Training in progress, step 580, checkpoint
Browse files
last-checkpoint/adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 70430032
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0550856e8c5ffe718f27b6251a10c2d584a524baf4c8152e1cd219f9169c37fc
|
| 3 |
size 70430032
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 141058579
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:474f7b4c43d108b4cd1d5366b625488d3654336c80ef295c20e8a3dbce1d4e8d
|
| 3 |
size 141058579
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14645
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a3140e01ac85c810d8fd77bf3a10cbe89cc874aefee356886db6544c7b6037ce
|
| 3 |
size 14645
|
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 sha256:282809178dae42b67982ea6894af4966949a61b782fee74d2b37ea8b3b19f28d
|
| 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": 0.
|
| 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,
|
|
@@ -588,6 +588,16 @@
|
|
| 588 |
"mean_token_accuracy": 0.7418766617774963,
|
| 589 |
"num_tokens": 2633308.0,
|
| 590 |
"step": 570
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 591 |
}
|
| 592 |
],
|
| 593 |
"logging_steps": 10,
|
|
@@ -607,7 +617,7 @@
|
|
| 607 |
"attributes": {}
|
| 608 |
}
|
| 609 |
},
|
| 610 |
-
"total_flos": 1.
|
| 611 |
"train_batch_size": 4,
|
| 612 |
"trial_name": null,
|
| 613 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.12373333333333333,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 580,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 588 |
"mean_token_accuracy": 0.7418766617774963,
|
| 589 |
"num_tokens": 2633308.0,
|
| 590 |
"step": 570
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"entropy": 1.0902433142066001,
|
| 594 |
+
"epoch": 0.12373333333333333,
|
| 595 |
+
"grad_norm": 0.20525577664375305,
|
| 596 |
+
"learning_rate": 9.976701840063136e-05,
|
| 597 |
+
"loss": 1.1464842796325683,
|
| 598 |
+
"mean_token_accuracy": 0.735442753136158,
|
| 599 |
+
"num_tokens": 2686009.0,
|
| 600 |
+
"step": 580
|
| 601 |
}
|
| 602 |
],
|
| 603 |
"logging_steps": 10,
|
|
|
|
| 617 |
"attributes": {}
|
| 618 |
}
|
| 619 |
},
|
| 620 |
+
"total_flos": 1.2798133199591424e+16,
|
| 621 |
"train_batch_size": 4,
|
| 622 |
"trial_name": null,
|
| 623 |
"trial_params": null
|