Commit
·
ddc16b6
1
Parent(s):
1727bbc
End of training
Browse files- trainer_state.json +95 -0
trainer_state.json
ADDED
|
@@ -0,0 +1,95 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 2.070624589920044,
|
| 3 |
+
"best_model_checkpoint": "detr-r50-cd45rb-2ah-6l\\checkpoint-23030",
|
| 4 |
+
"epoch": 5.0,
|
| 5 |
+
"global_step": 23030,
|
| 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": 8.0034737299175e-06,
|
| 13 |
+
"loss": 3.4851,
|
| 14 |
+
"step": 4606
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 1.0,
|
| 18 |
+
"eval_loss": 2.4806125164031982,
|
| 19 |
+
"eval_runtime": 237.1291,
|
| 20 |
+
"eval_samples_per_second": 7.511,
|
| 21 |
+
"eval_steps_per_second": 0.94,
|
| 22 |
+
"step": 4606
|
| 23 |
+
},
|
| 24 |
+
{
|
| 25 |
+
"epoch": 2.0,
|
| 26 |
+
"learning_rate": 6.004776378636562e-06,
|
| 27 |
+
"loss": 2.995,
|
| 28 |
+
"step": 9212
|
| 29 |
+
},
|
| 30 |
+
{
|
| 31 |
+
"epoch": 2.0,
|
| 32 |
+
"eval_loss": 2.2760725021362305,
|
| 33 |
+
"eval_runtime": 207.1825,
|
| 34 |
+
"eval_samples_per_second": 8.596,
|
| 35 |
+
"eval_steps_per_second": 1.076,
|
| 36 |
+
"step": 9212
|
| 37 |
+
},
|
| 38 |
+
{
|
| 39 |
+
"epoch": 3.0,
|
| 40 |
+
"learning_rate": 4.005644811115936e-06,
|
| 41 |
+
"loss": 2.7717,
|
| 42 |
+
"step": 13818
|
| 43 |
+
},
|
| 44 |
+
{
|
| 45 |
+
"epoch": 3.0,
|
| 46 |
+
"eval_loss": 2.160128355026245,
|
| 47 |
+
"eval_runtime": 205.8051,
|
| 48 |
+
"eval_samples_per_second": 8.654,
|
| 49 |
+
"eval_steps_per_second": 1.084,
|
| 50 |
+
"step": 13818
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 4.0,
|
| 54 |
+
"learning_rate": 2.0060790273556234e-06,
|
| 55 |
+
"loss": 2.674,
|
| 56 |
+
"step": 18424
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 4.0,
|
| 60 |
+
"eval_loss": 2.0849480628967285,
|
| 61 |
+
"eval_runtime": 198.2919,
|
| 62 |
+
"eval_samples_per_second": 8.982,
|
| 63 |
+
"eval_steps_per_second": 1.125,
|
| 64 |
+
"step": 18424
|
| 65 |
+
},
|
| 66 |
+
{
|
| 67 |
+
"epoch": 5.0,
|
| 68 |
+
"learning_rate": 6.513243595310465e-09,
|
| 69 |
+
"loss": 2.6185,
|
| 70 |
+
"step": 23030
|
| 71 |
+
},
|
| 72 |
+
{
|
| 73 |
+
"epoch": 5.0,
|
| 74 |
+
"eval_loss": 2.070624589920044,
|
| 75 |
+
"eval_runtime": 204.5209,
|
| 76 |
+
"eval_samples_per_second": 8.708,
|
| 77 |
+
"eval_steps_per_second": 1.09,
|
| 78 |
+
"step": 23030
|
| 79 |
+
},
|
| 80 |
+
{
|
| 81 |
+
"epoch": 5.0,
|
| 82 |
+
"step": 23030,
|
| 83 |
+
"total_flos": 4.401655508016e+19,
|
| 84 |
+
"train_loss": 2.908882859992401,
|
| 85 |
+
"train_runtime": 15260.3368,
|
| 86 |
+
"train_samples_per_second": 6.036,
|
| 87 |
+
"train_steps_per_second": 1.509
|
| 88 |
+
}
|
| 89 |
+
],
|
| 90 |
+
"max_steps": 23030,
|
| 91 |
+
"num_train_epochs": 5,
|
| 92 |
+
"total_flos": 4.401655508016e+19,
|
| 93 |
+
"trial_name": null,
|
| 94 |
+
"trial_params": null
|
| 95 |
+
}
|