Training in progress, step 2220, 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 sha256:805a1d439d8b1661d1dcd561c2d656a649f183684906cf40351cf07333418a31
|
| 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:bb30cac5a5906d2144f5e97a406c6bf0cd29435523e7e62fe5a4b5c994d313b7
|
| 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:c88d57e3a36904fb2632c79c3a4a73018f963d1d61ec3ae8c693a6a09c23f6bc
|
| 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": 17.
|
| 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,
|
|
@@ -3986,6 +3986,24 @@
|
|
| 3986 |
"mean_token_accuracy": 0.6438369482755661,
|
| 3987 |
"num_tokens": 8059785.0,
|
| 3988 |
"step": 2210
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3989 |
}
|
| 3990 |
],
|
| 3991 |
"logging_steps": 5,
|
|
@@ -4005,7 +4023,7 @@
|
|
| 4005 |
"attributes": {}
|
| 4006 |
}
|
| 4007 |
},
|
| 4008 |
-
"total_flos": 4.
|
| 4009 |
"train_batch_size": 4,
|
| 4010 |
"trial_name": null,
|
| 4011 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 17.076923076923077,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 2220,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 3986 |
"mean_token_accuracy": 0.6438369482755661,
|
| 3987 |
"num_tokens": 8059785.0,
|
| 3988 |
"step": 2210
|
| 3989 |
+
},
|
| 3990 |
+
{
|
| 3991 |
+
"epoch": 17.03846153846154,
|
| 3992 |
+
"grad_norm": 0.0,
|
| 3993 |
+
"learning_rate": 3.893e-05,
|
| 3994 |
+
"loss": 1.6973,
|
| 3995 |
+
"mean_token_accuracy": 0.6598532944917679,
|
| 3996 |
+
"num_tokens": 8078152.0,
|
| 3997 |
+
"step": 2215
|
| 3998 |
+
},
|
| 3999 |
+
{
|
| 4000 |
+
"epoch": 17.076923076923077,
|
| 4001 |
+
"grad_norm": 0.0,
|
| 4002 |
+
"learning_rate": 3.8905e-05,
|
| 4003 |
+
"loss": 1.7373,
|
| 4004 |
+
"mean_token_accuracy": 0.6510017067193985,
|
| 4005 |
+
"num_tokens": 8096780.0,
|
| 4006 |
+
"step": 2220
|
| 4007 |
}
|
| 4008 |
],
|
| 4009 |
"logging_steps": 5,
|
|
|
|
| 4023 |
"attributes": {}
|
| 4024 |
}
|
| 4025 |
},
|
| 4026 |
+
"total_flos": 4.1036883171508224e+17,
|
| 4027 |
"train_batch_size": 4,
|
| 4028 |
"trial_name": null,
|
| 4029 |
"trial_params": null
|