Commit
•
d122fb2
1
Parent(s):
9caaccf
End of training
Browse files- all_results.json +16 -0
- eval_results.json +11 -0
- runs/Sep18_08-14-37_patrick-general-gpu/events.out.tfevents.1631953045.patrick-general-gpu.335601.0 +2 -2
- runs/Sep18_08-14-37_patrick-general-gpu/events.out.tfevents.1631987369.patrick-general-gpu.335601.2 +3 -0
- train_results.json +8 -0
- trainer_state.json +76 -0
all_results.json
ADDED
|
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"eval_accuracy": 0.9083848627256987,
|
| 4 |
+
"eval_combined_score": 0.8925741188794849,
|
| 5 |
+
"eval_f1": 0.8767633750332712,
|
| 6 |
+
"eval_loss": 0.37517139315605164,
|
| 7 |
+
"eval_runtime": 413.627,
|
| 8 |
+
"eval_samples": 40430,
|
| 9 |
+
"eval_samples_per_second": 97.745,
|
| 10 |
+
"eval_steps_per_second": 12.219,
|
| 11 |
+
"train_loss": 0.21685483706122752,
|
| 12 |
+
"train_runtime": 33900.8837,
|
| 13 |
+
"train_samples": 363846,
|
| 14 |
+
"train_samples_per_second": 32.198,
|
| 15 |
+
"train_steps_per_second": 2.012
|
| 16 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"eval_accuracy": 0.9083848627256987,
|
| 4 |
+
"eval_combined_score": 0.8925741188794849,
|
| 5 |
+
"eval_f1": 0.8767633750332712,
|
| 6 |
+
"eval_loss": 0.37517139315605164,
|
| 7 |
+
"eval_runtime": 413.627,
|
| 8 |
+
"eval_samples": 40430,
|
| 9 |
+
"eval_samples_per_second": 97.745,
|
| 10 |
+
"eval_steps_per_second": 12.219
|
| 11 |
+
}
|
runs/Sep18_08-14-37_patrick-general-gpu/events.out.tfevents.1631953045.patrick-general-gpu.335601.0
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d496badc7c2f1e56510830ddd302cb01dc327360c28ca172f9f01b16385dfe0c
|
| 3 |
+
size 5383
|
runs/Sep18_08-14-37_patrick-general-gpu/events.out.tfevents.1631987369.patrick-general-gpu.335601.2
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0d39d0113bd1c46ae29af14b9b431f20dad91041f84f98332943c751a9485abe
|
| 3 |
+
size 475
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"train_loss": 0.21685483706122752,
|
| 4 |
+
"train_runtime": 33900.8837,
|
| 5 |
+
"train_samples": 363846,
|
| 6 |
+
"train_samples_per_second": 32.198,
|
| 7 |
+
"train_steps_per_second": 2.012
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,76 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 3.0,
|
| 5 |
+
"global_step": 68223,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 1.0,
|
| 12 |
+
"learning_rate": 1.3333333333333333e-05,
|
| 13 |
+
"loss": 0.308,
|
| 14 |
+
"step": 22741
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 1.0,
|
| 18 |
+
"eval_accuracy": 0.8924560969577047,
|
| 19 |
+
"eval_combined_score": 0.8740405069726762,
|
| 20 |
+
"eval_f1": 0.8556249169876479,
|
| 21 |
+
"eval_loss": 0.2548316419124603,
|
| 22 |
+
"eval_runtime": 413.8779,
|
| 23 |
+
"eval_samples_per_second": 97.686,
|
| 24 |
+
"eval_steps_per_second": 12.211,
|
| 25 |
+
"step": 22741
|
| 26 |
+
},
|
| 27 |
+
{
|
| 28 |
+
"epoch": 2.0,
|
| 29 |
+
"learning_rate": 6.666666666666667e-06,
|
| 30 |
+
"loss": 0.201,
|
| 31 |
+
"step": 45482
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 2.0,
|
| 35 |
+
"eval_accuracy": 0.9032401681919366,
|
| 36 |
+
"eval_combined_score": 0.886515570715593,
|
| 37 |
+
"eval_f1": 0.8697909732392491,
|
| 38 |
+
"eval_loss": 0.2880714237689972,
|
| 39 |
+
"eval_runtime": 412.3711,
|
| 40 |
+
"eval_samples_per_second": 98.043,
|
| 41 |
+
"eval_steps_per_second": 12.256,
|
| 42 |
+
"step": 45482
|
| 43 |
+
},
|
| 44 |
+
{
|
| 45 |
+
"epoch": 3.0,
|
| 46 |
+
"learning_rate": 0.0,
|
| 47 |
+
"loss": 0.1416,
|
| 48 |
+
"step": 68223
|
| 49 |
+
},
|
| 50 |
+
{
|
| 51 |
+
"epoch": 3.0,
|
| 52 |
+
"eval_accuracy": 0.9083848627256987,
|
| 53 |
+
"eval_combined_score": 0.8925741188794849,
|
| 54 |
+
"eval_f1": 0.8767633750332712,
|
| 55 |
+
"eval_loss": 0.37517139315605164,
|
| 56 |
+
"eval_runtime": 412.699,
|
| 57 |
+
"eval_samples_per_second": 97.965,
|
| 58 |
+
"eval_steps_per_second": 12.246,
|
| 59 |
+
"step": 68223
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 3.0,
|
| 63 |
+
"step": 68223,
|
| 64 |
+
"total_flos": 2.8719571514554368e+17,
|
| 65 |
+
"train_loss": 0.21685483706122752,
|
| 66 |
+
"train_runtime": 33900.8837,
|
| 67 |
+
"train_samples_per_second": 32.198,
|
| 68 |
+
"train_steps_per_second": 2.012
|
| 69 |
+
}
|
| 70 |
+
],
|
| 71 |
+
"max_steps": 68223,
|
| 72 |
+
"num_train_epochs": 3,
|
| 73 |
+
"total_flos": 2.8719571514554368e+17,
|
| 74 |
+
"trial_name": null,
|
| 75 |
+
"trial_params": null
|
| 76 |
+
}
|