Training in progress, step 3610, 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 sha256:5946e092817c33b1c880596ed9707c940052bb080175730284e9ae1f1522c828
|
| 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 sha256:12630e53a657ea86e2e8aa72c9a98409e0c66da704c7e3463849f04dc66bb1ca
|
| 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 sha256:2e1bb00994a4c4e87d5404278a1c2142958faad299de0c9dc68af0079fd3170e
|
| 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:b10098c4ee79ca867481d2aa5aab5913b79f18cc7282e5a3d2699aeeabee88fe
|
| 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,
|
|
@@ -3618,6 +3618,16 @@
|
|
| 3618 |
"mean_token_accuracy": 0.7743734329938888,
|
| 3619 |
"num_tokens": 16759830.0,
|
| 3620 |
"step": 3600
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3621 |
}
|
| 3622 |
],
|
| 3623 |
"logging_steps": 10,
|
|
@@ -3637,7 +3647,7 @@
|
|
| 3637 |
"attributes": {}
|
| 3638 |
}
|
| 3639 |
},
|
| 3640 |
-
"total_flos": 7.
|
| 3641 |
"train_batch_size": 4,
|
| 3642 |
"trial_name": null,
|
| 3643 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.7701333333333333,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 3610,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 3618 |
"mean_token_accuracy": 0.7743734329938888,
|
| 3619 |
"num_tokens": 16759830.0,
|
| 3620 |
"step": 3600
|
| 3621 |
+
},
|
| 3622 |
+
{
|
| 3623 |
+
"entropy": 0.8517782382667065,
|
| 3624 |
+
"epoch": 0.7701333333333333,
|
| 3625 |
+
"grad_norm": 0.2146274745464325,
|
| 3626 |
+
"learning_rate": 7.063469463595884e-05,
|
| 3627 |
+
"loss": 0.9309274673461914,
|
| 3628 |
+
"mean_token_accuracy": 0.7834656447172165,
|
| 3629 |
+
"num_tokens": 16802813.0,
|
| 3630 |
+
"step": 3610
|
| 3631 |
}
|
| 3632 |
],
|
| 3633 |
"logging_steps": 10,
|
|
|
|
| 3647 |
"attributes": {}
|
| 3648 |
}
|
| 3649 |
},
|
| 3650 |
+
"total_flos": 7.962290572873114e+16,
|
| 3651 |
"train_batch_size": 4,
|
| 3652 |
"trial_name": null,
|
| 3653 |
"trial_params": null
|