Upload trainer_state.json
Browse files- trainer_state.json +112 -0
trainer_state.json
ADDED
|
@@ -0,0 +1,112 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 6.0606060606060606,
|
| 5 |
+
"global_step": 3000,
|
| 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": 1.6203636363636364e-05,
|
| 13 |
+
"loss": 0.8991,
|
| 14 |
+
"step": 494
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 1.0,
|
| 18 |
+
"eval_accuracy": 0.7804532577903682,
|
| 19 |
+
"eval_f1": 0.7820792833566528,
|
| 20 |
+
"eval_loss": 0.6184162497520447,
|
| 21 |
+
"eval_runtime": 88.3049,
|
| 22 |
+
"eval_samples_per_second": 47.97,
|
| 23 |
+
"eval_steps_per_second": 2.401,
|
| 24 |
+
"step": 495
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 2.0,
|
| 28 |
+
"learning_rate": 1.440727272727273e-05,
|
| 29 |
+
"loss": 0.5228,
|
| 30 |
+
"step": 988
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 2.0,
|
| 34 |
+
"eval_accuracy": 0.8182247403210576,
|
| 35 |
+
"eval_f1": 0.8195587712666443,
|
| 36 |
+
"eval_loss": 0.5347467660903931,
|
| 37 |
+
"eval_runtime": 88.3154,
|
| 38 |
+
"eval_samples_per_second": 47.964,
|
| 39 |
+
"eval_steps_per_second": 2.4,
|
| 40 |
+
"step": 990
|
| 41 |
+
},
|
| 42 |
+
{
|
| 43 |
+
"epoch": 2.99,
|
| 44 |
+
"learning_rate": 1.2610909090909091e-05,
|
| 45 |
+
"loss": 0.3661,
|
| 46 |
+
"step": 1482
|
| 47 |
+
},
|
| 48 |
+
{
|
| 49 |
+
"epoch": 3.0,
|
| 50 |
+
"eval_accuracy": 0.8458451369216242,
|
| 51 |
+
"eval_f1": 0.8456365209622985,
|
| 52 |
+
"eval_loss": 0.47167500853538513,
|
| 53 |
+
"eval_runtime": 88.276,
|
| 54 |
+
"eval_samples_per_second": 47.986,
|
| 55 |
+
"eval_steps_per_second": 2.402,
|
| 56 |
+
"step": 1485
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 3.99,
|
| 60 |
+
"learning_rate": 1.0814545454545455e-05,
|
| 61 |
+
"loss": 0.2528,
|
| 62 |
+
"step": 1976
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 4.0,
|
| 66 |
+
"eval_accuracy": 0.8359301227573183,
|
| 67 |
+
"eval_f1": 0.8334971747863884,
|
| 68 |
+
"eval_loss": 0.5231624245643616,
|
| 69 |
+
"eval_runtime": 88.232,
|
| 70 |
+
"eval_samples_per_second": 48.01,
|
| 71 |
+
"eval_steps_per_second": 2.403,
|
| 72 |
+
"step": 1980
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 4.99,
|
| 76 |
+
"learning_rate": 9.018181818181818e-06,
|
| 77 |
+
"loss": 0.1714,
|
| 78 |
+
"step": 2470
|
| 79 |
+
},
|
| 80 |
+
{
|
| 81 |
+
"epoch": 5.0,
|
| 82 |
+
"eval_accuracy": 0.8621340887629839,
|
| 83 |
+
"eval_f1": 0.8597728023734812,
|
| 84 |
+
"eval_loss": 0.5139923095703125,
|
| 85 |
+
"eval_runtime": 88.2994,
|
| 86 |
+
"eval_samples_per_second": 47.973,
|
| 87 |
+
"eval_steps_per_second": 2.401,
|
| 88 |
+
"step": 2475
|
| 89 |
+
},
|
| 90 |
+
{
|
| 91 |
+
"epoch": 5.99,
|
| 92 |
+
"learning_rate": 7.221818181818181e-06,
|
| 93 |
+
"loss": 0.1313,
|
| 94 |
+
"step": 2964
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 6.0,
|
| 98 |
+
"eval_accuracy": 0.8611898016997167,
|
| 99 |
+
"eval_f1": 0.8589456922670535,
|
| 100 |
+
"eval_loss": 0.6027271747589111,
|
| 101 |
+
"eval_runtime": 88.3228,
|
| 102 |
+
"eval_samples_per_second": 47.96,
|
| 103 |
+
"eval_steps_per_second": 2.4,
|
| 104 |
+
"step": 2970
|
| 105 |
+
}
|
| 106 |
+
],
|
| 107 |
+
"max_steps": 4950,
|
| 108 |
+
"num_train_epochs": 10,
|
| 109 |
+
"total_flos": 5479149586954968.0,
|
| 110 |
+
"trial_name": null,
|
| 111 |
+
"trial_params": null
|
| 112 |
+
}
|