Training in progress, step 680, 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:e662e18cb399cf9961c676730fc8219261b448f779999220240afec4aa1e666b
|
| 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:e36912a1c7213b092cd2ce8abbe5c563bb7c29bad4dc75c05626318c71ffabc4
|
| 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 sha256:93dcce2dee28a333dba1ec7d9cf693b8862ecdd18e01e4945f131e266d2452fa
|
| 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": 5.
|
| 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,
|
|
@@ -1214,6 +1214,24 @@
|
|
| 1214 |
"mean_token_accuracy": 0.6496942937374115,
|
| 1215 |
"num_tokens": 2443792.0,
|
| 1216 |
"step": 670
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1217 |
}
|
| 1218 |
],
|
| 1219 |
"logging_steps": 5,
|
|
@@ -1233,7 +1251,7 @@
|
|
| 1233 |
"attributes": {}
|
| 1234 |
}
|
| 1235 |
},
|
| 1236 |
-
"total_flos": 1.
|
| 1237 |
"train_batch_size": 4,
|
| 1238 |
"trial_name": null,
|
| 1239 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 5.230769230769231,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 680,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 1214 |
"mean_token_accuracy": 0.6496942937374115,
|
| 1215 |
"num_tokens": 2443792.0,
|
| 1216 |
"step": 670
|
| 1217 |
+
},
|
| 1218 |
+
{
|
| 1219 |
+
"epoch": 5.1923076923076925,
|
| 1220 |
+
"grad_norm": 0.0,
|
| 1221 |
+
"learning_rate": 4.663e-05,
|
| 1222 |
+
"loss": 1.7879,
|
| 1223 |
+
"mean_token_accuracy": 0.6398061364889145,
|
| 1224 |
+
"num_tokens": 2461179.0,
|
| 1225 |
+
"step": 675
|
| 1226 |
+
},
|
| 1227 |
+
{
|
| 1228 |
+
"epoch": 5.230769230769231,
|
| 1229 |
+
"grad_norm": 0.0,
|
| 1230 |
+
"learning_rate": 4.6605000000000005e-05,
|
| 1231 |
+
"loss": 1.7348,
|
| 1232 |
+
"mean_token_accuracy": 0.642570036649704,
|
| 1233 |
+
"num_tokens": 2480028.0,
|
| 1234 |
+
"step": 680
|
| 1235 |
}
|
| 1236 |
],
|
| 1237 |
"logging_steps": 5,
|
|
|
|
| 1251 |
"attributes": {}
|
| 1252 |
}
|
| 1253 |
},
|
| 1254 |
+
"total_flos": 1.2574879678513152e+17,
|
| 1255 |
"train_batch_size": 4,
|
| 1256 |
"trial_name": null,
|
| 1257 |
"trial_params": null
|