training state at step 2
Browse files- trainer_state.json +20 -4
trainer_state.json
CHANGED
|
@@ -1,13 +1,29 @@
|
|
| 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,
|
| 10 |
-
"log_history": [
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 11 |
"logging_steps": 1,
|
| 12 |
"max_steps": 216,
|
| 13 |
"num_input_tokens_seen": 0,
|
|
@@ -25,7 +41,7 @@
|
|
| 25 |
"attributes": {}
|
| 26 |
}
|
| 27 |
},
|
| 28 |
-
"total_flos": 0,
|
| 29 |
"train_batch_size": 2,
|
| 30 |
"trial_name": null,
|
| 31 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.027586206896551724,
|
| 5 |
"eval_steps": 1,
|
| 6 |
+
"global_step": 2,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.013793103448275862,
|
| 13 |
+
"grad_norm": 6.989287853240967,
|
| 14 |
+
"learning_rate": 2.2727272727272728e-06,
|
| 15 |
+
"loss": 1.8926,
|
| 16 |
+
"step": 1
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.013793103448275862,
|
| 20 |
+
"eval_loss": 2.144650459289551,
|
| 21 |
+
"eval_runtime": 16.0395,
|
| 22 |
+
"eval_samples_per_second": 1.247,
|
| 23 |
+
"eval_steps_per_second": 0.623,
|
| 24 |
+
"step": 1
|
| 25 |
+
}
|
| 26 |
+
],
|
| 27 |
"logging_steps": 1,
|
| 28 |
"max_steps": 216,
|
| 29 |
"num_input_tokens_seen": 0,
|
|
|
|
| 41 |
"attributes": {}
|
| 42 |
}
|
| 43 |
},
|
| 44 |
+
"total_flos": 1280682607951872.0,
|
| 45 |
"train_batch_size": 2,
|
| 46 |
"trial_name": null,
|
| 47 |
"trial_params": null
|