.5317162871360779,
|
| 1475 |
+
"learning_rate": 1.8336189310485516e-05,
|
| 1476 |
+
"loss": 0.0839,
|
| 1477 |
+
"step": 2040
|
| 1478 |
+
},
|
| 1479 |
+
{
|
| 1480 |
+
"epoch": 0.8364786289911251,
|
| 1481 |
+
"grad_norm": 0.0,
|
| 1482 |
+
"learning_rate": 1.8328029375764995e-05,
|
| 1483 |
+
"loss": 0.2016,
|
| 1484 |
+
"step": 2050
|
| 1485 |
+
},
|
| 1486 |
+
{
|
| 1487 |
+
"epoch": 0.8405590125471795,
|
| 1488 |
+
"grad_norm": 0.5220463275909424,
|
| 1489 |
+
"learning_rate": 1.8319869441044474e-05,
|
| 1490 |
+
"loss": 0.1013,
|
| 1491 |
+
"step": 2060
|
| 1492 |
+
},
|
| 1493 |
+
{
|
| 1494 |
+
"epoch": 0.8446393961032337,
|
| 1495 |
+
"grad_norm": 0.755527913570404,
|
| 1496 |
+
"learning_rate": 1.831170950632395e-05,
|
| 1497 |
+
"loss": 0.2339,
|
| 1498 |
+
"step": 2070
|
| 1499 |
+
},
|
| 1500 |
+
{
|
| 1501 |
+
"epoch": 0.848719779659288,
|
| 1502 |
+
"grad_norm": 1.3820732831954956,
|
| 1503 |
+
"learning_rate": 1.830354957160343e-05,
|
| 1504 |
+
"loss": 0.1481,
|
| 1505 |
+
"step": 2080
|
| 1506 |
+
},
|
| 1507 |
+
{
|
| 1508 |
+
"epoch": 0.8528001632153422,
|
| 1509 |
+
"grad_norm": 1.9282928705215454,
|
| 1510 |
+
"learning_rate": 1.8295389636882905e-05,
|
| 1511 |
+
"loss": 0.1154,
|
| 1512 |
+
"step": 2090
|
| 1513 |
+
},
|
| 1514 |
+
{
|
| 1515 |
+
"epoch": 0.8568805467713965,
|
| 1516 |
+
"grad_norm": 1.7541260719299316,
|
| 1517 |
+
"learning_rate": 1.8287229702162384e-05,
|
| 1518 |
+
"loss": 0.1828,
|
| 1519 |
+
"step": 2100
|
| 1520 |
+
},
|
| 1521 |
+
{
|
| 1522 |
+
"epoch": 0.8609609303274508,
|
| 1523 |
+
"grad_norm": 1.4934720993041992,
|
| 1524 |
+
"learning_rate": 1.827906976744186e-05,
|
| 1525 |
+
"loss": 0.1316,
|
| 1526 |
+
"step": 2110
|
| 1527 |
+
},
|
| 1528 |
+
{
|
| 1529 |
+
"epoch": 0.865041313883505,
|
| 1530 |
+
"grad_norm": 0.8395527601242065,
|
| 1531 |
+
"learning_rate": 1.827090983272134e-05,
|
| 1532 |
+
"loss": 0.1496,
|
| 1533 |
+
"step": 2120
|
| 1534 |
+
},
|
| 1535 |
+
{
|
| 1536 |
+
"epoch": 0.8691216974395594,
|
| 1537 |
+
"grad_norm": 3.2863991260528564,
|
| 1538 |
+
"learning_rate": 1.8262749898000818e-05,
|
| 1539 |
+
"loss": 0.1944,
|
| 1540 |
+
"step": 2130
|
| 1541 |
+
},
|
| 1542 |
+
{
|
| 1543 |
+
"epoch": 0.8732020809956136,
|
| 1544 |
+
"grad_norm": 0.6508553624153137,
|
| 1545 |
+
"learning_rate": 1.8254589963280297e-05,
|
| 1546 |
+
"loss": 0.1392,
|
| 1547 |
+
"step": 2140
|
| 1548 |
+
},
|
| 1549 |
+
{
|
| 1550 |
+
"epoch": 0.8772824645516678,
|
| 1551 |
+
"grad_norm": 0.0,
|
| 1552 |
+
"learning_rate": 1.8246430028559773e-05,
|
| 1553 |
+
"loss": 0.1707,
|
| 1554 |
+
"step": 2150
|
| 1555 |
+
},
|
| 1556 |
+
{
|
| 1557 |
+
"epoch": 0.8813628481077221,
|
| 1558 |
+
"grad_norm": 1.3363920450210571,
|
| 1559 |
+
"learning_rate": 1.823827009383925e-05,
|
| 1560 |
+
"loss": 0.1975,
|
| 1561 |
+
"step": 2160
|
| 1562 |
+
},
|
| 1563 |
+
{
|
| 1564 |
+
"epoch": 0.8854432316637764,
|
| 1565 |
+
"grad_norm": 0.38948386907577515,
|
| 1566 |
+
"learning_rate": 1.8230110159118728e-05,
|
| 1567 |
+
"loss": 0.1374,
|
| 1568 |
+
"step": 2170
|
| 1569 |
+
},
|
| 1570 |
+
{
|
| 1571 |
+
"epoch": 0.8895236152198307,
|
| 1572 |
+
"grad_norm": 1.5190832614898682,
|
| 1573 |
+
"learning_rate": 1.8221950224398207e-05,
|
| 1574 |
+
"loss": 0.153,
|
| 1575 |
+
"step": 2180
|
| 1576 |
+
},
|
| 1577 |
+
{
|
| 1578 |
+
"epoch": 0.8936039987758849,
|
| 1579 |
+
"grad_norm": 1.8394863605499268,
|
| 1580 |
+
"learning_rate": 1.8213790289677683e-05,
|
| 1581 |
+
"loss": 0.207,
|
| 1582 |
+
"step": 2190
|
| 1583 |
+
},
|
| 1584 |
+
{
|
| 1585 |
+
"epoch": 0.8976843823319393,
|
| 1586 |
+
"grad_norm": 1.5787442922592163,
|
| 1587 |
+
"learning_rate": 1.8205630354957162e-05,
|
| 1588 |
+
"loss": 0.1856,
|
| 1589 |
+
"step": 2200
|
| 1590 |
+
},
|
| 1591 |
+
{
|
| 1592 |
+
"epoch": 0.9017647658879935,
|
| 1593 |
+
"grad_norm": 0.7729844450950623,
|
| 1594 |
+
"learning_rate": 1.819747042023664e-05,
|
| 1595 |
+
"loss": 0.1998,
|
| 1596 |
+
"step": 2210
|
| 1597 |
+
},
|
| 1598 |
+
{
|
| 1599 |
+
"epoch": 0.9058451494440477,
|
| 1600 |
+
"grad_norm": 1.661285400390625,
|
| 1601 |
+
"learning_rate": 1.8189310485516117e-05,
|
| 1602 |
+
"loss": 0.1606,
|
| 1603 |
+
"step": 2220
|
| 1604 |
+
},
|
| 1605 |
+
{
|
| 1606 |
+
"epoch": 0.909925533000102,
|
| 1607 |
+
"grad_norm": 3.445115804672241,
|
| 1608 |
+
"learning_rate": 1.8181150550795593e-05,
|
| 1609 |
+
"loss": 0.1219,
|
| 1610 |
+
"step": 2230
|
| 1611 |
+
},
|
| 1612 |
+
{
|
| 1613 |
+
"epoch": 0.9140059165561563,
|
| 1614 |
+
"grad_norm": 1.5525267124176025,
|
| 1615 |
+
"learning_rate": 1.8172990616075072e-05,
|
| 1616 |
+
"loss": 0.1664,
|
| 1617 |
+
"step": 2240
|
| 1618 |
+
},
|
| 1619 |
+
{
|
| 1620 |
+
"epoch": 0.9180863001122106,
|
| 1621 |
+
"grad_norm": 0.8300206661224365,
|
| 1622 |
+
"learning_rate": 1.816483068135455e-05,
|
| 1623 |
+
"loss": 0.1576,
|
| 1624 |
+
"step": 2250
|
| 1625 |
+
},
|
| 1626 |
+
{
|
| 1627 |
+
"epoch": 0.9221666836682648,
|
| 1628 |
+
"grad_norm": 1.2452751398086548,
|
| 1629 |
+
"learning_rate": 1.815667074663403e-05,
|
| 1630 |
+
"loss": 0.1384,
|
| 1631 |
+
"step": 2260
|
| 1632 |
+
},
|
| 1633 |
+
{
|
| 1634 |
+
"epoch": 0.926247067224319,
|
| 1635 |
+
"grad_norm": 1.6318614482879639,
|
| 1636 |
+
"learning_rate": 1.8148510811913506e-05,
|
| 1637 |
+
"loss": 0.1932,
|
| 1638 |
+
"step": 2270
|
| 1639 |
+
},
|
| 1640 |
+
{
|
| 1641 |
+
"epoch": 0.9303274507803734,
|
| 1642 |
+
"grad_norm": 1.384819507598877,
|
| 1643 |
+
"learning_rate": 1.8140350877192985e-05,
|
| 1644 |
+
"loss": 0.1398,
|
| 1645 |
+
"step": 2280
|
| 1646 |
+
},
|
| 1647 |
+
{
|
| 1648 |
+
"epoch": 0.9344078343364276,
|
| 1649 |
+
"grad_norm": 0.0,
|
| 1650 |
+
"learning_rate": 1.813219094247246e-05,
|
| 1651 |
+
"loss": 0.1721,
|
| 1652 |
+
"step": 2290
|
| 1653 |
+
},
|
| 1654 |
+
{
|
| 1655 |
+
"epoch": 0.9384882178924819,
|
| 1656 |
+
"grad_norm": 0.0,
|
| 1657 |
+
"learning_rate": 1.812403100775194e-05,
|
| 1658 |
+
"loss": 0.1654,
|
| 1659 |
+
"step": 2300
|
| 1660 |
+
},
|
| 1661 |
+
{
|
| 1662 |
+
"epoch": 0.9425686014485362,
|
| 1663 |
+
"grad_norm": 0.7114019393920898,
|
| 1664 |
+
"learning_rate": 1.8115871073031416e-05,
|
| 1665 |
+
"loss": 0.1158,
|
| 1666 |
+
"step": 2310
|
| 1667 |
+
},
|
| 1668 |
+
{
|
| 1669 |
+
"epoch": 0.9466489850045904,
|
| 1670 |
+
"grad_norm": 2.6222026348114014,
|
| 1671 |
+
"learning_rate": 1.8107711138310895e-05,
|
| 1672 |
+
"loss": 0.1539,
|
| 1673 |
+
"step": 2320
|
| 1674 |
+
},
|
| 1675 |
+
{
|
| 1676 |
+
"epoch": 0.9507293685606447,
|
| 1677 |
+
"grad_norm": 1.1143105030059814,
|
| 1678 |
+
"learning_rate": 1.8099551203590374e-05,
|
| 1679 |
+
"loss": 0.1768,
|
| 1680 |
+
"step": 2330
|
| 1681 |
+
},
|
| 1682 |
+
{
|
| 1683 |
+
"epoch": 0.9548097521166989,
|
| 1684 |
+
"grad_norm": 0.3291604518890381,
|
| 1685 |
+
"learning_rate": 1.809139126886985e-05,
|
| 1686 |
+
"loss": 0.0838,
|
| 1687 |
+
"step": 2340
|
| 1688 |
+
},
|
| 1689 |
+
{
|
| 1690 |
+
"epoch": 0.9588901356727533,
|
| 1691 |
+
"grad_norm": 0.5898478031158447,
|
| 1692 |
+
"learning_rate": 1.808323133414933e-05,
|
| 1693 |
+
"loss": 0.1646,
|
| 1694 |
+
"step": 2350
|
| 1695 |
+
},
|
| 1696 |
+
{
|
| 1697 |
+
"epoch": 0.9629705192288075,
|
| 1698 |
+
"grad_norm": 1.2440063953399658,
|
| 1699 |
+
"learning_rate": 1.8075071399428805e-05,
|
| 1700 |
+
"loss": 0.1116,
|
| 1701 |
+
"step": 2360
|
| 1702 |
+
},
|
| 1703 |
+
{
|
| 1704 |
+
"epoch": 0.9670509027848618,
|
| 1705 |
+
"grad_norm": 1.5655691623687744,
|
| 1706 |
+
"learning_rate": 1.8066911464708284e-05,
|
| 1707 |
+
"loss": 0.1588,
|
| 1708 |
+
"step": 2370
|
| 1709 |
+
},
|
| 1710 |
+
{
|
| 1711 |
+
"epoch": 0.9711312863409161,
|
| 1712 |
+
"grad_norm": 0.8769559264183044,
|
| 1713 |
+
"learning_rate": 1.8058751529987763e-05,
|
| 1714 |
+
"loss": 0.1125,
|
| 1715 |
+
"step": 2380
|
| 1716 |
+
},
|
| 1717 |
+
{
|
| 1718 |
+
"epoch": 0.9752116698969703,
|
| 1719 |
+
"grad_norm": 0.835755467414856,
|
| 1720 |
+
"learning_rate": 1.805059159526724e-05,
|
| 1721 |
+
"loss": 0.1997,
|
| 1722 |
+
"step": 2390
|
| 1723 |
+
},
|
| 1724 |
+
{
|
| 1725 |
+
"epoch": 0.9792920534530246,
|
| 1726 |
+
"grad_norm": 2.1245999336242676,
|
| 1727 |
+
"learning_rate": 1.8042431660546718e-05,
|
| 1728 |
+
"loss": 0.1586,
|
| 1729 |
+
"step": 2400
|
| 1730 |
+
},
|
| 1731 |
+
{
|
| 1732 |
+
"epoch": 0.9833724370090788,
|
| 1733 |
+
"grad_norm": 0.8960317373275757,
|
| 1734 |
+
"learning_rate": 1.8034271725826197e-05,
|
| 1735 |
+
"loss": 0.1208,
|
| 1736 |
+
"step": 2410
|
| 1737 |
+
},
|
| 1738 |
+
{
|
| 1739 |
+
"epoch": 0.9874528205651332,
|
| 1740 |
+
"grad_norm": 0.6613627076148987,
|
| 1741 |
+
"learning_rate": 1.8026111791105673e-05,
|
| 1742 |
+
"loss": 0.2237,
|
| 1743 |
+
"step": 2420
|
| 1744 |
+
},
|
| 1745 |
+
{
|
| 1746 |
+
"epoch": 0.9915332041211874,
|
| 1747 |
+
"grad_norm": 2.5867104530334473,
|
| 1748 |
+
"learning_rate": 1.801795185638515e-05,
|
| 1749 |
+
"loss": 0.1689,
|
| 1750 |
+
"step": 2430
|
| 1751 |
+
},
|
| 1752 |
+
{
|
| 1753 |
+
"epoch": 0.9956135876772416,
|
| 1754 |
+
"grad_norm": 1.074992060661316,
|
| 1755 |
+
"learning_rate": 1.8009791921664628e-05,
|
| 1756 |
+
"loss": 0.1577,
|
| 1757 |
+
"step": 2440
|
| 1758 |
+
},
|
| 1759 |
+
{
|
| 1760 |
+
"epoch": 0.999693971233296,
|
| 1761 |
+
"grad_norm": 1.3898792266845703,
|
| 1762 |
+
"learning_rate": 1.8001631986944107e-05,
|
| 1763 |
+
"loss": 0.169,
|
| 1764 |
+
"step": 2450
|
| 1765 |
+
},
|
| 1766 |
+
{
|
| 1767 |
+
"epoch": 1.0036723452004488,
|
| 1768 |
+
"grad_norm": 1.4916174411773682,
|
| 1769 |
+
"learning_rate": 1.7993472052223582e-05,
|
| 1770 |
+
"loss": 0.1197,
|
| 1771 |
+
"step": 2460
|
| 1772 |
+
},
|
| 1773 |
+
{
|
| 1774 |
+
"epoch": 1.0077527287565031,
|
| 1775 |
+
"grad_norm": 0.7944161295890808,
|
| 1776 |
+
"learning_rate": 1.798531211750306e-05,
|
| 1777 |
+
"loss": 0.1644,
|
| 1778 |
+
"step": 2470
|
| 1779 |
+
},
|
| 1780 |
+
{
|
| 1781 |
+
"epoch": 1.0118331123125575,
|
| 1782 |
+
"grad_norm": 1.5463371276855469,
|
| 1783 |
+
"learning_rate": 1.797715218278254e-05,
|
| 1784 |
+
"loss": 0.2344,
|
| 1785 |
+
"step": 2480
|
| 1786 |
+
},
|
| 1787 |
+
{
|
| 1788 |
+
"epoch": 1.0159134958686116,
|
| 1789 |
+
"grad_norm": 2.5019683837890625,
|
| 1790 |
+
"learning_rate": 1.7968992248062016e-05,
|
| 1791 |
+
"loss": 0.1641,
|
| 1792 |
+
"step": 2490
|
| 1793 |
+
},
|
| 1794 |
+
{
|
| 1795 |
+
"epoch": 1.019993879424666,
|
| 1796 |
+
"grad_norm": 0.33804982900619507,
|
| 1797 |
+
"learning_rate": 1.7960832313341496e-05,
|
| 1798 |
+
"loss": 0.105,
|
| 1799 |
+
"step": 2500
|
| 1800 |
+
},
|
| 1801 |
+
{
|
| 1802 |
+
"epoch": 1.019993879424666,
|
| 1803 |
+
"eval_loss": 0.15810872614383698,
|
| 1804 |
+
"eval_runtime": 5718.7353,
|
| 1805 |
+
"eval_samples_per_second": 0.646,
|
| 1806 |
+
"eval_steps_per_second": 0.323,
|
| 1807 |
+
"step": 2500
|
| 1808 |
+
},
|
| 1809 |
+
{
|
| 1810 |
+
"epoch": 1.0240742629807202,
|
| 1811 |
+
"grad_norm": 0.44688037037849426,
|
| 1812 |
+
"learning_rate": 1.795267237862097e-05,
|
| 1813 |
+
"loss": 0.0821,
|
| 1814 |
+
"step": 2510
|
| 1815 |
+
},
|
| 1816 |
+
{
|
| 1817 |
+
"epoch": 1.0281546465367744,
|
| 1818 |
+
"grad_norm": 1.251035451889038,
|
| 1819 |
+
"learning_rate": 1.794451244390045e-05,
|
| 1820 |
+
"loss": 0.1784,
|
| 1821 |
+
"step": 2520
|
| 1822 |
+
},
|
| 1823 |
+
{
|
| 1824 |
+
"epoch": 1.0322350300928287,
|
| 1825 |
+
"grad_norm": 2.9573662281036377,
|
| 1826 |
+
"learning_rate": 1.793635250917993e-05,
|
| 1827 |
+
"loss": 0.2249,
|
| 1828 |
+
"step": 2530
|
| 1829 |
+
},
|
| 1830 |
+
{
|
| 1831 |
+
"epoch": 1.036315413648883,
|
| 1832 |
+
"grad_norm": 1.3778438568115234,
|
| 1833 |
+
"learning_rate": 1.7928192574459405e-05,
|
| 1834 |
+
"loss": 0.1034,
|
| 1835 |
+
"step": 2540
|
| 1836 |
+
},
|
| 1837 |
+
{
|
| 1838 |
+
"epoch": 1.0403957972049374,
|
| 1839 |
+
"grad_norm": 1.9515317678451538,
|
| 1840 |
+
"learning_rate": 1.7920032639738884e-05,
|
| 1841 |
+
"loss": 0.1395,
|
| 1842 |
+
"step": 2550
|
| 1843 |
+
},
|
| 1844 |
+
{
|
| 1845 |
+
"epoch": 1.0444761807609915,
|
| 1846 |
+
"grad_norm": 0.7084790468215942,
|
| 1847 |
+
"learning_rate": 1.791187270501836e-05,
|
| 1848 |
+
"loss": 0.1052,
|
| 1849 |
+
"step": 2560
|
| 1850 |
+
},
|
| 1851 |
+
{
|
| 1852 |
+
"epoch": 1.0485565643170458,
|
| 1853 |
+
"grad_norm": 1.4658987522125244,
|
| 1854 |
+
"learning_rate": 1.790371277029784e-05,
|
| 1855 |
+
"loss": 0.1926,
|
| 1856 |
+
"step": 2570
|
| 1857 |
+
},
|
| 1858 |
+
{
|
| 1859 |
+
"epoch": 1.0526369478731001,
|
| 1860 |
+
"grad_norm": 1.8518738746643066,
|
| 1861 |
+
"learning_rate": 1.7895552835577315e-05,
|
| 1862 |
+
"loss": 0.1359,
|
| 1863 |
+
"step": 2580
|
| 1864 |
+
},
|
| 1865 |
+
{
|
| 1866 |
+
"epoch": 1.0567173314291542,
|
| 1867 |
+
"grad_norm": 0.0,
|
| 1868 |
+
"learning_rate": 1.7887392900856794e-05,
|
| 1869 |
+
"loss": 0.2138,
|
| 1870 |
+
"step": 2590
|
| 1871 |
+
},
|
| 1872 |
+
{
|
| 1873 |
+
"epoch": 1.0607977149852086,
|
| 1874 |
+
"grad_norm": 3.8889942169189453,
|
| 1875 |
+
"learning_rate": 1.7879232966136273e-05,
|
| 1876 |
+
"loss": 0.1807,
|
| 1877 |
+
"step": 2600
|
| 1878 |
+
},
|
| 1879 |
+
{
|
| 1880 |
+
"epoch": 1.064878098541263,
|
| 1881 |
+
"grad_norm": 0.2436802089214325,
|
| 1882 |
+
"learning_rate": 1.7871073031415753e-05,
|
| 1883 |
+
"loss": 0.1309,
|
| 1884 |
+
"step": 2610
|
| 1885 |
+
},
|
| 1886 |
+
{
|
| 1887 |
+
"epoch": 1.068958482097317,
|
| 1888 |
+
"grad_norm": 1.300466775894165,
|
| 1889 |
+
"learning_rate": 1.786291309669523e-05,
|
| 1890 |
+
"loss": 0.1192,
|
| 1891 |
+
"step": 2620
|
| 1892 |
+
},
|
| 1893 |
+
{
|
| 1894 |
+
"epoch": 1.0730388656533714,
|
| 1895 |
+
"grad_norm": 1.0126774311065674,
|
| 1896 |
+
"learning_rate": 1.7854753161974704e-05,
|
| 1897 |
+
"loss": 0.1204,
|
| 1898 |
+
"step": 2630
|
| 1899 |
+
},
|
| 1900 |
+
{
|
| 1901 |
+
"epoch": 1.0771192492094257,
|
| 1902 |
+
"grad_norm": 1.8178058862686157,
|
| 1903 |
+
"learning_rate": 1.7846593227254183e-05,
|
| 1904 |
+
"loss": 0.2804,
|
| 1905 |
+
"step": 2640
|
| 1906 |
+
},
|
| 1907 |
+
{
|
| 1908 |
+
"epoch": 1.08119963276548,
|
| 1909 |
+
"grad_norm": 3.756274938583374,
|
| 1910 |
+
"learning_rate": 1.7838433292533662e-05,
|
| 1911 |
+
"loss": 0.2423,
|
| 1912 |
+
"step": 2650
|
| 1913 |
+
},
|
| 1914 |
+
{
|
| 1915 |
+
"epoch": 1.0852800163215341,
|
| 1916 |
+
"grad_norm": 1.1179070472717285,
|
| 1917 |
+
"learning_rate": 1.7830273357813138e-05,
|
| 1918 |
+
"loss": 0.0965,
|
| 1919 |
+
"step": 2660
|
| 1920 |
+
},
|
| 1921 |
+
{
|
| 1922 |
+
"epoch": 1.0893603998775885,
|
| 1923 |
+
"grad_norm": 0.0,
|
| 1924 |
+
"learning_rate": 1.7822113423092617e-05,
|
| 1925 |
+
"loss": 0.1685,
|
| 1926 |
+
"step": 2670
|
| 1927 |
+
},
|
| 1928 |
+
{
|
| 1929 |
+
"epoch": 1.0934407834336428,
|
| 1930 |
+
"grad_norm": 1.443263292312622,
|
| 1931 |
+
"learning_rate": 1.7813953488372096e-05,
|
| 1932 |
+
"loss": 0.1253,
|
| 1933 |
+
"step": 2680
|
| 1934 |
+
},
|
| 1935 |
+
{
|
| 1936 |
+
"epoch": 1.097521166989697,
|
| 1937 |
+
"grad_norm": 0.5109815001487732,
|
| 1938 |
+
"learning_rate": 1.7805793553651572e-05,
|
| 1939 |
+
"loss": 0.1199,
|
| 1940 |
+
"step": 2690
|
| 1941 |
+
},
|
| 1942 |
+
{
|
| 1943 |
+
"epoch": 1.1016015505457513,
|
| 1944 |
+
"grad_norm": 0.22729843854904175,
|
| 1945 |
+
"learning_rate": 1.7797633618931048e-05,
|
| 1946 |
+
"loss": 0.0929,
|
| 1947 |
+
"step": 2700
|
| 1948 |
+
},
|
| 1949 |
+
{
|
| 1950 |
+
"epoch": 1.1056819341018056,
|
| 1951 |
+
"grad_norm": 1.8977311849594116,
|
| 1952 |
+
"learning_rate": 1.7789473684210527e-05,
|
| 1953 |
+
"loss": 0.1941,
|
| 1954 |
+
"step": 2710
|
| 1955 |
+
},
|
| 1956 |
+
{
|
| 1957 |
+
"epoch": 1.10976231765786,
|
| 1958 |
+
"grad_norm": 0.0,
|
| 1959 |
+
"learning_rate": 1.7781313749490006e-05,
|
| 1960 |
+
"loss": 0.1466,
|
| 1961 |
+
"step": 2720
|
| 1962 |
+
},
|
| 1963 |
+
{
|
| 1964 |
+
"epoch": 1.113842701213914,
|
| 1965 |
+
"grad_norm": 0.0,
|
| 1966 |
+
"learning_rate": 1.7773153814769485e-05,
|
| 1967 |
+
"loss": 0.2937,
|
| 1968 |
+
"step": 2730
|
| 1969 |
+
},
|
| 1970 |
+
{
|
| 1971 |
+
"epoch": 1.1179230847699684,
|
| 1972 |
+
"grad_norm": 1.0497016906738281,
|
| 1973 |
+
"learning_rate": 1.776499388004896e-05,
|
| 1974 |
+
"loss": 0.2416,
|
| 1975 |
+
"step": 2740
|
| 1976 |
+
},
|
| 1977 |
+
{
|
| 1978 |
+
"epoch": 1.1220034683260227,
|
| 1979 |
+
"grad_norm": 0.0,
|
| 1980 |
+
"learning_rate": 1.7756833945328437e-05,
|
| 1981 |
+
"loss": 0.2409,
|
| 1982 |
+
"step": 2750
|
| 1983 |
+
},
|
| 1984 |
+
{
|
| 1985 |
+
"epoch": 1.1260838518820768,
|
| 1986 |
+
"grad_norm": 1.1163699626922607,
|
| 1987 |
+
"learning_rate": 1.7748674010607916e-05,
|
| 1988 |
+
"loss": 0.1572,
|
| 1989 |
+
"step": 2760
|
| 1990 |
+
},
|
| 1991 |
+
{
|
| 1992 |
+
"epoch": 1.1301642354381312,
|
| 1993 |
+
"grad_norm": 1.966738224029541,
|
| 1994 |
+
"learning_rate": 1.7740514075887395e-05,
|
| 1995 |
+
"loss": 0.1724,
|
| 1996 |
+
"step": 2770
|
| 1997 |
+
},
|
| 1998 |
+
{
|
| 1999 |
+
"epoch": 1.1342446189941855,
|
| 2000 |
+
"grad_norm": 1.8599481582641602,
|
| 2001 |
+
"learning_rate": 1.773235414116687e-05,
|
| 2002 |
+
"loss": 0.1455,
|
| 2003 |
+
"step": 2780
|
| 2004 |
+
},
|
| 2005 |
+
{
|
| 2006 |
+
"epoch": 1.1383250025502396,
|
| 2007 |
+
"grad_norm": 0.1753341406583786,
|
| 2008 |
+
"learning_rate": 1.772419420644635e-05,
|
| 2009 |
+
"loss": 0.1785,
|
| 2010 |
+
"step": 2790
|
| 2011 |
+
},
|
| 2012 |
+
{
|
| 2013 |
+
"epoch": 1.142405386106294,
|
| 2014 |
+
"grad_norm": 1.0875040292739868,
|
| 2015 |
+
"learning_rate": 1.771603427172583e-05,
|
| 2016 |
+
"loss": 0.1644,
|
| 2017 |
+
"step": 2800
|
| 2018 |
+
},
|
| 2019 |
+
{
|
| 2020 |
+
"epoch": 1.1464857696623483,
|
| 2021 |
+
"grad_norm": 2.753896713256836,
|
| 2022 |
+
"learning_rate": 1.7707874337005305e-05,
|
| 2023 |
+
"loss": 0.1258,
|
| 2024 |
+
"step": 2810
|
| 2025 |
+
},
|
| 2026 |
+
{
|
| 2027 |
+
"epoch": 1.1505661532184026,
|
| 2028 |
+
"grad_norm": 0.49547603726387024,
|
| 2029 |
+
"learning_rate": 1.769971440228478e-05,
|
| 2030 |
+
"loss": 0.0947,
|
| 2031 |
+
"step": 2820
|
| 2032 |
+
},
|
| 2033 |
+
{
|
| 2034 |
+
"epoch": 1.1546465367744567,
|
| 2035 |
+
"grad_norm": 0.0,
|
| 2036 |
+
"learning_rate": 1.769155446756426e-05,
|
| 2037 |
+
"loss": 0.1007,
|
| 2038 |
+
"step": 2830
|
| 2039 |
+
},
|
| 2040 |
+
{
|
| 2041 |
+
"epoch": 1.158726920330511,
|
| 2042 |
+
"grad_norm": 0.2678370773792267,
|
| 2043 |
+
"learning_rate": 1.768339453284374e-05,
|
| 2044 |
+
"loss": 0.0747,
|
| 2045 |
+
"step": 2840
|
| 2046 |
+
},
|
| 2047 |
+
{
|
| 2048 |
+
"epoch": 1.1628073038865654,
|
| 2049 |
+
"grad_norm": 0.7357677817344666,
|
| 2050 |
+
"learning_rate": 1.7675234598123218e-05,
|
| 2051 |
+
"loss": 0.1259,
|
| 2052 |
+
"step": 2850
|
| 2053 |
+
},
|
| 2054 |
+
{
|
| 2055 |
+
"epoch": 1.1668876874426197,
|
| 2056 |
+
"grad_norm": 1.2190055847167969,
|
| 2057 |
+
"learning_rate": 1.7667074663402694e-05,
|
| 2058 |
+
"loss": 0.1064,
|
| 2059 |
+
"step": 2860
|
| 2060 |
+
},
|
| 2061 |
+
{
|
| 2062 |
+
"epoch": 1.1709680709986738,
|
| 2063 |
+
"grad_norm": 1.6289119720458984,
|
| 2064 |
+
"learning_rate": 1.7658914728682173e-05,
|
| 2065 |
+
"loss": 0.1711,
|
| 2066 |
+
"step": 2870
|
| 2067 |
+
},
|
| 2068 |
+
{
|
| 2069 |
+
"epoch": 1.1750484545547282,
|
| 2070 |
+
"grad_norm": 0.5327509641647339,
|
| 2071 |
+
"learning_rate": 1.7650754793961652e-05,
|
| 2072 |
+
"loss": 0.0959,
|
| 2073 |
+
"step": 2880
|
| 2074 |
+
},
|
| 2075 |
+
{
|
| 2076 |
+
"epoch": 1.1791288381107825,
|
| 2077 |
+
"grad_norm": 1.7999294996261597,
|
| 2078 |
+
"learning_rate": 1.7642594859241128e-05,
|
| 2079 |
+
"loss": 0.1594,
|
| 2080 |
+
"step": 2890
|
| 2081 |
+
},
|
| 2082 |
+
{
|
| 2083 |
+
"epoch": 1.1832092216668366,
|
| 2084 |
+
"grad_norm": 1.19373619556427,
|
| 2085 |
+
"learning_rate": 1.7634434924520604e-05,
|
| 2086 |
+
"loss": 0.1787,
|
| 2087 |
+
"step": 2900
|
| 2088 |
+
}
|
| 2089 |
+
],
|
| 2090 |
+
"logging_steps": 10,
|
| 2091 |
+
"max_steps": 24510,
|
| 2092 |
+
"num_input_tokens_seen": 0,
|
| 2093 |
+
"num_train_epochs": 10,
|
| 2094 |
+
"save_steps": 50,
|
| 2095 |
+
"stateful_callbacks": {
|
| 2096 |
+
"TrainerControl": {
|
| 2097 |
+
"args": {
|
| 2098 |
+
"should_epoch_stop": false,
|
| 2099 |
+
"should_evaluate": false,
|
| 2100 |
+
"should_log": false,
|
| 2101 |
+
"should_save": true,
|
| 2102 |
+
"should_training_stop": false
|
| 2103 |
+
},
|
| 2104 |
+
"attributes": {}
|
| 2105 |
+
}
|
| 2106 |
+
},
|
| 2107 |
+
"total_flos": 1.415936759096148e+18,
|
| 2108 |
+
"train_batch_size": 1,
|
| 2109 |
+
"trial_name": null,
|
| 2110 |
+
"trial_params": null
|
| 2111 |
+
}
|
prior_attributer_polymarket_4b_2900/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f46457bf3c59baf106bc05ea602d8e6a8d87e1840bac5cf73b3e22b6eab825a9
|
| 3 |
+
size 5496
|