Training in progress, step 1360, 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:fbec708f2f475e7b00ccff02e96a776f7a9f36380c88c211a4d139ab2bdc22c6
|
| 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 sha256:376e6e695887b5c60e46e042e29d30cc11cbe63c2c6bba1a49754f0bdc88abdd
|
| 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 sha256:8f50355b3eff1f76b4719279978837e734801892d879f841702c806b52745e1e
|
| 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,
|
|
@@ -2438,6 +2438,24 @@
|
|
| 2438 |
"mean_token_accuracy": 0.6666248500347137,
|
| 2439 |
"num_tokens": 4923475.0,
|
| 2440 |
"step": 1350
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2441 |
}
|
| 2442 |
],
|
| 2443 |
"logging_steps": 5,
|
|
@@ -2457,7 +2475,7 @@
|
|
| 2457 |
"attributes": {}
|
| 2458 |
}
|
| 2459 |
},
|
| 2460 |
-
"total_flos": 2.
|
| 2461 |
"train_batch_size": 4,
|
| 2462 |
"trial_name": null,
|
| 2463 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 10.461538461538462,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 1360,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 2438 |
"mean_token_accuracy": 0.6666248500347137,
|
| 2439 |
"num_tokens": 4923475.0,
|
| 2440 |
"step": 1350
|
| 2441 |
+
},
|
| 2442 |
+
{
|
| 2443 |
+
"epoch": 10.423076923076923,
|
| 2444 |
+
"grad_norm": 0.0,
|
| 2445 |
+
"learning_rate": 4.3230000000000005e-05,
|
| 2446 |
+
"loss": 1.7332,
|
| 2447 |
+
"mean_token_accuracy": 0.6488200217485428,
|
| 2448 |
+
"num_tokens": 4942112.0,
|
| 2449 |
+
"step": 1355
|
| 2450 |
+
},
|
| 2451 |
+
{
|
| 2452 |
+
"epoch": 10.461538461538462,
|
| 2453 |
+
"grad_norm": 0.0,
|
| 2454 |
+
"learning_rate": 4.3205000000000004e-05,
|
| 2455 |
+
"loss": 1.7457,
|
| 2456 |
+
"mean_token_accuracy": 0.6494636863470078,
|
| 2457 |
+
"num_tokens": 4960202.0,
|
| 2458 |
+
"step": 1360
|
| 2459 |
}
|
| 2460 |
],
|
| 2461 |
"logging_steps": 5,
|
|
|
|
| 2475 |
"attributes": {}
|
| 2476 |
}
|
| 2477 |
},
|
| 2478 |
+
"total_flos": 2.5133484494536704e+17,
|
| 2479 |
"train_batch_size": 4,
|
| 2480 |
"trial_name": null,
|
| 2481 |
"trial_params": null
|