| { | |
| "best_metric": 3.4749794006347656, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.8676789587852495, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.01735357917570499, | |
| "grad_norm": 0.429781049489975, | |
| "learning_rate": 5e-05, | |
| "loss": 3.4937, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.01735357917570499, | |
| "eval_loss": 4.655571460723877, | |
| "eval_runtime": 7.0689, | |
| "eval_samples_per_second": 55.03, | |
| "eval_steps_per_second": 6.932, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.03470715835140998, | |
| "grad_norm": 0.7056689858436584, | |
| "learning_rate": 0.0001, | |
| "loss": 3.7561, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.052060737527114966, | |
| "grad_norm": 0.8674584031105042, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 3.8154, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.06941431670281996, | |
| "grad_norm": 1.0940744876861572, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 3.9442, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.08676789587852494, | |
| "grad_norm": 1.1139893531799316, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 3.9416, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.10412147505422993, | |
| "grad_norm": 0.9208441376686096, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 3.8629, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.12147505422993492, | |
| "grad_norm": 1.0207349061965942, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 3.9172, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.13882863340563992, | |
| "grad_norm": 0.9483520984649658, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 3.8406, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.1561822125813449, | |
| "grad_norm": 1.065035104751587, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 3.8246, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.1735357917570499, | |
| "grad_norm": 1.3419954776763916, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 3.8084, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.19088937093275488, | |
| "grad_norm": 1.5892398357391357, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 3.8009, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.20824295010845986, | |
| "grad_norm": 2.3767173290252686, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 3.9248, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.22559652928416485, | |
| "grad_norm": 2.0926482677459717, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 3.3449, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.24295010845986983, | |
| "grad_norm": 2.0223922729492188, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 3.62, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.2603036876355748, | |
| "grad_norm": 1.3903629779815674, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 3.5502, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.27765726681127983, | |
| "grad_norm": 0.8590835332870483, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 3.5537, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.2950108459869848, | |
| "grad_norm": 0.7551249265670776, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 3.6046, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.3123644251626898, | |
| "grad_norm": 0.8206058740615845, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 3.6325, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.3297180043383948, | |
| "grad_norm": 0.9209147691726685, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 3.6654, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.3470715835140998, | |
| "grad_norm": 1.0374475717544556, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 3.5197, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.3644251626898048, | |
| "grad_norm": 1.0554020404815674, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 3.6211, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.38177874186550975, | |
| "grad_norm": 1.1623866558074951, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 3.6616, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.39913232104121477, | |
| "grad_norm": 1.513929009437561, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 3.7618, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.4164859002169197, | |
| "grad_norm": 1.8778696060180664, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 3.7603, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.43383947939262474, | |
| "grad_norm": 3.826092004776001, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 3.856, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.43383947939262474, | |
| "eval_loss": 3.54858136177063, | |
| "eval_runtime": 7.062, | |
| "eval_samples_per_second": 55.084, | |
| "eval_steps_per_second": 6.939, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.4511930585683297, | |
| "grad_norm": 0.7839721441268921, | |
| "learning_rate": 5e-05, | |
| "loss": 3.274, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.4685466377440347, | |
| "grad_norm": 1.0139122009277344, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 3.4114, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.48590021691973967, | |
| "grad_norm": 1.1178371906280518, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 3.5445, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.5032537960954447, | |
| "grad_norm": 1.1927067041397095, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 3.5377, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.5206073752711496, | |
| "grad_norm": 1.1140047311782837, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 3.5414, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.5379609544468547, | |
| "grad_norm": 0.9414491653442383, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 3.4979, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.5553145336225597, | |
| "grad_norm": 0.9263672232627869, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 3.4948, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.5726681127982647, | |
| "grad_norm": 0.94609534740448, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 3.5357, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.5900216919739696, | |
| "grad_norm": 1.0813770294189453, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 3.5867, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.6073752711496746, | |
| "grad_norm": 1.2149401903152466, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 3.5374, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.6247288503253796, | |
| "grad_norm": 1.7587355375289917, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 3.7121, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.6420824295010846, | |
| "grad_norm": 2.5012454986572266, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 3.5036, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.6594360086767896, | |
| "grad_norm": 0.4415558874607086, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 3.2048, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.6767895878524945, | |
| "grad_norm": 0.4357939064502716, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 3.3426, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.6941431670281996, | |
| "grad_norm": 0.4549647867679596, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 3.3791, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.7114967462039046, | |
| "grad_norm": 0.5158963203430176, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 3.356, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.7288503253796096, | |
| "grad_norm": 0.5373722910881042, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 3.4483, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.7462039045553145, | |
| "grad_norm": 0.6123077273368835, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 3.411, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.7635574837310195, | |
| "grad_norm": 0.7094330191612244, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 3.4948, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.7809110629067245, | |
| "grad_norm": 0.7887084484100342, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 3.4448, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.7982646420824295, | |
| "grad_norm": 1.0100810527801514, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 3.4833, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.8156182212581344, | |
| "grad_norm": 1.1634279489517212, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 3.5579, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.8329718004338394, | |
| "grad_norm": 1.4692707061767578, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 3.4763, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.8503253796095445, | |
| "grad_norm": 2.0087335109710693, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 3.6189, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.8676789587852495, | |
| "grad_norm": 3.6939210891723633, | |
| "learning_rate": 0.0, | |
| "loss": 3.8107, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.8676789587852495, | |
| "eval_loss": 3.4749794006347656, | |
| "eval_runtime": 7.061, | |
| "eval_samples_per_second": 55.091, | |
| "eval_steps_per_second": 6.94, | |
| "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": 2.254995537788928e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |