Training in progress, step 1850, 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 sha256:112e31d0f6c1e627733eba3ff680877bb1d80501a0d2acd9de587bbaeb0901a4
|
| 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:fbf7c24744ed29f726ae84ad6bd5ad94bba4b95d20cc161a8cafbae317655364
|
| 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 sha256:3ccfe218b66ac3020c4c59b6b79f61dda82f130851dd46e31f4658ca9d36e819
|
| 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": 14.
|
| 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,
|
|
@@ -3320,6 +3320,24 @@
|
|
| 3320 |
"mean_token_accuracy": 0.6440047711133957,
|
| 3321 |
"num_tokens": 6713034.0,
|
| 3322 |
"step": 1840
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3323 |
}
|
| 3324 |
],
|
| 3325 |
"logging_steps": 5,
|
|
@@ -3339,7 +3357,7 @@
|
|
| 3339 |
"attributes": {}
|
| 3340 |
}
|
| 3341 |
},
|
| 3342 |
-
"total_flos": 3.
|
| 3343 |
"train_batch_size": 4,
|
| 3344 |
"trial_name": null,
|
| 3345 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 14.23076923076923,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 1850,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 3320 |
"mean_token_accuracy": 0.6440047711133957,
|
| 3321 |
"num_tokens": 6713034.0,
|
| 3322 |
"step": 1840
|
| 3323 |
+
},
|
| 3324 |
+
{
|
| 3325 |
+
"epoch": 14.192307692307692,
|
| 3326 |
+
"grad_norm": 0.0,
|
| 3327 |
+
"learning_rate": 4.078e-05,
|
| 3328 |
+
"loss": 1.7022,
|
| 3329 |
+
"mean_token_accuracy": 0.6584948360919952,
|
| 3330 |
+
"num_tokens": 6731872.0,
|
| 3331 |
+
"step": 1845
|
| 3332 |
+
},
|
| 3333 |
+
{
|
| 3334 |
+
"epoch": 14.23076923076923,
|
| 3335 |
+
"grad_norm": 0.0,
|
| 3336 |
+
"learning_rate": 4.0755000000000005e-05,
|
| 3337 |
+
"loss": 1.7393,
|
| 3338 |
+
"mean_token_accuracy": 0.6503253132104874,
|
| 3339 |
+
"num_tokens": 6750060.0,
|
| 3340 |
+
"step": 1850
|
| 3341 |
}
|
| 3342 |
],
|
| 3343 |
"logging_steps": 5,
|
|
|
|
| 3357 |
"attributes": {}
|
| 3358 |
}
|
| 3359 |
},
|
| 3360 |
+
"total_flos": 3.420171085042483e+17,
|
| 3361 |
"train_batch_size": 4,
|
| 3362 |
"trial_name": null,
|
| 3363 |
"trial_params": null
|