Training in progress, step 2460, checkpoint
Browse files
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1657
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:de293b0484badfd52be2bd6c62c7691800544b0574b0412d0328b0c3071febb8
|
| 3 |
size 1657
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14709
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:43d714d3a028cf94045b6c479063c13fcccaf33a8b96f0ebad09bcde090f33df
|
| 3 |
size 14709
|
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:eeff3d76439ac9ab9b61c339bba29b707bd62c0218cebf7f5930610f6f188776
|
| 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": 18.
|
| 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,
|
|
@@ -4418,6 +4418,24 @@
|
|
| 4418 |
"mean_token_accuracy": 0.6655582249164581,
|
| 4419 |
"num_tokens": 8933916.0,
|
| 4420 |
"step": 2450
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 4421 |
}
|
| 4422 |
],
|
| 4423 |
"logging_steps": 5,
|
|
@@ -4437,7 +4455,7 @@
|
|
| 4437 |
"attributes": {}
|
| 4438 |
}
|
| 4439 |
},
|
| 4440 |
-
"total_flos": 4.
|
| 4441 |
"train_batch_size": 4,
|
| 4442 |
"trial_name": null,
|
| 4443 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 18.923076923076923,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 2460,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 4418 |
"mean_token_accuracy": 0.6655582249164581,
|
| 4419 |
"num_tokens": 8933916.0,
|
| 4420 |
"step": 2450
|
| 4421 |
+
},
|
| 4422 |
+
{
|
| 4423 |
+
"epoch": 18.884615384615383,
|
| 4424 |
+
"grad_norm": 0.0,
|
| 4425 |
+
"learning_rate": 3.7730000000000006e-05,
|
| 4426 |
+
"loss": 1.7298,
|
| 4427 |
+
"mean_token_accuracy": 0.6513529330492019,
|
| 4428 |
+
"num_tokens": 8952047.0,
|
| 4429 |
+
"step": 2455
|
| 4430 |
+
},
|
| 4431 |
+
{
|
| 4432 |
+
"epoch": 18.923076923076923,
|
| 4433 |
+
"grad_norm": 0.0,
|
| 4434 |
+
"learning_rate": 3.7705e-05,
|
| 4435 |
+
"loss": 1.6774,
|
| 4436 |
+
"mean_token_accuracy": 0.6640833884477615,
|
| 4437 |
+
"num_tokens": 8970281.0,
|
| 4438 |
+
"step": 2460
|
| 4439 |
}
|
| 4440 |
],
|
| 4441 |
"logging_steps": 5,
|
|
|
|
| 4455 |
"attributes": {}
|
| 4456 |
}
|
| 4457 |
},
|
| 4458 |
+
"total_flos": 4.545696116662272e+17,
|
| 4459 |
"train_batch_size": 4,
|
| 4460 |
"trial_name": null,
|
| 4461 |
"trial_params": null
|