test_ViT-Masked_5
Browse files- README.md +50 -0
- config.json +22 -0
- model.safetensors +3 -0
- trainer_state.json +380 -0
- training_args.bin +3 -0
README.md
ADDED
|
@@ -0,0 +1,50 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
tags:
|
| 3 |
+
- generated_from_trainer
|
| 4 |
+
model-index:
|
| 5 |
+
- name: test_ViT-Masked_5
|
| 6 |
+
results: []
|
| 7 |
+
---
|
| 8 |
+
|
| 9 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 10 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 11 |
+
|
| 12 |
+
# test_ViT-Masked_5
|
| 13 |
+
|
| 14 |
+
This model is a fine-tuned version of [](https://huggingface.co/) on the ppak10/Melt-Pool-Thermal-Images dataset.
|
| 15 |
+
|
| 16 |
+
## Model description
|
| 17 |
+
|
| 18 |
+
More information needed
|
| 19 |
+
|
| 20 |
+
## Intended uses & limitations
|
| 21 |
+
|
| 22 |
+
More information needed
|
| 23 |
+
|
| 24 |
+
## Training and evaluation data
|
| 25 |
+
|
| 26 |
+
More information needed
|
| 27 |
+
|
| 28 |
+
## Training procedure
|
| 29 |
+
|
| 30 |
+
### Training hyperparameters
|
| 31 |
+
|
| 32 |
+
The following hyperparameters were used during training:
|
| 33 |
+
- learning_rate: 1e-05
|
| 34 |
+
- train_batch_size: 2048
|
| 35 |
+
- eval_batch_size: 16
|
| 36 |
+
- seed: 42
|
| 37 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 38 |
+
- lr_scheduler_type: linear
|
| 39 |
+
- num_epochs: 50
|
| 40 |
+
|
| 41 |
+
### Training results
|
| 42 |
+
|
| 43 |
+
|
| 44 |
+
|
| 45 |
+
### Framework versions
|
| 46 |
+
|
| 47 |
+
- Transformers 4.40.1
|
| 48 |
+
- Pytorch 2.0.1+cu117
|
| 49 |
+
- Datasets 2.19.0
|
| 50 |
+
- Tokenizers 0.19.1
|
config.json
ADDED
|
@@ -0,0 +1,22 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"ViTForMaskedImageModeling"
|
| 4 |
+
],
|
| 5 |
+
"attention_probs_dropout_prob": 0.0,
|
| 6 |
+
"encoder_stride": 8,
|
| 7 |
+
"hidden_act": "gelu",
|
| 8 |
+
"hidden_dropout_prob": 0.0,
|
| 9 |
+
"hidden_size": 768,
|
| 10 |
+
"image_size": 64,
|
| 11 |
+
"initializer_range": 0.02,
|
| 12 |
+
"intermediate_size": 3072,
|
| 13 |
+
"layer_norm_eps": 1e-12,
|
| 14 |
+
"model_type": "vit",
|
| 15 |
+
"num_attention_heads": 12,
|
| 16 |
+
"num_channels": 1,
|
| 17 |
+
"num_hidden_layers": 12,
|
| 18 |
+
"patch_size": 8,
|
| 19 |
+
"qkv_bias": true,
|
| 20 |
+
"torch_dtype": "float32",
|
| 21 |
+
"transformers_version": "4.40.1"
|
| 22 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ddfca584a236659427dcb6cb5e42ccc8d6e47b86af70a15e217da0bbb6e0ebf9
|
| 3 |
+
size 340849656
|
trainer_state.json
ADDED
|
@@ -0,0 +1,380 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 50.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 12950,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 1.9305019305019306,
|
| 13 |
+
"grad_norm": 2.738110065460205,
|
| 14 |
+
"learning_rate": 9.613899613899614e-06,
|
| 15 |
+
"loss": 0.0888,
|
| 16 |
+
"step": 500
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 1.9305019305019306,
|
| 20 |
+
"eval_runtime": 667.5755,
|
| 21 |
+
"eval_samples_per_second": 264.418,
|
| 22 |
+
"eval_steps_per_second": 16.527,
|
| 23 |
+
"step": 500
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 3.861003861003861,
|
| 27 |
+
"grad_norm": 4.450708389282227,
|
| 28 |
+
"learning_rate": 9.227799227799229e-06,
|
| 29 |
+
"loss": 0.0558,
|
| 30 |
+
"step": 1000
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 3.861003861003861,
|
| 34 |
+
"eval_runtime": 651.8038,
|
| 35 |
+
"eval_samples_per_second": 270.816,
|
| 36 |
+
"eval_steps_per_second": 16.927,
|
| 37 |
+
"step": 1000
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 5.7915057915057915,
|
| 41 |
+
"grad_norm": 5.049165725708008,
|
| 42 |
+
"learning_rate": 8.841698841698842e-06,
|
| 43 |
+
"loss": 0.0409,
|
| 44 |
+
"step": 1500
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 5.7915057915057915,
|
| 48 |
+
"eval_runtime": 650.4821,
|
| 49 |
+
"eval_samples_per_second": 271.366,
|
| 50 |
+
"eval_steps_per_second": 16.961,
|
| 51 |
+
"step": 1500
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 7.722007722007722,
|
| 55 |
+
"grad_norm": 3.824125051498413,
|
| 56 |
+
"learning_rate": 8.455598455598457e-06,
|
| 57 |
+
"loss": 0.0319,
|
| 58 |
+
"step": 2000
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 7.722007722007722,
|
| 62 |
+
"eval_runtime": 652.7164,
|
| 63 |
+
"eval_samples_per_second": 270.438,
|
| 64 |
+
"eval_steps_per_second": 16.903,
|
| 65 |
+
"step": 2000
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 9.652509652509652,
|
| 69 |
+
"grad_norm": 3.7455878257751465,
|
| 70 |
+
"learning_rate": 8.06949806949807e-06,
|
| 71 |
+
"loss": 0.0277,
|
| 72 |
+
"step": 2500
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 9.652509652509652,
|
| 76 |
+
"eval_runtime": 652.469,
|
| 77 |
+
"eval_samples_per_second": 270.54,
|
| 78 |
+
"eval_steps_per_second": 16.91,
|
| 79 |
+
"step": 2500
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 11.583011583011583,
|
| 83 |
+
"grad_norm": 2.825524091720581,
|
| 84 |
+
"learning_rate": 7.683397683397685e-06,
|
| 85 |
+
"loss": 0.0249,
|
| 86 |
+
"step": 3000
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 11.583011583011583,
|
| 90 |
+
"eval_runtime": 724.8262,
|
| 91 |
+
"eval_samples_per_second": 243.533,
|
| 92 |
+
"eval_steps_per_second": 15.222,
|
| 93 |
+
"step": 3000
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 13.513513513513514,
|
| 97 |
+
"grad_norm": 1.5855698585510254,
|
| 98 |
+
"learning_rate": 7.297297297297298e-06,
|
| 99 |
+
"loss": 0.0233,
|
| 100 |
+
"step": 3500
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 13.513513513513514,
|
| 104 |
+
"eval_runtime": 721.7805,
|
| 105 |
+
"eval_samples_per_second": 244.56,
|
| 106 |
+
"eval_steps_per_second": 15.286,
|
| 107 |
+
"step": 3500
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 15.444015444015443,
|
| 111 |
+
"grad_norm": 2.516690254211426,
|
| 112 |
+
"learning_rate": 6.911196911196911e-06,
|
| 113 |
+
"loss": 0.0217,
|
| 114 |
+
"step": 4000
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 15.444015444015443,
|
| 118 |
+
"eval_runtime": 723.8804,
|
| 119 |
+
"eval_samples_per_second": 243.851,
|
| 120 |
+
"eval_steps_per_second": 15.241,
|
| 121 |
+
"step": 4000
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 17.374517374517374,
|
| 125 |
+
"grad_norm": 2.6874454021453857,
|
| 126 |
+
"learning_rate": 6.525096525096526e-06,
|
| 127 |
+
"loss": 0.0207,
|
| 128 |
+
"step": 4500
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 17.374517374517374,
|
| 132 |
+
"eval_runtime": 726.2467,
|
| 133 |
+
"eval_samples_per_second": 243.057,
|
| 134 |
+
"eval_steps_per_second": 15.192,
|
| 135 |
+
"step": 4500
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 19.305019305019304,
|
| 139 |
+
"grad_norm": 2.5405662059783936,
|
| 140 |
+
"learning_rate": 6.13899613899614e-06,
|
| 141 |
+
"loss": 0.0198,
|
| 142 |
+
"step": 5000
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 19.305019305019304,
|
| 146 |
+
"eval_runtime": 725.831,
|
| 147 |
+
"eval_samples_per_second": 243.196,
|
| 148 |
+
"eval_steps_per_second": 15.201,
|
| 149 |
+
"step": 5000
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 21.235521235521237,
|
| 153 |
+
"grad_norm": 2.5149359703063965,
|
| 154 |
+
"learning_rate": 5.752895752895753e-06,
|
| 155 |
+
"loss": 0.0191,
|
| 156 |
+
"step": 5500
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 21.235521235521237,
|
| 160 |
+
"eval_runtime": 724.4353,
|
| 161 |
+
"eval_samples_per_second": 243.664,
|
| 162 |
+
"eval_steps_per_second": 15.23,
|
| 163 |
+
"step": 5500
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 23.166023166023166,
|
| 167 |
+
"grad_norm": 1.5971148014068604,
|
| 168 |
+
"learning_rate": 5.366795366795368e-06,
|
| 169 |
+
"loss": 0.0183,
|
| 170 |
+
"step": 6000
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 23.166023166023166,
|
| 174 |
+
"eval_runtime": 725.1569,
|
| 175 |
+
"eval_samples_per_second": 243.422,
|
| 176 |
+
"eval_steps_per_second": 15.215,
|
| 177 |
+
"step": 6000
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 25.096525096525095,
|
| 181 |
+
"grad_norm": 2.0284860134124756,
|
| 182 |
+
"learning_rate": 4.980694980694981e-06,
|
| 183 |
+
"loss": 0.0178,
|
| 184 |
+
"step": 6500
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 25.096525096525095,
|
| 188 |
+
"eval_runtime": 726.8832,
|
| 189 |
+
"eval_samples_per_second": 242.844,
|
| 190 |
+
"eval_steps_per_second": 15.179,
|
| 191 |
+
"step": 6500
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 27.027027027027028,
|
| 195 |
+
"grad_norm": 2.005959987640381,
|
| 196 |
+
"learning_rate": 4.594594594594596e-06,
|
| 197 |
+
"loss": 0.0174,
|
| 198 |
+
"step": 7000
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 27.027027027027028,
|
| 202 |
+
"eval_runtime": 725.3449,
|
| 203 |
+
"eval_samples_per_second": 243.359,
|
| 204 |
+
"eval_steps_per_second": 15.211,
|
| 205 |
+
"step": 7000
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 28.957528957528957,
|
| 209 |
+
"grad_norm": 1.96770441532135,
|
| 210 |
+
"learning_rate": 4.208494208494209e-06,
|
| 211 |
+
"loss": 0.0168,
|
| 212 |
+
"step": 7500
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 28.957528957528957,
|
| 216 |
+
"eval_runtime": 765.8326,
|
| 217 |
+
"eval_samples_per_second": 230.493,
|
| 218 |
+
"eval_steps_per_second": 14.407,
|
| 219 |
+
"step": 7500
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 30.888030888030887,
|
| 223 |
+
"grad_norm": 1.844897747039795,
|
| 224 |
+
"learning_rate": 3.822393822393823e-06,
|
| 225 |
+
"loss": 0.0165,
|
| 226 |
+
"step": 8000
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 30.888030888030887,
|
| 230 |
+
"eval_runtime": 819.9764,
|
| 231 |
+
"eval_samples_per_second": 215.273,
|
| 232 |
+
"eval_steps_per_second": 13.455,
|
| 233 |
+
"step": 8000
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 32.818532818532816,
|
| 237 |
+
"grad_norm": 1.615881323814392,
|
| 238 |
+
"learning_rate": 3.4362934362934363e-06,
|
| 239 |
+
"loss": 0.0162,
|
| 240 |
+
"step": 8500
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 32.818532818532816,
|
| 244 |
+
"eval_runtime": 821.2267,
|
| 245 |
+
"eval_samples_per_second": 214.946,
|
| 246 |
+
"eval_steps_per_second": 13.435,
|
| 247 |
+
"step": 8500
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 34.74903474903475,
|
| 251 |
+
"grad_norm": 1.6435213088989258,
|
| 252 |
+
"learning_rate": 3.0501930501930503e-06,
|
| 253 |
+
"loss": 0.0158,
|
| 254 |
+
"step": 9000
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 34.74903474903475,
|
| 258 |
+
"eval_runtime": 819.0429,
|
| 259 |
+
"eval_samples_per_second": 215.519,
|
| 260 |
+
"eval_steps_per_second": 13.471,
|
| 261 |
+
"step": 9000
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 36.67953667953668,
|
| 265 |
+
"grad_norm": 1.7934831380844116,
|
| 266 |
+
"learning_rate": 2.6640926640926647e-06,
|
| 267 |
+
"loss": 0.0155,
|
| 268 |
+
"step": 9500
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 36.67953667953668,
|
| 272 |
+
"eval_runtime": 820.1169,
|
| 273 |
+
"eval_samples_per_second": 215.236,
|
| 274 |
+
"eval_steps_per_second": 13.453,
|
| 275 |
+
"step": 9500
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 38.61003861003861,
|
| 279 |
+
"grad_norm": 1.1239484548568726,
|
| 280 |
+
"learning_rate": 2.2779922779922782e-06,
|
| 281 |
+
"loss": 0.0152,
|
| 282 |
+
"step": 10000
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 38.61003861003861,
|
| 286 |
+
"eval_runtime": 821.2669,
|
| 287 |
+
"eval_samples_per_second": 214.935,
|
| 288 |
+
"eval_steps_per_second": 13.434,
|
| 289 |
+
"step": 10000
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 40.54054054054054,
|
| 293 |
+
"grad_norm": 1.256516456604004,
|
| 294 |
+
"learning_rate": 1.8918918918918922e-06,
|
| 295 |
+
"loss": 0.015,
|
| 296 |
+
"step": 10500
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 40.54054054054054,
|
| 300 |
+
"eval_runtime": 818.9208,
|
| 301 |
+
"eval_samples_per_second": 215.551,
|
| 302 |
+
"eval_steps_per_second": 13.473,
|
| 303 |
+
"step": 10500
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 42.47104247104247,
|
| 307 |
+
"grad_norm": 0.4177967607975006,
|
| 308 |
+
"learning_rate": 1.505791505791506e-06,
|
| 309 |
+
"loss": 0.0148,
|
| 310 |
+
"step": 11000
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 42.47104247104247,
|
| 314 |
+
"eval_runtime": 823.9199,
|
| 315 |
+
"eval_samples_per_second": 214.243,
|
| 316 |
+
"eval_steps_per_second": 13.391,
|
| 317 |
+
"step": 11000
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 44.4015444015444,
|
| 321 |
+
"grad_norm": 0.3761753737926483,
|
| 322 |
+
"learning_rate": 1.1196911196911197e-06,
|
| 323 |
+
"loss": 0.0146,
|
| 324 |
+
"step": 11500
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 44.4015444015444,
|
| 328 |
+
"eval_runtime": 821.1987,
|
| 329 |
+
"eval_samples_per_second": 214.953,
|
| 330 |
+
"eval_steps_per_second": 13.435,
|
| 331 |
+
"step": 11500
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 46.33204633204633,
|
| 335 |
+
"grad_norm": 0.4973774552345276,
|
| 336 |
+
"learning_rate": 7.335907335907337e-07,
|
| 337 |
+
"loss": 0.0145,
|
| 338 |
+
"step": 12000
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 46.33204633204633,
|
| 342 |
+
"eval_runtime": 821.7593,
|
| 343 |
+
"eval_samples_per_second": 214.806,
|
| 344 |
+
"eval_steps_per_second": 13.426,
|
| 345 |
+
"step": 12000
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 48.262548262548265,
|
| 349 |
+
"grad_norm": 0.3773488998413086,
|
| 350 |
+
"learning_rate": 3.474903474903475e-07,
|
| 351 |
+
"loss": 0.0144,
|
| 352 |
+
"step": 12500
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 48.262548262548265,
|
| 356 |
+
"eval_runtime": 824.3743,
|
| 357 |
+
"eval_samples_per_second": 214.125,
|
| 358 |
+
"eval_steps_per_second": 13.383,
|
| 359 |
+
"step": 12500
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 50.0,
|
| 363 |
+
"step": 12950,
|
| 364 |
+
"total_flos": 5.544539360447693e+19,
|
| 365 |
+
"train_loss": 0.023562463738283135,
|
| 366 |
+
"train_runtime": 98807.7466,
|
| 367 |
+
"train_samples_per_second": 267.972,
|
| 368 |
+
"train_steps_per_second": 0.131
|
| 369 |
+
}
|
| 370 |
+
],
|
| 371 |
+
"logging_steps": 500,
|
| 372 |
+
"max_steps": 12950,
|
| 373 |
+
"num_input_tokens_seen": 0,
|
| 374 |
+
"num_train_epochs": 50,
|
| 375 |
+
"save_steps": 100,
|
| 376 |
+
"total_flos": 5.544539360447693e+19,
|
| 377 |
+
"train_batch_size": 2048,
|
| 378 |
+
"trial_name": null,
|
| 379 |
+
"trial_params": null
|
| 380 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0942d68f90d6569eea9def5463bf1355978cdba23a55c8aa7a19449584d203d3
|
| 3 |
+
size 4539
|