Training in progress, step 780, 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:dff1fc7ea3c59c304c4d311a4ebca09aaa01e1d6fef63d60b8fa87adb56e45e1
|
| 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 sha256:523e491eca60c67003455d3c3b902e5beac92f8a47870bd1e8c4f598932de1e9
|
| 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 sha256:3cf55fc50d81331cb0541d2f160a8f5f1b390375e1ff0c84cc10cfe08f18ebd2
|
| 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": 500,
|
| 7 |
-
"global_step":
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
@@ -1394,6 +1394,24 @@
|
|
| 1394 |
"mean_token_accuracy": 0.6439933836460113,
|
| 1395 |
"num_tokens": 2808244.0,
|
| 1396 |
"step": 770
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1397 |
}
|
| 1398 |
],
|
| 1399 |
"logging_steps": 5,
|
|
@@ -1413,7 +1431,7 @@
|
|
| 1413 |
"attributes": {}
|
| 1414 |
}
|
| 1415 |
},
|
| 1416 |
-
"total_flos": 1.
|
| 1417 |
"train_batch_size": 4,
|
| 1418 |
"trial_name": null,
|
| 1419 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 6.0,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 780,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 1394 |
"mean_token_accuracy": 0.6439933836460113,
|
| 1395 |
"num_tokens": 2808244.0,
|
| 1396 |
"step": 770
|
| 1397 |
+
},
|
| 1398 |
+
{
|
| 1399 |
+
"epoch": 5.961538461538462,
|
| 1400 |
+
"grad_norm": 0.0,
|
| 1401 |
+
"learning_rate": 4.613e-05,
|
| 1402 |
+
"loss": 1.7215,
|
| 1403 |
+
"mean_token_accuracy": 0.6554672598838807,
|
| 1404 |
+
"num_tokens": 2826964.0,
|
| 1405 |
+
"step": 775
|
| 1406 |
+
},
|
| 1407 |
+
{
|
| 1408 |
+
"epoch": 6.0,
|
| 1409 |
+
"grad_norm": 0.0,
|
| 1410 |
+
"learning_rate": 4.610500000000001e-05,
|
| 1411 |
+
"loss": 1.8066,
|
| 1412 |
+
"mean_token_accuracy": 0.6397966831922531,
|
| 1413 |
+
"num_tokens": 2844630.0,
|
| 1414 |
+
"step": 780
|
| 1415 |
}
|
| 1416 |
],
|
| 1417 |
"logging_steps": 5,
|
|
|
|
| 1431 |
"attributes": {}
|
| 1432 |
}
|
| 1433 |
},
|
| 1434 |
+
"total_flos": 1.4419337630810112e+17,
|
| 1435 |
"train_batch_size": 4,
|
| 1436 |
"trial_name": null,
|
| 1437 |
"trial_params": null
|