Training in progress, step 7380, 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 sha256:0e9c00ae1fa60d9c1e8047e75a352e7eb899b690769eb69a4dbefeadd8faf707
|
| 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 sha256:2c6ec82d55e1a932bd90729a81340f7d07a0fc61d796c83f9913cad3fe187080
|
| 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:fb325c2e1da137380eb1094d752825e76322e405edb686b68436b38397a7d503
|
| 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,
|
|
@@ -13274,6 +13274,24 @@
|
|
| 13274 |
"mean_token_accuracy": 0.6502207726240158,
|
| 13275 |
"num_tokens": 26877909.0,
|
| 13276 |
"step": 7370
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 13277 |
}
|
| 13278 |
],
|
| 13279 |
"logging_steps": 5,
|
|
@@ -13293,7 +13311,7 @@
|
|
| 13293 |
"attributes": {}
|
| 13294 |
}
|
| 13295 |
},
|
| 13296 |
-
"total_flos": 1.
|
| 13297 |
"train_batch_size": 4,
|
| 13298 |
"trial_name": null,
|
| 13299 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 56.76923076923077,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 7380,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 13274 |
"mean_token_accuracy": 0.6502207726240158,
|
| 13275 |
"num_tokens": 26877909.0,
|
| 13276 |
"step": 7370
|
| 13277 |
+
},
|
| 13278 |
+
{
|
| 13279 |
+
"epoch": 56.73076923076923,
|
| 13280 |
+
"grad_norm": 0.0,
|
| 13281 |
+
"learning_rate": 1.3130000000000001e-05,
|
| 13282 |
+
"loss": 1.7571,
|
| 13283 |
+
"mean_token_accuracy": 0.6498846352100373,
|
| 13284 |
+
"num_tokens": 26895371.0,
|
| 13285 |
+
"step": 7375
|
| 13286 |
+
},
|
| 13287 |
+
{
|
| 13288 |
+
"epoch": 56.76923076923077,
|
| 13289 |
+
"grad_norm": 0.0,
|
| 13290 |
+
"learning_rate": 1.3105e-05,
|
| 13291 |
+
"loss": 1.7048,
|
| 13292 |
+
"mean_token_accuracy": 0.6559781163930893,
|
| 13293 |
+
"num_tokens": 26914341.0,
|
| 13294 |
+
"step": 7380
|
| 13295 |
}
|
| 13296 |
],
|
| 13297 |
"logging_steps": 5,
|
|
|
|
| 13311 |
"attributes": {}
|
| 13312 |
}
|
| 13313 |
},
|
| 13314 |
+
"total_flos": 1.3646537296979558e+18,
|
| 13315 |
"train_batch_size": 4,
|
| 13316 |
"trial_name": null,
|
| 13317 |
"trial_params": null
|