| { | |
| "best_metric": 0.5172708034515381, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.16, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0032, | |
| "grad_norm": 10.65385627746582, | |
| "learning_rate": 5e-05, | |
| "loss": 7.2202, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0032, | |
| "eval_loss": 8.333258628845215, | |
| "eval_runtime": 52.8655, | |
| "eval_samples_per_second": 39.837, | |
| "eval_steps_per_second": 4.994, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0064, | |
| "grad_norm": 10.906144142150879, | |
| "learning_rate": 0.0001, | |
| "loss": 7.6932, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0096, | |
| "grad_norm": 9.757308959960938, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 7.0564, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0128, | |
| "grad_norm": 6.420623302459717, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 5.4659, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.016, | |
| "grad_norm": 6.6838483810424805, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 4.592, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0192, | |
| "grad_norm": 7.881312370300293, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 3.4263, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0224, | |
| "grad_norm": 6.462822437286377, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 2.0724, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0256, | |
| "grad_norm": 3.7375383377075195, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 1.3954, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0288, | |
| "grad_norm": 6.439095497131348, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 1.6787, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.032, | |
| "grad_norm": 4.565333366394043, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 1.3844, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0352, | |
| "grad_norm": 9.651759147644043, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 1.365, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0384, | |
| "grad_norm": 5.498544692993164, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 1.2902, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0416, | |
| "grad_norm": 2.8767731189727783, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 1.1868, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0448, | |
| "grad_norm": 3.1457948684692383, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.924, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.048, | |
| "grad_norm": 2.4111177921295166, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 0.9046, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0512, | |
| "grad_norm": 3.076181650161743, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 0.8759, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0544, | |
| "grad_norm": 1.6956605911254883, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 0.8947, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.0576, | |
| "grad_norm": 1.6995573043823242, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.7684, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0608, | |
| "grad_norm": 2.3091602325439453, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 0.7666, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.064, | |
| "grad_norm": 1.582398533821106, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.725, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0672, | |
| "grad_norm": 1.2624642848968506, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 0.724, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0704, | |
| "grad_norm": 1.661531925201416, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 0.6808, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.0736, | |
| "grad_norm": 1.2881686687469482, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 0.6824, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.0768, | |
| "grad_norm": 1.3341009616851807, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 0.6676, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": 1.4096139669418335, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 0.7769, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "eval_loss": 0.6112602949142456, | |
| "eval_runtime": 52.7922, | |
| "eval_samples_per_second": 39.892, | |
| "eval_steps_per_second": 5.001, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0832, | |
| "grad_norm": 1.339646816253662, | |
| "learning_rate": 5e-05, | |
| "loss": 0.6826, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.0864, | |
| "grad_norm": 1.1944141387939453, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 0.6551, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.0896, | |
| "grad_norm": 1.4156867265701294, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 0.6128, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.0928, | |
| "grad_norm": 0.8293469548225403, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 0.5205, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.096, | |
| "grad_norm": 1.3624340295791626, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 0.6409, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0992, | |
| "grad_norm": 1.3279340267181396, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 0.5904, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.1024, | |
| "grad_norm": 1.172986388206482, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.5735, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.1056, | |
| "grad_norm": 1.1812784671783447, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 0.6204, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.1088, | |
| "grad_norm": 1.3767175674438477, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 0.5828, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.112, | |
| "grad_norm": 1.0632436275482178, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 0.57, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.1152, | |
| "grad_norm": 0.929205596446991, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 0.5006, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.1184, | |
| "grad_norm": 1.3007352352142334, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 0.7047, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.1216, | |
| "grad_norm": 1.4487941265106201, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.7684, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.1248, | |
| "grad_norm": 1.5427775382995605, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 0.5627, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.128, | |
| "grad_norm": 1.1064578294754028, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 0.548, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.1312, | |
| "grad_norm": 1.229816198348999, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 0.5352, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.1344, | |
| "grad_norm": 1.032274842262268, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 0.5009, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.1376, | |
| "grad_norm": 1.0685501098632812, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 0.5532, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.1408, | |
| "grad_norm": 1.0419175624847412, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.5462, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.144, | |
| "grad_norm": 0.9846985936164856, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 0.4817, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.1472, | |
| "grad_norm": 0.847055971622467, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 0.5303, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.1504, | |
| "grad_norm": 1.1482884883880615, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 0.6073, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.1536, | |
| "grad_norm": 1.1206740140914917, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 0.5682, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.1568, | |
| "grad_norm": 1.4303394556045532, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 0.6277, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "grad_norm": 1.308823823928833, | |
| "learning_rate": 0.0, | |
| "loss": 0.5633, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "eval_loss": 0.5172708034515381, | |
| "eval_runtime": 52.8099, | |
| "eval_samples_per_second": 39.879, | |
| "eval_steps_per_second": 4.999, | |
| "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": 5.305284264198144e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |