| { | |
| "best_metric": 2.353839635848999, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.026242414302115796, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0005248482860423159, | |
| "grad_norm": 0.831413209438324, | |
| "learning_rate": 5e-05, | |
| "loss": 2.731, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0005248482860423159, | |
| "eval_loss": 3.088779926300049, | |
| "eval_runtime": 365.9787, | |
| "eval_samples_per_second": 35.073, | |
| "eval_steps_per_second": 4.386, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0010496965720846318, | |
| "grad_norm": 0.9228999018669128, | |
| "learning_rate": 0.0001, | |
| "loss": 2.8181, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0015745448581269477, | |
| "grad_norm": 0.9139898419380188, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 2.7975, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0020993931441692635, | |
| "grad_norm": 0.6556994318962097, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 2.727, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0026242414302115793, | |
| "grad_norm": 0.7705853581428528, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 2.6088, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0031490897162538955, | |
| "grad_norm": 0.8731432557106018, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 2.7356, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0036739380022962113, | |
| "grad_norm": 0.7079653143882751, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 2.5427, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.004198786288338527, | |
| "grad_norm": 0.6633538007736206, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 2.5191, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.004723634574380843, | |
| "grad_norm": 0.5277618169784546, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 2.532, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0052484828604231586, | |
| "grad_norm": 0.6638272404670715, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 2.5514, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.005773331146465475, | |
| "grad_norm": 0.5617047548294067, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 2.5486, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.006298179432507791, | |
| "grad_norm": 0.566726565361023, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 2.5763, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.006823027718550106, | |
| "grad_norm": 0.6018803715705872, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 2.483, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0073478760045924225, | |
| "grad_norm": 0.5189393758773804, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 2.4624, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.007872724290634738, | |
| "grad_norm": 0.37369871139526367, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 2.4686, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.008397572576677054, | |
| "grad_norm": 0.37240904569625854, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 2.4119, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.00892242086271937, | |
| "grad_norm": 0.41036102175712585, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 2.4088, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.009447269148761686, | |
| "grad_norm": 0.399316668510437, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 2.4306, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.009972117434804003, | |
| "grad_norm": 0.37074264883995056, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 2.4352, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.010496965720846317, | |
| "grad_norm": 0.40131875872612, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 2.3428, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.011021814006888633, | |
| "grad_norm": 0.3649172782897949, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 2.4041, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.01154666229293095, | |
| "grad_norm": 0.4035312831401825, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 2.4775, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.012071510578973266, | |
| "grad_norm": 0.47777652740478516, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 2.4441, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.012596358865015582, | |
| "grad_norm": 0.4832243025302887, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 2.5476, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.013121207151057898, | |
| "grad_norm": 0.7023970484733582, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 2.6073, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.013121207151057898, | |
| "eval_loss": 2.399475336074829, | |
| "eval_runtime": 365.9955, | |
| "eval_samples_per_second": 35.071, | |
| "eval_steps_per_second": 4.385, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.013646055437100213, | |
| "grad_norm": 0.433169960975647, | |
| "learning_rate": 5e-05, | |
| "loss": 2.3497, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.014170903723142529, | |
| "grad_norm": 0.44894787669181824, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 2.3805, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.014695752009184845, | |
| "grad_norm": 0.48380163311958313, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 2.4482, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.015220600295227161, | |
| "grad_norm": 0.41069453954696655, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 2.424, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.015745448581269476, | |
| "grad_norm": 0.3481389582157135, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 2.3664, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.016270296867311792, | |
| "grad_norm": 0.3449362814426422, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 2.2724, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.016795145153354108, | |
| "grad_norm": 0.3418646454811096, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 2.3587, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.017319993439396424, | |
| "grad_norm": 0.4137051999568939, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 2.2393, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.01784484172543874, | |
| "grad_norm": 0.3769303560256958, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 2.4014, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.018369690011481057, | |
| "grad_norm": 0.44172248244285583, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 2.2937, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.018894538297523373, | |
| "grad_norm": 0.46419256925582886, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 2.4315, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.01941938658356569, | |
| "grad_norm": 0.6354751586914062, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 2.5355, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.019944234869608005, | |
| "grad_norm": 0.3062434196472168, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 2.4477, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.02046908315565032, | |
| "grad_norm": 0.29478734731674194, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 2.3797, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.020993931441692634, | |
| "grad_norm": 0.27740278840065, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 2.2876, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.02151877972773495, | |
| "grad_norm": 0.28595972061157227, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 2.3316, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.022043628013777267, | |
| "grad_norm": 0.36039939522743225, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 2.3168, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.022568476299819583, | |
| "grad_norm": 0.2989155650138855, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 2.3838, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.0230933245858619, | |
| "grad_norm": 0.32794296741485596, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 2.3061, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.023618172871904215, | |
| "grad_norm": 0.34658685326576233, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 2.227, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.02414302115794653, | |
| "grad_norm": 0.37640607357025146, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 2.2494, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.024667869443988848, | |
| "grad_norm": 0.3610791265964508, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 2.3854, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.025192717730031164, | |
| "grad_norm": 0.39148759841918945, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 2.403, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.02571756601607348, | |
| "grad_norm": 0.4699634313583374, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 2.3342, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.026242414302115796, | |
| "grad_norm": 0.7783499360084534, | |
| "learning_rate": 0.0, | |
| "loss": 2.4725, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.026242414302115796, | |
| "eval_loss": 2.353839635848999, | |
| "eval_runtime": 366.0989, | |
| "eval_samples_per_second": 35.062, | |
| "eval_steps_per_second": 4.384, | |
| "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": 5.969948642440643e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |