Training in progress, step 9800, 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 sha256:3d4a7c16fca1185f7b4ec8bba46d3d80f28aa0bb119a2a511c524970770650a2
|
| 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 sha256:65c33261b4bc861cb5f7526794f51cdb4b5a1e21aa33b7a3f11e652b2400e89c
|
| 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 sha256:8ba3dd4f37e1dad78fec8dc5e14481e73ae2ec26f976948fe1080d8d782c0520
|
| 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": 75.
|
| 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,
|
|
@@ -17630,6 +17630,24 @@
|
|
| 17630 |
"mean_token_accuracy": 0.6478731304407119,
|
| 17631 |
"num_tokens": 35546499.0,
|
| 17632 |
"step": 9790
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 17633 |
}
|
| 17634 |
],
|
| 17635 |
"logging_steps": 5,
|
|
@@ -17649,7 +17667,7 @@
|
|
| 17649 |
"attributes": {}
|
| 17650 |
}
|
| 17651 |
},
|
| 17652 |
-
"total_flos": 1.
|
| 17653 |
"train_batch_size": 4,
|
| 17654 |
"trial_name": null,
|
| 17655 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 75.38461538461539,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 9800,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 17630 |
"mean_token_accuracy": 0.6478731304407119,
|
| 17631 |
"num_tokens": 35546499.0,
|
| 17632 |
"step": 9790
|
| 17633 |
+
},
|
| 17634 |
+
{
|
| 17635 |
+
"epoch": 75.34615384615384,
|
| 17636 |
+
"grad_norm": 0.0,
|
| 17637 |
+
"learning_rate": 1.03e-06,
|
| 17638 |
+
"loss": 1.832,
|
| 17639 |
+
"mean_token_accuracy": 0.640063899755478,
|
| 17640 |
+
"num_tokens": 35564534.0,
|
| 17641 |
+
"step": 9795
|
| 17642 |
+
},
|
| 17643 |
+
{
|
| 17644 |
+
"epoch": 75.38461538461539,
|
| 17645 |
+
"grad_norm": 0.0,
|
| 17646 |
+
"learning_rate": 1.0050000000000001e-06,
|
| 17647 |
+
"loss": 1.8289,
|
| 17648 |
+
"mean_token_accuracy": 0.6418118208646775,
|
| 17649 |
+
"num_tokens": 35582483.0,
|
| 17650 |
+
"step": 9800
|
| 17651 |
}
|
| 17652 |
],
|
| 17653 |
"logging_steps": 5,
|
|
|
|
| 17667 |
"attributes": {}
|
| 17668 |
}
|
| 17669 |
},
|
| 17670 |
+
"total_flos": 1.0167151628373443e+18,
|
| 17671 |
"train_batch_size": 4,
|
| 17672 |
"trial_name": null,
|
| 17673 |
"trial_params": null
|