| { | |
| "best_metric": 0.11276409775018692, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.08653326122228232, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0017306652244456463, | |
| "grad_norm": 1.4002636671066284, | |
| "learning_rate": 5e-05, | |
| "loss": 1.5481, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0017306652244456463, | |
| "eval_loss": 0.5736979842185974, | |
| "eval_runtime": 254.0435, | |
| "eval_samples_per_second": 15.324, | |
| "eval_steps_per_second": 1.917, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0034613304488912925, | |
| "grad_norm": 1.3764536380767822, | |
| "learning_rate": 0.0001, | |
| "loss": 1.5904, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.005191995673336939, | |
| "grad_norm": 1.4798710346221924, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 1.6032, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.006922660897782585, | |
| "grad_norm": 1.3405709266662598, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 1.5342, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.008653326122228232, | |
| "grad_norm": 1.2640881538391113, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 1.5745, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.010383991346673878, | |
| "grad_norm": 1.7632824182510376, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 1.6276, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.012114656571119525, | |
| "grad_norm": 1.5980461835861206, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 1.7191, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.01384532179556517, | |
| "grad_norm": 2.0756115913391113, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 2.1301, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.015575987020010817, | |
| "grad_norm": 4.433633804321289, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 3.4465, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.017306652244456464, | |
| "grad_norm": 24.18182373046875, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 6.065, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.01903731746890211, | |
| "grad_norm": 27.007915496826172, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 11.0667, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.020767982693347755, | |
| "grad_norm": 30.23172378540039, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 13.4868, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0224986479177934, | |
| "grad_norm": 15.03230094909668, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 8.3147, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.02422931314223905, | |
| "grad_norm": 3.4996674060821533, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.8715, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.025959978366684695, | |
| "grad_norm": 2.583794593811035, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 0.7457, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.02769064359113034, | |
| "grad_norm": 1.7750343084335327, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 0.608, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.029421308815575985, | |
| "grad_norm": 1.2232266664505005, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 0.5744, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.031151974040021634, | |
| "grad_norm": 0.8187417984008789, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.639, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.03288263926446728, | |
| "grad_norm": 0.7798706889152527, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 0.7009, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.03461330448891293, | |
| "grad_norm": 0.8445702791213989, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.8675, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.03634396971335857, | |
| "grad_norm": 1.517020344734192, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 1.2753, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.03807463493780422, | |
| "grad_norm": 4.503598213195801, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 2.8101, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.03980530016224987, | |
| "grad_norm": 8.036548614501953, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 5.5756, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.04153596538669551, | |
| "grad_norm": 12.358596801757812, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 7.348, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.04326663061114116, | |
| "grad_norm": 10.770831108093262, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 8.5886, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.04326663061114116, | |
| "eval_loss": 0.129599466919899, | |
| "eval_runtime": 253.6383, | |
| "eval_samples_per_second": 15.349, | |
| "eval_steps_per_second": 1.92, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0449972958355868, | |
| "grad_norm": 0.32266557216644287, | |
| "learning_rate": 5e-05, | |
| "loss": 0.3074, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.04672796106003245, | |
| "grad_norm": 0.28177428245544434, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 0.3009, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.0484586262844781, | |
| "grad_norm": 0.33837753534317017, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 0.3084, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.05018929150892374, | |
| "grad_norm": 0.36775338649749756, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 0.3503, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.05191995673336939, | |
| "grad_norm": 0.42138978838920593, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 0.4526, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.05365062195781504, | |
| "grad_norm": 0.32471925020217896, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 0.4586, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.05538128718226068, | |
| "grad_norm": 0.4468209147453308, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.5963, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.05711195240670633, | |
| "grad_norm": 0.571643054485321, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 0.8194, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.05884261763115197, | |
| "grad_norm": 1.112444281578064, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 1.495, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.06057328285559762, | |
| "grad_norm": 2.6555335521698, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 3.1862, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.06230394808004327, | |
| "grad_norm": 5.029642581939697, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 5.3868, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.06403461330448891, | |
| "grad_norm": 5.934193134307861, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 6.6229, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.06576527852893456, | |
| "grad_norm": 5.213059425354004, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 3.9546, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.06749594375338021, | |
| "grad_norm": 0.23849663138389587, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 0.2603, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.06922660897782586, | |
| "grad_norm": 0.2760283946990967, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 0.2778, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.07095727420227149, | |
| "grad_norm": 0.27695363759994507, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 0.2952, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.07268793942671714, | |
| "grad_norm": 0.3437682092189789, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 0.3676, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.07441860465116279, | |
| "grad_norm": 0.3884122669696808, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 0.4221, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.07614926987560844, | |
| "grad_norm": 0.3740735948085785, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.4325, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.07787993510005409, | |
| "grad_norm": 0.5789932608604431, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 0.5894, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.07961060032449974, | |
| "grad_norm": 0.9600825309753418, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 0.8835, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.08134126554894537, | |
| "grad_norm": 1.3175654411315918, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 1.6708, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.08307193077339102, | |
| "grad_norm": 2.7750141620635986, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 3.8229, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.08480259599783667, | |
| "grad_norm": 5.7807769775390625, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 5.909, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.08653326122228232, | |
| "grad_norm": 7.599081993103027, | |
| "learning_rate": 0.0, | |
| "loss": 7.9763, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.08653326122228232, | |
| "eval_loss": 0.11276409775018692, | |
| "eval_runtime": 252.0036, | |
| "eval_samples_per_second": 15.448, | |
| "eval_steps_per_second": 1.933, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 25, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 1, | |
| "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": 6.542719156695859e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |