| { | |
| "best_metric": 0.4431842565536499, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.704225352112676, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.014084507042253521, | |
| "grad_norm": 9.345203399658203, | |
| "learning_rate": 5e-05, | |
| "loss": 12.2278, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.014084507042253521, | |
| "eval_loss": 12.823960304260254, | |
| "eval_runtime": 13.7469, | |
| "eval_samples_per_second": 34.844, | |
| "eval_steps_per_second": 4.365, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.028169014084507043, | |
| "grad_norm": 8.285017967224121, | |
| "learning_rate": 0.0001, | |
| "loss": 12.5554, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.04225352112676056, | |
| "grad_norm": 9.962447166442871, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 12.0693, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.056338028169014086, | |
| "grad_norm": 10.474084854125977, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 9.9324, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.07042253521126761, | |
| "grad_norm": 10.761260032653809, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 7.9931, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.08450704225352113, | |
| "grad_norm": 12.275903701782227, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 5.846, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.09859154929577464, | |
| "grad_norm": 8.618311882019043, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 4.0886, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.11267605633802817, | |
| "grad_norm": 6.54197359085083, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 2.842, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.1267605633802817, | |
| "grad_norm": 5.05172872543335, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 1.8497, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.14084507042253522, | |
| "grad_norm": 5.066522598266602, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 1.3839, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.15492957746478872, | |
| "grad_norm": 3.4137966632843018, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 1.0817, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.16901408450704225, | |
| "grad_norm": 3.5682404041290283, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 1.0354, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.18309859154929578, | |
| "grad_norm": 3.944023847579956, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 1.0996, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.19718309859154928, | |
| "grad_norm": 7.619630813598633, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 1.2909, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.2112676056338028, | |
| "grad_norm": 4.500230312347412, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 0.9198, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.22535211267605634, | |
| "grad_norm": 2.387722969055176, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 0.7861, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.23943661971830985, | |
| "grad_norm": 1.6559205055236816, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 0.69, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.2535211267605634, | |
| "grad_norm": 1.1613023281097412, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.5064, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.2676056338028169, | |
| "grad_norm": 1.4013922214508057, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 0.6321, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.28169014084507044, | |
| "grad_norm": 1.803591012954712, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.5667, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.29577464788732394, | |
| "grad_norm": 1.176186203956604, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 0.5092, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.30985915492957744, | |
| "grad_norm": 1.754784345626831, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 0.4354, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.323943661971831, | |
| "grad_norm": 1.2375812530517578, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 0.4359, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.3380281690140845, | |
| "grad_norm": 0.9423263669013977, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 0.3558, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.352112676056338, | |
| "grad_norm": 3.5504989624023438, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 0.3982, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.352112676056338, | |
| "eval_loss": 0.5917026996612549, | |
| "eval_runtime": 13.7657, | |
| "eval_samples_per_second": 34.797, | |
| "eval_steps_per_second": 4.359, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.36619718309859156, | |
| "grad_norm": 4.246863842010498, | |
| "learning_rate": 5e-05, | |
| "loss": 0.631, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.38028169014084506, | |
| "grad_norm": 4.5620503425598145, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 0.8535, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.39436619718309857, | |
| "grad_norm": 2.339592456817627, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 0.522, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.4084507042253521, | |
| "grad_norm": 2.5191361904144287, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 0.5956, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.4225352112676056, | |
| "grad_norm": 3.5583834648132324, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 0.5882, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.43661971830985913, | |
| "grad_norm": 2.130383014678955, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 0.5102, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.4507042253521127, | |
| "grad_norm": 1.9885919094085693, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.525, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.4647887323943662, | |
| "grad_norm": 1.752604365348816, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 0.4971, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.4788732394366197, | |
| "grad_norm": 1.4558221101760864, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 0.441, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.49295774647887325, | |
| "grad_norm": 0.9350324869155884, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 0.4291, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.5070422535211268, | |
| "grad_norm": 0.8899381160736084, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 0.4157, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.5211267605633803, | |
| "grad_norm": 0.6941632032394409, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 0.3612, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.5352112676056338, | |
| "grad_norm": 1.4537720680236816, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.4386, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.5492957746478874, | |
| "grad_norm": 1.35344398021698, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 0.5339, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.5633802816901409, | |
| "grad_norm": 0.8420842289924622, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 0.4795, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.5774647887323944, | |
| "grad_norm": 0.8056310415267944, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 0.491, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.5915492957746479, | |
| "grad_norm": 0.7623363733291626, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 0.478, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.6056338028169014, | |
| "grad_norm": 1.0704370737075806, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 0.4453, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.6197183098591549, | |
| "grad_norm": 1.269627332687378, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.4703, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.6338028169014085, | |
| "grad_norm": 1.4033896923065186, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 0.4217, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.647887323943662, | |
| "grad_norm": 0.8467299938201904, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 0.433, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.6619718309859155, | |
| "grad_norm": 0.46602192521095276, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 0.3919, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.676056338028169, | |
| "grad_norm": 0.6642929315567017, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 0.3828, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.6901408450704225, | |
| "grad_norm": 1.1457411050796509, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 0.3629, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.704225352112676, | |
| "grad_norm": 1.6525368690490723, | |
| "learning_rate": 0.0, | |
| "loss": 0.3039, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.704225352112676, | |
| "eval_loss": 0.4431842565536499, | |
| "eval_runtime": 13.7585, | |
| "eval_samples_per_second": 34.815, | |
| "eval_steps_per_second": 4.361, | |
| "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": 5.308600064850002e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |