Training in progress, step 9640, 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:e4b0f17f4f3b84cd0cef12078dc6b0abd225f55f3485348e5073c1b974f50431
|
| 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:f072cae9c40797f032ea267f9d42c4079697c209b53263bef82681470de00e3e
|
| 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 sha256:2492814eb54450e37ef97c2d81918e85079a3aeca24a5d05f8b6c012b0777387
|
| 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": 74.
|
| 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,
|
|
@@ -17342,6 +17342,24 @@
|
|
| 17342 |
"mean_token_accuracy": 0.6421703934669495,
|
| 17343 |
"num_tokens": 34965175.0,
|
| 17344 |
"step": 9630
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 17345 |
}
|
| 17346 |
],
|
| 17347 |
"logging_steps": 5,
|
|
@@ -17361,7 +17379,7 @@
|
|
| 17361 |
"attributes": {}
|
| 17362 |
}
|
| 17363 |
},
|
| 17364 |
-
"total_flos":
|
| 17365 |
"train_batch_size": 4,
|
| 17366 |
"trial_name": null,
|
| 17367 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 74.15384615384616,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 9640,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 17342 |
"mean_token_accuracy": 0.6421703934669495,
|
| 17343 |
"num_tokens": 34965175.0,
|
| 17344 |
"step": 9630
|
| 17345 |
+
},
|
| 17346 |
+
{
|
| 17347 |
+
"epoch": 74.11538461538461,
|
| 17348 |
+
"grad_norm": 0.0,
|
| 17349 |
+
"learning_rate": 1.83e-06,
|
| 17350 |
+
"loss": 1.8245,
|
| 17351 |
+
"mean_token_accuracy": 0.6394380062818528,
|
| 17352 |
+
"num_tokens": 34983290.0,
|
| 17353 |
+
"step": 9635
|
| 17354 |
+
},
|
| 17355 |
+
{
|
| 17356 |
+
"epoch": 74.15384615384616,
|
| 17357 |
+
"grad_norm": 0.0,
|
| 17358 |
+
"learning_rate": 1.805e-06,
|
| 17359 |
+
"loss": 1.8386,
|
| 17360 |
+
"mean_token_accuracy": 0.6405643105506897,
|
| 17361 |
+
"num_tokens": 35001223.0,
|
| 17362 |
+
"step": 9640
|
| 17363 |
}
|
| 17364 |
],
|
| 17365 |
"logging_steps": 5,
|
|
|
|
| 17379 |
"attributes": {}
|
| 17380 |
}
|
| 17381 |
},
|
| 17382 |
+
"total_flos": 1.0001239771530609e+18,
|
| 17383 |
"train_batch_size": 4,
|
| 17384 |
"trial_name": null,
|
| 17385 |
"trial_params": null
|