Training in progress, step 640, 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:a031186fad857ed27442646fa945802d103b5070b29970e2c85effc80838b56b
|
| 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:f638fc438ba9953bf254ad3a6b2aac7576a6b22d5b3d7bbc1db0fa94d0592a82
|
| 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 sha256:37faec2b709803256f69cb521c8aa3bed0c30eeec15307675432682753e8b6da
|
| 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,
|
|
@@ -1142,6 +1142,24 @@
|
|
| 1142 |
"mean_token_accuracy": 0.6247967123985291,
|
| 1143 |
"num_tokens": 2297161.0,
|
| 1144 |
"step": 630
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1145 |
}
|
| 1146 |
],
|
| 1147 |
"logging_steps": 5,
|
|
@@ -1161,7 +1179,7 @@
|
|
| 1161 |
"attributes": {}
|
| 1162 |
}
|
| 1163 |
},
|
| 1164 |
-
"total_flos": 1.
|
| 1165 |
"train_batch_size": 4,
|
| 1166 |
"trial_name": null,
|
| 1167 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 4.923076923076923,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 640,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 1142 |
"mean_token_accuracy": 0.6247967123985291,
|
| 1143 |
"num_tokens": 2297161.0,
|
| 1144 |
"step": 630
|
| 1145 |
+
},
|
| 1146 |
+
{
|
| 1147 |
+
"epoch": 4.884615384615385,
|
| 1148 |
+
"grad_norm": 0.0,
|
| 1149 |
+
"learning_rate": 4.6830000000000004e-05,
|
| 1150 |
+
"loss": 1.8183,
|
| 1151 |
+
"mean_token_accuracy": 0.6385220259428024,
|
| 1152 |
+
"num_tokens": 2314811.0,
|
| 1153 |
+
"step": 635
|
| 1154 |
+
},
|
| 1155 |
+
{
|
| 1156 |
+
"epoch": 4.923076923076923,
|
| 1157 |
+
"grad_norm": 0.0,
|
| 1158 |
+
"learning_rate": 4.6805e-05,
|
| 1159 |
+
"loss": 1.6373,
|
| 1160 |
+
"mean_token_accuracy": 0.6711235165596008,
|
| 1161 |
+
"num_tokens": 2333816.0,
|
| 1162 |
+
"step": 640
|
| 1163 |
}
|
| 1164 |
],
|
| 1165 |
"logging_steps": 5,
|
|
|
|
| 1179 |
"attributes": {}
|
| 1180 |
}
|
| 1181 |
},
|
| 1182 |
+
"total_flos": 1.1829379831087104e+17,
|
| 1183 |
"train_batch_size": 4,
|
| 1184 |
"trial_name": null,
|
| 1185 |
"trial_params": null
|