{ "best_metric": 1.7409106492996216, "best_model_checkpoint": "miner_id_24/checkpoint-50", "epoch": 0.05378874470517044, "eval_steps": 25, "global_step": 50, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0010757748941034088, "grad_norm": 2.889035224914551, "learning_rate": 5e-05, "loss": 1.7307, "step": 1 }, { "epoch": 0.0010757748941034088, "eval_loss": 2.065730094909668, "eval_runtime": 186.3032, "eval_samples_per_second": 33.617, "eval_steps_per_second": 4.203, "step": 1 }, { "epoch": 0.0021515497882068175, "grad_norm": 2.8928565979003906, "learning_rate": 0.0001, "loss": 1.8653, "step": 2 }, { "epoch": 0.0032273246823102267, "grad_norm": 1.6839524507522583, "learning_rate": 9.989294616193017e-05, "loss": 1.756, "step": 3 }, { "epoch": 0.004303099576413635, "grad_norm": 0.8242851495742798, "learning_rate": 9.957224306869053e-05, "loss": 1.7457, "step": 4 }, { "epoch": 0.005378874470517044, "grad_norm": 1.0334848165512085, "learning_rate": 9.903926402016153e-05, "loss": 1.7532, "step": 5 }, { "epoch": 0.006454649364620453, "grad_norm": 0.7117134928703308, "learning_rate": 9.829629131445342e-05, "loss": 1.7827, "step": 6 }, { "epoch": 0.007530424258723862, "grad_norm": 0.7202480435371399, "learning_rate": 9.73465064747553e-05, "loss": 1.8289, "step": 7 }, { "epoch": 0.00860619915282727, "grad_norm": 0.6732454299926758, "learning_rate": 9.619397662556435e-05, "loss": 1.7357, "step": 8 }, { "epoch": 0.00968197404693068, "grad_norm": 0.6462610960006714, "learning_rate": 9.484363707663442e-05, "loss": 1.7847, "step": 9 }, { "epoch": 0.010757748941034088, "grad_norm": 0.7184572815895081, "learning_rate": 9.330127018922194e-05, "loss": 1.8445, "step": 10 }, { "epoch": 0.011833523835137498, "grad_norm": 0.7928162813186646, "learning_rate": 9.157348061512727e-05, "loss": 1.8327, "step": 11 }, { "epoch": 0.012909298729240907, "grad_norm": 0.9331445693969727, "learning_rate": 8.966766701456177e-05, "loss": 2.0023, "step": 12 }, { "epoch": 0.013985073623344316, "grad_norm": 1.8583245277404785, "learning_rate": 8.759199037394887e-05, "loss": 1.6557, "step": 13 }, { "epoch": 0.015060848517447724, "grad_norm": 1.4030020236968994, "learning_rate": 8.535533905932738e-05, "loss": 1.6399, "step": 14 }, { "epoch": 0.016136623411551133, "grad_norm": 1.2228798866271973, "learning_rate": 8.296729075500344e-05, "loss": 1.637, "step": 15 }, { "epoch": 0.01721239830565454, "grad_norm": 0.8515083193778992, "learning_rate": 8.043807145043604e-05, "loss": 1.6325, "step": 16 }, { "epoch": 0.01828817319975795, "grad_norm": 0.6020737290382385, "learning_rate": 7.777851165098012e-05, "loss": 1.6861, "step": 17 }, { "epoch": 0.01936394809386136, "grad_norm": 0.658804714679718, "learning_rate": 7.500000000000001e-05, "loss": 1.7261, "step": 18 }, { "epoch": 0.02043972298796477, "grad_norm": 0.6308284997940063, "learning_rate": 7.211443451095007e-05, "loss": 1.7423, "step": 19 }, { "epoch": 0.021515497882068177, "grad_norm": 0.6279967427253723, "learning_rate": 6.91341716182545e-05, "loss": 1.7781, "step": 20 }, { "epoch": 0.022591272776171584, "grad_norm": 0.6446429491043091, "learning_rate": 6.607197326515808e-05, "loss": 1.747, "step": 21 }, { "epoch": 0.023667047670274995, "grad_norm": 0.6265982985496521, "learning_rate": 6.294095225512603e-05, "loss": 1.8178, "step": 22 }, { "epoch": 0.024742822564378403, "grad_norm": 0.695231556892395, "learning_rate": 5.9754516100806423e-05, "loss": 1.7954, "step": 23 }, { "epoch": 0.025818597458481814, "grad_norm": 0.7961277365684509, "learning_rate": 5.6526309611002594e-05, "loss": 1.9499, "step": 24 }, { "epoch": 0.02689437235258522, "grad_norm": 1.026402235031128, "learning_rate": 5.327015646150716e-05, "loss": 2.1511, "step": 25 }, { "epoch": 0.02689437235258522, "eval_loss": 1.753453016281128, "eval_runtime": 186.4029, "eval_samples_per_second": 33.599, "eval_steps_per_second": 4.201, "step": 25 }, { "epoch": 0.027970147246688632, "grad_norm": 0.6362124681472778, "learning_rate": 5e-05, "loss": 1.5936, "step": 26 }, { "epoch": 0.02904592214079204, "grad_norm": 0.5519288182258606, "learning_rate": 4.6729843538492847e-05, "loss": 1.5623, "step": 27 }, { "epoch": 0.030121697034895447, "grad_norm": 0.4948122501373291, "learning_rate": 4.347369038899744e-05, "loss": 1.6165, "step": 28 }, { "epoch": 0.031197471928998858, "grad_norm": 0.5037927627563477, "learning_rate": 4.0245483899193595e-05, "loss": 1.6709, "step": 29 }, { "epoch": 0.032273246823102265, "grad_norm": 0.5008567571640015, "learning_rate": 3.705904774487396e-05, "loss": 1.7043, "step": 30 }, { "epoch": 0.033349021717205676, "grad_norm": 0.5066686272621155, "learning_rate": 3.392802673484193e-05, "loss": 1.6957, "step": 31 }, { "epoch": 0.03442479661130908, "grad_norm": 0.5251875519752502, "learning_rate": 3.086582838174551e-05, "loss": 1.7502, "step": 32 }, { "epoch": 0.03550057150541249, "grad_norm": 0.5396082401275635, "learning_rate": 2.7885565489049946e-05, "loss": 1.7408, "step": 33 }, { "epoch": 0.0365763463995159, "grad_norm": 0.5625227689743042, "learning_rate": 2.500000000000001e-05, "loss": 1.7587, "step": 34 }, { "epoch": 0.03765212129361931, "grad_norm": 0.5840663909912109, "learning_rate": 2.2221488349019903e-05, "loss": 1.8015, "step": 35 }, { "epoch": 0.03872789618772272, "grad_norm": 0.6661264300346375, "learning_rate": 1.9561928549563968e-05, "loss": 1.8426, "step": 36 }, { "epoch": 0.03980367108182613, "grad_norm": 0.8346494436264038, "learning_rate": 1.703270924499656e-05, "loss": 1.9472, "step": 37 }, { "epoch": 0.04087944597592954, "grad_norm": 0.6206389665603638, "learning_rate": 1.4644660940672627e-05, "loss": 1.6175, "step": 38 }, { "epoch": 0.04195522087003294, "grad_norm": 0.5432288646697998, "learning_rate": 1.2408009626051137e-05, "loss": 1.6168, "step": 39 }, { "epoch": 0.043030995764136354, "grad_norm": 0.501873254776001, "learning_rate": 1.0332332985438248e-05, "loss": 1.5663, "step": 40 }, { "epoch": 0.044106770658239765, "grad_norm": 0.4983377158641815, "learning_rate": 8.426519384872733e-06, "loss": 1.6572, "step": 41 }, { "epoch": 0.04518254555234317, "grad_norm": 0.4926607608795166, "learning_rate": 6.698729810778065e-06, "loss": 1.7136, "step": 42 }, { "epoch": 0.04625832044644658, "grad_norm": 0.4842887222766876, "learning_rate": 5.156362923365588e-06, "loss": 1.6859, "step": 43 }, { "epoch": 0.04733409534054999, "grad_norm": 0.4948004484176636, "learning_rate": 3.8060233744356633e-06, "loss": 1.7795, "step": 44 }, { "epoch": 0.0484098702346534, "grad_norm": 0.5172557830810547, "learning_rate": 2.653493525244721e-06, "loss": 1.6963, "step": 45 }, { "epoch": 0.049485645128756806, "grad_norm": 0.5146644711494446, "learning_rate": 1.70370868554659e-06, "loss": 1.7358, "step": 46 }, { "epoch": 0.050561420022860216, "grad_norm": 0.5665210485458374, "learning_rate": 9.607359798384785e-07, "loss": 1.7453, "step": 47 }, { "epoch": 0.05163719491696363, "grad_norm": 0.6140392422676086, "learning_rate": 4.277569313094809e-07, "loss": 1.8031, "step": 48 }, { "epoch": 0.05271296981106703, "grad_norm": 0.7129289507865906, "learning_rate": 1.0705383806982606e-07, "loss": 1.9231, "step": 49 }, { "epoch": 0.05378874470517044, "grad_norm": 1.0026451349258423, "learning_rate": 0.0, "loss": 2.1672, "step": 50 }, { "epoch": 0.05378874470517044, "eval_loss": 1.7409106492996216, "eval_runtime": 186.33, "eval_samples_per_second": 33.612, "eval_steps_per_second": 4.202, "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": 5.658024559509504e+17, "train_batch_size": 2, "trial_name": null, "trial_params": null }