Training in progress, step 9230, checkpoint
Browse files
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1657
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d4cab95818a049240d4a9cbf7754ba67137659dd7ab8438f2230126c34667e2b
|
| 3 |
size 1657
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14709
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f1b9265d3ac2a3dac4ca1737f96287bdd7736a9993418d6691b46ee031b832cb
|
| 3 |
size 14709
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1465
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b02aced4e850e3a99cc9f14a8e6e8fd0a11bdb832af582c88a5c53ded714ceec
|
| 3 |
size 1465
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -2,9 +2,9 @@
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
-
"epoch":
|
| 6 |
"eval_steps": 500,
|
| 7 |
-
"global_step":
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
@@ -16604,6 +16604,24 @@
|
|
| 16604 |
"mean_token_accuracy": 0.6562773436307907,
|
| 16605 |
"num_tokens": 33623715.0,
|
| 16606 |
"step": 9220
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 16607 |
}
|
| 16608 |
],
|
| 16609 |
"logging_steps": 5,
|
|
@@ -16623,7 +16641,7 @@
|
|
| 16623 |
"attributes": {}
|
| 16624 |
}
|
| 16625 |
},
|
| 16626 |
-
"total_flos": 1.
|
| 16627 |
"train_batch_size": 4,
|
| 16628 |
"trial_name": null,
|
| 16629 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 71.0,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 9230,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 16604 |
"mean_token_accuracy": 0.6562773436307907,
|
| 16605 |
"num_tokens": 33623715.0,
|
| 16606 |
"step": 9220
|
| 16607 |
+
},
|
| 16608 |
+
{
|
| 16609 |
+
"epoch": 70.96153846153847,
|
| 16610 |
+
"grad_norm": 0.0,
|
| 16611 |
+
"learning_rate": 3.88e-06,
|
| 16612 |
+
"loss": 1.6681,
|
| 16613 |
+
"mean_token_accuracy": 0.6675117045640946,
|
| 16614 |
+
"num_tokens": 33642936.0,
|
| 16615 |
+
"step": 9225
|
| 16616 |
+
},
|
| 16617 |
+
{
|
| 16618 |
+
"epoch": 71.0,
|
| 16619 |
+
"grad_norm": 0.0,
|
| 16620 |
+
"learning_rate": 3.855e-06,
|
| 16621 |
+
"loss": 1.7163,
|
| 16622 |
+
"mean_token_accuracy": 0.6542115420103073,
|
| 16623 |
+
"num_tokens": 33661455.0,
|
| 16624 |
+
"step": 9230
|
| 16625 |
}
|
| 16626 |
],
|
| 16627 |
"logging_steps": 5,
|
|
|
|
| 16641 |
"attributes": {}
|
| 16642 |
}
|
| 16643 |
},
|
| 16644 |
+
"total_flos": 1.706881855687557e+18,
|
| 16645 |
"train_batch_size": 4,
|
| 16646 |
"trial_name": null,
|
| 16647 |
"trial_params": null
|