training state at step 5
Browse files- trainer_state.json +51 -6
trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
-
"epoch": 0.
|
| 5 |
"eval_steps": 1,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
@@ -18,10 +18,55 @@
|
|
| 18 |
{
|
| 19 |
"epoch": 0.013793103448275862,
|
| 20 |
"eval_loss": 2.144650459289551,
|
| 21 |
-
"eval_runtime":
|
| 22 |
-
"eval_samples_per_second": 1.
|
| 23 |
-
"eval_steps_per_second": 0.
|
| 24 |
"step": 1
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 25 |
}
|
| 26 |
],
|
| 27 |
"logging_steps": 1,
|
|
@@ -41,7 +86,7 @@
|
|
| 41 |
"attributes": {}
|
| 42 |
}
|
| 43 |
},
|
| 44 |
-
"total_flos":
|
| 45 |
"train_batch_size": 2,
|
| 46 |
"trial_name": null,
|
| 47 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.06896551724137931,
|
| 5 |
"eval_steps": 1,
|
| 6 |
+
"global_step": 5,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 18 |
{
|
| 19 |
"epoch": 0.013793103448275862,
|
| 20 |
"eval_loss": 2.144650459289551,
|
| 21 |
+
"eval_runtime": 17.2592,
|
| 22 |
+
"eval_samples_per_second": 1.159,
|
| 23 |
+
"eval_steps_per_second": 0.579,
|
| 24 |
"step": 1
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.027586206896551724,
|
| 28 |
+
"grad_norm": 6.281332492828369,
|
| 29 |
+
"learning_rate": 4.5454545454545455e-06,
|
| 30 |
+
"loss": 1.986,
|
| 31 |
+
"step": 2
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.027586206896551724,
|
| 35 |
+
"eval_loss": 2.0905685424804688,
|
| 36 |
+
"eval_runtime": 17.6184,
|
| 37 |
+
"eval_samples_per_second": 1.135,
|
| 38 |
+
"eval_steps_per_second": 0.568,
|
| 39 |
+
"step": 2
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.041379310344827586,
|
| 43 |
+
"grad_norm": 4.347537040710449,
|
| 44 |
+
"learning_rate": 6.818181818181818e-06,
|
| 45 |
+
"loss": 1.9355,
|
| 46 |
+
"step": 3
|
| 47 |
+
},
|
| 48 |
+
{
|
| 49 |
+
"epoch": 0.041379310344827586,
|
| 50 |
+
"eval_loss": 1.9983774423599243,
|
| 51 |
+
"eval_runtime": 17.5928,
|
| 52 |
+
"eval_samples_per_second": 1.137,
|
| 53 |
+
"eval_steps_per_second": 0.568,
|
| 54 |
+
"step": 3
|
| 55 |
+
},
|
| 56 |
+
{
|
| 57 |
+
"epoch": 0.05517241379310345,
|
| 58 |
+
"grad_norm": 4.809764385223389,
|
| 59 |
+
"learning_rate": 9.090909090909091e-06,
|
| 60 |
+
"loss": 1.7509,
|
| 61 |
+
"step": 4
|
| 62 |
+
},
|
| 63 |
+
{
|
| 64 |
+
"epoch": 0.05517241379310345,
|
| 65 |
+
"eval_loss": 1.8737837076187134,
|
| 66 |
+
"eval_runtime": 17.6375,
|
| 67 |
+
"eval_samples_per_second": 1.134,
|
| 68 |
+
"eval_steps_per_second": 0.567,
|
| 69 |
+
"step": 4
|
| 70 |
}
|
| 71 |
],
|
| 72 |
"logging_steps": 1,
|
|
|
|
| 86 |
"attributes": {}
|
| 87 |
}
|
| 88 |
},
|
| 89 |
+
"total_flos": 5047562107060224.0,
|
| 90 |
"train_batch_size": 2,
|
| 91 |
"trial_name": null,
|
| 92 |
"trial_params": null
|