| { | |
| "best_metric": 0.5326569676399231, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.9259259259259259, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.018518518518518517, | |
| "grad_norm": 0.5474225282669067, | |
| "learning_rate": 5e-05, | |
| "loss": 1.097, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.018518518518518517, | |
| "eval_loss": 1.6396740674972534, | |
| "eval_runtime": 4.0983, | |
| "eval_samples_per_second": 88.817, | |
| "eval_steps_per_second": 11.224, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.037037037037037035, | |
| "grad_norm": 0.6814149618148804, | |
| "learning_rate": 0.0001, | |
| "loss": 1.2547, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.05555555555555555, | |
| "grad_norm": 0.7163407802581787, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 1.2502, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.07407407407407407, | |
| "grad_norm": 0.6404975056648254, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 1.2215, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.09259259259259259, | |
| "grad_norm": 0.590765118598938, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 1.1955, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.1111111111111111, | |
| "grad_norm": 0.5880994200706482, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 1.124, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.12962962962962962, | |
| "grad_norm": 0.5782201886177063, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 1.086, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.14814814814814814, | |
| "grad_norm": 0.5449230074882507, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 1.06, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.16666666666666666, | |
| "grad_norm": 0.5347405076026917, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 0.9701, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.18518518518518517, | |
| "grad_norm": 0.5817571878433228, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 0.9558, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.2037037037037037, | |
| "grad_norm": 0.543773889541626, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 0.9536, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.2222222222222222, | |
| "grad_norm": 0.5493637919425964, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 0.9326, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.24074074074074073, | |
| "grad_norm": 0.24274133145809174, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 0.6924, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.25925925925925924, | |
| "grad_norm": 0.2198300063610077, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.6801, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.2777777777777778, | |
| "grad_norm": 0.21759666502475739, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 0.6965, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.2962962962962963, | |
| "grad_norm": 0.23276081681251526, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 0.6476, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.3148148148148148, | |
| "grad_norm": 0.24803251028060913, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 0.6523, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.3333333333333333, | |
| "grad_norm": 0.24354369938373566, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.631, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.35185185185185186, | |
| "grad_norm": 0.24335706233978271, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 0.6601, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.37037037037037035, | |
| "grad_norm": 0.2604289948940277, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.6603, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.3888888888888889, | |
| "grad_norm": 0.26426175236701965, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 0.6111, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.4074074074074074, | |
| "grad_norm": 0.2667665183544159, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 0.5973, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.42592592592592593, | |
| "grad_norm": 0.28260642290115356, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 0.5798, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.4444444444444444, | |
| "grad_norm": 0.3108558654785156, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 0.6035, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.46296296296296297, | |
| "grad_norm": 0.3848308324813843, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 0.6114, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.46296296296296297, | |
| "eval_loss": 0.575002133846283, | |
| "eval_runtime": 4.0913, | |
| "eval_samples_per_second": 88.969, | |
| "eval_steps_per_second": 11.243, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.48148148148148145, | |
| "grad_norm": 0.16580988466739655, | |
| "learning_rate": 5e-05, | |
| "loss": 0.5851, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "grad_norm": 0.16641582548618317, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 0.5467, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.5185185185185185, | |
| "grad_norm": 0.17972533404827118, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 0.5729, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.5370370370370371, | |
| "grad_norm": 0.19136375188827515, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 0.5963, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.5555555555555556, | |
| "grad_norm": 0.15340934693813324, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 0.5358, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.5740740740740741, | |
| "grad_norm": 0.17189480364322662, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 0.5382, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.5925925925925926, | |
| "grad_norm": 0.17463701963424683, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.5996, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.6111111111111112, | |
| "grad_norm": 0.1664072871208191, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 0.5222, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.6296296296296297, | |
| "grad_norm": 0.18913966417312622, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 0.5237, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.6481481481481481, | |
| "grad_norm": 0.19895462691783905, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 0.556, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.6666666666666666, | |
| "grad_norm": 0.20067861676216125, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 0.5157, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.6851851851851852, | |
| "grad_norm": 0.2393798828125, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 0.5419, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.7037037037037037, | |
| "grad_norm": 0.15917517244815826, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.515, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.7222222222222222, | |
| "grad_norm": 0.1433321088552475, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 0.521, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.7407407407407407, | |
| "grad_norm": 0.14987705647945404, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 0.5404, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.7592592592592593, | |
| "grad_norm": 0.14243093132972717, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 0.5115, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.7777777777777778, | |
| "grad_norm": 0.15107634663581848, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 0.557, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.7962962962962963, | |
| "grad_norm": 0.13823860883712769, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 0.4903, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.8148148148148148, | |
| "grad_norm": 0.1534203439950943, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.5418, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.8333333333333334, | |
| "grad_norm": 0.1534622311592102, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 0.5271, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.8518518518518519, | |
| "grad_norm": 0.16714034974575043, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 0.4919, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.8703703703703703, | |
| "grad_norm": 0.17615364491939545, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 0.5232, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.8888888888888888, | |
| "grad_norm": 0.18620406091213226, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 0.5164, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.9074074074074074, | |
| "grad_norm": 0.20223726332187653, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 0.5207, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.9259259259259259, | |
| "grad_norm": 0.3112916648387909, | |
| "learning_rate": 0.0, | |
| "loss": 0.4836, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.9259259259259259, | |
| "eval_loss": 0.5326569676399231, | |
| "eval_runtime": 4.091, | |
| "eval_samples_per_second": 88.977, | |
| "eval_steps_per_second": 11.244, | |
| "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 | |
| } | |