Training in progress, step 1390, 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 sha256:73899430dca7d066d606a83ac9f40176ec10a86ec7c731d0b3eda0ebdf00ef4c
|
| 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 sha256:6ce5477b2bc614a4d50329f119a2142f06ec850d1413c8855ceb8b8157464d2f
|
| 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 sha256:849bf10dd3c5f2021767d20796363ca13a77bf13979e16dcbfc198710b5791f2
|
| 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,
|
|
@@ -2492,6 +2492,24 @@
|
|
| 2492 |
"mean_token_accuracy": 0.6496962130069732,
|
| 2493 |
"num_tokens": 5033532.0,
|
| 2494 |
"step": 1380
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2495 |
}
|
| 2496 |
],
|
| 2497 |
"logging_steps": 5,
|
|
@@ -2511,7 +2529,7 @@
|
|
| 2511 |
"attributes": {}
|
| 2512 |
}
|
| 2513 |
},
|
| 2514 |
-
"total_flos": 2.
|
| 2515 |
"train_batch_size": 4,
|
| 2516 |
"trial_name": null,
|
| 2517 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 10.692307692307692,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 1390,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 2492 |
"mean_token_accuracy": 0.6496962130069732,
|
| 2493 |
"num_tokens": 5033532.0,
|
| 2494 |
"step": 1380
|
| 2495 |
+
},
|
| 2496 |
+
{
|
| 2497 |
+
"epoch": 10.653846153846153,
|
| 2498 |
+
"grad_norm": 0.0,
|
| 2499 |
+
"learning_rate": 4.308e-05,
|
| 2500 |
+
"loss": 1.7098,
|
| 2501 |
+
"mean_token_accuracy": 0.6550800025463104,
|
| 2502 |
+
"num_tokens": 5052100.0,
|
| 2503 |
+
"step": 1385
|
| 2504 |
+
},
|
| 2505 |
+
{
|
| 2506 |
+
"epoch": 10.692307692307692,
|
| 2507 |
+
"grad_norm": 0.0,
|
| 2508 |
+
"learning_rate": 4.3055e-05,
|
| 2509 |
+
"loss": 1.7241,
|
| 2510 |
+
"mean_token_accuracy": 0.6496223241090775,
|
| 2511 |
+
"num_tokens": 5070966.0,
|
| 2512 |
+
"step": 1390
|
| 2513 |
}
|
| 2514 |
],
|
| 2515 |
"logging_steps": 5,
|
|
|
|
| 2529 |
"attributes": {}
|
| 2530 |
}
|
| 2531 |
},
|
| 2532 |
+
"total_flos": 2.5698436574773248e+17,
|
| 2533 |
"train_batch_size": 4,
|
| 2534 |
"trial_name": null,
|
| 2535 |
"trial_params": null
|