| { | |
| "best_metric": 2.9313533306121826, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.012930128816408334, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00025860257632816664, | |
| "grad_norm": 5.741217136383057, | |
| "learning_rate": 5e-05, | |
| "loss": 4.6549, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00025860257632816664, | |
| "eval_loss": 6.674937725067139, | |
| "eval_runtime": 296.6341, | |
| "eval_samples_per_second": 87.822, | |
| "eval_steps_per_second": 10.98, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0005172051526563333, | |
| "grad_norm": 13.521225929260254, | |
| "learning_rate": 0.0001, | |
| "loss": 5.4911, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0007758077289845, | |
| "grad_norm": 12.85054874420166, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 5.5499, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0010344103053126666, | |
| "grad_norm": 8.233442306518555, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 5.2136, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0012930128816408333, | |
| "grad_norm": 4.432310581207275, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 5.1171, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.001551615457969, | |
| "grad_norm": 4.025936126708984, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 5.0315, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0018102180342971666, | |
| "grad_norm": 5.589695453643799, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 4.9262, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.002068820610625333, | |
| "grad_norm": 5.1999192237854, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 4.7665, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0023274231869535, | |
| "grad_norm": 7.176267147064209, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 4.6157, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0025860257632816666, | |
| "grad_norm": 5.858346462249756, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 4.3698, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0028446283396098334, | |
| "grad_norm": 6.558874130249023, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 4.2562, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.003103230915938, | |
| "grad_norm": 11.06159496307373, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 4.0369, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.003361833492266167, | |
| "grad_norm": 3.8055031299591064, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 3.2398, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0036204360685943332, | |
| "grad_norm": 2.373939275741577, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 2.9109, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0038790386449225, | |
| "grad_norm": 2.5665676593780518, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 2.9915, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.004137641221250666, | |
| "grad_norm": 2.2287397384643555, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 2.9531, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.004396243797578833, | |
| "grad_norm": 2.4629924297332764, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 3.0267, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.004654846373907, | |
| "grad_norm": 1.796347737312317, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 3.2085, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0049134489502351665, | |
| "grad_norm": 1.896411657333374, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 3.1843, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.005172051526563333, | |
| "grad_norm": 1.9694262742996216, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 3.1063, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0054306541028915, | |
| "grad_norm": 1.484022617340088, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 3.107, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.005689256679219667, | |
| "grad_norm": 2.0523884296417236, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 3.0146, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.0059478592555478335, | |
| "grad_norm": 2.0209202766418457, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 3.1336, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.006206461831876, | |
| "grad_norm": 2.6279311180114746, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 3.184, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.006465064408204167, | |
| "grad_norm": 2.708322048187256, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 3.4056, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.006465064408204167, | |
| "eval_loss": 3.034134864807129, | |
| "eval_runtime": 296.595, | |
| "eval_samples_per_second": 87.834, | |
| "eval_steps_per_second": 10.981, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.006723666984532334, | |
| "grad_norm": 1.964606523513794, | |
| "learning_rate": 5e-05, | |
| "loss": 2.7854, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.0069822695608605, | |
| "grad_norm": 1.8417248725891113, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 2.9155, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.0072408721371886664, | |
| "grad_norm": 1.793028473854065, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 2.8597, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.007499474713516833, | |
| "grad_norm": 1.854422926902771, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 2.9504, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.007758077289845, | |
| "grad_norm": 1.4125136137008667, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 2.8636, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.008016679866173167, | |
| "grad_norm": 1.5822298526763916, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 3.033, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.008275282442501333, | |
| "grad_norm": 1.4431718587875366, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 3.0272, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.0085338850188295, | |
| "grad_norm": 2.054440975189209, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 3.1003, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.008792487595157666, | |
| "grad_norm": 1.8294641971588135, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 2.9858, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.009051090171485834, | |
| "grad_norm": 1.8595656156539917, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 3.0471, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.009309692747814, | |
| "grad_norm": 2.144545316696167, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 2.9967, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.009568295324142167, | |
| "grad_norm": 2.1275172233581543, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 3.1765, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.009826897900470333, | |
| "grad_norm": 1.1156597137451172, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 2.7978, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.0100855004767985, | |
| "grad_norm": 1.2987682819366455, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 2.6641, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.010344103053126667, | |
| "grad_norm": 1.2446664571762085, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 2.7144, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.010602705629454834, | |
| "grad_norm": 1.220151662826538, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 2.8118, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.010861308205783, | |
| "grad_norm": 1.4637597799301147, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 2.8893, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.011119910782111166, | |
| "grad_norm": 1.2210360765457153, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 2.9138, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.011378513358439334, | |
| "grad_norm": 1.2036255598068237, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 3.0561, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.0116371159347675, | |
| "grad_norm": 1.1922022104263306, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 2.8757, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.011895718511095667, | |
| "grad_norm": 1.218916416168213, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 2.9347, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.012154321087423833, | |
| "grad_norm": 1.652422547340393, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 2.9598, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.012412923663752, | |
| "grad_norm": 1.3585187196731567, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 3.0889, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.012671526240080166, | |
| "grad_norm": 1.5648044347763062, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 3.1441, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.012930128816408334, | |
| "grad_norm": 2.3186755180358887, | |
| "learning_rate": 0.0, | |
| "loss": 3.2848, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.012930128816408334, | |
| "eval_loss": 2.9313533306121826, | |
| "eval_runtime": 296.4974, | |
| "eval_samples_per_second": 87.862, | |
| "eval_steps_per_second": 10.985, | |
| "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": 1.059536353886208e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |