| { | |
| "best_metric": 0.7373636960983276, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 2.816901408450704, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.056338028169014086, | |
| "grad_norm": 25.043020248413086, | |
| "learning_rate": 5e-05, | |
| "loss": 12.3344, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.056338028169014086, | |
| "eval_loss": 12.388128280639648, | |
| "eval_runtime": 1.3454, | |
| "eval_samples_per_second": 89.192, | |
| "eval_steps_per_second": 11.149, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.11267605633802817, | |
| "grad_norm": 22.335596084594727, | |
| "learning_rate": 0.0001, | |
| "loss": 12.412, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.16901408450704225, | |
| "grad_norm": 21.580015182495117, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 12.2237, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.22535211267605634, | |
| "grad_norm": 16.71055030822754, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 10.442, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.28169014084507044, | |
| "grad_norm": 15.653229713439941, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 8.3925, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.3380281690140845, | |
| "grad_norm": 14.434592247009277, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 6.7109, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.39436619718309857, | |
| "grad_norm": 12.084268569946289, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 5.9095, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.4507042253521127, | |
| "grad_norm": 14.198653221130371, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 5.1487, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.5070422535211268, | |
| "grad_norm": 13.856998443603516, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 4.039, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.5633802816901409, | |
| "grad_norm": 13.335588455200195, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 2.1799, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.6197183098591549, | |
| "grad_norm": 6.2130608558654785, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 1.3482, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.676056338028169, | |
| "grad_norm": 5.610598564147949, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 1.3538, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.7323943661971831, | |
| "grad_norm": 4.826842784881592, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 1.5145, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.7887323943661971, | |
| "grad_norm": 3.8220436573028564, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 1.057, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.8450704225352113, | |
| "grad_norm": 6.495180606842041, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 1.0878, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.9014084507042254, | |
| "grad_norm": 4.079573154449463, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 1.1101, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.9577464788732394, | |
| "grad_norm": 3.5554068088531494, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 1.0183, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 1.0140845070422535, | |
| "grad_norm": 4.620770454406738, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 1.0595, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 1.0704225352112675, | |
| "grad_norm": 2.241077423095703, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 0.7834, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 1.1267605633802817, | |
| "grad_norm": 3.594456434249878, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.8131, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.1830985915492958, | |
| "grad_norm": 1.6228787899017334, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 0.825, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 1.2394366197183098, | |
| "grad_norm": 4.617722511291504, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 0.8721, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 1.295774647887324, | |
| "grad_norm": 2.3542089462280273, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 0.8546, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 1.352112676056338, | |
| "grad_norm": 1.9718202352523804, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 0.7775, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 1.408450704225352, | |
| "grad_norm": 1.1844096183776855, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 0.7479, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.408450704225352, | |
| "eval_loss": 0.7588818073272705, | |
| "eval_runtime": 1.3426, | |
| "eval_samples_per_second": 89.38, | |
| "eval_steps_per_second": 11.173, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.4647887323943662, | |
| "grad_norm": 1.7001279592514038, | |
| "learning_rate": 5e-05, | |
| "loss": 0.8627, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 1.5211267605633803, | |
| "grad_norm": 1.0881457328796387, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 0.7834, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 1.5774647887323945, | |
| "grad_norm": 1.3560937643051147, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 0.7894, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 1.6338028169014085, | |
| "grad_norm": 1.1216421127319336, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 0.8246, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 1.6901408450704225, | |
| "grad_norm": 1.5690072774887085, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 0.8028, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.7464788732394365, | |
| "grad_norm": 1.6674970388412476, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 0.8028, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 1.8028169014084507, | |
| "grad_norm": 1.2421163320541382, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.8152, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 1.8591549295774648, | |
| "grad_norm": 1.976396083831787, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 0.8078, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 1.915492957746479, | |
| "grad_norm": 1.6364705562591553, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 0.8123, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 1.971830985915493, | |
| "grad_norm": 1.5316513776779175, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 0.8613, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 2.028169014084507, | |
| "grad_norm": 1.5757020711898804, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 0.856, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 2.084507042253521, | |
| "grad_norm": 0.8843956589698792, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 0.7801, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 2.140845070422535, | |
| "grad_norm": 1.490215539932251, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.7651, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 2.1971830985915495, | |
| "grad_norm": 1.2212885618209839, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 0.7514, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 2.2535211267605635, | |
| "grad_norm": 2.2902417182922363, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 0.7644, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 2.3098591549295775, | |
| "grad_norm": 0.8333585262298584, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 0.7863, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 2.3661971830985915, | |
| "grad_norm": 1.7875335216522217, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 0.7201, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 2.4225352112676055, | |
| "grad_norm": 1.2753856182098389, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 0.7981, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 2.4788732394366195, | |
| "grad_norm": 1.1924065351486206, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.7627, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 2.535211267605634, | |
| "grad_norm": 2.2087767124176025, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 0.7358, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 2.591549295774648, | |
| "grad_norm": 2.043612003326416, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 0.7413, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 2.647887323943662, | |
| "grad_norm": 0.983856737613678, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 0.7159, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 2.704225352112676, | |
| "grad_norm": 2.1408305168151855, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 0.8566, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 2.76056338028169, | |
| "grad_norm": 1.3574248552322388, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 0.7231, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 2.816901408450704, | |
| "grad_norm": 2.1828038692474365, | |
| "learning_rate": 0.0, | |
| "loss": 0.8049, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 2.816901408450704, | |
| "eval_loss": 0.7373636960983276, | |
| "eval_runtime": 1.3411, | |
| "eval_samples_per_second": 89.477, | |
| "eval_steps_per_second": 11.185, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "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 | |
| } | |