Instructions to use CodeIsAbstract/HybridModelScratch with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use CodeIsAbstract/HybridModelScratch with Transformers:
# Load model directly from transformers import HybridFourierLM model = HybridFourierLM.from_pretrained("CodeIsAbstract/HybridModelScratch", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Training in progress, step 2000, checkpoint
Browse files
last-checkpoint/model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 579748776
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:782162ee692bc89212bb1bf2237fad94be0a4f8d8e6006bd2ffb4a44a2317764
|
| 3 |
size 579748776
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1159627083
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0b7fcb1417225ab4b260a3b69014227cbfd71b2c42ffb3dfa186c5847e2fbe41
|
| 3 |
size 1159627083
|
last-checkpoint/rng_state_0.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14917
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bc46d826a65dffd9fffb4922acf95d98d089e8e092701fad0e51a5751ee5d30b
|
| 3 |
size 14917
|
last-checkpoint/rng_state_1.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14917
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4176a469ce53e5e5b4adef275d41a37a84a174b35795b06d37448f614386eab4
|
| 3 |
size 14917
|
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 sha256:0c0d627c7f8a0fb48b948b9cb274ead2ddc9dfdd7223d39ba3cdfe65192c3410
|
| 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":
|
| 6 |
"eval_steps": 100,
|
| 7 |
-
"global_step":
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
@@ -674,6 +674,80 @@
|
|
| 674 |
"eval_samples_per_second": 32.679,
|
| 675 |
"eval_steps_per_second": 1.078,
|
| 676 |
"step": 1800
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 677 |
}
|
| 678 |
],
|
| 679 |
"logging_steps": 25,
|
|
@@ -688,12 +762,12 @@
|
|
| 688 |
"should_evaluate": false,
|
| 689 |
"should_log": false,
|
| 690 |
"should_save": true,
|
| 691 |
-
"should_training_stop":
|
| 692 |
},
|
| 693 |
"attributes": {}
|
| 694 |
}
|
| 695 |
},
|
| 696 |
-
"total_flos": 1.
|
| 697 |
"train_batch_size": 64,
|
| 698 |
"trial_name": null,
|
| 699 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 1.0,
|
| 6 |
"eval_steps": 100,
|
| 7 |
+
"global_step": 2000,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 674 |
"eval_samples_per_second": 32.679,
|
| 675 |
"eval_steps_per_second": 1.078,
|
| 676 |
"step": 1800
|
| 677 |
+
},
|
| 678 |
+
{
|
| 679 |
+
"epoch": 0.9125,
|
| 680 |
+
"grad_norm": 300.458984375,
|
| 681 |
+
"learning_rate": 2.216595153886969e-06,
|
| 682 |
+
"loss": 96.5413,
|
| 683 |
+
"step": 1825
|
| 684 |
+
},
|
| 685 |
+
{
|
| 686 |
+
"epoch": 0.925,
|
| 687 |
+
"grad_norm": 1235.066162109375,
|
| 688 |
+
"learning_rate": 1.6348173407569557e-06,
|
| 689 |
+
"loss": 96.6509,
|
| 690 |
+
"step": 1850
|
| 691 |
+
},
|
| 692 |
+
{
|
| 693 |
+
"epoch": 0.9375,
|
| 694 |
+
"grad_norm": 1469.02978515625,
|
| 695 |
+
"learning_rate": 1.1401968558123976e-06,
|
| 696 |
+
"loss": 96.5367,
|
| 697 |
+
"step": 1875
|
| 698 |
+
},
|
| 699 |
+
{
|
| 700 |
+
"epoch": 0.95,
|
| 701 |
+
"grad_norm": 632.1422119140625,
|
| 702 |
+
"learning_rate": 7.336250385988896e-07,
|
| 703 |
+
"loss": 96.472,
|
| 704 |
+
"step": 1900
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 0.95,
|
| 708 |
+
"eval_accuracy": 0.15278578605365067,
|
| 709 |
+
"eval_loss": 6.0192670822143555,
|
| 710 |
+
"eval_runtime": 7.5713,
|
| 711 |
+
"eval_samples_per_second": 64.058,
|
| 712 |
+
"eval_steps_per_second": 2.113,
|
| 713 |
+
"step": 1900
|
| 714 |
+
},
|
| 715 |
+
{
|
| 716 |
+
"epoch": 0.9625,
|
| 717 |
+
"grad_norm": 2200.51904296875,
|
| 718 |
+
"learning_rate": 4.1583455901149647e-07,
|
| 719 |
+
"loss": 96.5353,
|
| 720 |
+
"step": 1925
|
| 721 |
+
},
|
| 722 |
+
{
|
| 723 |
+
"epoch": 0.975,
|
| 724 |
+
"grad_norm": 1819.2476806640625,
|
| 725 |
+
"learning_rate": 1.8739809697409517e-07,
|
| 726 |
+
"loss": 96.0391,
|
| 727 |
+
"step": 1950
|
| 728 |
+
},
|
| 729 |
+
{
|
| 730 |
+
"epoch": 0.9875,
|
| 731 |
+
"grad_norm": 1034.934326171875,
|
| 732 |
+
"learning_rate": 4.872731043143453e-08,
|
| 733 |
+
"loss": 96.1378,
|
| 734 |
+
"step": 1975
|
| 735 |
+
},
|
| 736 |
+
{
|
| 737 |
+
"epoch": 1.0,
|
| 738 |
+
"grad_norm": 477.2402648925781,
|
| 739 |
+
"learning_rate": 7.209351372550188e-11,
|
| 740 |
+
"loss": 96.5051,
|
| 741 |
+
"step": 2000
|
| 742 |
+
},
|
| 743 |
+
{
|
| 744 |
+
"epoch": 1.0,
|
| 745 |
+
"eval_accuracy": 0.15278376645343053,
|
| 746 |
+
"eval_loss": 6.019127368927002,
|
| 747 |
+
"eval_runtime": 7.2999,
|
| 748 |
+
"eval_samples_per_second": 66.44,
|
| 749 |
+
"eval_steps_per_second": 2.192,
|
| 750 |
+
"step": 2000
|
| 751 |
}
|
| 752 |
],
|
| 753 |
"logging_steps": 25,
|
|
|
|
| 762 |
"should_evaluate": false,
|
| 763 |
"should_log": false,
|
| 764 |
"should_save": true,
|
| 765 |
+
"should_training_stop": true
|
| 766 |
},
|
| 767 |
"attributes": {}
|
| 768 |
}
|
| 769 |
},
|
| 770 |
+
"total_flos": 1.337781380972544e+18,
|
| 771 |
"train_batch_size": 64,
|
| 772 |
"trial_name": null,
|
| 773 |
"trial_params": null
|