Training in progress, step 3460, 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 sha256:7812b22f640f6779046a94850c20d8130cbef98868c1bd6d52482119d9e468a1
|
| 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 sha256:89c24ca5067abc3c4007746375351b1234f6bbad64851d6d65632b67cf10a941
|
| 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 sha256:74630eab6c20ceb20051c7c99754c46602da37a1b83de2c58239d9a9bdd22c26
|
| 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 sha256:696dc354a288c906f25e166278fb460fd9fcaa4eafb9cbcfe466a3bb12d630e8
|
| 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,
|
|
@@ -3468,6 +3468,16 @@
|
|
| 3468 |
"mean_token_accuracy": 0.7602859303355217,
|
| 3469 |
"num_tokens": 16078997.0,
|
| 3470 |
"step": 3450
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3471 |
}
|
| 3472 |
],
|
| 3473 |
"logging_steps": 10,
|
|
@@ -3487,7 +3497,7 @@
|
|
| 3487 |
"attributes": {}
|
| 3488 |
}
|
| 3489 |
},
|
| 3490 |
-
"total_flos": 7.
|
| 3491 |
"train_batch_size": 4,
|
| 3492 |
"trial_name": null,
|
| 3493 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.7381333333333333,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 3460,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 3468 |
"mean_token_accuracy": 0.7602859303355217,
|
| 3469 |
"num_tokens": 16078997.0,
|
| 3470 |
"step": 3450
|
| 3471 |
+
},
|
| 3472 |
+
{
|
| 3473 |
+
"entropy": 0.9305942483246327,
|
| 3474 |
+
"epoch": 0.7381333333333333,
|
| 3475 |
+
"grad_norm": 0.25894254446029663,
|
| 3476 |
+
"learning_rate": 7.2970507761818e-05,
|
| 3477 |
+
"loss": 0.9928631782531738,
|
| 3478 |
+
"mean_token_accuracy": 0.7672612771391869,
|
| 3479 |
+
"num_tokens": 16128753.0,
|
| 3480 |
+
"step": 3460
|
| 3481 |
}
|
| 3482 |
],
|
| 3483 |
"logging_steps": 10,
|
|
|
|
| 3497 |
"attributes": {}
|
| 3498 |
}
|
| 3499 |
},
|
| 3500 |
+
"total_flos": 7.63869779972014e+16,
|
| 3501 |
"train_batch_size": 4,
|
| 3502 |
"trial_name": null,
|
| 3503 |
"trial_params": null
|