Training in progress, step 2930, 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 sha256:577f0c790fcc611863e994d9edb4a51dbf86c68af3fd1cf64ff73498e83b9d79
|
| 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 sha256:1858c7741ef430918d349cec2eae237c0572123e92a10452a877ce1bf019a584
|
| 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 sha256:6ae4f27214b4c790406062840ad6570d5df38f66c834f86fc5d6932c11ef6ab4
|
| 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": 22.
|
| 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,
|
|
@@ -5264,6 +5264,24 @@
|
|
| 5264 |
"mean_token_accuracy": 0.6465423703193665,
|
| 5265 |
"num_tokens": 10647956.0,
|
| 5266 |
"step": 2920
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 5267 |
}
|
| 5268 |
],
|
| 5269 |
"logging_steps": 5,
|
|
@@ -5283,7 +5301,7 @@
|
|
| 5283 |
"attributes": {}
|
| 5284 |
}
|
| 5285 |
},
|
| 5286 |
-
"total_flos": 5.
|
| 5287 |
"train_batch_size": 4,
|
| 5288 |
"trial_name": null,
|
| 5289 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 22.53846153846154,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 2930,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 5264 |
"mean_token_accuracy": 0.6465423703193665,
|
| 5265 |
"num_tokens": 10647956.0,
|
| 5266 |
"step": 2920
|
| 5267 |
+
},
|
| 5268 |
+
{
|
| 5269 |
+
"epoch": 22.5,
|
| 5270 |
+
"grad_norm": 0.0,
|
| 5271 |
+
"learning_rate": 3.5380000000000003e-05,
|
| 5272 |
+
"loss": 1.7415,
|
| 5273 |
+
"mean_token_accuracy": 0.6542441755533218,
|
| 5274 |
+
"num_tokens": 10666004.0,
|
| 5275 |
+
"step": 2925
|
| 5276 |
+
},
|
| 5277 |
+
{
|
| 5278 |
+
"epoch": 22.53846153846154,
|
| 5279 |
+
"grad_norm": 0.0,
|
| 5280 |
+
"learning_rate": 3.5354999999999996e-05,
|
| 5281 |
+
"loss": 1.7098,
|
| 5282 |
+
"mean_token_accuracy": 0.654433760046959,
|
| 5283 |
+
"num_tokens": 10684772.0,
|
| 5284 |
+
"step": 2930
|
| 5285 |
}
|
| 5286 |
],
|
| 5287 |
"logging_steps": 5,
|
|
|
|
| 5301 |
"attributes": {}
|
| 5302 |
}
|
| 5303 |
},
|
| 5304 |
+
"total_flos": 5.414353008869376e+17,
|
| 5305 |
"train_batch_size": 4,
|
| 5306 |
"trial_name": null,
|
| 5307 |
"trial_params": null
|