Commit
·
0fad10e
1
Parent(s):
0eeb4a2
End of training
Browse files- all_results.json +14 -0
- eval_results.json +9 -0
- runs/Sep17_18-08-55_patrick-general-gpu/events.out.tfevents.1631902166.patrick-general-gpu.299149.0 +2 -2
- runs/Sep17_18-08-55_patrick-general-gpu/events.out.tfevents.1631908712.patrick-general-gpu.299149.2 +3 -0
- train_results.json +8 -0
- trainer_state.json +70 -0
all_results.json
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"eval_accuracy": 0.8438586857038257,
|
| 4 |
+
"eval_loss": 0.4746157228946686,
|
| 5 |
+
"eval_runtime": 40.1993,
|
| 6 |
+
"eval_samples": 5463,
|
| 7 |
+
"eval_samples_per_second": 135.898,
|
| 8 |
+
"eval_steps_per_second": 16.99,
|
| 9 |
+
"train_loss": 0.33642483034333476,
|
| 10 |
+
"train_runtime": 6501.9071,
|
| 11 |
+
"train_samples": 104743,
|
| 12 |
+
"train_samples_per_second": 48.329,
|
| 13 |
+
"train_steps_per_second": 3.021
|
| 14 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"eval_accuracy": 0.8438586857038257,
|
| 4 |
+
"eval_loss": 0.4746157228946686,
|
| 5 |
+
"eval_runtime": 40.1993,
|
| 6 |
+
"eval_samples": 5463,
|
| 7 |
+
"eval_samples_per_second": 135.898,
|
| 8 |
+
"eval_steps_per_second": 16.99
|
| 9 |
+
}
|
runs/Sep17_18-08-55_patrick-general-gpu/events.out.tfevents.1631902166.patrick-general-gpu.299149.0
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:d1428946772e0efd5682a3aaecc74001ad97497b1adc23c11e11e47a62ebbee4
|
| 3 |
+
size 4993
|
runs/Sep17_18-08-55_patrick-general-gpu/events.out.tfevents.1631908712.patrick-general-gpu.299149.2
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:667b268873c5466b984f778883717b7aeec1c67a4d6e742869a9cd072c77073a
|
| 3 |
+
size 369
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"train_loss": 0.33642483034333476,
|
| 4 |
+
"train_runtime": 6501.9071,
|
| 5 |
+
"train_samples": 104743,
|
| 6 |
+
"train_samples_per_second": 48.329,
|
| 7 |
+
"train_steps_per_second": 3.021
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,70 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 3.0,
|
| 5 |
+
"global_step": 19641,
|
| 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": 0.4597,
|
| 14 |
+
"step": 6547
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 1.0,
|
| 18 |
+
"eval_accuracy": 0.8411129416071755,
|
| 19 |
+
"eval_loss": 0.37129390239715576,
|
| 20 |
+
"eval_runtime": 39.7582,
|
| 21 |
+
"eval_samples_per_second": 137.406,
|
| 22 |
+
"eval_steps_per_second": 17.179,
|
| 23 |
+
"step": 6547
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 2.0,
|
| 27 |
+
"learning_rate": 6.666666666666667e-06,
|
| 28 |
+
"loss": 0.3252,
|
| 29 |
+
"step": 13094
|
| 30 |
+
},
|
| 31 |
+
{
|
| 32 |
+
"epoch": 2.0,
|
| 33 |
+
"eval_accuracy": 0.8420281896393923,
|
| 34 |
+
"eval_loss": 0.378091961145401,
|
| 35 |
+
"eval_runtime": 39.5864,
|
| 36 |
+
"eval_samples_per_second": 138.002,
|
| 37 |
+
"eval_steps_per_second": 17.253,
|
| 38 |
+
"step": 13094
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 3.0,
|
| 42 |
+
"learning_rate": 0.0,
|
| 43 |
+
"loss": 0.2243,
|
| 44 |
+
"step": 19641
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 3.0,
|
| 48 |
+
"eval_accuracy": 0.8438586857038257,
|
| 49 |
+
"eval_loss": 0.4746157228946686,
|
| 50 |
+
"eval_runtime": 39.7955,
|
| 51 |
+
"eval_samples_per_second": 137.277,
|
| 52 |
+
"eval_steps_per_second": 17.163,
|
| 53 |
+
"step": 19641
|
| 54 |
+
},
|
| 55 |
+
{
|
| 56 |
+
"epoch": 3.0,
|
| 57 |
+
"step": 19641,
|
| 58 |
+
"total_flos": 5.588217742563533e+16,
|
| 59 |
+
"train_loss": 0.33642483034333476,
|
| 60 |
+
"train_runtime": 6501.9071,
|
| 61 |
+
"train_samples_per_second": 48.329,
|
| 62 |
+
"train_steps_per_second": 3.021
|
| 63 |
+
}
|
| 64 |
+
],
|
| 65 |
+
"max_steps": 19641,
|
| 66 |
+
"num_train_epochs": 3,
|
| 67 |
+
"total_flos": 5.588217742563533e+16,
|
| 68 |
+
"trial_name": null,
|
| 69 |
+
"trial_params": null
|
| 70 |
+
}
|