Commit
·
4178d1d
1
Parent(s):
ee8b74b
End of training
Browse files- all_results.json +14 -0
- eval_results.json +9 -0
- runs/Sep23_04-38-21_patrick-general-gpu/events.out.tfevents.1632371921.patrick-general-gpu.956617.0 +2 -2
- runs/Sep23_04-38-21_patrick-general-gpu/events.out.tfevents.1632372749.patrick-general-gpu.956617.2 +3 -0
- train_results.json +8 -0
- trainer_state.json +100 -0
all_results.json
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 5.0,
|
| 3 |
+
"eval_accuracy": 0.352112676056338,
|
| 4 |
+
"eval_loss": 0.7087209820747375,
|
| 5 |
+
"eval_runtime": 2.3558,
|
| 6 |
+
"eval_samples": 71,
|
| 7 |
+
"eval_samples_per_second": 30.138,
|
| 8 |
+
"eval_steps_per_second": 3.82,
|
| 9 |
+
"train_loss": 0.7095118300719832,
|
| 10 |
+
"train_runtime": 808.1685,
|
| 11 |
+
"train_samples": 635,
|
| 12 |
+
"train_samples_per_second": 3.929,
|
| 13 |
+
"train_steps_per_second": 0.984
|
| 14 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 5.0,
|
| 3 |
+
"eval_accuracy": 0.352112676056338,
|
| 4 |
+
"eval_loss": 0.7087209820747375,
|
| 5 |
+
"eval_runtime": 2.3558,
|
| 6 |
+
"eval_samples": 71,
|
| 7 |
+
"eval_samples_per_second": 30.138,
|
| 8 |
+
"eval_steps_per_second": 3.82
|
| 9 |
+
}
|
runs/Sep23_04-38-21_patrick-general-gpu/events.out.tfevents.1632371921.patrick-general-gpu.956617.0
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 sha256:8a0da1306767c96c874bd1d7aeea86e55211a4331fa593f273aaa80076dd6cbd
|
| 3 |
+
size 6195
|
runs/Sep23_04-38-21_patrick-general-gpu/events.out.tfevents.1632372749.patrick-general-gpu.956617.2
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:18933365f16286c495d1ae2bcddae7788b35319295e9d6517ea967167a128ea2
|
| 3 |
+
size 363
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 5.0,
|
| 3 |
+
"train_loss": 0.7095118300719832,
|
| 4 |
+
"train_runtime": 808.1685,
|
| 5 |
+
"train_samples": 635,
|
| 6 |
+
"train_samples_per_second": 3.929,
|
| 7 |
+
"train_steps_per_second": 0.984
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,100 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 5.0,
|
| 5 |
+
"global_step": 795,
|
| 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": 1.6000000000000003e-05,
|
| 13 |
+
"loss": 0.7114,
|
| 14 |
+
"step": 159
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 1.0,
|
| 18 |
+
"eval_accuracy": 0.5633802816901409,
|
| 19 |
+
"eval_loss": 0.6923297047615051,
|
| 20 |
+
"eval_runtime": 2.3107,
|
| 21 |
+
"eval_samples_per_second": 30.726,
|
| 22 |
+
"eval_steps_per_second": 3.895,
|
| 23 |
+
"step": 159
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 2.0,
|
| 27 |
+
"learning_rate": 1.2e-05,
|
| 28 |
+
"loss": 0.7141,
|
| 29 |
+
"step": 318
|
| 30 |
+
},
|
| 31 |
+
{
|
| 32 |
+
"epoch": 2.0,
|
| 33 |
+
"eval_accuracy": 0.5633802816901409,
|
| 34 |
+
"eval_loss": 0.6894838809967041,
|
| 35 |
+
"eval_runtime": 2.3191,
|
| 36 |
+
"eval_samples_per_second": 30.616,
|
| 37 |
+
"eval_steps_per_second": 3.881,
|
| 38 |
+
"step": 318
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 3.0,
|
| 42 |
+
"learning_rate": 8.000000000000001e-06,
|
| 43 |
+
"loss": 0.7063,
|
| 44 |
+
"step": 477
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 3.0,
|
| 48 |
+
"eval_accuracy": 0.5633802816901409,
|
| 49 |
+
"eval_loss": 0.6930345296859741,
|
| 50 |
+
"eval_runtime": 2.3253,
|
| 51 |
+
"eval_samples_per_second": 30.534,
|
| 52 |
+
"eval_steps_per_second": 3.87,
|
| 53 |
+
"step": 477
|
| 54 |
+
},
|
| 55 |
+
{
|
| 56 |
+
"epoch": 4.0,
|
| 57 |
+
"learning_rate": 4.000000000000001e-06,
|
| 58 |
+
"loss": 0.712,
|
| 59 |
+
"step": 636
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 4.0,
|
| 63 |
+
"eval_accuracy": 0.4507042253521127,
|
| 64 |
+
"eval_loss": 0.707716703414917,
|
| 65 |
+
"eval_runtime": 2.3283,
|
| 66 |
+
"eval_samples_per_second": 30.494,
|
| 67 |
+
"eval_steps_per_second": 3.865,
|
| 68 |
+
"step": 636
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 5.0,
|
| 72 |
+
"learning_rate": 0.0,
|
| 73 |
+
"loss": 0.7037,
|
| 74 |
+
"step": 795
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 5.0,
|
| 78 |
+
"eval_accuracy": 0.352112676056338,
|
| 79 |
+
"eval_loss": 0.7087209820747375,
|
| 80 |
+
"eval_runtime": 2.3213,
|
| 81 |
+
"eval_samples_per_second": 30.586,
|
| 82 |
+
"eval_steps_per_second": 3.877,
|
| 83 |
+
"step": 795
|
| 84 |
+
},
|
| 85 |
+
{
|
| 86 |
+
"epoch": 5.0,
|
| 87 |
+
"step": 795,
|
| 88 |
+
"total_flos": 2958882078566400.0,
|
| 89 |
+
"train_loss": 0.7095118300719832,
|
| 90 |
+
"train_runtime": 808.1685,
|
| 91 |
+
"train_samples_per_second": 3.929,
|
| 92 |
+
"train_steps_per_second": 0.984
|
| 93 |
+
}
|
| 94 |
+
],
|
| 95 |
+
"max_steps": 795,
|
| 96 |
+
"num_train_epochs": 5,
|
| 97 |
+
"total_flos": 2958882078566400.0,
|
| 98 |
+
"trial_name": null,
|
| 99 |
+
"trial_params": null
|
| 100 |
+
}
|