Training in progress, step 6850, 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:f327751fb87553b0ee14fdd2273fd9cceea9cf4a189189e5e151c95dc634e8ae
|
| 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:cec7f4342ff74f02d223b4f3374fb8c191fa6769882e6ac6d2ea8b90e5f27abb
|
| 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 sha256:45ec3c9a5af59d8b4ddc29a905737ead170be73d55a1bdf39492187217946d63
|
| 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": 52.
|
| 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,
|
|
@@ -12320,6 +12320,24 @@
|
|
| 12320 |
"mean_token_accuracy": 0.6486641079187393,
|
| 12321 |
"num_tokens": 24947565.0,
|
| 12322 |
"step": 6840
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 12323 |
}
|
| 12324 |
],
|
| 12325 |
"logging_steps": 5,
|
|
@@ -12339,7 +12357,7 @@
|
|
| 12339 |
"attributes": {}
|
| 12340 |
}
|
| 12341 |
},
|
| 12342 |
-
"total_flos": 1.
|
| 12343 |
"train_batch_size": 4,
|
| 12344 |
"trial_name": null,
|
| 12345 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 52.69230769230769,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 6850,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 12320 |
"mean_token_accuracy": 0.6486641079187393,
|
| 12321 |
"num_tokens": 24947565.0,
|
| 12322 |
"step": 6840
|
| 12323 |
+
},
|
| 12324 |
+
{
|
| 12325 |
+
"epoch": 52.65384615384615,
|
| 12326 |
+
"grad_norm": 0.0,
|
| 12327 |
+
"learning_rate": 1.578e-05,
|
| 12328 |
+
"loss": 1.7256,
|
| 12329 |
+
"mean_token_accuracy": 0.6513917237520218,
|
| 12330 |
+
"num_tokens": 24966020.0,
|
| 12331 |
+
"step": 6845
|
| 12332 |
+
},
|
| 12333 |
+
{
|
| 12334 |
+
"epoch": 52.69230769230769,
|
| 12335 |
+
"grad_norm": 0.0,
|
| 12336 |
+
"learning_rate": 1.5755e-05,
|
| 12337 |
+
"loss": 1.7481,
|
| 12338 |
+
"mean_token_accuracy": 0.6502928107976913,
|
| 12339 |
+
"num_tokens": 24983952.0,
|
| 12340 |
+
"step": 6850
|
| 12341 |
}
|
| 12342 |
],
|
| 12343 |
"logging_steps": 5,
|
|
|
|
| 12357 |
"attributes": {}
|
| 12358 |
}
|
| 12359 |
},
|
| 12360 |
+
"total_flos": 1.266726056137851e+18,
|
| 12361 |
"train_batch_size": 4,
|
| 12362 |
"trial_name": null,
|
| 12363 |
"trial_params": null
|