Training in progress, step 2550, 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 sha256:8a6170f15b9a6173c4baaff2bb685cfea09481fe9ac5d13f8b177332c4f496c1
|
| 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 sha256:1454a3edd73504ad1258eee7daf7b15a9df781c88dea774761aabfe9d08921cb
|
| 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 sha256:2c0631699d527e839754a27cff6e9a3e8240cbf41f0b02f19c8418adaa7d5d05
|
| 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": 19.
|
| 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,
|
|
@@ -4580,6 +4580,24 @@
|
|
| 4580 |
"mean_token_accuracy": 0.6506271123886108,
|
| 4581 |
"num_tokens": 9262267.0,
|
| 4582 |
"step": 2540
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 4583 |
}
|
| 4584 |
],
|
| 4585 |
"logging_steps": 5,
|
|
@@ -4599,7 +4617,7 @@
|
|
| 4599 |
"attributes": {}
|
| 4600 |
}
|
| 4601 |
},
|
| 4602 |
-
"total_flos": 4.
|
| 4603 |
"train_batch_size": 4,
|
| 4604 |
"trial_name": null,
|
| 4605 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 19.615384615384617,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 2550,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 4580 |
"mean_token_accuracy": 0.6506271123886108,
|
| 4581 |
"num_tokens": 9262267.0,
|
| 4582 |
"step": 2540
|
| 4583 |
+
},
|
| 4584 |
+
{
|
| 4585 |
+
"epoch": 19.576923076923077,
|
| 4586 |
+
"grad_norm": 0.0,
|
| 4587 |
+
"learning_rate": 3.728e-05,
|
| 4588 |
+
"loss": 1.7494,
|
| 4589 |
+
"mean_token_accuracy": 0.6438189834356308,
|
| 4590 |
+
"num_tokens": 9280916.0,
|
| 4591 |
+
"step": 2545
|
| 4592 |
+
},
|
| 4593 |
+
{
|
| 4594 |
+
"epoch": 19.615384615384617,
|
| 4595 |
+
"grad_norm": 0.0,
|
| 4596 |
+
"learning_rate": 3.7255e-05,
|
| 4597 |
+
"loss": 1.7621,
|
| 4598 |
+
"mean_token_accuracy": 0.6443462133407593,
|
| 4599 |
+
"num_tokens": 9299236.0,
|
| 4600 |
+
"step": 2550
|
| 4601 |
}
|
| 4602 |
],
|
| 4603 |
"logging_steps": 5,
|
|
|
|
| 4617 |
"attributes": {}
|
| 4618 |
}
|
| 4619 |
},
|
| 4620 |
+
"total_flos": 4.712311013769216e+17,
|
| 4621 |
"train_batch_size": 4,
|
| 4622 |
"trial_name": null,
|
| 4623 |
"trial_params": null
|