Training in progress, step 6870, 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:adddd114760476264d8e2a34289be826295c37e9ff2e8ac22fb2fdafaf6dac5a
|
| 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 sha256:1a62dd0354729bc83b72ae6583c2c267a00a7503b8c5a869f598272008a3de1c
|
| 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 sha256:45969be73de0b7c8e6c294a922463273a5ad161fae138b17e43c3d286f482fd9
|
| 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": 52.
|
| 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,
|
|
@@ -12356,6 +12356,24 @@
|
|
| 12356 |
"mean_token_accuracy": 0.6445726931095124,
|
| 12357 |
"num_tokens": 25020198.0,
|
| 12358 |
"step": 6860
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 12359 |
}
|
| 12360 |
],
|
| 12361 |
"logging_steps": 5,
|
|
@@ -12375,7 +12393,7 @@
|
|
| 12375 |
"attributes": {}
|
| 12376 |
}
|
| 12377 |
},
|
| 12378 |
-
"total_flos": 1.
|
| 12379 |
"train_batch_size": 4,
|
| 12380 |
"trial_name": null,
|
| 12381 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 52.84615384615385,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 6870,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 12356 |
"mean_token_accuracy": 0.6445726931095124,
|
| 12357 |
"num_tokens": 25020198.0,
|
| 12358 |
"step": 6860
|
| 12359 |
+
},
|
| 12360 |
+
{
|
| 12361 |
+
"epoch": 52.80769230769231,
|
| 12362 |
+
"grad_norm": 0.0,
|
| 12363 |
+
"learning_rate": 1.568e-05,
|
| 12364 |
+
"loss": 1.831,
|
| 12365 |
+
"mean_token_accuracy": 0.6385212212800979,
|
| 12366 |
+
"num_tokens": 25037190.0,
|
| 12367 |
+
"step": 6865
|
| 12368 |
+
},
|
| 12369 |
+
{
|
| 12370 |
+
"epoch": 52.84615384615385,
|
| 12371 |
+
"grad_norm": 0.0,
|
| 12372 |
+
"learning_rate": 1.5655000000000002e-05,
|
| 12373 |
+
"loss": 1.7463,
|
| 12374 |
+
"mean_token_accuracy": 0.6501509785652161,
|
| 12375 |
+
"num_tokens": 25055025.0,
|
| 12376 |
+
"step": 6870
|
| 12377 |
}
|
| 12378 |
],
|
| 12379 |
"logging_steps": 5,
|
|
|
|
| 12393 |
"attributes": {}
|
| 12394 |
}
|
| 12395 |
},
|
| 12396 |
+
"total_flos": 1.2702738173814374e+18,
|
| 12397 |
"train_batch_size": 4,
|
| 12398 |
"trial_name": null,
|
| 12399 |
"trial_params": null
|