| { | |
| "best_metric": 0.004239150322973728, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 1.7699115044247788, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.035398230088495575, | |
| "grad_norm": 1.0221329927444458, | |
| "learning_rate": 5e-05, | |
| "loss": 1.134, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.035398230088495575, | |
| "eval_loss": 2.497450351715088, | |
| "eval_runtime": 5.8535, | |
| "eval_samples_per_second": 32.459, | |
| "eval_steps_per_second": 4.1, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.07079646017699115, | |
| "grad_norm": 1.1683621406555176, | |
| "learning_rate": 0.0001, | |
| "loss": 1.3929, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.10619469026548672, | |
| "grad_norm": 1.4631526470184326, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 1.6041, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.1415929203539823, | |
| "grad_norm": 1.8949447870254517, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 1.543, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.17699115044247787, | |
| "grad_norm": 3.3410162925720215, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 1.5788, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.21238938053097345, | |
| "grad_norm": 3.959629535675049, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 1.5927, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.24778761061946902, | |
| "grad_norm": 6.53699254989624, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 2.2757, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.2831858407079646, | |
| "grad_norm": 1.920776128768921, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.2632, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.3185840707964602, | |
| "grad_norm": 1.0803369283676147, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 0.1739, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.35398230088495575, | |
| "grad_norm": 0.7359183430671692, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 0.085, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.3893805309734513, | |
| "grad_norm": 0.422931045293808, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 0.0551, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.4247787610619469, | |
| "grad_norm": 0.5463584065437317, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 0.0647, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.46017699115044247, | |
| "grad_norm": 1.427022099494934, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 0.1006, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.49557522123893805, | |
| "grad_norm": 1.973958134651184, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.257, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.5309734513274337, | |
| "grad_norm": 0.4866352379322052, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 0.0476, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.5663716814159292, | |
| "grad_norm": 0.2800993025302887, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 0.0258, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.6017699115044248, | |
| "grad_norm": 0.32655978202819824, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 0.025, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.6371681415929203, | |
| "grad_norm": 0.24829503893852234, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.0212, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.672566371681416, | |
| "grad_norm": 0.24665923416614532, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 0.0168, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.7079646017699115, | |
| "grad_norm": 0.34969601035118103, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.02, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.7433628318584071, | |
| "grad_norm": 1.1210227012634277, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 0.0705, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.7787610619469026, | |
| "grad_norm": 0.17592571675777435, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 0.0126, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.8141592920353983, | |
| "grad_norm": 0.3712072968482971, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 0.0076, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.8495575221238938, | |
| "grad_norm": 0.3783921003341675, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 0.0098, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.8849557522123894, | |
| "grad_norm": 0.26639214158058167, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 0.0149, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.8849557522123894, | |
| "eval_loss": 0.009557968936860561, | |
| "eval_runtime": 5.8398, | |
| "eval_samples_per_second": 32.536, | |
| "eval_steps_per_second": 4.11, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.9203539823008849, | |
| "grad_norm": 0.17116095125675201, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0109, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.9557522123893806, | |
| "grad_norm": 0.374548077583313, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 0.0133, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.9911504424778761, | |
| "grad_norm": 0.458191454410553, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 0.015, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 1.0265486725663717, | |
| "grad_norm": 0.30738526582717896, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 0.0112, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 1.0619469026548674, | |
| "grad_norm": 0.13246457278728485, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 0.0026, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.0973451327433628, | |
| "grad_norm": 0.18884605169296265, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 0.0055, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 1.1327433628318584, | |
| "grad_norm": 0.021148117259144783, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.0027, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 1.168141592920354, | |
| "grad_norm": 0.2229768931865692, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 0.0058, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 1.2035398230088497, | |
| "grad_norm": 0.1037597805261612, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 0.0024, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 1.238938053097345, | |
| "grad_norm": 0.2901352345943451, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 0.0197, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 1.2743362831858407, | |
| "grad_norm": 0.2113533914089203, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 0.0057, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 1.3097345132743363, | |
| "grad_norm": 0.36708688735961914, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 0.0125, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 1.3451327433628317, | |
| "grad_norm": 0.20552334189414978, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.0029, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 1.3805309734513274, | |
| "grad_norm": 0.08920054882764816, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 0.006, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 1.415929203539823, | |
| "grad_norm": 0.6489487886428833, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 0.0039, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.4513274336283186, | |
| "grad_norm": 0.10894274711608887, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 0.0014, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 1.4867256637168142, | |
| "grad_norm": 0.07067730277776718, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 0.0032, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 1.5221238938053099, | |
| "grad_norm": 1.4301823377609253, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 0.0046, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 1.5575221238938053, | |
| "grad_norm": 0.07354891300201416, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.0052, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 1.592920353982301, | |
| "grad_norm": 0.15491953492164612, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 0.0052, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 1.6283185840707963, | |
| "grad_norm": 0.07862751930952072, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 0.003, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 1.663716814159292, | |
| "grad_norm": 0.031061874702572823, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 0.0011, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 1.6991150442477876, | |
| "grad_norm": 0.2089461386203766, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 0.0015, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 1.7345132743362832, | |
| "grad_norm": 0.2084563821554184, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 0.0051, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 1.7699115044247788, | |
| "grad_norm": 0.07801011949777603, | |
| "learning_rate": 0.0, | |
| "loss": 0.0054, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.7699115044247788, | |
| "eval_loss": 0.004239150322973728, | |
| "eval_runtime": 5.8375, | |
| "eval_samples_per_second": 32.548, | |
| "eval_steps_per_second": 4.111, | |
| "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": 0 | |
| } | |
| }, | |
| "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 | |
| } | |