Commit
•
1e169f3
1
Parent(s):
6d35716
End of training
Browse files- all_results.json +14 -0
- eval_results.json +9 -0
- runs/Sep16_18-47-00_patrick-general-gpu/events.out.tfevents.1631818036.patrick-general-gpu.195949.0 +2 -2
- runs/Sep16_18-47-00_patrick-general-gpu/events.out.tfevents.1631818916.patrick-general-gpu.195949.2 +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": 0.6747468709945679,
|
| 4 |
+
"eval_matthews_correlation": 0.5956649094312695,
|
| 5 |
+
"eval_runtime": 10.7534,
|
| 6 |
+
"eval_samples": 1043,
|
| 7 |
+
"eval_samples_per_second": 96.992,
|
| 8 |
+
"eval_steps_per_second": 12.182,
|
| 9 |
+
"train_loss": 0.31777251056421585,
|
| 10 |
+
"train_runtime": 860.3783,
|
| 11 |
+
"train_samples": 8551,
|
| 12 |
+
"train_samples_per_second": 29.816,
|
| 13 |
+
"train_steps_per_second": 1.865
|
| 14 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"eval_loss": 0.6747468709945679,
|
| 4 |
+
"eval_matthews_correlation": 0.5956649094312695,
|
| 5 |
+
"eval_runtime": 10.7534,
|
| 6 |
+
"eval_samples": 1043,
|
| 7 |
+
"eval_samples_per_second": 96.992,
|
| 8 |
+
"eval_steps_per_second": 12.182
|
| 9 |
+
}
|
runs/Sep16_18-47-00_patrick-general-gpu/events.out.tfevents.1631818036.patrick-general-gpu.195949.0
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:c9fc7eb5b1138270bd5d18acbcb5002eaea759fdf30f5ababfd8560c2b98770c
|
| 3 |
+
size 5072
|
runs/Sep16_18-47-00_patrick-general-gpu/events.out.tfevents.1631818916.patrick-general-gpu.195949.2
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:276eb0da7ff9200cf723312841b212a3e00546cf8720229a8897ace088f81186
|
| 3 |
+
size 375
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"train_loss": 0.31777251056421585,
|
| 4 |
+
"train_runtime": 860.3783,
|
| 5 |
+
"train_samples": 8551,
|
| 6 |
+
"train_samples_per_second": 29.816,
|
| 7 |
+
"train_steps_per_second": 1.865
|
| 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": 0.4921,
|
| 14 |
+
"step": 535
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 1.0,
|
| 18 |
+
"eval_loss": 0.5283351540565491,
|
| 19 |
+
"eval_matthews_correlation": 0.5068375331988826,
|
| 20 |
+
"eval_runtime": 10.6748,
|
| 21 |
+
"eval_samples_per_second": 97.706,
|
| 22 |
+
"eval_steps_per_second": 12.272,
|
| 23 |
+
"step": 535
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 2.0,
|
| 27 |
+
"learning_rate": 6.666666666666667e-06,
|
| 28 |
+
"loss": 0.2837,
|
| 29 |
+
"step": 1070
|
| 30 |
+
},
|
| 31 |
+
{
|
| 32 |
+
"epoch": 2.0,
|
| 33 |
+
"eval_loss": 0.5132979154586792,
|
| 34 |
+
"eval_matthews_correlation": 0.5521390429003941,
|
| 35 |
+
"eval_runtime": 10.6848,
|
| 36 |
+
"eval_samples_per_second": 97.616,
|
| 37 |
+
"eval_steps_per_second": 12.26,
|
| 38 |
+
"step": 1070
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 3.0,
|
| 42 |
+
"learning_rate": 0.0,
|
| 43 |
+
"loss": 0.1775,
|
| 44 |
+
"step": 1605
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 3.0,
|
| 48 |
+
"eval_loss": 0.6747468709945679,
|
| 49 |
+
"eval_matthews_correlation": 0.5956649094312695,
|
| 50 |
+
"eval_runtime": 10.6837,
|
| 51 |
+
"eval_samples_per_second": 97.625,
|
| 52 |
+
"eval_steps_per_second": 12.262,
|
| 53 |
+
"step": 1605
|
| 54 |
+
},
|
| 55 |
+
{
|
| 56 |
+
"epoch": 3.0,
|
| 57 |
+
"step": 1605,
|
| 58 |
+
"total_flos": 6749587903150080.0,
|
| 59 |
+
"train_loss": 0.31777251056421585,
|
| 60 |
+
"train_runtime": 860.3783,
|
| 61 |
+
"train_samples_per_second": 29.816,
|
| 62 |
+
"train_steps_per_second": 1.865
|
| 63 |
+
}
|
| 64 |
+
],
|
| 65 |
+
"max_steps": 1605,
|
| 66 |
+
"num_train_epochs": 3,
|
| 67 |
+
"total_flos": 6749587903150080.0,
|
| 68 |
+
"trial_name": null,
|
| 69 |
+
"trial_params": null
|
| 70 |
+
}
|