| { | |
| "best_metric": 2.793840169906616, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-500", | |
| "epoch": 0.029735355337496282, | |
| "eval_steps": 50, | |
| "global_step": 500, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 5.947071067499257e-05, | |
| "eval_loss": 3.2442233562469482, | |
| "eval_runtime": 149.0831, | |
| "eval_samples_per_second": 47.49, | |
| "eval_steps_per_second": 11.873, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0005947071067499256, | |
| "grad_norm": 0.7875794172286987, | |
| "learning_rate": 4.1400000000000003e-05, | |
| "loss": 3.0668, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0011894142134998512, | |
| "grad_norm": 0.8943319916725159, | |
| "learning_rate": 8.280000000000001e-05, | |
| "loss": 3.1298, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.001784121320249777, | |
| "grad_norm": 1.10039222240448, | |
| "learning_rate": 0.00012419999999999998, | |
| "loss": 3.0946, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0023788284269997025, | |
| "grad_norm": 1.2827677726745605, | |
| "learning_rate": 0.00016560000000000001, | |
| "loss": 2.9561, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0029735355337496285, | |
| "grad_norm": 2.5582001209259033, | |
| "learning_rate": 0.000207, | |
| "loss": 2.998, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.0029735355337496285, | |
| "eval_loss": 2.9912269115448, | |
| "eval_runtime": 148.1587, | |
| "eval_samples_per_second": 47.787, | |
| "eval_steps_per_second": 11.947, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.003568242640499554, | |
| "grad_norm": 0.7799744009971619, | |
| "learning_rate": 0.00020674787920189178, | |
| "loss": 3.003, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.004162949747249479, | |
| "grad_norm": 0.8374800682067871, | |
| "learning_rate": 0.00020599274511475253, | |
| "loss": 3.0247, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.004757656853999405, | |
| "grad_norm": 0.9920192956924438, | |
| "learning_rate": 0.00020473827667594888, | |
| "loss": 2.9491, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.0053523639607493305, | |
| "grad_norm": 1.210517168045044, | |
| "learning_rate": 0.00020299058552961598, | |
| "loss": 2.9129, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.005947071067499257, | |
| "grad_norm": 2.20344614982605, | |
| "learning_rate": 0.00020075818625134152, | |
| "loss": 2.9891, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.005947071067499257, | |
| "eval_loss": 2.934997797012329, | |
| "eval_runtime": 149.0913, | |
| "eval_samples_per_second": 47.488, | |
| "eval_steps_per_second": 11.872, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.006541778174249183, | |
| "grad_norm": 0.7027397155761719, | |
| "learning_rate": 0.00019805195486600916, | |
| "loss": 2.9015, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.007136485280999108, | |
| "grad_norm": 0.7384776473045349, | |
| "learning_rate": 0.00019488507586089894, | |
| "loss": 2.9129, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.007731192387749034, | |
| "grad_norm": 0.8933420777320862, | |
| "learning_rate": 0.00019127297795219008, | |
| "loss": 2.8789, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.008325899494498959, | |
| "grad_norm": 1.1296390295028687, | |
| "learning_rate": 0.00018723325891780706, | |
| "loss": 2.8091, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.008920606601248885, | |
| "grad_norm": 1.680759310722351, | |
| "learning_rate": 0.0001827855998628142, | |
| "loss": 2.8615, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.008920606601248885, | |
| "eval_loss": 2.9041831493377686, | |
| "eval_runtime": 149.8181, | |
| "eval_samples_per_second": 47.257, | |
| "eval_steps_per_second": 11.814, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.00951531370799881, | |
| "grad_norm": 0.7546591758728027, | |
| "learning_rate": 0.0001779516693350504, | |
| "loss": 2.8554, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.010110020814748736, | |
| "grad_norm": 0.7574900388717651, | |
| "learning_rate": 0.00017275501775814182, | |
| "loss": 2.7957, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.010704727921498661, | |
| "grad_norm": 0.8689918518066406, | |
| "learning_rate": 0.00016722096269620562, | |
| "loss": 2.8529, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.011299435028248588, | |
| "grad_norm": 1.0633153915405273, | |
| "learning_rate": 0.00016137646550922228, | |
| "loss": 2.8309, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.011894142134998514, | |
| "grad_norm": 2.1989660263061523, | |
| "learning_rate": 0.00015525, | |
| "loss": 2.9186, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.011894142134998514, | |
| "eval_loss": 2.8749983310699463, | |
| "eval_runtime": 149.067, | |
| "eval_samples_per_second": 47.495, | |
| "eval_steps_per_second": 11.874, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.012488849241748439, | |
| "grad_norm": 0.6521171927452087, | |
| "learning_rate": 0.0001488714136926695, | |
| "loss": 2.9137, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.013083556348498365, | |
| "grad_norm": 0.7320899963378906, | |
| "learning_rate": 0.0001422717824185469, | |
| "loss": 2.8405, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.01367826345524829, | |
| "grad_norm": 0.8370326161384583, | |
| "learning_rate": 0.00013548325891780705, | |
| "loss": 2.8327, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.014272970561998216, | |
| "grad_norm": 1.010695219039917, | |
| "learning_rate": 0.0001285389161945656, | |
| "loss": 2.8228, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.014867677668748141, | |
| "grad_norm": 1.9595260620117188, | |
| "learning_rate": 0.0001214725863885273, | |
| "loss": 2.772, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.014867677668748141, | |
| "eval_loss": 2.844726085662842, | |
| "eval_runtime": 150.3953, | |
| "eval_samples_per_second": 47.076, | |
| "eval_steps_per_second": 11.769, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.015462384775498068, | |
| "grad_norm": 0.6232745051383972, | |
| "learning_rate": 0.00011431869594820213, | |
| "loss": 2.8667, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.016057091882247992, | |
| "grad_norm": 0.7752615213394165, | |
| "learning_rate": 0.00010711209790870886, | |
| "loss": 2.8185, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.016651798988997917, | |
| "grad_norm": 0.8857811093330383, | |
| "learning_rate": 9.988790209129117e-05, | |
| "loss": 2.7915, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.017246506095747845, | |
| "grad_norm": 1.0391193628311157, | |
| "learning_rate": 9.268130405179787e-05, | |
| "loss": 2.795, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.01784121320249777, | |
| "grad_norm": 1.5660728216171265, | |
| "learning_rate": 8.55274136114727e-05, | |
| "loss": 2.771, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.01784121320249777, | |
| "eval_loss": 2.820711851119995, | |
| "eval_runtime": 149.8338, | |
| "eval_samples_per_second": 47.252, | |
| "eval_steps_per_second": 11.813, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.018435920309247695, | |
| "grad_norm": 0.658405065536499, | |
| "learning_rate": 7.84610838054344e-05, | |
| "loss": 2.8653, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.01903062741599762, | |
| "grad_norm": 0.7782045602798462, | |
| "learning_rate": 7.151674108219295e-05, | |
| "loss": 2.8074, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.019625334522747548, | |
| "grad_norm": 0.9159675240516663, | |
| "learning_rate": 6.472821758145309e-05, | |
| "loss": 2.814, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.020220041629497473, | |
| "grad_norm": 1.0867841243743896, | |
| "learning_rate": 5.8128586307330475e-05, | |
| "loss": 2.7224, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.020814748736247397, | |
| "grad_norm": 1.6991764307022095, | |
| "learning_rate": 5.175000000000002e-05, | |
| "loss": 2.7216, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.020814748736247397, | |
| "eval_loss": 2.8091001510620117, | |
| "eval_runtime": 150.0782, | |
| "eval_samples_per_second": 47.175, | |
| "eval_steps_per_second": 11.794, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.021409455842997322, | |
| "grad_norm": 0.6833013296127319, | |
| "learning_rate": 4.5623534490777714e-05, | |
| "loss": 2.8396, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.02200416294974725, | |
| "grad_norm": 0.7645152807235718, | |
| "learning_rate": 3.9779037303794365e-05, | |
| "loss": 2.7683, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.022598870056497175, | |
| "grad_norm": 0.88221675157547, | |
| "learning_rate": 3.42449822418582e-05, | |
| "loss": 2.7769, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.0231935771632471, | |
| "grad_norm": 1.0650640726089478, | |
| "learning_rate": 2.9048330664949622e-05, | |
| "loss": 2.782, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.023788284269997028, | |
| "grad_norm": 1.8103938102722168, | |
| "learning_rate": 2.4214400137185785e-05, | |
| "loss": 2.8704, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.023788284269997028, | |
| "eval_loss": 2.798283100128174, | |
| "eval_runtime": 149.8594, | |
| "eval_samples_per_second": 47.244, | |
| "eval_steps_per_second": 11.811, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.024382991376746953, | |
| "grad_norm": 0.6215288639068604, | |
| "learning_rate": 1.976674108219295e-05, | |
| "loss": 2.8352, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.024977698483496878, | |
| "grad_norm": 0.7338668704032898, | |
| "learning_rate": 1.572702204780991e-05, | |
| "loss": 2.801, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.025572405590246802, | |
| "grad_norm": 0.9176461100578308, | |
| "learning_rate": 1.2114924139101056e-05, | |
| "loss": 2.7443, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.02616711269699673, | |
| "grad_norm": 1.041648507118225, | |
| "learning_rate": 8.948045133990798e-06, | |
| "loss": 2.7708, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.026761819803746655, | |
| "grad_norm": 1.8905234336853027, | |
| "learning_rate": 6.241813748658489e-06, | |
| "loss": 2.7077, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.026761819803746655, | |
| "eval_loss": 2.7940969467163086, | |
| "eval_runtime": 149.9687, | |
| "eval_samples_per_second": 47.21, | |
| "eval_steps_per_second": 11.802, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.02735652691049658, | |
| "grad_norm": 0.6684868931770325, | |
| "learning_rate": 4.009414470383994e-06, | |
| "loss": 2.8264, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.027951234017246505, | |
| "grad_norm": 0.767475426197052, | |
| "learning_rate": 2.261723324051111e-06, | |
| "loss": 2.8228, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 0.028545941123996433, | |
| "grad_norm": 0.8956049084663391, | |
| "learning_rate": 1.0072548852474675e-06, | |
| "loss": 2.8007, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.029140648230746358, | |
| "grad_norm": 1.0334606170654297, | |
| "learning_rate": 2.5212079810819554e-07, | |
| "loss": 2.7903, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 0.029735355337496282, | |
| "grad_norm": 1.8637531995773315, | |
| "learning_rate": 0.0, | |
| "loss": 2.8391, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.029735355337496282, | |
| "eval_loss": 2.793840169906616, | |
| "eval_runtime": 149.431, | |
| "eval_samples_per_second": 47.38, | |
| "eval_steps_per_second": 11.845, | |
| "step": 500 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 500, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 50, | |
| "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": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 5280990253547520.0, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |