Commit
•
482e804
1
Parent(s):
7a5f389
End of training
Browse files- trainer_state.json +56 -14
trainer_state.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric": 2.
|
| 3 |
-
"best_model_checkpoint": "cdetr-cd45rb-s/checkpoint-
|
| 4 |
-
"epoch":
|
| 5 |
-
"global_step":
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
|
@@ -36,18 +36,60 @@
|
|
| 36 |
"step": 484
|
| 37 |
},
|
| 38 |
{
|
| 39 |
-
"epoch":
|
| 40 |
-
"
|
| 41 |
-
"
|
| 42 |
-
"
|
| 43 |
-
|
| 44 |
-
|
| 45 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 46 |
}
|
| 47 |
],
|
| 48 |
-
"max_steps":
|
| 49 |
-
"num_train_epochs":
|
| 50 |
-
"total_flos":
|
| 51 |
"trial_name": null,
|
| 52 |
"trial_params": null
|
| 53 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 2.0293631553649902,
|
| 3 |
+
"best_model_checkpoint": "cdetr-cd45rb-s/checkpoint-1210",
|
| 4 |
+
"epoch": 5.0,
|
| 5 |
+
"global_step": 1210,
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
|
|
|
| 36 |
"step": 484
|
| 37 |
},
|
| 38 |
{
|
| 39 |
+
"epoch": 3.0,
|
| 40 |
+
"learning_rate": 4e-05,
|
| 41 |
+
"loss": 2.2027,
|
| 42 |
+
"step": 726
|
| 43 |
+
},
|
| 44 |
+
{
|
| 45 |
+
"epoch": 3.0,
|
| 46 |
+
"eval_loss": 2.145615339279175,
|
| 47 |
+
"eval_runtime": 17.7242,
|
| 48 |
+
"eval_samples_per_second": 5.642,
|
| 49 |
+
"eval_steps_per_second": 0.733,
|
| 50 |
+
"step": 726
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 4.0,
|
| 54 |
+
"learning_rate": 2e-05,
|
| 55 |
+
"loss": 2.183,
|
| 56 |
+
"step": 968
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 4.0,
|
| 60 |
+
"eval_loss": 2.0863144397735596,
|
| 61 |
+
"eval_runtime": 17.5156,
|
| 62 |
+
"eval_samples_per_second": 5.709,
|
| 63 |
+
"eval_steps_per_second": 0.742,
|
| 64 |
+
"step": 968
|
| 65 |
+
},
|
| 66 |
+
{
|
| 67 |
+
"epoch": 5.0,
|
| 68 |
+
"learning_rate": 0.0,
|
| 69 |
+
"loss": 2.0628,
|
| 70 |
+
"step": 1210
|
| 71 |
+
},
|
| 72 |
+
{
|
| 73 |
+
"epoch": 5.0,
|
| 74 |
+
"eval_loss": 2.0293631553649902,
|
| 75 |
+
"eval_runtime": 17.5041,
|
| 76 |
+
"eval_samples_per_second": 5.713,
|
| 77 |
+
"eval_steps_per_second": 0.743,
|
| 78 |
+
"step": 1210
|
| 79 |
+
},
|
| 80 |
+
{
|
| 81 |
+
"epoch": 5.0,
|
| 82 |
+
"step": 1210,
|
| 83 |
+
"total_flos": 2.4107363634816e+18,
|
| 84 |
+
"train_loss": 1.2896953235973012,
|
| 85 |
+
"train_runtime": 786.99,
|
| 86 |
+
"train_samples_per_second": 6.137,
|
| 87 |
+
"train_steps_per_second": 1.538
|
| 88 |
}
|
| 89 |
],
|
| 90 |
+
"max_steps": 1210,
|
| 91 |
+
"num_train_epochs": 5,
|
| 92 |
+
"total_flos": 2.4107363634816e+18,
|
| 93 |
"trial_name": null,
|
| 94 |
"trial_params": null
|
| 95 |
}
|