| { | |
| "best_metric": 3.1890745162963867, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.6920415224913494, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.01384083044982699, | |
| "grad_norm": 0.7485857605934143, | |
| "learning_rate": 5e-05, | |
| "loss": 6.6306, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.01384083044982699, | |
| "eval_loss": 6.805291175842285, | |
| "eval_runtime": 6.2097, | |
| "eval_samples_per_second": 78.426, | |
| "eval_steps_per_second": 9.823, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.02768166089965398, | |
| "grad_norm": 0.8643624186515808, | |
| "learning_rate": 0.0001, | |
| "loss": 6.4903, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.04152249134948097, | |
| "grad_norm": 0.6605107188224792, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 6.5307, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.05536332179930796, | |
| "grad_norm": 0.7111093997955322, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 6.4379, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.06920415224913495, | |
| "grad_norm": 0.7479893565177917, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 6.4083, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.08304498269896193, | |
| "grad_norm": 0.8989283442497253, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 6.445, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.09688581314878893, | |
| "grad_norm": 0.9780114889144897, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 6.3956, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.11072664359861592, | |
| "grad_norm": 1.2237392663955688, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 6.3558, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.1245674740484429, | |
| "grad_norm": 1.4933561086654663, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 6.3084, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.1384083044982699, | |
| "grad_norm": 1.5895549058914185, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 6.1206, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.1522491349480969, | |
| "grad_norm": 1.7232730388641357, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 6.1455, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.16608996539792387, | |
| "grad_norm": 1.8274600505828857, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 5.8453, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.17993079584775087, | |
| "grad_norm": 1.4549096822738647, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 5.8408, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.19377162629757785, | |
| "grad_norm": 1.2946592569351196, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 5.0619, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.20761245674740483, | |
| "grad_norm": 1.2284226417541504, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 4.8974, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.22145328719723184, | |
| "grad_norm": 1.2975873947143555, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 4.9138, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.23529411764705882, | |
| "grad_norm": 1.4106292724609375, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 4.8518, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.2491349480968858, | |
| "grad_norm": 1.4355554580688477, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 4.7725, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.2629757785467128, | |
| "grad_norm": 1.3611592054367065, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 4.4971, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.2768166089965398, | |
| "grad_norm": 1.6109015941619873, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 4.3995, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.2906574394463668, | |
| "grad_norm": 1.844136357307434, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 4.1623, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.3044982698961938, | |
| "grad_norm": 1.99616539478302, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 4.3871, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.31833910034602075, | |
| "grad_norm": 1.9316785335540771, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 4.2035, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.33217993079584773, | |
| "grad_norm": 1.7456412315368652, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 3.981, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.3460207612456747, | |
| "grad_norm": 1.6280741691589355, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 4.2911, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.3460207612456747, | |
| "eval_loss": 3.8750054836273193, | |
| "eval_runtime": 6.2087, | |
| "eval_samples_per_second": 78.439, | |
| "eval_steps_per_second": 9.825, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.35986159169550175, | |
| "grad_norm": 1.2438147068023682, | |
| "learning_rate": 5e-05, | |
| "loss": 3.9151, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.3737024221453287, | |
| "grad_norm": 1.0506852865219116, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 3.7531, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.3875432525951557, | |
| "grad_norm": 1.0012786388397217, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 3.7794, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.4013840830449827, | |
| "grad_norm": 0.98823481798172, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 3.659, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.41522491349480967, | |
| "grad_norm": 1.0248918533325195, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 3.5903, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.4290657439446367, | |
| "grad_norm": 1.0814943313598633, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 3.4663, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.4429065743944637, | |
| "grad_norm": 1.1849011182785034, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 3.397, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.45674740484429066, | |
| "grad_norm": 1.5150214433670044, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 3.5301, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.47058823529411764, | |
| "grad_norm": 1.6340036392211914, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 3.5942, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.4844290657439446, | |
| "grad_norm": 1.5461198091506958, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 3.4832, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.4982698961937716, | |
| "grad_norm": 1.5538333654403687, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 3.3929, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.5121107266435986, | |
| "grad_norm": 1.4813439846038818, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 3.3781, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.5259515570934256, | |
| "grad_norm": 1.2175124883651733, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 3.5876, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.5397923875432526, | |
| "grad_norm": 1.1959764957427979, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 3.1674, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.5536332179930796, | |
| "grad_norm": 1.058384656906128, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 3.1204, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.5674740484429066, | |
| "grad_norm": 0.9045761227607727, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 3.2443, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.5813148788927336, | |
| "grad_norm": 1.022927165031433, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 3.1241, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.5951557093425606, | |
| "grad_norm": 0.936863899230957, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 3.0281, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.6089965397923875, | |
| "grad_norm": 0.9517385363578796, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 3.1129, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.6228373702422145, | |
| "grad_norm": 1.131404161453247, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 3.2927, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.6366782006920415, | |
| "grad_norm": 1.437263011932373, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 3.3686, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.6505190311418685, | |
| "grad_norm": 1.5570812225341797, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 3.2489, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.6643598615916955, | |
| "grad_norm": 1.5820376873016357, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 3.3061, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.6782006920415224, | |
| "grad_norm": 1.4706281423568726, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 3.0915, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.6920415224913494, | |
| "grad_norm": 1.5056296586990356, | |
| "learning_rate": 0.0, | |
| "loss": 3.5272, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.6920415224913494, | |
| "eval_loss": 3.1890745162963867, | |
| "eval_runtime": 6.2141, | |
| "eval_samples_per_second": 78.37, | |
| "eval_steps_per_second": 9.816, | |
| "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": 1.3004277953855488e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |