|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 3.0, |
|
"global_step": 49971, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.03, |
|
"learning_rate": 1.9799883932680958e-05, |
|
"loss": 0.7935, |
|
"step": 500 |
|
}, |
|
{ |
|
"epoch": 0.06, |
|
"learning_rate": 1.959976786536191e-05, |
|
"loss": 0.6149, |
|
"step": 1000 |
|
}, |
|
{ |
|
"epoch": 0.09, |
|
"learning_rate": 1.9399651798042868e-05, |
|
"loss": 0.5758, |
|
"step": 1500 |
|
}, |
|
{ |
|
"epoch": 0.12, |
|
"learning_rate": 1.919953573072382e-05, |
|
"loss": 0.5473, |
|
"step": 2000 |
|
}, |
|
{ |
|
"epoch": 0.15, |
|
"learning_rate": 1.8999419663404778e-05, |
|
"loss": 0.5186, |
|
"step": 2500 |
|
}, |
|
{ |
|
"epoch": 0.18, |
|
"learning_rate": 1.879930359608573e-05, |
|
"loss": 0.5147, |
|
"step": 3000 |
|
}, |
|
{ |
|
"epoch": 0.21, |
|
"learning_rate": 1.8599187528766688e-05, |
|
"loss": 0.5012, |
|
"step": 3500 |
|
}, |
|
{ |
|
"epoch": 0.24, |
|
"learning_rate": 1.839907146144764e-05, |
|
"loss": 0.49, |
|
"step": 4000 |
|
}, |
|
{ |
|
"epoch": 0.27, |
|
"learning_rate": 1.8198955394128598e-05, |
|
"loss": 0.4918, |
|
"step": 4500 |
|
}, |
|
{ |
|
"epoch": 0.3, |
|
"learning_rate": 1.799883932680955e-05, |
|
"loss": 0.4766, |
|
"step": 5000 |
|
}, |
|
{ |
|
"epoch": 0.33, |
|
"learning_rate": 1.7798723259490508e-05, |
|
"loss": 0.4886, |
|
"step": 5500 |
|
}, |
|
{ |
|
"epoch": 0.36, |
|
"learning_rate": 1.759860719217146e-05, |
|
"loss": 0.4762, |
|
"step": 6000 |
|
}, |
|
{ |
|
"epoch": 0.39, |
|
"learning_rate": 1.7398491124852417e-05, |
|
"loss": 0.4621, |
|
"step": 6500 |
|
}, |
|
{ |
|
"epoch": 0.42, |
|
"learning_rate": 1.719837505753337e-05, |
|
"loss": 0.46, |
|
"step": 7000 |
|
}, |
|
{ |
|
"epoch": 0.45, |
|
"learning_rate": 1.6998258990214324e-05, |
|
"loss": 0.457, |
|
"step": 7500 |
|
}, |
|
{ |
|
"epoch": 0.48, |
|
"learning_rate": 1.679814292289528e-05, |
|
"loss": 0.4413, |
|
"step": 8000 |
|
}, |
|
{ |
|
"epoch": 0.51, |
|
"learning_rate": 1.6598026855576234e-05, |
|
"loss": 0.4482, |
|
"step": 8500 |
|
}, |
|
{ |
|
"epoch": 0.54, |
|
"learning_rate": 1.639791078825719e-05, |
|
"loss": 0.4495, |
|
"step": 9000 |
|
}, |
|
{ |
|
"epoch": 0.57, |
|
"learning_rate": 1.6197794720938144e-05, |
|
"loss": 0.4391, |
|
"step": 9500 |
|
}, |
|
{ |
|
"epoch": 0.6, |
|
"learning_rate": 1.59976786536191e-05, |
|
"loss": 0.4369, |
|
"step": 10000 |
|
}, |
|
{ |
|
"epoch": 0.63, |
|
"learning_rate": 1.5797562586300054e-05, |
|
"loss": 0.4413, |
|
"step": 10500 |
|
}, |
|
{ |
|
"epoch": 0.66, |
|
"learning_rate": 1.559744651898101e-05, |
|
"loss": 0.4354, |
|
"step": 11000 |
|
}, |
|
{ |
|
"epoch": 0.69, |
|
"learning_rate": 1.5397330451661963e-05, |
|
"loss": 0.4218, |
|
"step": 11500 |
|
}, |
|
{ |
|
"epoch": 0.72, |
|
"learning_rate": 1.519721438434292e-05, |
|
"loss": 0.4267, |
|
"step": 12000 |
|
}, |
|
{ |
|
"epoch": 0.75, |
|
"learning_rate": 1.4997098317023875e-05, |
|
"loss": 0.424, |
|
"step": 12500 |
|
}, |
|
{ |
|
"epoch": 0.78, |
|
"learning_rate": 1.479698224970483e-05, |
|
"loss": 0.4234, |
|
"step": 13000 |
|
}, |
|
{ |
|
"epoch": 0.81, |
|
"learning_rate": 1.4596866182385785e-05, |
|
"loss": 0.423, |
|
"step": 13500 |
|
}, |
|
{ |
|
"epoch": 0.84, |
|
"learning_rate": 1.439675011506674e-05, |
|
"loss": 0.4188, |
|
"step": 14000 |
|
}, |
|
{ |
|
"epoch": 0.87, |
|
"learning_rate": 1.4196634047747695e-05, |
|
"loss": 0.4145, |
|
"step": 14500 |
|
}, |
|
{ |
|
"epoch": 0.9, |
|
"learning_rate": 1.399651798042865e-05, |
|
"loss": 0.4213, |
|
"step": 15000 |
|
}, |
|
{ |
|
"epoch": 0.93, |
|
"learning_rate": 1.3796401913109605e-05, |
|
"loss": 0.4177, |
|
"step": 15500 |
|
}, |
|
{ |
|
"epoch": 0.96, |
|
"learning_rate": 1.359628584579056e-05, |
|
"loss": 0.4071, |
|
"step": 16000 |
|
}, |
|
{ |
|
"epoch": 0.99, |
|
"learning_rate": 1.3396169778471514e-05, |
|
"loss": 0.4067, |
|
"step": 16500 |
|
}, |
|
{ |
|
"epoch": 1.0, |
|
"eval_accuracy": 0.9200714826583862, |
|
"eval_loss": 0.22239993512630463, |
|
"eval_runtime": 27.5138, |
|
"eval_samples_per_second": 142.329, |
|
"eval_steps_per_second": 4.47, |
|
"step": 16657 |
|
}, |
|
{ |
|
"epoch": 1.02, |
|
"learning_rate": 1.319605371115247e-05, |
|
"loss": 0.3698, |
|
"step": 17000 |
|
}, |
|
{ |
|
"epoch": 1.05, |
|
"learning_rate": 1.2995937643833424e-05, |
|
"loss": 0.3628, |
|
"step": 17500 |
|
}, |
|
{ |
|
"epoch": 1.08, |
|
"learning_rate": 1.279582157651438e-05, |
|
"loss": 0.3584, |
|
"step": 18000 |
|
}, |
|
{ |
|
"epoch": 1.11, |
|
"learning_rate": 1.2595705509195336e-05, |
|
"loss": 0.3546, |
|
"step": 18500 |
|
}, |
|
{ |
|
"epoch": 1.14, |
|
"learning_rate": 1.239558944187629e-05, |
|
"loss": 0.359, |
|
"step": 19000 |
|
}, |
|
{ |
|
"epoch": 1.17, |
|
"learning_rate": 1.2195473374557246e-05, |
|
"loss": 0.3564, |
|
"step": 19500 |
|
}, |
|
{ |
|
"epoch": 1.2, |
|
"learning_rate": 1.19953573072382e-05, |
|
"loss": 0.3621, |
|
"step": 20000 |
|
}, |
|
{ |
|
"epoch": 1.23, |
|
"learning_rate": 1.1795241239919156e-05, |
|
"loss": 0.353, |
|
"step": 20500 |
|
}, |
|
{ |
|
"epoch": 1.26, |
|
"learning_rate": 1.1595125172600107e-05, |
|
"loss": 0.3525, |
|
"step": 21000 |
|
}, |
|
{ |
|
"epoch": 1.29, |
|
"learning_rate": 1.1395009105281064e-05, |
|
"loss": 0.3564, |
|
"step": 21500 |
|
}, |
|
{ |
|
"epoch": 1.32, |
|
"learning_rate": 1.1194893037962019e-05, |
|
"loss": 0.3506, |
|
"step": 22000 |
|
}, |
|
{ |
|
"epoch": 1.35, |
|
"learning_rate": 1.0994776970642974e-05, |
|
"loss": 0.3454, |
|
"step": 22500 |
|
}, |
|
{ |
|
"epoch": 1.38, |
|
"learning_rate": 1.0794660903323929e-05, |
|
"loss": 0.3479, |
|
"step": 23000 |
|
}, |
|
{ |
|
"epoch": 1.41, |
|
"learning_rate": 1.0594544836004884e-05, |
|
"loss": 0.3604, |
|
"step": 23500 |
|
}, |
|
{ |
|
"epoch": 1.44, |
|
"learning_rate": 1.0394428768685838e-05, |
|
"loss": 0.36, |
|
"step": 24000 |
|
}, |
|
{ |
|
"epoch": 1.47, |
|
"learning_rate": 1.0194312701366793e-05, |
|
"loss": 0.356, |
|
"step": 24500 |
|
}, |
|
{ |
|
"epoch": 1.5, |
|
"learning_rate": 9.994196634047748e-06, |
|
"loss": 0.3515, |
|
"step": 25000 |
|
}, |
|
{ |
|
"epoch": 1.53, |
|
"learning_rate": 9.794080566728703e-06, |
|
"loss": 0.3447, |
|
"step": 25500 |
|
}, |
|
{ |
|
"epoch": 1.56, |
|
"learning_rate": 9.593964499409658e-06, |
|
"loss": 0.3548, |
|
"step": 26000 |
|
}, |
|
{ |
|
"epoch": 1.59, |
|
"learning_rate": 9.393848432090613e-06, |
|
"loss": 0.3558, |
|
"step": 26500 |
|
}, |
|
{ |
|
"epoch": 1.62, |
|
"learning_rate": 9.193732364771568e-06, |
|
"loss": 0.349, |
|
"step": 27000 |
|
}, |
|
{ |
|
"epoch": 1.65, |
|
"learning_rate": 8.993616297452523e-06, |
|
"loss": 0.3352, |
|
"step": 27500 |
|
}, |
|
{ |
|
"epoch": 1.68, |
|
"learning_rate": 8.793500230133478e-06, |
|
"loss": 0.3475, |
|
"step": 28000 |
|
}, |
|
{ |
|
"epoch": 1.71, |
|
"learning_rate": 8.593384162814433e-06, |
|
"loss": 0.3482, |
|
"step": 28500 |
|
}, |
|
{ |
|
"epoch": 1.74, |
|
"learning_rate": 8.393268095495388e-06, |
|
"loss": 0.3389, |
|
"step": 29000 |
|
}, |
|
{ |
|
"epoch": 1.77, |
|
"learning_rate": 8.193152028176343e-06, |
|
"loss": 0.3485, |
|
"step": 29500 |
|
}, |
|
{ |
|
"epoch": 1.8, |
|
"learning_rate": 7.993035960857298e-06, |
|
"loss": 0.3454, |
|
"step": 30000 |
|
}, |
|
{ |
|
"epoch": 1.83, |
|
"learning_rate": 7.792919893538253e-06, |
|
"loss": 0.3354, |
|
"step": 30500 |
|
}, |
|
{ |
|
"epoch": 1.86, |
|
"learning_rate": 7.592803826219208e-06, |
|
"loss": 0.3284, |
|
"step": 31000 |
|
}, |
|
{ |
|
"epoch": 1.89, |
|
"learning_rate": 7.3926877589001625e-06, |
|
"loss": 0.3361, |
|
"step": 31500 |
|
}, |
|
{ |
|
"epoch": 1.92, |
|
"learning_rate": 7.192571691581117e-06, |
|
"loss": 0.3418, |
|
"step": 32000 |
|
}, |
|
{ |
|
"epoch": 1.95, |
|
"learning_rate": 6.992455624262072e-06, |
|
"loss": 0.3373, |
|
"step": 32500 |
|
}, |
|
{ |
|
"epoch": 1.98, |
|
"learning_rate": 6.792339556943027e-06, |
|
"loss": 0.3397, |
|
"step": 33000 |
|
}, |
|
{ |
|
"epoch": 2.0, |
|
"eval_accuracy": 0.9208375811576843, |
|
"eval_loss": 0.21520225703716278, |
|
"eval_runtime": 27.5064, |
|
"eval_samples_per_second": 142.367, |
|
"eval_steps_per_second": 4.472, |
|
"step": 33314 |
|
}, |
|
{ |
|
"epoch": 2.01, |
|
"learning_rate": 6.592223489623982e-06, |
|
"loss": 0.32, |
|
"step": 33500 |
|
}, |
|
{ |
|
"epoch": 2.04, |
|
"learning_rate": 6.392107422304937e-06, |
|
"loss": 0.2961, |
|
"step": 34000 |
|
}, |
|
{ |
|
"epoch": 2.07, |
|
"learning_rate": 6.191991354985892e-06, |
|
"loss": 0.2895, |
|
"step": 34500 |
|
}, |
|
{ |
|
"epoch": 2.1, |
|
"learning_rate": 5.991875287666847e-06, |
|
"loss": 0.2965, |
|
"step": 35000 |
|
}, |
|
{ |
|
"epoch": 2.13, |
|
"learning_rate": 5.791759220347802e-06, |
|
"loss": 0.2922, |
|
"step": 35500 |
|
}, |
|
{ |
|
"epoch": 2.16, |
|
"learning_rate": 5.591643153028758e-06, |
|
"loss": 0.2837, |
|
"step": 36000 |
|
}, |
|
{ |
|
"epoch": 2.19, |
|
"learning_rate": 5.391527085709713e-06, |
|
"loss": 0.2812, |
|
"step": 36500 |
|
}, |
|
{ |
|
"epoch": 2.22, |
|
"learning_rate": 5.191411018390668e-06, |
|
"loss": 0.2819, |
|
"step": 37000 |
|
}, |
|
{ |
|
"epoch": 2.25, |
|
"learning_rate": 4.991294951071622e-06, |
|
"loss": 0.2874, |
|
"step": 37500 |
|
}, |
|
{ |
|
"epoch": 2.28, |
|
"learning_rate": 4.791178883752577e-06, |
|
"loss": 0.2727, |
|
"step": 38000 |
|
}, |
|
{ |
|
"epoch": 2.31, |
|
"learning_rate": 4.5910628164335316e-06, |
|
"loss": 0.2733, |
|
"step": 38500 |
|
}, |
|
{ |
|
"epoch": 2.34, |
|
"learning_rate": 4.390946749114487e-06, |
|
"loss": 0.2865, |
|
"step": 39000 |
|
}, |
|
{ |
|
"epoch": 2.37, |
|
"learning_rate": 4.190830681795442e-06, |
|
"loss": 0.2799, |
|
"step": 39500 |
|
}, |
|
{ |
|
"epoch": 2.4, |
|
"learning_rate": 3.990714614476396e-06, |
|
"loss": 0.2833, |
|
"step": 40000 |
|
}, |
|
{ |
|
"epoch": 2.43, |
|
"learning_rate": 3.7905985471573513e-06, |
|
"loss": 0.2874, |
|
"step": 40500 |
|
}, |
|
{ |
|
"epoch": 2.46, |
|
"learning_rate": 3.5904824798383066e-06, |
|
"loss": 0.2853, |
|
"step": 41000 |
|
}, |
|
{ |
|
"epoch": 2.49, |
|
"learning_rate": 3.3903664125192616e-06, |
|
"loss": 0.2862, |
|
"step": 41500 |
|
}, |
|
{ |
|
"epoch": 2.52, |
|
"learning_rate": 3.1902503452002165e-06, |
|
"loss": 0.2851, |
|
"step": 42000 |
|
}, |
|
{ |
|
"epoch": 2.55, |
|
"learning_rate": 2.9901342778811715e-06, |
|
"loss": 0.2744, |
|
"step": 42500 |
|
}, |
|
{ |
|
"epoch": 2.58, |
|
"learning_rate": 2.7900182105621264e-06, |
|
"loss": 0.2729, |
|
"step": 43000 |
|
}, |
|
{ |
|
"epoch": 2.61, |
|
"learning_rate": 2.589902143243081e-06, |
|
"loss": 0.2792, |
|
"step": 43500 |
|
}, |
|
{ |
|
"epoch": 2.64, |
|
"learning_rate": 2.3897860759240363e-06, |
|
"loss": 0.2828, |
|
"step": 44000 |
|
}, |
|
{ |
|
"epoch": 2.67, |
|
"learning_rate": 2.189670008604991e-06, |
|
"loss": 0.277, |
|
"step": 44500 |
|
}, |
|
{ |
|
"epoch": 2.7, |
|
"learning_rate": 1.989553941285946e-06, |
|
"loss": 0.2812, |
|
"step": 45000 |
|
}, |
|
{ |
|
"epoch": 2.73, |
|
"learning_rate": 1.789437873966901e-06, |
|
"loss": 0.2807, |
|
"step": 45500 |
|
}, |
|
{ |
|
"epoch": 2.76, |
|
"learning_rate": 1.5893218066478558e-06, |
|
"loss": 0.2852, |
|
"step": 46000 |
|
}, |
|
{ |
|
"epoch": 2.79, |
|
"learning_rate": 1.3892057393288107e-06, |
|
"loss": 0.2824, |
|
"step": 46500 |
|
}, |
|
{ |
|
"epoch": 2.82, |
|
"learning_rate": 1.1890896720097659e-06, |
|
"loss": 0.2784, |
|
"step": 47000 |
|
}, |
|
{ |
|
"epoch": 2.85, |
|
"learning_rate": 9.889736046907208e-07, |
|
"loss": 0.2736, |
|
"step": 47500 |
|
}, |
|
{ |
|
"epoch": 2.88, |
|
"learning_rate": 7.888575373716756e-07, |
|
"loss": 0.281, |
|
"step": 48000 |
|
}, |
|
{ |
|
"epoch": 2.91, |
|
"learning_rate": 5.887414700526306e-07, |
|
"loss": 0.2781, |
|
"step": 48500 |
|
}, |
|
{ |
|
"epoch": 2.94, |
|
"learning_rate": 3.886254027335855e-07, |
|
"loss": 0.2833, |
|
"step": 49000 |
|
}, |
|
{ |
|
"epoch": 2.97, |
|
"learning_rate": 1.8850933541454047e-07, |
|
"loss": 0.2775, |
|
"step": 49500 |
|
}, |
|
{ |
|
"epoch": 3.0, |
|
"eval_accuracy": 0.9328396320343018, |
|
"eval_loss": 0.2038867175579071, |
|
"eval_runtime": 27.4892, |
|
"eval_samples_per_second": 142.456, |
|
"eval_steps_per_second": 4.474, |
|
"step": 49971 |
|
}, |
|
{ |
|
"epoch": 3.0, |
|
"step": 49971, |
|
"total_flos": 4.207223016483379e+17, |
|
"train_loss": 0.36741465170648585, |
|
"train_runtime": 31812.3263, |
|
"train_samples_per_second": 50.264, |
|
"train_steps_per_second": 1.571 |
|
} |
|
], |
|
"max_steps": 49971, |
|
"num_train_epochs": 3, |
|
"total_flos": 4.207223016483379e+17, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|