Upload trainer_state.json
Browse files- trainer_state.json +98 -0
trainer_state.json
ADDED
|
@@ -0,0 +1,98 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 5.0,
|
| 5 |
+
"global_step": 3995,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.63,
|
| 12 |
+
"learning_rate": 1.7496871088861077e-05,
|
| 13 |
+
"loss": 0.5079,
|
| 14 |
+
"step": 500
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 1.0,
|
| 18 |
+
"eval_loss": 0.5189032554626465,
|
| 19 |
+
"eval_runtime": 2.8243,
|
| 20 |
+
"eval_samples_per_second": 1225.772,
|
| 21 |
+
"eval_steps_per_second": 9.914,
|
| 22 |
+
"step": 799
|
| 23 |
+
},
|
| 24 |
+
{
|
| 25 |
+
"epoch": 1.25,
|
| 26 |
+
"learning_rate": 1.4993742177722154e-05,
|
| 27 |
+
"loss": 0.4379,
|
| 28 |
+
"step": 1000
|
| 29 |
+
},
|
| 30 |
+
{
|
| 31 |
+
"epoch": 1.88,
|
| 32 |
+
"learning_rate": 1.249061326658323e-05,
|
| 33 |
+
"loss": 0.3846,
|
| 34 |
+
"step": 1500
|
| 35 |
+
},
|
| 36 |
+
{
|
| 37 |
+
"epoch": 2.0,
|
| 38 |
+
"eval_loss": 0.5475935935974121,
|
| 39 |
+
"eval_runtime": 2.8018,
|
| 40 |
+
"eval_samples_per_second": 1235.643,
|
| 41 |
+
"eval_steps_per_second": 9.994,
|
| 42 |
+
"step": 1598
|
| 43 |
+
},
|
| 44 |
+
{
|
| 45 |
+
"epoch": 2.5,
|
| 46 |
+
"learning_rate": 9.987484355444305e-06,
|
| 47 |
+
"loss": 0.3219,
|
| 48 |
+
"step": 2000
|
| 49 |
+
},
|
| 50 |
+
{
|
| 51 |
+
"epoch": 3.0,
|
| 52 |
+
"eval_loss": 0.5914019346237183,
|
| 53 |
+
"eval_runtime": 2.7995,
|
| 54 |
+
"eval_samples_per_second": 1236.649,
|
| 55 |
+
"eval_steps_per_second": 10.002,
|
| 56 |
+
"step": 2397
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 3.13,
|
| 60 |
+
"learning_rate": 7.484355444305382e-06,
|
| 61 |
+
"loss": 0.2964,
|
| 62 |
+
"step": 2500
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 3.75,
|
| 66 |
+
"learning_rate": 4.981226533166458e-06,
|
| 67 |
+
"loss": 0.2524,
|
| 68 |
+
"step": 3000
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 4.0,
|
| 72 |
+
"eval_loss": 0.6955985426902771,
|
| 73 |
+
"eval_runtime": 2.8279,
|
| 74 |
+
"eval_samples_per_second": 1224.237,
|
| 75 |
+
"eval_steps_per_second": 9.901,
|
| 76 |
+
"step": 3196
|
| 77 |
+
},
|
| 78 |
+
{
|
| 79 |
+
"epoch": 4.38,
|
| 80 |
+
"learning_rate": 2.4780976220275346e-06,
|
| 81 |
+
"loss": 0.2253,
|
| 82 |
+
"step": 3500
|
| 83 |
+
},
|
| 84 |
+
{
|
| 85 |
+
"epoch": 5.0,
|
| 86 |
+
"eval_loss": 0.7501208186149597,
|
| 87 |
+
"eval_runtime": 2.7917,
|
| 88 |
+
"eval_samples_per_second": 1240.104,
|
| 89 |
+
"eval_steps_per_second": 10.03,
|
| 90 |
+
"step": 3995
|
| 91 |
+
}
|
| 92 |
+
],
|
| 93 |
+
"max_steps": 3995,
|
| 94 |
+
"num_train_epochs": 5,
|
| 95 |
+
"total_flos": 1.804454718241824e+16,
|
| 96 |
+
"trial_name": null,
|
| 97 |
+
"trial_params": null
|
| 98 |
+
}
|