Training in progress, epoch 8
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:c8d329899e0f975c7630bae0001dd8b706ee1b21fe7fa26701a8693f8041359d
|
| 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 sha256:3b0daf00d818f84e07a4ca2e76d8aee5d170fdfb6f41a7f60e35ba8b7e39a1d5
|
| 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:ed4f4b5a06665af3ea8b2ea26772a4575204bfd64911f21184d2bb3b95738fe2
|
| 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 sha256:2d9b3d1fa4c9cea32ac8ba5a422297d6566a911a577301b950237c40fa2ec4fe
|
| 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,
|
|
@@ -105,11 +105,20 @@
|
|
| 105 |
"eval_samples_per_second": 236.758,
|
| 106 |
"eval_steps_per_second": 3.752,
|
| 107 |
"step": 3010
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 108 |
}
|
| 109 |
],
|
| 110 |
"max_steps": 8600,
|
| 111 |
"num_train_epochs": 20,
|
| 112 |
-
"total_flos": 1.
|
| 113 |
"trial_name": null,
|
| 114 |
"trial_params": null
|
| 115 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": 0.508567750453949,
|
| 3 |
"best_model_checkpoint": "bert_final_model/checkpoint-430",
|
| 4 |
+
"epoch": 8.0,
|
| 5 |
+
"global_step": 3440,
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
|
|
|
| 105 |
"eval_samples_per_second": 236.758,
|
| 106 |
"eval_steps_per_second": 3.752,
|
| 107 |
"step": 3010
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 8.0,
|
| 111 |
+
"eval_accuracy": 0.7821165817770233,
|
| 112 |
+
"eval_loss": 0.7725191116333008,
|
| 113 |
+
"eval_runtime": 14.9366,
|
| 114 |
+
"eval_samples_per_second": 236.601,
|
| 115 |
+
"eval_steps_per_second": 3.749,
|
| 116 |
+
"step": 3440
|
| 117 |
}
|
| 118 |
],
|
| 119 |
"max_steps": 8600,
|
| 120 |
"num_train_epochs": 20,
|
| 121 |
+
"total_flos": 1.242762783725232e+16,
|
| 122 |
"trial_name": null,
|
| 123 |
"trial_params": null
|
| 124 |
}
|
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 sha256:3b0daf00d818f84e07a4ca2e76d8aee5d170fdfb6f41a7f60e35ba8b7e39a1d5
|
| 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 sha256:6c8a1a62b859f4380bbee507ab8b3caa5fd7ecd53b1b5af3420287e278bf41c1
|
| 3 |
+
size 7719
|