| { | |
| "best_metric": 0.09009819477796555, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 2.0556962025316454, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.04050632911392405, | |
| "grad_norm": 4.336637496948242, | |
| "learning_rate": 5e-05, | |
| "loss": 2.9946, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.04050632911392405, | |
| "eval_loss": 3.5646121501922607, | |
| "eval_runtime": 4.9544, | |
| "eval_samples_per_second": 33.708, | |
| "eval_steps_per_second": 4.239, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0810126582278481, | |
| "grad_norm": 4.202060222625732, | |
| "learning_rate": 0.0001, | |
| "loss": 2.9095, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.12151898734177215, | |
| "grad_norm": 4.256785869598389, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 2.7783, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.1620253164556962, | |
| "grad_norm": 4.0002264976501465, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 2.2739, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.20253164556962025, | |
| "grad_norm": 4.200502872467041, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 2.2335, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.2430379746835443, | |
| "grad_norm": 5.617342472076416, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 2.4807, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.28354430379746837, | |
| "grad_norm": 4.100435733795166, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 0.8623, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.3240506329113924, | |
| "grad_norm": 4.162398338317871, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.4838, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.36455696202531646, | |
| "grad_norm": 1.463178277015686, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 0.2443, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.4050632911392405, | |
| "grad_norm": 1.8628356456756592, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 0.1866, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.44556962025316454, | |
| "grad_norm": 1.7597520351409912, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 0.1913, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.4860759493670886, | |
| "grad_norm": 1.9096077680587769, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 0.1731, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.5265822784810127, | |
| "grad_norm": 0.9818510413169861, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 0.0955, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.5670886075949367, | |
| "grad_norm": 0.8177430629730225, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.0905, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.6075949367088608, | |
| "grad_norm": 1.386397123336792, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 0.1895, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.6481012658227848, | |
| "grad_norm": 1.5397404432296753, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 0.1229, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.6886075949367089, | |
| "grad_norm": 0.8175281286239624, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 0.0915, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.7291139240506329, | |
| "grad_norm": 0.6687910556793213, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.0782, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.769620253164557, | |
| "grad_norm": 0.6697981953620911, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 0.1068, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.810126582278481, | |
| "grad_norm": 0.513208270072937, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.0695, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.850632911392405, | |
| "grad_norm": 0.5951077342033386, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 0.0975, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.8911392405063291, | |
| "grad_norm": 0.6136615872383118, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 0.1191, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.9316455696202531, | |
| "grad_norm": 0.7782850861549377, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 0.1073, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.9721518987341772, | |
| "grad_norm": 0.8574443459510803, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 0.0402, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 1.0278481012658227, | |
| "grad_norm": 0.4839467704296112, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 0.0391, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.0278481012658227, | |
| "eval_loss": 0.09560767561197281, | |
| "eval_runtime": 4.9249, | |
| "eval_samples_per_second": 33.909, | |
| "eval_steps_per_second": 4.264, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.0683544303797468, | |
| "grad_norm": 0.20028449594974518, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0578, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 1.1088607594936708, | |
| "grad_norm": 0.17910338938236237, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 0.0266, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 1.1493670886075948, | |
| "grad_norm": 0.6377457976341248, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 0.0856, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 1.189873417721519, | |
| "grad_norm": 0.6066492795944214, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 0.0464, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 1.230379746835443, | |
| "grad_norm": 0.09580016881227493, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 0.0327, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.2708860759493672, | |
| "grad_norm": 0.6638514995574951, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 0.0382, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 1.311392405063291, | |
| "grad_norm": 0.2734617292881012, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.0544, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 1.3518987341772153, | |
| "grad_norm": 0.5110018253326416, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 0.1043, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 1.3924050632911391, | |
| "grad_norm": 0.5602982640266418, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 0.0719, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 1.4329113924050634, | |
| "grad_norm": 0.3711053431034088, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 0.0676, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 1.4734177215189874, | |
| "grad_norm": 0.16281400620937347, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 0.0146, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 1.5139240506329115, | |
| "grad_norm": 0.15146973729133606, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 0.0525, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 1.5544303797468353, | |
| "grad_norm": 0.46896079182624817, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.0544, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 1.5949367088607596, | |
| "grad_norm": 0.8656461834907532, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 0.0566, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 1.6354430379746834, | |
| "grad_norm": 0.6313591003417969, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 0.084, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.6759493670886076, | |
| "grad_norm": 1.0002316236495972, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 0.1236, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 1.7164556962025317, | |
| "grad_norm": 0.25096988677978516, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 0.0603, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 1.7569620253164557, | |
| "grad_norm": 0.6598709225654602, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 0.0335, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 1.7974683544303798, | |
| "grad_norm": 0.2084610015153885, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.0304, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 1.8379746835443038, | |
| "grad_norm": 0.3605667054653168, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 0.0538, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 1.8784810126582279, | |
| "grad_norm": 0.5047392249107361, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 0.0532, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 1.918987341772152, | |
| "grad_norm": 0.1747433990240097, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 0.0328, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 1.959493670886076, | |
| "grad_norm": 0.3657343089580536, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 0.065, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 2.0151898734177216, | |
| "grad_norm": 0.3927527666091919, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 0.0802, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 2.0556962025316454, | |
| "grad_norm": 0.4265093505382538, | |
| "learning_rate": 0.0, | |
| "loss": 0.0281, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 2.0556962025316454, | |
| "eval_loss": 0.09009819477796555, | |
| "eval_runtime": 4.9245, | |
| "eval_samples_per_second": 33.912, | |
| "eval_steps_per_second": 4.264, | |
| "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": 5.32019209568256e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |