Training in progress, step 6100, 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 sha256:7d6d1606447d7d635c46c3b26788bda578e35cbb13c84b96e537eb6ad47e8221
|
| 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 sha256:562cae1da759eba0582d1641b021925502f148f97242b3e56285ca02b5e6fed2
|
| 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:f08cd97ea0814a25f8d8c98433af7f8ff74c408b1563b5295c376bc7cbad404c
|
| 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": 46.
|
| 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,
|
|
@@ -10970,6 +10970,24 @@
|
|
| 10970 |
"mean_token_accuracy": 0.6619850039482117,
|
| 10971 |
"num_tokens": 22210517.0,
|
| 10972 |
"step": 6090
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 10973 |
}
|
| 10974 |
],
|
| 10975 |
"logging_steps": 5,
|
|
@@ -10989,7 +11007,7 @@
|
|
| 10989 |
"attributes": {}
|
| 10990 |
}
|
| 10991 |
},
|
| 10992 |
-
"total_flos": 1.
|
| 10993 |
"train_batch_size": 4,
|
| 10994 |
"trial_name": null,
|
| 10995 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 46.92307692307692,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 6100,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 10970 |
"mean_token_accuracy": 0.6619850039482117,
|
| 10971 |
"num_tokens": 22210517.0,
|
| 10972 |
"step": 6090
|
| 10973 |
+
},
|
| 10974 |
+
{
|
| 10975 |
+
"epoch": 46.88461538461539,
|
| 10976 |
+
"grad_norm": 0.0,
|
| 10977 |
+
"learning_rate": 1.953e-05,
|
| 10978 |
+
"loss": 1.729,
|
| 10979 |
+
"mean_token_accuracy": 0.6496035814285278,
|
| 10980 |
+
"num_tokens": 22228596.0,
|
| 10981 |
+
"step": 6095
|
| 10982 |
+
},
|
| 10983 |
+
{
|
| 10984 |
+
"epoch": 46.92307692307692,
|
| 10985 |
+
"grad_norm": 0.0,
|
| 10986 |
+
"learning_rate": 1.9505e-05,
|
| 10987 |
+
"loss": 1.7949,
|
| 10988 |
+
"mean_token_accuracy": 0.6454124927520752,
|
| 10989 |
+
"num_tokens": 22245784.0,
|
| 10990 |
+
"step": 6100
|
| 10991 |
}
|
| 10992 |
],
|
| 10993 |
"logging_steps": 5,
|
|
|
|
| 11007 |
"attributes": {}
|
| 11008 |
}
|
| 11009 |
},
|
| 11010 |
+
"total_flos": 1.1273792544895795e+18,
|
| 11011 |
"train_batch_size": 4,
|
| 11012 |
"trial_name": null,
|
| 11013 |
"trial_params": null
|