Training in progress, step 1380, 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 sha256:9ffe84bd0fe9bb65e981e5c5c1d3605763da6b7599d79ba6ec4517d403d05594
|
| 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:c95cc1ac2784850d440e3205854bef3a70352a1637c9500d2051ebda0e3d8ef1
|
| 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 sha256:9226d6365338aae9d5725b6e29d6c0b0c842a4cc71b5640c9a03e1c69cfc1e7b
|
| 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,
|
|
@@ -2474,6 +2474,24 @@
|
|
| 2474 |
"mean_token_accuracy": 0.6498746544122695,
|
| 2475 |
"num_tokens": 4997586.0,
|
| 2476 |
"step": 1370
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2477 |
}
|
| 2478 |
],
|
| 2479 |
"logging_steps": 5,
|
|
@@ -2493,7 +2511,7 @@
|
|
| 2493 |
"attributes": {}
|
| 2494 |
}
|
| 2495 |
},
|
| 2496 |
-
"total_flos": 2.
|
| 2497 |
"train_batch_size": 4,
|
| 2498 |
"trial_name": null,
|
| 2499 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 10.615384615384615,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 1380,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 2474 |
"mean_token_accuracy": 0.6498746544122695,
|
| 2475 |
"num_tokens": 4997586.0,
|
| 2476 |
"step": 1370
|
| 2477 |
+
},
|
| 2478 |
+
{
|
| 2479 |
+
"epoch": 10.576923076923077,
|
| 2480 |
+
"grad_norm": 0.0,
|
| 2481 |
+
"learning_rate": 4.313e-05,
|
| 2482 |
+
"loss": 1.7511,
|
| 2483 |
+
"mean_token_accuracy": 0.647632023692131,
|
| 2484 |
+
"num_tokens": 5015966.0,
|
| 2485 |
+
"step": 1375
|
| 2486 |
+
},
|
| 2487 |
+
{
|
| 2488 |
+
"epoch": 10.615384615384615,
|
| 2489 |
+
"grad_norm": 0.0,
|
| 2490 |
+
"learning_rate": 4.3105e-05,
|
| 2491 |
+
"loss": 1.7565,
|
| 2492 |
+
"mean_token_accuracy": 0.6496962130069732,
|
| 2493 |
+
"num_tokens": 5033532.0,
|
| 2494 |
+
"step": 1380
|
| 2495 |
}
|
| 2496 |
],
|
| 2497 |
"logging_steps": 5,
|
|
|
|
| 2511 |
"attributes": {}
|
| 2512 |
}
|
| 2513 |
},
|
| 2514 |
+
"total_flos": 2.55086637391872e+17,
|
| 2515 |
"train_batch_size": 4,
|
| 2516 |
"trial_name": null,
|
| 2517 |
"trial_params": null
|