sekarmulyani's picture
Upload 11 files
20402e0
raw
history blame
8.73 kB
{
"best_metric": 0.49651709628372404,
"best_model_checkpoint": "./indobertweet-review-rating/checkpoint-28596",
"epoch": 4.0,
"eval_steps": 500,
"global_step": 28596,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.07,
"learning_rate": 1.9825150370681216e-05,
"loss": 0.43,
"step": 500
},
{
"epoch": 0.14,
"learning_rate": 1.965030074136243e-05,
"loss": 0.3942,
"step": 1000
},
{
"epoch": 0.21,
"learning_rate": 1.9475451112043644e-05,
"loss": 0.3869,
"step": 1500
},
{
"epoch": 0.28,
"learning_rate": 1.9300601482724858e-05,
"loss": 0.389,
"step": 2000
},
{
"epoch": 0.35,
"learning_rate": 1.9125751853406072e-05,
"loss": 0.3822,
"step": 2500
},
{
"epoch": 0.42,
"learning_rate": 1.8950902224087286e-05,
"loss": 0.3766,
"step": 3000
},
{
"epoch": 0.49,
"learning_rate": 1.87760525947685e-05,
"loss": 0.382,
"step": 3500
},
{
"epoch": 0.56,
"learning_rate": 1.8601202965449715e-05,
"loss": 0.3849,
"step": 4000
},
{
"epoch": 0.63,
"learning_rate": 1.842635333613093e-05,
"loss": 0.3761,
"step": 4500
},
{
"epoch": 0.7,
"learning_rate": 1.8251503706812143e-05,
"loss": 0.376,
"step": 5000
},
{
"epoch": 0.77,
"learning_rate": 1.8076654077493357e-05,
"loss": 0.3789,
"step": 5500
},
{
"epoch": 0.84,
"learning_rate": 1.790180444817457e-05,
"loss": 0.3677,
"step": 6000
},
{
"epoch": 0.91,
"learning_rate": 1.7726954818855785e-05,
"loss": 0.3728,
"step": 6500
},
{
"epoch": 0.98,
"learning_rate": 1.7552105189537e-05,
"loss": 0.3748,
"step": 7000
},
{
"epoch": 1.0,
"eval_akurasi": 0.3444364303980067,
"eval_f1": 0.4382533261041832,
"eval_loss": 0.37478938698768616,
"eval_roc_auc": 0.6437938495836338,
"eval_runtime": 259.2098,
"eval_samples_per_second": 58.837,
"eval_steps_per_second": 7.357,
"step": 7149
},
{
"epoch": 1.05,
"learning_rate": 1.7377255560218214e-05,
"loss": 0.356,
"step": 7500
},
{
"epoch": 1.12,
"learning_rate": 1.7202405930899428e-05,
"loss": 0.3519,
"step": 8000
},
{
"epoch": 1.19,
"learning_rate": 1.7027556301580642e-05,
"loss": 0.3475,
"step": 8500
},
{
"epoch": 1.26,
"learning_rate": 1.6852706672261856e-05,
"loss": 0.3497,
"step": 9000
},
{
"epoch": 1.33,
"learning_rate": 1.667785704294307e-05,
"loss": 0.3467,
"step": 9500
},
{
"epoch": 1.4,
"learning_rate": 1.6503007413624284e-05,
"loss": 0.3518,
"step": 10000
},
{
"epoch": 1.47,
"learning_rate": 1.63281577843055e-05,
"loss": 0.345,
"step": 10500
},
{
"epoch": 1.54,
"learning_rate": 1.6153308154986713e-05,
"loss": 0.3461,
"step": 11000
},
{
"epoch": 1.61,
"learning_rate": 1.5978458525667927e-05,
"loss": 0.3439,
"step": 11500
},
{
"epoch": 1.68,
"learning_rate": 1.580360889634914e-05,
"loss": 0.3465,
"step": 12000
},
{
"epoch": 1.75,
"learning_rate": 1.5628759267030355e-05,
"loss": 0.3478,
"step": 12500
},
{
"epoch": 1.82,
"learning_rate": 1.545390963771157e-05,
"loss": 0.3393,
"step": 13000
},
{
"epoch": 1.89,
"learning_rate": 1.5279060008392783e-05,
"loss": 0.3432,
"step": 13500
},
{
"epoch": 1.96,
"learning_rate": 1.5104210379073997e-05,
"loss": 0.3463,
"step": 14000
},
{
"epoch": 2.0,
"eval_akurasi": 0.38469608550259,
"eval_f1": 0.46908843863645444,
"eval_loss": 0.36731091141700745,
"eval_roc_auc": 0.6604239066290736,
"eval_runtime": 259.0823,
"eval_samples_per_second": 58.865,
"eval_steps_per_second": 7.361,
"step": 14298
},
{
"epoch": 2.03,
"learning_rate": 1.492936074975521e-05,
"loss": 0.3333,
"step": 14500
},
{
"epoch": 2.1,
"learning_rate": 1.4754511120436426e-05,
"loss": 0.3077,
"step": 15000
},
{
"epoch": 2.17,
"learning_rate": 1.457966149111764e-05,
"loss": 0.3109,
"step": 15500
},
{
"epoch": 2.24,
"learning_rate": 1.4404811861798856e-05,
"loss": 0.31,
"step": 16000
},
{
"epoch": 2.31,
"learning_rate": 1.4229962232480068e-05,
"loss": 0.3054,
"step": 16500
},
{
"epoch": 2.38,
"learning_rate": 1.4055112603161282e-05,
"loss": 0.3105,
"step": 17000
},
{
"epoch": 2.45,
"learning_rate": 1.3880262973842498e-05,
"loss": 0.3142,
"step": 17500
},
{
"epoch": 2.52,
"learning_rate": 1.370541334452371e-05,
"loss": 0.3097,
"step": 18000
},
{
"epoch": 2.59,
"learning_rate": 1.3530563715204925e-05,
"loss": 0.3145,
"step": 18500
},
{
"epoch": 2.66,
"learning_rate": 1.335571408588614e-05,
"loss": 0.3153,
"step": 19000
},
{
"epoch": 2.73,
"learning_rate": 1.3180864456567353e-05,
"loss": 0.3163,
"step": 19500
},
{
"epoch": 2.8,
"learning_rate": 1.3006014827248567e-05,
"loss": 0.3044,
"step": 20000
},
{
"epoch": 2.87,
"learning_rate": 1.2831165197929783e-05,
"loss": 0.3118,
"step": 20500
},
{
"epoch": 2.94,
"learning_rate": 1.2656315568610995e-05,
"loss": 0.3115,
"step": 21000
},
{
"epoch": 3.0,
"eval_akurasi": 0.4235787817192315,
"eval_f1": 0.4809589398056807,
"eval_loss": 0.3863948583602905,
"eval_roc_auc": 0.6695626516294014,
"eval_runtime": 258.9039,
"eval_samples_per_second": 58.906,
"eval_steps_per_second": 7.366,
"step": 21447
},
{
"epoch": 3.01,
"learning_rate": 1.248146593929221e-05,
"loss": 0.3029,
"step": 21500
},
{
"epoch": 3.08,
"learning_rate": 1.2306616309973425e-05,
"loss": 0.2587,
"step": 22000
},
{
"epoch": 3.15,
"learning_rate": 1.2131766680654638e-05,
"loss": 0.2592,
"step": 22500
},
{
"epoch": 3.22,
"learning_rate": 1.1956917051335852e-05,
"loss": 0.2679,
"step": 23000
},
{
"epoch": 3.29,
"learning_rate": 1.1782067422017068e-05,
"loss": 0.2645,
"step": 23500
},
{
"epoch": 3.36,
"learning_rate": 1.160721779269828e-05,
"loss": 0.2669,
"step": 24000
},
{
"epoch": 3.43,
"learning_rate": 1.1432368163379494e-05,
"loss": 0.2676,
"step": 24500
},
{
"epoch": 3.5,
"learning_rate": 1.125751853406071e-05,
"loss": 0.2683,
"step": 25000
},
{
"epoch": 3.57,
"learning_rate": 1.1082668904741923e-05,
"loss": 0.272,
"step": 25500
},
{
"epoch": 3.64,
"learning_rate": 1.0907819275423137e-05,
"loss": 0.2718,
"step": 26000
},
{
"epoch": 3.71,
"learning_rate": 1.0732969646104353e-05,
"loss": 0.2731,
"step": 26500
},
{
"epoch": 3.78,
"learning_rate": 1.0558120016785565e-05,
"loss": 0.2641,
"step": 27000
},
{
"epoch": 3.85,
"learning_rate": 1.0383270387466779e-05,
"loss": 0.2795,
"step": 27500
},
{
"epoch": 3.92,
"learning_rate": 1.0208420758147995e-05,
"loss": 0.2715,
"step": 28000
},
{
"epoch": 3.99,
"learning_rate": 1.0033571128829207e-05,
"loss": 0.2618,
"step": 28500
},
{
"epoch": 4.0,
"eval_akurasi": 0.45898629598059143,
"eval_f1": 0.49651709628372404,
"eval_loss": 0.43184059858322144,
"eval_roc_auc": 0.6809307586387777,
"eval_runtime": 259.0229,
"eval_samples_per_second": 58.879,
"eval_steps_per_second": 7.362,
"step": 28596
}
],
"logging_steps": 500,
"max_steps": 57192,
"num_train_epochs": 8,
"save_steps": 500,
"total_flos": 4.514475841140326e+16,
"trial_name": null,
"trial_params": null
}