You can deploy this model and start earning money today!

a3ilab-llm-uncertainty/
Qwen2_5_7B_bfcl_lr1_5e5_ep15_new

Name: Qwen2_5_7B_bfcl_lr1_5e5_ep15_new
Availability: InStock

Qwen/Qwen2.5-7B-Instruct

other

Views

No views yet

Qwen2_5_7B_bfcl_lr1_5e5_ep15_new

This model is a fine-tuned version of Qwen/Qwen2.5-7B-Instruct on the sampled20new_fix2_fix2_toollist_remove_sys_Anyscale_no_tail_dropped dataset. It achieves the following results on the evaluation set:

Loss: 0.2237

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: 1.5e-05
train_batch_size: 1
eval_batch_size: 1
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 4
optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: cosine
lr_scheduler_warmup_ratio: 0.05
num_epochs: 15

Training results

Training Loss	Epoch	Step	Validation Loss
1.8942	1.0	20	1.5297
0.8515	2.0	40	0.7265
0.5111	3.0	60	0.5543
0.4477	4.0	80	0.4513
0.3714	5.0	100	0.3596
0.3233	6.0	120	0.2945
0.1548	7.0	140	0.2564
0.2141	8.0	160	0.2387
0.1343	9.0	180	0.2284
0.1353	10.0	200	0.2249
0.0823	11.0	220	0.2246
0.1318	12.0	240	0.2235
0.0998	13.0	260	0.2238
0.123	14.0	280	0.2238
0.0796	15.0	300	0.2237

Framework versions

PEFT 0.17.0
Transformers 4.55.2
Pytorch 2.4.1+cu121
Datasets 4.0.0
Tokenizers 0.21.4

a3ilab-llm-uncertainty/Qwen2_5_7B_bfcl_lr1_5e5_ep15_new

Qwen2_5_7B_bfcl_lr1_5e5_ep15_new

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

a3ilab-llm-uncertainty/
Qwen2_5_7B_bfcl_lr1_5e5_ep15_new