Training in progress, step 3440, 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 sha256:51352825e456fc9189b1e5dfddfa4babad7f75511c8ec489e78ff1a3de338f87
|
| 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:e06d3cd2fb04d72abcc0008b4d588c8e8083784298237cd20852cdb95e3f0523
|
| 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:ddc21210cdbfad33c045629b1dcb92169570a41a295e1a328d0d865b35ea1cb5
|
| 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 sha256:99e58e88c4c4cadecd08c67b9da11d26c1eec21844733026b7df7963f70c4527
|
| 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,
|
|
@@ -3448,6 +3448,16 @@
|
|
| 3448 |
"mean_token_accuracy": 0.7584069922566414,
|
| 3449 |
"num_tokens": 15984086.0,
|
| 3450 |
"step": 3430
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3451 |
}
|
| 3452 |
],
|
| 3453 |
"logging_steps": 10,
|
|
@@ -3467,7 +3477,7 @@
|
|
| 3467 |
"attributes": {}
|
| 3468 |
}
|
| 3469 |
},
|
| 3470 |
-
"total_flos": 7.
|
| 3471 |
"train_batch_size": 4,
|
| 3472 |
"trial_name": null,
|
| 3473 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.7338666666666667,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 3440,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 3448 |
"mean_token_accuracy": 0.7584069922566414,
|
| 3449 |
"num_tokens": 15984086.0,
|
| 3450 |
"step": 3430
|
| 3451 |
+
},
|
| 3452 |
+
{
|
| 3453 |
+
"entropy": 0.9371322847902774,
|
| 3454 |
+
"epoch": 0.7338666666666667,
|
| 3455 |
+
"grad_norm": 0.21763980388641357,
|
| 3456 |
+
"learning_rate": 7.32774073524142e-05,
|
| 3457 |
+
"loss": 1.0160024642944336,
|
| 3458 |
+
"mean_token_accuracy": 0.7715103484690189,
|
| 3459 |
+
"num_tokens": 16029965.0,
|
| 3460 |
+
"step": 3440
|
| 3461 |
}
|
| 3462 |
],
|
| 3463 |
"logging_steps": 10,
|
|
|
|
| 3477 |
"attributes": {}
|
| 3478 |
}
|
| 3479 |
},
|
| 3480 |
+
"total_flos": 7.592043355605197e+16,
|
| 3481 |
"train_batch_size": 4,
|
| 3482 |
"trial_name": null,
|
| 3483 |
"trial_params": null
|