Commit
•
12ddf06
1
Parent(s):
b4cf6fb
End of training
Browse files- all_results.json +14 -0
- eval_results.json +9 -0
- runs/Oct10_07-25-26_patrick-general-gpu/events.out.tfevents.1633850743.patrick-general-gpu.98066.0 +2 -2
- runs/Oct10_07-25-26_patrick-general-gpu/events.out.tfevents.1633852867.patrick-general-gpu.98066.2 +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": 0.6554446816444397,
|
| 4 |
+
"eval_matthews_correlation": 0.0,
|
| 5 |
+
"eval_runtime": 22.8156,
|
| 6 |
+
"eval_samples": 1043,
|
| 7 |
+
"eval_samples_per_second": 45.714,
|
| 8 |
+
"eval_steps_per_second": 5.742,
|
| 9 |
+
"train_loss": 0.6488206683195451,
|
| 10 |
+
"train_runtime": 2083.1528,
|
| 11 |
+
"train_samples": 8551,
|
| 12 |
+
"train_samples_per_second": 12.315,
|
| 13 |
+
"train_steps_per_second": 3.079
|
| 14 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"eval_loss": 0.6554446816444397,
|
| 4 |
+
"eval_matthews_correlation": 0.0,
|
| 5 |
+
"eval_runtime": 22.8156,
|
| 6 |
+
"eval_samples": 1043,
|
| 7 |
+
"eval_samples_per_second": 45.714,
|
| 8 |
+
"eval_steps_per_second": 5.742
|
| 9 |
+
}
|
runs/Oct10_07-25-26_patrick-general-gpu/events.out.tfevents.1633850743.patrick-general-gpu.98066.0
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:fd24ffd47f0308a34d40783b9550226c3473f605fb64de98f869d58f6db228da
|
| 3 |
+
size 5103
|
runs/Oct10_07-25-26_patrick-general-gpu/events.out.tfevents.1633852867.patrick-general-gpu.98066.2
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d61db6b3218503f641f316de6b2ddef0694aa1a600b8259485d7872f76a769b6
|
| 3 |
+
size 375
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"train_loss": 0.6488206683195451,
|
| 4 |
+
"train_runtime": 2083.1528,
|
| 5 |
+
"train_samples": 8551,
|
| 6 |
+
"train_samples_per_second": 12.315,
|
| 7 |
+
"train_steps_per_second": 3.079
|
| 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": 7.408177408177407e-05,
|
| 13 |
+
"loss": 0.6408,
|
| 14 |
+
"step": 2138
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 1.0,
|
| 18 |
+
"eval_loss": 0.7329378128051758,
|
| 19 |
+
"eval_matthews_correlation": 0.0,
|
| 20 |
+
"eval_runtime": 22.7321,
|
| 21 |
+
"eval_samples_per_second": 45.882,
|
| 22 |
+
"eval_steps_per_second": 5.763,
|
| 23 |
+
"step": 2138
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 2.0,
|
| 27 |
+
"learning_rate": 3.704088704088704e-05,
|
| 28 |
+
"loss": 0.6589,
|
| 29 |
+
"step": 4276
|
| 30 |
+
},
|
| 31 |
+
{
|
| 32 |
+
"epoch": 2.0,
|
| 33 |
+
"eval_loss": 0.6311050057411194,
|
| 34 |
+
"eval_matthews_correlation": 0.0,
|
| 35 |
+
"eval_runtime": 22.7597,
|
| 36 |
+
"eval_samples_per_second": 45.827,
|
| 37 |
+
"eval_steps_per_second": 5.756,
|
| 38 |
+
"step": 4276
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 3.0,
|
| 42 |
+
"learning_rate": 0.0,
|
| 43 |
+
"loss": 0.6467,
|
| 44 |
+
"step": 6414
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 3.0,
|
| 48 |
+
"eval_loss": 0.6554446816444397,
|
| 49 |
+
"eval_matthews_correlation": 0.0,
|
| 50 |
+
"eval_runtime": 22.7256,
|
| 51 |
+
"eval_samples_per_second": 45.895,
|
| 52 |
+
"eval_steps_per_second": 5.764,
|
| 53 |
+
"step": 6414
|
| 54 |
+
},
|
| 55 |
+
{
|
| 56 |
+
"epoch": 3.0,
|
| 57 |
+
"step": 6414,
|
| 58 |
+
"total_flos": 1.6048929796061184e+16,
|
| 59 |
+
"train_loss": 0.6488206683195451,
|
| 60 |
+
"train_runtime": 2083.1528,
|
| 61 |
+
"train_samples_per_second": 12.315,
|
| 62 |
+
"train_steps_per_second": 3.079
|
| 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 |
+
}
|