Training in progress, step 2970, 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:d07c2fee823b6ee51c4823dd714b801a1b8255ee5bc3bfe393096e3432781a12
|
| 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 sha256:0e80f4cbf6a0e6dd7db777d1dc52468a20c8c7474829c59b3d4431d0f6e009d4
|
| 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:a7cd2038394c585ddbf0af928ad2d41d92087a5ee145d508ed707425c5c2cc03
|
| 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,
|
|
@@ -5336,6 +5336,24 @@
|
|
| 5336 |
"mean_token_accuracy": 0.6521429270505905,
|
| 5337 |
"num_tokens": 10794398.0,
|
| 5338 |
"step": 2960
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 5339 |
}
|
| 5340 |
],
|
| 5341 |
"logging_steps": 5,
|
|
@@ -5355,7 +5373,7 @@
|
|
| 5355 |
"attributes": {}
|
| 5356 |
}
|
| 5357 |
},
|
| 5358 |
-
"total_flos": 5.
|
| 5359 |
"train_batch_size": 4,
|
| 5360 |
"trial_name": null,
|
| 5361 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 22.846153846153847,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 2970,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 5336 |
"mean_token_accuracy": 0.6521429270505905,
|
| 5337 |
"num_tokens": 10794398.0,
|
| 5338 |
"step": 2960
|
| 5339 |
+
},
|
| 5340 |
+
{
|
| 5341 |
+
"epoch": 22.807692307692307,
|
| 5342 |
+
"grad_norm": 0.0,
|
| 5343 |
+
"learning_rate": 3.518e-05,
|
| 5344 |
+
"loss": 1.667,
|
| 5345 |
+
"mean_token_accuracy": 0.6644465386867523,
|
| 5346 |
+
"num_tokens": 10813475.0,
|
| 5347 |
+
"step": 2965
|
| 5348 |
+
},
|
| 5349 |
+
{
|
| 5350 |
+
"epoch": 22.846153846153847,
|
| 5351 |
+
"grad_norm": 0.0,
|
| 5352 |
+
"learning_rate": 3.5155e-05,
|
| 5353 |
+
"loss": 1.7503,
|
| 5354 |
+
"mean_token_accuracy": 0.6510158330202103,
|
| 5355 |
+
"num_tokens": 10831125.0,
|
| 5356 |
+
"step": 2970
|
| 5357 |
}
|
| 5358 |
],
|
| 5359 |
"logging_steps": 5,
|
|
|
|
| 5373 |
"attributes": {}
|
| 5374 |
}
|
| 5375 |
},
|
| 5376 |
+
"total_flos": 5.4888823523229696e+17,
|
| 5377 |
"train_batch_size": 4,
|
| 5378 |
"trial_name": null,
|
| 5379 |
"trial_params": null
|