Training in progress, step 770, 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 sha256:0abeec8e6bf37f101f20b0110bf2ea7f9c038dcd1099e742346617a23ab9f387
|
| 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 sha256:26751437946aa40433e2bb46a47201fd63c70cfd8a57ecf83d48c6fd1977afc1
|
| 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 sha256:94c13e5052205e4e417a45590b6ce886482baaa40232d2048bb65a340146c36e
|
| 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,
|
|
@@ -1376,6 +1376,24 @@
|
|
| 1376 |
"mean_token_accuracy": 0.6450219005346298,
|
| 1377 |
"num_tokens": 2771304.0,
|
| 1378 |
"step": 760
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1379 |
}
|
| 1380 |
],
|
| 1381 |
"logging_steps": 5,
|
|
@@ -1395,7 +1413,7 @@
|
|
| 1395 |
"attributes": {}
|
| 1396 |
}
|
| 1397 |
},
|
| 1398 |
-
"total_flos": 1.
|
| 1399 |
"train_batch_size": 4,
|
| 1400 |
"trial_name": null,
|
| 1401 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 5.923076923076923,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 770,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 1376 |
"mean_token_accuracy": 0.6450219005346298,
|
| 1377 |
"num_tokens": 2771304.0,
|
| 1378 |
"step": 760
|
| 1379 |
+
},
|
| 1380 |
+
{
|
| 1381 |
+
"epoch": 5.884615384615385,
|
| 1382 |
+
"grad_norm": 0.0,
|
| 1383 |
+
"learning_rate": 4.618e-05,
|
| 1384 |
+
"loss": 1.6985,
|
| 1385 |
+
"mean_token_accuracy": 0.655203464627266,
|
| 1386 |
+
"num_tokens": 2789693.0,
|
| 1387 |
+
"step": 765
|
| 1388 |
+
},
|
| 1389 |
+
{
|
| 1390 |
+
"epoch": 5.923076923076923,
|
| 1391 |
+
"grad_norm": 0.0,
|
| 1392 |
+
"learning_rate": 4.6155e-05,
|
| 1393 |
+
"loss": 1.7607,
|
| 1394 |
+
"mean_token_accuracy": 0.6439933836460113,
|
| 1395 |
+
"num_tokens": 2808244.0,
|
| 1396 |
+
"step": 770
|
| 1397 |
}
|
| 1398 |
],
|
| 1399 |
"logging_steps": 5,
|
|
|
|
| 1413 |
"attributes": {}
|
| 1414 |
}
|
| 1415 |
},
|
| 1416 |
+
"total_flos": 1.4238059479547904e+17,
|
| 1417 |
"train_batch_size": 4,
|
| 1418 |
"trial_name": null,
|
| 1419 |
"trial_params": null
|