Training in progress, step 1370, 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 sha256:62d56b22cffae14876a7ed108a71d54b1d289c893dcb62491b304930846fd475
|
| 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 sha256:26a5aad68da72f9b097a8ab053623aced1c7072e69a84a32bcb3cc1350acaa2a
|
| 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:cdfdeec19ae0ce809733ad947a52e1ecf0df7b538a7be9657dabc458b05765cd
|
| 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,
|
|
@@ -2456,6 +2456,24 @@
|
|
| 2456 |
"mean_token_accuracy": 0.6494636863470078,
|
| 2457 |
"num_tokens": 4960202.0,
|
| 2458 |
"step": 1360
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2459 |
}
|
| 2460 |
],
|
| 2461 |
"logging_steps": 5,
|
|
@@ -2475,7 +2493,7 @@
|
|
| 2475 |
"attributes": {}
|
| 2476 |
}
|
| 2477 |
},
|
| 2478 |
-
"total_flos": 2.
|
| 2479 |
"train_batch_size": 4,
|
| 2480 |
"trial_name": null,
|
| 2481 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 10.538461538461538,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 1370,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 2456 |
"mean_token_accuracy": 0.6494636863470078,
|
| 2457 |
"num_tokens": 4960202.0,
|
| 2458 |
"step": 1360
|
| 2459 |
+
},
|
| 2460 |
+
{
|
| 2461 |
+
"epoch": 10.5,
|
| 2462 |
+
"grad_norm": 0.0,
|
| 2463 |
+
"learning_rate": 4.318e-05,
|
| 2464 |
+
"loss": 1.7592,
|
| 2465 |
+
"mean_token_accuracy": 0.6439968854188919,
|
| 2466 |
+
"num_tokens": 4978469.0,
|
| 2467 |
+
"step": 1365
|
| 2468 |
+
},
|
| 2469 |
+
{
|
| 2470 |
+
"epoch": 10.538461538461538,
|
| 2471 |
+
"grad_norm": 0.0,
|
| 2472 |
+
"learning_rate": 4.3155e-05,
|
| 2473 |
+
"loss": 1.7408,
|
| 2474 |
+
"mean_token_accuracy": 0.6498746544122695,
|
| 2475 |
+
"num_tokens": 4997586.0,
|
| 2476 |
+
"step": 1370
|
| 2477 |
}
|
| 2478 |
],
|
| 2479 |
"logging_steps": 5,
|
|
|
|
| 2493 |
"attributes": {}
|
| 2494 |
}
|
| 2495 |
},
|
| 2496 |
+
"total_flos": 2.5323733667561472e+17,
|
| 2497 |
"train_batch_size": 4,
|
| 2498 |
"trial_name": null,
|
| 2499 |
"trial_params": null
|