Commit
·
d7312c9
1
Parent(s):
535e9c7
End of training
Browse files- all_results.json +14 -0
- eval_results.json +9 -0
- runs/Sep19_08-31-53_patrick-general-gpu/events.out.tfevents.1632040336.patrick-general-gpu.480409.0 +2 -2
- runs/Sep19_08-31-53_patrick-general-gpu/events.out.tfevents.1632044512.patrick-general-gpu.480409.2 +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": 0.8944954128440367,
|
| 4 |
+
"eval_loss": 0.4674423038959503,
|
| 5 |
+
"eval_runtime": 6.426,
|
| 6 |
+
"eval_samples": 872,
|
| 7 |
+
"eval_samples_per_second": 135.699,
|
| 8 |
+
"eval_steps_per_second": 16.962,
|
| 9 |
+
"train_loss": 0.196843689883029,
|
| 10 |
+
"train_runtime": 4166.7694,
|
| 11 |
+
"train_samples": 67349,
|
| 12 |
+
"train_samples_per_second": 48.49,
|
| 13 |
+
"train_steps_per_second": 3.031
|
| 14 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"eval_accuracy": 0.8944954128440367,
|
| 4 |
+
"eval_loss": 0.4674423038959503,
|
| 5 |
+
"eval_runtime": 6.426,
|
| 6 |
+
"eval_samples": 872,
|
| 7 |
+
"eval_samples_per_second": 135.699,
|
| 8 |
+
"eval_steps_per_second": 16.962
|
| 9 |
+
}
|
runs/Sep19_08-31-53_patrick-general-gpu/events.out.tfevents.1632040336.patrick-general-gpu.480409.0
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 sha256:23dd7e3bc333162dc9d724854efca6ff56660f05bc780a39067cf10ca4e91e53
|
| 3 |
+
size 4962
|
runs/Sep19_08-31-53_patrick-general-gpu/events.out.tfevents.1632044512.patrick-general-gpu.480409.2
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2f6bc6d2b8b7cf518cb62d9abae3622dce67b697140beeb8ab607cd8470f4b25
|
| 3 |
+
size 363
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"train_loss": 0.196843689883029,
|
| 4 |
+
"train_runtime": 4166.7694,
|
| 5 |
+
"train_samples": 67349,
|
| 6 |
+
"train_samples_per_second": 48.49,
|
| 7 |
+
"train_steps_per_second": 3.031
|
| 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": 12630,
|
| 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": 0.2956,
|
| 14 |
+
"step": 4210
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 1.0,
|
| 18 |
+
"eval_accuracy": 0.8818807339449541,
|
| 19 |
+
"eval_loss": 0.3128007650375366,
|
| 20 |
+
"eval_runtime": 6.3233,
|
| 21 |
+
"eval_samples_per_second": 137.902,
|
| 22 |
+
"eval_steps_per_second": 17.238,
|
| 23 |
+
"step": 4210
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 2.0,
|
| 27 |
+
"learning_rate": 6.666666666666667e-06,
|
| 28 |
+
"loss": 0.1746,
|
| 29 |
+
"step": 8420
|
| 30 |
+
},
|
| 31 |
+
{
|
| 32 |
+
"epoch": 2.0,
|
| 33 |
+
"eval_accuracy": 0.8979357798165137,
|
| 34 |
+
"eval_loss": 0.38503018021583557,
|
| 35 |
+
"eval_runtime": 6.3387,
|
| 36 |
+
"eval_samples_per_second": 137.568,
|
| 37 |
+
"eval_steps_per_second": 17.196,
|
| 38 |
+
"step": 8420
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 3.0,
|
| 42 |
+
"learning_rate": 0.0,
|
| 43 |
+
"loss": 0.1204,
|
| 44 |
+
"step": 12630
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 3.0,
|
| 48 |
+
"eval_accuracy": 0.8944954128440367,
|
| 49 |
+
"eval_loss": 0.4674423038959503,
|
| 50 |
+
"eval_runtime": 6.3626,
|
| 51 |
+
"eval_samples_per_second": 137.05,
|
| 52 |
+
"eval_steps_per_second": 17.131,
|
| 53 |
+
"step": 12630
|
| 54 |
+
},
|
| 55 |
+
{
|
| 56 |
+
"epoch": 3.0,
|
| 57 |
+
"step": 12630,
|
| 58 |
+
"total_flos": 3.5931840480405504e+16,
|
| 59 |
+
"train_loss": 0.196843689883029,
|
| 60 |
+
"train_runtime": 4166.7694,
|
| 61 |
+
"train_samples_per_second": 48.49,
|
| 62 |
+
"train_steps_per_second": 3.031
|
| 63 |
+
}
|
| 64 |
+
],
|
| 65 |
+
"max_steps": 12630,
|
| 66 |
+
"num_train_epochs": 3,
|
| 67 |
+
"total_flos": 3.5931840480405504e+16,
|
| 68 |
+
"trial_name": null,
|
| 69 |
+
"trial_params": null
|
| 70 |
+
}
|