Training in progress, step 800, 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 sha256:6cf7de87723ae01ee21e6a0963fbfb83323677a0272b18a9b8a77d5011402751
|
| 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 sha256:1c2fd265d1321cc386aa82a6f4583dbe678514c34065a5b323ae9f384465348e
|
| 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:c3472764f657ffe1789e9e4d4e24bd69c8a7c66a767a9f80ea83990b7dbb2b40
|
| 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,
|
|
@@ -1430,6 +1430,24 @@
|
|
| 1430 |
"mean_token_accuracy": 0.6515646994113922,
|
| 1431 |
"num_tokens": 2880896.0,
|
| 1432 |
"step": 790
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1433 |
}
|
| 1434 |
],
|
| 1435 |
"logging_steps": 5,
|
|
@@ -1449,7 +1467,7 @@
|
|
| 1449 |
"attributes": {}
|
| 1450 |
}
|
| 1451 |
},
|
| 1452 |
-
"total_flos": 1.
|
| 1453 |
"train_batch_size": 4,
|
| 1454 |
"trial_name": null,
|
| 1455 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 6.153846153846154,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 800,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 1430 |
"mean_token_accuracy": 0.6515646994113922,
|
| 1431 |
"num_tokens": 2880896.0,
|
| 1432 |
"step": 790
|
| 1433 |
+
},
|
| 1434 |
+
{
|
| 1435 |
+
"epoch": 6.115384615384615,
|
| 1436 |
+
"grad_norm": 0.0,
|
| 1437 |
+
"learning_rate": 4.603e-05,
|
| 1438 |
+
"loss": 1.7509,
|
| 1439 |
+
"mean_token_accuracy": 0.6432402580976486,
|
| 1440 |
+
"num_tokens": 2899195.0,
|
| 1441 |
+
"step": 795
|
| 1442 |
+
},
|
| 1443 |
+
{
|
| 1444 |
+
"epoch": 6.153846153846154,
|
| 1445 |
+
"grad_norm": 0.0,
|
| 1446 |
+
"learning_rate": 4.6005000000000004e-05,
|
| 1447 |
+
"loss": 1.7547,
|
| 1448 |
+
"mean_token_accuracy": 0.6499321848154068,
|
| 1449 |
+
"num_tokens": 2916949.0,
|
| 1450 |
+
"step": 800
|
| 1451 |
}
|
| 1452 |
],
|
| 1453 |
"logging_steps": 5,
|
|
|
|
| 1467 |
"attributes": {}
|
| 1468 |
}
|
| 1469 |
},
|
| 1470 |
+
"total_flos": 1.4789944036048896e+17,
|
| 1471 |
"train_batch_size": 4,
|
| 1472 |
"trial_name": null,
|
| 1473 |
"trial_params": null
|