Training in progress, step 6930, 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:e0f8a9f127fcec5f7e61b0f8033419ef26551b5e2ac33e9d38e67eed77a2dcd3
|
| 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:af5a029d6b7bb5819df4c09ceffaf8fd45759a1e5323ece73524c6c786df53cc
|
| 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:a3737f3b1ab69d88aff15f600cf5b8ab12cc4c40b17e374c9a495814e99eaf7c
|
| 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": 53.
|
| 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,
|
|
@@ -12464,6 +12464,24 @@
|
|
| 12464 |
"mean_token_accuracy": 0.6613812148571014,
|
| 12465 |
"num_tokens": 25236653.0,
|
| 12466 |
"step": 6920
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 12467 |
}
|
| 12468 |
],
|
| 12469 |
"logging_steps": 5,
|
|
@@ -12483,7 +12501,7 @@
|
|
| 12483 |
"attributes": {}
|
| 12484 |
}
|
| 12485 |
},
|
| 12486 |
-
"total_flos": 1.
|
| 12487 |
"train_batch_size": 4,
|
| 12488 |
"trial_name": null,
|
| 12489 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 53.30769230769231,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 6930,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 12464 |
"mean_token_accuracy": 0.6613812148571014,
|
| 12465 |
"num_tokens": 25236653.0,
|
| 12466 |
"step": 6920
|
| 12467 |
+
},
|
| 12468 |
+
{
|
| 12469 |
+
"epoch": 53.26923076923077,
|
| 12470 |
+
"grad_norm": 0.0,
|
| 12471 |
+
"learning_rate": 1.538e-05,
|
| 12472 |
+
"loss": 1.6697,
|
| 12473 |
+
"mean_token_accuracy": 0.6670442432165146,
|
| 12474 |
+
"num_tokens": 25255752.0,
|
| 12475 |
+
"step": 6925
|
| 12476 |
+
},
|
| 12477 |
+
{
|
| 12478 |
+
"epoch": 53.30769230769231,
|
| 12479 |
+
"grad_norm": 0.0,
|
| 12480 |
+
"learning_rate": 1.5355e-05,
|
| 12481 |
+
"loss": 1.7525,
|
| 12482 |
+
"mean_token_accuracy": 0.6471881836652755,
|
| 12483 |
+
"num_tokens": 25273909.0,
|
| 12484 |
+
"step": 6930
|
| 12485 |
}
|
| 12486 |
],
|
| 12487 |
"logging_steps": 5,
|
|
|
|
| 12501 |
"attributes": {}
|
| 12502 |
}
|
| 12503 |
},
|
| 12504 |
+
"total_flos": 1.2814898174926848e+18,
|
| 12505 |
"train_batch_size": 4,
|
| 12506 |
"trial_name": null,
|
| 12507 |
"trial_params": null
|