Training in progress, step 9070, 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 sha256:0f1a0434a6ca437e681c4ae77ee41f98492556b2139c158214c5fea8915e3497
|
| 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 sha256:5f24ac2ec8c19c25c2b25a8a5c2ae533fc699e9c68712689b48d1678c563482a
|
| 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 sha256:4d8f1622c549dc04ac7ee581bbb54e6ca3d47e9e606b04df4f713bd10f5caffa
|
| 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": 69.
|
| 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,
|
|
@@ -16316,6 +16316,24 @@
|
|
| 16316 |
"mean_token_accuracy": 0.6455245047807694,
|
| 16317 |
"num_tokens": 33040528.0,
|
| 16318 |
"step": 9060
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 16319 |
}
|
| 16320 |
],
|
| 16321 |
"logging_steps": 5,
|
|
@@ -16335,7 +16353,7 @@
|
|
| 16335 |
"attributes": {}
|
| 16336 |
}
|
| 16337 |
},
|
| 16338 |
-
"total_flos": 1.
|
| 16339 |
"train_batch_size": 4,
|
| 16340 |
"trial_name": null,
|
| 16341 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 69.76923076923077,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 9070,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 16316 |
"mean_token_accuracy": 0.6455245047807694,
|
| 16317 |
"num_tokens": 33040528.0,
|
| 16318 |
"step": 9060
|
| 16319 |
+
},
|
| 16320 |
+
{
|
| 16321 |
+
"epoch": 69.73076923076923,
|
| 16322 |
+
"grad_norm": 0.0,
|
| 16323 |
+
"learning_rate": 4.68e-06,
|
| 16324 |
+
"loss": 1.734,
|
| 16325 |
+
"mean_token_accuracy": 0.6510042399168015,
|
| 16326 |
+
"num_tokens": 33058790.0,
|
| 16327 |
+
"step": 9065
|
| 16328 |
+
},
|
| 16329 |
+
{
|
| 16330 |
+
"epoch": 69.76923076923077,
|
| 16331 |
+
"grad_norm": 0.0,
|
| 16332 |
+
"learning_rate": 4.655e-06,
|
| 16333 |
+
"loss": 1.7801,
|
| 16334 |
+
"mean_token_accuracy": 0.6483240693807601,
|
| 16335 |
+
"num_tokens": 33076529.0,
|
| 16336 |
+
"step": 9070
|
| 16337 |
}
|
| 16338 |
],
|
| 16339 |
"logging_steps": 5,
|
|
|
|
| 16353 |
"attributes": {}
|
| 16354 |
}
|
| 16355 |
},
|
| 16356 |
+
"total_flos": 1.677153636137042e+18,
|
| 16357 |
"train_batch_size": 4,
|
| 16358 |
"trial_name": null,
|
| 16359 |
"trial_params": null
|