learning_rate: 2e-05
train_batch_size: 8
eval_batch_size: 8
seed: 42
optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
lr_scheduler_warmup_ratio: 0.05
num_epochs: 3

Training Loss	Epoch	Step	Validation Loss	Bleu	Rougel	Meteor	Bertscore Precision	Bertscore Recall	Bertscore F1
3.1489	0.1961	10	3.1053	0.0087	0.1611	0.1915	0.6600	0.8409	0.7388
2.9865	0.3922	20	2.9819	0.0092	0.1583	0.1966	0.6676	0.8419	0.7439
2.9398	0.5882	30	2.8149	0.0096	0.1619	0.2009	0.6747	0.8409	0.7478
2.62	0.7843	40	2.6788	0.0101	0.1786	0.2076	0.6705	0.8435	0.7463
2.5973	0.9804	50	2.5979	0.0104	0.1888	0.2071	0.6631	0.8448	0.7421
2.5534	1.1765	60	2.5571	0.0102	0.1945	0.2017	0.6561	0.8458	0.7379
2.5526	1.3725	70	2.5235	0.0099	0.1976	0.1984	0.6474	0.8463	0.7324
2.4333	1.5686	80	2.4956	0.0096	0.1996	0.1966	0.6421	0.8473	0.7293
2.4096	1.7647	90	2.4721	0.0096	0.1996	0.1987	0.6409	0.8473	0.7284
2.3812	1.9608	100	2.4536	0.0096	0.2023	0.1997	0.6411	0.8480	0.7287
2.472	2.1569	110	2.4399	0.0097	0.1995	0.1994	0.6402	0.8484	0.7282
2.3531	2.3529	120	2.4307	0.0097	0.2010	0.2008	0.6389	0.8492	0.7277
2.425	2.5490	130	2.4239	0.0098	0.2011	0.2010	0.6399	0.8496	0.7284
2.3681	2.7451	140	2.4196	0.0097	0.2016	0.2039	0.6402	0.8499	0.7287
2.3491	2.9412	150	2.4166	0.0098	0.2035	0.2043	0.6399	0.8494	0.7284

RyanZZZZZ/mental_health_llm_baseline_sft_Llama-3.1-8B_lora_YT_0223

mental_health_llm_baseline_sft_Llama-3.1-8B_lora_YT_0223-4