End of training
Browse files- all_results.json +8 -0
- train_results.json +8 -0
- trainer_state.json +136 -0
all_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.98,
|
| 3 |
+
"total_flos": 1.1739110279510753e+18,
|
| 4 |
+
"train_loss": 1.9657008977646524,
|
| 5 |
+
"train_runtime": 10337.147,
|
| 6 |
+
"train_samples_per_second": 3.501,
|
| 7 |
+
"train_steps_per_second": 0.014
|
| 8 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.98,
|
| 3 |
+
"total_flos": 1.1739110279510753e+18,
|
| 4 |
+
"train_loss": 1.9657008977646524,
|
| 5 |
+
"train_runtime": 10337.147,
|
| 6 |
+
"train_samples_per_second": 3.501,
|
| 7 |
+
"train_steps_per_second": 0.014
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,136 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.796875,
|
| 3 |
+
"best_model_checkpoint": "swinv2-tiny-patch4-window8-256-finetuned-thai/checkpoint-141",
|
| 4 |
+
"epoch": 2.984126984126984,
|
| 5 |
+
"global_step": 141,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.21,
|
| 12 |
+
"learning_rate": 3.3333333333333335e-05,
|
| 13 |
+
"loss": 3.9036,
|
| 14 |
+
"step": 10
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.42,
|
| 18 |
+
"learning_rate": 4.801587301587302e-05,
|
| 19 |
+
"loss": 3.6941,
|
| 20 |
+
"step": 20
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.63,
|
| 24 |
+
"learning_rate": 4.404761904761905e-05,
|
| 25 |
+
"loss": 3.2435,
|
| 26 |
+
"step": 30
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.85,
|
| 30 |
+
"learning_rate": 4.007936507936508e-05,
|
| 31 |
+
"loss": 2.6781,
|
| 32 |
+
"step": 40
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.99,
|
| 36 |
+
"eval_accuracy": 0.5475,
|
| 37 |
+
"eval_loss": 1.804018497467041,
|
| 38 |
+
"eval_runtime": 1355.5013,
|
| 39 |
+
"eval_samples_per_second": 1.18,
|
| 40 |
+
"eval_steps_per_second": 0.018,
|
| 41 |
+
"step": 47
|
| 42 |
+
},
|
| 43 |
+
{
|
| 44 |
+
"epoch": 1.06,
|
| 45 |
+
"learning_rate": 3.611111111111111e-05,
|
| 46 |
+
"loss": 2.1369,
|
| 47 |
+
"step": 50
|
| 48 |
+
},
|
| 49 |
+
{
|
| 50 |
+
"epoch": 1.27,
|
| 51 |
+
"learning_rate": 3.2142857142857144e-05,
|
| 52 |
+
"loss": 1.7713,
|
| 53 |
+
"step": 60
|
| 54 |
+
},
|
| 55 |
+
{
|
| 56 |
+
"epoch": 1.48,
|
| 57 |
+
"learning_rate": 2.8174603174603175e-05,
|
| 58 |
+
"loss": 1.5953,
|
| 59 |
+
"step": 70
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 1.69,
|
| 63 |
+
"learning_rate": 2.4206349206349206e-05,
|
| 64 |
+
"loss": 1.4488,
|
| 65 |
+
"step": 80
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 1.9,
|
| 69 |
+
"learning_rate": 2.023809523809524e-05,
|
| 70 |
+
"loss": 1.3191,
|
| 71 |
+
"step": 90
|
| 72 |
+
},
|
| 73 |
+
{
|
| 74 |
+
"epoch": 1.99,
|
| 75 |
+
"eval_accuracy": 0.745,
|
| 76 |
+
"eval_loss": 0.9501311779022217,
|
| 77 |
+
"eval_runtime": 43.9724,
|
| 78 |
+
"eval_samples_per_second": 36.386,
|
| 79 |
+
"eval_steps_per_second": 0.569,
|
| 80 |
+
"step": 94
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 2.12,
|
| 84 |
+
"learning_rate": 1.626984126984127e-05,
|
| 85 |
+
"loss": 1.2881,
|
| 86 |
+
"step": 100
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 2.33,
|
| 90 |
+
"learning_rate": 1.2301587301587301e-05,
|
| 91 |
+
"loss": 1.211,
|
| 92 |
+
"step": 110
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 2.54,
|
| 96 |
+
"learning_rate": 8.333333333333334e-06,
|
| 97 |
+
"loss": 1.1237,
|
| 98 |
+
"step": 120
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 2.75,
|
| 102 |
+
"learning_rate": 4.365079365079365e-06,
|
| 103 |
+
"loss": 1.1179,
|
| 104 |
+
"step": 130
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 2.96,
|
| 108 |
+
"learning_rate": 3.9682539682539683e-07,
|
| 109 |
+
"loss": 1.078,
|
| 110 |
+
"step": 140
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 2.98,
|
| 114 |
+
"eval_accuracy": 0.796875,
|
| 115 |
+
"eval_loss": 0.776684582233429,
|
| 116 |
+
"eval_runtime": 43.7767,
|
| 117 |
+
"eval_samples_per_second": 36.549,
|
| 118 |
+
"eval_steps_per_second": 0.571,
|
| 119 |
+
"step": 141
|
| 120 |
+
},
|
| 121 |
+
{
|
| 122 |
+
"epoch": 2.98,
|
| 123 |
+
"step": 141,
|
| 124 |
+
"total_flos": 1.1739110279510753e+18,
|
| 125 |
+
"train_loss": 1.9657008977646524,
|
| 126 |
+
"train_runtime": 10337.147,
|
| 127 |
+
"train_samples_per_second": 3.501,
|
| 128 |
+
"train_steps_per_second": 0.014
|
| 129 |
+
}
|
| 130 |
+
],
|
| 131 |
+
"max_steps": 141,
|
| 132 |
+
"num_train_epochs": 3,
|
| 133 |
+
"total_flos": 1.1739110279510753e+18,
|
| 134 |
+
"trial_name": null,
|
| 135 |
+
"trial_params": null
|
| 136 |
+
}
|