Training in progress, step 740, 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 sha256:7b63cd1893e39b38942535f19ea1905f8747becf1c3f7d747c15bde2caaad169
|
| 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 sha256:444c13016d16316981f6f45c3fd023943a5e25d2595f41c910e7f29fbd95a22a
|
| 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 sha256:69e6fdd157d9620a771c9f4e52c0698ca2672ad316de62b1a1de9d11fe70a6a9
|
| 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,
|
|
@@ -1322,6 +1322,24 @@
|
|
| 1322 |
"mean_token_accuracy": 0.6429726481437683,
|
| 1323 |
"num_tokens": 2662473.0,
|
| 1324 |
"step": 730
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1325 |
}
|
| 1326 |
],
|
| 1327 |
"logging_steps": 5,
|
|
@@ -1341,7 +1359,7 @@
|
|
| 1341 |
"attributes": {}
|
| 1342 |
}
|
| 1343 |
},
|
| 1344 |
-
"total_flos": 1.
|
| 1345 |
"train_batch_size": 4,
|
| 1346 |
"trial_name": null,
|
| 1347 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 5.6923076923076925,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 740,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 1322 |
"mean_token_accuracy": 0.6429726481437683,
|
| 1323 |
"num_tokens": 2662473.0,
|
| 1324 |
"step": 730
|
| 1325 |
+
},
|
| 1326 |
+
{
|
| 1327 |
+
"epoch": 5.653846153846154,
|
| 1328 |
+
"grad_norm": 0.0,
|
| 1329 |
+
"learning_rate": 4.633e-05,
|
| 1330 |
+
"loss": 1.7277,
|
| 1331 |
+
"mean_token_accuracy": 0.6474452137947082,
|
| 1332 |
+
"num_tokens": 2681136.0,
|
| 1333 |
+
"step": 735
|
| 1334 |
+
},
|
| 1335 |
+
{
|
| 1336 |
+
"epoch": 5.6923076923076925,
|
| 1337 |
+
"grad_norm": 0.0,
|
| 1338 |
+
"learning_rate": 4.6305000000000005e-05,
|
| 1339 |
+
"loss": 1.7779,
|
| 1340 |
+
"mean_token_accuracy": 0.6477038502693176,
|
| 1341 |
+
"num_tokens": 2698512.0,
|
| 1342 |
+
"step": 740
|
| 1343 |
}
|
| 1344 |
],
|
| 1345 |
"logging_steps": 5,
|
|
|
|
| 1359 |
"attributes": {}
|
| 1360 |
}
|
| 1361 |
},
|
| 1362 |
+
"total_flos": 1.3678839326490624e+17,
|
| 1363 |
"train_batch_size": 4,
|
| 1364 |
"trial_name": null,
|
| 1365 |
"trial_params": null
|