Training in progress, step 730, 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 sha256:08bd0405365eaac6e8512d868715a680762c595a30b942959bd2ed5963f90ee4
|
| 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 sha256:75103c17cf242030ad98913bf72c542ec9a45c71e8f4e3778802a1754d72e2bc
|
| 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 sha256:42cec43a9442f876045bde0f605f03a0cbe09086c16741bbf10fec4debb981a5
|
| 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,
|
|
@@ -1304,6 +1304,24 @@
|
|
| 1304 |
"mean_token_accuracy": 0.6509989589452744,
|
| 1305 |
"num_tokens": 2625915.0,
|
| 1306 |
"step": 720
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1307 |
}
|
| 1308 |
],
|
| 1309 |
"logging_steps": 5,
|
|
@@ -1323,7 +1341,7 @@
|
|
| 1323 |
"attributes": {}
|
| 1324 |
}
|
| 1325 |
},
|
| 1326 |
-
"total_flos": 1.
|
| 1327 |
"train_batch_size": 4,
|
| 1328 |
"trial_name": null,
|
| 1329 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 5.615384615384615,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 730,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 1304 |
"mean_token_accuracy": 0.6509989589452744,
|
| 1305 |
"num_tokens": 2625915.0,
|
| 1306 |
"step": 720
|
| 1307 |
+
},
|
| 1308 |
+
{
|
| 1309 |
+
"epoch": 5.576923076923077,
|
| 1310 |
+
"grad_norm": 0.0,
|
| 1311 |
+
"learning_rate": 4.638e-05,
|
| 1312 |
+
"loss": 1.6809,
|
| 1313 |
+
"mean_token_accuracy": 0.6608490258455276,
|
| 1314 |
+
"num_tokens": 2644604.0,
|
| 1315 |
+
"step": 725
|
| 1316 |
+
},
|
| 1317 |
+
{
|
| 1318 |
+
"epoch": 5.615384615384615,
|
| 1319 |
+
"grad_norm": 0.0,
|
| 1320 |
+
"learning_rate": 4.6355000000000006e-05,
|
| 1321 |
+
"loss": 1.7797,
|
| 1322 |
+
"mean_token_accuracy": 0.6429726481437683,
|
| 1323 |
+
"num_tokens": 2662473.0,
|
| 1324 |
+
"step": 730
|
| 1325 |
}
|
| 1326 |
],
|
| 1327 |
"logging_steps": 5,
|
|
|
|
| 1341 |
"attributes": {}
|
| 1342 |
}
|
| 1343 |
},
|
| 1344 |
+
"total_flos": 1.349678315741184e+17,
|
| 1345 |
"train_batch_size": 4,
|
| 1346 |
"trial_name": null,
|
| 1347 |
"trial_params": null
|