camembert_question_answering_tools_qlora_fr

AntoineD/camembert_question_answering_tools_qlora_fr

camembert_question_answering_tools_qlora_fr is a machine learning model from AntoineD. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as mit.

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

Downloads · 30 days

Access

Public

Updated Nov 10, 2023

Repo size

281 MB

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.bin5.2 MB · 62%

At a glance

License: mit
Access: Public
Created: Nov 10, 2023
Updated: Nov 10, 2023
SHA: 7dd043f6

Base models

Model card

From the Hugging Face model README

camembert_question_answering_tools_qlora_fr

This model is a fine-tuned version of camembert-base on the None dataset. It achieves the following results on the evaluation set:

Loss: 2.3275
Learning Rate: 0.0

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: 0.0001
train_batch_size: 24
eval_batch_size: 192
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 60

Training results

Training Loss	Epoch	Step	Validation Loss	Rate
No log	1.0	7	5.8555	0.0001
No log	2.0	14	5.7277	0.0001
No log	3.0	21	5.5916	0.0001
No log	4.0	28	5.4433	0.0001
No log	5.0	35	5.2833	0.0001
No log	6.0	42	5.1312	9e-05
No log	7.0	49	4.9815	0.0001
No log	8.0	56	4.8317	0.0001
No log	9.0	63	4.6800	0.0001
No log	10.0	70	4.5265	0.0001
No log	11.0	77	4.3673	0.0001
No log	12.0	84	4.2002	8e-05
No log	13.0	91	4.0344	0.0001
No log	14.0	98	3.8807	0.0001
No log	15.0	105	3.7267	0.0001
No log	16.0	112	3.5812	0.0001
No log	17.0	119	3.4528	0.0001
No log	18.0	126	3.3323	7e-05
No log	19.0	133	3.2173	0.0001
No log	20.0	140	3.1382	0.0001
No log	21.0	147	3.0190	0.0001
No log	22.0	154	2.9614	0.0001
No log	23.0	161	2.8867	0.0001
No log	24.0	168	2.8360	6e-05
No log	25.0	175	2.7882	0.0001
No log	26.0	182	2.7450	0.0001
No log	27.0	189	2.6969	0.0001
No log	28.0	196	2.6651	0.0001
No log	29.0	203	2.6440	0.0001
No log	30.0	210	2.6032	5e-05
No log	31.0	217	2.5762	0.0000
No log	32.0	224	2.5473	0.0000
No log	33.0	231	2.5338	0.0000
No log	34.0	238	2.5056	0.0000
No log	35.0	245	2.4919	0.0000
No log	36.0	252	2.4773	4e-05
No log	37.0	259	2.4594	0.0000
No log	38.0	266	2.4429	0.0000
No log	39.0	273	2.4275	0.0000
No log	40.0	280	2.4184	0.0000
No log	41.0	287	2.4123	0.0000
No log	42.0	294	2.3951	3e-05
No log	43.0	301	2.3963	0.0000
No log	44.0	308	2.3848	0.0000
No log	45.0	315	2.3714	0.0000
No log	46.0	322	2.3696	0.0000
No log	47.0	329	2.3626	0.0000
No log	48.0	336	2.3545	2e-05
No log	49.0	343	2.3523	0.0000
No log	50.0	350	2.3492	0.0000
No log	51.0	357	2.3429	0.0000
No log	52.0	364	2.3364	0.0000
No log	53.0	371	2.3371	0.0000
No log	54.0	378	2.3360	1e-05
No log	55.0	385	2.3329	0.0000
No log	56.0	392	2.3316	0.0000
No log	57.0	399	2.3292	5e-06
No log	58.0	406	2.3281	0.0000
No log	59.0	413	2.3278	0.0000
No log	60.0	420	2.3275	0.0

Framework versions

Transformers 4.34.0
Pytorch 2.0.1+cu117
Datasets 2.14.5
Tokenizers 0.14.1

License: mit
Created: Nov 10, 2023
Updated: Nov 10, 2023