Training in progress, step 6460, 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 sha256:1ac8f9ee393e7ad16ed31ccedcb20328302d2913028b6ddacc61705176d262d0
|
| 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 sha256:5d7fcdb3e9631dc492abe9796013a4657712d092c0181dc52262c1ea8d725b35
|
| 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 sha256:8bf9d541dad367043d1f0683c0503a0e1fac068a476204016f4e8d94a9231682
|
| 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": 49.
|
| 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,
|
|
@@ -11618,6 +11618,24 @@
|
|
| 11618 |
"mean_token_accuracy": 0.6565153568983078,
|
| 11619 |
"num_tokens": 23522965.0,
|
| 11620 |
"step": 6450
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 11621 |
}
|
| 11622 |
],
|
| 11623 |
"logging_steps": 5,
|
|
@@ -11637,7 +11655,7 @@
|
|
| 11637 |
"attributes": {}
|
| 11638 |
}
|
| 11639 |
},
|
| 11640 |
-
"total_flos": 1.
|
| 11641 |
"train_batch_size": 4,
|
| 11642 |
"trial_name": null,
|
| 11643 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 49.69230769230769,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 6460,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 11618 |
"mean_token_accuracy": 0.6565153568983078,
|
| 11619 |
"num_tokens": 23522965.0,
|
| 11620 |
"step": 6450
|
| 11621 |
+
},
|
| 11622 |
+
{
|
| 11623 |
+
"epoch": 49.65384615384615,
|
| 11624 |
+
"grad_norm": 0.0,
|
| 11625 |
+
"learning_rate": 1.773e-05,
|
| 11626 |
+
"loss": 1.7125,
|
| 11627 |
+
"mean_token_accuracy": 0.6582383394241333,
|
| 11628 |
+
"num_tokens": 23541321.0,
|
| 11629 |
+
"step": 6455
|
| 11630 |
+
},
|
| 11631 |
+
{
|
| 11632 |
+
"epoch": 49.69230769230769,
|
| 11633 |
+
"grad_norm": 0.0,
|
| 11634 |
+
"learning_rate": 1.7705e-05,
|
| 11635 |
+
"loss": 1.7213,
|
| 11636 |
+
"mean_token_accuracy": 0.6557675808668136,
|
| 11637 |
+
"num_tokens": 23559830.0,
|
| 11638 |
+
"step": 6460
|
| 11639 |
}
|
| 11640 |
],
|
| 11641 |
"logging_steps": 5,
|
|
|
|
| 11655 |
"attributes": {}
|
| 11656 |
}
|
| 11657 |
},
|
| 11658 |
+
"total_flos": 1.194267192751227e+18,
|
| 11659 |
"train_batch_size": 4,
|
| 11660 |
"trial_name": null,
|
| 11661 |
"trial_params": null
|