Upload trainer_state.json
Browse files- trainer_state.json +121 -0
trainer_state.json
ADDED
|
@@ -0,0 +1,121 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 5.0,
|
| 5 |
+
"global_step": 36725,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 1.0,
|
| 12 |
+
"learning_rate": 1.8e-05,
|
| 13 |
+
"loss": 0.0085,
|
| 14 |
+
"step": 7345
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 1.0,
|
| 18 |
+
"eval_EG_f1": 0.9962079135863944,
|
| 19 |
+
"eval_ET_f1": 0.9989276960784315,
|
| 20 |
+
"eval_TE_f1": 0.9956351941189985,
|
| 21 |
+
"eval_loss": 0.002211587270721793,
|
| 22 |
+
"eval_overall_accuracy": 0.9995236481225324,
|
| 23 |
+
"eval_overall_f1": 0.9969235482594433,
|
| 24 |
+
"eval_overall_precision": 0.9969871827605576,
|
| 25 |
+
"eval_overall_recall": 0.9968599218809834,
|
| 26 |
+
"eval_runtime": 329.5116,
|
| 27 |
+
"eval_samples_per_second": 39.625,
|
| 28 |
+
"eval_steps_per_second": 2.479,
|
| 29 |
+
"step": 7345
|
| 30 |
+
},
|
| 31 |
+
{
|
| 32 |
+
"epoch": 2.0,
|
| 33 |
+
"learning_rate": 1.6000000000000003e-05,
|
| 34 |
+
"loss": 0.0014,
|
| 35 |
+
"step": 14690
|
| 36 |
+
},
|
| 37 |
+
{
|
| 38 |
+
"epoch": 2.0,
|
| 39 |
+
"eval_EG_f1": 0.9987363584147042,
|
| 40 |
+
"eval_ET_f1": 0.9995787861382348,
|
| 41 |
+
"eval_TE_f1": 0.9985064910197986,
|
| 42 |
+
"eval_loss": 0.0008891239413060248,
|
| 43 |
+
"eval_overall_accuracy": 0.9998259483524637,
|
| 44 |
+
"eval_overall_f1": 0.9989405562717792,
|
| 45 |
+
"eval_overall_precision": 0.998927805575411,
|
| 46 |
+
"eval_overall_recall": 0.9989533072936612,
|
| 47 |
+
"eval_runtime": 314.9732,
|
| 48 |
+
"eval_samples_per_second": 41.454,
|
| 49 |
+
"eval_steps_per_second": 2.594,
|
| 50 |
+
"step": 14690
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 3.0,
|
| 54 |
+
"learning_rate": 1.4e-05,
|
| 55 |
+
"loss": 0.0008,
|
| 56 |
+
"step": 22035
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 3.0,
|
| 60 |
+
"eval_EG_f1": 0.9983534367221903,
|
| 61 |
+
"eval_ET_f1": 0.9996170636440224,
|
| 62 |
+
"eval_TE_f1": 0.9983917904732731,
|
| 63 |
+
"eval_loss": 0.0008875366183929145,
|
| 64 |
+
"eval_overall_accuracy": 0.999835108965492,
|
| 65 |
+
"eval_overall_f1": 0.9987874146403727,
|
| 66 |
+
"eval_overall_precision": 0.9987491703681013,
|
| 67 |
+
"eval_overall_recall": 0.9988256618416685,
|
| 68 |
+
"eval_runtime": 316.3291,
|
| 69 |
+
"eval_samples_per_second": 41.277,
|
| 70 |
+
"eval_steps_per_second": 2.583,
|
| 71 |
+
"step": 22035
|
| 72 |
+
},
|
| 73 |
+
{
|
| 74 |
+
"epoch": 4.0,
|
| 75 |
+
"learning_rate": 1.2e-05,
|
| 76 |
+
"loss": 0.0005,
|
| 77 |
+
"step": 29380
|
| 78 |
+
},
|
| 79 |
+
{
|
| 80 |
+
"epoch": 4.0,
|
| 81 |
+
"eval_EG_f1": 0.9991574754901962,
|
| 82 |
+
"eval_ET_f1": 0.9996553968679404,
|
| 83 |
+
"eval_TE_f1": 0.9989277782032626,
|
| 84 |
+
"eval_loss": 0.000532182864844799,
|
| 85 |
+
"eval_overall_accuracy": 0.9998717514176049,
|
| 86 |
+
"eval_overall_f1": 0.9992469014462045,
|
| 87 |
+
"eval_overall_precision": 0.9992341468395793,
|
| 88 |
+
"eval_overall_recall": 0.9992596563784433,
|
| 89 |
+
"eval_runtime": 328.7608,
|
| 90 |
+
"eval_samples_per_second": 39.716,
|
| 91 |
+
"eval_steps_per_second": 2.485,
|
| 92 |
+
"step": 29380
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 5.0,
|
| 96 |
+
"learning_rate": 1e-05,
|
| 97 |
+
"loss": 0.0003,
|
| 98 |
+
"step": 36725
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 5.0,
|
| 102 |
+
"eval_EG_f1": 0.9992341272880447,
|
| 103 |
+
"eval_ET_f1": 0.999846825457609,
|
| 104 |
+
"eval_TE_f1": 0.9992724487842237,
|
| 105 |
+
"eval_loss": 0.00026392185827717185,
|
| 106 |
+
"eval_overall_accuracy": 0.9999404560153166,
|
| 107 |
+
"eval_overall_f1": 0.999451131562488,
|
| 108 |
+
"eval_overall_precision": 0.9994383743490248,
|
| 109 |
+
"eval_overall_recall": 0.9994638891016313,
|
| 110 |
+
"eval_runtime": 321.322,
|
| 111 |
+
"eval_samples_per_second": 40.635,
|
| 112 |
+
"eval_steps_per_second": 2.543,
|
| 113 |
+
"step": 36725
|
| 114 |
+
}
|
| 115 |
+
],
|
| 116 |
+
"max_steps": 73450,
|
| 117 |
+
"num_train_epochs": 10,
|
| 118 |
+
"total_flos": 8945844807242016.0,
|
| 119 |
+
"trial_name": null,
|
| 120 |
+
"trial_params": null
|
| 121 |
+
}
|