Training in progress, step 3300, checkpoint
Browse files
last-checkpoint/adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 20814808
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fc19303a0059a9bd3cef9383344c1970c866cef910a80be81fce23bbaec6c4a7
|
| 3 |
size 20814808
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 21506325
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7697fc27b0dc2afe5eeb1609893e8b1a0638f7c1a60aa51849627255d02d8a05
|
| 3 |
size 21506325
|
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:e1868f5b3985b17bc9517aa4adad17b968c0ca25cc39f9c06ba06f94a13b6df3
|
| 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":
|
| 6 |
"eval_steps": 300,
|
| 7 |
-
"global_step":
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
@@ -1318,6 +1318,16 @@
|
|
| 1318 |
"mean_token_accuracy": 0.9430344653129578,
|
| 1319 |
"num_tokens": 5355357.0,
|
| 1320 |
"step": 3275
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1321 |
}
|
| 1322 |
],
|
| 1323 |
"logging_steps": 25,
|
|
@@ -1332,12 +1342,12 @@
|
|
| 1332 |
"should_evaluate": false,
|
| 1333 |
"should_log": false,
|
| 1334 |
"should_save": true,
|
| 1335 |
-
"should_training_stop":
|
| 1336 |
},
|
| 1337 |
"attributes": {}
|
| 1338 |
}
|
| 1339 |
},
|
| 1340 |
-
"total_flos": 7.
|
| 1341 |
"train_batch_size": 2,
|
| 1342 |
"trial_name": null,
|
| 1343 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 1.0,
|
| 6 |
"eval_steps": 300,
|
| 7 |
+
"global_step": 3300,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 1318 |
"mean_token_accuracy": 0.9430344653129578,
|
| 1319 |
"num_tokens": 5355357.0,
|
| 1320 |
"step": 3275
|
| 1321 |
+
},
|
| 1322 |
+
{
|
| 1323 |
+
"entropy": 0.15088965865422269,
|
| 1324 |
+
"epoch": 1.0,
|
| 1325 |
+
"grad_norm": 0.4375,
|
| 1326 |
+
"learning_rate": 0.0002,
|
| 1327 |
+
"loss": 0.1564,
|
| 1328 |
+
"mean_token_accuracy": 0.9488337550844465,
|
| 1329 |
+
"num_tokens": 5394110.0,
|
| 1330 |
+
"step": 3300
|
| 1331 |
}
|
| 1332 |
],
|
| 1333 |
"logging_steps": 25,
|
|
|
|
| 1342 |
"should_evaluate": false,
|
| 1343 |
"should_log": false,
|
| 1344 |
"should_save": true,
|
| 1345 |
+
"should_training_stop": true
|
| 1346 |
},
|
| 1347 |
"attributes": {}
|
| 1348 |
}
|
| 1349 |
},
|
| 1350 |
+
"total_flos": 7.203637122878669e+16,
|
| 1351 |
"train_batch_size": 2,
|
| 1352 |
"trial_name": null,
|
| 1353 |
"trial_params": null
|