End of training
Browse files- all_results.json +8 -0
- test_results.json +8 -0
- trainer_state.json +136 -0
all_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 9.1,
|
| 3 |
+
"eval_accuracy": 1.0,
|
| 4 |
+
"eval_loss": 0.495527982711792,
|
| 5 |
+
"eval_runtime": 4.8094,
|
| 6 |
+
"eval_samples_per_second": 0.416,
|
| 7 |
+
"eval_steps_per_second": 0.416
|
| 8 |
+
}
|
test_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 9.1,
|
| 3 |
+
"eval_accuracy": 1.0,
|
| 4 |
+
"eval_loss": 0.495527982711792,
|
| 5 |
+
"eval_runtime": 4.8094,
|
| 6 |
+
"eval_samples_per_second": 0.416,
|
| 7 |
+
"eval_steps_per_second": 0.416
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,136 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 1.0,
|
| 3 |
+
"best_model_checkpoint": "videomae-base-finetuned-ucf101-subset-SBDtoy/checkpoint-6",
|
| 4 |
+
"epoch": 9.1,
|
| 5 |
+
"global_step": 20,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.1,
|
| 12 |
+
"eval_accuracy": 0.5,
|
| 13 |
+
"eval_loss": 0.6590014696121216,
|
| 14 |
+
"eval_runtime": 4.5937,
|
| 15 |
+
"eval_samples_per_second": 0.435,
|
| 16 |
+
"eval_steps_per_second": 0.435,
|
| 17 |
+
"step": 2
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 1.1,
|
| 21 |
+
"eval_accuracy": 0.5,
|
| 22 |
+
"eval_loss": 0.5487387776374817,
|
| 23 |
+
"eval_runtime": 4.2064,
|
| 24 |
+
"eval_samples_per_second": 0.475,
|
| 25 |
+
"eval_steps_per_second": 0.475,
|
| 26 |
+
"step": 4
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 2.1,
|
| 30 |
+
"eval_accuracy": 1.0,
|
| 31 |
+
"eval_loss": 0.495527982711792,
|
| 32 |
+
"eval_runtime": 4.8671,
|
| 33 |
+
"eval_samples_per_second": 0.411,
|
| 34 |
+
"eval_steps_per_second": 0.411,
|
| 35 |
+
"step": 6
|
| 36 |
+
},
|
| 37 |
+
{
|
| 38 |
+
"epoch": 3.1,
|
| 39 |
+
"eval_accuracy": 0.5,
|
| 40 |
+
"eval_loss": 0.5463187098503113,
|
| 41 |
+
"eval_runtime": 4.4465,
|
| 42 |
+
"eval_samples_per_second": 0.45,
|
| 43 |
+
"eval_steps_per_second": 0.45,
|
| 44 |
+
"step": 8
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 4.1,
|
| 48 |
+
"learning_rate": 2.777777777777778e-05,
|
| 49 |
+
"loss": 0.4651,
|
| 50 |
+
"step": 10
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 4.1,
|
| 54 |
+
"eval_accuracy": 0.5,
|
| 55 |
+
"eval_loss": 0.5728206634521484,
|
| 56 |
+
"eval_runtime": 4.8812,
|
| 57 |
+
"eval_samples_per_second": 0.41,
|
| 58 |
+
"eval_steps_per_second": 0.41,
|
| 59 |
+
"step": 10
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 5.1,
|
| 63 |
+
"eval_accuracy": 0.5,
|
| 64 |
+
"eval_loss": 0.5635135173797607,
|
| 65 |
+
"eval_runtime": 4.1811,
|
| 66 |
+
"eval_samples_per_second": 0.478,
|
| 67 |
+
"eval_steps_per_second": 0.478,
|
| 68 |
+
"step": 12
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 6.1,
|
| 72 |
+
"eval_accuracy": 0.5,
|
| 73 |
+
"eval_loss": 0.6039651036262512,
|
| 74 |
+
"eval_runtime": 4.5568,
|
| 75 |
+
"eval_samples_per_second": 0.439,
|
| 76 |
+
"eval_steps_per_second": 0.439,
|
| 77 |
+
"step": 14
|
| 78 |
+
},
|
| 79 |
+
{
|
| 80 |
+
"epoch": 7.1,
|
| 81 |
+
"eval_accuracy": 0.5,
|
| 82 |
+
"eval_loss": 0.6417381763458252,
|
| 83 |
+
"eval_runtime": 4.1268,
|
| 84 |
+
"eval_samples_per_second": 0.485,
|
| 85 |
+
"eval_steps_per_second": 0.485,
|
| 86 |
+
"step": 16
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 8.1,
|
| 90 |
+
"eval_accuracy": 0.5,
|
| 91 |
+
"eval_loss": 0.6530583500862122,
|
| 92 |
+
"eval_runtime": 4.4257,
|
| 93 |
+
"eval_samples_per_second": 0.452,
|
| 94 |
+
"eval_steps_per_second": 0.452,
|
| 95 |
+
"step": 18
|
| 96 |
+
},
|
| 97 |
+
{
|
| 98 |
+
"epoch": 9.1,
|
| 99 |
+
"learning_rate": 0.0,
|
| 100 |
+
"loss": 0.122,
|
| 101 |
+
"step": 20
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 9.1,
|
| 105 |
+
"eval_accuracy": 0.5,
|
| 106 |
+
"eval_loss": 0.6686117649078369,
|
| 107 |
+
"eval_runtime": 4.2322,
|
| 108 |
+
"eval_samples_per_second": 0.473,
|
| 109 |
+
"eval_steps_per_second": 0.473,
|
| 110 |
+
"step": 20
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 9.1,
|
| 114 |
+
"step": 20,
|
| 115 |
+
"total_flos": 2.492129178943488e+16,
|
| 116 |
+
"train_loss": 0.2935513317584991,
|
| 117 |
+
"train_runtime": 388.5356,
|
| 118 |
+
"train_samples_per_second": 0.051,
|
| 119 |
+
"train_steps_per_second": 0.051
|
| 120 |
+
},
|
| 121 |
+
{
|
| 122 |
+
"epoch": 9.1,
|
| 123 |
+
"eval_accuracy": 1.0,
|
| 124 |
+
"eval_loss": 0.495527982711792,
|
| 125 |
+
"eval_runtime": 4.8094,
|
| 126 |
+
"eval_samples_per_second": 0.416,
|
| 127 |
+
"eval_steps_per_second": 0.416,
|
| 128 |
+
"step": 20
|
| 129 |
+
}
|
| 130 |
+
],
|
| 131 |
+
"max_steps": 20,
|
| 132 |
+
"num_train_epochs": 9223372036854775807,
|
| 133 |
+
"total_flos": 2.492129178943488e+16,
|
| 134 |
+
"trial_name": null,
|
| 135 |
+
"trial_params": null
|
| 136 |
+
}
|