Commit
·
f4a7daf
1
Parent(s):
5dc7deb
End of training
Browse files- all_results.json +14 -0
- eval_results.json +9 -0
- runs/Oct10_12-10-25_patrick-general-gpu/events.out.tfevents.1633867847.patrick-general-gpu.107480.0 +2 -2
- runs/Oct10_12-10-25_patrick-general-gpu/events.out.tfevents.1633869966.patrick-general-gpu.107480.2 +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": 0.6499619483947754,
|
| 4 |
+
"eval_matthews_correlation": 0.0,
|
| 5 |
+
"eval_runtime": 22.8972,
|
| 6 |
+
"eval_samples": 1043,
|
| 7 |
+
"eval_samples_per_second": 45.551,
|
| 8 |
+
"eval_steps_per_second": 5.721,
|
| 9 |
+
"train_loss": 0.6344882166939507,
|
| 10 |
+
"train_runtime": 2078.6327,
|
| 11 |
+
"train_samples": 8551,
|
| 12 |
+
"train_samples_per_second": 12.341,
|
| 13 |
+
"train_steps_per_second": 3.086
|
| 14 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"eval_loss": 0.6499619483947754,
|
| 4 |
+
"eval_matthews_correlation": 0.0,
|
| 5 |
+
"eval_runtime": 22.8972,
|
| 6 |
+
"eval_samples": 1043,
|
| 7 |
+
"eval_samples_per_second": 45.551,
|
| 8 |
+
"eval_steps_per_second": 5.721
|
| 9 |
+
}
|
runs/Oct10_12-10-25_patrick-general-gpu/events.out.tfevents.1633867847.patrick-general-gpu.107480.0
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 sha256:66444e1b3054917437a507e6dced26a0a888744e912be3a7ef1ca8e7681163c8
|
| 3 |
+
size 5106
|
runs/Oct10_12-10-25_patrick-general-gpu/events.out.tfevents.1633869966.patrick-general-gpu.107480.2
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ba56c4dd3e7052ccfbf03272c209960eeb6ed7d6d635aa1d131767f2d20cbf61
|
| 3 |
+
size 375
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"train_loss": 0.6344882166939507,
|
| 4 |
+
"train_runtime": 2078.6327,
|
| 5 |
+
"train_samples": 8551,
|
| 6 |
+
"train_samples_per_second": 12.341,
|
| 7 |
+
"train_steps_per_second": 3.086
|
| 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": 6414,
|
| 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": 2.6700000000000002e-05,
|
| 13 |
+
"loss": 0.6345,
|
| 14 |
+
"step": 2138
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 1.0,
|
| 18 |
+
"eval_loss": 0.6611062288284302,
|
| 19 |
+
"eval_matthews_correlation": 0.0,
|
| 20 |
+
"eval_runtime": 22.7702,
|
| 21 |
+
"eval_samples_per_second": 45.805,
|
| 22 |
+
"eval_steps_per_second": 5.753,
|
| 23 |
+
"step": 2138
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 2.0,
|
| 27 |
+
"learning_rate": 1.3400000000000002e-05,
|
| 28 |
+
"loss": 0.6359,
|
| 29 |
+
"step": 4276
|
| 30 |
+
},
|
| 31 |
+
{
|
| 32 |
+
"epoch": 2.0,
|
| 33 |
+
"eval_loss": 0.6839953064918518,
|
| 34 |
+
"eval_matthews_correlation": 0.0,
|
| 35 |
+
"eval_runtime": 22.7541,
|
| 36 |
+
"eval_samples_per_second": 45.838,
|
| 37 |
+
"eval_steps_per_second": 5.757,
|
| 38 |
+
"step": 4276
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 3.0,
|
| 42 |
+
"learning_rate": 1e-07,
|
| 43 |
+
"loss": 0.6331,
|
| 44 |
+
"step": 6414
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 3.0,
|
| 48 |
+
"eval_loss": 0.6499619483947754,
|
| 49 |
+
"eval_matthews_correlation": 0.0,
|
| 50 |
+
"eval_runtime": 22.8768,
|
| 51 |
+
"eval_samples_per_second": 45.592,
|
| 52 |
+
"eval_steps_per_second": 5.726,
|
| 53 |
+
"step": 6414
|
| 54 |
+
},
|
| 55 |
+
{
|
| 56 |
+
"epoch": 3.0,
|
| 57 |
+
"step": 6414,
|
| 58 |
+
"total_flos": 1.6048929796061184e+16,
|
| 59 |
+
"train_loss": 0.6344882166939507,
|
| 60 |
+
"train_runtime": 2078.6327,
|
| 61 |
+
"train_samples_per_second": 12.341,
|
| 62 |
+
"train_steps_per_second": 3.086
|
| 63 |
+
}
|
| 64 |
+
],
|
| 65 |
+
"max_steps": 6414,
|
| 66 |
+
"num_train_epochs": 3,
|
| 67 |
+
"total_flos": 1.6048929796061184e+16,
|
| 68 |
+
"trial_name": null,
|
| 69 |
+
"trial_params": null
|
| 70 |
+
}
|