| { | |
| "best_metric": 1.3664671182632446, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 1.0101010101010102, | |
| "eval_steps": 50, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.020202020202020204, | |
| "grad_norm": 5.289388179779053, | |
| "learning_rate": 5e-06, | |
| "loss": 3.9043, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.020202020202020204, | |
| "eval_loss": 5.048096656799316, | |
| "eval_runtime": 4.2841, | |
| "eval_samples_per_second": 19.607, | |
| "eval_steps_per_second": 9.804, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.04040404040404041, | |
| "grad_norm": 6.221162796020508, | |
| "learning_rate": 1e-05, | |
| "loss": 4.4545, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.06060606060606061, | |
| "grad_norm": 6.830175876617432, | |
| "learning_rate": 1.5e-05, | |
| "loss": 4.4955, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.08080808080808081, | |
| "grad_norm": 7.195596694946289, | |
| "learning_rate": 2e-05, | |
| "loss": 4.5755, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.10101010101010101, | |
| "grad_norm": 6.808708667755127, | |
| "learning_rate": 2.5e-05, | |
| "loss": 4.6561, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.12121212121212122, | |
| "grad_norm": 7.063287258148193, | |
| "learning_rate": 3e-05, | |
| "loss": 4.7259, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.1414141414141414, | |
| "grad_norm": 7.591980934143066, | |
| "learning_rate": 3.5e-05, | |
| "loss": 4.7279, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.16161616161616163, | |
| "grad_norm": 6.363076686859131, | |
| "learning_rate": 4e-05, | |
| "loss": 4.4684, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.18181818181818182, | |
| "grad_norm": 4.987633228302002, | |
| "learning_rate": 4.5e-05, | |
| "loss": 4.4504, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.20202020202020202, | |
| "grad_norm": 4.296280860900879, | |
| "learning_rate": 5e-05, | |
| "loss": 4.0533, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.2222222222222222, | |
| "grad_norm": 3.862339735031128, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 4.0011, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.24242424242424243, | |
| "grad_norm": 3.470243453979492, | |
| "learning_rate": 6e-05, | |
| "loss": 4.0229, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.26262626262626265, | |
| "grad_norm": 2.2312989234924316, | |
| "learning_rate": 6.500000000000001e-05, | |
| "loss": 2.9522, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.2828282828282828, | |
| "grad_norm": 2.9605283737182617, | |
| "learning_rate": 7e-05, | |
| "loss": 3.0682, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.30303030303030304, | |
| "grad_norm": 2.9798710346221924, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 3.2887, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.32323232323232326, | |
| "grad_norm": 2.613205671310425, | |
| "learning_rate": 8e-05, | |
| "loss": 3.043, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.3434343434343434, | |
| "grad_norm": 2.627354860305786, | |
| "learning_rate": 8.5e-05, | |
| "loss": 3.0214, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.36363636363636365, | |
| "grad_norm": 2.2543275356292725, | |
| "learning_rate": 9e-05, | |
| "loss": 2.7168, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.3838383838383838, | |
| "grad_norm": 1.868975281715393, | |
| "learning_rate": 9.5e-05, | |
| "loss": 2.8404, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.40404040404040403, | |
| "grad_norm": 1.8961381912231445, | |
| "learning_rate": 0.0001, | |
| "loss": 2.6021, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.42424242424242425, | |
| "grad_norm": 1.7066221237182617, | |
| "learning_rate": 9.998517349225698e-05, | |
| "loss": 2.5649, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.4444444444444444, | |
| "grad_norm": 1.9032788276672363, | |
| "learning_rate": 9.994070276204116e-05, | |
| "loss": 2.3567, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.46464646464646464, | |
| "grad_norm": 1.6003658771514893, | |
| "learning_rate": 9.986661418317759e-05, | |
| "loss": 2.2917, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.48484848484848486, | |
| "grad_norm": 1.7048600912094116, | |
| "learning_rate": 9.976295169466178e-05, | |
| "loss": 2.5865, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.5050505050505051, | |
| "grad_norm": 1.562213659286499, | |
| "learning_rate": 9.962977677460132e-05, | |
| "loss": 2.0904, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.5252525252525253, | |
| "grad_norm": 1.4012371301651, | |
| "learning_rate": 9.946716840375551e-05, | |
| "loss": 1.9331, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.5454545454545454, | |
| "grad_norm": 1.4172520637512207, | |
| "learning_rate": 9.927522301869515e-05, | |
| "loss": 2.04, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.5656565656565656, | |
| "grad_norm": 1.2087681293487549, | |
| "learning_rate": 9.905405445460972e-05, | |
| "loss": 2.0439, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.5858585858585859, | |
| "grad_norm": 1.3168634176254272, | |
| "learning_rate": 9.880379387779637e-05, | |
| "loss": 2.0186, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.6060606060606061, | |
| "grad_norm": 1.3884882926940918, | |
| "learning_rate": 9.852458970787026e-05, | |
| "loss": 1.7423, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.6262626262626263, | |
| "grad_norm": 1.2662495374679565, | |
| "learning_rate": 9.821660752974293e-05, | |
| "loss": 1.8134, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.6464646464646465, | |
| "grad_norm": 1.2647764682769775, | |
| "learning_rate": 9.78800299954203e-05, | |
| "loss": 1.9441, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.6666666666666666, | |
| "grad_norm": 1.4162395000457764, | |
| "learning_rate": 9.751505671567913e-05, | |
| "loss": 1.7532, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.6868686868686869, | |
| "grad_norm": 1.3138062953948975, | |
| "learning_rate": 9.712190414168572e-05, | |
| "loss": 1.8705, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.7070707070707071, | |
| "grad_norm": 1.2262977361679077, | |
| "learning_rate": 9.67008054366274e-05, | |
| "loss": 1.7738, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.7272727272727273, | |
| "grad_norm": 1.5342642068862915, | |
| "learning_rate": 9.625201033743261e-05, | |
| "loss": 1.9003, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.7474747474747475, | |
| "grad_norm": 1.0173803567886353, | |
| "learning_rate": 9.577578500666187e-05, | |
| "loss": 1.4541, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.7676767676767676, | |
| "grad_norm": 0.9901583194732666, | |
| "learning_rate": 9.527241187465734e-05, | |
| "loss": 1.577, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.7878787878787878, | |
| "grad_norm": 0.9777953028678894, | |
| "learning_rate": 9.474218947204459e-05, | |
| "loss": 1.396, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.8080808080808081, | |
| "grad_norm": 1.240479588508606, | |
| "learning_rate": 9.418543225268596e-05, | |
| "loss": 1.6402, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.8282828282828283, | |
| "grad_norm": 1.1354819536209106, | |
| "learning_rate": 9.360247040719039e-05, | |
| "loss": 1.5014, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.8484848484848485, | |
| "grad_norm": 1.0067344903945923, | |
| "learning_rate": 9.29936496670905e-05, | |
| "loss": 1.4353, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.8686868686868687, | |
| "grad_norm": 1.0829236507415771, | |
| "learning_rate": 9.235933109980301e-05, | |
| "loss": 1.4657, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.8888888888888888, | |
| "grad_norm": 1.0891422033309937, | |
| "learning_rate": 9.16998908944939e-05, | |
| "loss": 1.5081, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.9090909090909091, | |
| "grad_norm": 1.0870673656463623, | |
| "learning_rate": 9.101572013897555e-05, | |
| "loss": 1.4492, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.9292929292929293, | |
| "grad_norm": 1.154875636100769, | |
| "learning_rate": 9.030722458776814e-05, | |
| "loss": 1.4784, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.9494949494949495, | |
| "grad_norm": 1.2022784948349, | |
| "learning_rate": 8.957482442146272e-05, | |
| "loss": 1.4172, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.9696969696969697, | |
| "grad_norm": 1.1286842823028564, | |
| "learning_rate": 8.881895399752874e-05, | |
| "loss": 1.3976, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.98989898989899, | |
| "grad_norm": 1.2492576837539673, | |
| "learning_rate": 8.80400615927139e-05, | |
| "loss": 1.3521, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 1.0101010101010102, | |
| "grad_norm": 1.5818628072738647, | |
| "learning_rate": 8.72386091371891e-05, | |
| "loss": 1.8895, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.0101010101010102, | |
| "eval_loss": 1.3664671182632446, | |
| "eval_runtime": 4.2876, | |
| "eval_samples_per_second": 19.591, | |
| "eval_steps_per_second": 9.796, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 149, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 4, | |
| "save_steps": 50, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 5, | |
| "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": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.359873201143808e+16, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |