Training in progress, epoch 2, checkpoint
Browse files
last-checkpoint/model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1447317080
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:734a2080aeb8b234856db56b501df0d6a8b93f9db7e4f19aa755eb1cca19b4ce
|
| 3 |
size 1447317080
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 2894813242
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8837fa91ace6c6b9aa324ab04a1618a72468931fac6ee3964460d89bb2fbf656
|
| 3 |
size 2894813242
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14244
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8d138cfe3a4adf21f048848ee35837c9a757a0a3616ff7adbb45b69aac247435
|
| 3 |
size 14244
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1064
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:350bc2964da995e89f1edcfd77857f78843f160ccef873eaed540186a8325344
|
| 3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric": 0.
|
| 3 |
-
"best_model_checkpoint": "./opt_trained2/checkpoint-
|
| 4 |
-
"epoch":
|
| 5 |
"eval_steps": 500,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
@@ -15,6 +15,14 @@
|
|
| 15 |
"eval_samples_per_second": 10.422,
|
| 16 |
"eval_steps_per_second": 2.605,
|
| 17 |
"step": 85
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 18 |
}
|
| 19 |
],
|
| 20 |
"logging_steps": 500,
|
|
@@ -34,7 +42,7 @@
|
|
| 34 |
"attributes": {}
|
| 35 |
}
|
| 36 |
},
|
| 37 |
-
"total_flos":
|
| 38 |
"train_batch_size": 4,
|
| 39 |
"trial_name": null,
|
| 40 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 0.5468895435333252,
|
| 3 |
+
"best_model_checkpoint": "./opt_trained2/checkpoint-170",
|
| 4 |
+
"epoch": 2.0,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 170,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 15 |
"eval_samples_per_second": 10.422,
|
| 16 |
"eval_steps_per_second": 2.605,
|
| 17 |
"step": 85
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 2.0,
|
| 21 |
+
"eval_loss": 0.5468895435333252,
|
| 22 |
+
"eval_runtime": 28.8025,
|
| 23 |
+
"eval_samples_per_second": 10.416,
|
| 24 |
+
"eval_steps_per_second": 2.604,
|
| 25 |
+
"step": 170
|
| 26 |
}
|
| 27 |
],
|
| 28 |
"logging_steps": 500,
|
|
|
|
| 42 |
"attributes": {}
|
| 43 |
}
|
| 44 |
},
|
| 45 |
+
"total_flos": 6560634750912000.0,
|
| 46 |
"train_batch_size": 4,
|
| 47 |
"trial_name": null,
|
| 48 |
"trial_params": null
|