| { | |
| "best_metric": 2.15939998626709, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.46865846514352666, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.009373169302870533, | |
| "grad_norm": 20.430110931396484, | |
| "learning_rate": 5e-05, | |
| "loss": 17.5316, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.009373169302870533, | |
| "eval_loss": 17.71308135986328, | |
| "eval_runtime": 0.7502, | |
| "eval_samples_per_second": 958.412, | |
| "eval_steps_per_second": 119.968, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.018746338605741066, | |
| "grad_norm": 20.638513565063477, | |
| "learning_rate": 0.0001, | |
| "loss": 17.6906, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.028119507908611598, | |
| "grad_norm": 21.161043167114258, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 17.636, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.03749267721148213, | |
| "grad_norm": 20.05705451965332, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 16.8356, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.04686584651435267, | |
| "grad_norm": 20.52109718322754, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 16.1378, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.056239015817223195, | |
| "grad_norm": 19.574811935424805, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 15.1629, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.06561218512009373, | |
| "grad_norm": 19.021949768066406, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 14.498, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.07498535442296426, | |
| "grad_norm": 18.655065536499023, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 13.6439, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0843585237258348, | |
| "grad_norm": 17.7081241607666, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 12.8421, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.09373169302870533, | |
| "grad_norm": 17.016998291015625, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 12.2078, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.10310486233157587, | |
| "grad_norm": 16.17796516418457, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 11.5572, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.11247803163444639, | |
| "grad_norm": 15.21249008178711, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 10.7787, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.12185120093731693, | |
| "grad_norm": 14.588255882263184, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 10.4646, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.13122437024018746, | |
| "grad_norm": 15.17662239074707, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 9.3852, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.140597539543058, | |
| "grad_norm": 15.120278358459473, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 9.092, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.14997070884592853, | |
| "grad_norm": 15.053887367248535, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 8.5909, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.15934387814879905, | |
| "grad_norm": 15.286741256713867, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 8.101, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.1687170474516696, | |
| "grad_norm": 15.559879302978516, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 7.6821, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.17809021675454012, | |
| "grad_norm": 16.10878562927246, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 7.2054, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.18746338605741067, | |
| "grad_norm": 16.9025821685791, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 6.681, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.1968365553602812, | |
| "grad_norm": 17.329208374023438, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 6.2885, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.20620972466315174, | |
| "grad_norm": 17.769147872924805, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 5.8574, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.21558289396602226, | |
| "grad_norm": 17.88469696044922, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 5.3692, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.22495606326889278, | |
| "grad_norm": 17.019548416137695, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 5.0614, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.23432923257176333, | |
| "grad_norm": 16.17799186706543, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 4.7711, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.23432923257176333, | |
| "eval_loss": 4.283140182495117, | |
| "eval_runtime": 0.7369, | |
| "eval_samples_per_second": 975.695, | |
| "eval_steps_per_second": 122.132, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.24370240187463385, | |
| "grad_norm": 12.770657539367676, | |
| "learning_rate": 5e-05, | |
| "loss": 4.2317, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.2530755711775044, | |
| "grad_norm": 12.256872177124023, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 3.9734, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.2624487404803749, | |
| "grad_norm": 12.620009422302246, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 3.7845, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.27182190978324544, | |
| "grad_norm": 13.734941482543945, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 3.6367, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.281195079086116, | |
| "grad_norm": 13.673043251037598, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 3.554, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.29056824838898654, | |
| "grad_norm": 13.149415969848633, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 3.2785, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.29994141769185706, | |
| "grad_norm": 13.390870094299316, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 3.2042, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.3093145869947276, | |
| "grad_norm": 12.210992813110352, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 3.0077, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.3186877562975981, | |
| "grad_norm": 11.547277450561523, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 2.8702, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.3280609256004687, | |
| "grad_norm": 11.762548446655273, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 2.8338, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.3374340949033392, | |
| "grad_norm": 10.924531936645508, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 2.6657, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.3468072642062097, | |
| "grad_norm": 11.15406322479248, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 2.4972, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.35618043350908024, | |
| "grad_norm": 10.379179000854492, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 2.6364, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.3655536028119508, | |
| "grad_norm": 10.591771125793457, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 2.4719, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.37492677211482134, | |
| "grad_norm": 10.571476936340332, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 2.3302, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.38429994141769186, | |
| "grad_norm": 10.627779006958008, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 2.2841, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.3936731107205624, | |
| "grad_norm": 10.701957702636719, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 2.2543, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.4030462800234329, | |
| "grad_norm": 10.787554740905762, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 2.2541, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.4124194493263035, | |
| "grad_norm": 10.766562461853027, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 2.2785, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.421792618629174, | |
| "grad_norm": 10.696857452392578, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 2.1263, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.4311657879320445, | |
| "grad_norm": 10.436224937438965, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 2.1326, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.44053895723491504, | |
| "grad_norm": 10.621663093566895, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 2.185, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.44991212653778556, | |
| "grad_norm": 10.477226257324219, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 2.1113, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.45928529584065614, | |
| "grad_norm": 10.463092803955078, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 2.1375, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.46865846514352666, | |
| "grad_norm": 10.640161514282227, | |
| "learning_rate": 0.0, | |
| "loss": 2.155, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.46865846514352666, | |
| "eval_loss": 2.15939998626709, | |
| "eval_runtime": 0.7372, | |
| "eval_samples_per_second": 975.261, | |
| "eval_steps_per_second": 122.077, | |
| "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": 3506283793612800.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |