Training in progress, step 580, 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 sha256:10f2d6a0899decfc1fa1b262de18998f9076aef2ef6b2016f8d3758ea8d181bc
|
| 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:bc05d6270f19a3144dcb9f510039288190eccc72e9e205153a1bd4aeb37135a6
|
| 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:e9c82969fa647ae214d70bd66d28e8dabcc0a1570aa48db7c7173173d817fd77
|
| 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": 4.
|
| 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,
|
|
@@ -1034,6 +1034,24 @@
|
|
| 1034 |
"mean_token_accuracy": 0.6538840979337692,
|
| 1035 |
"num_tokens": 2079449.0,
|
| 1036 |
"step": 570
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1037 |
}
|
| 1038 |
],
|
| 1039 |
"logging_steps": 5,
|
|
@@ -1053,7 +1071,7 @@
|
|
| 1053 |
"attributes": {}
|
| 1054 |
}
|
| 1055 |
},
|
| 1056 |
-
"total_flos": 1.
|
| 1057 |
"train_batch_size": 4,
|
| 1058 |
"trial_name": null,
|
| 1059 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 4.461538461538462,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 580,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 1034 |
"mean_token_accuracy": 0.6538840979337692,
|
| 1035 |
"num_tokens": 2079449.0,
|
| 1036 |
"step": 570
|
| 1037 |
+
},
|
| 1038 |
+
{
|
| 1039 |
+
"epoch": 4.423076923076923,
|
| 1040 |
+
"grad_norm": 0.0,
|
| 1041 |
+
"learning_rate": 4.7130000000000004e-05,
|
| 1042 |
+
"loss": 1.719,
|
| 1043 |
+
"mean_token_accuracy": 0.6608097106218338,
|
| 1044 |
+
"num_tokens": 2097502.0,
|
| 1045 |
+
"step": 575
|
| 1046 |
+
},
|
| 1047 |
+
{
|
| 1048 |
+
"epoch": 4.461538461538462,
|
| 1049 |
+
"grad_norm": 0.0,
|
| 1050 |
+
"learning_rate": 4.7105000000000004e-05,
|
| 1051 |
+
"loss": 1.6963,
|
| 1052 |
+
"mean_token_accuracy": 0.6655160158872604,
|
| 1053 |
+
"num_tokens": 2115911.0,
|
| 1054 |
+
"step": 580
|
| 1055 |
}
|
| 1056 |
],
|
| 1057 |
"logging_steps": 5,
|
|
|
|
| 1071 |
"attributes": {}
|
| 1072 |
}
|
| 1073 |
},
|
| 1074 |
+
"total_flos": 1.0722482768904192e+17,
|
| 1075 |
"train_batch_size": 4,
|
| 1076 |
"trial_name": null,
|
| 1077 |
"trial_params": null
|