Training in progress, step 5330, 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:b2793719a845f35a7869758a55fdf8e01c6819b8e068bf277a7fc11d69c5c8ac
|
| 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 sha256:8d8645c395454a990cc870a8044d3df7bed4dd2d960fc543a858857056df78a2
|
| 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:c61cc28a2ca8127ad6ad885b12b734d576453268c3498e95b163222e1722e849
|
| 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 |
"eval_steps": 500,
|
| 7 |
-
"global_step":
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
@@ -9584,6 +9584,24 @@
|
|
| 9584 |
"mean_token_accuracy": 0.6605125904083252,
|
| 9585 |
"num_tokens": 19401413.0,
|
| 9586 |
"step": 5320
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 9587 |
}
|
| 9588 |
],
|
| 9589 |
"logging_steps": 5,
|
|
@@ -9603,7 +9621,7 @@
|
|
| 9603 |
"attributes": {}
|
| 9604 |
}
|
| 9605 |
},
|
| 9606 |
-
"total_flos": 9.
|
| 9607 |
"train_batch_size": 4,
|
| 9608 |
"trial_name": null,
|
| 9609 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 41.0,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 5330,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 9584 |
"mean_token_accuracy": 0.6605125904083252,
|
| 9585 |
"num_tokens": 19401413.0,
|
| 9586 |
"step": 5320
|
| 9587 |
+
},
|
| 9588 |
+
{
|
| 9589 |
+
"epoch": 40.96153846153846,
|
| 9590 |
+
"grad_norm": 0.0,
|
| 9591 |
+
"learning_rate": 2.3380000000000003e-05,
|
| 9592 |
+
"loss": 1.7979,
|
| 9593 |
+
"mean_token_accuracy": 0.6404047667980194,
|
| 9594 |
+
"num_tokens": 19419042.0,
|
| 9595 |
+
"step": 5325
|
| 9596 |
+
},
|
| 9597 |
+
{
|
| 9598 |
+
"epoch": 41.0,
|
| 9599 |
+
"grad_norm": 0.0,
|
| 9600 |
+
"learning_rate": 2.3355000000000003e-05,
|
| 9601 |
+
"loss": 1.6808,
|
| 9602 |
+
"mean_token_accuracy": 0.6540407299995422,
|
| 9603 |
+
"num_tokens": 19438305.0,
|
| 9604 |
+
"step": 5330
|
| 9605 |
}
|
| 9606 |
],
|
| 9607 |
"logging_steps": 5,
|
|
|
|
| 9621 |
"attributes": {}
|
| 9622 |
}
|
| 9623 |
},
|
| 9624 |
+
"total_flos": 9.849475328090112e+17,
|
| 9625 |
"train_batch_size": 4,
|
| 9626 |
"trial_name": null,
|
| 9627 |
"trial_params": null
|