|
{ |
|
"best_metric": 0.2939682602882385, |
|
"best_model_checkpoint": "autotrain-hyyfj-borac/checkpoint-104", |
|
"epoch": 2.0, |
|
"eval_steps": 500, |
|
"global_step": 104, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.038461538461538464, |
|
"grad_norm": 6.025815963745117, |
|
"learning_rate": 6.25e-06, |
|
"loss": 0.5818, |
|
"step": 2 |
|
}, |
|
{ |
|
"epoch": 0.07692307692307693, |
|
"grad_norm": 9.179534912109375, |
|
"learning_rate": 1.25e-05, |
|
"loss": 0.584, |
|
"step": 4 |
|
}, |
|
{ |
|
"epoch": 0.11538461538461539, |
|
"grad_norm": 4.207178115844727, |
|
"learning_rate": 1.8750000000000002e-05, |
|
"loss": 0.5044, |
|
"step": 6 |
|
}, |
|
{ |
|
"epoch": 0.15384615384615385, |
|
"grad_norm": 5.58507776260376, |
|
"learning_rate": 2.5e-05, |
|
"loss": 0.3244, |
|
"step": 8 |
|
}, |
|
{ |
|
"epoch": 0.19230769230769232, |
|
"grad_norm": 2.5677101612091064, |
|
"learning_rate": 3.125e-05, |
|
"loss": 0.2411, |
|
"step": 10 |
|
}, |
|
{ |
|
"epoch": 0.23076923076923078, |
|
"grad_norm": 3.239185094833374, |
|
"learning_rate": 3.7500000000000003e-05, |
|
"loss": 0.2572, |
|
"step": 12 |
|
}, |
|
{ |
|
"epoch": 0.2692307692307692, |
|
"grad_norm": 1.5567970275878906, |
|
"learning_rate": 4.375e-05, |
|
"loss": 0.0463, |
|
"step": 14 |
|
}, |
|
{ |
|
"epoch": 0.3076923076923077, |
|
"grad_norm": 0.34924909472465515, |
|
"learning_rate": 5e-05, |
|
"loss": 0.0205, |
|
"step": 16 |
|
}, |
|
{ |
|
"epoch": 0.34615384615384615, |
|
"grad_norm": 1.1856858730316162, |
|
"learning_rate": 4.928571428571429e-05, |
|
"loss": 0.2883, |
|
"step": 18 |
|
}, |
|
{ |
|
"epoch": 0.38461538461538464, |
|
"grad_norm": 9.244117736816406, |
|
"learning_rate": 4.8571428571428576e-05, |
|
"loss": 0.6795, |
|
"step": 20 |
|
}, |
|
{ |
|
"epoch": 0.4230769230769231, |
|
"grad_norm": 3.249788522720337, |
|
"learning_rate": 4.785714285714286e-05, |
|
"loss": 0.2357, |
|
"step": 22 |
|
}, |
|
{ |
|
"epoch": 0.46153846153846156, |
|
"grad_norm": 1.3072822093963623, |
|
"learning_rate": 4.714285714285714e-05, |
|
"loss": 0.0682, |
|
"step": 24 |
|
}, |
|
{ |
|
"epoch": 0.5, |
|
"grad_norm": 3.7042837142944336, |
|
"learning_rate": 4.642857142857143e-05, |
|
"loss": 0.4232, |
|
"step": 26 |
|
}, |
|
{ |
|
"epoch": 0.5384615384615384, |
|
"grad_norm": 1.0529388189315796, |
|
"learning_rate": 4.5714285714285716e-05, |
|
"loss": 0.0337, |
|
"step": 28 |
|
}, |
|
{ |
|
"epoch": 0.5769230769230769, |
|
"grad_norm": 0.3905356228351593, |
|
"learning_rate": 4.5e-05, |
|
"loss": 0.2535, |
|
"step": 30 |
|
}, |
|
{ |
|
"epoch": 0.6153846153846154, |
|
"grad_norm": 4.982702255249023, |
|
"learning_rate": 4.428571428571428e-05, |
|
"loss": 0.3307, |
|
"step": 32 |
|
}, |
|
{ |
|
"epoch": 0.6538461538461539, |
|
"grad_norm": 0.19216814637184143, |
|
"learning_rate": 4.3571428571428576e-05, |
|
"loss": 0.3452, |
|
"step": 34 |
|
}, |
|
{ |
|
"epoch": 0.6923076923076923, |
|
"grad_norm": 4.820222854614258, |
|
"learning_rate": 4.2857142857142856e-05, |
|
"loss": 0.5677, |
|
"step": 36 |
|
}, |
|
{ |
|
"epoch": 0.7307692307692307, |
|
"grad_norm": 1.0272815227508545, |
|
"learning_rate": 4.214285714285714e-05, |
|
"loss": 0.4791, |
|
"step": 38 |
|
}, |
|
{ |
|
"epoch": 0.7692307692307693, |
|
"grad_norm": 1.5378814935684204, |
|
"learning_rate": 4.1428571428571437e-05, |
|
"loss": 0.0582, |
|
"step": 40 |
|
}, |
|
{ |
|
"epoch": 0.8076923076923077, |
|
"grad_norm": 0.989844560623169, |
|
"learning_rate": 4.0714285714285717e-05, |
|
"loss": 0.2427, |
|
"step": 42 |
|
}, |
|
{ |
|
"epoch": 0.8461538461538461, |
|
"grad_norm": 17.12215232849121, |
|
"learning_rate": 4e-05, |
|
"loss": 0.7269, |
|
"step": 44 |
|
}, |
|
{ |
|
"epoch": 0.8846153846153846, |
|
"grad_norm": 0.5058056712150574, |
|
"learning_rate": 3.928571428571429e-05, |
|
"loss": 0.2946, |
|
"step": 46 |
|
}, |
|
{ |
|
"epoch": 0.9230769230769231, |
|
"grad_norm": 11.418269157409668, |
|
"learning_rate": 3.857142857142858e-05, |
|
"loss": 0.6127, |
|
"step": 48 |
|
}, |
|
{ |
|
"epoch": 0.9615384615384616, |
|
"grad_norm": 0.5562339425086975, |
|
"learning_rate": 3.785714285714286e-05, |
|
"loss": 0.3462, |
|
"step": 50 |
|
}, |
|
{ |
|
"epoch": 1.0, |
|
"grad_norm": 0.3832690119743347, |
|
"learning_rate": 3.7142857142857143e-05, |
|
"loss": 0.0145, |
|
"step": 52 |
|
}, |
|
{ |
|
"epoch": 1.0, |
|
"eval_accuracy": 0.9326923076923077, |
|
"eval_auc": 0.49926362297496313, |
|
"eval_f1": 0.0, |
|
"eval_loss": 0.31564611196517944, |
|
"eval_precision": 0.0, |
|
"eval_recall": 0.0, |
|
"eval_runtime": 1.4422, |
|
"eval_samples_per_second": 72.114, |
|
"eval_steps_per_second": 4.854, |
|
"step": 52 |
|
}, |
|
{ |
|
"epoch": 1.0384615384615385, |
|
"grad_norm": 0.30034294724464417, |
|
"learning_rate": 3.642857142857143e-05, |
|
"loss": 0.0115, |
|
"step": 54 |
|
}, |
|
{ |
|
"epoch": 1.0769230769230769, |
|
"grad_norm": 4.174347877502441, |
|
"learning_rate": 3.571428571428572e-05, |
|
"loss": 0.3074, |
|
"step": 56 |
|
}, |
|
{ |
|
"epoch": 1.1153846153846154, |
|
"grad_norm": 4.107996940612793, |
|
"learning_rate": 3.5e-05, |
|
"loss": 0.658, |
|
"step": 58 |
|
}, |
|
{ |
|
"epoch": 1.1538461538461537, |
|
"grad_norm": 3.2274246215820312, |
|
"learning_rate": 3.428571428571429e-05, |
|
"loss": 0.3278, |
|
"step": 60 |
|
}, |
|
{ |
|
"epoch": 1.1923076923076923, |
|
"grad_norm": 3.1883745193481445, |
|
"learning_rate": 3.357142857142857e-05, |
|
"loss": 0.6058, |
|
"step": 62 |
|
}, |
|
{ |
|
"epoch": 1.2307692307692308, |
|
"grad_norm": 0.4613792598247528, |
|
"learning_rate": 3.285714285714286e-05, |
|
"loss": 0.0172, |
|
"step": 64 |
|
}, |
|
{ |
|
"epoch": 1.2692307692307692, |
|
"grad_norm": 0.6901736855506897, |
|
"learning_rate": 3.2142857142857144e-05, |
|
"loss": 0.0238, |
|
"step": 66 |
|
}, |
|
{ |
|
"epoch": 1.3076923076923077, |
|
"grad_norm": 0.6056439876556396, |
|
"learning_rate": 3.142857142857143e-05, |
|
"loss": 0.2596, |
|
"step": 68 |
|
}, |
|
{ |
|
"epoch": 1.3461538461538463, |
|
"grad_norm": 0.6580448746681213, |
|
"learning_rate": 3.071428571428572e-05, |
|
"loss": 0.649, |
|
"step": 70 |
|
}, |
|
{ |
|
"epoch": 1.3846153846153846, |
|
"grad_norm": 0.5795997381210327, |
|
"learning_rate": 3e-05, |
|
"loss": 0.0279, |
|
"step": 72 |
|
}, |
|
{ |
|
"epoch": 1.4230769230769231, |
|
"grad_norm": 3.1971044540405273, |
|
"learning_rate": 2.9285714285714288e-05, |
|
"loss": 0.471, |
|
"step": 74 |
|
}, |
|
{ |
|
"epoch": 1.4615384615384617, |
|
"grad_norm": 0.772407054901123, |
|
"learning_rate": 2.857142857142857e-05, |
|
"loss": 0.2271, |
|
"step": 76 |
|
}, |
|
{ |
|
"epoch": 1.5, |
|
"grad_norm": 0.8196155428886414, |
|
"learning_rate": 2.785714285714286e-05, |
|
"loss": 0.2429, |
|
"step": 78 |
|
}, |
|
{ |
|
"epoch": 1.5384615384615383, |
|
"grad_norm": 1.0081214904785156, |
|
"learning_rate": 2.714285714285714e-05, |
|
"loss": 0.2523, |
|
"step": 80 |
|
}, |
|
{ |
|
"epoch": 1.5769230769230769, |
|
"grad_norm": 0.9642893075942993, |
|
"learning_rate": 2.642857142857143e-05, |
|
"loss": 0.4355, |
|
"step": 82 |
|
}, |
|
{ |
|
"epoch": 1.6153846153846154, |
|
"grad_norm": 2.410957098007202, |
|
"learning_rate": 2.5714285714285714e-05, |
|
"loss": 0.213, |
|
"step": 84 |
|
}, |
|
{ |
|
"epoch": 1.6538461538461537, |
|
"grad_norm": 0.9146873950958252, |
|
"learning_rate": 2.5e-05, |
|
"loss": 0.1876, |
|
"step": 86 |
|
}, |
|
{ |
|
"epoch": 1.6923076923076923, |
|
"grad_norm": 1.0689085721969604, |
|
"learning_rate": 2.4285714285714288e-05, |
|
"loss": 0.0379, |
|
"step": 88 |
|
}, |
|
{ |
|
"epoch": 1.7307692307692308, |
|
"grad_norm": 5.386611461639404, |
|
"learning_rate": 2.357142857142857e-05, |
|
"loss": 0.6832, |
|
"step": 90 |
|
}, |
|
{ |
|
"epoch": 1.7692307692307692, |
|
"grad_norm": 6.125481605529785, |
|
"learning_rate": 2.2857142857142858e-05, |
|
"loss": 0.519, |
|
"step": 92 |
|
}, |
|
{ |
|
"epoch": 1.8076923076923077, |
|
"grad_norm": 10.108115196228027, |
|
"learning_rate": 2.214285714285714e-05, |
|
"loss": 0.4923, |
|
"step": 94 |
|
}, |
|
{ |
|
"epoch": 1.8461538461538463, |
|
"grad_norm": 1.2555135488510132, |
|
"learning_rate": 2.1428571428571428e-05, |
|
"loss": 0.0383, |
|
"step": 96 |
|
}, |
|
{ |
|
"epoch": 1.8846153846153846, |
|
"grad_norm": 2.7871651649475098, |
|
"learning_rate": 2.0714285714285718e-05, |
|
"loss": 0.2861, |
|
"step": 98 |
|
}, |
|
{ |
|
"epoch": 1.9230769230769231, |
|
"grad_norm": 3.00709867477417, |
|
"learning_rate": 2e-05, |
|
"loss": 0.2901, |
|
"step": 100 |
|
}, |
|
{ |
|
"epoch": 1.9615384615384617, |
|
"grad_norm": 0.6466115713119507, |
|
"learning_rate": 1.928571428571429e-05, |
|
"loss": 0.021, |
|
"step": 102 |
|
}, |
|
{ |
|
"epoch": 2.0, |
|
"grad_norm": 0.5404049158096313, |
|
"learning_rate": 1.8571428571428572e-05, |
|
"loss": 0.2653, |
|
"step": 104 |
|
}, |
|
{ |
|
"epoch": 2.0, |
|
"eval_accuracy": 0.9326923076923077, |
|
"eval_auc": 0.6833578792341679, |
|
"eval_f1": 0.0, |
|
"eval_loss": 0.2939682602882385, |
|
"eval_precision": 0.0, |
|
"eval_recall": 0.0, |
|
"eval_runtime": 1.3953, |
|
"eval_samples_per_second": 74.536, |
|
"eval_steps_per_second": 5.017, |
|
"step": 104 |
|
} |
|
], |
|
"logging_steps": 2, |
|
"max_steps": 156, |
|
"num_input_tokens_seen": 0, |
|
"num_train_epochs": 3, |
|
"save_steps": 500, |
|
"total_flos": 54595543987200.0, |
|
"train_batch_size": 8, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|