Training in progress, step 7510, 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 sha256:5e1950ae9b973a7a657bba02639d0a59afcc2636f894ba370ce1b8bf35b69b85
|
| 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 sha256:3be79b636cb8dfc0d125b2f6bff1def2bd11f71b499c4cd4023c5f3b5bf8b753
|
| 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 sha256:8286ff3437ef8cdc99de68d36ee7a63b2edaff1a0fd61637a6b36300d8724500
|
| 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": 57.
|
| 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,
|
|
@@ -13508,6 +13508,24 @@
|
|
| 13508 |
"mean_token_accuracy": 0.6529757559299469,
|
| 13509 |
"num_tokens": 27354439.0,
|
| 13510 |
"step": 7500
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 13511 |
}
|
| 13512 |
],
|
| 13513 |
"logging_steps": 5,
|
|
@@ -13527,7 +13545,7 @@
|
|
| 13527 |
"attributes": {}
|
| 13528 |
}
|
| 13529 |
},
|
| 13530 |
-
"total_flos": 1.
|
| 13531 |
"train_batch_size": 4,
|
| 13532 |
"trial_name": null,
|
| 13533 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 57.76923076923077,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 7510,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 13508 |
"mean_token_accuracy": 0.6529757559299469,
|
| 13509 |
"num_tokens": 27354439.0,
|
| 13510 |
"step": 7500
|
| 13511 |
+
},
|
| 13512 |
+
{
|
| 13513 |
+
"epoch": 57.73076923076923,
|
| 13514 |
+
"grad_norm": 0.0,
|
| 13515 |
+
"learning_rate": 1.248e-05,
|
| 13516 |
+
"loss": 1.7176,
|
| 13517 |
+
"mean_token_accuracy": 0.6583882302045823,
|
| 13518 |
+
"num_tokens": 27372701.0,
|
| 13519 |
+
"step": 7505
|
| 13520 |
+
},
|
| 13521 |
+
{
|
| 13522 |
+
"epoch": 57.76923076923077,
|
| 13523 |
+
"grad_norm": 0.0,
|
| 13524 |
+
"learning_rate": 1.2455e-05,
|
| 13525 |
+
"loss": 1.7395,
|
| 13526 |
+
"mean_token_accuracy": 0.6499318182468414,
|
| 13527 |
+
"num_tokens": 27390861.0,
|
| 13528 |
+
"step": 7510
|
| 13529 |
}
|
| 13530 |
],
|
| 13531 |
"logging_steps": 5,
|
|
|
|
| 13545 |
"attributes": {}
|
| 13546 |
}
|
| 13547 |
},
|
| 13548 |
+
"total_flos": 1.3887933996382618e+18,
|
| 13549 |
"train_batch_size": 4,
|
| 13550 |
"trial_name": null,
|
| 13551 |
"trial_params": null
|