Training in progress, step 3520, 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:f44b326ed2e4cb5c0890a365a32d5bd7921b6ea765d526cf17c22235b6aacf6a
|
| 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 sha256:2adbc39b1a79e97ceb924df4dd23190e284011e7449178a9d78c1044042e9d66
|
| 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:b000c99a5f75aff8de57545b947c0563e126f1132adce4d9b8a36f3da67270d2
|
| 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": 27.
|
| 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,
|
|
@@ -6326,6 +6326,24 @@
|
|
| 6326 |
"mean_token_accuracy": 0.6360502719879151,
|
| 6327 |
"num_tokens": 12800835.0,
|
| 6328 |
"step": 3510
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 6329 |
}
|
| 6330 |
],
|
| 6331 |
"logging_steps": 5,
|
|
@@ -6345,7 +6363,7 @@
|
|
| 6345 |
"attributes": {}
|
| 6346 |
}
|
| 6347 |
},
|
| 6348 |
-
"total_flos": 6.
|
| 6349 |
"train_batch_size": 4,
|
| 6350 |
"trial_name": null,
|
| 6351 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 27.076923076923077,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 3520,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 6326 |
"mean_token_accuracy": 0.6360502719879151,
|
| 6327 |
"num_tokens": 12800835.0,
|
| 6328 |
"step": 3510
|
| 6329 |
+
},
|
| 6330 |
+
{
|
| 6331 |
+
"epoch": 27.03846153846154,
|
| 6332 |
+
"grad_norm": 0.0,
|
| 6333 |
+
"learning_rate": 3.243e-05,
|
| 6334 |
+
"loss": 1.6903,
|
| 6335 |
+
"mean_token_accuracy": 0.6623231947422028,
|
| 6336 |
+
"num_tokens": 12819454.0,
|
| 6337 |
+
"step": 3515
|
| 6338 |
+
},
|
| 6339 |
+
{
|
| 6340 |
+
"epoch": 27.076923076923077,
|
| 6341 |
+
"grad_norm": 0.0,
|
| 6342 |
+
"learning_rate": 3.2405e-05,
|
| 6343 |
+
"loss": 1.7798,
|
| 6344 |
+
"mean_token_accuracy": 0.6476831644773483,
|
| 6345 |
+
"num_tokens": 12837657.0,
|
| 6346 |
+
"step": 3520
|
| 6347 |
}
|
| 6348 |
],
|
| 6349 |
"logging_steps": 5,
|
|
|
|
| 6363 |
"attributes": {}
|
| 6364 |
}
|
| 6365 |
},
|
| 6366 |
+
"total_flos": 6.504417893759386e+17,
|
| 6367 |
"train_batch_size": 4,
|
| 6368 |
"trial_name": null,
|
| 6369 |
"trial_params": null
|