| { | |
| "best_metric": 2.54923321563183e-07, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-720", | |
| "epoch": 4.848484848484849, | |
| "eval_steps": 20, | |
| "global_step": 720, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.006734006734006734, | |
| "eval_loss": 0.47625598311424255, | |
| "eval_runtime": 4.3305, | |
| "eval_samples_per_second": 28.865, | |
| "eval_steps_per_second": 0.924, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.13468013468013468, | |
| "eval_loss": 5.0069978897226974e-05, | |
| "eval_runtime": 4.3728, | |
| "eval_samples_per_second": 28.585, | |
| "eval_steps_per_second": 0.915, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.26936026936026936, | |
| "eval_loss": 8.045045433391351e-06, | |
| "eval_runtime": 4.3441, | |
| "eval_samples_per_second": 28.775, | |
| "eval_steps_per_second": 0.921, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.40404040404040403, | |
| "eval_loss": 3.3631840778980404e-06, | |
| "eval_runtime": 4.4814, | |
| "eval_samples_per_second": 27.893, | |
| "eval_steps_per_second": 0.893, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.5387205387205387, | |
| "eval_loss": 2.012430513786967e-06, | |
| "eval_runtime": 4.4241, | |
| "eval_samples_per_second": 28.254, | |
| "eval_steps_per_second": 0.904, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.6734006734006734, | |
| "grad_norm": 4.331162563175894e-05, | |
| "learning_rate": 0.0002886742611435581, | |
| "loss": 0.0221, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.6734006734006734, | |
| "eval_loss": 1.4569956192644895e-06, | |
| "eval_runtime": 4.4112, | |
| "eval_samples_per_second": 28.337, | |
| "eval_steps_per_second": 0.907, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.8080808080808081, | |
| "eval_loss": 1.157558699560468e-06, | |
| "eval_runtime": 4.3819, | |
| "eval_samples_per_second": 28.526, | |
| "eval_steps_per_second": 0.913, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.9427609427609428, | |
| "eval_loss": 9.559958016325254e-07, | |
| "eval_runtime": 4.3682, | |
| "eval_samples_per_second": 28.616, | |
| "eval_steps_per_second": 0.916, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 1.0774410774410774, | |
| "eval_loss": 8.15467842585349e-07, | |
| "eval_runtime": 4.377, | |
| "eval_samples_per_second": 28.559, | |
| "eval_steps_per_second": 0.914, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 1.2121212121212122, | |
| "eval_loss": 7.171624929469544e-07, | |
| "eval_runtime": 4.3662, | |
| "eval_samples_per_second": 28.629, | |
| "eval_steps_per_second": 0.916, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 1.3468013468013469, | |
| "grad_norm": 1.526053893030621e-05, | |
| "learning_rate": 0.0002522394955933096, | |
| "loss": 0.0, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.3468013468013469, | |
| "eval_loss": 6.367617970681749e-07, | |
| "eval_runtime": 4.4095, | |
| "eval_samples_per_second": 28.348, | |
| "eval_steps_per_second": 0.907, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.4814814814814814, | |
| "eval_loss": 5.753882987846737e-07, | |
| "eval_runtime": 4.3487, | |
| "eval_samples_per_second": 28.744, | |
| "eval_steps_per_second": 0.92, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 1.6161616161616161, | |
| "eval_loss": 5.237209279584931e-07, | |
| "eval_runtime": 4.3453, | |
| "eval_samples_per_second": 28.767, | |
| "eval_steps_per_second": 0.921, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 1.7508417508417509, | |
| "eval_loss": 4.83989538224705e-07, | |
| "eval_runtime": 4.3646, | |
| "eval_samples_per_second": 28.64, | |
| "eval_steps_per_second": 0.916, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 1.8855218855218854, | |
| "eval_loss": 4.489497769100126e-07, | |
| "eval_runtime": 4.3601, | |
| "eval_samples_per_second": 28.669, | |
| "eval_steps_per_second": 0.917, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 2.0202020202020203, | |
| "grad_norm": 1.0282737093803007e-05, | |
| "learning_rate": 0.00019721004253231048, | |
| "loss": 0.0, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 2.0202020202020203, | |
| "eval_loss": 4.185091029285104e-07, | |
| "eval_runtime": 4.3862, | |
| "eval_samples_per_second": 28.499, | |
| "eval_steps_per_second": 0.912, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 2.154882154882155, | |
| "eval_loss": 3.925752878330968e-07, | |
| "eval_runtime": 4.3765, | |
| "eval_samples_per_second": 28.562, | |
| "eval_steps_per_second": 0.914, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 2.28956228956229, | |
| "eval_loss": 3.6971795225326787e-07, | |
| "eval_runtime": 4.3977, | |
| "eval_samples_per_second": 28.424, | |
| "eval_steps_per_second": 0.91, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 2.4242424242424243, | |
| "eval_loss": 3.503983521113696e-07, | |
| "eval_runtime": 4.387, | |
| "eval_samples_per_second": 28.493, | |
| "eval_steps_per_second": 0.912, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 2.558922558922559, | |
| "eval_loss": 3.3884660410876677e-07, | |
| "eval_runtime": 4.549, | |
| "eval_samples_per_second": 27.478, | |
| "eval_steps_per_second": 0.879, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 2.6936026936026938, | |
| "grad_norm": 7.30554893380031e-06, | |
| "learning_rate": 0.00013359431874331886, | |
| "loss": 0.0, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 2.6936026936026938, | |
| "eval_loss": 3.222342002118239e-07, | |
| "eval_runtime": 4.5438, | |
| "eval_samples_per_second": 27.51, | |
| "eval_steps_per_second": 0.88, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 2.8282828282828283, | |
| "eval_loss": 3.13235887006158e-07, | |
| "eval_runtime": 4.3887, | |
| "eval_samples_per_second": 28.482, | |
| "eval_steps_per_second": 0.911, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 2.962962962962963, | |
| "eval_loss": 3.009457714142627e-07, | |
| "eval_runtime": 4.3984, | |
| "eval_samples_per_second": 28.419, | |
| "eval_steps_per_second": 0.909, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 3.0976430976430978, | |
| "eval_loss": 2.9283941671565117e-07, | |
| "eval_runtime": 4.4076, | |
| "eval_samples_per_second": 28.36, | |
| "eval_steps_per_second": 0.908, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 3.2323232323232323, | |
| "eval_loss": 2.863944814635033e-07, | |
| "eval_runtime": 4.3566, | |
| "eval_samples_per_second": 28.692, | |
| "eval_steps_per_second": 0.918, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 3.3670033670033668, | |
| "grad_norm": 6.557375400007004e-06, | |
| "learning_rate": 7.29623588569039e-05, | |
| "loss": 0.0, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 3.3670033670033668, | |
| "eval_loss": 2.800263985136553e-07, | |
| "eval_runtime": 4.3855, | |
| "eval_samples_per_second": 28.503, | |
| "eval_steps_per_second": 0.912, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 3.5016835016835017, | |
| "eval_loss": 2.736429962624243e-07, | |
| "eval_runtime": 4.3648, | |
| "eval_samples_per_second": 28.638, | |
| "eval_steps_per_second": 0.916, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 3.6363636363636362, | |
| "eval_loss": 2.6893604854194564e-07, | |
| "eval_runtime": 4.3884, | |
| "eval_samples_per_second": 28.484, | |
| "eval_steps_per_second": 0.912, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 3.771043771043771, | |
| "eval_loss": 2.6898223381977004e-07, | |
| "eval_runtime": 4.4647, | |
| "eval_samples_per_second": 27.998, | |
| "eval_steps_per_second": 0.896, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 3.9057239057239057, | |
| "eval_loss": 2.6613662384988857e-07, | |
| "eval_runtime": 4.3975, | |
| "eval_samples_per_second": 28.425, | |
| "eval_steps_per_second": 0.91, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 4.040404040404041, | |
| "grad_norm": 6.343952009046916e-06, | |
| "learning_rate": 2.6341528967837533e-05, | |
| "loss": 0.0, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 4.040404040404041, | |
| "eval_loss": 2.6435236577526666e-07, | |
| "eval_runtime": 4.4258, | |
| "eval_samples_per_second": 28.244, | |
| "eval_steps_per_second": 0.904, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 4.175084175084175, | |
| "eval_loss": 2.6299875344193424e-07, | |
| "eval_runtime": 4.3837, | |
| "eval_samples_per_second": 28.514, | |
| "eval_steps_per_second": 0.912, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 4.30976430976431, | |
| "eval_loss": 2.578611599801661e-07, | |
| "eval_runtime": 4.3645, | |
| "eval_samples_per_second": 28.64, | |
| "eval_steps_per_second": 0.916, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 4.444444444444445, | |
| "eval_loss": 2.583842331205233e-07, | |
| "eval_runtime": 4.3769, | |
| "eval_samples_per_second": 28.559, | |
| "eval_steps_per_second": 0.914, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 4.57912457912458, | |
| "eval_loss": 2.556154470312322e-07, | |
| "eval_runtime": 4.368, | |
| "eval_samples_per_second": 28.617, | |
| "eval_steps_per_second": 0.916, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 4.713804713804714, | |
| "grad_norm": 5.829084329889156e-06, | |
| "learning_rate": 2.2109374505137555e-06, | |
| "loss": 0.0, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 4.713804713804714, | |
| "eval_loss": 2.5736900965966925e-07, | |
| "eval_runtime": 4.3762, | |
| "eval_samples_per_second": 28.563, | |
| "eval_steps_per_second": 0.914, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 4.848484848484849, | |
| "eval_loss": 2.54923321563183e-07, | |
| "eval_runtime": 4.3625, | |
| "eval_samples_per_second": 28.653, | |
| "eval_steps_per_second": 0.917, | |
| "step": 720 | |
| } | |
| ], | |
| "logging_steps": 100, | |
| "max_steps": 740, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 5, | |
| "save_steps": 20, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 3, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 0 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3.040487007898829e+17, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |