Training in progress, step 5880, 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:e41eebfefabcaacfa242a43c804d673ddb9a825d33a1be91483448b64940c59a
|
| 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 sha256:95dd032eab2f9d6f7fc7edbc0b3e592dcbcdcd03ccee4145cebc9960c69dd4d1
|
| 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 sha256:880b93c3266220f3b920899de28f68a706d57badf990d82216b7e2a3f3ec19a3
|
| 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": 45.
|
| 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,
|
|
@@ -10574,6 +10574,24 @@
|
|
| 10574 |
"mean_token_accuracy": 0.6544335097074508,
|
| 10575 |
"num_tokens": 21409214.0,
|
| 10576 |
"step": 5870
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 10577 |
}
|
| 10578 |
],
|
| 10579 |
"logging_steps": 5,
|
|
@@ -10593,7 +10611,7 @@
|
|
| 10593 |
"attributes": {}
|
| 10594 |
}
|
| 10595 |
},
|
| 10596 |
-
"total_flos": 1.
|
| 10597 |
"train_batch_size": 4,
|
| 10598 |
"trial_name": null,
|
| 10599 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 45.23076923076923,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 5880,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 10574 |
"mean_token_accuracy": 0.6544335097074508,
|
| 10575 |
"num_tokens": 21409214.0,
|
| 10576 |
"step": 5870
|
| 10577 |
+
},
|
| 10578 |
+
{
|
| 10579 |
+
"epoch": 45.19230769230769,
|
| 10580 |
+
"grad_norm": 0.0,
|
| 10581 |
+
"learning_rate": 2.063e-05,
|
| 10582 |
+
"loss": 1.6598,
|
| 10583 |
+
"mean_token_accuracy": 0.6647601097822189,
|
| 10584 |
+
"num_tokens": 21428341.0,
|
| 10585 |
+
"step": 5875
|
| 10586 |
+
},
|
| 10587 |
+
{
|
| 10588 |
+
"epoch": 45.23076923076923,
|
| 10589 |
+
"grad_norm": 0.0,
|
| 10590 |
+
"learning_rate": 2.0605000000000003e-05,
|
| 10591 |
+
"loss": 1.7528,
|
| 10592 |
+
"mean_token_accuracy": 0.6484750181436538,
|
| 10593 |
+
"num_tokens": 21446444.0,
|
| 10594 |
+
"step": 5880
|
| 10595 |
}
|
| 10596 |
],
|
| 10597 |
"logging_steps": 5,
|
|
|
|
| 10611 |
"attributes": {}
|
| 10612 |
}
|
| 10613 |
},
|
| 10614 |
+
"total_flos": 1.086802926109655e+18,
|
| 10615 |
"train_batch_size": 4,
|
| 10616 |
"trial_name": null,
|
| 10617 |
"trial_params": null
|