Training in progress, step 9700, 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 sha256:970dc2afbb75bed057af67a7f1321ea8a01aaffe99d4e18e34a9f393666cc0ac
|
| 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:ee4c29d7a7d3cbb584c60b306a1bde40b3a34676841d7193e58a1073e81eb706
|
| 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 sha256:64570d97131659bc377fd1dbf018f69dece5624953d03af3c2bf5599e3dac7be
|
| 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": 74.
|
| 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,
|
|
@@ -17450,6 +17450,24 @@
|
|
| 17450 |
"mean_token_accuracy": 0.6595968753099442,
|
| 17451 |
"num_tokens": 35338994.0,
|
| 17452 |
"step": 9690
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 17453 |
}
|
| 17454 |
],
|
| 17455 |
"logging_steps": 5,
|
|
@@ -17469,7 +17487,7 @@
|
|
| 17469 |
"attributes": {}
|
| 17470 |
}
|
| 17471 |
},
|
| 17472 |
-
"total_flos": 1.
|
| 17473 |
"train_batch_size": 4,
|
| 17474 |
"trial_name": null,
|
| 17475 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 74.61538461538461,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 9700,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 17450 |
"mean_token_accuracy": 0.6595968753099442,
|
| 17451 |
"num_tokens": 35338994.0,
|
| 17452 |
"step": 9690
|
| 17453 |
+
},
|
| 17454 |
+
{
|
| 17455 |
+
"epoch": 74.57692307692308,
|
| 17456 |
+
"grad_norm": 0.0,
|
| 17457 |
+
"learning_rate": 1.53e-06,
|
| 17458 |
+
"loss": 1.7309,
|
| 17459 |
+
"mean_token_accuracy": 0.6514750987291336,
|
| 17460 |
+
"num_tokens": 35357001.0,
|
| 17461 |
+
"step": 9695
|
| 17462 |
+
},
|
| 17463 |
+
{
|
| 17464 |
+
"epoch": 74.61538461538461,
|
| 17465 |
+
"grad_norm": 0.0,
|
| 17466 |
+
"learning_rate": 1.505e-06,
|
| 17467 |
+
"loss": 1.6814,
|
| 17468 |
+
"mean_token_accuracy": 0.6643463402986527,
|
| 17469 |
+
"num_tokens": 35375365.0,
|
| 17470 |
+
"step": 9700
|
| 17471 |
}
|
| 17472 |
],
|
| 17473 |
"logging_steps": 5,
|
|
|
|
| 17487 |
"attributes": {}
|
| 17488 |
}
|
| 17489 |
},
|
| 17490 |
+
"total_flos": 1.7939545929149645e+18,
|
| 17491 |
"train_batch_size": 4,
|
| 17492 |
"trial_name": null,
|
| 17493 |
"trial_params": null
|