exceptions_exp2_swap_last_to_push_40817

craa/exceptions_exp2_swap_last_to_push_40817

exceptions_exp2_swap_last_to_push_40817 is a text generation model from craa. Use it when you need the model to write or continue text. It is set up for transformers.

should probably proofread and complete it, then remove this comment. --

Downloads · 30 days

22% of all-time downloads

All-time downloads

Public

Parameters

124M

498 MB on disk

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors498 MB · 99%

At a glance

Task: Text Generation
Library: transformers
Model type: gpt2
Access: Public
Created: Dec 2, 2025
Updated: Dec 2, 2025
SHA: bb418913

Try a prompt

Model card

From the Hugging Face model README

exceptions_exp2_swap_last_to_push_40817

This model is a fine-tuned version of on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 3.5637
Accuracy: 0.3686

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 0.0006
train_batch_size: 16
eval_batch_size: 16
seed: 40817
gradient_accumulation_steps: 5
total_train_batch_size: 80
optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.98) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 100
num_epochs: 50.0
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
4.8333	0.2915	1000	4.7595	0.2551
4.3474	0.5830	2000	4.2823	0.2993
4.1466	0.8744	3000	4.1005	0.3143
3.9855	1.1659	4000	3.9938	0.3244
3.9349	1.4573	5000	3.9186	0.3310
3.8868	1.7488	6000	3.8600	0.3359
3.7534	2.0402	7000	3.8180	0.3405
3.7611	2.3317	8000	3.7881	0.3433
3.7365	2.6232	9000	3.7584	0.3464
3.7294	2.9147	10000	3.7321	0.3487
3.6365	3.2061	11000	3.7209	0.3503
3.6395	3.4976	12000	3.7024	0.3523
3.6539	3.7890	13000	3.6821	0.3540
3.5389	4.0804	14000	3.6776	0.3547
3.5789	4.3719	15000	3.6676	0.3561
3.5861	4.6634	16000	3.6516	0.3576
3.5831	4.9549	17000	3.6379	0.3587
3.5175	5.2463	18000	3.6433	0.3590
3.5255	5.5378	19000	3.6305	0.3599
3.5236	5.8293	20000	3.6206	0.3609
3.4443	6.1207	21000	3.6248	0.3612
3.4788	6.4121	22000	3.6156	0.3618
3.4908	6.7036	23000	3.6048	0.3628
3.4965	6.9951	24000	3.5965	0.3635
3.4368	7.2865	25000	3.6057	0.3636
3.4499	7.5780	26000	3.5951	0.3641
3.4674	7.8695	27000	3.5876	0.3646
3.3995	8.1609	28000	3.5972	0.3646
3.4221	8.4524	29000	3.5888	0.3652
3.4411	8.7438	30000	3.5820	0.3657
3.3299	9.0353	31000	3.5847	0.3659
3.3802	9.3267	32000	3.5844	0.3663
3.4028	9.6182	33000	3.5755	0.3668
3.4193	9.9097	34000	3.5677	0.3672
3.3426	10.2011	35000	3.5833	0.3669
3.3634	10.4926	36000	3.5749	0.3673
3.3886	10.7841	37000	3.5661	0.3679
3.295	11.0755	38000	3.5768	0.3678
3.3423	11.3670	39000	3.5708	0.3681
3.3508	11.6584	40000	3.5637	0.3686
3.3788	11.9499	41000	3.5586	0.3688
3.3158	12.2413	42000	3.5734	0.3685
3.3295	12.5328	43000	3.5628	0.3689
3.3484	12.8243	44000	3.5556	0.3694
3.2682	13.1157	45000	3.5716	0.3692
3.316	13.4072	46000	3.5611	0.3695
3.322	13.6987	47000	3.5544	0.3702
3.3351	13.9901	48000	3.5482	0.3703
3.2862	14.2816	49000	3.5628	0.3699
3.3166	14.5730	50000	3.5553	0.3700
3.3206	14.8645	51000	3.5457	0.3708
3.2457	15.1559	52000	3.5645	0.3699
3.2895	15.4474	53000	3.5576	0.3702
3.3157	15.7389	54000	3.5518	0.3710
3.2036	16.0303	55000	3.5612	0.3703
3.2577	16.3218	56000	3.5583	0.3705
3.2907	16.6133	57000	3.5545	0.3711
3.2893	16.9047	58000	3.5440	0.3713
3.2085	17.1962	59000	3.5627	0.3706
3.2532	17.4876	60000	3.5515	0.3714
3.2767	17.7791	61000	3.5436	0.3719
3.1989	18.0705	62000	3.5625	0.3708
3.2344	18.3620	63000	3.5542	0.3712
3.2569	18.6535	64000	3.5499	0.3717
3.2778	18.9450	65000	3.5424	0.3722
3.2199	19.2364	66000	3.5578	0.3711
3.2416	19.5279	67000	3.5513	0.3719
3.2699	19.8193	68000	3.5420	0.3725
3.1871	20.1108	69000	3.5613	0.3715
3.2204	20.4022	70000	3.5539	0.3718
3.2428	20.6937	71000	3.5460	0.3722
3.2579	20.9852	72000	3.5403	0.3728
3.1905	21.2766	73000	3.5602	0.3718
3.2173	21.5681	74000	3.5505	0.3726
3.2475	21.8596	75000	3.5404	0.3728
3.1725	22.1510	76000	3.5602	0.3718
3.2011	22.4425	77000	3.5552	0.3722
3.2288	22.7339	78000	3.5456	0.3728
3.1316	23.0254	79000	3.5590	0.3723
3.1744	23.3168	80000	3.5578	0.3719
3.2078	23.6083	81000	3.5460	0.3726
3.2247	23.8998	82000	3.5399	0.3732
3.1467	24.1912	83000	3.5590	0.3725
3.1776	24.4827	84000	3.5488	0.3731
3.1968	24.7742	85000	3.5434	0.3729
3.1225	25.0656	86000	3.5623	0.3725
3.167	25.3571	87000	3.5540	0.3727
3.1937	25.6485	88000	3.5463	0.3731
3.1972	25.9400	89000	3.5370	0.3739
3.1391	26.2314	90000	3.5564	0.3730
3.1865	26.5229	91000	3.5526	0.3729
3.1868	26.8144	92000	3.5420	0.3736
3.1113	27.1058	93000	3.5615	0.3726
3.1558	27.3973	94000	3.5503	0.3731
3.1724	27.6888	95000	3.5506	0.3735
3.1894	27.9802	96000	3.5387	0.3740
3.1235	28.2717	97000	3.5597	0.3728
3.1559	28.5631	98000	3.5497	0.3734
3.1607	28.8546	99000	3.5445	0.3737
3.1008	29.1460	100000	3.5610	0.3731
3.1358	29.4375	101000	3.5525	0.3733
3.1542	29.7290	102000	3.5496	0.3738
3.0903	30.0204	103000	3.5608	0.3732
3.1188	30.3119	104000	3.5564	0.3735
3.1385	30.6034	105000	3.5513	0.3739
3.1614	30.8948	106000	3.5415	0.3744
3.0896	31.1863	107000	3.5602	0.3733
3.1154	31.4777	108000	3.5531	0.3739
3.1412	31.7692	109000	3.5479	0.3740

Framework versions

Transformers 4.55.2
Pytorch 2.8.0+cu128
Datasets 4.0.0
Tokenizers 0.21.4

Task: Text Generation
Library: transformers
Type: gpt2
Created: Dec 2, 2025
Updated: Dec 2, 2025