Training in progress, step 6110, 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 sha256:8b4da5983936c63f138627aa8c79cd58504663469d21274d883e561ff78b2fe1
|
| 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 sha256:0d23556b7ce08d8854cdb51548278890938a005b5ab8e265531a2de83d75c783
|
| 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:d47bfbad5b43bdab93179a7ac4a879933e727f68132825dd949e8bd3d5752b29
|
| 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":
|
| 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,
|
|
@@ -10988,6 +10988,24 @@
|
|
| 10988 |
"mean_token_accuracy": 0.6454124927520752,
|
| 10989 |
"num_tokens": 22245784.0,
|
| 10990 |
"step": 6100
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 10991 |
}
|
| 10992 |
],
|
| 10993 |
"logging_steps": 5,
|
|
@@ -11007,7 +11025,7 @@
|
|
| 11007 |
"attributes": {}
|
| 11008 |
}
|
| 11009 |
},
|
| 11010 |
-
"total_flos": 1.
|
| 11011 |
"train_batch_size": 4,
|
| 11012 |
"trial_name": null,
|
| 11013 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 47.0,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 6110,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 10988 |
"mean_token_accuracy": 0.6454124927520752,
|
| 10989 |
"num_tokens": 22245784.0,
|
| 10990 |
"step": 6100
|
| 10991 |
+
},
|
| 10992 |
+
{
|
| 10993 |
+
"epoch": 46.96153846153846,
|
| 10994 |
+
"grad_norm": 0.0,
|
| 10995 |
+
"learning_rate": 1.948e-05,
|
| 10996 |
+
"loss": 1.6937,
|
| 10997 |
+
"mean_token_accuracy": 0.6616695493459701,
|
| 10998 |
+
"num_tokens": 22263991.0,
|
| 10999 |
+
"step": 6105
|
| 11000 |
+
},
|
| 11001 |
+
{
|
| 11002 |
+
"epoch": 47.0,
|
| 11003 |
+
"grad_norm": 0.0,
|
| 11004 |
+
"learning_rate": 1.9455000000000003e-05,
|
| 11005 |
+
"loss": 1.7195,
|
| 11006 |
+
"mean_token_accuracy": 0.6506162971258164,
|
| 11007 |
+
"num_tokens": 22282935.0,
|
| 11008 |
+
"step": 6110
|
| 11009 |
}
|
| 11010 |
],
|
| 11011 |
"logging_steps": 5,
|
|
|
|
| 11025 |
"attributes": {}
|
| 11026 |
}
|
| 11027 |
},
|
| 11028 |
+
"total_flos": 1.1293441464242995e+18,
|
| 11029 |
"train_batch_size": 4,
|
| 11030 |
"trial_name": null,
|
| 11031 |
"trial_params": null
|