Training in progress, step 7960, 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 sha256:961a6480853f330497a3de2aa1130d6b7f67b3b20e9ef4b303c59dbe5e25bb5a
|
| 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:dd9d0daf4e0047a526dea6270e589847329abe31bbd7416c3d08f2467c0c3bbf
|
| 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 sha256:9f3c5bd9a6345193d6e66cd84e0d53fcc00f3437d49ebc8f22bf039ade097d84
|
| 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": 61.
|
| 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,
|
|
@@ -14318,6 +14318,24 @@
|
|
| 14318 |
"mean_token_accuracy": 0.6496328443288804,
|
| 14319 |
"num_tokens": 28991130.0,
|
| 14320 |
"step": 7950
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 14321 |
}
|
| 14322 |
],
|
| 14323 |
"logging_steps": 5,
|
|
@@ -14337,7 +14355,7 @@
|
|
| 14337 |
"attributes": {}
|
| 14338 |
}
|
| 14339 |
},
|
| 14340 |
-
"total_flos": 1.
|
| 14341 |
"train_batch_size": 4,
|
| 14342 |
"trial_name": null,
|
| 14343 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 61.23076923076923,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 7960,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 14318 |
"mean_token_accuracy": 0.6496328443288804,
|
| 14319 |
"num_tokens": 28991130.0,
|
| 14320 |
"step": 7950
|
| 14321 |
+
},
|
| 14322 |
+
{
|
| 14323 |
+
"epoch": 61.19230769230769,
|
| 14324 |
+
"grad_norm": 0.0,
|
| 14325 |
+
"learning_rate": 1.023e-05,
|
| 14326 |
+
"loss": 1.7164,
|
| 14327 |
+
"mean_token_accuracy": 0.6583995938301086,
|
| 14328 |
+
"num_tokens": 29009479.0,
|
| 14329 |
+
"step": 7955
|
| 14330 |
+
},
|
| 14331 |
+
{
|
| 14332 |
+
"epoch": 61.23076923076923,
|
| 14333 |
+
"grad_norm": 0.0,
|
| 14334 |
+
"learning_rate": 1.0205000000000001e-05,
|
| 14335 |
+
"loss": 1.7438,
|
| 14336 |
+
"mean_token_accuracy": 0.6459792077541351,
|
| 14337 |
+
"num_tokens": 29027531.0,
|
| 14338 |
+
"step": 7960
|
| 14339 |
}
|
| 14340 |
],
|
| 14341 |
"logging_steps": 5,
|
|
|
|
| 14355 |
"attributes": {}
|
| 14356 |
}
|
| 14357 |
},
|
| 14358 |
+
"total_flos": 1.4717474058122035e+18,
|
| 14359 |
"train_batch_size": 4,
|
| 14360 |
"trial_name": null,
|
| 14361 |
"trial_params": null
|