learning_rate: 0.0002
train_batch_size: 4
eval_batch_size: 4
seed: 42
gradient_accumulation_steps: 8
total_train_batch_size: 32
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: constant
lr_scheduler_warmup_ratio: 0.03
num_epochs: 3

Training Loss	Epoch	Step	Validation Loss
2.8769	0.1130	10	2.3660
2.0843	0.2260	20	1.5363
1.1442	0.3390	30	0.6542
0.5756	0.4520	40	0.4312
0.4821	0.5650	50	0.4034
0.4743	0.6780	60	0.3902
0.4445	0.7910	70	0.3732
0.4353	0.9040	80	0.3488
0.3692	1.0113	90	0.2830
0.3362	1.1243	100	0.2695
0.3219	1.2373	110	0.2662
0.3257	1.3503	120	0.2613
0.3012	1.4633	130	0.2603
0.3132	1.5763	140	0.2568
0.3054	1.6893	150	0.2548
0.3119	1.8023	160	0.2528
0.2956	1.9153	170	0.2507
0.2989	2.0226	180	0.2500
0.3087	2.1356	190	0.2476
0.2943	2.2486	200	0.2481
0.3064	2.3616	210	0.2453
0.2896	2.4746	220	0.2438
0.2825	2.5876	230	0.2435
0.2817	2.7006	240	0.2400
0.2758	2.8136	250	0.2401
0.2775	2.9266	260	0.2406

dcaisc/qwen2-7b-instruct-trl-sft-ChartQA

qwen2-7b-instruct-trl-sft-ChartQA