End of training
Browse files- README.md +4 -2
- all_results.json +12 -0
- eval_results.json +8 -0
- train_results.json +7 -0
- trainer_state.json +501 -0
README.md
CHANGED
|
@@ -2,6 +2,8 @@
|
|
| 2 |
license: apache-2.0
|
| 3 |
base_model: google/vit-base-patch16-224-in21k
|
| 4 |
tags:
|
|
|
|
|
|
|
| 5 |
- generated_from_trainer
|
| 6 |
datasets:
|
| 7 |
- imagefolder
|
|
@@ -14,7 +16,7 @@ model-index:
|
|
| 14 |
name: Image Classification
|
| 15 |
type: image-classification
|
| 16 |
dataset:
|
| 17 |
-
name:
|
| 18 |
type: imagefolder
|
| 19 |
config: default
|
| 20 |
split: train
|
|
@@ -30,7 +32,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 30 |
|
| 31 |
# vit-base-mgas
|
| 32 |
|
| 33 |
-
This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on the
|
| 34 |
It achieves the following results on the evaluation set:
|
| 35 |
- Loss: 0.8530
|
| 36 |
- Accuracy: 0.7323
|
|
|
|
| 2 |
license: apache-2.0
|
| 3 |
base_model: google/vit-base-patch16-224-in21k
|
| 4 |
tags:
|
| 5 |
+
- image-classification
|
| 6 |
+
- vision
|
| 7 |
- generated_from_trainer
|
| 8 |
datasets:
|
| 9 |
- imagefolder
|
|
|
|
| 16 |
name: Image Classification
|
| 17 |
type: image-classification
|
| 18 |
dataset:
|
| 19 |
+
name: ./mgr/dataset/HF_DS
|
| 20 |
type: imagefolder
|
| 21 |
config: default
|
| 22 |
split: train
|
|
|
|
| 32 |
|
| 33 |
# vit-base-mgas
|
| 34 |
|
| 35 |
+
This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on the ./mgr/dataset/HF_DS dataset.
|
| 36 |
It achieves the following results on the evaluation set:
|
| 37 |
- Loss: 0.8530
|
| 38 |
- Accuracy: 0.7323
|
all_results.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 5.0,
|
| 3 |
+
"eval_accuracy": 0.7322834645669292,
|
| 4 |
+
"eval_loss": 0.8530173897743225,
|
| 5 |
+
"eval_runtime": 10.1757,
|
| 6 |
+
"eval_samples_per_second": 12.481,
|
| 7 |
+
"eval_steps_per_second": 1.572,
|
| 8 |
+
"train_loss": 0.18311181501908735,
|
| 9 |
+
"train_runtime": 299.5589,
|
| 10 |
+
"train_samples_per_second": 19.061,
|
| 11 |
+
"train_steps_per_second": 2.387
|
| 12 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 5.0,
|
| 3 |
+
"eval_accuracy": 0.7322834645669292,
|
| 4 |
+
"eval_loss": 0.8530173897743225,
|
| 5 |
+
"eval_runtime": 10.1757,
|
| 6 |
+
"eval_samples_per_second": 12.481,
|
| 7 |
+
"eval_steps_per_second": 1.572
|
| 8 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 5.0,
|
| 3 |
+
"train_loss": 0.18311181501908735,
|
| 4 |
+
"train_runtime": 299.5589,
|
| 5 |
+
"train_samples_per_second": 19.061,
|
| 6 |
+
"train_steps_per_second": 2.387
|
| 7 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,501 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.8530173897743225,
|
| 3 |
+
"best_model_checkpoint": "./beans_outputs/checkpoint-715",
|
| 4 |
+
"epoch": 5.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 715,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.07,
|
| 13 |
+
"learning_rate": 1.9720279720279722e-05,
|
| 14 |
+
"loss": 1.7594,
|
| 15 |
+
"step": 10
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.14,
|
| 19 |
+
"learning_rate": 1.944055944055944e-05,
|
| 20 |
+
"loss": 1.7247,
|
| 21 |
+
"step": 20
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.21,
|
| 25 |
+
"learning_rate": 1.916083916083916e-05,
|
| 26 |
+
"loss": 1.6869,
|
| 27 |
+
"step": 30
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 0.28,
|
| 31 |
+
"learning_rate": 1.888111888111888e-05,
|
| 32 |
+
"loss": 1.6615,
|
| 33 |
+
"step": 40
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 0.35,
|
| 37 |
+
"learning_rate": 1.8601398601398602e-05,
|
| 38 |
+
"loss": 1.6413,
|
| 39 |
+
"step": 50
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.42,
|
| 43 |
+
"learning_rate": 1.8321678321678323e-05,
|
| 44 |
+
"loss": 1.6369,
|
| 45 |
+
"step": 60
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.49,
|
| 49 |
+
"learning_rate": 1.8041958041958044e-05,
|
| 50 |
+
"loss": 1.5629,
|
| 51 |
+
"step": 70
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.56,
|
| 55 |
+
"learning_rate": 1.7762237762237765e-05,
|
| 56 |
+
"loss": 1.4909,
|
| 57 |
+
"step": 80
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 0.63,
|
| 61 |
+
"learning_rate": 1.7482517482517486e-05,
|
| 62 |
+
"loss": 1.585,
|
| 63 |
+
"step": 90
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 0.7,
|
| 67 |
+
"learning_rate": 1.7202797202797203e-05,
|
| 68 |
+
"loss": 1.4428,
|
| 69 |
+
"step": 100
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 0.77,
|
| 73 |
+
"learning_rate": 1.6923076923076924e-05,
|
| 74 |
+
"loss": 1.4252,
|
| 75 |
+
"step": 110
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 0.84,
|
| 79 |
+
"learning_rate": 1.6643356643356645e-05,
|
| 80 |
+
"loss": 1.3894,
|
| 81 |
+
"step": 120
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 0.91,
|
| 85 |
+
"learning_rate": 1.6363636363636366e-05,
|
| 86 |
+
"loss": 1.4099,
|
| 87 |
+
"step": 130
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.98,
|
| 91 |
+
"learning_rate": 1.6083916083916083e-05,
|
| 92 |
+
"loss": 1.4331,
|
| 93 |
+
"step": 140
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 1.0,
|
| 97 |
+
"eval_accuracy": 0.48031496062992124,
|
| 98 |
+
"eval_loss": 1.380394458770752,
|
| 99 |
+
"eval_runtime": 13.5035,
|
| 100 |
+
"eval_samples_per_second": 9.405,
|
| 101 |
+
"eval_steps_per_second": 1.185,
|
| 102 |
+
"step": 143
|
| 103 |
+
},
|
| 104 |
+
{
|
| 105 |
+
"epoch": 1.05,
|
| 106 |
+
"learning_rate": 1.5804195804195804e-05,
|
| 107 |
+
"loss": 1.4025,
|
| 108 |
+
"step": 150
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 1.12,
|
| 112 |
+
"learning_rate": 1.5524475524475525e-05,
|
| 113 |
+
"loss": 1.341,
|
| 114 |
+
"step": 160
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 1.19,
|
| 118 |
+
"learning_rate": 1.5244755244755244e-05,
|
| 119 |
+
"loss": 1.2961,
|
| 120 |
+
"step": 170
|
| 121 |
+
},
|
| 122 |
+
{
|
| 123 |
+
"epoch": 1.26,
|
| 124 |
+
"learning_rate": 1.4965034965034965e-05,
|
| 125 |
+
"loss": 1.3105,
|
| 126 |
+
"step": 180
|
| 127 |
+
},
|
| 128 |
+
{
|
| 129 |
+
"epoch": 1.33,
|
| 130 |
+
"learning_rate": 1.4685314685314686e-05,
|
| 131 |
+
"loss": 1.2829,
|
| 132 |
+
"step": 190
|
| 133 |
+
},
|
| 134 |
+
{
|
| 135 |
+
"epoch": 1.4,
|
| 136 |
+
"learning_rate": 1.4405594405594407e-05,
|
| 137 |
+
"loss": 1.291,
|
| 138 |
+
"step": 200
|
| 139 |
+
},
|
| 140 |
+
{
|
| 141 |
+
"epoch": 1.47,
|
| 142 |
+
"learning_rate": 1.4125874125874126e-05,
|
| 143 |
+
"loss": 1.2477,
|
| 144 |
+
"step": 210
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 1.54,
|
| 148 |
+
"learning_rate": 1.3846153846153847e-05,
|
| 149 |
+
"loss": 1.1525,
|
| 150 |
+
"step": 220
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 1.61,
|
| 154 |
+
"learning_rate": 1.3566433566433568e-05,
|
| 155 |
+
"loss": 1.2458,
|
| 156 |
+
"step": 230
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 1.68,
|
| 160 |
+
"learning_rate": 1.3286713286713288e-05,
|
| 161 |
+
"loss": 1.1054,
|
| 162 |
+
"step": 240
|
| 163 |
+
},
|
| 164 |
+
{
|
| 165 |
+
"epoch": 1.75,
|
| 166 |
+
"learning_rate": 1.3006993006993008e-05,
|
| 167 |
+
"loss": 1.2257,
|
| 168 |
+
"step": 250
|
| 169 |
+
},
|
| 170 |
+
{
|
| 171 |
+
"epoch": 1.82,
|
| 172 |
+
"learning_rate": 1.2727272727272728e-05,
|
| 173 |
+
"loss": 1.1471,
|
| 174 |
+
"step": 260
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 1.89,
|
| 178 |
+
"learning_rate": 1.244755244755245e-05,
|
| 179 |
+
"loss": 1.1859,
|
| 180 |
+
"step": 270
|
| 181 |
+
},
|
| 182 |
+
{
|
| 183 |
+
"epoch": 1.96,
|
| 184 |
+
"learning_rate": 1.216783216783217e-05,
|
| 185 |
+
"loss": 1.1653,
|
| 186 |
+
"step": 280
|
| 187 |
+
},
|
| 188 |
+
{
|
| 189 |
+
"epoch": 2.0,
|
| 190 |
+
"eval_accuracy": 0.6850393700787402,
|
| 191 |
+
"eval_loss": 1.0843431949615479,
|
| 192 |
+
"eval_runtime": 10.8218,
|
| 193 |
+
"eval_samples_per_second": 11.736,
|
| 194 |
+
"eval_steps_per_second": 1.479,
|
| 195 |
+
"step": 286
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 2.03,
|
| 199 |
+
"learning_rate": 1.1888111888111888e-05,
|
| 200 |
+
"loss": 1.2361,
|
| 201 |
+
"step": 290
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 2.1,
|
| 205 |
+
"learning_rate": 1.1608391608391608e-05,
|
| 206 |
+
"loss": 1.1012,
|
| 207 |
+
"step": 300
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 2.17,
|
| 211 |
+
"learning_rate": 1.132867132867133e-05,
|
| 212 |
+
"loss": 1.0819,
|
| 213 |
+
"step": 310
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 2.24,
|
| 217 |
+
"learning_rate": 1.1048951048951048e-05,
|
| 218 |
+
"loss": 1.0283,
|
| 219 |
+
"step": 320
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 2.31,
|
| 223 |
+
"learning_rate": 1.076923076923077e-05,
|
| 224 |
+
"loss": 1.0479,
|
| 225 |
+
"step": 330
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 2.38,
|
| 229 |
+
"learning_rate": 1.048951048951049e-05,
|
| 230 |
+
"loss": 1.0286,
|
| 231 |
+
"step": 340
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 2.45,
|
| 235 |
+
"learning_rate": 1.0209790209790211e-05,
|
| 236 |
+
"loss": 1.0439,
|
| 237 |
+
"step": 350
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 2.52,
|
| 241 |
+
"learning_rate": 9.93006993006993e-06,
|
| 242 |
+
"loss": 1.0562,
|
| 243 |
+
"step": 360
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 2.59,
|
| 247 |
+
"learning_rate": 9.650349650349651e-06,
|
| 248 |
+
"loss": 1.0392,
|
| 249 |
+
"step": 370
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 2.66,
|
| 253 |
+
"learning_rate": 9.370629370629372e-06,
|
| 254 |
+
"loss": 1.111,
|
| 255 |
+
"step": 380
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 2.73,
|
| 259 |
+
"learning_rate": 9.090909090909091e-06,
|
| 260 |
+
"loss": 1.1265,
|
| 261 |
+
"step": 390
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 2.8,
|
| 265 |
+
"learning_rate": 8.811188811188812e-06,
|
| 266 |
+
"loss": 1.0098,
|
| 267 |
+
"step": 400
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 2.87,
|
| 271 |
+
"learning_rate": 8.531468531468533e-06,
|
| 272 |
+
"loss": 1.1216,
|
| 273 |
+
"step": 410
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 2.94,
|
| 277 |
+
"learning_rate": 8.251748251748254e-06,
|
| 278 |
+
"loss": 1.0919,
|
| 279 |
+
"step": 420
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 3.0,
|
| 283 |
+
"eval_accuracy": 0.7165354330708661,
|
| 284 |
+
"eval_loss": 0.9539378881454468,
|
| 285 |
+
"eval_runtime": 9.6357,
|
| 286 |
+
"eval_samples_per_second": 13.18,
|
| 287 |
+
"eval_steps_per_second": 1.66,
|
| 288 |
+
"step": 429
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"epoch": 3.01,
|
| 292 |
+
"learning_rate": 7.972027972027973e-06,
|
| 293 |
+
"loss": 1.0267,
|
| 294 |
+
"step": 430
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 3.08,
|
| 298 |
+
"learning_rate": 7.692307692307694e-06,
|
| 299 |
+
"loss": 1.042,
|
| 300 |
+
"step": 440
|
| 301 |
+
},
|
| 302 |
+
{
|
| 303 |
+
"epoch": 3.15,
|
| 304 |
+
"learning_rate": 7.412587412587413e-06,
|
| 305 |
+
"loss": 0.8939,
|
| 306 |
+
"step": 450
|
| 307 |
+
},
|
| 308 |
+
{
|
| 309 |
+
"epoch": 3.22,
|
| 310 |
+
"learning_rate": 7.132867132867134e-06,
|
| 311 |
+
"loss": 1.0723,
|
| 312 |
+
"step": 460
|
| 313 |
+
},
|
| 314 |
+
{
|
| 315 |
+
"epoch": 3.29,
|
| 316 |
+
"learning_rate": 6.853146853146854e-06,
|
| 317 |
+
"loss": 1.0155,
|
| 318 |
+
"step": 470
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 3.36,
|
| 322 |
+
"learning_rate": 6.573426573426574e-06,
|
| 323 |
+
"loss": 1.0215,
|
| 324 |
+
"step": 480
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 3.43,
|
| 328 |
+
"learning_rate": 6.2937062937062944e-06,
|
| 329 |
+
"loss": 0.9736,
|
| 330 |
+
"step": 490
|
| 331 |
+
},
|
| 332 |
+
{
|
| 333 |
+
"epoch": 3.5,
|
| 334 |
+
"learning_rate": 6.013986013986014e-06,
|
| 335 |
+
"loss": 0.968,
|
| 336 |
+
"step": 500
|
| 337 |
+
},
|
| 338 |
+
{
|
| 339 |
+
"epoch": 3.57,
|
| 340 |
+
"learning_rate": 5.7342657342657345e-06,
|
| 341 |
+
"loss": 0.9836,
|
| 342 |
+
"step": 510
|
| 343 |
+
},
|
| 344 |
+
{
|
| 345 |
+
"epoch": 3.64,
|
| 346 |
+
"learning_rate": 5.4545454545454545e-06,
|
| 347 |
+
"loss": 0.9847,
|
| 348 |
+
"step": 520
|
| 349 |
+
},
|
| 350 |
+
{
|
| 351 |
+
"epoch": 3.71,
|
| 352 |
+
"learning_rate": 5.174825174825175e-06,
|
| 353 |
+
"loss": 0.9006,
|
| 354 |
+
"step": 530
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 3.78,
|
| 358 |
+
"learning_rate": 4.895104895104895e-06,
|
| 359 |
+
"loss": 0.9513,
|
| 360 |
+
"step": 540
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 3.85,
|
| 364 |
+
"learning_rate": 4.615384615384616e-06,
|
| 365 |
+
"loss": 0.7749,
|
| 366 |
+
"step": 550
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 3.92,
|
| 370 |
+
"learning_rate": 4.335664335664336e-06,
|
| 371 |
+
"loss": 0.8459,
|
| 372 |
+
"step": 560
|
| 373 |
+
},
|
| 374 |
+
{
|
| 375 |
+
"epoch": 3.99,
|
| 376 |
+
"learning_rate": 4.055944055944056e-06,
|
| 377 |
+
"loss": 0.9689,
|
| 378 |
+
"step": 570
|
| 379 |
+
},
|
| 380 |
+
{
|
| 381 |
+
"epoch": 4.0,
|
| 382 |
+
"eval_accuracy": 0.7322834645669292,
|
| 383 |
+
"eval_loss": 0.8723652958869934,
|
| 384 |
+
"eval_runtime": 9.8772,
|
| 385 |
+
"eval_samples_per_second": 12.858,
|
| 386 |
+
"eval_steps_per_second": 1.62,
|
| 387 |
+
"step": 572
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 4.06,
|
| 391 |
+
"learning_rate": 3.776223776223776e-06,
|
| 392 |
+
"loss": 0.9308,
|
| 393 |
+
"step": 580
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 4.13,
|
| 397 |
+
"learning_rate": 3.4965034965034966e-06,
|
| 398 |
+
"loss": 0.9629,
|
| 399 |
+
"step": 590
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 4.2,
|
| 403 |
+
"learning_rate": 3.216783216783217e-06,
|
| 404 |
+
"loss": 0.9307,
|
| 405 |
+
"step": 600
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 4.27,
|
| 409 |
+
"learning_rate": 2.937062937062937e-06,
|
| 410 |
+
"loss": 0.8897,
|
| 411 |
+
"step": 610
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 4.34,
|
| 415 |
+
"learning_rate": 2.6573426573426574e-06,
|
| 416 |
+
"loss": 0.921,
|
| 417 |
+
"step": 620
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 4.41,
|
| 421 |
+
"learning_rate": 2.377622377622378e-06,
|
| 422 |
+
"loss": 0.9482,
|
| 423 |
+
"step": 630
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 4.48,
|
| 427 |
+
"learning_rate": 2.0979020979020983e-06,
|
| 428 |
+
"loss": 0.9577,
|
| 429 |
+
"step": 640
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 4.55,
|
| 433 |
+
"learning_rate": 1.8181818181818183e-06,
|
| 434 |
+
"loss": 0.8544,
|
| 435 |
+
"step": 650
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 4.62,
|
| 439 |
+
"learning_rate": 1.5384615384615387e-06,
|
| 440 |
+
"loss": 0.9408,
|
| 441 |
+
"step": 660
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 4.69,
|
| 445 |
+
"learning_rate": 1.258741258741259e-06,
|
| 446 |
+
"loss": 0.8936,
|
| 447 |
+
"step": 670
|
| 448 |
+
},
|
| 449 |
+
{
|
| 450 |
+
"epoch": 4.76,
|
| 451 |
+
"learning_rate": 9.790209790209791e-07,
|
| 452 |
+
"loss": 0.9222,
|
| 453 |
+
"step": 680
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 4.83,
|
| 457 |
+
"learning_rate": 6.993006993006994e-07,
|
| 458 |
+
"loss": 0.8527,
|
| 459 |
+
"step": 690
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 4.9,
|
| 463 |
+
"learning_rate": 4.195804195804196e-07,
|
| 464 |
+
"loss": 0.8538,
|
| 465 |
+
"step": 700
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 4.97,
|
| 469 |
+
"learning_rate": 1.3986013986013987e-07,
|
| 470 |
+
"loss": 0.9175,
|
| 471 |
+
"step": 710
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 5.0,
|
| 475 |
+
"eval_accuracy": 0.7322834645669292,
|
| 476 |
+
"eval_loss": 0.8530173897743225,
|
| 477 |
+
"eval_runtime": 12.0509,
|
| 478 |
+
"eval_samples_per_second": 10.539,
|
| 479 |
+
"eval_steps_per_second": 1.328,
|
| 480 |
+
"step": 715
|
| 481 |
+
},
|
| 482 |
+
{
|
| 483 |
+
"epoch": 5.0,
|
| 484 |
+
"step": 715,
|
| 485 |
+
"total_flos": 4.424951239059456e+17,
|
| 486 |
+
"train_loss": 0.18311181501908735,
|
| 487 |
+
"train_runtime": 299.5589,
|
| 488 |
+
"train_samples_per_second": 19.061,
|
| 489 |
+
"train_steps_per_second": 2.387
|
| 490 |
+
}
|
| 491 |
+
],
|
| 492 |
+
"logging_steps": 10,
|
| 493 |
+
"max_steps": 715,
|
| 494 |
+
"num_input_tokens_seen": 0,
|
| 495 |
+
"num_train_epochs": 5,
|
| 496 |
+
"save_steps": 500,
|
| 497 |
+
"total_flos": 4.424951239059456e+17,
|
| 498 |
+
"train_batch_size": 8,
|
| 499 |
+
"trial_name": null,
|
| 500 |
+
"trial_params": null
|
| 501 |
+
}
|