| { | |
| "best_metric": NaN, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 1.9047619047619047, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0380952380952381, | |
| "grad_norm": 0.9098623394966125, | |
| "learning_rate": 5e-05, | |
| "loss": 2.6337, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0380952380952381, | |
| "eval_loss": NaN, | |
| "eval_runtime": 12.4545, | |
| "eval_samples_per_second": 14.212, | |
| "eval_steps_per_second": 1.847, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0761904761904762, | |
| "grad_norm": 1.0923771858215332, | |
| "learning_rate": 0.0001, | |
| "loss": 2.5771, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.11428571428571428, | |
| "grad_norm": 2.1162688732147217, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 4.3459, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.1523809523809524, | |
| "grad_norm": 1.5628211498260498, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 3.1138, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.19047619047619047, | |
| "grad_norm": 2.7540507316589355, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 2.9157, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.22857142857142856, | |
| "grad_norm": 2.937060594558716, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 2.6642, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.26666666666666666, | |
| "grad_norm": 3.5528767108917236, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 2.4905, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.3047619047619048, | |
| "grad_norm": 2.8882346153259277, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 2.2952, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.34285714285714286, | |
| "grad_norm": 1.6182169914245605, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 2.438, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.38095238095238093, | |
| "grad_norm": 1.3022983074188232, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 2.3042, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.41904761904761906, | |
| "grad_norm": 1.3987462520599365, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 2.1143, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.45714285714285713, | |
| "grad_norm": 1.4563645124435425, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 1.9665, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.49523809523809526, | |
| "grad_norm": 2.0373780727386475, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 1.7774, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.5333333333333333, | |
| "grad_norm": 1.0493792295455933, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 2.2941, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.5714285714285714, | |
| "grad_norm": 0.95171719789505, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 2.0555, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.6095238095238096, | |
| "grad_norm": 1.5632261037826538, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 1.9817, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.6476190476190476, | |
| "grad_norm": 1.0696916580200195, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 2.2164, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.6857142857142857, | |
| "grad_norm": 1.2561990022659302, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 1.6283, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.7238095238095238, | |
| "grad_norm": 1.7892498970031738, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 1.4975, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.7619047619047619, | |
| "grad_norm": 0.8777750730514526, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 1.961, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "grad_norm": 0.9096943736076355, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 2.1097, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.8380952380952381, | |
| "grad_norm": 1.3310202360153198, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 1.7139, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.8761904761904762, | |
| "grad_norm": 1.3908442258834839, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 2.0266, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.9142857142857143, | |
| "grad_norm": 1.0093380212783813, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 1.712, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.9523809523809523, | |
| "grad_norm": 1.205411434173584, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 1.4849, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.9523809523809523, | |
| "eval_loss": NaN, | |
| "eval_runtime": 12.4402, | |
| "eval_samples_per_second": 14.228, | |
| "eval_steps_per_second": 1.849, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.9904761904761905, | |
| "grad_norm": 1.7644603252410889, | |
| "learning_rate": 5e-05, | |
| "loss": 1.3783, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 1.0285714285714285, | |
| "grad_norm": 1.728111982345581, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 3.1437, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 1.0666666666666667, | |
| "grad_norm": 1.1753063201904297, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 1.9938, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 1.1047619047619048, | |
| "grad_norm": 1.6626451015472412, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 1.4311, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 1.1428571428571428, | |
| "grad_norm": 1.8298120498657227, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 1.8651, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.180952380952381, | |
| "grad_norm": 1.8219621181488037, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 1.4195, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 1.2190476190476192, | |
| "grad_norm": 2.4925100803375244, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 1.4548, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 1.2571428571428571, | |
| "grad_norm": 1.085057020187378, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 1.1806, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 1.2952380952380953, | |
| "grad_norm": 1.118369698524475, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 2.3083, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 1.3333333333333333, | |
| "grad_norm": 1.8153469562530518, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 1.4447, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 1.3714285714285714, | |
| "grad_norm": 2.3695998191833496, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 1.3817, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 1.4095238095238094, | |
| "grad_norm": 1.7949069738388062, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 1.7265, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 1.4476190476190476, | |
| "grad_norm": 1.624284267425537, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 1.2413, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 1.4857142857142858, | |
| "grad_norm": 1.9687860012054443, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 1.0754, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 1.5238095238095237, | |
| "grad_norm": 1.0471829175949097, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 1.5677, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.561904761904762, | |
| "grad_norm": 1.2650785446166992, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 1.5782, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "grad_norm": 1.6667383909225464, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 1.3541, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 1.638095238095238, | |
| "grad_norm": 1.6385276317596436, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 1.7588, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 1.6761904761904762, | |
| "grad_norm": 1.7854325771331787, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 1.3247, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 1.7142857142857144, | |
| "grad_norm": 2.053854465484619, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 1.07, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 1.7523809523809524, | |
| "grad_norm": 0.8745402693748474, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 1.0016, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 1.7904761904761903, | |
| "grad_norm": 1.2501132488250732, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 2.2583, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 1.8285714285714287, | |
| "grad_norm": 1.4963077306747437, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 1.4846, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 1.8666666666666667, | |
| "grad_norm": 1.8609797954559326, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 1.594, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 1.9047619047619047, | |
| "grad_norm": 1.9615119695663452, | |
| "learning_rate": 0.0, | |
| "loss": 1.8321, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.9047619047619047, | |
| "eval_loss": NaN, | |
| "eval_runtime": 12.43, | |
| "eval_samples_per_second": 14.24, | |
| "eval_steps_per_second": 1.85, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "save_steps": 25, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 1, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 1 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 5.968083617316864e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |