Training in progress, step 5190, 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:b2e8955144557765a29898cdd71202cf7c9d50aeaff2546a1df8ff63f9dac837
|
| 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:bda2a9d80e105693796757ecd9e2f7529c697e0b26538b10bed4da3792246022
|
| 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 sha256:787b047b971534363fbdd7c72cfeeced04e2437157bc6b894f6ea7ae6a132625
|
| 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": 39.
|
| 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,
|
|
@@ -9332,6 +9332,24 @@
|
|
| 9332 |
"mean_token_accuracy": 0.6371575862169265,
|
| 9333 |
"num_tokens": 18891917.0,
|
| 9334 |
"step": 5180
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 9335 |
}
|
| 9336 |
],
|
| 9337 |
"logging_steps": 5,
|
|
@@ -9351,7 +9369,7 @@
|
|
| 9351 |
"attributes": {}
|
| 9352 |
}
|
| 9353 |
},
|
| 9354 |
-
"total_flos": 9.
|
| 9355 |
"train_batch_size": 4,
|
| 9356 |
"trial_name": null,
|
| 9357 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 39.92307692307692,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 5190,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 9332 |
"mean_token_accuracy": 0.6371575862169265,
|
| 9333 |
"num_tokens": 18891917.0,
|
| 9334 |
"step": 5180
|
| 9335 |
+
},
|
| 9336 |
+
{
|
| 9337 |
+
"epoch": 39.88461538461539,
|
| 9338 |
+
"grad_norm": 0.0,
|
| 9339 |
+
"learning_rate": 2.408e-05,
|
| 9340 |
+
"loss": 1.7642,
|
| 9341 |
+
"mean_token_accuracy": 0.6434910297393799,
|
| 9342 |
+
"num_tokens": 18909826.0,
|
| 9343 |
+
"step": 5185
|
| 9344 |
+
},
|
| 9345 |
+
{
|
| 9346 |
+
"epoch": 39.92307692307692,
|
| 9347 |
+
"grad_norm": 0.0,
|
| 9348 |
+
"learning_rate": 2.4055000000000003e-05,
|
| 9349 |
+
"loss": 1.7481,
|
| 9350 |
+
"mean_token_accuracy": 0.6525659114122391,
|
| 9351 |
+
"num_tokens": 18928215.0,
|
| 9352 |
+
"step": 5190
|
| 9353 |
}
|
| 9354 |
],
|
| 9355 |
"logging_steps": 5,
|
|
|
|
| 9369 |
"attributes": {}
|
| 9370 |
}
|
| 9371 |
},
|
| 9372 |
+
"total_flos": 9.591324253175808e+17,
|
| 9373 |
"train_batch_size": 4,
|
| 9374 |
"trial_name": null,
|
| 9375 |
"trial_params": null
|