Training in progress, step 1860, 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 sha256:75740b8fedec433c64d092cc796ac1d013ef09293ff710cccba6f35d50b4d824
|
| 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 sha256:432f0aa9010d8eaa3e0ee4d81ab9f316f2d755b9189ae0583a0b8a164eb9f38e
|
| 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 sha256:53e6ef28e63af8b869d983ef9a867032a64461ee37c63745fe96fff7d201c212
|
| 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,
|
|
@@ -3338,6 +3338,24 @@
|
|
| 3338 |
"mean_token_accuracy": 0.6503253132104874,
|
| 3339 |
"num_tokens": 6750060.0,
|
| 3340 |
"step": 1850
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3341 |
}
|
| 3342 |
],
|
| 3343 |
"logging_steps": 5,
|
|
@@ -3357,7 +3375,7 @@
|
|
| 3357 |
"attributes": {}
|
| 3358 |
}
|
| 3359 |
},
|
| 3360 |
-
"total_flos": 3.
|
| 3361 |
"train_batch_size": 4,
|
| 3362 |
"trial_name": null,
|
| 3363 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 14.307692307692308,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 1860,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 3338 |
"mean_token_accuracy": 0.6503253132104874,
|
| 3339 |
"num_tokens": 6750060.0,
|
| 3340 |
"step": 1850
|
| 3341 |
+
},
|
| 3342 |
+
{
|
| 3343 |
+
"epoch": 14.26923076923077,
|
| 3344 |
+
"grad_norm": 0.0,
|
| 3345 |
+
"learning_rate": 4.0730000000000005e-05,
|
| 3346 |
+
"loss": 1.7848,
|
| 3347 |
+
"mean_token_accuracy": 0.6464446872472763,
|
| 3348 |
+
"num_tokens": 6767696.0,
|
| 3349 |
+
"step": 1855
|
| 3350 |
+
},
|
| 3351 |
+
{
|
| 3352 |
+
"epoch": 14.307692307692308,
|
| 3353 |
+
"grad_norm": 0.0,
|
| 3354 |
+
"learning_rate": 4.0705000000000004e-05,
|
| 3355 |
+
"loss": 1.7344,
|
| 3356 |
+
"mean_token_accuracy": 0.6560231685638428,
|
| 3357 |
+
"num_tokens": 6785928.0,
|
| 3358 |
+
"step": 1860
|
| 3359 |
}
|
| 3360 |
],
|
| 3361 |
"logging_steps": 5,
|
|
|
|
| 3375 |
"attributes": {}
|
| 3376 |
}
|
| 3377 |
},
|
| 3378 |
+
"total_flos": 3.438648214290432e+17,
|
| 3379 |
"train_batch_size": 4,
|
| 3380 |
"trial_name": null,
|
| 3381 |
"trial_params": null
|