Training in progress, step 1400, 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:d9205ec92700882e84f270d8c718e66af7397fce7a673d2233ecd34e95cec758
|
| 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 sha256:4c3b817b9c565becc0580b89ee6c17a5399be350d1ff39247506c0a79736f0af
|
| 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:a18e96c87a0227bc4529ffe69d30b26eb48c6f3fdc4326aaedf07c4a8e527bae
|
| 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,
|
|
@@ -2510,6 +2510,24 @@
|
|
| 2510 |
"mean_token_accuracy": 0.6496223241090775,
|
| 2511 |
"num_tokens": 5070966.0,
|
| 2512 |
"step": 1390
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2513 |
}
|
| 2514 |
],
|
| 2515 |
"logging_steps": 5,
|
|
@@ -2529,7 +2547,7 @@
|
|
| 2529 |
"attributes": {}
|
| 2530 |
}
|
| 2531 |
},
|
| 2532 |
-
"total_flos": 2.
|
| 2533 |
"train_batch_size": 4,
|
| 2534 |
"trial_name": null,
|
| 2535 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 10.76923076923077,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 1400,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 2510 |
"mean_token_accuracy": 0.6496223241090775,
|
| 2511 |
"num_tokens": 5070966.0,
|
| 2512 |
"step": 1390
|
| 2513 |
+
},
|
| 2514 |
+
{
|
| 2515 |
+
"epoch": 10.73076923076923,
|
| 2516 |
+
"grad_norm": 0.0,
|
| 2517 |
+
"learning_rate": 4.3030000000000006e-05,
|
| 2518 |
+
"loss": 1.7204,
|
| 2519 |
+
"mean_token_accuracy": 0.6540403842926026,
|
| 2520 |
+
"num_tokens": 5089950.0,
|
| 2521 |
+
"step": 1395
|
| 2522 |
+
},
|
| 2523 |
+
{
|
| 2524 |
+
"epoch": 10.76923076923077,
|
| 2525 |
+
"grad_norm": 0.0,
|
| 2526 |
+
"learning_rate": 4.3005e-05,
|
| 2527 |
+
"loss": 1.7644,
|
| 2528 |
+
"mean_token_accuracy": 0.6442721575498581,
|
| 2529 |
+
"num_tokens": 5107960.0,
|
| 2530 |
+
"step": 1400
|
| 2531 |
}
|
| 2532 |
],
|
| 2533 |
"logging_steps": 5,
|
|
|
|
| 2547 |
"attributes": {}
|
| 2548 |
}
|
| 2549 |
},
|
| 2550 |
+
"total_flos": 2.5884446344593408e+17,
|
| 2551 |
"train_batch_size": 4,
|
| 2552 |
"trial_name": null,
|
| 2553 |
"trial_params": null
|