Commit
•
2eb2aef
1
Parent(s):
d4b5e76
nlp04/test
Browse files- all_results.json +8 -0
- train_results.json +8 -0
- train_results.txt +6 -0
- trainer_state.json +55 -0
all_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"train_loss": 0.616782742018053,
|
| 4 |
+
"train_runtime": 648.5631,
|
| 5 |
+
"train_samples": 7978,
|
| 6 |
+
"train_samples_per_second": 36.903,
|
| 7 |
+
"train_steps_per_second": 4.616
|
| 8 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"train_loss": 0.616782742018053,
|
| 4 |
+
"train_runtime": 648.5631,
|
| 5 |
+
"train_samples": 7978,
|
| 6 |
+
"train_samples_per_second": 36.903,
|
| 7 |
+
"train_steps_per_second": 4.616
|
| 8 |
+
}
|
train_results.txt
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
epoch = 3.0
|
| 2 |
+
train_loss = 0.616782742018053
|
| 3 |
+
train_runtime = 648.5631
|
| 4 |
+
train_samples = 7978
|
| 5 |
+
train_samples_per_second = 36.903
|
| 6 |
+
train_steps_per_second = 4.616
|
trainer_state.json
ADDED
|
@@ -0,0 +1,55 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 3.0,
|
| 5 |
+
"global_step": 2994,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.5,
|
| 12 |
+
"learning_rate": 4.1649966599866405e-05,
|
| 13 |
+
"loss": 1.6003,
|
| 14 |
+
"step": 500
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 1.0,
|
| 18 |
+
"learning_rate": 3.32999331997328e-05,
|
| 19 |
+
"loss": 1.0598,
|
| 20 |
+
"step": 1000
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 1.5,
|
| 24 |
+
"learning_rate": 2.49498997995992e-05,
|
| 25 |
+
"loss": 0.3999,
|
| 26 |
+
"step": 1500
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 2.0,
|
| 30 |
+
"learning_rate": 1.65998663994656e-05,
|
| 31 |
+
"loss": 0.3829,
|
| 32 |
+
"step": 2000
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 2.51,
|
| 36 |
+
"learning_rate": 8.249832999331998e-06,
|
| 37 |
+
"loss": 0.131,
|
| 38 |
+
"step": 2500
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 3.0,
|
| 42 |
+
"step": 2994,
|
| 43 |
+
"total_flos": 4688778409821792.0,
|
| 44 |
+
"train_loss": 0.616782742018053,
|
| 45 |
+
"train_runtime": 648.5631,
|
| 46 |
+
"train_samples_per_second": 36.903,
|
| 47 |
+
"train_steps_per_second": 4.616
|
| 48 |
+
}
|
| 49 |
+
],
|
| 50 |
+
"max_steps": 2994,
|
| 51 |
+
"num_train_epochs": 3,
|
| 52 |
+
"total_flos": 4688778409821792.0,
|
| 53 |
+
"trial_name": null,
|
| 54 |
+
"trial_params": null
|
| 55 |
+
}
|