Spaces:
Sleeping
Sleeping
| { | |
| "best_metric": 0.591158390045166, | |
| "best_model_checkpoint": "/home/ubuntu/lf_output_V12_locked_warmup/checkpoint-15189", | |
| "epoch": 90.0, | |
| "global_step": 455670, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 2.48e-07, | |
| "loss": 0.3185, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 4.98e-07, | |
| "loss": 0.3178, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 7.480000000000001e-07, | |
| "loss": 0.3206, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 9.98e-07, | |
| "loss": 0.3145, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 1.2475000000000001e-06, | |
| "loss": 0.3127, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 1.4975e-06, | |
| "loss": 0.3226, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 1.7470000000000002e-06, | |
| "loss": 0.3161, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 1.997e-06, | |
| "loss": 0.3184, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 2.2470000000000003e-06, | |
| "loss": 0.3248, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 2.4970000000000004e-06, | |
| "loss": 0.3276, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.8403498029009913, | |
| "eval_f1": 0.4677493043153217, | |
| "eval_loss": 0.5944358706474304, | |
| "eval_precision": 0.4114724150529777, | |
| "eval_recall": 0.5418591224018475, | |
| "eval_runtime": 23.8244, | |
| "eval_samples_per_second": 127.978, | |
| "eval_steps_per_second": 16.034, | |
| "step": 5063 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "learning_rate": 2.4975364053461002e-06, | |
| "loss": 0.3306, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "learning_rate": 2.4950428884899264e-06, | |
| "loss": 0.3286, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "learning_rate": 2.4925493716337525e-06, | |
| "loss": 0.3257, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "learning_rate": 2.4900558547775786e-06, | |
| "loss": 0.3242, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "learning_rate": 2.4875623379214043e-06, | |
| "loss": 0.3223, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 1.58, | |
| "learning_rate": 2.4850738080989428e-06, | |
| "loss": 0.3276, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 1.68, | |
| "learning_rate": 2.482580291242769e-06, | |
| "loss": 0.3321, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 1.78, | |
| "learning_rate": 2.480086774386595e-06, | |
| "loss": 0.3232, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 1.88, | |
| "learning_rate": 2.477593257530421e-06, | |
| "loss": 0.3214, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 1.98, | |
| "learning_rate": 2.4751047277079596e-06, | |
| "loss": 0.3293, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.8365149833518313, | |
| "eval_f1": 0.4657225216192505, | |
| "eval_loss": 0.6071960926055908, | |
| "eval_precision": 0.4115171650055371, | |
| "eval_recall": 0.5363741339491916, | |
| "eval_runtime": 24.2984, | |
| "eval_samples_per_second": 125.482, | |
| "eval_steps_per_second": 15.721, | |
| "step": 10126 | |
| }, | |
| { | |
| "epoch": 2.07, | |
| "learning_rate": 2.472616197885498e-06, | |
| "loss": 0.3365, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 2.17, | |
| "learning_rate": 2.4701226810293237e-06, | |
| "loss": 0.3266, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 2.27, | |
| "learning_rate": 2.4676291641731503e-06, | |
| "loss": 0.3354, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 2.37, | |
| "learning_rate": 2.465135647316976e-06, | |
| "loss": 0.3345, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 2.47, | |
| "learning_rate": 2.462642130460802e-06, | |
| "loss": 0.3273, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 2.57, | |
| "learning_rate": 2.4601536006383405e-06, | |
| "loss": 0.328, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 2.67, | |
| "learning_rate": 2.4576600837821667e-06, | |
| "loss": 0.3278, | |
| "step": 13500 | |
| }, | |
| { | |
| "epoch": 2.77, | |
| "learning_rate": 2.455166566925993e-06, | |
| "loss": 0.316, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 2.86, | |
| "learning_rate": 2.4526730500698185e-06, | |
| "loss": 0.3277, | |
| "step": 14500 | |
| }, | |
| { | |
| "epoch": 2.96, | |
| "learning_rate": 2.4501795332136446e-06, | |
| "loss": 0.3325, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.8391633816831873, | |
| "eval_f1": 0.4654475777898113, | |
| "eval_loss": 0.591158390045166, | |
| "eval_precision": 0.41035622475211164, | |
| "eval_recall": 0.5376250962278676, | |
| "eval_runtime": 24.0176, | |
| "eval_samples_per_second": 126.949, | |
| "eval_steps_per_second": 15.905, | |
| "step": 15189 | |
| }, | |
| { | |
| "epoch": 3.06, | |
| "learning_rate": 2.4476860163574707e-06, | |
| "loss": 0.3239, | |
| "step": 15500 | |
| }, | |
| { | |
| "epoch": 3.16, | |
| "learning_rate": 2.445192499501297e-06, | |
| "loss": 0.3314, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 3.26, | |
| "learning_rate": 2.4427039696788353e-06, | |
| "loss": 0.3241, | |
| "step": 16500 | |
| }, | |
| { | |
| "epoch": 3.36, | |
| "learning_rate": 2.4402104528226614e-06, | |
| "loss": 0.3135, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 3.46, | |
| "learning_rate": 2.437716935966487e-06, | |
| "loss": 0.3267, | |
| "step": 17500 | |
| }, | |
| { | |
| "epoch": 3.56, | |
| "learning_rate": 2.4352234191103133e-06, | |
| "loss": 0.3215, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 3.65, | |
| "learning_rate": 2.4327299022541394e-06, | |
| "loss": 0.315, | |
| "step": 18500 | |
| }, | |
| { | |
| "epoch": 3.75, | |
| "learning_rate": 2.4302363853979655e-06, | |
| "loss": 0.323, | |
| "step": 19000 | |
| }, | |
| { | |
| "epoch": 3.85, | |
| "learning_rate": 2.427742868541791e-06, | |
| "loss": 0.3224, | |
| "step": 19500 | |
| }, | |
| { | |
| "epoch": 3.95, | |
| "learning_rate": 2.4252493516856178e-06, | |
| "loss": 0.3183, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.8383711584829117, | |
| "eval_f1": 0.4724905501889962, | |
| "eval_loss": 0.5957902669906616, | |
| "eval_precision": 0.4192129974660903, | |
| "eval_recall": 0.5412817551963048, | |
| "eval_runtime": 23.7397, | |
| "eval_samples_per_second": 128.435, | |
| "eval_steps_per_second": 16.091, | |
| "step": 20252 | |
| }, | |
| { | |
| "epoch": 4.05, | |
| "learning_rate": 2.4227658088968685e-06, | |
| "loss": 0.3154, | |
| "step": 20500 | |
| }, | |
| { | |
| "epoch": 4.15, | |
| "learning_rate": 2.4202722920406942e-06, | |
| "loss": 0.319, | |
| "step": 21000 | |
| }, | |
| { | |
| "epoch": 4.25, | |
| "learning_rate": 2.4177787751845203e-06, | |
| "loss": 0.3196, | |
| "step": 21500 | |
| }, | |
| { | |
| "epoch": 4.35, | |
| "learning_rate": 2.4152852583283465e-06, | |
| "loss": 0.3197, | |
| "step": 22000 | |
| }, | |
| { | |
| "epoch": 4.44, | |
| "learning_rate": 2.4127917414721726e-06, | |
| "loss": 0.3256, | |
| "step": 22500 | |
| }, | |
| { | |
| "epoch": 4.54, | |
| "learning_rate": 2.4102982246159987e-06, | |
| "loss": 0.3183, | |
| "step": 23000 | |
| }, | |
| { | |
| "epoch": 4.64, | |
| "learning_rate": 2.407809694793537e-06, | |
| "loss": 0.3209, | |
| "step": 23500 | |
| }, | |
| { | |
| "epoch": 4.74, | |
| "learning_rate": 2.405316177937363e-06, | |
| "loss": 0.3317, | |
| "step": 24000 | |
| }, | |
| { | |
| "epoch": 4.84, | |
| "learning_rate": 2.402822661081189e-06, | |
| "loss": 0.3144, | |
| "step": 24500 | |
| }, | |
| { | |
| "epoch": 4.94, | |
| "learning_rate": 2.400329144225015e-06, | |
| "loss": 0.312, | |
| "step": 25000 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.8374870833173869, | |
| "eval_f1": 0.4686698121016472, | |
| "eval_loss": 0.6015240550041199, | |
| "eval_precision": 0.4111837327523602, | |
| "eval_recall": 0.5448421862971516, | |
| "eval_runtime": 24.0516, | |
| "eval_samples_per_second": 126.769, | |
| "eval_steps_per_second": 15.883, | |
| "step": 25315 | |
| }, | |
| { | |
| "epoch": 5.04, | |
| "learning_rate": 2.3978356273688412e-06, | |
| "loss": 0.323, | |
| "step": 25500 | |
| }, | |
| { | |
| "epoch": 5.14, | |
| "learning_rate": 2.3953421105126674e-06, | |
| "loss": 0.325, | |
| "step": 26000 | |
| }, | |
| { | |
| "epoch": 5.23, | |
| "learning_rate": 2.392848593656493e-06, | |
| "loss": 0.3243, | |
| "step": 26500 | |
| }, | |
| { | |
| "epoch": 5.33, | |
| "learning_rate": 2.390360063834032e-06, | |
| "loss": 0.3281, | |
| "step": 27000 | |
| }, | |
| { | |
| "epoch": 5.43, | |
| "learning_rate": 2.3878665469778576e-06, | |
| "loss": 0.3126, | |
| "step": 27500 | |
| }, | |
| { | |
| "epoch": 5.53, | |
| "learning_rate": 2.3853730301216838e-06, | |
| "loss": 0.3271, | |
| "step": 28000 | |
| }, | |
| { | |
| "epoch": 5.63, | |
| "learning_rate": 2.38287951326551e-06, | |
| "loss": 0.3153, | |
| "step": 28500 | |
| }, | |
| { | |
| "epoch": 5.73, | |
| "learning_rate": 2.380385996409336e-06, | |
| "loss": 0.3243, | |
| "step": 29000 | |
| }, | |
| { | |
| "epoch": 5.83, | |
| "learning_rate": 2.3778924795531617e-06, | |
| "loss": 0.3068, | |
| "step": 29500 | |
| }, | |
| { | |
| "epoch": 5.93, | |
| "learning_rate": 2.3753989626969883e-06, | |
| "loss": 0.3108, | |
| "step": 30000 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.8403842473879597, | |
| "eval_f1": 0.47207586933614337, | |
| "eval_loss": 0.60483717918396, | |
| "eval_precision": 0.4200105002625066, | |
| "eval_recall": 0.5388760585065435, | |
| "eval_runtime": 24.2316, | |
| "eval_samples_per_second": 125.828, | |
| "eval_steps_per_second": 15.765, | |
| "step": 30378 | |
| }, | |
| { | |
| "epoch": 6.02, | |
| "learning_rate": 2.372905445840814e-06, | |
| "loss": 0.3109, | |
| "step": 30500 | |
| }, | |
| { | |
| "epoch": 6.12, | |
| "learning_rate": 2.3704169160183524e-06, | |
| "loss": 0.308, | |
| "step": 31000 | |
| }, | |
| { | |
| "epoch": 6.22, | |
| "learning_rate": 2.367928386195891e-06, | |
| "loss": 0.3135, | |
| "step": 31500 | |
| }, | |
| { | |
| "epoch": 6.32, | |
| "learning_rate": 2.365434869339717e-06, | |
| "loss": 0.3175, | |
| "step": 32000 | |
| }, | |
| { | |
| "epoch": 6.42, | |
| "learning_rate": 2.362941352483543e-06, | |
| "loss": 0.3083, | |
| "step": 32500 | |
| }, | |
| { | |
| "epoch": 6.52, | |
| "learning_rate": 2.3604478356273692e-06, | |
| "loss": 0.3176, | |
| "step": 33000 | |
| }, | |
| { | |
| "epoch": 6.62, | |
| "learning_rate": 2.3579593058049072e-06, | |
| "loss": 0.3176, | |
| "step": 33500 | |
| }, | |
| { | |
| "epoch": 6.72, | |
| "learning_rate": 2.3554657889487334e-06, | |
| "loss": 0.3123, | |
| "step": 34000 | |
| }, | |
| { | |
| "epoch": 6.81, | |
| "learning_rate": 2.3529722720925595e-06, | |
| "loss": 0.317, | |
| "step": 34500 | |
| }, | |
| { | |
| "epoch": 6.91, | |
| "learning_rate": 2.3504787552363856e-06, | |
| "loss": 0.3041, | |
| "step": 35000 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_accuracy": 0.8368594282215164, | |
| "eval_f1": 0.4661911316898177, | |
| "eval_loss": 0.617274284362793, | |
| "eval_precision": 0.4114571828289522, | |
| "eval_recall": 0.537721324095458, | |
| "eval_runtime": 23.4998, | |
| "eval_samples_per_second": 129.746, | |
| "eval_steps_per_second": 16.255, | |
| "step": 35441 | |
| }, | |
| { | |
| "epoch": 7.01, | |
| "learning_rate": 2.3479852383802117e-06, | |
| "loss": 0.3207, | |
| "step": 35500 | |
| }, | |
| { | |
| "epoch": 7.11, | |
| "learning_rate": 2.345491721524038e-06, | |
| "loss": 0.3163, | |
| "step": 36000 | |
| }, | |
| { | |
| "epoch": 7.21, | |
| "learning_rate": 2.3429982046678636e-06, | |
| "loss": 0.3053, | |
| "step": 36500 | |
| }, | |
| { | |
| "epoch": 7.31, | |
| "learning_rate": 2.34050468781169e-06, | |
| "loss": 0.3114, | |
| "step": 37000 | |
| }, | |
| { | |
| "epoch": 7.41, | |
| "learning_rate": 2.338011170955516e-06, | |
| "loss": 0.3071, | |
| "step": 37500 | |
| }, | |
| { | |
| "epoch": 7.51, | |
| "learning_rate": 2.335517654099342e-06, | |
| "loss": 0.3131, | |
| "step": 38000 | |
| }, | |
| { | |
| "epoch": 7.6, | |
| "learning_rate": 2.333024137243168e-06, | |
| "loss": 0.3149, | |
| "step": 38500 | |
| }, | |
| { | |
| "epoch": 7.7, | |
| "learning_rate": 2.330530620386994e-06, | |
| "loss": 0.3185, | |
| "step": 39000 | |
| }, | |
| { | |
| "epoch": 7.8, | |
| "learning_rate": 2.32803710353082e-06, | |
| "loss": 0.3135, | |
| "step": 39500 | |
| }, | |
| { | |
| "epoch": 7.9, | |
| "learning_rate": 2.3255535607420706e-06, | |
| "loss": 0.3119, | |
| "step": 40000 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "learning_rate": 2.3230600438858968e-06, | |
| "loss": 0.3154, | |
| "step": 40500 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.834505721612002, | |
| "eval_f1": 0.46665559338925333, | |
| "eval_loss": 0.6168600916862488, | |
| "eval_precision": 0.41044558071585097, | |
| "eval_recall": 0.5407043879907621, | |
| "eval_runtime": 24.2307, | |
| "eval_samples_per_second": 125.832, | |
| "eval_steps_per_second": 15.765, | |
| "step": 40504 | |
| }, | |
| { | |
| "epoch": 8.1, | |
| "learning_rate": 2.320566527029723e-06, | |
| "loss": 0.3061, | |
| "step": 41000 | |
| }, | |
| { | |
| "epoch": 8.2, | |
| "learning_rate": 2.318073010173549e-06, | |
| "loss": 0.3099, | |
| "step": 41500 | |
| }, | |
| { | |
| "epoch": 8.3, | |
| "learning_rate": 2.315579493317375e-06, | |
| "loss": 0.3216, | |
| "step": 42000 | |
| }, | |
| { | |
| "epoch": 8.39, | |
| "learning_rate": 2.313085976461201e-06, | |
| "loss": 0.3064, | |
| "step": 42500 | |
| }, | |
| { | |
| "epoch": 8.49, | |
| "learning_rate": 2.3105924596050274e-06, | |
| "loss": 0.3075, | |
| "step": 43000 | |
| }, | |
| { | |
| "epoch": 8.59, | |
| "learning_rate": 2.308098942748853e-06, | |
| "loss": 0.3126, | |
| "step": 43500 | |
| }, | |
| { | |
| "epoch": 8.69, | |
| "learning_rate": 2.3056104129263915e-06, | |
| "loss": 0.3141, | |
| "step": 44000 | |
| }, | |
| { | |
| "epoch": 8.79, | |
| "learning_rate": 2.3031168960702177e-06, | |
| "loss": 0.3132, | |
| "step": 44500 | |
| }, | |
| { | |
| "epoch": 8.89, | |
| "learning_rate": 2.300623379214044e-06, | |
| "loss": 0.3156, | |
| "step": 45000 | |
| }, | |
| { | |
| "epoch": 8.99, | |
| "learning_rate": 2.298134849391582e-06, | |
| "loss": 0.313, | |
| "step": 45500 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_accuracy": 0.8388112824830648, | |
| "eval_f1": 0.467983144674874, | |
| "eval_loss": 0.6226583123207092, | |
| "eval_precision": 0.41001882148544955, | |
| "eval_recall": 0.5450346420323325, | |
| "eval_runtime": 23.4782, | |
| "eval_samples_per_second": 129.865, | |
| "eval_steps_per_second": 16.27, | |
| "step": 45567 | |
| }, | |
| { | |
| "epoch": 9.09, | |
| "learning_rate": 2.2956413325354084e-06, | |
| "loss": 0.3038, | |
| "step": 46000 | |
| }, | |
| { | |
| "epoch": 9.18, | |
| "learning_rate": 2.293147815679234e-06, | |
| "loss": 0.3101, | |
| "step": 46500 | |
| }, | |
| { | |
| "epoch": 9.28, | |
| "learning_rate": 2.29065429882306e-06, | |
| "loss": 0.3245, | |
| "step": 47000 | |
| }, | |
| { | |
| "epoch": 9.38, | |
| "learning_rate": 2.2881607819668863e-06, | |
| "loss": 0.3215, | |
| "step": 47500 | |
| }, | |
| { | |
| "epoch": 9.48, | |
| "learning_rate": 2.2856672651107124e-06, | |
| "loss": 0.316, | |
| "step": 48000 | |
| }, | |
| { | |
| "epoch": 9.58, | |
| "learning_rate": 2.2831737482545386e-06, | |
| "loss": 0.3109, | |
| "step": 48500 | |
| }, | |
| { | |
| "epoch": 9.68, | |
| "learning_rate": 2.2806802313983647e-06, | |
| "loss": 0.3119, | |
| "step": 49000 | |
| }, | |
| { | |
| "epoch": 9.78, | |
| "learning_rate": 2.2781867145421904e-06, | |
| "loss": 0.3092, | |
| "step": 49500 | |
| }, | |
| { | |
| "epoch": 9.88, | |
| "learning_rate": 2.275703171753441e-06, | |
| "loss": 0.3061, | |
| "step": 50000 | |
| }, | |
| { | |
| "epoch": 9.97, | |
| "learning_rate": 2.2732096548972673e-06, | |
| "loss": 0.3205, | |
| "step": 50500 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_accuracy": 0.8380420222741016, | |
| "eval_f1": 0.4691952972456483, | |
| "eval_loss": 0.607540488243103, | |
| "eval_precision": 0.4128225747496162, | |
| "eval_recall": 0.5433987682832948, | |
| "eval_runtime": 23.5452, | |
| "eval_samples_per_second": 129.496, | |
| "eval_steps_per_second": 16.224, | |
| "step": 50630 | |
| }, | |
| { | |
| "epoch": 10.07, | |
| "learning_rate": 2.2707161380410934e-06, | |
| "loss": 0.2944, | |
| "step": 51000 | |
| }, | |
| { | |
| "epoch": 10.17, | |
| "learning_rate": 2.268222621184919e-06, | |
| "loss": 0.3022, | |
| "step": 51500 | |
| }, | |
| { | |
| "epoch": 10.27, | |
| "learning_rate": 2.2657291043287456e-06, | |
| "loss": 0.3006, | |
| "step": 52000 | |
| }, | |
| { | |
| "epoch": 10.37, | |
| "learning_rate": 2.2632355874725713e-06, | |
| "loss": 0.3047, | |
| "step": 52500 | |
| }, | |
| { | |
| "epoch": 10.47, | |
| "learning_rate": 2.2607420706163975e-06, | |
| "loss": 0.3105, | |
| "step": 53000 | |
| }, | |
| { | |
| "epoch": 10.57, | |
| "learning_rate": 2.2582485537602236e-06, | |
| "loss": 0.3173, | |
| "step": 53500 | |
| }, | |
| { | |
| "epoch": 10.67, | |
| "learning_rate": 2.2557550369040497e-06, | |
| "loss": 0.3052, | |
| "step": 54000 | |
| }, | |
| { | |
| "epoch": 10.76, | |
| "learning_rate": 2.253261520047876e-06, | |
| "loss": 0.2972, | |
| "step": 54500 | |
| }, | |
| { | |
| "epoch": 10.86, | |
| "learning_rate": 2.2507779772591266e-06, | |
| "loss": 0.299, | |
| "step": 55000 | |
| }, | |
| { | |
| "epoch": 10.96, | |
| "learning_rate": 2.2482844604029523e-06, | |
| "loss": 0.3055, | |
| "step": 55500 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_accuracy": 0.8372344904129512, | |
| "eval_f1": 0.4717340848806366, | |
| "eval_loss": 0.6190317869186401, | |
| "eval_precision": 0.41431275480489227, | |
| "eval_recall": 0.5476327944572749, | |
| "eval_runtime": 24.5177, | |
| "eval_samples_per_second": 124.359, | |
| "eval_steps_per_second": 15.581, | |
| "step": 55693 | |
| }, | |
| { | |
| "epoch": 11.06, | |
| "learning_rate": 2.245790943546779e-06, | |
| "loss": 0.3127, | |
| "step": 56000 | |
| }, | |
| { | |
| "epoch": 11.16, | |
| "learning_rate": 2.2432974266906046e-06, | |
| "loss": 0.3065, | |
| "step": 56500 | |
| }, | |
| { | |
| "epoch": 11.26, | |
| "learning_rate": 2.2408039098344307e-06, | |
| "loss": 0.3004, | |
| "step": 57000 | |
| }, | |
| { | |
| "epoch": 11.36, | |
| "learning_rate": 2.238310392978257e-06, | |
| "loss": 0.2948, | |
| "step": 57500 | |
| }, | |
| { | |
| "epoch": 11.46, | |
| "learning_rate": 2.235816876122083e-06, | |
| "loss": 0.2973, | |
| "step": 58000 | |
| }, | |
| { | |
| "epoch": 11.55, | |
| "learning_rate": 2.2333233592659086e-06, | |
| "loss": 0.3115, | |
| "step": 58500 | |
| }, | |
| { | |
| "epoch": 11.65, | |
| "learning_rate": 2.2308298424097348e-06, | |
| "loss": 0.3011, | |
| "step": 59000 | |
| }, | |
| { | |
| "epoch": 11.75, | |
| "learning_rate": 2.228341312587273e-06, | |
| "loss": 0.3096, | |
| "step": 59500 | |
| }, | |
| { | |
| "epoch": 11.85, | |
| "learning_rate": 2.2258527827648116e-06, | |
| "loss": 0.3055, | |
| "step": 60000 | |
| }, | |
| { | |
| "epoch": 11.95, | |
| "learning_rate": 2.2233592659086378e-06, | |
| "loss": 0.3054, | |
| "step": 60500 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_accuracy": 0.8388572084656895, | |
| "eval_f1": 0.4739519825085145, | |
| "eval_loss": 0.627370297908783, | |
| "eval_precision": 0.4208796953177507, | |
| "eval_recall": 0.5423402617397999, | |
| "eval_runtime": 24.2182, | |
| "eval_samples_per_second": 125.897, | |
| "eval_steps_per_second": 15.773, | |
| "step": 60756 | |
| }, | |
| { | |
| "epoch": 12.05, | |
| "learning_rate": 2.220865749052464e-06, | |
| "loss": 0.2957, | |
| "step": 61000 | |
| }, | |
| { | |
| "epoch": 12.15, | |
| "learning_rate": 2.2183722321962896e-06, | |
| "loss": 0.3049, | |
| "step": 61500 | |
| }, | |
| { | |
| "epoch": 12.25, | |
| "learning_rate": 2.215878715340116e-06, | |
| "loss": 0.2989, | |
| "step": 62000 | |
| }, | |
| { | |
| "epoch": 12.34, | |
| "learning_rate": 2.213385198483942e-06, | |
| "loss": 0.3047, | |
| "step": 62500 | |
| }, | |
| { | |
| "epoch": 12.44, | |
| "learning_rate": 2.210891681627768e-06, | |
| "loss": 0.3031, | |
| "step": 63000 | |
| }, | |
| { | |
| "epoch": 12.54, | |
| "learning_rate": 2.208398164771594e-06, | |
| "loss": 0.2882, | |
| "step": 63500 | |
| }, | |
| { | |
| "epoch": 12.64, | |
| "learning_rate": 2.2059046479154202e-06, | |
| "loss": 0.3107, | |
| "step": 64000 | |
| }, | |
| { | |
| "epoch": 12.74, | |
| "learning_rate": 2.2034161180929582e-06, | |
| "loss": 0.3006, | |
| "step": 64500 | |
| }, | |
| { | |
| "epoch": 12.84, | |
| "learning_rate": 2.2009226012367848e-06, | |
| "loss": 0.297, | |
| "step": 65000 | |
| }, | |
| { | |
| "epoch": 12.94, | |
| "learning_rate": 2.1984290843806105e-06, | |
| "loss": 0.3023, | |
| "step": 65500 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_accuracy": 0.8370890581346396, | |
| "eval_f1": 0.47168787815564367, | |
| "eval_loss": 0.6190006732940674, | |
| "eval_precision": 0.4164149414278347, | |
| "eval_recall": 0.5438799076212472, | |
| "eval_runtime": 24.4283, | |
| "eval_samples_per_second": 124.814, | |
| "eval_steps_per_second": 15.638, | |
| "step": 65819 | |
| }, | |
| { | |
| "epoch": 13.04, | |
| "learning_rate": 2.195940554558149e-06, | |
| "loss": 0.3061, | |
| "step": 66000 | |
| }, | |
| { | |
| "epoch": 13.13, | |
| "learning_rate": 2.193447037701975e-06, | |
| "loss": 0.3053, | |
| "step": 66500 | |
| }, | |
| { | |
| "epoch": 13.23, | |
| "learning_rate": 2.190953520845801e-06, | |
| "loss": 0.3003, | |
| "step": 67000 | |
| }, | |
| { | |
| "epoch": 13.33, | |
| "learning_rate": 2.1884600039896273e-06, | |
| "loss": 0.2951, | |
| "step": 67500 | |
| }, | |
| { | |
| "epoch": 13.43, | |
| "learning_rate": 2.1859664871334534e-06, | |
| "loss": 0.2988, | |
| "step": 68000 | |
| }, | |
| { | |
| "epoch": 13.53, | |
| "learning_rate": 2.183472970277279e-06, | |
| "loss": 0.2967, | |
| "step": 68500 | |
| }, | |
| { | |
| "epoch": 13.63, | |
| "learning_rate": 2.1809794534211052e-06, | |
| "loss": 0.2943, | |
| "step": 69000 | |
| }, | |
| { | |
| "epoch": 13.73, | |
| "learning_rate": 2.1784909235986437e-06, | |
| "loss": 0.293, | |
| "step": 69500 | |
| }, | |
| { | |
| "epoch": 13.83, | |
| "learning_rate": 2.17599740674247e-06, | |
| "loss": 0.2929, | |
| "step": 70000 | |
| }, | |
| { | |
| "epoch": 13.92, | |
| "learning_rate": 2.173503889886296e-06, | |
| "loss": 0.3002, | |
| "step": 70500 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_accuracy": 0.8366718971257989, | |
| "eval_f1": 0.46755174404221983, | |
| "eval_loss": 0.6290284991264343, | |
| "eval_precision": 0.40903188573077476, | |
| "eval_recall": 0.5456120092378753, | |
| "eval_runtime": 24.3972, | |
| "eval_samples_per_second": 124.973, | |
| "eval_steps_per_second": 15.658, | |
| "step": 70882 | |
| }, | |
| { | |
| "epoch": 14.02, | |
| "learning_rate": 2.1710103730301216e-06, | |
| "loss": 0.3033, | |
| "step": 71000 | |
| }, | |
| { | |
| "epoch": 14.12, | |
| "learning_rate": 2.1685168561739478e-06, | |
| "loss": 0.2906, | |
| "step": 71500 | |
| }, | |
| { | |
| "epoch": 14.22, | |
| "learning_rate": 2.166023339317774e-06, | |
| "loss": 0.294, | |
| "step": 72000 | |
| }, | |
| { | |
| "epoch": 14.32, | |
| "learning_rate": 2.1635298224616e-06, | |
| "loss": 0.2994, | |
| "step": 72500 | |
| }, | |
| { | |
| "epoch": 14.42, | |
| "learning_rate": 2.161036305605426e-06, | |
| "loss": 0.2927, | |
| "step": 73000 | |
| }, | |
| { | |
| "epoch": 14.52, | |
| "learning_rate": 2.1585427887492523e-06, | |
| "loss": 0.3221, | |
| "step": 73500 | |
| }, | |
| { | |
| "epoch": 14.62, | |
| "learning_rate": 2.156049271893078e-06, | |
| "loss": 0.294, | |
| "step": 74000 | |
| }, | |
| { | |
| "epoch": 14.71, | |
| "learning_rate": 2.1535607420706164e-06, | |
| "loss": 0.292, | |
| "step": 74500 | |
| }, | |
| { | |
| "epoch": 14.81, | |
| "learning_rate": 2.1510672252144425e-06, | |
| "loss": 0.2976, | |
| "step": 75000 | |
| }, | |
| { | |
| "epoch": 14.91, | |
| "learning_rate": 2.1485737083582687e-06, | |
| "loss": 0.2959, | |
| "step": 75500 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "eval_accuracy": 0.8372536262390448, | |
| "eval_f1": 0.4673331397519393, | |
| "eval_loss": 0.6437515020370483, | |
| "eval_precision": 0.4107181917608458, | |
| "eval_recall": 0.5420515781370285, | |
| "eval_runtime": 24.1488, | |
| "eval_samples_per_second": 126.259, | |
| "eval_steps_per_second": 15.819, | |
| "step": 75945 | |
| }, | |
| { | |
| "epoch": 15.01, | |
| "learning_rate": 2.1460801915020948e-06, | |
| "loss": 0.2922, | |
| "step": 76000 | |
| }, | |
| { | |
| "epoch": 15.11, | |
| "learning_rate": 2.1435916616796332e-06, | |
| "loss": 0.2853, | |
| "step": 76500 | |
| }, | |
| { | |
| "epoch": 15.21, | |
| "learning_rate": 2.141098144823459e-06, | |
| "loss": 0.2995, | |
| "step": 77000 | |
| }, | |
| { | |
| "epoch": 15.31, | |
| "learning_rate": 2.1386046279672855e-06, | |
| "loss": 0.2983, | |
| "step": 77500 | |
| }, | |
| { | |
| "epoch": 15.41, | |
| "learning_rate": 2.136111111111111e-06, | |
| "loss": 0.2869, | |
| "step": 78000 | |
| }, | |
| { | |
| "epoch": 15.5, | |
| "learning_rate": 2.1336225812886496e-06, | |
| "loss": 0.2956, | |
| "step": 78500 | |
| }, | |
| { | |
| "epoch": 15.6, | |
| "learning_rate": 2.1311290644324757e-06, | |
| "loss": 0.2963, | |
| "step": 79000 | |
| }, | |
| { | |
| "epoch": 15.7, | |
| "learning_rate": 2.128635547576302e-06, | |
| "loss": 0.2911, | |
| "step": 79500 | |
| }, | |
| { | |
| "epoch": 15.8, | |
| "learning_rate": 2.1261420307201276e-06, | |
| "loss": 0.2931, | |
| "step": 80000 | |
| }, | |
| { | |
| "epoch": 15.9, | |
| "learning_rate": 2.1236535008976664e-06, | |
| "loss": 0.2867, | |
| "step": 80500 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "learning_rate": 2.121159984041492e-06, | |
| "loss": 0.3072, | |
| "step": 81000 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_accuracy": 0.8390447395614069, | |
| "eval_f1": 0.4751165113182424, | |
| "eval_loss": 0.6363312602043152, | |
| "eval_precision": 0.41854838709677417, | |
| "eval_recall": 0.549364896073903, | |
| "eval_runtime": 24.5371, | |
| "eval_samples_per_second": 124.261, | |
| "eval_steps_per_second": 15.568, | |
| "step": 81008 | |
| }, | |
| { | |
| "epoch": 16.1, | |
| "learning_rate": 2.1186714542190306e-06, | |
| "loss": 0.3032, | |
| "step": 81500 | |
| }, | |
| { | |
| "epoch": 16.2, | |
| "learning_rate": 2.1161779373628567e-06, | |
| "loss": 0.2825, | |
| "step": 82000 | |
| }, | |
| { | |
| "epoch": 16.29, | |
| "learning_rate": 2.113684420506683e-06, | |
| "loss": 0.3021, | |
| "step": 82500 | |
| }, | |
| { | |
| "epoch": 16.39, | |
| "learning_rate": 2.1111958906842213e-06, | |
| "loss": 0.2898, | |
| "step": 83000 | |
| }, | |
| { | |
| "epoch": 16.49, | |
| "learning_rate": 2.1087023738280474e-06, | |
| "loss": 0.2983, | |
| "step": 83500 | |
| }, | |
| { | |
| "epoch": 16.59, | |
| "learning_rate": 2.1062088569718735e-06, | |
| "loss": 0.2914, | |
| "step": 84000 | |
| }, | |
| { | |
| "epoch": 16.69, | |
| "learning_rate": 2.1037153401156992e-06, | |
| "loss": 0.2878, | |
| "step": 84500 | |
| }, | |
| { | |
| "epoch": 16.79, | |
| "learning_rate": 2.1012218232595253e-06, | |
| "loss": 0.2899, | |
| "step": 85000 | |
| }, | |
| { | |
| "epoch": 16.89, | |
| "learning_rate": 2.0987283064033515e-06, | |
| "loss": 0.2821, | |
| "step": 85500 | |
| }, | |
| { | |
| "epoch": 16.99, | |
| "learning_rate": 2.0962347895471776e-06, | |
| "loss": 0.2922, | |
| "step": 86000 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "eval_accuracy": 0.8359906617168663, | |
| "eval_f1": 0.47037298848184955, | |
| "eval_loss": 0.6440777778625488, | |
| "eval_precision": 0.4141465914915428, | |
| "eval_recall": 0.544264819091609, | |
| "eval_runtime": 23.6318, | |
| "eval_samples_per_second": 129.021, | |
| "eval_steps_per_second": 16.165, | |
| "step": 86071 | |
| }, | |
| { | |
| "epoch": 17.08, | |
| "learning_rate": 2.0937412726910037e-06, | |
| "loss": 0.2905, | |
| "step": 86500 | |
| }, | |
| { | |
| "epoch": 17.18, | |
| "learning_rate": 2.0912477558348294e-06, | |
| "loss": 0.2984, | |
| "step": 87000 | |
| }, | |
| { | |
| "epoch": 17.28, | |
| "learning_rate": 2.0887542389786555e-06, | |
| "loss": 0.2914, | |
| "step": 87500 | |
| }, | |
| { | |
| "epoch": 17.38, | |
| "learning_rate": 2.0862607221224817e-06, | |
| "loss": 0.2974, | |
| "step": 88000 | |
| }, | |
| { | |
| "epoch": 17.48, | |
| "learning_rate": 2.083767205266308e-06, | |
| "loss": 0.2833, | |
| "step": 88500 | |
| }, | |
| { | |
| "epoch": 17.58, | |
| "learning_rate": 2.081273688410134e-06, | |
| "loss": 0.2928, | |
| "step": 89000 | |
| }, | |
| { | |
| "epoch": 17.68, | |
| "learning_rate": 2.07878017155396e-06, | |
| "loss": 0.2865, | |
| "step": 89500 | |
| }, | |
| { | |
| "epoch": 17.78, | |
| "learning_rate": 2.076291641731498e-06, | |
| "loss": 0.2916, | |
| "step": 90000 | |
| }, | |
| { | |
| "epoch": 17.87, | |
| "learning_rate": 2.0737981248753246e-06, | |
| "loss": 0.29, | |
| "step": 90500 | |
| }, | |
| { | |
| "epoch": 17.97, | |
| "learning_rate": 2.0713046080191503e-06, | |
| "loss": 0.2917, | |
| "step": 91000 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "eval_accuracy": 0.8377128860652915, | |
| "eval_f1": 0.47028940245679784, | |
| "eval_loss": 0.6375299096107483, | |
| "eval_precision": 0.4145195625045878, | |
| "eval_recall": 0.5433987682832948, | |
| "eval_runtime": 23.5063, | |
| "eval_samples_per_second": 129.71, | |
| "eval_steps_per_second": 16.251, | |
| "step": 91134 | |
| }, | |
| { | |
| "epoch": 18.07, | |
| "learning_rate": 2.0688110911629764e-06, | |
| "loss": 0.2896, | |
| "step": 91500 | |
| }, | |
| { | |
| "epoch": 18.17, | |
| "learning_rate": 2.066322561340515e-06, | |
| "loss": 0.2799, | |
| "step": 92000 | |
| }, | |
| { | |
| "epoch": 18.27, | |
| "learning_rate": 2.063829044484341e-06, | |
| "loss": 0.2841, | |
| "step": 92500 | |
| }, | |
| { | |
| "epoch": 18.37, | |
| "learning_rate": 2.0613355276281667e-06, | |
| "loss": 0.2844, | |
| "step": 93000 | |
| }, | |
| { | |
| "epoch": 18.47, | |
| "learning_rate": 2.0588420107719933e-06, | |
| "loss": 0.29, | |
| "step": 93500 | |
| }, | |
| { | |
| "epoch": 18.57, | |
| "learning_rate": 2.056348493915819e-06, | |
| "loss": 0.2793, | |
| "step": 94000 | |
| }, | |
| { | |
| "epoch": 18.66, | |
| "learning_rate": 2.0538599640933574e-06, | |
| "loss": 0.2849, | |
| "step": 94500 | |
| }, | |
| { | |
| "epoch": 18.76, | |
| "learning_rate": 2.0513664472371835e-06, | |
| "loss": 0.3024, | |
| "step": 95000 | |
| }, | |
| { | |
| "epoch": 18.86, | |
| "learning_rate": 2.0488729303810097e-06, | |
| "loss": 0.2812, | |
| "step": 95500 | |
| }, | |
| { | |
| "epoch": 18.96, | |
| "learning_rate": 2.0463794135248354e-06, | |
| "loss": 0.2902, | |
| "step": 96000 | |
| }, | |
| { | |
| "epoch": 19.0, | |
| "eval_accuracy": 0.8378315281870719, | |
| "eval_f1": 0.473609487222315, | |
| "eval_loss": 0.6511485576629639, | |
| "eval_precision": 0.41833874299203305, | |
| "eval_recall": 0.5457082371054658, | |
| "eval_runtime": 24.4979, | |
| "eval_samples_per_second": 124.459, | |
| "eval_steps_per_second": 15.593, | |
| "step": 96197 | |
| }, | |
| { | |
| "epoch": 19.06, | |
| "learning_rate": 2.043885896668662e-06, | |
| "loss": 0.3001, | |
| "step": 96500 | |
| }, | |
| { | |
| "epoch": 19.16, | |
| "learning_rate": 2.0413973668462e-06, | |
| "loss": 0.2863, | |
| "step": 97000 | |
| }, | |
| { | |
| "epoch": 19.26, | |
| "learning_rate": 2.038903849990026e-06, | |
| "loss": 0.2861, | |
| "step": 97500 | |
| }, | |
| { | |
| "epoch": 19.36, | |
| "learning_rate": 2.036410333133852e-06, | |
| "loss": 0.2863, | |
| "step": 98000 | |
| }, | |
| { | |
| "epoch": 19.45, | |
| "learning_rate": 2.0339168162776783e-06, | |
| "loss": 0.2827, | |
| "step": 98500 | |
| }, | |
| { | |
| "epoch": 19.55, | |
| "learning_rate": 2.031423299421504e-06, | |
| "loss": 0.2832, | |
| "step": 99000 | |
| }, | |
| { | |
| "epoch": 19.65, | |
| "learning_rate": 2.0289297825653305e-06, | |
| "loss": 0.2847, | |
| "step": 99500 | |
| }, | |
| { | |
| "epoch": 19.75, | |
| "learning_rate": 2.0264412527428686e-06, | |
| "loss": 0.2889, | |
| "step": 100000 | |
| }, | |
| { | |
| "epoch": 19.85, | |
| "learning_rate": 2.0239477358866947e-06, | |
| "loss": 0.2835, | |
| "step": 100500 | |
| }, | |
| { | |
| "epoch": 19.95, | |
| "learning_rate": 2.021454219030521e-06, | |
| "loss": 0.2878, | |
| "step": 101000 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_accuracy": 0.8355620192123694, | |
| "eval_f1": 0.46679081315952825, | |
| "eval_loss": 0.6431704163551331, | |
| "eval_precision": 0.4094968416467001, | |
| "eval_recall": 0.5427251732101617, | |
| "eval_runtime": 23.6323, | |
| "eval_samples_per_second": 129.018, | |
| "eval_steps_per_second": 16.164, | |
| "step": 101260 | |
| }, | |
| { | |
| "epoch": 20.05, | |
| "learning_rate": 2.018960702174347e-06, | |
| "loss": 0.2854, | |
| "step": 101500 | |
| }, | |
| { | |
| "epoch": 20.15, | |
| "learning_rate": 2.016467185318173e-06, | |
| "loss": 0.2831, | |
| "step": 102000 | |
| }, | |
| { | |
| "epoch": 20.24, | |
| "learning_rate": 2.0139786554957115e-06, | |
| "loss": 0.2859, | |
| "step": 102500 | |
| }, | |
| { | |
| "epoch": 20.34, | |
| "learning_rate": 2.011485138639537e-06, | |
| "loss": 0.2892, | |
| "step": 103000 | |
| }, | |
| { | |
| "epoch": 20.44, | |
| "learning_rate": 2.0089916217833638e-06, | |
| "loss": 0.2886, | |
| "step": 103500 | |
| }, | |
| { | |
| "epoch": 20.54, | |
| "learning_rate": 2.0064981049271895e-06, | |
| "loss": 0.2792, | |
| "step": 104000 | |
| }, | |
| { | |
| "epoch": 20.64, | |
| "learning_rate": 2.0040045880710156e-06, | |
| "loss": 0.2864, | |
| "step": 104500 | |
| }, | |
| { | |
| "epoch": 20.74, | |
| "learning_rate": 2.0015110712148417e-06, | |
| "loss": 0.274, | |
| "step": 105000 | |
| }, | |
| { | |
| "epoch": 20.84, | |
| "learning_rate": 1.999017554358668e-06, | |
| "loss": 0.2821, | |
| "step": 105500 | |
| }, | |
| { | |
| "epoch": 20.94, | |
| "learning_rate": 1.9965240375024935e-06, | |
| "loss": 0.2755, | |
| "step": 106000 | |
| }, | |
| { | |
| "epoch": 21.0, | |
| "eval_accuracy": 0.8393623942745608, | |
| "eval_f1": 0.47563336419493313, | |
| "eval_loss": 0.6629786491394043, | |
| "eval_precision": 0.4226626776364996, | |
| "eval_recall": 0.5437836797536567, | |
| "eval_runtime": 24.3778, | |
| "eval_samples_per_second": 125.073, | |
| "eval_steps_per_second": 15.67, | |
| "step": 106323 | |
| }, | |
| { | |
| "epoch": 21.03, | |
| "learning_rate": 1.9940305206463197e-06, | |
| "loss": 0.2888, | |
| "step": 106500 | |
| }, | |
| { | |
| "epoch": 21.13, | |
| "learning_rate": 1.9915370037901458e-06, | |
| "loss": 0.2889, | |
| "step": 107000 | |
| }, | |
| { | |
| "epoch": 21.23, | |
| "learning_rate": 1.9890484739676842e-06, | |
| "loss": 0.2746, | |
| "step": 107500 | |
| }, | |
| { | |
| "epoch": 21.33, | |
| "learning_rate": 1.9865599441452227e-06, | |
| "loss": 0.2697, | |
| "step": 108000 | |
| }, | |
| { | |
| "epoch": 21.43, | |
| "learning_rate": 1.984066427289049e-06, | |
| "loss": 0.2843, | |
| "step": 108500 | |
| }, | |
| { | |
| "epoch": 21.53, | |
| "learning_rate": 1.9815729104328745e-06, | |
| "loss": 0.2823, | |
| "step": 109000 | |
| }, | |
| { | |
| "epoch": 21.63, | |
| "learning_rate": 1.9790793935767006e-06, | |
| "loss": 0.2864, | |
| "step": 109500 | |
| }, | |
| { | |
| "epoch": 21.73, | |
| "learning_rate": 1.9765858767205267e-06, | |
| "loss": 0.2849, | |
| "step": 110000 | |
| }, | |
| { | |
| "epoch": 21.83, | |
| "learning_rate": 1.974092359864353e-06, | |
| "loss": 0.2831, | |
| "step": 110500 | |
| }, | |
| { | |
| "epoch": 21.92, | |
| "learning_rate": 1.971598843008179e-06, | |
| "loss": 0.2842, | |
| "step": 111000 | |
| }, | |
| { | |
| "epoch": 22.0, | |
| "eval_accuracy": 0.8373914041869187, | |
| "eval_f1": 0.47138215446138465, | |
| "eval_loss": 0.64870285987854, | |
| "eval_precision": 0.41560158660202734, | |
| "eval_recall": 0.5444572748267898, | |
| "eval_runtime": 23.5627, | |
| "eval_samples_per_second": 129.399, | |
| "eval_steps_per_second": 16.212, | |
| "step": 111386 | |
| }, | |
| { | |
| "epoch": 22.02, | |
| "learning_rate": 1.9691053261520047e-06, | |
| "loss": 0.2736, | |
| "step": 111500 | |
| }, | |
| { | |
| "epoch": 22.12, | |
| "learning_rate": 1.966616796329543e-06, | |
| "loss": 0.2822, | |
| "step": 112000 | |
| }, | |
| { | |
| "epoch": 22.22, | |
| "learning_rate": 1.9641232794733693e-06, | |
| "loss": 0.2809, | |
| "step": 112500 | |
| }, | |
| { | |
| "epoch": 22.32, | |
| "learning_rate": 1.9616297626171954e-06, | |
| "loss": 0.2829, | |
| "step": 113000 | |
| }, | |
| { | |
| "epoch": 22.42, | |
| "learning_rate": 1.959141232794734e-06, | |
| "loss": 0.2886, | |
| "step": 113500 | |
| }, | |
| { | |
| "epoch": 22.52, | |
| "learning_rate": 1.95664771593856e-06, | |
| "loss": 0.2802, | |
| "step": 114000 | |
| }, | |
| { | |
| "epoch": 22.62, | |
| "learning_rate": 1.954154199082386e-06, | |
| "loss": 0.2795, | |
| "step": 114500 | |
| }, | |
| { | |
| "epoch": 22.71, | |
| "learning_rate": 1.951665669259924e-06, | |
| "loss": 0.2797, | |
| "step": 115000 | |
| }, | |
| { | |
| "epoch": 22.81, | |
| "learning_rate": 1.9491721524037506e-06, | |
| "loss": 0.2828, | |
| "step": 115500 | |
| }, | |
| { | |
| "epoch": 22.91, | |
| "learning_rate": 1.9466786355475763e-06, | |
| "loss": 0.2845, | |
| "step": 116000 | |
| }, | |
| { | |
| "epoch": 23.0, | |
| "eval_accuracy": 0.8386811588656282, | |
| "eval_f1": 0.47448125836680055, | |
| "eval_loss": 0.6472445726394653, | |
| "eval_precision": 0.4197010065127294, | |
| "eval_recall": 0.5457082371054658, | |
| "eval_runtime": 23.7562, | |
| "eval_samples_per_second": 128.345, | |
| "eval_steps_per_second": 16.08, | |
| "step": 116449 | |
| }, | |
| { | |
| "epoch": 23.01, | |
| "learning_rate": 1.9441851186914025e-06, | |
| "loss": 0.282, | |
| "step": 116500 | |
| }, | |
| { | |
| "epoch": 23.11, | |
| "learning_rate": 1.9416916018352286e-06, | |
| "loss": 0.2757, | |
| "step": 117000 | |
| }, | |
| { | |
| "epoch": 23.21, | |
| "learning_rate": 1.9391980849790547e-06, | |
| "loss": 0.2837, | |
| "step": 117500 | |
| }, | |
| { | |
| "epoch": 23.31, | |
| "learning_rate": 1.936704568122881e-06, | |
| "loss": 0.2737, | |
| "step": 118000 | |
| }, | |
| { | |
| "epoch": 23.41, | |
| "learning_rate": 1.9342110512667065e-06, | |
| "loss": 0.2774, | |
| "step": 118500 | |
| }, | |
| { | |
| "epoch": 23.5, | |
| "learning_rate": 1.9317175344105327e-06, | |
| "loss": 0.2779, | |
| "step": 119000 | |
| }, | |
| { | |
| "epoch": 23.6, | |
| "learning_rate": 1.929229004588071e-06, | |
| "loss": 0.2776, | |
| "step": 119500 | |
| }, | |
| { | |
| "epoch": 23.7, | |
| "learning_rate": 1.9267354877318972e-06, | |
| "loss": 0.289, | |
| "step": 120000 | |
| }, | |
| { | |
| "epoch": 23.8, | |
| "learning_rate": 1.9242419708757234e-06, | |
| "loss": 0.2731, | |
| "step": 120500 | |
| }, | |
| { | |
| "epoch": 23.9, | |
| "learning_rate": 1.9217484540195495e-06, | |
| "loss": 0.2738, | |
| "step": 121000 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "learning_rate": 1.919259924197088e-06, | |
| "loss": 0.2877, | |
| "step": 121500 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "eval_accuracy": 0.8382027632132879, | |
| "eval_f1": 0.47804428816610156, | |
| "eval_loss": 0.6589922308921814, | |
| "eval_precision": 0.4230569756242128, | |
| "eval_recall": 0.5494611239414935, | |
| "eval_runtime": 23.7626, | |
| "eval_samples_per_second": 128.311, | |
| "eval_steps_per_second": 16.076, | |
| "step": 121512 | |
| }, | |
| { | |
| "epoch": 24.1, | |
| "learning_rate": 1.9167664073409136e-06, | |
| "loss": 0.2805, | |
| "step": 122000 | |
| }, | |
| { | |
| "epoch": 24.2, | |
| "learning_rate": 1.9142728904847398e-06, | |
| "loss": 0.2735, | |
| "step": 122500 | |
| }, | |
| { | |
| "epoch": 24.29, | |
| "learning_rate": 1.911779373628566e-06, | |
| "loss": 0.2688, | |
| "step": 123000 | |
| }, | |
| { | |
| "epoch": 24.39, | |
| "learning_rate": 1.909285856772392e-06, | |
| "loss": 0.2881, | |
| "step": 123500 | |
| }, | |
| { | |
| "epoch": 24.49, | |
| "learning_rate": 1.9067923399162181e-06, | |
| "loss": 0.2755, | |
| "step": 124000 | |
| }, | |
| { | |
| "epoch": 24.59, | |
| "learning_rate": 1.904298823060044e-06, | |
| "loss": 0.2799, | |
| "step": 124500 | |
| }, | |
| { | |
| "epoch": 24.69, | |
| "learning_rate": 1.9018053062038702e-06, | |
| "loss": 0.2716, | |
| "step": 125000 | |
| }, | |
| { | |
| "epoch": 24.79, | |
| "learning_rate": 1.899311789347696e-06, | |
| "loss": 0.2837, | |
| "step": 125500 | |
| }, | |
| { | |
| "epoch": 24.89, | |
| "learning_rate": 1.8968182724915222e-06, | |
| "loss": 0.2855, | |
| "step": 126000 | |
| }, | |
| { | |
| "epoch": 24.99, | |
| "learning_rate": 1.8943247556353483e-06, | |
| "loss": 0.2745, | |
| "step": 126500 | |
| }, | |
| { | |
| "epoch": 25.0, | |
| "eval_accuracy": 0.8376172069348233, | |
| "eval_f1": 0.47353063776573573, | |
| "eval_loss": 0.6596588492393494, | |
| "eval_precision": 0.41770848654213855, | |
| "eval_recall": 0.5465742879137798, | |
| "eval_runtime": 23.6288, | |
| "eval_samples_per_second": 129.037, | |
| "eval_steps_per_second": 16.167, | |
| "step": 126575 | |
| }, | |
| { | |
| "epoch": 25.08, | |
| "learning_rate": 1.8918312387791742e-06, | |
| "loss": 0.2715, | |
| "step": 127000 | |
| }, | |
| { | |
| "epoch": 25.18, | |
| "learning_rate": 1.8893377219230001e-06, | |
| "loss": 0.2714, | |
| "step": 127500 | |
| }, | |
| { | |
| "epoch": 25.28, | |
| "learning_rate": 1.8868442050668265e-06, | |
| "loss": 0.2827, | |
| "step": 128000 | |
| }, | |
| { | |
| "epoch": 25.38, | |
| "learning_rate": 1.8843506882106524e-06, | |
| "loss": 0.2745, | |
| "step": 128500 | |
| }, | |
| { | |
| "epoch": 25.48, | |
| "learning_rate": 1.8818621583881908e-06, | |
| "loss": 0.2717, | |
| "step": 129000 | |
| }, | |
| { | |
| "epoch": 25.58, | |
| "learning_rate": 1.879368641532017e-06, | |
| "loss": 0.2747, | |
| "step": 129500 | |
| }, | |
| { | |
| "epoch": 25.68, | |
| "learning_rate": 1.8768751246758429e-06, | |
| "loss": 0.269, | |
| "step": 130000 | |
| }, | |
| { | |
| "epoch": 25.78, | |
| "learning_rate": 1.8743816078196688e-06, | |
| "loss": 0.2766, | |
| "step": 130500 | |
| }, | |
| { | |
| "epoch": 25.87, | |
| "learning_rate": 1.8718880909634951e-06, | |
| "loss": 0.2684, | |
| "step": 131000 | |
| }, | |
| { | |
| "epoch": 25.97, | |
| "learning_rate": 1.8693995611410334e-06, | |
| "loss": 0.2714, | |
| "step": 131500 | |
| }, | |
| { | |
| "epoch": 26.0, | |
| "eval_accuracy": 0.8359294270733667, | |
| "eval_f1": 0.4756838269174381, | |
| "eval_loss": 0.6624502539634705, | |
| "eval_precision": 0.42118537200504413, | |
| "eval_recall": 0.5463818321785989, | |
| "eval_runtime": 24.4351, | |
| "eval_samples_per_second": 124.78, | |
| "eval_steps_per_second": 15.633, | |
| "step": 131638 | |
| }, | |
| { | |
| "epoch": 26.07, | |
| "learning_rate": 1.8669060442848595e-06, | |
| "loss": 0.2782, | |
| "step": 132000 | |
| }, | |
| { | |
| "epoch": 26.17, | |
| "learning_rate": 1.8644125274286856e-06, | |
| "loss": 0.2704, | |
| "step": 132500 | |
| }, | |
| { | |
| "epoch": 26.27, | |
| "learning_rate": 1.8619190105725115e-06, | |
| "loss": 0.2747, | |
| "step": 133000 | |
| }, | |
| { | |
| "epoch": 26.37, | |
| "learning_rate": 1.8594254937163379e-06, | |
| "loss": 0.2756, | |
| "step": 133500 | |
| }, | |
| { | |
| "epoch": 26.47, | |
| "learning_rate": 1.8569319768601638e-06, | |
| "loss": 0.2747, | |
| "step": 134000 | |
| }, | |
| { | |
| "epoch": 26.57, | |
| "learning_rate": 1.8544484340714145e-06, | |
| "loss": 0.2793, | |
| "step": 134500 | |
| }, | |
| { | |
| "epoch": 26.66, | |
| "learning_rate": 1.8519549172152404e-06, | |
| "loss": 0.2729, | |
| "step": 135000 | |
| }, | |
| { | |
| "epoch": 26.76, | |
| "learning_rate": 1.8494614003590666e-06, | |
| "loss": 0.2852, | |
| "step": 135500 | |
| }, | |
| { | |
| "epoch": 26.86, | |
| "learning_rate": 1.8469678835028925e-06, | |
| "loss": 0.2648, | |
| "step": 136000 | |
| }, | |
| { | |
| "epoch": 26.96, | |
| "learning_rate": 1.8444743666467188e-06, | |
| "loss": 0.2696, | |
| "step": 136500 | |
| }, | |
| { | |
| "epoch": 27.0, | |
| "eval_accuracy": 0.8369244900302346, | |
| "eval_f1": 0.47798795129965876, | |
| "eval_loss": 0.6801736354827881, | |
| "eval_precision": 0.42510303484451106, | |
| "eval_recall": 0.5459006928406467, | |
| "eval_runtime": 23.7599, | |
| "eval_samples_per_second": 128.325, | |
| "eval_steps_per_second": 16.077, | |
| "step": 136701 | |
| }, | |
| { | |
| "epoch": 27.06, | |
| "learning_rate": 1.8419808497905447e-06, | |
| "loss": 0.2712, | |
| "step": 137000 | |
| }, | |
| { | |
| "epoch": 27.16, | |
| "learning_rate": 1.8394923199680832e-06, | |
| "loss": 0.2618, | |
| "step": 137500 | |
| }, | |
| { | |
| "epoch": 27.26, | |
| "learning_rate": 1.8369988031119093e-06, | |
| "loss": 0.2696, | |
| "step": 138000 | |
| }, | |
| { | |
| "epoch": 27.36, | |
| "learning_rate": 1.8345052862557352e-06, | |
| "loss": 0.2811, | |
| "step": 138500 | |
| }, | |
| { | |
| "epoch": 27.45, | |
| "learning_rate": 1.8320117693995611e-06, | |
| "loss": 0.2694, | |
| "step": 139000 | |
| }, | |
| { | |
| "epoch": 27.55, | |
| "learning_rate": 1.8295182525433875e-06, | |
| "loss": 0.2752, | |
| "step": 139500 | |
| }, | |
| { | |
| "epoch": 27.65, | |
| "learning_rate": 1.8270247356872134e-06, | |
| "loss": 0.2695, | |
| "step": 140000 | |
| }, | |
| { | |
| "epoch": 27.75, | |
| "learning_rate": 1.8245312188310393e-06, | |
| "loss": 0.2798, | |
| "step": 140500 | |
| }, | |
| { | |
| "epoch": 27.85, | |
| "learning_rate": 1.8220377019748656e-06, | |
| "loss": 0.2761, | |
| "step": 141000 | |
| }, | |
| { | |
| "epoch": 27.95, | |
| "learning_rate": 1.8195491721524039e-06, | |
| "loss": 0.2731, | |
| "step": 141500 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "eval_accuracy": 0.8383022695089747, | |
| "eval_f1": 0.4802879383945761, | |
| "eval_loss": 0.6660904884338379, | |
| "eval_precision": 0.4249740779143831, | |
| "eval_recall": 0.5521555042340262, | |
| "eval_runtime": 24.3606, | |
| "eval_samples_per_second": 125.161, | |
| "eval_steps_per_second": 15.681, | |
| "step": 141764 | |
| }, | |
| { | |
| "epoch": 28.05, | |
| "learning_rate": 1.8170556552962298e-06, | |
| "loss": 0.2698, | |
| "step": 142000 | |
| }, | |
| { | |
| "epoch": 28.15, | |
| "learning_rate": 1.8145621384400561e-06, | |
| "loss": 0.264, | |
| "step": 142500 | |
| }, | |
| { | |
| "epoch": 28.24, | |
| "learning_rate": 1.812068621583882e-06, | |
| "loss": 0.2612, | |
| "step": 143000 | |
| }, | |
| { | |
| "epoch": 28.34, | |
| "learning_rate": 1.809575104727708e-06, | |
| "loss": 0.2699, | |
| "step": 143500 | |
| }, | |
| { | |
| "epoch": 28.44, | |
| "learning_rate": 1.8070815878715343e-06, | |
| "loss": 0.2689, | |
| "step": 144000 | |
| }, | |
| { | |
| "epoch": 28.54, | |
| "learning_rate": 1.8045930580490725e-06, | |
| "loss": 0.2776, | |
| "step": 144500 | |
| }, | |
| { | |
| "epoch": 28.64, | |
| "learning_rate": 1.802104528226611e-06, | |
| "loss": 0.2742, | |
| "step": 145000 | |
| }, | |
| { | |
| "epoch": 28.74, | |
| "learning_rate": 1.799611011370437e-06, | |
| "loss": 0.2666, | |
| "step": 145500 | |
| }, | |
| { | |
| "epoch": 28.84, | |
| "learning_rate": 1.797117494514263e-06, | |
| "loss": 0.2659, | |
| "step": 146000 | |
| }, | |
| { | |
| "epoch": 28.94, | |
| "learning_rate": 1.7946239776580889e-06, | |
| "loss": 0.2701, | |
| "step": 146500 | |
| }, | |
| { | |
| "epoch": 29.0, | |
| "eval_accuracy": 0.8383520226568181, | |
| "eval_f1": 0.47666694694358025, | |
| "eval_loss": 0.6661925315856934, | |
| "eval_precision": 0.42324921606689564, | |
| "eval_recall": 0.5455157813702848, | |
| "eval_runtime": 23.5786, | |
| "eval_samples_per_second": 129.312, | |
| "eval_steps_per_second": 16.201, | |
| "step": 146827 | |
| }, | |
| { | |
| "epoch": 29.03, | |
| "learning_rate": 1.7921304608019152e-06, | |
| "loss": 0.2604, | |
| "step": 147000 | |
| }, | |
| { | |
| "epoch": 29.13, | |
| "learning_rate": 1.7896369439457411e-06, | |
| "loss": 0.2697, | |
| "step": 147500 | |
| }, | |
| { | |
| "epoch": 29.23, | |
| "learning_rate": 1.7871434270895675e-06, | |
| "loss": 0.2711, | |
| "step": 148000 | |
| }, | |
| { | |
| "epoch": 29.33, | |
| "learning_rate": 1.7846499102333934e-06, | |
| "loss": 0.2653, | |
| "step": 148500 | |
| }, | |
| { | |
| "epoch": 29.43, | |
| "learning_rate": 1.7821563933772193e-06, | |
| "loss": 0.2611, | |
| "step": 149000 | |
| }, | |
| { | |
| "epoch": 29.53, | |
| "learning_rate": 1.779667863554758e-06, | |
| "loss": 0.2751, | |
| "step": 149500 | |
| }, | |
| { | |
| "epoch": 29.63, | |
| "learning_rate": 1.7771743466985839e-06, | |
| "loss": 0.2696, | |
| "step": 150000 | |
| }, | |
| { | |
| "epoch": 29.73, | |
| "learning_rate": 1.7746808298424098e-06, | |
| "loss": 0.265, | |
| "step": 150500 | |
| }, | |
| { | |
| "epoch": 29.82, | |
| "learning_rate": 1.7721873129862361e-06, | |
| "loss": 0.2761, | |
| "step": 151000 | |
| }, | |
| { | |
| "epoch": 29.92, | |
| "learning_rate": 1.769693796130062e-06, | |
| "loss": 0.2653, | |
| "step": 151500 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "eval_accuracy": 0.8400933828313368, | |
| "eval_f1": 0.48114688043432163, | |
| "eval_loss": 0.67595374584198, | |
| "eval_precision": 0.43018581721653393, | |
| "eval_recall": 0.5458044649730562, | |
| "eval_runtime": 24.4081, | |
| "eval_samples_per_second": 124.917, | |
| "eval_steps_per_second": 15.651, | |
| "step": 151890 | |
| }, | |
| { | |
| "epoch": 30.02, | |
| "learning_rate": 1.7672052663076003e-06, | |
| "loss": 0.2619, | |
| "step": 152000 | |
| }, | |
| { | |
| "epoch": 30.12, | |
| "learning_rate": 1.7647117494514266e-06, | |
| "loss": 0.2608, | |
| "step": 152500 | |
| }, | |
| { | |
| "epoch": 30.22, | |
| "learning_rate": 1.7622182325952525e-06, | |
| "loss": 0.2693, | |
| "step": 153000 | |
| }, | |
| { | |
| "epoch": 30.32, | |
| "learning_rate": 1.7597247157390784e-06, | |
| "loss": 0.2671, | |
| "step": 153500 | |
| }, | |
| { | |
| "epoch": 30.42, | |
| "learning_rate": 1.7572311988829048e-06, | |
| "loss": 0.2735, | |
| "step": 154000 | |
| }, | |
| { | |
| "epoch": 30.52, | |
| "learning_rate": 1.754742669060443e-06, | |
| "loss": 0.2573, | |
| "step": 154500 | |
| }, | |
| { | |
| "epoch": 30.61, | |
| "learning_rate": 1.752249152204269e-06, | |
| "loss": 0.2622, | |
| "step": 155000 | |
| }, | |
| { | |
| "epoch": 30.71, | |
| "learning_rate": 1.7497556353480952e-06, | |
| "loss": 0.2791, | |
| "step": 155500 | |
| }, | |
| { | |
| "epoch": 30.81, | |
| "learning_rate": 1.7472621184919212e-06, | |
| "loss": 0.2673, | |
| "step": 156000 | |
| }, | |
| { | |
| "epoch": 30.91, | |
| "learning_rate": 1.7447735886694594e-06, | |
| "loss": 0.2547, | |
| "step": 156500 | |
| }, | |
| { | |
| "epoch": 31.0, | |
| "eval_accuracy": 0.8380305407784454, | |
| "eval_f1": 0.4841168996188056, | |
| "eval_loss": 0.6825248003005981, | |
| "eval_precision": 0.43236495687698595, | |
| "eval_recall": 0.5499422632794457, | |
| "eval_runtime": 23.8749, | |
| "eval_samples_per_second": 127.707, | |
| "eval_steps_per_second": 16.0, | |
| "step": 156953 | |
| }, | |
| { | |
| "epoch": 31.01, | |
| "learning_rate": 1.742285058846998e-06, | |
| "loss": 0.2735, | |
| "step": 157000 | |
| }, | |
| { | |
| "epoch": 31.11, | |
| "learning_rate": 1.739791541990824e-06, | |
| "loss": 0.2532, | |
| "step": 157500 | |
| }, | |
| { | |
| "epoch": 31.21, | |
| "learning_rate": 1.7372980251346499e-06, | |
| "loss": 0.2748, | |
| "step": 158000 | |
| }, | |
| { | |
| "epoch": 31.31, | |
| "learning_rate": 1.7348045082784762e-06, | |
| "loss": 0.2593, | |
| "step": 158500 | |
| }, | |
| { | |
| "epoch": 31.4, | |
| "learning_rate": 1.7323109914223021e-06, | |
| "loss": 0.2634, | |
| "step": 159000 | |
| }, | |
| { | |
| "epoch": 31.5, | |
| "learning_rate": 1.729817474566128e-06, | |
| "loss": 0.2645, | |
| "step": 159500 | |
| }, | |
| { | |
| "epoch": 31.6, | |
| "learning_rate": 1.7273239577099544e-06, | |
| "loss": 0.2637, | |
| "step": 160000 | |
| }, | |
| { | |
| "epoch": 31.7, | |
| "learning_rate": 1.7248304408537803e-06, | |
| "loss": 0.2652, | |
| "step": 160500 | |
| }, | |
| { | |
| "epoch": 31.8, | |
| "learning_rate": 1.7223369239976064e-06, | |
| "loss": 0.2757, | |
| "step": 161000 | |
| }, | |
| { | |
| "epoch": 31.9, | |
| "learning_rate": 1.7198434071414325e-06, | |
| "loss": 0.2655, | |
| "step": 161500 | |
| }, | |
| { | |
| "epoch": 32.0, | |
| "learning_rate": 1.7173498902852584e-06, | |
| "loss": 0.2682, | |
| "step": 162000 | |
| }, | |
| { | |
| "epoch": 32.0, | |
| "eval_accuracy": 0.8379693061349458, | |
| "eval_f1": 0.48521260841971653, | |
| "eval_loss": 0.6861287355422974, | |
| "eval_precision": 0.4329834629615646, | |
| "eval_recall": 0.5517705927636644, | |
| "eval_runtime": 23.7494, | |
| "eval_samples_per_second": 128.382, | |
| "eval_steps_per_second": 16.085, | |
| "step": 162016 | |
| }, | |
| { | |
| "epoch": 32.1, | |
| "learning_rate": 1.714861360462797e-06, | |
| "loss": 0.2703, | |
| "step": 162500 | |
| }, | |
| { | |
| "epoch": 32.19, | |
| "learning_rate": 1.712367843606623e-06, | |
| "loss": 0.2646, | |
| "step": 163000 | |
| }, | |
| { | |
| "epoch": 32.29, | |
| "learning_rate": 1.709874326750449e-06, | |
| "loss": 0.2559, | |
| "step": 163500 | |
| }, | |
| { | |
| "epoch": 32.39, | |
| "learning_rate": 1.707380809894275e-06, | |
| "loss": 0.2658, | |
| "step": 164000 | |
| }, | |
| { | |
| "epoch": 32.49, | |
| "learning_rate": 1.7048872930381012e-06, | |
| "loss": 0.2594, | |
| "step": 164500 | |
| }, | |
| { | |
| "epoch": 32.59, | |
| "learning_rate": 1.702393776181927e-06, | |
| "loss": 0.2635, | |
| "step": 165000 | |
| }, | |
| { | |
| "epoch": 32.69, | |
| "learning_rate": 1.6999052463594655e-06, | |
| "loss": 0.2641, | |
| "step": 165500 | |
| }, | |
| { | |
| "epoch": 32.79, | |
| "learning_rate": 1.6974117295032917e-06, | |
| "loss": 0.2594, | |
| "step": 166000 | |
| }, | |
| { | |
| "epoch": 32.89, | |
| "learning_rate": 1.6949182126471176e-06, | |
| "loss": 0.264, | |
| "step": 166500 | |
| }, | |
| { | |
| "epoch": 32.98, | |
| "learning_rate": 1.6924246957909437e-06, | |
| "loss": 0.2579, | |
| "step": 167000 | |
| }, | |
| { | |
| "epoch": 33.0, | |
| "eval_accuracy": 0.8380075777871331, | |
| "eval_f1": 0.4819972826086957, | |
| "eval_loss": 0.6779205203056335, | |
| "eval_precision": 0.43130699088145896, | |
| "eval_recall": 0.546189376443418, | |
| "eval_runtime": 23.6072, | |
| "eval_samples_per_second": 129.156, | |
| "eval_steps_per_second": 16.182, | |
| "step": 167079 | |
| }, | |
| { | |
| "epoch": 33.08, | |
| "learning_rate": 1.6899361659684821e-06, | |
| "loss": 0.2686, | |
| "step": 167500 | |
| }, | |
| { | |
| "epoch": 33.18, | |
| "learning_rate": 1.687442649112308e-06, | |
| "loss": 0.2653, | |
| "step": 168000 | |
| }, | |
| { | |
| "epoch": 33.28, | |
| "learning_rate": 1.6849491322561342e-06, | |
| "loss": 0.254, | |
| "step": 168500 | |
| }, | |
| { | |
| "epoch": 33.38, | |
| "learning_rate": 1.6824556153999603e-06, | |
| "loss": 0.2575, | |
| "step": 169000 | |
| }, | |
| { | |
| "epoch": 33.48, | |
| "learning_rate": 1.6799620985437862e-06, | |
| "loss": 0.2601, | |
| "step": 169500 | |
| }, | |
| { | |
| "epoch": 33.58, | |
| "learning_rate": 1.6774735687213249e-06, | |
| "loss": 0.2525, | |
| "step": 170000 | |
| }, | |
| { | |
| "epoch": 33.68, | |
| "learning_rate": 1.6749800518651508e-06, | |
| "loss": 0.2604, | |
| "step": 170500 | |
| }, | |
| { | |
| "epoch": 33.77, | |
| "learning_rate": 1.6724865350089767e-06, | |
| "loss": 0.2631, | |
| "step": 171000 | |
| }, | |
| { | |
| "epoch": 33.87, | |
| "learning_rate": 1.6699980051865153e-06, | |
| "loss": 0.2613, | |
| "step": 171500 | |
| }, | |
| { | |
| "epoch": 33.97, | |
| "learning_rate": 1.6675044883303413e-06, | |
| "loss": 0.2682, | |
| "step": 172000 | |
| }, | |
| { | |
| "epoch": 34.0, | |
| "eval_accuracy": 0.8394504190745915, | |
| "eval_f1": 0.488143978164449, | |
| "eval_loss": 0.686414361000061, | |
| "eval_precision": 0.43834252450980393, | |
| "eval_recall": 0.5507120862201693, | |
| "eval_runtime": 23.3121, | |
| "eval_samples_per_second": 130.791, | |
| "eval_steps_per_second": 16.386, | |
| "step": 172142 | |
| }, | |
| { | |
| "epoch": 34.07, | |
| "learning_rate": 1.6650109714741672e-06, | |
| "loss": 0.2538, | |
| "step": 172500 | |
| }, | |
| { | |
| "epoch": 34.17, | |
| "learning_rate": 1.6625174546179935e-06, | |
| "loss": 0.2737, | |
| "step": 173000 | |
| }, | |
| { | |
| "epoch": 34.27, | |
| "learning_rate": 1.6600239377618194e-06, | |
| "loss": 0.262, | |
| "step": 173500 | |
| }, | |
| { | |
| "epoch": 34.37, | |
| "learning_rate": 1.6575304209056455e-06, | |
| "loss": 0.2621, | |
| "step": 174000 | |
| }, | |
| { | |
| "epoch": 34.47, | |
| "learning_rate": 1.6550369040494715e-06, | |
| "loss": 0.2641, | |
| "step": 174500 | |
| }, | |
| { | |
| "epoch": 34.56, | |
| "learning_rate": 1.6525433871932976e-06, | |
| "loss": 0.269, | |
| "step": 175000 | |
| }, | |
| { | |
| "epoch": 34.66, | |
| "learning_rate": 1.6500498703371237e-06, | |
| "loss": 0.2574, | |
| "step": 175500 | |
| }, | |
| { | |
| "epoch": 34.76, | |
| "learning_rate": 1.6475563534809496e-06, | |
| "loss": 0.2641, | |
| "step": 176000 | |
| }, | |
| { | |
| "epoch": 34.86, | |
| "learning_rate": 1.6450628366247755e-06, | |
| "loss": 0.2542, | |
| "step": 176500 | |
| }, | |
| { | |
| "epoch": 34.96, | |
| "learning_rate": 1.6425693197686019e-06, | |
| "loss": 0.2576, | |
| "step": 177000 | |
| }, | |
| { | |
| "epoch": 35.0, | |
| "eval_accuracy": 0.8376593057522294, | |
| "eval_f1": 0.48530031168393556, | |
| "eval_loss": 0.6970050930976868, | |
| "eval_precision": 0.43153558052434454, | |
| "eval_recall": 0.5543687451886066, | |
| "eval_runtime": 24.2014, | |
| "eval_samples_per_second": 125.984, | |
| "eval_steps_per_second": 15.784, | |
| "step": 177205 | |
| }, | |
| { | |
| "epoch": 35.06, | |
| "learning_rate": 1.6400758029124278e-06, | |
| "loss": 0.2672, | |
| "step": 177500 | |
| }, | |
| { | |
| "epoch": 35.16, | |
| "learning_rate": 1.6375972471573909e-06, | |
| "loss": 0.2669, | |
| "step": 178000 | |
| }, | |
| { | |
| "epoch": 35.26, | |
| "learning_rate": 1.6351037303012172e-06, | |
| "loss": 0.2566, | |
| "step": 178500 | |
| }, | |
| { | |
| "epoch": 35.35, | |
| "learning_rate": 1.6326102134450431e-06, | |
| "loss": 0.261, | |
| "step": 179000 | |
| }, | |
| { | |
| "epoch": 35.45, | |
| "learning_rate": 1.630116696588869e-06, | |
| "loss": 0.2639, | |
| "step": 179500 | |
| }, | |
| { | |
| "epoch": 35.55, | |
| "learning_rate": 1.6276231797326951e-06, | |
| "loss": 0.271, | |
| "step": 180000 | |
| }, | |
| { | |
| "epoch": 35.65, | |
| "learning_rate": 1.6251296628765213e-06, | |
| "loss": 0.2673, | |
| "step": 180500 | |
| }, | |
| { | |
| "epoch": 35.75, | |
| "learning_rate": 1.6226361460203472e-06, | |
| "loss": 0.2645, | |
| "step": 181000 | |
| }, | |
| { | |
| "epoch": 35.85, | |
| "learning_rate": 1.6201426291641733e-06, | |
| "loss": 0.2517, | |
| "step": 181500 | |
| }, | |
| { | |
| "epoch": 35.95, | |
| "learning_rate": 1.6176491123079992e-06, | |
| "loss": 0.2671, | |
| "step": 182000 | |
| }, | |
| { | |
| "epoch": 36.0, | |
| "eval_accuracy": 0.8383175781698496, | |
| "eval_f1": 0.4893308296346876, | |
| "eval_loss": 0.6999177932739258, | |
| "eval_precision": 0.43964723926380367, | |
| "eval_recall": 0.5516743648960739, | |
| "eval_runtime": 23.6795, | |
| "eval_samples_per_second": 128.761, | |
| "eval_steps_per_second": 16.132, | |
| "step": 182268 | |
| }, | |
| { | |
| "epoch": 36.05, | |
| "learning_rate": 1.6151605824855377e-06, | |
| "loss": 0.2671, | |
| "step": 182500 | |
| }, | |
| { | |
| "epoch": 36.14, | |
| "learning_rate": 1.6126670656293638e-06, | |
| "loss": 0.2579, | |
| "step": 183000 | |
| }, | |
| { | |
| "epoch": 36.24, | |
| "learning_rate": 1.61017354877319e-06, | |
| "loss": 0.2638, | |
| "step": 183500 | |
| }, | |
| { | |
| "epoch": 36.34, | |
| "learning_rate": 1.6076800319170158e-06, | |
| "loss": 0.2613, | |
| "step": 184000 | |
| }, | |
| { | |
| "epoch": 36.44, | |
| "learning_rate": 1.605186515060842e-06, | |
| "loss": 0.2675, | |
| "step": 184500 | |
| }, | |
| { | |
| "epoch": 36.54, | |
| "learning_rate": 1.6026929982046679e-06, | |
| "loss": 0.2473, | |
| "step": 185000 | |
| }, | |
| { | |
| "epoch": 36.64, | |
| "learning_rate": 1.6002044683822063e-06, | |
| "loss": 0.2561, | |
| "step": 185500 | |
| }, | |
| { | |
| "epoch": 36.74, | |
| "learning_rate": 1.5977109515260324e-06, | |
| "loss": 0.2563, | |
| "step": 186000 | |
| }, | |
| { | |
| "epoch": 36.84, | |
| "learning_rate": 1.5952174346698586e-06, | |
| "loss": 0.2556, | |
| "step": 186500 | |
| }, | |
| { | |
| "epoch": 36.93, | |
| "learning_rate": 1.5927239178136847e-06, | |
| "loss": 0.2556, | |
| "step": 187000 | |
| }, | |
| { | |
| "epoch": 37.0, | |
| "eval_accuracy": 0.8364690573692066, | |
| "eval_f1": 0.48543032353563115, | |
| "eval_loss": 0.7063097357749939, | |
| "eval_precision": 0.4330340300309364, | |
| "eval_recall": 0.5522517321016166, | |
| "eval_runtime": 23.9877, | |
| "eval_samples_per_second": 127.107, | |
| "eval_steps_per_second": 15.925, | |
| "step": 187331 | |
| }, | |
| { | |
| "epoch": 37.03, | |
| "learning_rate": 1.5902304009575106e-06, | |
| "loss": 0.2535, | |
| "step": 187500 | |
| }, | |
| { | |
| "epoch": 37.13, | |
| "learning_rate": 1.5877368841013365e-06, | |
| "loss": 0.2611, | |
| "step": 188000 | |
| }, | |
| { | |
| "epoch": 37.23, | |
| "learning_rate": 1.5852483542788752e-06, | |
| "loss": 0.2493, | |
| "step": 188500 | |
| }, | |
| { | |
| "epoch": 37.33, | |
| "learning_rate": 1.582754837422701e-06, | |
| "loss": 0.249, | |
| "step": 189000 | |
| }, | |
| { | |
| "epoch": 37.43, | |
| "learning_rate": 1.580261320566527e-06, | |
| "loss": 0.2495, | |
| "step": 189500 | |
| }, | |
| { | |
| "epoch": 37.53, | |
| "learning_rate": 1.5777678037103533e-06, | |
| "loss": 0.2591, | |
| "step": 190000 | |
| }, | |
| { | |
| "epoch": 37.63, | |
| "learning_rate": 1.5752792738878916e-06, | |
| "loss": 0.244, | |
| "step": 190500 | |
| }, | |
| { | |
| "epoch": 37.72, | |
| "learning_rate": 1.5727857570317177e-06, | |
| "loss": 0.258, | |
| "step": 191000 | |
| }, | |
| { | |
| "epoch": 37.82, | |
| "learning_rate": 1.5702922401755438e-06, | |
| "loss": 0.2564, | |
| "step": 191500 | |
| }, | |
| { | |
| "epoch": 37.92, | |
| "learning_rate": 1.5677987233193697e-06, | |
| "loss": 0.2557, | |
| "step": 192000 | |
| }, | |
| { | |
| "epoch": 38.0, | |
| "eval_accuracy": 0.837223008917295, | |
| "eval_f1": 0.48226590572817585, | |
| "eval_loss": 0.7124492526054382, | |
| "eval_precision": 0.4300686119279198, | |
| "eval_recall": 0.5488837567359507, | |
| "eval_runtime": 24.7192, | |
| "eval_samples_per_second": 123.346, | |
| "eval_steps_per_second": 15.454, | |
| "step": 192394 | |
| }, | |
| { | |
| "epoch": 38.02, | |
| "learning_rate": 1.5653052064631956e-06, | |
| "loss": 0.2488, | |
| "step": 192500 | |
| }, | |
| { | |
| "epoch": 38.12, | |
| "learning_rate": 1.5628166766407343e-06, | |
| "loss": 0.2465, | |
| "step": 193000 | |
| }, | |
| { | |
| "epoch": 38.22, | |
| "learning_rate": 1.5603231597845602e-06, | |
| "loss": 0.2465, | |
| "step": 193500 | |
| }, | |
| { | |
| "epoch": 38.32, | |
| "learning_rate": 1.5578346299620986e-06, | |
| "loss": 0.2622, | |
| "step": 194000 | |
| }, | |
| { | |
| "epoch": 38.42, | |
| "learning_rate": 1.5553411131059248e-06, | |
| "loss": 0.2587, | |
| "step": 194500 | |
| }, | |
| { | |
| "epoch": 38.51, | |
| "learning_rate": 1.5528475962497509e-06, | |
| "loss": 0.2482, | |
| "step": 195000 | |
| }, | |
| { | |
| "epoch": 38.61, | |
| "learning_rate": 1.5503540793935768e-06, | |
| "loss": 0.2426, | |
| "step": 195500 | |
| }, | |
| { | |
| "epoch": 38.71, | |
| "learning_rate": 1.5478655495711153e-06, | |
| "loss": 0.2529, | |
| "step": 196000 | |
| }, | |
| { | |
| "epoch": 38.81, | |
| "learning_rate": 1.5453720327149414e-06, | |
| "loss": 0.2564, | |
| "step": 196500 | |
| }, | |
| { | |
| "epoch": 38.91, | |
| "learning_rate": 1.5428785158587673e-06, | |
| "loss": 0.2518, | |
| "step": 197000 | |
| }, | |
| { | |
| "epoch": 39.0, | |
| "eval_accuracy": 0.8392246163266868, | |
| "eval_f1": 0.487758945386064, | |
| "eval_loss": 0.7146723866462708, | |
| "eval_precision": 0.43925377736663584, | |
| "eval_recall": 0.548306389530408, | |
| "eval_runtime": 23.4197, | |
| "eval_samples_per_second": 130.189, | |
| "eval_steps_per_second": 16.311, | |
| "step": 197457 | |
| }, | |
| { | |
| "epoch": 39.01, | |
| "learning_rate": 1.5403849990025934e-06, | |
| "loss": 0.2478, | |
| "step": 197500 | |
| }, | |
| { | |
| "epoch": 39.11, | |
| "learning_rate": 1.5378914821464193e-06, | |
| "loss": 0.2541, | |
| "step": 198000 | |
| }, | |
| { | |
| "epoch": 39.21, | |
| "learning_rate": 1.5353979652902454e-06, | |
| "loss": 0.2546, | |
| "step": 198500 | |
| }, | |
| { | |
| "epoch": 39.3, | |
| "learning_rate": 1.5329044484340716e-06, | |
| "loss": 0.2498, | |
| "step": 199000 | |
| }, | |
| { | |
| "epoch": 39.4, | |
| "learning_rate": 1.5304109315778975e-06, | |
| "loss": 0.2499, | |
| "step": 199500 | |
| }, | |
| { | |
| "epoch": 39.5, | |
| "learning_rate": 1.5279174147217238e-06, | |
| "loss": 0.2615, | |
| "step": 200000 | |
| }, | |
| { | |
| "epoch": 39.6, | |
| "learning_rate": 1.525428884899262e-06, | |
| "loss": 0.2469, | |
| "step": 200500 | |
| }, | |
| { | |
| "epoch": 39.7, | |
| "learning_rate": 1.522935368043088e-06, | |
| "loss": 0.247, | |
| "step": 201000 | |
| }, | |
| { | |
| "epoch": 39.8, | |
| "learning_rate": 1.5204418511869143e-06, | |
| "loss": 0.25, | |
| "step": 201500 | |
| }, | |
| { | |
| "epoch": 39.9, | |
| "learning_rate": 1.5179483343307402e-06, | |
| "loss": 0.2564, | |
| "step": 202000 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "learning_rate": 1.5154548174745661e-06, | |
| "loss": 0.2515, | |
| "step": 202500 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "eval_accuracy": 0.8385012821003482, | |
| "eval_f1": 0.4914221993480871, | |
| "eval_loss": 0.7163015604019165, | |
| "eval_precision": 0.4432838130609718, | |
| "eval_recall": 0.5512894534257121, | |
| "eval_runtime": 24.4401, | |
| "eval_samples_per_second": 124.754, | |
| "eval_steps_per_second": 15.63, | |
| "step": 202520 | |
| }, | |
| { | |
| "epoch": 40.09, | |
| "learning_rate": 1.5129613006183925e-06, | |
| "loss": 0.2662, | |
| "step": 203000 | |
| }, | |
| { | |
| "epoch": 40.19, | |
| "learning_rate": 1.5104677837622184e-06, | |
| "loss": 0.2548, | |
| "step": 203500 | |
| }, | |
| { | |
| "epoch": 40.29, | |
| "learning_rate": 1.5079742669060443e-06, | |
| "loss": 0.251, | |
| "step": 204000 | |
| }, | |
| { | |
| "epoch": 40.39, | |
| "learning_rate": 1.5054807500498706e-06, | |
| "loss": 0.2498, | |
| "step": 204500 | |
| }, | |
| { | |
| "epoch": 40.49, | |
| "learning_rate": 1.5029872331936965e-06, | |
| "loss": 0.2461, | |
| "step": 205000 | |
| }, | |
| { | |
| "epoch": 40.59, | |
| "learning_rate": 1.5004937163375225e-06, | |
| "loss": 0.2457, | |
| "step": 205500 | |
| }, | |
| { | |
| "epoch": 40.69, | |
| "learning_rate": 1.4980001994813486e-06, | |
| "loss": 0.2554, | |
| "step": 206000 | |
| }, | |
| { | |
| "epoch": 40.79, | |
| "learning_rate": 1.495511669658887e-06, | |
| "loss": 0.2522, | |
| "step": 206500 | |
| }, | |
| { | |
| "epoch": 40.88, | |
| "learning_rate": 1.493018152802713e-06, | |
| "loss": 0.2436, | |
| "step": 207000 | |
| }, | |
| { | |
| "epoch": 40.98, | |
| "learning_rate": 1.4905246359465393e-06, | |
| "loss": 0.243, | |
| "step": 207500 | |
| }, | |
| { | |
| "epoch": 41.0, | |
| "eval_accuracy": 0.8361093038386467, | |
| "eval_f1": 0.4854713868798376, | |
| "eval_loss": 0.7213875651359558, | |
| "eval_precision": 0.43309938872537923, | |
| "eval_recall": 0.5522517321016166, | |
| "eval_runtime": 23.8024, | |
| "eval_samples_per_second": 128.096, | |
| "eval_steps_per_second": 16.049, | |
| "step": 207583 | |
| }, | |
| { | |
| "epoch": 41.08, | |
| "learning_rate": 1.4880311190903652e-06, | |
| "loss": 0.2445, | |
| "step": 208000 | |
| }, | |
| { | |
| "epoch": 41.18, | |
| "learning_rate": 1.4855425892679034e-06, | |
| "loss": 0.2505, | |
| "step": 208500 | |
| }, | |
| { | |
| "epoch": 41.28, | |
| "learning_rate": 1.4830490724117297e-06, | |
| "loss": 0.2508, | |
| "step": 209000 | |
| }, | |
| { | |
| "epoch": 41.38, | |
| "learning_rate": 1.4805555555555557e-06, | |
| "loss": 0.2499, | |
| "step": 209500 | |
| }, | |
| { | |
| "epoch": 41.48, | |
| "learning_rate": 1.4780620386993818e-06, | |
| "loss": 0.2459, | |
| "step": 210000 | |
| }, | |
| { | |
| "epoch": 41.58, | |
| "learning_rate": 1.4755735088769202e-06, | |
| "loss": 0.2502, | |
| "step": 210500 | |
| }, | |
| { | |
| "epoch": 41.67, | |
| "learning_rate": 1.4730799920207461e-06, | |
| "loss": 0.2509, | |
| "step": 211000 | |
| }, | |
| { | |
| "epoch": 41.77, | |
| "learning_rate": 1.4705864751645723e-06, | |
| "loss": 0.2568, | |
| "step": 211500 | |
| }, | |
| { | |
| "epoch": 41.87, | |
| "learning_rate": 1.4680929583083984e-06, | |
| "loss": 0.2475, | |
| "step": 212000 | |
| }, | |
| { | |
| "epoch": 41.97, | |
| "learning_rate": 1.4656044284859366e-06, | |
| "loss": 0.2504, | |
| "step": 212500 | |
| }, | |
| { | |
| "epoch": 42.0, | |
| "eval_accuracy": 0.8370967124650771, | |
| "eval_f1": 0.4893995929443691, | |
| "eval_loss": 0.7146164178848267, | |
| "eval_precision": 0.4374620982413584, | |
| "eval_recall": 0.5553310238645112, | |
| "eval_runtime": 24.4183, | |
| "eval_samples_per_second": 124.865, | |
| "eval_steps_per_second": 15.644, | |
| "step": 212646 | |
| }, | |
| { | |
| "epoch": 42.07, | |
| "learning_rate": 1.463110911629763e-06, | |
| "loss": 0.2393, | |
| "step": 213000 | |
| }, | |
| { | |
| "epoch": 42.17, | |
| "learning_rate": 1.4606173947735889e-06, | |
| "loss": 0.2512, | |
| "step": 213500 | |
| }, | |
| { | |
| "epoch": 42.27, | |
| "learning_rate": 1.4581238779174148e-06, | |
| "loss": 0.2452, | |
| "step": 214000 | |
| }, | |
| { | |
| "epoch": 42.37, | |
| "learning_rate": 1.455630361061241e-06, | |
| "loss": 0.2527, | |
| "step": 214500 | |
| }, | |
| { | |
| "epoch": 42.46, | |
| "learning_rate": 1.453136844205067e-06, | |
| "loss": 0.2433, | |
| "step": 215000 | |
| }, | |
| { | |
| "epoch": 42.56, | |
| "learning_rate": 1.450643327348893e-06, | |
| "loss": 0.2451, | |
| "step": 215500 | |
| }, | |
| { | |
| "epoch": 42.66, | |
| "learning_rate": 1.448149810492719e-06, | |
| "loss": 0.2452, | |
| "step": 216000 | |
| }, | |
| { | |
| "epoch": 42.76, | |
| "learning_rate": 1.445656293636545e-06, | |
| "loss": 0.2595, | |
| "step": 216500 | |
| }, | |
| { | |
| "epoch": 42.86, | |
| "learning_rate": 1.4431677638140834e-06, | |
| "loss": 0.2398, | |
| "step": 217000 | |
| }, | |
| { | |
| "epoch": 42.96, | |
| "learning_rate": 1.4406742469579096e-06, | |
| "loss": 0.2467, | |
| "step": 217500 | |
| }, | |
| { | |
| "epoch": 43.0, | |
| "eval_accuracy": 0.8372115274216388, | |
| "eval_f1": 0.4870404878875148, | |
| "eval_loss": 0.7194024324417114, | |
| "eval_precision": 0.434947049924357, | |
| "eval_recall": 0.5533102386451116, | |
| "eval_runtime": 24.5076, | |
| "eval_samples_per_second": 124.41, | |
| "eval_steps_per_second": 15.587, | |
| "step": 217709 | |
| }, | |
| { | |
| "epoch": 43.06, | |
| "learning_rate": 1.4381807301017357e-06, | |
| "loss": 0.2496, | |
| "step": 218000 | |
| }, | |
| { | |
| "epoch": 43.16, | |
| "learning_rate": 1.4356872132455616e-06, | |
| "loss": 0.246, | |
| "step": 218500 | |
| }, | |
| { | |
| "epoch": 43.25, | |
| "learning_rate": 1.4331936963893877e-06, | |
| "loss": 0.2455, | |
| "step": 219000 | |
| }, | |
| { | |
| "epoch": 43.35, | |
| "learning_rate": 1.4307051665669262e-06, | |
| "loss": 0.2452, | |
| "step": 219500 | |
| }, | |
| { | |
| "epoch": 43.45, | |
| "learning_rate": 1.428211649710752e-06, | |
| "loss": 0.2481, | |
| "step": 220000 | |
| }, | |
| { | |
| "epoch": 43.55, | |
| "learning_rate": 1.4257181328545782e-06, | |
| "loss": 0.2471, | |
| "step": 220500 | |
| }, | |
| { | |
| "epoch": 43.65, | |
| "learning_rate": 1.4232246159984043e-06, | |
| "loss": 0.2448, | |
| "step": 221000 | |
| }, | |
| { | |
| "epoch": 43.75, | |
| "learning_rate": 1.4207360861759426e-06, | |
| "loss": 0.2474, | |
| "step": 221500 | |
| }, | |
| { | |
| "epoch": 43.85, | |
| "learning_rate": 1.4182425693197687e-06, | |
| "loss": 0.2453, | |
| "step": 222000 | |
| }, | |
| { | |
| "epoch": 43.95, | |
| "learning_rate": 1.4157490524635948e-06, | |
| "loss": 0.2485, | |
| "step": 222500 | |
| }, | |
| { | |
| "epoch": 44.0, | |
| "eval_accuracy": 0.8376210341000421, | |
| "eval_f1": 0.4923129484113427, | |
| "eval_loss": 0.7221771478652954, | |
| "eval_precision": 0.44256756756756754, | |
| "eval_recall": 0.554657428791378, | |
| "eval_runtime": 23.7235, | |
| "eval_samples_per_second": 128.523, | |
| "eval_steps_per_second": 16.102, | |
| "step": 222772 | |
| }, | |
| { | |
| "epoch": 44.05, | |
| "learning_rate": 1.413255535607421e-06, | |
| "loss": 0.2506, | |
| "step": 223000 | |
| }, | |
| { | |
| "epoch": 44.14, | |
| "learning_rate": 1.4107620187512468e-06, | |
| "loss": 0.2426, | |
| "step": 223500 | |
| }, | |
| { | |
| "epoch": 44.24, | |
| "learning_rate": 1.4082734889287853e-06, | |
| "loss": 0.2462, | |
| "step": 224000 | |
| }, | |
| { | |
| "epoch": 44.34, | |
| "learning_rate": 1.4057799720726112e-06, | |
| "loss": 0.2574, | |
| "step": 224500 | |
| }, | |
| { | |
| "epoch": 44.44, | |
| "learning_rate": 1.4032864552164373e-06, | |
| "loss": 0.25, | |
| "step": 225000 | |
| }, | |
| { | |
| "epoch": 44.54, | |
| "learning_rate": 1.4007929383602634e-06, | |
| "loss": 0.2494, | |
| "step": 225500 | |
| }, | |
| { | |
| "epoch": 44.64, | |
| "learning_rate": 1.3983044085378017e-06, | |
| "loss": 0.2491, | |
| "step": 226000 | |
| }, | |
| { | |
| "epoch": 44.74, | |
| "learning_rate": 1.395810891681628e-06, | |
| "loss": 0.2412, | |
| "step": 226500 | |
| }, | |
| { | |
| "epoch": 44.84, | |
| "learning_rate": 1.393317374825454e-06, | |
| "loss": 0.2578, | |
| "step": 227000 | |
| }, | |
| { | |
| "epoch": 44.93, | |
| "learning_rate": 1.39082385796928e-06, | |
| "loss": 0.2407, | |
| "step": 227500 | |
| }, | |
| { | |
| "epoch": 45.0, | |
| "eval_accuracy": 0.8363848597343947, | |
| "eval_f1": 0.4902906406043276, | |
| "eval_loss": 0.7273271083831787, | |
| "eval_precision": 0.44052458010583634, | |
| "eval_recall": 0.552732871439569, | |
| "eval_runtime": 24.6123, | |
| "eval_samples_per_second": 123.881, | |
| "eval_steps_per_second": 15.521, | |
| "step": 227835 | |
| }, | |
| { | |
| "epoch": 45.03, | |
| "learning_rate": 1.388330341113106e-06, | |
| "loss": 0.2457, | |
| "step": 228000 | |
| }, | |
| { | |
| "epoch": 45.13, | |
| "learning_rate": 1.385836824256932e-06, | |
| "loss": 0.246, | |
| "step": 228500 | |
| }, | |
| { | |
| "epoch": 45.23, | |
| "learning_rate": 1.3833433074007582e-06, | |
| "loss": 0.2406, | |
| "step": 229000 | |
| }, | |
| { | |
| "epoch": 45.33, | |
| "learning_rate": 1.3808497905445841e-06, | |
| "loss": 0.2444, | |
| "step": 229500 | |
| }, | |
| { | |
| "epoch": 45.43, | |
| "learning_rate": 1.3783612607221226e-06, | |
| "loss": 0.241, | |
| "step": 230000 | |
| }, | |
| { | |
| "epoch": 45.53, | |
| "learning_rate": 1.3758677438659487e-06, | |
| "loss": 0.2425, | |
| "step": 230500 | |
| }, | |
| { | |
| "epoch": 45.63, | |
| "learning_rate": 1.3733742270097746e-06, | |
| "loss": 0.2333, | |
| "step": 231000 | |
| }, | |
| { | |
| "epoch": 45.72, | |
| "learning_rate": 1.3708807101536007e-06, | |
| "loss": 0.2361, | |
| "step": 231500 | |
| }, | |
| { | |
| "epoch": 45.82, | |
| "learning_rate": 1.3683871932974269e-06, | |
| "loss": 0.2418, | |
| "step": 232000 | |
| }, | |
| { | |
| "epoch": 45.92, | |
| "learning_rate": 1.3658986634749653e-06, | |
| "loss": 0.2508, | |
| "step": 232500 | |
| }, | |
| { | |
| "epoch": 46.0, | |
| "eval_accuracy": 0.8403995560488347, | |
| "eval_f1": 0.49452783665700567, | |
| "eval_loss": 0.7349366545677185, | |
| "eval_precision": 0.4491944990176817, | |
| "eval_recall": 0.5500384911470362, | |
| "eval_runtime": 24.4005, | |
| "eval_samples_per_second": 124.956, | |
| "eval_steps_per_second": 15.655, | |
| "step": 232898 | |
| }, | |
| { | |
| "epoch": 46.02, | |
| "learning_rate": 1.3634051466187912e-06, | |
| "loss": 0.2456, | |
| "step": 233000 | |
| }, | |
| { | |
| "epoch": 46.12, | |
| "learning_rate": 1.3609116297626173e-06, | |
| "loss": 0.2381, | |
| "step": 233500 | |
| }, | |
| { | |
| "epoch": 46.22, | |
| "learning_rate": 1.3584181129064432e-06, | |
| "loss": 0.2434, | |
| "step": 234000 | |
| }, | |
| { | |
| "epoch": 46.32, | |
| "learning_rate": 1.3559245960502696e-06, | |
| "loss": 0.2546, | |
| "step": 234500 | |
| }, | |
| { | |
| "epoch": 46.42, | |
| "learning_rate": 1.3534360662278078e-06, | |
| "loss": 0.2551, | |
| "step": 235000 | |
| }, | |
| { | |
| "epoch": 46.51, | |
| "learning_rate": 1.3509425493716337e-06, | |
| "loss": 0.2374, | |
| "step": 235500 | |
| }, | |
| { | |
| "epoch": 46.61, | |
| "learning_rate": 1.3484490325154599e-06, | |
| "loss": 0.2452, | |
| "step": 236000 | |
| }, | |
| { | |
| "epoch": 46.71, | |
| "learning_rate": 1.345955515659286e-06, | |
| "loss": 0.2417, | |
| "step": 236500 | |
| }, | |
| { | |
| "epoch": 46.81, | |
| "learning_rate": 1.3434669858368244e-06, | |
| "loss": 0.2434, | |
| "step": 237000 | |
| }, | |
| { | |
| "epoch": 46.91, | |
| "learning_rate": 1.3409734689806503e-06, | |
| "loss": 0.2407, | |
| "step": 237500 | |
| }, | |
| { | |
| "epoch": 47.0, | |
| "eval_accuracy": 0.8388304183091584, | |
| "eval_f1": 0.4877632813166198, | |
| "eval_loss": 0.7191833257675171, | |
| "eval_precision": 0.4379114990047466, | |
| "eval_recall": 0.550423402617398, | |
| "eval_runtime": 23.4257, | |
| "eval_samples_per_second": 130.156, | |
| "eval_steps_per_second": 16.307, | |
| "step": 237961 | |
| }, | |
| { | |
| "epoch": 47.01, | |
| "learning_rate": 1.3384799521244765e-06, | |
| "loss": 0.2404, | |
| "step": 238000 | |
| }, | |
| { | |
| "epoch": 47.11, | |
| "learning_rate": 1.3359864352683024e-06, | |
| "loss": 0.2394, | |
| "step": 238500 | |
| }, | |
| { | |
| "epoch": 47.21, | |
| "learning_rate": 1.3334929184121287e-06, | |
| "loss": 0.2508, | |
| "step": 239000 | |
| }, | |
| { | |
| "epoch": 47.3, | |
| "learning_rate": 1.331004388589667e-06, | |
| "loss": 0.2454, | |
| "step": 239500 | |
| }, | |
| { | |
| "epoch": 47.4, | |
| "learning_rate": 1.328510871733493e-06, | |
| "loss": 0.2387, | |
| "step": 240000 | |
| }, | |
| { | |
| "epoch": 47.5, | |
| "learning_rate": 1.3260173548773192e-06, | |
| "loss": 0.2426, | |
| "step": 240500 | |
| }, | |
| { | |
| "epoch": 47.6, | |
| "learning_rate": 1.323523838021145e-06, | |
| "loss": 0.2313, | |
| "step": 241000 | |
| }, | |
| { | |
| "epoch": 47.7, | |
| "learning_rate": 1.321030321164971e-06, | |
| "loss": 0.2434, | |
| "step": 241500 | |
| }, | |
| { | |
| "epoch": 47.8, | |
| "learning_rate": 1.3185368043087973e-06, | |
| "loss": 0.2422, | |
| "step": 242000 | |
| }, | |
| { | |
| "epoch": 47.9, | |
| "learning_rate": 1.3160432874526233e-06, | |
| "loss": 0.2391, | |
| "step": 242500 | |
| }, | |
| { | |
| "epoch": 48.0, | |
| "learning_rate": 1.3135497705964492e-06, | |
| "loss": 0.2397, | |
| "step": 243000 | |
| }, | |
| { | |
| "epoch": 48.0, | |
| "eval_accuracy": 0.8379080714914463, | |
| "eval_f1": 0.48708299860471016, | |
| "eval_loss": 0.7313714623451233, | |
| "eval_precision": 0.4344219021042311, | |
| "eval_recall": 0.5542725173210161, | |
| "eval_runtime": 23.7407, | |
| "eval_samples_per_second": 128.429, | |
| "eval_steps_per_second": 16.091, | |
| "step": 243024 | |
| }, | |
| { | |
| "epoch": 48.09, | |
| "learning_rate": 1.3110612407739878e-06, | |
| "loss": 0.2454, | |
| "step": 243500 | |
| }, | |
| { | |
| "epoch": 48.19, | |
| "learning_rate": 1.3085677239178137e-06, | |
| "loss": 0.2403, | |
| "step": 244000 | |
| }, | |
| { | |
| "epoch": 48.29, | |
| "learning_rate": 1.3060742070616397e-06, | |
| "loss": 0.2336, | |
| "step": 244500 | |
| }, | |
| { | |
| "epoch": 48.39, | |
| "learning_rate": 1.3035856772391783e-06, | |
| "loss": 0.2453, | |
| "step": 245000 | |
| }, | |
| { | |
| "epoch": 48.49, | |
| "learning_rate": 1.3010921603830042e-06, | |
| "loss": 0.2378, | |
| "step": 245500 | |
| }, | |
| { | |
| "epoch": 48.59, | |
| "learning_rate": 1.2985986435268301e-06, | |
| "loss": 0.2423, | |
| "step": 246000 | |
| }, | |
| { | |
| "epoch": 48.69, | |
| "learning_rate": 1.2961051266706565e-06, | |
| "loss": 0.2421, | |
| "step": 246500 | |
| }, | |
| { | |
| "epoch": 48.79, | |
| "learning_rate": 1.2936116098144824e-06, | |
| "loss": 0.2428, | |
| "step": 247000 | |
| }, | |
| { | |
| "epoch": 48.88, | |
| "learning_rate": 1.2911180929583083e-06, | |
| "loss": 0.2423, | |
| "step": 247500 | |
| }, | |
| { | |
| "epoch": 48.98, | |
| "learning_rate": 1.288629563135847e-06, | |
| "loss": 0.237, | |
| "step": 248000 | |
| }, | |
| { | |
| "epoch": 49.0, | |
| "eval_accuracy": 0.8377014045696353, | |
| "eval_f1": 0.4901437548420418, | |
| "eval_loss": 0.7322969436645508, | |
| "eval_precision": 0.44338888023672324, | |
| "eval_recall": 0.5479214780600462, | |
| "eval_runtime": 23.821, | |
| "eval_samples_per_second": 127.996, | |
| "eval_steps_per_second": 16.036, | |
| "step": 248087 | |
| }, | |
| { | |
| "epoch": 49.08, | |
| "learning_rate": 1.2861360462796729e-06, | |
| "loss": 0.2419, | |
| "step": 248500 | |
| }, | |
| { | |
| "epoch": 49.18, | |
| "learning_rate": 1.2836425294234988e-06, | |
| "loss": 0.2345, | |
| "step": 249000 | |
| }, | |
| { | |
| "epoch": 49.28, | |
| "learning_rate": 1.2811490125673251e-06, | |
| "loss": 0.2374, | |
| "step": 249500 | |
| }, | |
| { | |
| "epoch": 49.38, | |
| "learning_rate": 1.278655495711151e-06, | |
| "loss": 0.241, | |
| "step": 250000 | |
| }, | |
| { | |
| "epoch": 49.48, | |
| "learning_rate": 1.2761669658886895e-06, | |
| "loss": 0.2362, | |
| "step": 250500 | |
| }, | |
| { | |
| "epoch": 49.58, | |
| "learning_rate": 1.2736734490325156e-06, | |
| "loss": 0.2375, | |
| "step": 251000 | |
| }, | |
| { | |
| "epoch": 49.67, | |
| "learning_rate": 1.2711799321763415e-06, | |
| "loss": 0.2377, | |
| "step": 251500 | |
| }, | |
| { | |
| "epoch": 49.77, | |
| "learning_rate": 1.2686864153201678e-06, | |
| "loss": 0.2387, | |
| "step": 252000 | |
| }, | |
| { | |
| "epoch": 49.87, | |
| "learning_rate": 1.266197885497706e-06, | |
| "loss": 0.2382, | |
| "step": 252500 | |
| }, | |
| { | |
| "epoch": 49.97, | |
| "learning_rate": 1.263704368641532e-06, | |
| "loss": 0.2419, | |
| "step": 253000 | |
| }, | |
| { | |
| "epoch": 50.0, | |
| "eval_accuracy": 0.8384898006046921, | |
| "eval_f1": 0.4932128634436689, | |
| "eval_loss": 0.7357666492462158, | |
| "eval_precision": 0.44433299899699097, | |
| "eval_recall": 0.5541762894534257, | |
| "eval_runtime": 23.5559, | |
| "eval_samples_per_second": 129.437, | |
| "eval_steps_per_second": 16.217, | |
| "step": 253150 | |
| }, | |
| { | |
| "epoch": 50.07, | |
| "learning_rate": 1.2612108517853583e-06, | |
| "loss": 0.2507, | |
| "step": 253500 | |
| }, | |
| { | |
| "epoch": 50.17, | |
| "learning_rate": 1.2587173349291842e-06, | |
| "loss": 0.2388, | |
| "step": 254000 | |
| }, | |
| { | |
| "epoch": 50.27, | |
| "learning_rate": 1.2562238180730102e-06, | |
| "loss": 0.2325, | |
| "step": 254500 | |
| }, | |
| { | |
| "epoch": 50.37, | |
| "learning_rate": 1.2537352882505488e-06, | |
| "loss": 0.2406, | |
| "step": 255000 | |
| }, | |
| { | |
| "epoch": 50.46, | |
| "learning_rate": 1.2512417713943747e-06, | |
| "loss": 0.2246, | |
| "step": 255500 | |
| }, | |
| { | |
| "epoch": 50.56, | |
| "learning_rate": 1.2487482545382008e-06, | |
| "loss": 0.2405, | |
| "step": 256000 | |
| }, | |
| { | |
| "epoch": 50.66, | |
| "learning_rate": 1.2462547376820268e-06, | |
| "loss": 0.2297, | |
| "step": 256500 | |
| }, | |
| { | |
| "epoch": 50.76, | |
| "learning_rate": 1.2437612208258529e-06, | |
| "loss": 0.2303, | |
| "step": 257000 | |
| }, | |
| { | |
| "epoch": 50.86, | |
| "learning_rate": 1.2412726910033913e-06, | |
| "loss": 0.2514, | |
| "step": 257500 | |
| }, | |
| { | |
| "epoch": 50.96, | |
| "learning_rate": 1.2387791741472172e-06, | |
| "loss": 0.248, | |
| "step": 258000 | |
| }, | |
| { | |
| "epoch": 51.0, | |
| "eval_accuracy": 0.8372612805694822, | |
| "eval_f1": 0.48591877355693897, | |
| "eval_loss": 0.7367214560508728, | |
| "eval_precision": 0.43393086755918614, | |
| "eval_recall": 0.5520592763664357, | |
| "eval_runtime": 23.3101, | |
| "eval_samples_per_second": 130.802, | |
| "eval_steps_per_second": 16.388, | |
| "step": 258213 | |
| }, | |
| { | |
| "epoch": 51.06, | |
| "learning_rate": 1.2362856572910434e-06, | |
| "loss": 0.2515, | |
| "step": 258500 | |
| }, | |
| { | |
| "epoch": 51.16, | |
| "learning_rate": 1.2337921404348695e-06, | |
| "loss": 0.2386, | |
| "step": 259000 | |
| }, | |
| { | |
| "epoch": 51.25, | |
| "learning_rate": 1.2312986235786954e-06, | |
| "loss": 0.2333, | |
| "step": 259500 | |
| }, | |
| { | |
| "epoch": 51.35, | |
| "learning_rate": 1.2288100937562338e-06, | |
| "loss": 0.2427, | |
| "step": 260000 | |
| }, | |
| { | |
| "epoch": 51.45, | |
| "learning_rate": 1.22631657690006e-06, | |
| "loss": 0.238, | |
| "step": 260500 | |
| }, | |
| { | |
| "epoch": 51.55, | |
| "learning_rate": 1.2238230600438859e-06, | |
| "loss": 0.2393, | |
| "step": 261000 | |
| }, | |
| { | |
| "epoch": 51.65, | |
| "learning_rate": 1.221329543187712e-06, | |
| "loss": 0.2428, | |
| "step": 261500 | |
| }, | |
| { | |
| "epoch": 51.75, | |
| "learning_rate": 1.2188360263315381e-06, | |
| "loss": 0.2339, | |
| "step": 262000 | |
| }, | |
| { | |
| "epoch": 51.85, | |
| "learning_rate": 1.2163474965090764e-06, | |
| "loss": 0.2446, | |
| "step": 262500 | |
| }, | |
| { | |
| "epoch": 51.95, | |
| "learning_rate": 1.2138539796529025e-06, | |
| "loss": 0.2447, | |
| "step": 263000 | |
| }, | |
| { | |
| "epoch": 52.0, | |
| "eval_accuracy": 0.8375712809521987, | |
| "eval_f1": 0.4877675840978593, | |
| "eval_loss": 0.7343346476554871, | |
| "eval_precision": 0.4365875912408759, | |
| "eval_recall": 0.5525404157043879, | |
| "eval_runtime": 23.403, | |
| "eval_samples_per_second": 130.282, | |
| "eval_steps_per_second": 16.323, | |
| "step": 263276 | |
| }, | |
| { | |
| "epoch": 52.04, | |
| "learning_rate": 1.2113604627967286e-06, | |
| "loss": 0.2364, | |
| "step": 263500 | |
| }, | |
| { | |
| "epoch": 52.14, | |
| "learning_rate": 1.2088669459405547e-06, | |
| "loss": 0.2466, | |
| "step": 264000 | |
| }, | |
| { | |
| "epoch": 52.24, | |
| "learning_rate": 1.2063834031518055e-06, | |
| "loss": 0.2397, | |
| "step": 264500 | |
| }, | |
| { | |
| "epoch": 52.34, | |
| "learning_rate": 1.2038898862956314e-06, | |
| "loss": 0.2418, | |
| "step": 265000 | |
| }, | |
| { | |
| "epoch": 52.44, | |
| "learning_rate": 1.2013963694394575e-06, | |
| "loss": 0.2417, | |
| "step": 265500 | |
| }, | |
| { | |
| "epoch": 52.54, | |
| "learning_rate": 1.1989028525832834e-06, | |
| "loss": 0.2397, | |
| "step": 266000 | |
| }, | |
| { | |
| "epoch": 52.64, | |
| "learning_rate": 1.1964093357271096e-06, | |
| "loss": 0.2353, | |
| "step": 266500 | |
| }, | |
| { | |
| "epoch": 52.74, | |
| "learning_rate": 1.1939158188709357e-06, | |
| "loss": 0.2339, | |
| "step": 267000 | |
| }, | |
| { | |
| "epoch": 52.83, | |
| "learning_rate": 1.1914223020147616e-06, | |
| "loss": 0.2397, | |
| "step": 267500 | |
| }, | |
| { | |
| "epoch": 52.93, | |
| "learning_rate": 1.1889287851585877e-06, | |
| "loss": 0.2365, | |
| "step": 268000 | |
| }, | |
| { | |
| "epoch": 53.0, | |
| "eval_accuracy": 0.8388954801178767, | |
| "eval_f1": 0.4917008898015058, | |
| "eval_loss": 0.7243747711181641, | |
| "eval_precision": 0.44262168823166975, | |
| "eval_recall": 0.5530215550423403, | |
| "eval_runtime": 23.8942, | |
| "eval_samples_per_second": 127.604, | |
| "eval_steps_per_second": 15.987, | |
| "step": 268339 | |
| }, | |
| { | |
| "epoch": 53.03, | |
| "learning_rate": 1.1864352683024139e-06, | |
| "loss": 0.2441, | |
| "step": 268500 | |
| }, | |
| { | |
| "epoch": 53.13, | |
| "learning_rate": 1.183946738479952e-06, | |
| "loss": 0.2346, | |
| "step": 269000 | |
| }, | |
| { | |
| "epoch": 53.23, | |
| "learning_rate": 1.1814532216237782e-06, | |
| "loss": 0.2338, | |
| "step": 269500 | |
| }, | |
| { | |
| "epoch": 53.33, | |
| "learning_rate": 1.1789597047676043e-06, | |
| "loss": 0.2317, | |
| "step": 270000 | |
| }, | |
| { | |
| "epoch": 53.43, | |
| "learning_rate": 1.1764661879114305e-06, | |
| "loss": 0.2358, | |
| "step": 270500 | |
| }, | |
| { | |
| "epoch": 53.53, | |
| "learning_rate": 1.1739726710552564e-06, | |
| "loss": 0.2344, | |
| "step": 271000 | |
| }, | |
| { | |
| "epoch": 53.62, | |
| "learning_rate": 1.1714791541990825e-06, | |
| "loss": 0.2296, | |
| "step": 271500 | |
| }, | |
| { | |
| "epoch": 53.72, | |
| "learning_rate": 1.168990624376621e-06, | |
| "loss": 0.2459, | |
| "step": 272000 | |
| }, | |
| { | |
| "epoch": 53.82, | |
| "learning_rate": 1.1664971075204469e-06, | |
| "loss": 0.2351, | |
| "step": 272500 | |
| }, | |
| { | |
| "epoch": 53.92, | |
| "learning_rate": 1.164003590664273e-06, | |
| "loss": 0.239, | |
| "step": 273000 | |
| }, | |
| { | |
| "epoch": 54.0, | |
| "eval_accuracy": 0.8386275785525661, | |
| "eval_f1": 0.4864291772688719, | |
| "eval_loss": 0.7417691946029663, | |
| "eval_precision": 0.4348650288140734, | |
| "eval_recall": 0.5518668206312548, | |
| "eval_runtime": 24.0372, | |
| "eval_samples_per_second": 126.845, | |
| "eval_steps_per_second": 15.892, | |
| "step": 273402 | |
| }, | |
| { | |
| "epoch": 54.02, | |
| "learning_rate": 1.1615100738080991e-06, | |
| "loss": 0.2333, | |
| "step": 273500 | |
| }, | |
| { | |
| "epoch": 54.12, | |
| "learning_rate": 1.159016556951925e-06, | |
| "loss": 0.2399, | |
| "step": 274000 | |
| }, | |
| { | |
| "epoch": 54.22, | |
| "learning_rate": 1.1565280271294635e-06, | |
| "loss": 0.2508, | |
| "step": 274500 | |
| }, | |
| { | |
| "epoch": 54.32, | |
| "learning_rate": 1.1540345102732896e-06, | |
| "loss": 0.2289, | |
| "step": 275000 | |
| }, | |
| { | |
| "epoch": 54.41, | |
| "learning_rate": 1.1515409934171155e-06, | |
| "loss": 0.2352, | |
| "step": 275500 | |
| }, | |
| { | |
| "epoch": 54.51, | |
| "learning_rate": 1.1490474765609416e-06, | |
| "loss": 0.2317, | |
| "step": 276000 | |
| }, | |
| { | |
| "epoch": 54.61, | |
| "learning_rate": 1.1465539597047677e-06, | |
| "loss": 0.2275, | |
| "step": 276500 | |
| }, | |
| { | |
| "epoch": 54.71, | |
| "learning_rate": 1.144065429882306e-06, | |
| "loss": 0.2359, | |
| "step": 277000 | |
| }, | |
| { | |
| "epoch": 54.81, | |
| "learning_rate": 1.1415719130261321e-06, | |
| "loss": 0.2288, | |
| "step": 277500 | |
| }, | |
| { | |
| "epoch": 54.91, | |
| "learning_rate": 1.1390783961699582e-06, | |
| "loss": 0.2273, | |
| "step": 278000 | |
| }, | |
| { | |
| "epoch": 55.0, | |
| "eval_accuracy": 0.8372651077347009, | |
| "eval_f1": 0.4906031936298643, | |
| "eval_loss": 0.7420364618301392, | |
| "eval_precision": 0.44189095396005246, | |
| "eval_recall": 0.5513856812933026, | |
| "eval_runtime": 23.2371, | |
| "eval_samples_per_second": 131.213, | |
| "eval_steps_per_second": 16.439, | |
| "step": 278465 | |
| }, | |
| { | |
| "epoch": 55.01, | |
| "learning_rate": 1.1365848793137844e-06, | |
| "loss": 0.2417, | |
| "step": 278500 | |
| }, | |
| { | |
| "epoch": 55.11, | |
| "learning_rate": 1.1340913624576103e-06, | |
| "loss": 0.2337, | |
| "step": 279000 | |
| }, | |
| { | |
| "epoch": 55.2, | |
| "learning_rate": 1.1315978456014364e-06, | |
| "loss": 0.2307, | |
| "step": 279500 | |
| }, | |
| { | |
| "epoch": 55.3, | |
| "learning_rate": 1.1291143028126872e-06, | |
| "loss": 0.2269, | |
| "step": 280000 | |
| }, | |
| { | |
| "epoch": 55.4, | |
| "learning_rate": 1.126620785956513e-06, | |
| "loss": 0.2289, | |
| "step": 280500 | |
| }, | |
| { | |
| "epoch": 55.5, | |
| "learning_rate": 1.1241272691003392e-06, | |
| "loss": 0.2377, | |
| "step": 281000 | |
| }, | |
| { | |
| "epoch": 55.6, | |
| "learning_rate": 1.1216337522441653e-06, | |
| "loss": 0.2288, | |
| "step": 281500 | |
| }, | |
| { | |
| "epoch": 55.7, | |
| "learning_rate": 1.1191402353879912e-06, | |
| "loss": 0.2312, | |
| "step": 282000 | |
| }, | |
| { | |
| "epoch": 55.8, | |
| "learning_rate": 1.1166467185318174e-06, | |
| "loss": 0.2358, | |
| "step": 282500 | |
| }, | |
| { | |
| "epoch": 55.9, | |
| "learning_rate": 1.1141532016756435e-06, | |
| "loss": 0.2381, | |
| "step": 283000 | |
| }, | |
| { | |
| "epoch": 55.99, | |
| "learning_rate": 1.1116596848194696e-06, | |
| "loss": 0.2383, | |
| "step": 283500 | |
| }, | |
| { | |
| "epoch": 56.0, | |
| "eval_accuracy": 0.837800910865322, | |
| "eval_f1": 0.48603658794203386, | |
| "eval_loss": 0.7458629012107849, | |
| "eval_precision": 0.433230398433381, | |
| "eval_recall": 0.5535026943802925, | |
| "eval_runtime": 23.9922, | |
| "eval_samples_per_second": 127.083, | |
| "eval_steps_per_second": 15.922, | |
| "step": 283528 | |
| }, | |
| { | |
| "epoch": 56.09, | |
| "learning_rate": 1.1091661679632955e-06, | |
| "loss": 0.2293, | |
| "step": 284000 | |
| }, | |
| { | |
| "epoch": 56.19, | |
| "learning_rate": 1.1066726511071216e-06, | |
| "loss": 0.237, | |
| "step": 284500 | |
| }, | |
| { | |
| "epoch": 56.29, | |
| "learning_rate": 1.10418412128466e-06, | |
| "loss": 0.2326, | |
| "step": 285000 | |
| }, | |
| { | |
| "epoch": 56.39, | |
| "learning_rate": 1.101690604428486e-06, | |
| "loss": 0.232, | |
| "step": 285500 | |
| }, | |
| { | |
| "epoch": 56.49, | |
| "learning_rate": 1.0992020746060244e-06, | |
| "loss": 0.233, | |
| "step": 286000 | |
| }, | |
| { | |
| "epoch": 56.59, | |
| "learning_rate": 1.0967085577498504e-06, | |
| "loss": 0.2384, | |
| "step": 286500 | |
| }, | |
| { | |
| "epoch": 56.69, | |
| "learning_rate": 1.0942150408936765e-06, | |
| "loss": 0.2327, | |
| "step": 287000 | |
| }, | |
| { | |
| "epoch": 56.78, | |
| "learning_rate": 1.0917215240375026e-06, | |
| "loss": 0.2289, | |
| "step": 287500 | |
| }, | |
| { | |
| "epoch": 56.88, | |
| "learning_rate": 1.0892280071813287e-06, | |
| "loss": 0.2313, | |
| "step": 288000 | |
| }, | |
| { | |
| "epoch": 56.98, | |
| "learning_rate": 1.0867344903251546e-06, | |
| "loss": 0.2301, | |
| "step": 288500 | |
| }, | |
| { | |
| "epoch": 57.0, | |
| "eval_accuracy": 0.8362585632821768, | |
| "eval_f1": 0.4886406904429496, | |
| "eval_loss": 0.745151937007904, | |
| "eval_precision": 0.4360135900339751, | |
| "eval_recall": 0.555715935334873, | |
| "eval_runtime": 23.3249, | |
| "eval_samples_per_second": 130.719, | |
| "eval_steps_per_second": 16.377, | |
| "step": 288591 | |
| }, | |
| { | |
| "epoch": 57.08, | |
| "learning_rate": 1.0842409734689808e-06, | |
| "loss": 0.2353, | |
| "step": 289000 | |
| }, | |
| { | |
| "epoch": 57.18, | |
| "learning_rate": 1.0817474566128069e-06, | |
| "loss": 0.2281, | |
| "step": 289500 | |
| }, | |
| { | |
| "epoch": 57.28, | |
| "learning_rate": 1.0792539397566328e-06, | |
| "loss": 0.2427, | |
| "step": 290000 | |
| }, | |
| { | |
| "epoch": 57.38, | |
| "learning_rate": 1.076760422900459e-06, | |
| "loss": 0.2285, | |
| "step": 290500 | |
| }, | |
| { | |
| "epoch": 57.48, | |
| "learning_rate": 1.0742718930779974e-06, | |
| "loss": 0.2288, | |
| "step": 291000 | |
| }, | |
| { | |
| "epoch": 57.57, | |
| "learning_rate": 1.0717783762218235e-06, | |
| "loss": 0.2317, | |
| "step": 291500 | |
| }, | |
| { | |
| "epoch": 57.67, | |
| "learning_rate": 1.0692848593656494e-06, | |
| "loss": 0.2247, | |
| "step": 292000 | |
| }, | |
| { | |
| "epoch": 57.77, | |
| "learning_rate": 1.0667913425094755e-06, | |
| "loss": 0.2336, | |
| "step": 292500 | |
| }, | |
| { | |
| "epoch": 57.87, | |
| "learning_rate": 1.0642978256533014e-06, | |
| "loss": 0.2302, | |
| "step": 293000 | |
| }, | |
| { | |
| "epoch": 57.97, | |
| "learning_rate": 1.0618043087971276e-06, | |
| "loss": 0.2382, | |
| "step": 293500 | |
| }, | |
| { | |
| "epoch": 58.0, | |
| "eval_accuracy": 0.8389949864135635, | |
| "eval_f1": 0.49114762450643235, | |
| "eval_loss": 0.7444238662719727, | |
| "eval_precision": 0.4394802826532938, | |
| "eval_recall": 0.5565819861431871, | |
| "eval_runtime": 23.2287, | |
| "eval_samples_per_second": 131.26, | |
| "eval_steps_per_second": 16.445, | |
| "step": 293654 | |
| }, | |
| { | |
| "epoch": 58.07, | |
| "learning_rate": 1.0593107919409535e-06, | |
| "loss": 0.2279, | |
| "step": 294000 | |
| }, | |
| { | |
| "epoch": 58.17, | |
| "learning_rate": 1.0568172750847796e-06, | |
| "loss": 0.2375, | |
| "step": 294500 | |
| }, | |
| { | |
| "epoch": 58.27, | |
| "learning_rate": 1.0543337322960304e-06, | |
| "loss": 0.2264, | |
| "step": 295000 | |
| }, | |
| { | |
| "epoch": 58.36, | |
| "learning_rate": 1.0518402154398565e-06, | |
| "loss": 0.2357, | |
| "step": 295500 | |
| }, | |
| { | |
| "epoch": 58.46, | |
| "learning_rate": 1.0493466985836826e-06, | |
| "loss": 0.2345, | |
| "step": 296000 | |
| }, | |
| { | |
| "epoch": 58.56, | |
| "learning_rate": 1.0468531817275085e-06, | |
| "loss": 0.2256, | |
| "step": 296500 | |
| }, | |
| { | |
| "epoch": 58.66, | |
| "learning_rate": 1.0443596648713347e-06, | |
| "loss": 0.234, | |
| "step": 297000 | |
| }, | |
| { | |
| "epoch": 58.76, | |
| "learning_rate": 1.041871135048873e-06, | |
| "loss": 0.2261, | |
| "step": 297500 | |
| }, | |
| { | |
| "epoch": 58.86, | |
| "learning_rate": 1.039377618192699e-06, | |
| "loss": 0.2392, | |
| "step": 298000 | |
| }, | |
| { | |
| "epoch": 58.96, | |
| "learning_rate": 1.0368841013365251e-06, | |
| "loss": 0.2324, | |
| "step": 298500 | |
| }, | |
| { | |
| "epoch": 59.0, | |
| "eval_accuracy": 0.8388265911439396, | |
| "eval_f1": 0.4904518329070759, | |
| "eval_loss": 0.7444677948951721, | |
| "eval_precision": 0.44023569023569026, | |
| "eval_recall": 0.553598922247883, | |
| "eval_runtime": 24.0702, | |
| "eval_samples_per_second": 126.671, | |
| "eval_steps_per_second": 15.87, | |
| "step": 298717 | |
| }, | |
| { | |
| "epoch": 59.06, | |
| "learning_rate": 1.0343905844803513e-06, | |
| "loss": 0.241, | |
| "step": 299000 | |
| }, | |
| { | |
| "epoch": 59.15, | |
| "learning_rate": 1.0318970676241772e-06, | |
| "loss": 0.2239, | |
| "step": 299500 | |
| }, | |
| { | |
| "epoch": 59.25, | |
| "learning_rate": 1.0294035507680033e-06, | |
| "loss": 0.227, | |
| "step": 300000 | |
| }, | |
| { | |
| "epoch": 59.35, | |
| "learning_rate": 1.0269150209455417e-06, | |
| "loss": 0.2331, | |
| "step": 300500 | |
| }, | |
| { | |
| "epoch": 59.45, | |
| "learning_rate": 1.0244215040893679e-06, | |
| "loss": 0.2204, | |
| "step": 301000 | |
| }, | |
| { | |
| "epoch": 59.55, | |
| "learning_rate": 1.0219279872331938e-06, | |
| "loss": 0.2362, | |
| "step": 301500 | |
| }, | |
| { | |
| "epoch": 59.65, | |
| "learning_rate": 1.01943447037702e-06, | |
| "loss": 0.2263, | |
| "step": 302000 | |
| }, | |
| { | |
| "epoch": 59.75, | |
| "learning_rate": 1.0169459405545583e-06, | |
| "loss": 0.2359, | |
| "step": 302500 | |
| }, | |
| { | |
| "epoch": 59.85, | |
| "learning_rate": 1.0144524236983843e-06, | |
| "loss": 0.2358, | |
| "step": 303000 | |
| }, | |
| { | |
| "epoch": 59.94, | |
| "learning_rate": 1.0119589068422104e-06, | |
| "loss": 0.2377, | |
| "step": 303500 | |
| }, | |
| { | |
| "epoch": 60.0, | |
| "eval_accuracy": 0.8369665888476405, | |
| "eval_f1": 0.48964250629991884, | |
| "eval_loss": 0.752280056476593, | |
| "eval_precision": 0.4402119652868443, | |
| "eval_recall": 0.5515781370284835, | |
| "eval_runtime": 23.2481, | |
| "eval_samples_per_second": 131.15, | |
| "eval_steps_per_second": 16.431, | |
| "step": 303780 | |
| }, | |
| { | |
| "epoch": 60.04, | |
| "learning_rate": 1.0094653899860365e-06, | |
| "loss": 0.2355, | |
| "step": 304000 | |
| }, | |
| { | |
| "epoch": 60.14, | |
| "learning_rate": 1.0069718731298624e-06, | |
| "loss": 0.2269, | |
| "step": 304500 | |
| }, | |
| { | |
| "epoch": 60.24, | |
| "learning_rate": 1.0044833433074009e-06, | |
| "loss": 0.2294, | |
| "step": 305000 | |
| }, | |
| { | |
| "epoch": 60.34, | |
| "learning_rate": 1.001989826451227e-06, | |
| "loss": 0.2317, | |
| "step": 305500 | |
| }, | |
| { | |
| "epoch": 60.44, | |
| "learning_rate": 9.99496309595053e-07, | |
| "loss": 0.2251, | |
| "step": 306000 | |
| }, | |
| { | |
| "epoch": 60.54, | |
| "learning_rate": 9.97002792738879e-07, | |
| "loss": 0.2348, | |
| "step": 306500 | |
| }, | |
| { | |
| "epoch": 60.64, | |
| "learning_rate": 9.945142629164175e-07, | |
| "loss": 0.2337, | |
| "step": 307000 | |
| }, | |
| { | |
| "epoch": 60.73, | |
| "learning_rate": 9.920207460602436e-07, | |
| "loss": 0.2243, | |
| "step": 307500 | |
| }, | |
| { | |
| "epoch": 60.83, | |
| "learning_rate": 9.895272292040695e-07, | |
| "loss": 0.2304, | |
| "step": 308000 | |
| }, | |
| { | |
| "epoch": 60.93, | |
| "learning_rate": 9.870337123478956e-07, | |
| "loss": 0.22, | |
| "step": 308500 | |
| }, | |
| { | |
| "epoch": 61.0, | |
| "eval_accuracy": 0.8390600482222818, | |
| "eval_f1": 0.49161582113751756, | |
| "eval_loss": 0.7522650957107544, | |
| "eval_precision": 0.44162514373323114, | |
| "eval_recall": 0.5543687451886066, | |
| "eval_runtime": 24.048, | |
| "eval_samples_per_second": 126.788, | |
| "eval_steps_per_second": 15.885, | |
| "step": 308843 | |
| }, | |
| { | |
| "epoch": 61.03, | |
| "learning_rate": 9.84545182525434e-07, | |
| "loss": 0.2371, | |
| "step": 309000 | |
| }, | |
| { | |
| "epoch": 61.13, | |
| "learning_rate": 9.8205166566926e-07, | |
| "loss": 0.2343, | |
| "step": 309500 | |
| }, | |
| { | |
| "epoch": 61.23, | |
| "learning_rate": 9.795581488130861e-07, | |
| "loss": 0.2277, | |
| "step": 310000 | |
| }, | |
| { | |
| "epoch": 61.33, | |
| "learning_rate": 9.770646319569122e-07, | |
| "loss": 0.222, | |
| "step": 310500 | |
| }, | |
| { | |
| "epoch": 61.43, | |
| "learning_rate": 9.745711151007382e-07, | |
| "loss": 0.2267, | |
| "step": 311000 | |
| }, | |
| { | |
| "epoch": 61.52, | |
| "learning_rate": 9.720825852782766e-07, | |
| "loss": 0.2287, | |
| "step": 311500 | |
| }, | |
| { | |
| "epoch": 61.62, | |
| "learning_rate": 9.695890684221027e-07, | |
| "loss": 0.2382, | |
| "step": 312000 | |
| }, | |
| { | |
| "epoch": 61.72, | |
| "learning_rate": 9.670955515659286e-07, | |
| "loss": 0.2295, | |
| "step": 312500 | |
| }, | |
| { | |
| "epoch": 61.82, | |
| "learning_rate": 9.646020347097548e-07, | |
| "loss": 0.2211, | |
| "step": 313000 | |
| }, | |
| { | |
| "epoch": 61.92, | |
| "learning_rate": 9.621085178535809e-07, | |
| "loss": 0.2241, | |
| "step": 313500 | |
| }, | |
| { | |
| "epoch": 62.0, | |
| "eval_accuracy": 0.8374909104826055, | |
| "eval_f1": 0.48761904761904756, | |
| "eval_loss": 0.7565447688102722, | |
| "eval_precision": 0.4352754477442757, | |
| "eval_recall": 0.5542725173210161, | |
| "eval_runtime": 23.4085, | |
| "eval_samples_per_second": 130.252, | |
| "eval_steps_per_second": 16.319, | |
| "step": 313906 | |
| }, | |
| { | |
| "epoch": 62.02, | |
| "learning_rate": 9.596150009974068e-07, | |
| "loss": 0.2265, | |
| "step": 314000 | |
| }, | |
| { | |
| "epoch": 62.12, | |
| "learning_rate": 9.57121484141233e-07, | |
| "loss": 0.2231, | |
| "step": 314500 | |
| }, | |
| { | |
| "epoch": 62.22, | |
| "learning_rate": 9.546279672850588e-07, | |
| "loss": 0.2279, | |
| "step": 315000 | |
| }, | |
| { | |
| "epoch": 62.31, | |
| "learning_rate": 9.521394374625974e-07, | |
| "loss": 0.2293, | |
| "step": 315500 | |
| }, | |
| { | |
| "epoch": 62.41, | |
| "learning_rate": 9.496459206064233e-07, | |
| "loss": 0.2265, | |
| "step": 316000 | |
| }, | |
| { | |
| "epoch": 62.51, | |
| "learning_rate": 9.471573907839618e-07, | |
| "loss": 0.2177, | |
| "step": 316500 | |
| }, | |
| { | |
| "epoch": 62.61, | |
| "learning_rate": 9.446638739277879e-07, | |
| "loss": 0.2271, | |
| "step": 317000 | |
| }, | |
| { | |
| "epoch": 62.71, | |
| "learning_rate": 9.421703570716139e-07, | |
| "loss": 0.2298, | |
| "step": 317500 | |
| }, | |
| { | |
| "epoch": 62.81, | |
| "learning_rate": 9.396768402154399e-07, | |
| "loss": 0.2224, | |
| "step": 318000 | |
| }, | |
| { | |
| "epoch": 62.91, | |
| "learning_rate": 9.371883103929783e-07, | |
| "loss": 0.2294, | |
| "step": 318500 | |
| }, | |
| { | |
| "epoch": 63.0, | |
| "eval_accuracy": 0.8375751081174174, | |
| "eval_f1": 0.49037727850784235, | |
| "eval_loss": 0.7564020156860352, | |
| "eval_precision": 0.43824821942718595, | |
| "eval_recall": 0.5565819861431871, | |
| "eval_runtime": 23.5821, | |
| "eval_samples_per_second": 129.293, | |
| "eval_steps_per_second": 16.199, | |
| "step": 318969 | |
| }, | |
| { | |
| "epoch": 63.01, | |
| "learning_rate": 9.346947935368044e-07, | |
| "loss": 0.2259, | |
| "step": 319000 | |
| }, | |
| { | |
| "epoch": 63.1, | |
| "learning_rate": 9.322012766806304e-07, | |
| "loss": 0.2192, | |
| "step": 319500 | |
| }, | |
| { | |
| "epoch": 63.2, | |
| "learning_rate": 9.297127468581689e-07, | |
| "loss": 0.2248, | |
| "step": 320000 | |
| }, | |
| { | |
| "epoch": 63.3, | |
| "learning_rate": 9.272192300019948e-07, | |
| "loss": 0.2301, | |
| "step": 320500 | |
| }, | |
| { | |
| "epoch": 63.4, | |
| "learning_rate": 9.24725713145821e-07, | |
| "loss": 0.2351, | |
| "step": 321000 | |
| }, | |
| { | |
| "epoch": 63.5, | |
| "learning_rate": 9.22232196289647e-07, | |
| "loss": 0.2335, | |
| "step": 321500 | |
| }, | |
| { | |
| "epoch": 63.6, | |
| "learning_rate": 9.197386794334731e-07, | |
| "loss": 0.2288, | |
| "step": 322000 | |
| }, | |
| { | |
| "epoch": 63.7, | |
| "learning_rate": 9.17245162577299e-07, | |
| "loss": 0.2216, | |
| "step": 322500 | |
| }, | |
| { | |
| "epoch": 63.8, | |
| "learning_rate": 9.147516457211251e-07, | |
| "loss": 0.225, | |
| "step": 323000 | |
| }, | |
| { | |
| "epoch": 63.89, | |
| "learning_rate": 9.122581288649513e-07, | |
| "loss": 0.2375, | |
| "step": 323500 | |
| }, | |
| { | |
| "epoch": 63.99, | |
| "learning_rate": 9.097646120087772e-07, | |
| "loss": 0.2271, | |
| "step": 324000 | |
| }, | |
| { | |
| "epoch": 64.0, | |
| "eval_accuracy": 0.8373033793868881, | |
| "eval_f1": 0.49073640274287667, | |
| "eval_loss": 0.7552084922790527, | |
| "eval_precision": 0.44020783984106365, | |
| "eval_recall": 0.5543687451886066, | |
| "eval_runtime": 24.2365, | |
| "eval_samples_per_second": 125.802, | |
| "eval_steps_per_second": 15.761, | |
| "step": 324032 | |
| }, | |
| { | |
| "epoch": 64.09, | |
| "learning_rate": 9.072710951526033e-07, | |
| "loss": 0.2197, | |
| "step": 324500 | |
| }, | |
| { | |
| "epoch": 64.19, | |
| "learning_rate": 9.047825653301418e-07, | |
| "loss": 0.2251, | |
| "step": 325000 | |
| }, | |
| { | |
| "epoch": 64.29, | |
| "learning_rate": 9.022890484739677e-07, | |
| "loss": 0.2232, | |
| "step": 325500 | |
| }, | |
| { | |
| "epoch": 64.39, | |
| "learning_rate": 8.997955316177938e-07, | |
| "loss": 0.2338, | |
| "step": 326000 | |
| }, | |
| { | |
| "epoch": 64.49, | |
| "learning_rate": 8.973020147616199e-07, | |
| "loss": 0.2304, | |
| "step": 326500 | |
| }, | |
| { | |
| "epoch": 64.59, | |
| "learning_rate": 8.948134849391583e-07, | |
| "loss": 0.2264, | |
| "step": 327000 | |
| }, | |
| { | |
| "epoch": 64.68, | |
| "learning_rate": 8.923199680829843e-07, | |
| "loss": 0.2274, | |
| "step": 327500 | |
| }, | |
| { | |
| "epoch": 64.78, | |
| "learning_rate": 8.898264512268104e-07, | |
| "loss": 0.232, | |
| "step": 328000 | |
| }, | |
| { | |
| "epoch": 64.88, | |
| "learning_rate": 8.873329343706365e-07, | |
| "loss": 0.2282, | |
| "step": 328500 | |
| }, | |
| { | |
| "epoch": 64.98, | |
| "learning_rate": 8.848394175144624e-07, | |
| "loss": 0.2273, | |
| "step": 329000 | |
| }, | |
| { | |
| "epoch": 65.0, | |
| "eval_accuracy": 0.8390409123961882, | |
| "eval_f1": 0.49424991417782355, | |
| "eval_loss": 0.7529916763305664, | |
| "eval_precision": 0.44601920693928127, | |
| "eval_recall": 0.5541762894534257, | |
| "eval_runtime": 23.3862, | |
| "eval_samples_per_second": 130.376, | |
| "eval_steps_per_second": 16.334, | |
| "step": 329095 | |
| }, | |
| { | |
| "epoch": 65.08, | |
| "learning_rate": 8.823508876920009e-07, | |
| "loss": 0.2284, | |
| "step": 329500 | |
| }, | |
| { | |
| "epoch": 65.18, | |
| "learning_rate": 8.79857370835827e-07, | |
| "loss": 0.2289, | |
| "step": 330000 | |
| }, | |
| { | |
| "epoch": 65.28, | |
| "learning_rate": 8.773638539796529e-07, | |
| "loss": 0.2342, | |
| "step": 330500 | |
| }, | |
| { | |
| "epoch": 65.38, | |
| "learning_rate": 8.748753241571914e-07, | |
| "loss": 0.2251, | |
| "step": 331000 | |
| }, | |
| { | |
| "epoch": 65.48, | |
| "learning_rate": 8.723818073010175e-07, | |
| "loss": 0.2293, | |
| "step": 331500 | |
| }, | |
| { | |
| "epoch": 65.57, | |
| "learning_rate": 8.698882904448434e-07, | |
| "loss": 0.2346, | |
| "step": 332000 | |
| }, | |
| { | |
| "epoch": 65.67, | |
| "learning_rate": 8.673947735886695e-07, | |
| "loss": 0.2329, | |
| "step": 332500 | |
| }, | |
| { | |
| "epoch": 65.77, | |
| "learning_rate": 8.649012567324956e-07, | |
| "loss": 0.2259, | |
| "step": 333000 | |
| }, | |
| { | |
| "epoch": 65.87, | |
| "learning_rate": 8.624077398763217e-07, | |
| "loss": 0.2227, | |
| "step": 333500 | |
| }, | |
| { | |
| "epoch": 65.97, | |
| "learning_rate": 8.599142230201477e-07, | |
| "loss": 0.2217, | |
| "step": 334000 | |
| }, | |
| { | |
| "epoch": 66.0, | |
| "eval_accuracy": 0.8372995522216694, | |
| "eval_f1": 0.4910174542358451, | |
| "eval_loss": 0.7608162760734558, | |
| "eval_precision": 0.44029622843182165, | |
| "eval_recall": 0.5549461123941494, | |
| "eval_runtime": 24.1639, | |
| "eval_samples_per_second": 126.18, | |
| "eval_steps_per_second": 15.809, | |
| "step": 334158 | |
| }, | |
| { | |
| "epoch": 66.07, | |
| "learning_rate": 8.574207061639737e-07, | |
| "loss": 0.2267, | |
| "step": 334500 | |
| }, | |
| { | |
| "epoch": 66.17, | |
| "learning_rate": 8.549271893077998e-07, | |
| "loss": 0.2262, | |
| "step": 335000 | |
| }, | |
| { | |
| "epoch": 66.27, | |
| "learning_rate": 8.524386594853382e-07, | |
| "loss": 0.2277, | |
| "step": 335500 | |
| }, | |
| { | |
| "epoch": 66.36, | |
| "learning_rate": 8.499451426291643e-07, | |
| "loss": 0.2242, | |
| "step": 336000 | |
| }, | |
| { | |
| "epoch": 66.46, | |
| "learning_rate": 8.474516257729903e-07, | |
| "loss": 0.2329, | |
| "step": 336500 | |
| }, | |
| { | |
| "epoch": 66.56, | |
| "learning_rate": 8.449581089168163e-07, | |
| "loss": 0.227, | |
| "step": 337000 | |
| }, | |
| { | |
| "epoch": 66.66, | |
| "learning_rate": 8.424645920606423e-07, | |
| "loss": 0.2201, | |
| "step": 337500 | |
| }, | |
| { | |
| "epoch": 66.76, | |
| "learning_rate": 8.399760622381809e-07, | |
| "loss": 0.2354, | |
| "step": 338000 | |
| }, | |
| { | |
| "epoch": 66.86, | |
| "learning_rate": 8.374825453820068e-07, | |
| "loss": 0.227, | |
| "step": 338500 | |
| }, | |
| { | |
| "epoch": 66.96, | |
| "learning_rate": 8.349890285258329e-07, | |
| "loss": 0.2236, | |
| "step": 339000 | |
| }, | |
| { | |
| "epoch": 67.0, | |
| "eval_accuracy": 0.8383099238394122, | |
| "eval_f1": 0.4886561954624782, | |
| "eval_loss": 0.7648459076881409, | |
| "eval_precision": 0.4381344935501107, | |
| "eval_recall": 0.552347959969207, | |
| "eval_runtime": 24.0499, | |
| "eval_samples_per_second": 126.778, | |
| "eval_steps_per_second": 15.884, | |
| "step": 339221 | |
| }, | |
| { | |
| "epoch": 67.06, | |
| "learning_rate": 8.324955116696589e-07, | |
| "loss": 0.2249, | |
| "step": 339500 | |
| }, | |
| { | |
| "epoch": 67.15, | |
| "learning_rate": 8.300019948134851e-07, | |
| "loss": 0.2288, | |
| "step": 340000 | |
| }, | |
| { | |
| "epoch": 67.25, | |
| "learning_rate": 8.275134649910234e-07, | |
| "loss": 0.2279, | |
| "step": 340500 | |
| }, | |
| { | |
| "epoch": 67.35, | |
| "learning_rate": 8.250199481348494e-07, | |
| "loss": 0.2237, | |
| "step": 341000 | |
| }, | |
| { | |
| "epoch": 67.45, | |
| "learning_rate": 8.225264312786756e-07, | |
| "loss": 0.2217, | |
| "step": 341500 | |
| }, | |
| { | |
| "epoch": 67.55, | |
| "learning_rate": 8.200329144225016e-07, | |
| "loss": 0.2337, | |
| "step": 342000 | |
| }, | |
| { | |
| "epoch": 67.65, | |
| "learning_rate": 8.1754438460004e-07, | |
| "loss": 0.2227, | |
| "step": 342500 | |
| }, | |
| { | |
| "epoch": 67.75, | |
| "learning_rate": 8.15050867743866e-07, | |
| "loss": 0.2251, | |
| "step": 343000 | |
| }, | |
| { | |
| "epoch": 67.85, | |
| "learning_rate": 8.12557350887692e-07, | |
| "loss": 0.2152, | |
| "step": 343500 | |
| }, | |
| { | |
| "epoch": 67.94, | |
| "learning_rate": 8.100638340315181e-07, | |
| "loss": 0.2186, | |
| "step": 344000 | |
| }, | |
| { | |
| "epoch": 68.0, | |
| "eval_accuracy": 0.8376669600826667, | |
| "eval_f1": 0.48827047893776776, | |
| "eval_loss": 0.7637174129486084, | |
| "eval_precision": 0.43661330703285034, | |
| "eval_recall": 0.5537913779830639, | |
| "eval_runtime": 23.9648, | |
| "eval_samples_per_second": 127.228, | |
| "eval_steps_per_second": 15.94, | |
| "step": 344284 | |
| }, | |
| { | |
| "epoch": 68.04, | |
| "learning_rate": 8.075753042090566e-07, | |
| "loss": 0.2306, | |
| "step": 344500 | |
| }, | |
| { | |
| "epoch": 68.14, | |
| "learning_rate": 8.05086774386595e-07, | |
| "loss": 0.2247, | |
| "step": 345000 | |
| }, | |
| { | |
| "epoch": 68.24, | |
| "learning_rate": 8.02593257530421e-07, | |
| "loss": 0.2277, | |
| "step": 345500 | |
| }, | |
| { | |
| "epoch": 68.34, | |
| "learning_rate": 8.000997406742471e-07, | |
| "loss": 0.2197, | |
| "step": 346000 | |
| }, | |
| { | |
| "epoch": 68.44, | |
| "learning_rate": 7.97606223818073e-07, | |
| "loss": 0.2357, | |
| "step": 346500 | |
| }, | |
| { | |
| "epoch": 68.54, | |
| "learning_rate": 7.951127069618991e-07, | |
| "loss": 0.2294, | |
| "step": 347000 | |
| }, | |
| { | |
| "epoch": 68.64, | |
| "learning_rate": 7.926191901057253e-07, | |
| "loss": 0.2169, | |
| "step": 347500 | |
| }, | |
| { | |
| "epoch": 68.73, | |
| "learning_rate": 7.901256732495512e-07, | |
| "loss": 0.2302, | |
| "step": 348000 | |
| }, | |
| { | |
| "epoch": 68.83, | |
| "learning_rate": 7.876321563933773e-07, | |
| "loss": 0.2298, | |
| "step": 348500 | |
| }, | |
| { | |
| "epoch": 68.93, | |
| "learning_rate": 7.851386395372033e-07, | |
| "loss": 0.2138, | |
| "step": 349000 | |
| }, | |
| { | |
| "epoch": 69.0, | |
| "eval_accuracy": 0.8371770829346703, | |
| "eval_f1": 0.48854312800238064, | |
| "eval_loss": 0.7689042091369629, | |
| "eval_precision": 0.43759043484883103, | |
| "eval_recall": 0.5529253271747498, | |
| "eval_runtime": 25.1434, | |
| "eval_samples_per_second": 121.265, | |
| "eval_steps_per_second": 15.193, | |
| "step": 349347 | |
| }, | |
| { | |
| "epoch": 69.03, | |
| "learning_rate": 7.826501097147417e-07, | |
| "loss": 0.2283, | |
| "step": 349500 | |
| }, | |
| { | |
| "epoch": 69.13, | |
| "learning_rate": 7.801565928585678e-07, | |
| "loss": 0.2206, | |
| "step": 350000 | |
| }, | |
| { | |
| "epoch": 69.23, | |
| "learning_rate": 7.776630760023938e-07, | |
| "loss": 0.2242, | |
| "step": 350500 | |
| }, | |
| { | |
| "epoch": 69.33, | |
| "learning_rate": 7.751745461799321e-07, | |
| "loss": 0.2172, | |
| "step": 351000 | |
| }, | |
| { | |
| "epoch": 69.43, | |
| "learning_rate": 7.726810293237583e-07, | |
| "loss": 0.2189, | |
| "step": 351500 | |
| }, | |
| { | |
| "epoch": 69.52, | |
| "learning_rate": 7.701875124675844e-07, | |
| "loss": 0.2224, | |
| "step": 352000 | |
| }, | |
| { | |
| "epoch": 69.62, | |
| "learning_rate": 7.676939956114104e-07, | |
| "loss": 0.2122, | |
| "step": 352500 | |
| }, | |
| { | |
| "epoch": 69.72, | |
| "learning_rate": 7.652004787552364e-07, | |
| "loss": 0.2306, | |
| "step": 353000 | |
| }, | |
| { | |
| "epoch": 69.82, | |
| "learning_rate": 7.627069618990624e-07, | |
| "loss": 0.2245, | |
| "step": 353500 | |
| }, | |
| { | |
| "epoch": 69.92, | |
| "learning_rate": 7.602134450428886e-07, | |
| "loss": 0.2353, | |
| "step": 354000 | |
| }, | |
| { | |
| "epoch": 70.0, | |
| "eval_accuracy": 0.8379654789697272, | |
| "eval_f1": 0.49071425521922896, | |
| "eval_loss": 0.7559919953346252, | |
| "eval_precision": 0.44102524748676236, | |
| "eval_recall": 0.5530215550423403, | |
| "eval_runtime": 23.4919, | |
| "eval_samples_per_second": 129.789, | |
| "eval_steps_per_second": 16.261, | |
| "step": 354410 | |
| }, | |
| { | |
| "epoch": 70.02, | |
| "learning_rate": 7.577199281867147e-07, | |
| "loss": 0.2265, | |
| "step": 354500 | |
| }, | |
| { | |
| "epoch": 70.12, | |
| "learning_rate": 7.552264113305406e-07, | |
| "loss": 0.2252, | |
| "step": 355000 | |
| }, | |
| { | |
| "epoch": 70.22, | |
| "learning_rate": 7.52737881508079e-07, | |
| "loss": 0.2197, | |
| "step": 355500 | |
| }, | |
| { | |
| "epoch": 70.31, | |
| "learning_rate": 7.502443646519052e-07, | |
| "loss": 0.2233, | |
| "step": 356000 | |
| }, | |
| { | |
| "epoch": 70.41, | |
| "learning_rate": 7.477508477957311e-07, | |
| "loss": 0.223, | |
| "step": 356500 | |
| }, | |
| { | |
| "epoch": 70.51, | |
| "learning_rate": 7.452573309395572e-07, | |
| "loss": 0.2363, | |
| "step": 357000 | |
| }, | |
| { | |
| "epoch": 70.61, | |
| "learning_rate": 7.427638140833833e-07, | |
| "loss": 0.2181, | |
| "step": 357500 | |
| }, | |
| { | |
| "epoch": 70.71, | |
| "learning_rate": 7.402702972272092e-07, | |
| "loss": 0.2208, | |
| "step": 358000 | |
| }, | |
| { | |
| "epoch": 70.81, | |
| "learning_rate": 7.377767803710354e-07, | |
| "loss": 0.2221, | |
| "step": 358500 | |
| }, | |
| { | |
| "epoch": 70.91, | |
| "learning_rate": 7.352832635148614e-07, | |
| "loss": 0.2245, | |
| "step": 359000 | |
| }, | |
| { | |
| "epoch": 71.0, | |
| "eval_accuracy": 0.839415974587623, | |
| "eval_f1": 0.489203721089016, | |
| "eval_loss": 0.7731532454490662, | |
| "eval_precision": 0.4395031436896182, | |
| "eval_recall": 0.5515781370284835, | |
| "eval_runtime": 23.9793, | |
| "eval_samples_per_second": 127.151, | |
| "eval_steps_per_second": 15.93, | |
| "step": 359473 | |
| }, | |
| { | |
| "epoch": 71.01, | |
| "learning_rate": 7.327947336923997e-07, | |
| "loss": 0.2226, | |
| "step": 359500 | |
| }, | |
| { | |
| "epoch": 71.1, | |
| "learning_rate": 7.303062038699383e-07, | |
| "loss": 0.2242, | |
| "step": 360000 | |
| }, | |
| { | |
| "epoch": 71.2, | |
| "learning_rate": 7.278176740474765e-07, | |
| "loss": 0.221, | |
| "step": 360500 | |
| }, | |
| { | |
| "epoch": 71.3, | |
| "learning_rate": 7.253241571913026e-07, | |
| "loss": 0.2187, | |
| "step": 361000 | |
| }, | |
| { | |
| "epoch": 71.4, | |
| "learning_rate": 7.228306403351288e-07, | |
| "loss": 0.2279, | |
| "step": 361500 | |
| }, | |
| { | |
| "epoch": 71.5, | |
| "learning_rate": 7.203371234789548e-07, | |
| "loss": 0.2328, | |
| "step": 362000 | |
| }, | |
| { | |
| "epoch": 71.6, | |
| "learning_rate": 7.178436066227808e-07, | |
| "loss": 0.2199, | |
| "step": 362500 | |
| }, | |
| { | |
| "epoch": 71.7, | |
| "learning_rate": 7.153500897666068e-07, | |
| "loss": 0.2272, | |
| "step": 363000 | |
| }, | |
| { | |
| "epoch": 71.8, | |
| "learning_rate": 7.128565729104329e-07, | |
| "loss": 0.227, | |
| "step": 363500 | |
| }, | |
| { | |
| "epoch": 71.89, | |
| "learning_rate": 7.103680430879713e-07, | |
| "loss": 0.2213, | |
| "step": 364000 | |
| }, | |
| { | |
| "epoch": 71.99, | |
| "learning_rate": 7.078745262317974e-07, | |
| "loss": 0.2239, | |
| "step": 364500 | |
| }, | |
| { | |
| "epoch": 72.0, | |
| "eval_accuracy": 0.8369130085345784, | |
| "eval_f1": 0.48701106072805866, | |
| "eval_loss": 0.7701214551925659, | |
| "eval_precision": 0.43513820522529345, | |
| "eval_recall": 0.5529253271747498, | |
| "eval_runtime": 23.5415, | |
| "eval_samples_per_second": 129.516, | |
| "eval_steps_per_second": 16.227, | |
| "step": 364536 | |
| }, | |
| { | |
| "epoch": 72.09, | |
| "learning_rate": 7.053810093756234e-07, | |
| "loss": 0.2288, | |
| "step": 365000 | |
| }, | |
| { | |
| "epoch": 72.19, | |
| "learning_rate": 7.028874925194495e-07, | |
| "loss": 0.2218, | |
| "step": 365500 | |
| }, | |
| { | |
| "epoch": 72.29, | |
| "learning_rate": 7.003939756632755e-07, | |
| "loss": 0.2138, | |
| "step": 366000 | |
| }, | |
| { | |
| "epoch": 72.39, | |
| "learning_rate": 6.979004588071016e-07, | |
| "loss": 0.225, | |
| "step": 366500 | |
| }, | |
| { | |
| "epoch": 72.49, | |
| "learning_rate": 6.954069419509277e-07, | |
| "loss": 0.2252, | |
| "step": 367000 | |
| }, | |
| { | |
| "epoch": 72.59, | |
| "learning_rate": 6.929134250947537e-07, | |
| "loss": 0.2271, | |
| "step": 367500 | |
| }, | |
| { | |
| "epoch": 72.68, | |
| "learning_rate": 6.904248952722921e-07, | |
| "loss": 0.2195, | |
| "step": 368000 | |
| }, | |
| { | |
| "epoch": 72.78, | |
| "learning_rate": 6.879313784161182e-07, | |
| "loss": 0.226, | |
| "step": 368500 | |
| }, | |
| { | |
| "epoch": 72.88, | |
| "learning_rate": 6.854378615599443e-07, | |
| "loss": 0.2214, | |
| "step": 369000 | |
| }, | |
| { | |
| "epoch": 72.98, | |
| "learning_rate": 6.829443447037702e-07, | |
| "loss": 0.2129, | |
| "step": 369500 | |
| }, | |
| { | |
| "epoch": 73.0, | |
| "eval_accuracy": 0.8376707872478855, | |
| "eval_f1": 0.4907186648501363, | |
| "eval_loss": 0.7788528203964233, | |
| "eval_precision": 0.44005803298717167, | |
| "eval_recall": 0.5545612009237876, | |
| "eval_runtime": 23.966, | |
| "eval_samples_per_second": 127.222, | |
| "eval_steps_per_second": 15.939, | |
| "step": 369599 | |
| }, | |
| { | |
| "epoch": 73.08, | |
| "learning_rate": 6.804558148813087e-07, | |
| "loss": 0.2357, | |
| "step": 370000 | |
| }, | |
| { | |
| "epoch": 73.18, | |
| "learning_rate": 6.77967285058847e-07, | |
| "loss": 0.216, | |
| "step": 370500 | |
| }, | |
| { | |
| "epoch": 73.28, | |
| "learning_rate": 6.754737682026731e-07, | |
| "loss": 0.2102, | |
| "step": 371000 | |
| }, | |
| { | |
| "epoch": 73.38, | |
| "learning_rate": 6.729802513464991e-07, | |
| "loss": 0.2182, | |
| "step": 371500 | |
| }, | |
| { | |
| "epoch": 73.47, | |
| "learning_rate": 6.704867344903252e-07, | |
| "loss": 0.2189, | |
| "step": 372000 | |
| }, | |
| { | |
| "epoch": 73.57, | |
| "learning_rate": 6.679932176341512e-07, | |
| "loss": 0.2218, | |
| "step": 372500 | |
| }, | |
| { | |
| "epoch": 73.67, | |
| "learning_rate": 6.654997007779773e-07, | |
| "loss": 0.2262, | |
| "step": 373000 | |
| }, | |
| { | |
| "epoch": 73.77, | |
| "learning_rate": 6.630061839218034e-07, | |
| "loss": 0.2245, | |
| "step": 373500 | |
| }, | |
| { | |
| "epoch": 73.87, | |
| "learning_rate": 6.605126670656293e-07, | |
| "loss": 0.2231, | |
| "step": 374000 | |
| }, | |
| { | |
| "epoch": 73.97, | |
| "learning_rate": 6.580241372431678e-07, | |
| "loss": 0.2207, | |
| "step": 374500 | |
| }, | |
| { | |
| "epoch": 74.0, | |
| "eval_accuracy": 0.838684986030847, | |
| "eval_f1": 0.49589123607107516, | |
| "eval_loss": 0.78349369764328, | |
| "eval_precision": 0.44844759162711073, | |
| "eval_recall": 0.5545612009237876, | |
| "eval_runtime": 24.1896, | |
| "eval_samples_per_second": 126.046, | |
| "eval_steps_per_second": 15.792, | |
| "step": 374662 | |
| }, | |
| { | |
| "epoch": 74.07, | |
| "learning_rate": 6.555306203869939e-07, | |
| "loss": 0.2211, | |
| "step": 375000 | |
| }, | |
| { | |
| "epoch": 74.17, | |
| "learning_rate": 6.530371035308198e-07, | |
| "loss": 0.2198, | |
| "step": 375500 | |
| }, | |
| { | |
| "epoch": 74.26, | |
| "learning_rate": 6.50543586674646e-07, | |
| "loss": 0.2185, | |
| "step": 376000 | |
| }, | |
| { | |
| "epoch": 74.36, | |
| "learning_rate": 6.480500698184721e-07, | |
| "loss": 0.2228, | |
| "step": 376500 | |
| }, | |
| { | |
| "epoch": 74.46, | |
| "learning_rate": 6.455615399960104e-07, | |
| "loss": 0.2249, | |
| "step": 377000 | |
| }, | |
| { | |
| "epoch": 74.56, | |
| "learning_rate": 6.430680231398364e-07, | |
| "loss": 0.2134, | |
| "step": 377500 | |
| }, | |
| { | |
| "epoch": 74.66, | |
| "learning_rate": 6.405745062836626e-07, | |
| "loss": 0.2162, | |
| "step": 378000 | |
| }, | |
| { | |
| "epoch": 74.76, | |
| "learning_rate": 6.380809894274887e-07, | |
| "loss": 0.2149, | |
| "step": 378500 | |
| }, | |
| { | |
| "epoch": 74.86, | |
| "learning_rate": 6.355874725713146e-07, | |
| "loss": 0.214, | |
| "step": 379000 | |
| }, | |
| { | |
| "epoch": 74.96, | |
| "learning_rate": 6.331039297825655e-07, | |
| "loss": 0.2218, | |
| "step": 379500 | |
| }, | |
| { | |
| "epoch": 75.0, | |
| "eval_accuracy": 0.8382793065176624, | |
| "eval_f1": 0.4926268861454046, | |
| "eval_loss": 0.7711018919944763, | |
| "eval_precision": 0.44418676561533704, | |
| "eval_recall": 0.5529253271747498, | |
| "eval_runtime": 24.2584, | |
| "eval_samples_per_second": 125.688, | |
| "eval_steps_per_second": 15.747, | |
| "step": 379725 | |
| }, | |
| { | |
| "epoch": 75.05, | |
| "learning_rate": 6.306104129263914e-07, | |
| "loss": 0.2316, | |
| "step": 380000 | |
| }, | |
| { | |
| "epoch": 75.15, | |
| "learning_rate": 6.281168960702175e-07, | |
| "loss": 0.2168, | |
| "step": 380500 | |
| }, | |
| { | |
| "epoch": 75.25, | |
| "learning_rate": 6.256233792140435e-07, | |
| "loss": 0.2174, | |
| "step": 381000 | |
| }, | |
| { | |
| "epoch": 75.35, | |
| "learning_rate": 6.231298623578695e-07, | |
| "loss": 0.2229, | |
| "step": 381500 | |
| }, | |
| { | |
| "epoch": 75.45, | |
| "learning_rate": 6.20641332535408e-07, | |
| "loss": 0.2168, | |
| "step": 382000 | |
| }, | |
| { | |
| "epoch": 75.55, | |
| "learning_rate": 6.181478156792341e-07, | |
| "loss": 0.2184, | |
| "step": 382500 | |
| }, | |
| { | |
| "epoch": 75.65, | |
| "learning_rate": 6.156542988230601e-07, | |
| "loss": 0.2099, | |
| "step": 383000 | |
| }, | |
| { | |
| "epoch": 75.75, | |
| "learning_rate": 6.131607819668861e-07, | |
| "loss": 0.2153, | |
| "step": 383500 | |
| }, | |
| { | |
| "epoch": 75.84, | |
| "learning_rate": 6.106722521444246e-07, | |
| "loss": 0.2214, | |
| "step": 384000 | |
| }, | |
| { | |
| "epoch": 75.94, | |
| "learning_rate": 6.081787352882506e-07, | |
| "loss": 0.2257, | |
| "step": 384500 | |
| }, | |
| { | |
| "epoch": 76.0, | |
| "eval_accuracy": 0.837069922308546, | |
| "eval_f1": 0.4922721239885259, | |
| "eval_loss": 0.7748467922210693, | |
| "eval_precision": 0.4434246047049749, | |
| "eval_recall": 0.5532140107775212, | |
| "eval_runtime": 23.4467, | |
| "eval_samples_per_second": 130.04, | |
| "eval_steps_per_second": 16.292, | |
| "step": 384788 | |
| }, | |
| { | |
| "epoch": 76.04, | |
| "learning_rate": 6.056852184320766e-07, | |
| "loss": 0.2208, | |
| "step": 385000 | |
| }, | |
| { | |
| "epoch": 76.14, | |
| "learning_rate": 6.031917015759027e-07, | |
| "loss": 0.23, | |
| "step": 385500 | |
| }, | |
| { | |
| "epoch": 76.24, | |
| "learning_rate": 6.006981847197288e-07, | |
| "loss": 0.2093, | |
| "step": 386000 | |
| }, | |
| { | |
| "epoch": 76.34, | |
| "learning_rate": 5.982046678635548e-07, | |
| "loss": 0.2182, | |
| "step": 386500 | |
| }, | |
| { | |
| "epoch": 76.44, | |
| "learning_rate": 5.957111510073808e-07, | |
| "loss": 0.2226, | |
| "step": 387000 | |
| }, | |
| { | |
| "epoch": 76.54, | |
| "learning_rate": 5.932176341512069e-07, | |
| "loss": 0.2185, | |
| "step": 387500 | |
| }, | |
| { | |
| "epoch": 76.63, | |
| "learning_rate": 5.90724117295033e-07, | |
| "loss": 0.2246, | |
| "step": 388000 | |
| }, | |
| { | |
| "epoch": 76.73, | |
| "learning_rate": 5.882355874725714e-07, | |
| "loss": 0.2287, | |
| "step": 388500 | |
| }, | |
| { | |
| "epoch": 76.83, | |
| "learning_rate": 5.857420706163974e-07, | |
| "loss": 0.2206, | |
| "step": 389000 | |
| }, | |
| { | |
| "epoch": 76.93, | |
| "learning_rate": 5.832535407939359e-07, | |
| "loss": 0.231, | |
| "step": 389500 | |
| }, | |
| { | |
| "epoch": 77.0, | |
| "eval_accuracy": 0.8387041218569405, | |
| "eval_f1": 0.49053553958058616, | |
| "eval_loss": 0.7716959118843079, | |
| "eval_precision": 0.4395822215445605, | |
| "eval_recall": 0.5548498845265589, | |
| "eval_runtime": 24.1315, | |
| "eval_samples_per_second": 126.349, | |
| "eval_steps_per_second": 15.83, | |
| "step": 389851 | |
| }, | |
| { | |
| "epoch": 77.03, | |
| "learning_rate": 5.807600239377619e-07, | |
| "loss": 0.2233, | |
| "step": 390000 | |
| }, | |
| { | |
| "epoch": 77.13, | |
| "learning_rate": 5.782665070815879e-07, | |
| "loss": 0.2144, | |
| "step": 390500 | |
| }, | |
| { | |
| "epoch": 77.23, | |
| "learning_rate": 5.757729902254139e-07, | |
| "loss": 0.223, | |
| "step": 391000 | |
| }, | |
| { | |
| "epoch": 77.33, | |
| "learning_rate": 5.7327947336924e-07, | |
| "loss": 0.2235, | |
| "step": 391500 | |
| }, | |
| { | |
| "epoch": 77.42, | |
| "learning_rate": 5.707859565130661e-07, | |
| "loss": 0.2127, | |
| "step": 392000 | |
| }, | |
| { | |
| "epoch": 77.52, | |
| "learning_rate": 5.682924396568922e-07, | |
| "loss": 0.2161, | |
| "step": 392500 | |
| }, | |
| { | |
| "epoch": 77.62, | |
| "learning_rate": 5.658039098344305e-07, | |
| "loss": 0.2258, | |
| "step": 393000 | |
| }, | |
| { | |
| "epoch": 77.72, | |
| "learning_rate": 5.633103929782565e-07, | |
| "loss": 0.2197, | |
| "step": 393500 | |
| }, | |
| { | |
| "epoch": 77.82, | |
| "learning_rate": 5.608168761220827e-07, | |
| "loss": 0.2291, | |
| "step": 394000 | |
| }, | |
| { | |
| "epoch": 77.92, | |
| "learning_rate": 5.583233592659087e-07, | |
| "loss": 0.2187, | |
| "step": 394500 | |
| }, | |
| { | |
| "epoch": 78.0, | |
| "eval_accuracy": 0.8378353553522906, | |
| "eval_f1": 0.49114893617021277, | |
| "eval_loss": 0.7635823488235474, | |
| "eval_precision": 0.44026548672566373, | |
| "eval_recall": 0.5553310238645112, | |
| "eval_runtime": 24.4109, | |
| "eval_samples_per_second": 124.903, | |
| "eval_steps_per_second": 15.649, | |
| "step": 394914 | |
| }, | |
| { | |
| "epoch": 78.02, | |
| "learning_rate": 5.558298424097348e-07, | |
| "loss": 0.2156, | |
| "step": 395000 | |
| }, | |
| { | |
| "epoch": 78.12, | |
| "learning_rate": 5.533363255535608e-07, | |
| "loss": 0.2141, | |
| "step": 395500 | |
| }, | |
| { | |
| "epoch": 78.21, | |
| "learning_rate": 5.508428086973868e-07, | |
| "loss": 0.216, | |
| "step": 396000 | |
| }, | |
| { | |
| "epoch": 78.31, | |
| "learning_rate": 5.483492918412129e-07, | |
| "loss": 0.2186, | |
| "step": 396500 | |
| }, | |
| { | |
| "epoch": 78.41, | |
| "learning_rate": 5.458557749850389e-07, | |
| "loss": 0.2144, | |
| "step": 397000 | |
| }, | |
| { | |
| "epoch": 78.51, | |
| "learning_rate": 5.43362258128865e-07, | |
| "loss": 0.221, | |
| "step": 397500 | |
| }, | |
| { | |
| "epoch": 78.61, | |
| "learning_rate": 5.408737283064034e-07, | |
| "loss": 0.226, | |
| "step": 398000 | |
| }, | |
| { | |
| "epoch": 78.71, | |
| "learning_rate": 5.383802114502295e-07, | |
| "loss": 0.2218, | |
| "step": 398500 | |
| }, | |
| { | |
| "epoch": 78.81, | |
| "learning_rate": 5.358866945940555e-07, | |
| "loss": 0.2271, | |
| "step": 399000 | |
| }, | |
| { | |
| "epoch": 78.91, | |
| "learning_rate": 5.333931777378815e-07, | |
| "loss": 0.2165, | |
| "step": 399500 | |
| }, | |
| { | |
| "epoch": 79.0, | |
| "eval_accuracy": 0.8372153545868575, | |
| "eval_f1": 0.4910901243536601, | |
| "eval_loss": 0.7801523804664612, | |
| "eval_precision": 0.4416942116995926, | |
| "eval_recall": 0.5529253271747498, | |
| "eval_runtime": 24.1131, | |
| "eval_samples_per_second": 126.446, | |
| "eval_steps_per_second": 15.842, | |
| "step": 399977 | |
| }, | |
| { | |
| "epoch": 79.0, | |
| "learning_rate": 5.309046479154199e-07, | |
| "loss": 0.2287, | |
| "step": 400000 | |
| }, | |
| { | |
| "epoch": 79.1, | |
| "learning_rate": 5.284111310592461e-07, | |
| "loss": 0.2196, | |
| "step": 400500 | |
| }, | |
| { | |
| "epoch": 79.2, | |
| "learning_rate": 5.259176142030721e-07, | |
| "loss": 0.2266, | |
| "step": 401000 | |
| }, | |
| { | |
| "epoch": 79.3, | |
| "learning_rate": 5.234290843806104e-07, | |
| "loss": 0.2199, | |
| "step": 401500 | |
| }, | |
| { | |
| "epoch": 79.4, | |
| "learning_rate": 5.209355675244365e-07, | |
| "loss": 0.2189, | |
| "step": 402000 | |
| }, | |
| { | |
| "epoch": 79.5, | |
| "learning_rate": 5.184420506682626e-07, | |
| "loss": 0.2273, | |
| "step": 402500 | |
| }, | |
| { | |
| "epoch": 79.6, | |
| "learning_rate": 5.159535208458009e-07, | |
| "loss": 0.2125, | |
| "step": 403000 | |
| }, | |
| { | |
| "epoch": 79.7, | |
| "learning_rate": 5.13460003989627e-07, | |
| "loss": 0.2241, | |
| "step": 403500 | |
| }, | |
| { | |
| "epoch": 79.79, | |
| "learning_rate": 5.10966487133453e-07, | |
| "loss": 0.2177, | |
| "step": 404000 | |
| }, | |
| { | |
| "epoch": 79.89, | |
| "learning_rate": 5.084729702772792e-07, | |
| "loss": 0.2159, | |
| "step": 404500 | |
| }, | |
| { | |
| "epoch": 79.99, | |
| "learning_rate": 5.059794534211052e-07, | |
| "loss": 0.2173, | |
| "step": 405000 | |
| }, | |
| { | |
| "epoch": 80.0, | |
| "eval_accuracy": 0.8373301695434192, | |
| "eval_f1": 0.49182712879760376, | |
| "eval_loss": 0.7780812978744507, | |
| "eval_precision": 0.44282632146709816, | |
| "eval_recall": 0.5530215550423403, | |
| "eval_runtime": 23.2524, | |
| "eval_samples_per_second": 131.126, | |
| "eval_steps_per_second": 16.428, | |
| "step": 405040 | |
| }, | |
| { | |
| "epoch": 80.09, | |
| "learning_rate": 5.034859365649312e-07, | |
| "loss": 0.2145, | |
| "step": 405500 | |
| }, | |
| { | |
| "epoch": 80.19, | |
| "learning_rate": 5.009924197087572e-07, | |
| "loss": 0.2144, | |
| "step": 406000 | |
| }, | |
| { | |
| "epoch": 80.29, | |
| "learning_rate": 4.984989028525834e-07, | |
| "loss": 0.2121, | |
| "step": 406500 | |
| }, | |
| { | |
| "epoch": 80.39, | |
| "learning_rate": 4.960053859964094e-07, | |
| "loss": 0.2188, | |
| "step": 407000 | |
| }, | |
| { | |
| "epoch": 80.49, | |
| "learning_rate": 4.935118691402354e-07, | |
| "loss": 0.2163, | |
| "step": 407500 | |
| }, | |
| { | |
| "epoch": 80.58, | |
| "learning_rate": 4.910183522840615e-07, | |
| "loss": 0.2056, | |
| "step": 408000 | |
| }, | |
| { | |
| "epoch": 80.68, | |
| "learning_rate": 4.885248354278875e-07, | |
| "loss": 0.2233, | |
| "step": 408500 | |
| }, | |
| { | |
| "epoch": 80.78, | |
| "learning_rate": 4.860363056054259e-07, | |
| "loss": 0.2178, | |
| "step": 409000 | |
| }, | |
| { | |
| "epoch": 80.88, | |
| "learning_rate": 4.83542788749252e-07, | |
| "loss": 0.2088, | |
| "step": 409500 | |
| }, | |
| { | |
| "epoch": 80.98, | |
| "learning_rate": 4.81049271893078e-07, | |
| "loss": 0.2251, | |
| "step": 410000 | |
| }, | |
| { | |
| "epoch": 81.0, | |
| "eval_accuracy": 0.8379425159784147, | |
| "eval_f1": 0.49120115897567007, | |
| "eval_loss": 0.7737105488777161, | |
| "eval_precision": 0.4407738778007188, | |
| "eval_recall": 0.554657428791378, | |
| "eval_runtime": 23.4259, | |
| "eval_samples_per_second": 130.155, | |
| "eval_steps_per_second": 16.307, | |
| "step": 410103 | |
| }, | |
| { | |
| "epoch": 81.08, | |
| "learning_rate": 4.785557550369041e-07, | |
| "loss": 0.2209, | |
| "step": 410500 | |
| }, | |
| { | |
| "epoch": 81.18, | |
| "learning_rate": 4.760622381807301e-07, | |
| "loss": 0.2155, | |
| "step": 411000 | |
| }, | |
| { | |
| "epoch": 81.28, | |
| "learning_rate": 4.7356872132455623e-07, | |
| "loss": 0.2093, | |
| "step": 411500 | |
| }, | |
| { | |
| "epoch": 81.37, | |
| "learning_rate": 4.710801915020946e-07, | |
| "loss": 0.2196, | |
| "step": 412000 | |
| }, | |
| { | |
| "epoch": 81.47, | |
| "learning_rate": 4.6858667464592064e-07, | |
| "loss": 0.2227, | |
| "step": 412500 | |
| }, | |
| { | |
| "epoch": 81.57, | |
| "learning_rate": 4.660931577897467e-07, | |
| "loss": 0.2134, | |
| "step": 413000 | |
| }, | |
| { | |
| "epoch": 81.67, | |
| "learning_rate": 4.6359964093357273e-07, | |
| "loss": 0.2152, | |
| "step": 413500 | |
| }, | |
| { | |
| "epoch": 81.77, | |
| "learning_rate": 4.611061240773988e-07, | |
| "loss": 0.2141, | |
| "step": 414000 | |
| }, | |
| { | |
| "epoch": 81.87, | |
| "learning_rate": 4.5861759425493724e-07, | |
| "loss": 0.2238, | |
| "step": 414500 | |
| }, | |
| { | |
| "epoch": 81.97, | |
| "learning_rate": 4.5612407739876326e-07, | |
| "loss": 0.2195, | |
| "step": 415000 | |
| }, | |
| { | |
| "epoch": 82.0, | |
| "eval_accuracy": 0.8383596769872556, | |
| "eval_f1": 0.4898150515639649, | |
| "eval_loss": 0.7843115925788879, | |
| "eval_precision": 0.43957472846871654, | |
| "eval_recall": 0.5530215550423403, | |
| "eval_runtime": 24.3105, | |
| "eval_samples_per_second": 125.419, | |
| "eval_steps_per_second": 15.713, | |
| "step": 415166 | |
| }, | |
| { | |
| "epoch": 82.07, | |
| "learning_rate": 4.5363056054258933e-07, | |
| "loss": 0.2136, | |
| "step": 415500 | |
| }, | |
| { | |
| "epoch": 82.16, | |
| "learning_rate": 4.5113704368641535e-07, | |
| "loss": 0.2171, | |
| "step": 416000 | |
| }, | |
| { | |
| "epoch": 82.26, | |
| "learning_rate": 4.486435268302414e-07, | |
| "loss": 0.2173, | |
| "step": 416500 | |
| }, | |
| { | |
| "epoch": 82.36, | |
| "learning_rate": 4.4615000997406744e-07, | |
| "loss": 0.2093, | |
| "step": 417000 | |
| }, | |
| { | |
| "epoch": 82.46, | |
| "learning_rate": 4.4366148015160583e-07, | |
| "loss": 0.2203, | |
| "step": 417500 | |
| }, | |
| { | |
| "epoch": 82.56, | |
| "learning_rate": 4.4116796329543196e-07, | |
| "loss": 0.2237, | |
| "step": 418000 | |
| }, | |
| { | |
| "epoch": 82.66, | |
| "learning_rate": 4.38674446439258e-07, | |
| "loss": 0.2147, | |
| "step": 418500 | |
| }, | |
| { | |
| "epoch": 82.76, | |
| "learning_rate": 4.36180929583084e-07, | |
| "loss": 0.2145, | |
| "step": 419000 | |
| }, | |
| { | |
| "epoch": 82.86, | |
| "learning_rate": 4.3368741272691007e-07, | |
| "loss": 0.2124, | |
| "step": 419500 | |
| }, | |
| { | |
| "epoch": 82.95, | |
| "learning_rate": 4.3119888290444846e-07, | |
| "loss": 0.2208, | |
| "step": 420000 | |
| }, | |
| { | |
| "epoch": 83.0, | |
| "eval_accuracy": 0.8378506640131654, | |
| "eval_f1": 0.4901736066895878, | |
| "eval_loss": 0.7780388593673706, | |
| "eval_precision": 0.4385205437837017, | |
| "eval_recall": 0.5556197074672825, | |
| "eval_runtime": 24.1182, | |
| "eval_samples_per_second": 126.419, | |
| "eval_steps_per_second": 15.839, | |
| "step": 420229 | |
| }, | |
| { | |
| "epoch": 83.05, | |
| "learning_rate": 4.287053660482745e-07, | |
| "loss": 0.2155, | |
| "step": 420500 | |
| }, | |
| { | |
| "epoch": 83.15, | |
| "learning_rate": 4.262118491921006e-07, | |
| "loss": 0.2045, | |
| "step": 421000 | |
| }, | |
| { | |
| "epoch": 83.25, | |
| "learning_rate": 4.237183323359266e-07, | |
| "loss": 0.2212, | |
| "step": 421500 | |
| }, | |
| { | |
| "epoch": 83.35, | |
| "learning_rate": 4.21229802513465e-07, | |
| "loss": 0.2137, | |
| "step": 422000 | |
| }, | |
| { | |
| "epoch": 83.45, | |
| "learning_rate": 4.187362856572911e-07, | |
| "loss": 0.2226, | |
| "step": 422500 | |
| }, | |
| { | |
| "epoch": 83.55, | |
| "learning_rate": 4.162427688011171e-07, | |
| "loss": 0.2136, | |
| "step": 423000 | |
| }, | |
| { | |
| "epoch": 83.65, | |
| "learning_rate": 4.1374925194494317e-07, | |
| "loss": 0.2184, | |
| "step": 423500 | |
| }, | |
| { | |
| "epoch": 83.74, | |
| "learning_rate": 4.1125573508876924e-07, | |
| "loss": 0.2121, | |
| "step": 424000 | |
| }, | |
| { | |
| "epoch": 83.84, | |
| "learning_rate": 4.0876720526630763e-07, | |
| "loss": 0.2127, | |
| "step": 424500 | |
| }, | |
| { | |
| "epoch": 83.94, | |
| "learning_rate": 4.062736884101337e-07, | |
| "loss": 0.2144, | |
| "step": 425000 | |
| }, | |
| { | |
| "epoch": 84.0, | |
| "eval_accuracy": 0.8380764667610701, | |
| "eval_f1": 0.49133415662394075, | |
| "eval_loss": 0.7888113856315613, | |
| "eval_precision": 0.44068443969139104, | |
| "eval_recall": 0.5551385681293303, | |
| "eval_runtime": 24.19, | |
| "eval_samples_per_second": 126.044, | |
| "eval_steps_per_second": 15.792, | |
| "step": 425292 | |
| }, | |
| { | |
| "epoch": 84.04, | |
| "learning_rate": 4.037801715539597e-07, | |
| "loss": 0.2187, | |
| "step": 425500 | |
| }, | |
| { | |
| "epoch": 84.14, | |
| "learning_rate": 4.012866546977858e-07, | |
| "loss": 0.2165, | |
| "step": 426000 | |
| }, | |
| { | |
| "epoch": 84.24, | |
| "learning_rate": 3.987931378416118e-07, | |
| "loss": 0.2147, | |
| "step": 426500 | |
| }, | |
| { | |
| "epoch": 84.34, | |
| "learning_rate": 3.9629962098543794e-07, | |
| "loss": 0.2092, | |
| "step": 427000 | |
| }, | |
| { | |
| "epoch": 84.44, | |
| "learning_rate": 3.9381109116297633e-07, | |
| "loss": 0.2179, | |
| "step": 427500 | |
| }, | |
| { | |
| "epoch": 84.53, | |
| "learning_rate": 3.9131757430680235e-07, | |
| "loss": 0.2123, | |
| "step": 428000 | |
| }, | |
| { | |
| "epoch": 84.63, | |
| "learning_rate": 3.888240574506284e-07, | |
| "loss": 0.2127, | |
| "step": 428500 | |
| }, | |
| { | |
| "epoch": 84.73, | |
| "learning_rate": 3.8633054059445444e-07, | |
| "loss": 0.2192, | |
| "step": 429000 | |
| }, | |
| { | |
| "epoch": 84.83, | |
| "learning_rate": 3.8383702373828046e-07, | |
| "loss": 0.2166, | |
| "step": 429500 | |
| }, | |
| { | |
| "epoch": 84.93, | |
| "learning_rate": 3.813435068821066e-07, | |
| "loss": 0.2123, | |
| "step": 430000 | |
| }, | |
| { | |
| "epoch": 85.0, | |
| "eval_accuracy": 0.8388112824830648, | |
| "eval_f1": 0.4910889400528694, | |
| "eval_loss": 0.7885710000991821, | |
| "eval_precision": 0.4408972592252335, | |
| "eval_recall": 0.5541762894534257, | |
| "eval_runtime": 24.1837, | |
| "eval_samples_per_second": 126.077, | |
| "eval_steps_per_second": 15.796, | |
| "step": 430355 | |
| }, | |
| { | |
| "epoch": 85.03, | |
| "learning_rate": 3.788499900259326e-07, | |
| "loss": 0.2197, | |
| "step": 430500 | |
| }, | |
| { | |
| "epoch": 85.13, | |
| "learning_rate": 3.76361460203471e-07, | |
| "loss": 0.2193, | |
| "step": 431000 | |
| }, | |
| { | |
| "epoch": 85.23, | |
| "learning_rate": 3.7386794334729706e-07, | |
| "loss": 0.213, | |
| "step": 431500 | |
| }, | |
| { | |
| "epoch": 85.32, | |
| "learning_rate": 3.713744264911231e-07, | |
| "loss": 0.216, | |
| "step": 432000 | |
| }, | |
| { | |
| "epoch": 85.42, | |
| "learning_rate": 3.6888090963494915e-07, | |
| "loss": 0.2137, | |
| "step": 432500 | |
| }, | |
| { | |
| "epoch": 85.52, | |
| "learning_rate": 3.6639237981248754e-07, | |
| "loss": 0.2204, | |
| "step": 433000 | |
| }, | |
| { | |
| "epoch": 85.62, | |
| "learning_rate": 3.638988629563136e-07, | |
| "loss": 0.2121, | |
| "step": 433500 | |
| }, | |
| { | |
| "epoch": 85.72, | |
| "learning_rate": 3.61410333133852e-07, | |
| "loss": 0.2184, | |
| "step": 434000 | |
| }, | |
| { | |
| "epoch": 85.82, | |
| "learning_rate": 3.589168162776781e-07, | |
| "loss": 0.2083, | |
| "step": 434500 | |
| }, | |
| { | |
| "epoch": 85.92, | |
| "learning_rate": 3.564232994215041e-07, | |
| "loss": 0.2195, | |
| "step": 435000 | |
| }, | |
| { | |
| "epoch": 86.0, | |
| "eval_accuracy": 0.8386696773699721, | |
| "eval_f1": 0.49464025383757826, | |
| "eval_loss": 0.7830442786216736, | |
| "eval_precision": 0.4460943542150039, | |
| "eval_recall": 0.5550423402617398, | |
| "eval_runtime": 23.4037, | |
| "eval_samples_per_second": 130.278, | |
| "eval_steps_per_second": 16.322, | |
| "step": 435418 | |
| }, | |
| { | |
| "epoch": 86.02, | |
| "learning_rate": 3.5392978256533017e-07, | |
| "loss": 0.2097, | |
| "step": 435500 | |
| }, | |
| { | |
| "epoch": 86.11, | |
| "learning_rate": 3.514362657091562e-07, | |
| "loss": 0.2071, | |
| "step": 436000 | |
| }, | |
| { | |
| "epoch": 86.21, | |
| "learning_rate": 3.489477358866946e-07, | |
| "loss": 0.2152, | |
| "step": 436500 | |
| }, | |
| { | |
| "epoch": 86.31, | |
| "learning_rate": 3.464542190305207e-07, | |
| "loss": 0.2152, | |
| "step": 437000 | |
| }, | |
| { | |
| "epoch": 86.41, | |
| "learning_rate": 3.439607021743467e-07, | |
| "loss": 0.218, | |
| "step": 437500 | |
| }, | |
| { | |
| "epoch": 86.51, | |
| "learning_rate": 3.414671853181728e-07, | |
| "loss": 0.2185, | |
| "step": 438000 | |
| }, | |
| { | |
| "epoch": 86.61, | |
| "learning_rate": 3.389736684619988e-07, | |
| "loss": 0.2211, | |
| "step": 438500 | |
| }, | |
| { | |
| "epoch": 86.71, | |
| "learning_rate": 3.3648015160582493e-07, | |
| "loss": 0.2207, | |
| "step": 439000 | |
| }, | |
| { | |
| "epoch": 86.81, | |
| "learning_rate": 3.3398663474965095e-07, | |
| "loss": 0.2272, | |
| "step": 439500 | |
| }, | |
| { | |
| "epoch": 86.9, | |
| "learning_rate": 3.31493117893477e-07, | |
| "loss": 0.2105, | |
| "step": 440000 | |
| }, | |
| { | |
| "epoch": 87.0, | |
| "eval_accuracy": 0.8389414061005014, | |
| "eval_f1": 0.492742453436095, | |
| "eval_loss": 0.7846280932426453, | |
| "eval_precision": 0.44387873177505205, | |
| "eval_recall": 0.5536951501154734, | |
| "eval_runtime": 23.9106, | |
| "eval_samples_per_second": 127.517, | |
| "eval_steps_per_second": 15.976, | |
| "step": 440481 | |
| }, | |
| { | |
| "epoch": 87.0, | |
| "learning_rate": 3.2899960103730304e-07, | |
| "loss": 0.2167, | |
| "step": 440500 | |
| }, | |
| { | |
| "epoch": 87.1, | |
| "learning_rate": 3.2651107121484143e-07, | |
| "loss": 0.2137, | |
| "step": 441000 | |
| }, | |
| { | |
| "epoch": 87.2, | |
| "learning_rate": 3.240175543586675e-07, | |
| "loss": 0.2162, | |
| "step": 441500 | |
| }, | |
| { | |
| "epoch": 87.3, | |
| "learning_rate": 3.215240375024935e-07, | |
| "loss": 0.2167, | |
| "step": 442000 | |
| }, | |
| { | |
| "epoch": 87.4, | |
| "learning_rate": 3.190355076800319e-07, | |
| "loss": 0.2144, | |
| "step": 442500 | |
| }, | |
| { | |
| "epoch": 87.5, | |
| "learning_rate": 3.16541990823858e-07, | |
| "loss": 0.2148, | |
| "step": 443000 | |
| }, | |
| { | |
| "epoch": 87.6, | |
| "learning_rate": 3.1404847396768406e-07, | |
| "loss": 0.218, | |
| "step": 443500 | |
| }, | |
| { | |
| "epoch": 87.7, | |
| "learning_rate": 3.1155495711151013e-07, | |
| "loss": 0.223, | |
| "step": 444000 | |
| }, | |
| { | |
| "epoch": 87.79, | |
| "learning_rate": 3.0906144025533615e-07, | |
| "loss": 0.2204, | |
| "step": 444500 | |
| }, | |
| { | |
| "epoch": 87.89, | |
| "learning_rate": 3.065679233991622e-07, | |
| "loss": 0.2136, | |
| "step": 445000 | |
| }, | |
| { | |
| "epoch": 87.99, | |
| "learning_rate": 3.040744065429883e-07, | |
| "loss": 0.2203, | |
| "step": 445500 | |
| }, | |
| { | |
| "epoch": 88.0, | |
| "eval_accuracy": 0.8378238738566344, | |
| "eval_f1": 0.4915982473305824, | |
| "eval_loss": 0.7851070761680603, | |
| "eval_precision": 0.4405642394205109, | |
| "eval_recall": 0.5560046189376443, | |
| "eval_runtime": 23.4737, | |
| "eval_samples_per_second": 129.89, | |
| "eval_steps_per_second": 16.274, | |
| "step": 445544 | |
| }, | |
| { | |
| "epoch": 88.09, | |
| "learning_rate": 3.015808896868143e-07, | |
| "loss": 0.2159, | |
| "step": 446000 | |
| }, | |
| { | |
| "epoch": 88.19, | |
| "learning_rate": 2.990923598643527e-07, | |
| "loss": 0.2045, | |
| "step": 446500 | |
| }, | |
| { | |
| "epoch": 88.29, | |
| "learning_rate": 2.9659884300817877e-07, | |
| "loss": 0.2064, | |
| "step": 447000 | |
| }, | |
| { | |
| "epoch": 88.39, | |
| "learning_rate": 2.9410532615200484e-07, | |
| "loss": 0.2214, | |
| "step": 447500 | |
| }, | |
| { | |
| "epoch": 88.49, | |
| "learning_rate": 2.9161180929583086e-07, | |
| "loss": 0.2136, | |
| "step": 448000 | |
| }, | |
| { | |
| "epoch": 88.58, | |
| "learning_rate": 2.891182924396569e-07, | |
| "loss": 0.2092, | |
| "step": 448500 | |
| }, | |
| { | |
| "epoch": 88.68, | |
| "learning_rate": 2.8662477558348295e-07, | |
| "loss": 0.2104, | |
| "step": 449000 | |
| }, | |
| { | |
| "epoch": 88.78, | |
| "learning_rate": 2.84131258727309e-07, | |
| "loss": 0.2084, | |
| "step": 449500 | |
| }, | |
| { | |
| "epoch": 88.88, | |
| "learning_rate": 2.816427289048474e-07, | |
| "loss": 0.2156, | |
| "step": 450000 | |
| }, | |
| { | |
| "epoch": 88.98, | |
| "learning_rate": 2.791492120486735e-07, | |
| "loss": 0.2079, | |
| "step": 450500 | |
| }, | |
| { | |
| "epoch": 89.0, | |
| "eval_accuracy": 0.8380956025871636, | |
| "eval_f1": 0.49355966902669957, | |
| "eval_loss": 0.7890189290046692, | |
| "eval_precision": 0.443235789796231, | |
| "eval_recall": 0.556774441878368, | |
| "eval_runtime": 23.2357, | |
| "eval_samples_per_second": 131.22, | |
| "eval_steps_per_second": 16.44, | |
| "step": 450607 | |
| }, | |
| { | |
| "epoch": 89.08, | |
| "learning_rate": 2.766556951924995e-07, | |
| "loss": 0.2051, | |
| "step": 451000 | |
| }, | |
| { | |
| "epoch": 89.18, | |
| "learning_rate": 2.741621783363256e-07, | |
| "loss": 0.2181, | |
| "step": 451500 | |
| }, | |
| { | |
| "epoch": 89.28, | |
| "learning_rate": 2.7166866148015165e-07, | |
| "loss": 0.2126, | |
| "step": 452000 | |
| }, | |
| { | |
| "epoch": 89.37, | |
| "learning_rate": 2.6918013165769004e-07, | |
| "loss": 0.2175, | |
| "step": 452500 | |
| }, | |
| { | |
| "epoch": 89.47, | |
| "learning_rate": 2.6668661480151606e-07, | |
| "loss": 0.2105, | |
| "step": 453000 | |
| }, | |
| { | |
| "epoch": 89.57, | |
| "learning_rate": 2.6419309794534213e-07, | |
| "loss": 0.207, | |
| "step": 453500 | |
| }, | |
| { | |
| "epoch": 89.67, | |
| "learning_rate": 2.616995810891682e-07, | |
| "loss": 0.2101, | |
| "step": 454000 | |
| }, | |
| { | |
| "epoch": 89.77, | |
| "learning_rate": 2.592110512667066e-07, | |
| "loss": 0.2084, | |
| "step": 454500 | |
| }, | |
| { | |
| "epoch": 89.87, | |
| "learning_rate": 2.5671753441053266e-07, | |
| "loss": 0.208, | |
| "step": 455000 | |
| }, | |
| { | |
| "epoch": 89.97, | |
| "learning_rate": 2.542240175543587e-07, | |
| "loss": 0.2109, | |
| "step": 455500 | |
| }, | |
| { | |
| "epoch": 90.0, | |
| "eval_accuracy": 0.8384974549351295, | |
| "eval_f1": 0.49219216656711323, | |
| "eval_loss": 0.7881253957748413, | |
| "eval_precision": 0.44212785528131227, | |
| "eval_recall": 0.5550423402617398, | |
| "eval_runtime": 23.2564, | |
| "eval_samples_per_second": 131.104, | |
| "eval_steps_per_second": 16.426, | |
| "step": 455670 | |
| } | |
| ], | |
| "max_steps": 506300, | |
| "num_train_epochs": 100, | |
| "total_flos": 6.575301079423942e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |