Commit
•
5dafd3d
1
Parent(s):
710d2c9
End of training
Browse files- all_results.json +6 -6
- train_results.json +6 -6
- trainer_state.json +29 -11
all_results.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"train_loss":
|
| 4 |
-
"train_runtime":
|
| 5 |
-
"train_samples":
|
| 6 |
-
"train_samples_per_second":
|
| 7 |
-
"train_steps_per_second": 0.
|
| 8 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 0.99,
|
| 3 |
+
"train_loss": 4.877151981476815,
|
| 4 |
+
"train_runtime": 551.4767,
|
| 5 |
+
"train_samples": 4000,
|
| 6 |
+
"train_samples_per_second": 7.253,
|
| 7 |
+
"train_steps_per_second": 0.056
|
| 8 |
}
|
train_results.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"train_loss":
|
| 4 |
-
"train_runtime":
|
| 5 |
-
"train_samples":
|
| 6 |
-
"train_samples_per_second":
|
| 7 |
-
"train_steps_per_second": 0.
|
| 8 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 0.99,
|
| 3 |
+
"train_loss": 4.877151981476815,
|
| 4 |
+
"train_runtime": 551.4767,
|
| 5 |
+
"train_samples": 4000,
|
| 6 |
+
"train_samples_per_second": 7.253,
|
| 7 |
+
"train_steps_per_second": 0.056
|
| 8 |
}
|
trainer_state.json
CHANGED
|
@@ -1,28 +1,46 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
-
"epoch":
|
| 5 |
"eval_steps": 500,
|
| 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 |
{
|
| 12 |
-
"epoch":
|
| 13 |
-
"
|
| 14 |
-
"
|
| 15 |
-
"
|
| 16 |
-
|
| 17 |
-
|
| 18 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 19 |
}
|
| 20 |
],
|
| 21 |
"logging_steps": 10,
|
| 22 |
-
"max_steps":
|
| 23 |
"num_train_epochs": 1,
|
| 24 |
"save_steps": 200.0,
|
| 25 |
-
"total_flos":
|
| 26 |
"trial_name": null,
|
| 27 |
"trial_params": null
|
| 28 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.992,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 31,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
+
"epoch": 0.32,
|
| 13 |
+
"learning_rate": 2.3333333333333336e-05,
|
| 14 |
+
"loss": 5.7397,
|
| 15 |
+
"step": 10
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.64,
|
| 19 |
+
"learning_rate": 1.2222222222222222e-05,
|
| 20 |
+
"loss": 4.7137,
|
| 21 |
+
"step": 20
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.96,
|
| 25 |
+
"learning_rate": 1.111111111111111e-06,
|
| 26 |
+
"loss": 4.2477,
|
| 27 |
+
"step": 30
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 0.99,
|
| 31 |
+
"step": 31,
|
| 32 |
+
"total_flos": 777619148046336.0,
|
| 33 |
+
"train_loss": 4.877151981476815,
|
| 34 |
+
"train_runtime": 551.4767,
|
| 35 |
+
"train_samples_per_second": 7.253,
|
| 36 |
+
"train_steps_per_second": 0.056
|
| 37 |
}
|
| 38 |
],
|
| 39 |
"logging_steps": 10,
|
| 40 |
+
"max_steps": 31,
|
| 41 |
"num_train_epochs": 1,
|
| 42 |
"save_steps": 200.0,
|
| 43 |
+
"total_flos": 777619148046336.0,
|
| 44 |
"trial_name": null,
|
| 45 |
"trial_params": null
|
| 46 |
}
|