Training in progress, step 4100, 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 sha256:5fbb2a060faf96b9c155b883dcdec5dd53e70125366eb862ec7454866dc3c6f4
|
| 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 sha256:5f9e684978b8867b4dc154beb3757eab978d031619b2773f5122c7ca05b16816
|
| 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 sha256:778fe612f15146620c3815755198b4e5c24c5032860433d0f0c2fc8a5324fe92
|
| 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": 31.
|
| 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,
|
|
@@ -7370,6 +7370,24 @@
|
|
| 7370 |
"mean_token_accuracy": 0.6495876848697663,
|
| 7371 |
"num_tokens": 14915712.0,
|
| 7372 |
"step": 4090
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 7373 |
}
|
| 7374 |
],
|
| 7375 |
"logging_steps": 5,
|
|
@@ -7389,7 +7407,7 @@
|
|
| 7389 |
"attributes": {}
|
| 7390 |
}
|
| 7391 |
},
|
| 7392 |
-
"total_flos": 7.
|
| 7393 |
"train_batch_size": 4,
|
| 7394 |
"trial_name": null,
|
| 7395 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 31.53846153846154,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 4100,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 7370 |
"mean_token_accuracy": 0.6495876848697663,
|
| 7371 |
"num_tokens": 14915712.0,
|
| 7372 |
"step": 4090
|
| 7373 |
+
},
|
| 7374 |
+
{
|
| 7375 |
+
"epoch": 31.5,
|
| 7376 |
+
"grad_norm": 0.0,
|
| 7377 |
+
"learning_rate": 2.9530000000000004e-05,
|
| 7378 |
+
"loss": 1.7165,
|
| 7379 |
+
"mean_token_accuracy": 0.6608868330717087,
|
| 7380 |
+
"num_tokens": 14933929.0,
|
| 7381 |
+
"step": 4095
|
| 7382 |
+
},
|
| 7383 |
+
{
|
| 7384 |
+
"epoch": 31.53846153846154,
|
| 7385 |
+
"grad_norm": 0.0,
|
| 7386 |
+
"learning_rate": 2.9505e-05,
|
| 7387 |
+
"loss": 1.7196,
|
| 7388 |
+
"mean_token_accuracy": 0.6539542943239212,
|
| 7389 |
+
"num_tokens": 14952726.0,
|
| 7390 |
+
"step": 4100
|
| 7391 |
}
|
| 7392 |
],
|
| 7393 |
"logging_steps": 5,
|
|
|
|
| 7407 |
"attributes": {}
|
| 7408 |
}
|
| 7409 |
},
|
| 7410 |
+
"total_flos": 7.578674726849741e+17,
|
| 7411 |
"train_batch_size": 4,
|
| 7412 |
"trial_name": null,
|
| 7413 |
"trial_params": null
|