Commit
•
e9c907c
1
Parent(s):
c569782
Upload trainer_state.json
Browse files- trainer_state.json +106 -0
trainer_state.json
ADDED
|
@@ -0,0 +1,106 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.976475715637207,
|
| 3 |
+
"best_model_checkpoint": "microsoft-swin-base-patch4-window7-224_bert-base-multilingual-cased_bert-base-multilingual-cased/checkpoint-3864",
|
| 4 |
+
"epoch": 6.0,
|
| 5 |
+
"global_step": 3864,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.78,
|
| 12 |
+
"learning_rate": 3.923136645962734e-05,
|
| 13 |
+
"loss": 2.2925,
|
| 14 |
+
"step": 500
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 1.0,
|
| 18 |
+
"eval_loss": 1.6365079879760742,
|
| 19 |
+
"eval_runtime": 232.7485,
|
| 20 |
+
"eval_samples_per_second": 11.068,
|
| 21 |
+
"eval_steps_per_second": 0.692,
|
| 22 |
+
"step": 644
|
| 23 |
+
},
|
| 24 |
+
{
|
| 25 |
+
"epoch": 1.55,
|
| 26 |
+
"learning_rate": 3.845496894409938e-05,
|
| 27 |
+
"loss": 1.4969,
|
| 28 |
+
"step": 1000
|
| 29 |
+
},
|
| 30 |
+
{
|
| 31 |
+
"epoch": 2.0,
|
| 32 |
+
"eval_loss": 1.3718241453170776,
|
| 33 |
+
"eval_runtime": 40.4125,
|
| 34 |
+
"eval_samples_per_second": 63.743,
|
| 35 |
+
"eval_steps_per_second": 3.984,
|
| 36 |
+
"step": 1288
|
| 37 |
+
},
|
| 38 |
+
{
|
| 39 |
+
"epoch": 2.33,
|
| 40 |
+
"learning_rate": 3.7678571428571433e-05,
|
| 41 |
+
"loss": 1.2926,
|
| 42 |
+
"step": 1500
|
| 43 |
+
},
|
| 44 |
+
{
|
| 45 |
+
"epoch": 3.0,
|
| 46 |
+
"eval_loss": 1.1062968969345093,
|
| 47 |
+
"eval_runtime": 40.4904,
|
| 48 |
+
"eval_samples_per_second": 63.62,
|
| 49 |
+
"eval_steps_per_second": 3.976,
|
| 50 |
+
"step": 1932
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 3.11,
|
| 54 |
+
"learning_rate": 3.690217391304348e-05,
|
| 55 |
+
"loss": 1.1515,
|
| 56 |
+
"step": 2000
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 3.88,
|
| 60 |
+
"learning_rate": 3.612577639751553e-05,
|
| 61 |
+
"loss": 1.0376,
|
| 62 |
+
"step": 2500
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 4.0,
|
| 66 |
+
"eval_loss": 1.0416237115859985,
|
| 67 |
+
"eval_runtime": 40.3883,
|
| 68 |
+
"eval_samples_per_second": 63.781,
|
| 69 |
+
"eval_steps_per_second": 3.986,
|
| 70 |
+
"step": 2576
|
| 71 |
+
},
|
| 72 |
+
{
|
| 73 |
+
"epoch": 4.66,
|
| 74 |
+
"learning_rate": 3.534937888198758e-05,
|
| 75 |
+
"loss": 0.9386,
|
| 76 |
+
"step": 3000
|
| 77 |
+
},
|
| 78 |
+
{
|
| 79 |
+
"epoch": 5.0,
|
| 80 |
+
"eval_loss": 1.0240283012390137,
|
| 81 |
+
"eval_runtime": 40.487,
|
| 82 |
+
"eval_samples_per_second": 63.625,
|
| 83 |
+
"eval_steps_per_second": 3.977,
|
| 84 |
+
"step": 3220
|
| 85 |
+
},
|
| 86 |
+
{
|
| 87 |
+
"epoch": 5.43,
|
| 88 |
+
"learning_rate": 3.4572981366459633e-05,
|
| 89 |
+
"loss": 0.867,
|
| 90 |
+
"step": 3500
|
| 91 |
+
},
|
| 92 |
+
{
|
| 93 |
+
"epoch": 6.0,
|
| 94 |
+
"eval_loss": 0.976475715637207,
|
| 95 |
+
"eval_runtime": 40.4063,
|
| 96 |
+
"eval_samples_per_second": 63.752,
|
| 97 |
+
"eval_steps_per_second": 3.985,
|
| 98 |
+
"step": 3864
|
| 99 |
+
}
|
| 100 |
+
],
|
| 101 |
+
"max_steps": 25760,
|
| 102 |
+
"num_train_epochs": 40,
|
| 103 |
+
"total_flos": 1.1256086855275315e+19,
|
| 104 |
+
"trial_name": null,
|
| 105 |
+
"trial_params": null
|
| 106 |
+
}
|