Training in progress, step 610, 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 sha256:5703c83f563616e4837d6e014233b2b89ccf5bdecca342b1e5a40af0c4dc6d10
|
| 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 sha256:46f22bd132e82e973dabf6c22cbc1b83c6e99c67473c785e285e7c1365cd1e0d
|
| 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 sha256:42dde3fa0ef6c4f5c2d4d2496a08574785a97880a4cf3a8f8e0261681a4492c2
|
| 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,
|
|
@@ -1088,6 +1088,24 @@
|
|
| 1088 |
"mean_token_accuracy": 0.6509936511516571,
|
| 1089 |
"num_tokens": 2187439.0,
|
| 1090 |
"step": 600
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1091 |
}
|
| 1092 |
],
|
| 1093 |
"logging_steps": 5,
|
|
@@ -1107,7 +1125,7 @@
|
|
| 1107 |
"attributes": {}
|
| 1108 |
}
|
| 1109 |
},
|
| 1110 |
-
"total_flos": 1.
|
| 1111 |
"train_batch_size": 4,
|
| 1112 |
"trial_name": null,
|
| 1113 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 4.6923076923076925,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 610,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 1088 |
"mean_token_accuracy": 0.6509936511516571,
|
| 1089 |
"num_tokens": 2187439.0,
|
| 1090 |
"step": 600
|
| 1091 |
+
},
|
| 1092 |
+
{
|
| 1093 |
+
"epoch": 4.653846153846154,
|
| 1094 |
+
"grad_norm": 0.0,
|
| 1095 |
+
"learning_rate": 4.698e-05,
|
| 1096 |
+
"loss": 1.712,
|
| 1097 |
+
"mean_token_accuracy": 0.6584094524383545,
|
| 1098 |
+
"num_tokens": 2206096.0,
|
| 1099 |
+
"step": 605
|
| 1100 |
+
},
|
| 1101 |
+
{
|
| 1102 |
+
"epoch": 4.6923076923076925,
|
| 1103 |
+
"grad_norm": 0.0,
|
| 1104 |
+
"learning_rate": 4.695500000000001e-05,
|
| 1105 |
+
"loss": 1.6726,
|
| 1106 |
+
"mean_token_accuracy": 0.6688409745693207,
|
| 1107 |
+
"num_tokens": 2225085.0,
|
| 1108 |
+
"step": 610
|
| 1109 |
}
|
| 1110 |
],
|
| 1111 |
"logging_steps": 5,
|
|
|
|
| 1125 |
"attributes": {}
|
| 1126 |
}
|
| 1127 |
},
|
| 1128 |
+
"total_flos": 1.127697130340352e+17,
|
| 1129 |
"train_batch_size": 4,
|
| 1130 |
"trial_name": null,
|
| 1131 |
"trial_params": null
|