Training in progress, step 810, 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:dba242de91b0429ebdbe530487f3bc3ade6b35529323e9148987d0d82f1769a8
|
| 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 sha256:835f638db9e4c4893a2ced041ea1149cde88428eea997ffcb551d5ee17ebd5aa
|
| 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:bb57cf2cb1ecb4a5f31ef1492658ab91c8519f349d7b77dc2225bd591b8ea138
|
| 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.
|
| 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,
|
|
@@ -1448,6 +1448,24 @@
|
|
| 1448 |
"mean_token_accuracy": 0.6499321848154068,
|
| 1449 |
"num_tokens": 2916949.0,
|
| 1450 |
"step": 800
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1451 |
}
|
| 1452 |
],
|
| 1453 |
"logging_steps": 5,
|
|
@@ -1467,7 +1485,7 @@
|
|
| 1467 |
"attributes": {}
|
| 1468 |
}
|
| 1469 |
},
|
| 1470 |
-
"total_flos": 1.
|
| 1471 |
"train_batch_size": 4,
|
| 1472 |
"trial_name": null,
|
| 1473 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 6.230769230769231,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 810,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 1448 |
"mean_token_accuracy": 0.6499321848154068,
|
| 1449 |
"num_tokens": 2916949.0,
|
| 1450 |
"step": 800
|
| 1451 |
+
},
|
| 1452 |
+
{
|
| 1453 |
+
"epoch": 6.1923076923076925,
|
| 1454 |
+
"grad_norm": 0.0,
|
| 1455 |
+
"learning_rate": 4.5980000000000004e-05,
|
| 1456 |
+
"loss": 1.7903,
|
| 1457 |
+
"mean_token_accuracy": 0.6418056339025497,
|
| 1458 |
+
"num_tokens": 2935129.0,
|
| 1459 |
+
"step": 805
|
| 1460 |
+
},
|
| 1461 |
+
{
|
| 1462 |
+
"epoch": 6.230769230769231,
|
| 1463 |
+
"grad_norm": 0.0,
|
| 1464 |
+
"learning_rate": 4.5955e-05,
|
| 1465 |
+
"loss": 1.7601,
|
| 1466 |
+
"mean_token_accuracy": 0.64379281103611,
|
| 1467 |
+
"num_tokens": 2953207.0,
|
| 1468 |
+
"step": 810
|
| 1469 |
}
|
| 1470 |
],
|
| 1471 |
"logging_steps": 5,
|
|
|
|
| 1485 |
"attributes": {}
|
| 1486 |
}
|
| 1487 |
},
|
| 1488 |
+
"total_flos": 1.4969761419165696e+17,
|
| 1489 |
"train_batch_size": 4,
|
| 1490 |
"trial_name": null,
|
| 1491 |
"trial_params": null
|