Training in progress, step 2410, 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 sha256:8a4d535403356a51d8bc7b8b56a8153dab468bc7bb3d7edc5b4924d1b152196b
|
| 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 sha256:88d4f71e1986c36227ad672a9e37fff87f9f8e850345322ded8dcf692c7b3ce4
|
| 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 sha256:5ffb530d377eaabf9273b4ae7044a599cc346eb67552636a318613f5e0b8e578
|
| 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": 18.
|
| 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,
|
|
@@ -4328,6 +4328,24 @@
|
|
| 4328 |
"mean_token_accuracy": 0.6472231477499009,
|
| 4329 |
"num_tokens": 8750733.0,
|
| 4330 |
"step": 2400
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 4331 |
}
|
| 4332 |
],
|
| 4333 |
"logging_steps": 5,
|
|
@@ -4347,7 +4365,7 @@
|
|
| 4347 |
"attributes": {}
|
| 4348 |
}
|
| 4349 |
},
|
| 4350 |
-
"total_flos": 4.
|
| 4351 |
"train_batch_size": 4,
|
| 4352 |
"trial_name": null,
|
| 4353 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 18.53846153846154,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 2410,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 4328 |
"mean_token_accuracy": 0.6472231477499009,
|
| 4329 |
"num_tokens": 8750733.0,
|
| 4330 |
"step": 2400
|
| 4331 |
+
},
|
| 4332 |
+
{
|
| 4333 |
+
"epoch": 18.5,
|
| 4334 |
+
"grad_norm": 0.0,
|
| 4335 |
+
"learning_rate": 3.7980000000000006e-05,
|
| 4336 |
+
"loss": 1.822,
|
| 4337 |
+
"mean_token_accuracy": 0.6343230813741684,
|
| 4338 |
+
"num_tokens": 8768670.0,
|
| 4339 |
+
"step": 2405
|
| 4340 |
+
},
|
| 4341 |
+
{
|
| 4342 |
+
"epoch": 18.53846153846154,
|
| 4343 |
+
"grad_norm": 0.0,
|
| 4344 |
+
"learning_rate": 3.7955e-05,
|
| 4345 |
+
"loss": 1.7632,
|
| 4346 |
+
"mean_token_accuracy": 0.6466387540102005,
|
| 4347 |
+
"num_tokens": 8786506.0,
|
| 4348 |
+
"step": 2410
|
| 4349 |
}
|
| 4350 |
],
|
| 4351 |
"logging_steps": 5,
|
|
|
|
| 4365 |
"attributes": {}
|
| 4366 |
}
|
| 4367 |
},
|
| 4368 |
+
"total_flos": 4.452270467014656e+17,
|
| 4369 |
"train_batch_size": 4,
|
| 4370 |
"trial_name": null,
|
| 4371 |
"trial_params": null
|