Training in progress, step 7390, 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 sha256:6a4e6018c5e5c58727900d4cd01d322af82af16a3bb4a067231b64cc1caab662
|
| 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 sha256:7318c772a78f1ce8ca09d1c0dd9adf4d76e10b76750332044b7dff6061f18037
|
| 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 sha256:1fb0ab5083eabbd37a919b074f0e4ae681c5f8092d88a296218aa6bf8aa02176
|
| 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": 56.
|
| 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,
|
|
@@ -13292,6 +13292,24 @@
|
|
| 13292 |
"mean_token_accuracy": 0.6559781163930893,
|
| 13293 |
"num_tokens": 26914341.0,
|
| 13294 |
"step": 7380
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 13295 |
}
|
| 13296 |
],
|
| 13297 |
"logging_steps": 5,
|
|
@@ -13311,7 +13329,7 @@
|
|
| 13311 |
"attributes": {}
|
| 13312 |
}
|
| 13313 |
},
|
| 13314 |
-
"total_flos": 1.
|
| 13315 |
"train_batch_size": 4,
|
| 13316 |
"trial_name": null,
|
| 13317 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 56.84615384615385,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 7390,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 13292 |
"mean_token_accuracy": 0.6559781163930893,
|
| 13293 |
"num_tokens": 26914341.0,
|
| 13294 |
"step": 7380
|
| 13295 |
+
},
|
| 13296 |
+
{
|
| 13297 |
+
"epoch": 56.80769230769231,
|
| 13298 |
+
"grad_norm": 0.0,
|
| 13299 |
+
"learning_rate": 1.308e-05,
|
| 13300 |
+
"loss": 1.7642,
|
| 13301 |
+
"mean_token_accuracy": 0.6446814894676208,
|
| 13302 |
+
"num_tokens": 26932597.0,
|
| 13303 |
+
"step": 7385
|
| 13304 |
+
},
|
| 13305 |
+
{
|
| 13306 |
+
"epoch": 56.84615384615385,
|
| 13307 |
+
"grad_norm": 0.0,
|
| 13308 |
+
"learning_rate": 1.3055000000000001e-05,
|
| 13309 |
+
"loss": 1.7919,
|
| 13310 |
+
"mean_token_accuracy": 0.6469128876924515,
|
| 13311 |
+
"num_tokens": 26950520.0,
|
| 13312 |
+
"step": 7390
|
| 13313 |
}
|
| 13314 |
],
|
| 13315 |
"logging_steps": 5,
|
|
|
|
| 13329 |
"attributes": {}
|
| 13330 |
}
|
| 13331 |
},
|
| 13332 |
+
"total_flos": 1.366459207369851e+18,
|
| 13333 |
"train_batch_size": 4,
|
| 13334 |
"trial_name": null,
|
| 13335 |
"trial_params": null
|