| { | |
| "best_metric": 0.6839619874954224, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 2.4242424242424243, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.048484848484848485, | |
| "grad_norm": 1.6512070894241333, | |
| "learning_rate": 5e-05, | |
| "loss": 1.3474, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.048484848484848485, | |
| "eval_loss": 1.8917512893676758, | |
| "eval_runtime": 3.3225, | |
| "eval_samples_per_second": 41.836, | |
| "eval_steps_per_second": 5.418, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.09696969696969697, | |
| "grad_norm": 2.2326605319976807, | |
| "learning_rate": 0.0001, | |
| "loss": 1.687, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.14545454545454545, | |
| "grad_norm": 2.798654079437256, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 1.8097, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.19393939393939394, | |
| "grad_norm": 2.2003002166748047, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 1.7174, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.24242424242424243, | |
| "grad_norm": 2.369185447692871, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 1.6609, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.2909090909090909, | |
| "grad_norm": 1.5308661460876465, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 0.9369, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.3393939393939394, | |
| "grad_norm": 2.308574914932251, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 1.1685, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.3878787878787879, | |
| "grad_norm": 1.9228012561798096, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 1.0444, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.43636363636363634, | |
| "grad_norm": 1.4574872255325317, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 1.129, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.48484848484848486, | |
| "grad_norm": 1.4358528852462769, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 1.0859, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.5333333333333333, | |
| "grad_norm": 0.6643686294555664, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 0.7866, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.5818181818181818, | |
| "grad_norm": 0.7521995902061462, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 0.8776, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.6303030303030303, | |
| "grad_norm": 0.7262008190155029, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 0.878, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.6787878787878788, | |
| "grad_norm": 0.824934184551239, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.9436, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.7272727272727273, | |
| "grad_norm": 1.0625873804092407, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 1.0623, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.7757575757575758, | |
| "grad_norm": 0.46969833970069885, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 0.6119, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.8242424242424242, | |
| "grad_norm": 0.6232872605323792, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 0.8001, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.8727272727272727, | |
| "grad_norm": 0.7167707681655884, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.83, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.9212121212121213, | |
| "grad_norm": 0.6755483746528625, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 0.8227, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.9696969696969697, | |
| "grad_norm": 0.9275709986686707, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.8702, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.018181818181818, | |
| "grad_norm": 1.0646840333938599, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 1.0489, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 1.0666666666666667, | |
| "grad_norm": 0.801042377948761, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 0.6547, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 1.1151515151515152, | |
| "grad_norm": 0.7962119579315186, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 0.723, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 1.1636363636363636, | |
| "grad_norm": 0.8724921345710754, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 0.6937, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 1.2121212121212122, | |
| "grad_norm": 1.1883344650268555, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 0.7744, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.2121212121212122, | |
| "eval_loss": 0.707122802734375, | |
| "eval_runtime": 3.3013, | |
| "eval_samples_per_second": 42.104, | |
| "eval_steps_per_second": 5.452, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.2606060606060607, | |
| "grad_norm": 0.8380623459815979, | |
| "learning_rate": 5e-05, | |
| "loss": 0.639, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 1.309090909090909, | |
| "grad_norm": 0.732282817363739, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 0.6241, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 1.3575757575757577, | |
| "grad_norm": 0.7353828549385071, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 0.6116, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 1.406060606060606, | |
| "grad_norm": 0.8748971819877625, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 0.6333, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 1.4545454545454546, | |
| "grad_norm": 1.0290173292160034, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 0.7567, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.503030303030303, | |
| "grad_norm": 0.7504650354385376, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 0.641, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 1.5515151515151515, | |
| "grad_norm": 0.6707954406738281, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.5967, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "grad_norm": 0.8035198450088501, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 0.6397, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 1.6484848484848484, | |
| "grad_norm": 1.0750758647918701, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 0.7201, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 1.696969696969697, | |
| "grad_norm": 0.8901678919792175, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 0.6931, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 1.7454545454545456, | |
| "grad_norm": 0.808151364326477, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 0.6304, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 1.793939393939394, | |
| "grad_norm": 0.800571858882904, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 0.6342, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 1.8424242424242423, | |
| "grad_norm": 0.732184112071991, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.6579, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 1.8909090909090909, | |
| "grad_norm": 0.8361778855323792, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 0.6471, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 1.9393939393939394, | |
| "grad_norm": 1.0458678007125854, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 0.6809, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.9878787878787878, | |
| "grad_norm": 1.5578941106796265, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 0.7013, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 2.036363636363636, | |
| "grad_norm": 0.7779700756072998, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 0.6391, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 2.084848484848485, | |
| "grad_norm": 0.8941618204116821, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 0.5834, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 2.1333333333333333, | |
| "grad_norm": 0.9314845204353333, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.5874, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 2.1818181818181817, | |
| "grad_norm": 1.1137163639068604, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 0.6653, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 2.2303030303030305, | |
| "grad_norm": 1.257054090499878, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 0.5913, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 2.278787878787879, | |
| "grad_norm": 0.7937349677085876, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 0.4917, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 2.327272727272727, | |
| "grad_norm": 0.9872217774391174, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 0.6183, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 2.375757575757576, | |
| "grad_norm": 0.9808546304702759, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 0.5957, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 2.4242424242424243, | |
| "grad_norm": 1.1789116859436035, | |
| "learning_rate": 0.0, | |
| "loss": 0.6563, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 2.4242424242424243, | |
| "eval_loss": 0.6839619874954224, | |
| "eval_runtime": 3.3023, | |
| "eval_samples_per_second": 42.092, | |
| "eval_steps_per_second": 5.451, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "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": 2.654149397184512e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |