Training in progress, epoch 15
Browse files- last-checkpoint/optimizer.pt +1 -1
- last-checkpoint/pytorch_model.bin +1 -1
- last-checkpoint/rng_state.pth +1 -1
- last-checkpoint/scheduler.pt +1 -1
- last-checkpoint/trainer_state.json +12 -3
- pytorch_model.bin +1 -1
- runs/Apr30_07-42-25_943994db1dae/events.out.tfevents.1682840548.943994db1dae.1004.2 +2 -2
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 875994245
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0224467ba7fa1c04ee59a3dc093eecbabfa5f3380c87857341e4aa14c1e9f8b0
|
| 3 |
size 875994245
|
last-checkpoint/pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 438010997
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c2e6f883ae219e59d43498bf31e93bdd325d9cd4ec3d044b211b3113e5a9e5bf
|
| 3 |
size 438010997
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14575
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1b95044e0e0dd1cf03324c6d0a41ae9e1cc83e92cabb5ced8d57b590b22c6471
|
| 3 |
size 14575
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 627
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a22266ab70009f9523ffd69a057ee9e48f24be4a6e49f76032cd8b959cdb3f8d
|
| 3 |
size 627
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": 0.508567750453949,
|
| 3 |
"best_model_checkpoint": "bert_final_model/checkpoint-430",
|
| 4 |
-
"epoch":
|
| 5 |
-
"global_step":
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
|
@@ -204,11 +204,20 @@
|
|
| 204 |
"eval_samples_per_second": 235.249,
|
| 205 |
"eval_steps_per_second": 3.728,
|
| 206 |
"step": 6020
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 207 |
}
|
| 208 |
],
|
| 209 |
"max_steps": 8600,
|
| 210 |
"num_train_epochs": 20,
|
| 211 |
-
"total_flos": 2.
|
| 212 |
"trial_name": null,
|
| 213 |
"trial_params": null
|
| 214 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": 0.508567750453949,
|
| 3 |
"best_model_checkpoint": "bert_final_model/checkpoint-430",
|
| 4 |
+
"epoch": 15.0,
|
| 5 |
+
"global_step": 6450,
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
|
|
|
| 204 |
"eval_samples_per_second": 235.249,
|
| 205 |
"eval_steps_per_second": 3.728,
|
| 206 |
"step": 6020
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 15.0,
|
| 210 |
+
"eval_accuracy": 0.7784380305602716,
|
| 211 |
+
"eval_loss": 1.1496540307998657,
|
| 212 |
+
"eval_runtime": 14.9724,
|
| 213 |
+
"eval_samples_per_second": 236.034,
|
| 214 |
+
"eval_steps_per_second": 3.74,
|
| 215 |
+
"step": 6450
|
| 216 |
}
|
| 217 |
],
|
| 218 |
"max_steps": 8600,
|
| 219 |
"num_train_epochs": 20,
|
| 220 |
+
"total_flos": 2.33018021948481e+16,
|
| 221 |
"trial_name": null,
|
| 222 |
"trial_params": null
|
| 223 |
}
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 438010997
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c2e6f883ae219e59d43498bf31e93bdd325d9cd4ec3d044b211b3113e5a9e5bf
|
| 3 |
size 438010997
|
runs/Apr30_07-42-25_943994db1dae/events.out.tfevents.1682840548.943994db1dae.1004.2
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:fdd9fe6a9656056aff0121f5d9a06343c9b8ec9681ef729cbc8b7614ae75003a
|
| 3 |
+
size 10922
|