Commit
•
89bbb6b
1
Parent(s):
05c581a
End of training
Browse files- all_results.json +14 -0
- eval_results.json +9 -0
- runs/Sep16_19-30-53_patrick-general-gpu/events.out.tfevents.1631820668.patrick-general-gpu.205020.0 +2 -2
- runs/Sep16_19-30-53_patrick-general-gpu/events.out.tfevents.1631821267.patrick-general-gpu.205020.2 +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_loss": 0.5929099917411804,
|
| 4 |
+
"eval_matthews_correlation": 0.35940659235571387,
|
| 5 |
+
"eval_runtime": 7.6143,
|
| 6 |
+
"eval_samples": 1043,
|
| 7 |
+
"eval_samples_per_second": 136.98,
|
| 8 |
+
"eval_steps_per_second": 17.205,
|
| 9 |
+
"train_loss": 0.46265685654874905,
|
| 10 |
+
"train_runtime": 587.6397,
|
| 11 |
+
"train_samples": 8551,
|
| 12 |
+
"train_samples_per_second": 43.654,
|
| 13 |
+
"train_steps_per_second": 2.731
|
| 14 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"eval_loss": 0.5929099917411804,
|
| 4 |
+
"eval_matthews_correlation": 0.35940659235571387,
|
| 5 |
+
"eval_runtime": 7.6143,
|
| 6 |
+
"eval_samples": 1043,
|
| 7 |
+
"eval_samples_per_second": 136.98,
|
| 8 |
+
"eval_steps_per_second": 17.205
|
| 9 |
+
}
|
runs/Sep16_19-30-53_patrick-general-gpu/events.out.tfevents.1631820668.patrick-general-gpu.205020.0
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 sha256:72dae69d48ea243dfbc3f88791130ae67e58e942cec8bf3e97f76bb6265830e9
|
| 3 |
+
size 5010
|
runs/Sep16_19-30-53_patrick-general-gpu/events.out.tfevents.1631821267.patrick-general-gpu.205020.2
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e5c8f0a4da05269d23d1785c3c61b88239e9e1958798a21a8fa80ec85b8fd0f7
|
| 3 |
+
size 375
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"train_loss": 0.46265685654874905,
|
| 4 |
+
"train_runtime": 587.6397,
|
| 5 |
+
"train_samples": 8551,
|
| 6 |
+
"train_samples_per_second": 43.654,
|
| 7 |
+
"train_steps_per_second": 2.731
|
| 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": 1605,
|
| 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": 0.5895,
|
| 14 |
+
"step": 535
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 1.0,
|
| 18 |
+
"eval_loss": 0.6146270632743835,
|
| 19 |
+
"eval_matthews_correlation": 0.16988650877044353,
|
| 20 |
+
"eval_runtime": 7.5781,
|
| 21 |
+
"eval_samples_per_second": 137.634,
|
| 22 |
+
"eval_steps_per_second": 17.287,
|
| 23 |
+
"step": 535
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 2.0,
|
| 27 |
+
"learning_rate": 6.666666666666667e-06,
|
| 28 |
+
"loss": 0.4656,
|
| 29 |
+
"step": 1070
|
| 30 |
+
},
|
| 31 |
+
{
|
| 32 |
+
"epoch": 2.0,
|
| 33 |
+
"eval_loss": 0.5666966438293457,
|
| 34 |
+
"eval_matthews_correlation": 0.30468062994701894,
|
| 35 |
+
"eval_runtime": 7.5686,
|
| 36 |
+
"eval_samples_per_second": 137.807,
|
| 37 |
+
"eval_steps_per_second": 17.308,
|
| 38 |
+
"step": 1070
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 3.0,
|
| 42 |
+
"learning_rate": 0.0,
|
| 43 |
+
"loss": 0.3329,
|
| 44 |
+
"step": 1605
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 3.0,
|
| 48 |
+
"eval_loss": 0.5929099917411804,
|
| 49 |
+
"eval_matthews_correlation": 0.35940659235571387,
|
| 50 |
+
"eval_runtime": 7.5654,
|
| 51 |
+
"eval_samples_per_second": 137.865,
|
| 52 |
+
"eval_steps_per_second": 17.316,
|
| 53 |
+
"step": 1605
|
| 54 |
+
},
|
| 55 |
+
{
|
| 56 |
+
"epoch": 3.0,
|
| 57 |
+
"step": 1605,
|
| 58 |
+
"total_flos": 4562104380880896.0,
|
| 59 |
+
"train_loss": 0.46265685654874905,
|
| 60 |
+
"train_runtime": 587.6397,
|
| 61 |
+
"train_samples_per_second": 43.654,
|
| 62 |
+
"train_steps_per_second": 2.731
|
| 63 |
+
}
|
| 64 |
+
],
|
| 65 |
+
"max_steps": 1605,
|
| 66 |
+
"num_train_epochs": 3,
|
| 67 |
+
"total_flos": 4562104380880896.0,
|
| 68 |
+
"trial_name": null,
|
| 69 |
+
"trial_params": null
|
| 70 |
+
}
|