Jeremiah Zhou
commited on
Commit
•
d1d1516
1
Parent(s):
41d2058
End of training
Browse files- all_results.json +16 -0
- eval_results.json +11 -0
- runs/Jun13_21-38-12_pikachu/events.out.tfevents.1655128056.pikachu.3892108.2 +3 -0
- train_results.json +8 -0
- trainer_state.json +37 -0
all_results.json
ADDED
|
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 5.0,
|
| 3 |
+
"eval_accuracy": 0.9019607843137255,
|
| 4 |
+
"eval_combined_score": 0.9157691245512289,
|
| 5 |
+
"eval_f1": 0.9295774647887324,
|
| 6 |
+
"eval_loss": 0.4898183345794678,
|
| 7 |
+
"eval_runtime": 0.8404,
|
| 8 |
+
"eval_samples": 408,
|
| 9 |
+
"eval_samples_per_second": 485.493,
|
| 10 |
+
"eval_steps_per_second": 60.687,
|
| 11 |
+
"train_loss": 0.2764597121528957,
|
| 12 |
+
"train_runtime": 134.1282,
|
| 13 |
+
"train_samples": 3668,
|
| 14 |
+
"train_samples_per_second": 136.735,
|
| 15 |
+
"train_steps_per_second": 8.574
|
| 16 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 5.0,
|
| 3 |
+
"eval_accuracy": 0.9019607843137255,
|
| 4 |
+
"eval_combined_score": 0.9157691245512289,
|
| 5 |
+
"eval_f1": 0.9295774647887324,
|
| 6 |
+
"eval_loss": 0.4898183345794678,
|
| 7 |
+
"eval_runtime": 0.8404,
|
| 8 |
+
"eval_samples": 408,
|
| 9 |
+
"eval_samples_per_second": 485.493,
|
| 10 |
+
"eval_steps_per_second": 60.687
|
| 11 |
+
}
|
runs/Jun13_21-38-12_pikachu/events.out.tfevents.1655128056.pikachu.3892108.2
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ff1ccb31fbe124c0b6fb9c4d717a2f474301d536766effebeed77386a7433093
|
| 3 |
+
size 467
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 5.0,
|
| 3 |
+
"train_loss": 0.2764597121528957,
|
| 4 |
+
"train_runtime": 134.1282,
|
| 5 |
+
"train_samples": 3668,
|
| 6 |
+
"train_samples_per_second": 136.735,
|
| 7 |
+
"train_steps_per_second": 8.574
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 5.0,
|
| 5 |
+
"global_step": 1150,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 2.17,
|
| 12 |
+
"learning_rate": 1.2025901942645698e-05,
|
| 13 |
+
"loss": 0.4285,
|
| 14 |
+
"step": 500
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 4.35,
|
| 18 |
+
"learning_rate": 2.7752081406105456e-06,
|
| 19 |
+
"loss": 0.1748,
|
| 20 |
+
"step": 1000
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 5.0,
|
| 24 |
+
"step": 1150,
|
| 25 |
+
"total_flos": 1206364188825600.0,
|
| 26 |
+
"train_loss": 0.2764597121528957,
|
| 27 |
+
"train_runtime": 134.1282,
|
| 28 |
+
"train_samples_per_second": 136.735,
|
| 29 |
+
"train_steps_per_second": 8.574
|
| 30 |
+
}
|
| 31 |
+
],
|
| 32 |
+
"max_steps": 1150,
|
| 33 |
+
"num_train_epochs": 5,
|
| 34 |
+
"total_flos": 1206364188825600.0,
|
| 35 |
+
"trial_name": null,
|
| 36 |
+
"trial_params": null
|
| 37 |
+
}
|