| { | |
| "best_metric": 0.4735645055770874, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.22598870056497175, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.004519774011299435, | |
| "grad_norm": 8.21904182434082, | |
| "learning_rate": 5e-05, | |
| "loss": 4.4381, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.004519774011299435, | |
| "eval_loss": 5.951687812805176, | |
| "eval_runtime": 45.6763, | |
| "eval_samples_per_second": 32.643, | |
| "eval_steps_per_second": 4.094, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00903954802259887, | |
| "grad_norm": 13.002219200134277, | |
| "learning_rate": 0.0001, | |
| "loss": 5.023, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.013559322033898305, | |
| "grad_norm": 10.776192665100098, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 4.5764, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.01807909604519774, | |
| "grad_norm": 8.736804962158203, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 2.4086, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.022598870056497175, | |
| "grad_norm": 8.48847770690918, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 1.912, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.02711864406779661, | |
| "grad_norm": 4.094654560089111, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 1.2446, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.031638418079096044, | |
| "grad_norm": 3.8300228118896484, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 1.078, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.03615819209039548, | |
| "grad_norm": 3.783612012863159, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.9286, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.04067796610169491, | |
| "grad_norm": 2.466135025024414, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 0.6932, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.04519774011299435, | |
| "grad_norm": 2.876997947692871, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 0.689, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.04971751412429379, | |
| "grad_norm": 4.741170406341553, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 1.017, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.05423728813559322, | |
| "grad_norm": 5.207798957824707, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 1.227, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.05875706214689266, | |
| "grad_norm": 3.274278163909912, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 0.8698, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.06327683615819209, | |
| "grad_norm": 3.666516065597534, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.6803, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.06779661016949153, | |
| "grad_norm": 3.6715118885040283, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 0.3187, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.07231638418079096, | |
| "grad_norm": 4.110116958618164, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 0.4916, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0768361581920904, | |
| "grad_norm": 3.0237069129943848, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 0.472, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.08135593220338982, | |
| "grad_norm": 2.0605337619781494, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.4241, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.08587570621468926, | |
| "grad_norm": 2.0675086975097656, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 0.4192, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.0903954802259887, | |
| "grad_norm": 2.2563467025756836, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.5129, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.09491525423728814, | |
| "grad_norm": 1.2747396230697632, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 0.3892, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.09943502824858758, | |
| "grad_norm": 1.0977623462677002, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 0.3669, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.103954802259887, | |
| "grad_norm": 1.2149648666381836, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 0.4668, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.10847457627118644, | |
| "grad_norm": 2.5276224613189697, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 0.7854, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.11299435028248588, | |
| "grad_norm": 3.073773145675659, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 1.2577, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.11299435028248588, | |
| "eval_loss": 0.5865195989608765, | |
| "eval_runtime": 45.7222, | |
| "eval_samples_per_second": 32.61, | |
| "eval_steps_per_second": 4.09, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.11751412429378531, | |
| "grad_norm": 1.8527536392211914, | |
| "learning_rate": 5e-05, | |
| "loss": 0.3976, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.12203389830508475, | |
| "grad_norm": 2.8209228515625, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 0.3309, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.12655367231638417, | |
| "grad_norm": 2.0492920875549316, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 0.2644, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.1310734463276836, | |
| "grad_norm": 2.1586620807647705, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 0.3537, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.13559322033898305, | |
| "grad_norm": 1.6471965312957764, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 0.3327, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.1401129943502825, | |
| "grad_norm": 1.7886873483657837, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 0.3424, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.14463276836158193, | |
| "grad_norm": 1.3556740283966064, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.3908, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.14915254237288136, | |
| "grad_norm": 1.0796656608581543, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 0.309, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.1536723163841808, | |
| "grad_norm": 1.0365829467773438, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 0.3266, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.15819209039548024, | |
| "grad_norm": 1.349151372909546, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 0.4729, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.16271186440677965, | |
| "grad_norm": 1.5345674753189087, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 0.6634, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.1672316384180791, | |
| "grad_norm": 2.3143022060394287, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 0.9111, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.17175141242937852, | |
| "grad_norm": 2.0356972217559814, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.6721, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.17627118644067796, | |
| "grad_norm": 2.04655122756958, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 0.3078, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.1807909604519774, | |
| "grad_norm": 1.8083769083023071, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 0.2806, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.18531073446327684, | |
| "grad_norm": 1.5266116857528687, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 0.2657, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.18983050847457628, | |
| "grad_norm": 1.4158159494400024, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 0.3006, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.1943502824858757, | |
| "grad_norm": 1.438349962234497, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 0.2911, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.19887005649717515, | |
| "grad_norm": 1.2258505821228027, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.2923, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.2033898305084746, | |
| "grad_norm": 1.1532789468765259, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 0.292, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.207909604519774, | |
| "grad_norm": 1.1727447509765625, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 0.3245, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.21242937853107344, | |
| "grad_norm": 0.9141059517860413, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 0.3134, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.21694915254237288, | |
| "grad_norm": 1.4333127737045288, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 0.637, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.2214689265536723, | |
| "grad_norm": 2.0578904151916504, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 0.7578, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.22598870056497175, | |
| "grad_norm": 2.9676828384399414, | |
| "learning_rate": 0.0, | |
| "loss": 1.1515, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.22598870056497175, | |
| "eval_loss": 0.4735645055770874, | |
| "eval_runtime": 45.7075, | |
| "eval_samples_per_second": 32.62, | |
| "eval_steps_per_second": 4.091, | |
| "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": 5.9736786926882e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |