Training in progress, step 1350, 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:b23a545e1f3bf01ec008e99548d88344f77748d66287533aac0862069148d88d
|
| 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 sha256:17cd6b5f61b2e0a126baf7780af34b67fcac1721a2b0f680761eb9b752a93099
|
| 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 sha256:602612eee9c28dd5a7434c5013693deaed85c3fd5e7c26726913b3b78c3b5464
|
| 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": 10.
|
| 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,
|
|
@@ -2420,6 +2420,24 @@
|
|
| 2420 |
"mean_token_accuracy": 0.650857400894165,
|
| 2421 |
"num_tokens": 4885905.0,
|
| 2422 |
"step": 1340
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2423 |
}
|
| 2424 |
],
|
| 2425 |
"logging_steps": 5,
|
|
@@ -2439,7 +2457,7 @@
|
|
| 2439 |
"attributes": {}
|
| 2440 |
}
|
| 2441 |
},
|
| 2442 |
-
"total_flos": 2.
|
| 2443 |
"train_batch_size": 4,
|
| 2444 |
"trial_name": null,
|
| 2445 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 10.384615384615385,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 1350,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 2420 |
"mean_token_accuracy": 0.650857400894165,
|
| 2421 |
"num_tokens": 4885905.0,
|
| 2422 |
"step": 1340
|
| 2423 |
+
},
|
| 2424 |
+
{
|
| 2425 |
+
"epoch": 10.346153846153847,
|
| 2426 |
+
"grad_norm": 0.0,
|
| 2427 |
+
"learning_rate": 4.3280000000000006e-05,
|
| 2428 |
+
"loss": 1.7016,
|
| 2429 |
+
"mean_token_accuracy": 0.6605552464723587,
|
| 2430 |
+
"num_tokens": 4904774.0,
|
| 2431 |
+
"step": 1345
|
| 2432 |
+
},
|
| 2433 |
+
{
|
| 2434 |
+
"epoch": 10.384615384615385,
|
| 2435 |
+
"grad_norm": 0.0,
|
| 2436 |
+
"learning_rate": 4.3255e-05,
|
| 2437 |
+
"loss": 1.6779,
|
| 2438 |
+
"mean_token_accuracy": 0.6666248500347137,
|
| 2439 |
+
"num_tokens": 4923475.0,
|
| 2440 |
+
"step": 1350
|
| 2441 |
}
|
| 2442 |
],
|
| 2443 |
"logging_steps": 5,
|
|
|
|
| 2457 |
"attributes": {}
|
| 2458 |
}
|
| 2459 |
},
|
| 2460 |
+
"total_flos": 2.4942743106158592e+17,
|
| 2461 |
"train_batch_size": 4,
|
| 2462 |
"trial_name": null,
|
| 2463 |
"trial_params": null
|