| { | |
| "best_metric": 0.39160192012786865, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.04747774480712166, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0009495548961424333, | |
| "grad_norm": 7.661884307861328, | |
| "learning_rate": 5e-05, | |
| "loss": 2.5959, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0009495548961424333, | |
| "eval_loss": 4.306151866912842, | |
| "eval_runtime": 93.0407, | |
| "eval_samples_per_second": 76.257, | |
| "eval_steps_per_second": 9.533, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0018991097922848666, | |
| "grad_norm": 11.511931419372559, | |
| "learning_rate": 0.0001, | |
| "loss": 3.3436, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0028486646884273, | |
| "grad_norm": 7.516351699829102, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 2.3697, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.003798219584569733, | |
| "grad_norm": 5.4108710289001465, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 1.585, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.004747774480712166, | |
| "grad_norm": 3.9081742763519287, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 1.0724, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0056973293768546, | |
| "grad_norm": 4.953296184539795, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 0.9248, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.006646884272997033, | |
| "grad_norm": 3.4243087768554688, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 0.7177, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.007596439169139466, | |
| "grad_norm": 1.8715609312057495, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.5938, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0085459940652819, | |
| "grad_norm": 2.0616214275360107, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 0.6257, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.009495548961424332, | |
| "grad_norm": 1.8348668813705444, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 0.5286, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.010445103857566765, | |
| "grad_norm": 1.3536250591278076, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 0.5025, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0113946587537092, | |
| "grad_norm": 1.6615864038467407, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 0.5754, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.012344213649851632, | |
| "grad_norm": 1.378383994102478, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 0.5091, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.013293768545994065, | |
| "grad_norm": 1.4611592292785645, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.5618, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.014243323442136498, | |
| "grad_norm": 1.462814211845398, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 0.6127, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.015192878338278933, | |
| "grad_norm": 1.3176627159118652, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 0.4622, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.016142433234421365, | |
| "grad_norm": 1.149091362953186, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 0.5356, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.0170919881305638, | |
| "grad_norm": 1.1545970439910889, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.5104, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.01804154302670623, | |
| "grad_norm": 1.013222098350525, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 0.3924, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.018991097922848664, | |
| "grad_norm": 1.1423275470733643, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.4742, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.019940652818991097, | |
| "grad_norm": 1.0759767293930054, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 0.4157, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.02089020771513353, | |
| "grad_norm": 1.0587694644927979, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 0.392, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.021839762611275966, | |
| "grad_norm": 1.3421058654785156, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 0.4272, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.0227893175074184, | |
| "grad_norm": 1.6769137382507324, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 0.4728, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.02373887240356083, | |
| "grad_norm": 1.447285771369934, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 0.4399, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.02373887240356083, | |
| "eval_loss": 0.41518697142601013, | |
| "eval_runtime": 93.1452, | |
| "eval_samples_per_second": 76.171, | |
| "eval_steps_per_second": 9.523, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.024688427299703265, | |
| "grad_norm": 1.7641550302505493, | |
| "learning_rate": 5e-05, | |
| "loss": 0.4681, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.025637982195845697, | |
| "grad_norm": 1.335742473602295, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 0.4068, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.02658753709198813, | |
| "grad_norm": 1.402836561203003, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 0.4425, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.027537091988130563, | |
| "grad_norm": 1.0987377166748047, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 0.4945, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.028486646884272996, | |
| "grad_norm": 1.0857986211776733, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 0.4374, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.02943620178041543, | |
| "grad_norm": 1.2346323728561401, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 0.4112, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.030385756676557865, | |
| "grad_norm": 1.0568417310714722, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.3237, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.031335311572700295, | |
| "grad_norm": 1.2580246925354004, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 0.447, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.03228486646884273, | |
| "grad_norm": 1.4497991800308228, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 0.4942, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.03323442136498516, | |
| "grad_norm": 1.3102707862854004, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 0.3935, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.0341839762611276, | |
| "grad_norm": 1.256971001625061, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 0.4037, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.03513353115727003, | |
| "grad_norm": 1.3087794780731201, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 0.4081, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.03608308605341246, | |
| "grad_norm": 0.9994477033615112, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.4166, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.0370326409495549, | |
| "grad_norm": 1.091837763786316, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 0.4421, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.03798219584569733, | |
| "grad_norm": 1.204852819442749, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 0.3832, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.038931750741839764, | |
| "grad_norm": 1.171751618385315, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 0.4178, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.039881305637982194, | |
| "grad_norm": 1.04241943359375, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 0.4405, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.04083086053412463, | |
| "grad_norm": 0.9827619194984436, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 0.4198, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.04178041543026706, | |
| "grad_norm": 1.0108426809310913, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.4326, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.042729970326409496, | |
| "grad_norm": 1.0313923358917236, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 0.3465, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.04367952522255193, | |
| "grad_norm": 1.1074979305267334, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 0.4653, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.04462908011869436, | |
| "grad_norm": 0.974529504776001, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 0.4359, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.0455786350148368, | |
| "grad_norm": 1.2183024883270264, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 0.3577, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.04652818991097923, | |
| "grad_norm": 1.121361494064331, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 0.4082, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.04747774480712166, | |
| "grad_norm": 1.1952590942382812, | |
| "learning_rate": 0.0, | |
| "loss": 0.4594, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.04747774480712166, | |
| "eval_loss": 0.39160192012786865, | |
| "eval_runtime": 93.198, | |
| "eval_samples_per_second": 76.128, | |
| "eval_steps_per_second": 9.517, | |
| "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": 1.589463780163584e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |