Training in progress, step 3140, 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:f6c30c20e13cc0439ead944463143bb40f879c2b828a571aaf064527b5be6da2
|
| 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 sha256:3a91faccd4fa51dbc0df053da53b84b2e8ff1049b4da30ab91b756c4eb5de5dd
|
| 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 sha256:7c339d6920d751abfa12926c02558f58e1c16c4e5bded9a1b5f59f9360438b9b
|
| 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": 24.
|
| 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,
|
|
@@ -5642,6 +5642,24 @@
|
|
| 5642 |
"mean_token_accuracy": 0.6540484815835953,
|
| 5643 |
"num_tokens": 11415431.0,
|
| 5644 |
"step": 3130
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 5645 |
}
|
| 5646 |
],
|
| 5647 |
"logging_steps": 5,
|
|
@@ -5661,7 +5679,7 @@
|
|
| 5661 |
"attributes": {}
|
| 5662 |
}
|
| 5663 |
},
|
| 5664 |
-
"total_flos": 5.
|
| 5665 |
"train_batch_size": 4,
|
| 5666 |
"trial_name": null,
|
| 5667 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 24.153846153846153,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 3140,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 5642 |
"mean_token_accuracy": 0.6540484815835953,
|
| 5643 |
"num_tokens": 11415431.0,
|
| 5644 |
"step": 3130
|
| 5645 |
+
},
|
| 5646 |
+
{
|
| 5647 |
+
"epoch": 24.115384615384617,
|
| 5648 |
+
"grad_norm": 0.0,
|
| 5649 |
+
"learning_rate": 3.433e-05,
|
| 5650 |
+
"loss": 1.7791,
|
| 5651 |
+
"mean_token_accuracy": 0.6443376511335372,
|
| 5652 |
+
"num_tokens": 11433445.0,
|
| 5653 |
+
"step": 3135
|
| 5654 |
+
},
|
| 5655 |
+
{
|
| 5656 |
+
"epoch": 24.153846153846153,
|
| 5657 |
+
"grad_norm": 0.0,
|
| 5658 |
+
"learning_rate": 3.4305000000000004e-05,
|
| 5659 |
+
"loss": 1.7501,
|
| 5660 |
+
"mean_token_accuracy": 0.6464499235153198,
|
| 5661 |
+
"num_tokens": 11451759.0,
|
| 5662 |
+
"step": 3140
|
| 5663 |
}
|
| 5664 |
],
|
| 5665 |
"logging_steps": 5,
|
|
|
|
| 5679 |
"attributes": {}
|
| 5680 |
}
|
| 5681 |
},
|
| 5682 |
+
"total_flos": 5.803055473405133e+17,
|
| 5683 |
"train_batch_size": 4,
|
| 5684 |
"trial_name": null,
|
| 5685 |
"trial_params": null
|