Training in progress, step 620, 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:db8767a0dd1fd718ad2065af373407eb04bc38e4aa298fb7a16061762291a105
|
| 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:ad7197604db69051054f333cc181d7e36299a73357cb3e36134fbfa901eb5e9f
|
| 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 sha256:82a1a43c6d9cc7b1b23b62214228e9165ebfe48b3bc0c0198ba241225d3465aa
|
| 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,
|
|
@@ -1106,6 +1106,24 @@
|
|
| 1106 |
"mean_token_accuracy": 0.6688409745693207,
|
| 1107 |
"num_tokens": 2225085.0,
|
| 1108 |
"step": 610
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1109 |
}
|
| 1110 |
],
|
| 1111 |
"logging_steps": 5,
|
|
@@ -1125,7 +1143,7 @@
|
|
| 1125 |
"attributes": {}
|
| 1126 |
}
|
| 1127 |
},
|
| 1128 |
-
"total_flos": 1.
|
| 1129 |
"train_batch_size": 4,
|
| 1130 |
"trial_name": null,
|
| 1131 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 4.769230769230769,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 620,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 1106 |
"mean_token_accuracy": 0.6688409745693207,
|
| 1107 |
"num_tokens": 2225085.0,
|
| 1108 |
"step": 610
|
| 1109 |
+
},
|
| 1110 |
+
{
|
| 1111 |
+
"epoch": 4.730769230769231,
|
| 1112 |
+
"grad_norm": 0.0,
|
| 1113 |
+
"learning_rate": 4.693e-05,
|
| 1114 |
+
"loss": 1.6953,
|
| 1115 |
+
"mean_token_accuracy": 0.6592785984277725,
|
| 1116 |
+
"num_tokens": 2243907.0,
|
| 1117 |
+
"step": 615
|
| 1118 |
+
},
|
| 1119 |
+
{
|
| 1120 |
+
"epoch": 4.769230769230769,
|
| 1121 |
+
"grad_norm": 0.0,
|
| 1122 |
+
"learning_rate": 4.6905000000000006e-05,
|
| 1123 |
+
"loss": 1.7659,
|
| 1124 |
+
"mean_token_accuracy": 0.6406325221061706,
|
| 1125 |
+
"num_tokens": 2261272.0,
|
| 1126 |
+
"step": 620
|
| 1127 |
}
|
| 1128 |
],
|
| 1129 |
"logging_steps": 5,
|
|
|
|
| 1143 |
"attributes": {}
|
| 1144 |
}
|
| 1145 |
},
|
| 1146 |
+
"total_flos": 1.1465299248758784e+17,
|
| 1147 |
"train_batch_size": 4,
|
| 1148 |
"trial_name": null,
|
| 1149 |
"trial_params": null
|