| { | |
| "best_metric": 5.28487491607666, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.22560631697687536, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0045121263395375075, | |
| "grad_norm": 0.779909610748291, | |
| "learning_rate": 5e-05, | |
| "loss": 5.4973, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0045121263395375075, | |
| "eval_loss": 5.5700364112854, | |
| "eval_runtime": 17.0098, | |
| "eval_samples_per_second": 87.773, | |
| "eval_steps_per_second": 10.994, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.009024252679075015, | |
| "grad_norm": 0.7312822937965393, | |
| "learning_rate": 0.0001, | |
| "loss": 5.4864, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.01353637901861252, | |
| "grad_norm": 0.6232210397720337, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 5.4522, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.01804850535815003, | |
| "grad_norm": 1.3436734676361084, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 5.5301, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.022560631697687534, | |
| "grad_norm": 0.7657508254051208, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 5.4629, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.02707275803722504, | |
| "grad_norm": 0.3754770755767822, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 5.4092, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.03158488437676255, | |
| "grad_norm": 0.349260538816452, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 5.4115, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.03609701071630006, | |
| "grad_norm": 0.3250214755535126, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 5.4518, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.04060913705583756, | |
| "grad_norm": 0.3496224582195282, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 5.4726, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.04512126339537507, | |
| "grad_norm": 0.34312787652015686, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 5.4703, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.049633389734912575, | |
| "grad_norm": 0.32074207067489624, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 5.4666, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.05414551607445008, | |
| "grad_norm": 0.3685069978237152, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 5.4333, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.05865764241398759, | |
| "grad_norm": 0.3047601282596588, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 5.4115, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0631697687535251, | |
| "grad_norm": 0.48723435401916504, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 5.3694, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0676818950930626, | |
| "grad_norm": 0.5016087293624878, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 5.3333, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.07219402143260012, | |
| "grad_norm": 0.35524889826774597, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 5.3867, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.07670614777213762, | |
| "grad_norm": 0.3417850136756897, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 5.3897, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.08121827411167512, | |
| "grad_norm": 0.3581264317035675, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 5.3349, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.08573040045121263, | |
| "grad_norm": 0.37793871760368347, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 5.3239, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.09024252679075014, | |
| "grad_norm": 0.37636879086494446, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 5.3461, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.09475465313028765, | |
| "grad_norm": 0.376545786857605, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 5.3628, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.09926677946982515, | |
| "grad_norm": 0.3357970714569092, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 5.3641, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.10377890580936266, | |
| "grad_norm": 0.42382362484931946, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 5.3917, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.10829103214890017, | |
| "grad_norm": 0.43022873997688293, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 5.3326, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.11280315848843768, | |
| "grad_norm": 0.537429690361023, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 5.3388, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.11280315848843768, | |
| "eval_loss": 5.323215484619141, | |
| "eval_runtime": 17.0376, | |
| "eval_samples_per_second": 87.63, | |
| "eval_steps_per_second": 10.976, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.11731528482797518, | |
| "grad_norm": 0.5437615513801575, | |
| "learning_rate": 5e-05, | |
| "loss": 5.3644, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.1218274111675127, | |
| "grad_norm": 0.6228774785995483, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 5.2771, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.1263395375070502, | |
| "grad_norm": 0.5897179245948792, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 5.3137, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.1308516638465877, | |
| "grad_norm": 0.6028752326965332, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 5.3606, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.1353637901861252, | |
| "grad_norm": 0.5325168967247009, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 5.3051, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.13987591652566272, | |
| "grad_norm": 0.5063620805740356, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 5.2901, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.14438804286520024, | |
| "grad_norm": 0.4882858395576477, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 5.2739, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.14890016920473773, | |
| "grad_norm": 0.4943495988845825, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 5.3036, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.15341229554427524, | |
| "grad_norm": 0.4519631266593933, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 5.318, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.15792442188381275, | |
| "grad_norm": 0.502394437789917, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 5.3522, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.16243654822335024, | |
| "grad_norm": 0.46117448806762695, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 5.3156, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.16694867456288776, | |
| "grad_norm": 0.5970073342323303, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 5.3131, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.17146080090242527, | |
| "grad_norm": 0.5500613451004028, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 5.3299, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.17597292724196278, | |
| "grad_norm": 0.537351667881012, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 5.3052, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.18048505358150027, | |
| "grad_norm": 0.6283145546913147, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 5.2214, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.18499717992103779, | |
| "grad_norm": 0.582278311252594, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 5.3105, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.1895093062605753, | |
| "grad_norm": 0.5104334354400635, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 5.3162, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.19402143260011281, | |
| "grad_norm": 0.4248177409172058, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 5.2871, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.1985335589396503, | |
| "grad_norm": 0.41239920258522034, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 5.2435, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.20304568527918782, | |
| "grad_norm": 0.42970484495162964, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 5.2902, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.20755781161872533, | |
| "grad_norm": 0.3964599668979645, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 5.3027, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.21206993795826284, | |
| "grad_norm": 0.3762015998363495, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 5.307, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.21658206429780033, | |
| "grad_norm": 0.46960142254829407, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 5.307, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.22109419063733785, | |
| "grad_norm": 0.4847152829170227, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 5.3012, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.22560631697687536, | |
| "grad_norm": 0.5823029279708862, | |
| "learning_rate": 0.0, | |
| "loss": 5.2784, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.22560631697687536, | |
| "eval_loss": 5.28487491607666, | |
| "eval_runtime": 17.0383, | |
| "eval_samples_per_second": 87.626, | |
| "eval_steps_per_second": 10.975, | |
| "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": 1.059536353886208e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |