Commit
•
10f8ee9
1
Parent(s):
829107c
Upload trainer_state.json
Browse files- trainer_state.json +114 -0
trainer_state.json
ADDED
|
@@ -0,0 +1,114 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 6.990967741935484,
|
| 5 |
+
"global_step": 336,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.99,
|
| 12 |
+
"learning_rate": 9e-06,
|
| 13 |
+
"loss": 0.4828,
|
| 14 |
+
"step": 48
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.99,
|
| 18 |
+
"eval_acc": 86.17021276595744,
|
| 19 |
+
"eval_loss": 0.3562283217906952,
|
| 20 |
+
"eval_runtime": 82.5249,
|
| 21 |
+
"eval_samples_per_second": 4.556,
|
| 22 |
+
"step": 48
|
| 23 |
+
},
|
| 24 |
+
{
|
| 25 |
+
"epoch": 1.99,
|
| 26 |
+
"learning_rate": 8.000000000000001e-06,
|
| 27 |
+
"loss": 0.1477,
|
| 28 |
+
"step": 96
|
| 29 |
+
},
|
| 30 |
+
{
|
| 31 |
+
"epoch": 1.99,
|
| 32 |
+
"eval_acc": 85.63829787234043,
|
| 33 |
+
"eval_loss": 0.3522704243659973,
|
| 34 |
+
"eval_runtime": 82.6705,
|
| 35 |
+
"eval_samples_per_second": 4.548,
|
| 36 |
+
"step": 96
|
| 37 |
+
},
|
| 38 |
+
{
|
| 39 |
+
"epoch": 2.99,
|
| 40 |
+
"learning_rate": 7e-06,
|
| 41 |
+
"loss": 0.0398,
|
| 42 |
+
"step": 144
|
| 43 |
+
},
|
| 44 |
+
{
|
| 45 |
+
"epoch": 2.99,
|
| 46 |
+
"eval_acc": 87.76595744680851,
|
| 47 |
+
"eval_loss": 0.7263116836547852,
|
| 48 |
+
"eval_runtime": 82.5944,
|
| 49 |
+
"eval_samples_per_second": 4.552,
|
| 50 |
+
"step": 144
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 3.99,
|
| 54 |
+
"learning_rate": 6e-06,
|
| 55 |
+
"loss": 0.0179,
|
| 56 |
+
"step": 192
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 3.99,
|
| 60 |
+
"eval_acc": 87.5,
|
| 61 |
+
"eval_loss": 0.8694424033164978,
|
| 62 |
+
"eval_runtime": 82.5077,
|
| 63 |
+
"eval_samples_per_second": 4.557,
|
| 64 |
+
"step": 192
|
| 65 |
+
},
|
| 66 |
+
{
|
| 67 |
+
"epoch": 4.99,
|
| 68 |
+
"learning_rate": 5e-06,
|
| 69 |
+
"loss": 0.0047,
|
| 70 |
+
"step": 240
|
| 71 |
+
},
|
| 72 |
+
{
|
| 73 |
+
"epoch": 4.99,
|
| 74 |
+
"eval_acc": 86.70212765957447,
|
| 75 |
+
"eval_loss": 1.1555883884429932,
|
| 76 |
+
"eval_runtime": 82.5664,
|
| 77 |
+
"eval_samples_per_second": 4.554,
|
| 78 |
+
"step": 240
|
| 79 |
+
},
|
| 80 |
+
{
|
| 81 |
+
"epoch": 5.99,
|
| 82 |
+
"learning_rate": 4.000000000000001e-06,
|
| 83 |
+
"loss": 0.0005,
|
| 84 |
+
"step": 288
|
| 85 |
+
},
|
| 86 |
+
{
|
| 87 |
+
"epoch": 5.99,
|
| 88 |
+
"eval_acc": 89.09574468085107,
|
| 89 |
+
"eval_loss": 1.2453709840774536,
|
| 90 |
+
"eval_runtime": 82.6312,
|
| 91 |
+
"eval_samples_per_second": 4.55,
|
| 92 |
+
"step": 288
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 6.99,
|
| 96 |
+
"learning_rate": 3e-06,
|
| 97 |
+
"loss": 0.0004,
|
| 98 |
+
"step": 336
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 6.99,
|
| 102 |
+
"eval_acc": 89.09574468085107,
|
| 103 |
+
"eval_loss": 1.210463523864746,
|
| 104 |
+
"eval_runtime": 82.502,
|
| 105 |
+
"eval_samples_per_second": 4.557,
|
| 106 |
+
"step": 336
|
| 107 |
+
}
|
| 108 |
+
],
|
| 109 |
+
"max_steps": 480,
|
| 110 |
+
"num_train_epochs": 10,
|
| 111 |
+
"total_flos": 1.4028769825494106e+17,
|
| 112 |
+
"trial_name": null,
|
| 113 |
+
"trial_params": null
|
| 114 |
+
}
|