Training in progress, step 3580, 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:caa9b7c0a190c86f2695462813e725ed6169d7c326e76dbf137bd88402ae8cbe
|
| 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 sha256:0cb9e092b3f120ee3aa810a1773d3cd2154dc52ef0aa15c04fa4f15a5e5e5099
|
| 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:e75f99ba7404a13d285204d93a3e3637658ba102c01a0944ff1a22abbf3246be
|
| 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 sha256:3d6b09727e622e66e0924ba95376900463ef4050999980640d19d577396a0b5a
|
| 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,
|
|
@@ -3588,6 +3588,16 @@
|
|
| 3588 |
"mean_token_accuracy": 0.7954168729484081,
|
| 3589 |
"num_tokens": 16623992.0,
|
| 3590 |
"step": 3570
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3591 |
}
|
| 3592 |
],
|
| 3593 |
"logging_steps": 10,
|
|
@@ -3607,7 +3617,7 @@
|
|
| 3607 |
"attributes": {}
|
| 3608 |
}
|
| 3609 |
},
|
| 3610 |
-
"total_flos": 7.
|
| 3611 |
"train_batch_size": 4,
|
| 3612 |
"trial_name": null,
|
| 3613 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.7637333333333334,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 3580,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 3588 |
"mean_token_accuracy": 0.7954168729484081,
|
| 3589 |
"num_tokens": 16623992.0,
|
| 3590 |
"step": 3570
|
| 3591 |
+
},
|
| 3592 |
+
{
|
| 3593 |
+
"entropy": 0.8905762024223804,
|
| 3594 |
+
"epoch": 0.7637333333333334,
|
| 3595 |
+
"grad_norm": 0.24514277279376984,
|
| 3596 |
+
"learning_rate": 7.110651020476873e-05,
|
| 3597 |
+
"loss": 0.9519443511962891,
|
| 3598 |
+
"mean_token_accuracy": 0.7789977833628654,
|
| 3599 |
+
"num_tokens": 16666011.0,
|
| 3600 |
+
"step": 3580
|
| 3601 |
}
|
| 3602 |
],
|
| 3603 |
"logging_steps": 10,
|
|
|
|
| 3617 |
"attributes": {}
|
| 3618 |
}
|
| 3619 |
},
|
| 3620 |
+
"total_flos": 7.898810969947546e+16,
|
| 3621 |
"train_batch_size": 4,
|
| 3622 |
"trial_name": null,
|
| 3623 |
"trial_params": null
|