Training in progress, step 5930, 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:a178a2d4e62fee86f3ac1dcd077346e09cad76616e627c89c8a7b999e4dd96ae
|
| 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 sha256:07b4fa81a21b4bda1ee34f16eaed0f0324986918213493a2e594620f9ad37d73
|
| 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:b4b9051b2892166ab74d3ccbd42e613a60677549dd67dadcda73de8215810382
|
| 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": 45.
|
| 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,
|
|
@@ -10664,6 +10664,24 @@
|
|
| 10664 |
"mean_token_accuracy": 0.6452647089958191,
|
| 10665 |
"num_tokens": 21591748.0,
|
| 10666 |
"step": 5920
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 10667 |
}
|
| 10668 |
],
|
| 10669 |
"logging_steps": 5,
|
|
@@ -10683,7 +10701,7 @@
|
|
| 10683 |
"attributes": {}
|
| 10684 |
}
|
| 10685 |
},
|
| 10686 |
-
"total_flos": 1.
|
| 10687 |
"train_batch_size": 4,
|
| 10688 |
"trial_name": null,
|
| 10689 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 45.61538461538461,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 5930,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 10664 |
"mean_token_accuracy": 0.6452647089958191,
|
| 10665 |
"num_tokens": 21591748.0,
|
| 10666 |
"step": 5920
|
| 10667 |
+
},
|
| 10668 |
+
{
|
| 10669 |
+
"epoch": 45.57692307692308,
|
| 10670 |
+
"grad_norm": 0.0,
|
| 10671 |
+
"learning_rate": 2.038e-05,
|
| 10672 |
+
"loss": 1.8003,
|
| 10673 |
+
"mean_token_accuracy": 0.6423941493034363,
|
| 10674 |
+
"num_tokens": 21608855.0,
|
| 10675 |
+
"step": 5925
|
| 10676 |
+
},
|
| 10677 |
+
{
|
| 10678 |
+
"epoch": 45.61538461538461,
|
| 10679 |
+
"grad_norm": 0.0,
|
| 10680 |
+
"learning_rate": 2.0355e-05,
|
| 10681 |
+
"loss": 1.7603,
|
| 10682 |
+
"mean_token_accuracy": 0.6519896745681762,
|
| 10683 |
+
"num_tokens": 21626524.0,
|
| 10684 |
+
"step": 5930
|
| 10685 |
}
|
| 10686 |
],
|
| 10687 |
"logging_steps": 5,
|
|
|
|
| 10701 |
"attributes": {}
|
| 10702 |
}
|
| 10703 |
},
|
| 10704 |
+
"total_flos": 1.0959232002696806e+18,
|
| 10705 |
"train_batch_size": 4,
|
| 10706 |
"trial_name": null,
|
| 10707 |
"trial_params": null
|