Training in progress, step 9240, 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 sha256:191803bb4a438a119ed784ea958e1a9bcd0f9286322b55a23d9e738f39cead8a
|
| 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 sha256:7050f48681249dd4e3a227744a4562066ad9bd7428128a5fff9b7c1ce2c619a9
|
| 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:d12af1954089d8cd2be3ceed67d950733925cd3325c7b37a34c24e58802f3f9d
|
| 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": 71.
|
| 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,
|
|
@@ -16622,6 +16622,24 @@
|
|
| 16622 |
"mean_token_accuracy": 0.6542115420103073,
|
| 16623 |
"num_tokens": 33661455.0,
|
| 16624 |
"step": 9230
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 16625 |
}
|
| 16626 |
],
|
| 16627 |
"logging_steps": 5,
|
|
@@ -16641,7 +16659,7 @@
|
|
| 16641 |
"attributes": {}
|
| 16642 |
}
|
| 16643 |
},
|
| 16644 |
-
"total_flos": 1.
|
| 16645 |
"train_batch_size": 4,
|
| 16646 |
"trial_name": null,
|
| 16647 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 71.07692307692308,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 9240,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 16622 |
"mean_token_accuracy": 0.6542115420103073,
|
| 16623 |
"num_tokens": 33661455.0,
|
| 16624 |
"step": 9230
|
| 16625 |
+
},
|
| 16626 |
+
{
|
| 16627 |
+
"epoch": 71.03846153846153,
|
| 16628 |
+
"grad_norm": 0.0,
|
| 16629 |
+
"learning_rate": 3.830000000000001e-06,
|
| 16630 |
+
"loss": 1.7668,
|
| 16631 |
+
"mean_token_accuracy": 0.6549015700817108,
|
| 16632 |
+
"num_tokens": 33679273.0,
|
| 16633 |
+
"step": 9235
|
| 16634 |
+
},
|
| 16635 |
+
{
|
| 16636 |
+
"epoch": 71.07692307692308,
|
| 16637 |
+
"grad_norm": 0.0,
|
| 16638 |
+
"learning_rate": 3.8050000000000004e-06,
|
| 16639 |
+
"loss": 1.7505,
|
| 16640 |
+
"mean_token_accuracy": 0.6491267591714859,
|
| 16641 |
+
"num_tokens": 33697022.0,
|
| 16642 |
+
"step": 9240
|
| 16643 |
}
|
| 16644 |
],
|
| 16645 |
"logging_steps": 5,
|
|
|
|
| 16659 |
"attributes": {}
|
| 16660 |
}
|
| 16661 |
},
|
| 16662 |
+
"total_flos": 1.7086916203964006e+18,
|
| 16663 |
"train_batch_size": 4,
|
| 16664 |
"trial_name": null,
|
| 16665 |
"trial_params": null
|