Training in progress, step 7460, 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:ad0e60b84d7518aa7119f4c1e7486a0851dd467edffc7817b74cf4d580ee3ad8
|
| 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:b49f624ea8fc04d205d851b1464c63039a46018514b558baeb3ae8791f1d103b
|
| 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 sha256:17b83b53d751d00fd4f56da76008ea043939e2e8ac459219380dc210ee592188
|
| 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,
|
|
@@ -13418,6 +13418,24 @@
|
|
| 13418 |
"mean_token_accuracy": 0.645848673582077,
|
| 13419 |
"num_tokens": 27171115.0,
|
| 13420 |
"step": 7450
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 13421 |
}
|
| 13422 |
],
|
| 13423 |
"logging_steps": 5,
|
|
@@ -13437,7 +13455,7 @@
|
|
| 13437 |
"attributes": {}
|
| 13438 |
}
|
| 13439 |
},
|
| 13440 |
-
"total_flos": 1.
|
| 13441 |
"train_batch_size": 4,
|
| 13442 |
"trial_name": null,
|
| 13443 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 57.38461538461539,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 7460,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 13418 |
"mean_token_accuracy": 0.645848673582077,
|
| 13419 |
"num_tokens": 27171115.0,
|
| 13420 |
"step": 7450
|
| 13421 |
+
},
|
| 13422 |
+
{
|
| 13423 |
+
"epoch": 57.34615384615385,
|
| 13424 |
+
"grad_norm": 0.0,
|
| 13425 |
+
"learning_rate": 1.273e-05,
|
| 13426 |
+
"loss": 1.7698,
|
| 13427 |
+
"mean_token_accuracy": 0.6474648177623749,
|
| 13428 |
+
"num_tokens": 27188950.0,
|
| 13429 |
+
"step": 7455
|
| 13430 |
+
},
|
| 13431 |
+
{
|
| 13432 |
+
"epoch": 57.38461538461539,
|
| 13433 |
+
"grad_norm": 0.0,
|
| 13434 |
+
"learning_rate": 1.2705e-05,
|
| 13435 |
+
"loss": 1.7511,
|
| 13436 |
+
"mean_token_accuracy": 0.6489328056573868,
|
| 13437 |
+
"num_tokens": 27207207.0,
|
| 13438 |
+
"step": 7460
|
| 13439 |
}
|
| 13440 |
],
|
| 13441 |
"logging_steps": 5,
|
|
|
|
| 13455 |
"attributes": {}
|
| 13456 |
}
|
| 13457 |
},
|
| 13458 |
+
"total_flos": 1.3794773507909222e+18,
|
| 13459 |
"train_batch_size": 4,
|
| 13460 |
"trial_name": null,
|
| 13461 |
"trial_params": null
|