| { | |
| "best_metric": 0.7745351195335388, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 1.4184397163120568, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.028368794326241134, | |
| "grad_norm": 0.3985974192619324, | |
| "learning_rate": 5e-05, | |
| "loss": 1.6702, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.028368794326241134, | |
| "eval_loss": 1.899458646774292, | |
| "eval_runtime": 2.2162, | |
| "eval_samples_per_second": 107.393, | |
| "eval_steps_per_second": 13.537, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.05673758865248227, | |
| "grad_norm": 0.5140787959098816, | |
| "learning_rate": 0.0001, | |
| "loss": 1.7848, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0851063829787234, | |
| "grad_norm": 0.5856381058692932, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 1.8057, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.11347517730496454, | |
| "grad_norm": 0.6149824261665344, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 1.8163, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.14184397163120568, | |
| "grad_norm": 0.7225697636604309, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 1.7495, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.1702127659574468, | |
| "grad_norm": 0.740507185459137, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 1.6687, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.19858156028368795, | |
| "grad_norm": 0.7978124022483826, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 1.4804, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.22695035460992907, | |
| "grad_norm": 0.8922854065895081, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 1.3501, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.2553191489361702, | |
| "grad_norm": 0.579936146736145, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 1.4268, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.28368794326241137, | |
| "grad_norm": 0.4345473647117615, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 1.3293, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.3120567375886525, | |
| "grad_norm": 0.44009342789649963, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 1.2333, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.3404255319148936, | |
| "grad_norm": 0.46212610602378845, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 1.162, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.36879432624113473, | |
| "grad_norm": 0.4617663621902466, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 1.1012, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.3971631205673759, | |
| "grad_norm": 0.4596976935863495, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.9991, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.425531914893617, | |
| "grad_norm": 0.4672059714794159, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 0.8918, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.45390070921985815, | |
| "grad_norm": 0.4531814754009247, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 0.7934, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.48226950354609927, | |
| "grad_norm": 0.6572938561439514, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 0.7457, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.5106382978723404, | |
| "grad_norm": 0.6012714505195618, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 1.1878, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.5390070921985816, | |
| "grad_norm": 0.6261995434761047, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 1.1167, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.5673758865248227, | |
| "grad_norm": 0.5403241515159607, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 1.0432, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.5957446808510638, | |
| "grad_norm": 0.42570388317108154, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 0.8996, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.624113475177305, | |
| "grad_norm": 0.36389097571372986, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 0.846, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.6524822695035462, | |
| "grad_norm": 0.3820289969444275, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 0.7839, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.6808510638297872, | |
| "grad_norm": 0.4526003301143646, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 0.6523, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.7092198581560284, | |
| "grad_norm": 0.510269045829773, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 0.6165, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.7092198581560284, | |
| "eval_loss": 0.8404024839401245, | |
| "eval_runtime": 2.2097, | |
| "eval_samples_per_second": 107.708, | |
| "eval_steps_per_second": 13.577, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.7375886524822695, | |
| "grad_norm": 0.6525234580039978, | |
| "learning_rate": 5e-05, | |
| "loss": 0.6425, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.7659574468085106, | |
| "grad_norm": 0.37175679206848145, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 1.0672, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.7943262411347518, | |
| "grad_norm": 0.3560580015182495, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 0.9941, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.8226950354609929, | |
| "grad_norm": 0.29323962330818176, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 0.9064, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.851063829787234, | |
| "grad_norm": 0.2811514437198639, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 0.8322, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.8794326241134752, | |
| "grad_norm": 0.24265116453170776, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 0.7745, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.9078014184397163, | |
| "grad_norm": 0.2871304154396057, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.6722, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.9361702127659575, | |
| "grad_norm": 0.31180500984191895, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 0.6407, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.9645390070921985, | |
| "grad_norm": 0.3772461712360382, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 0.5475, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.9929078014184397, | |
| "grad_norm": 0.8375016450881958, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 0.5158, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 1.0212765957446808, | |
| "grad_norm": 0.6372146606445312, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 1.7406, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 1.049645390070922, | |
| "grad_norm": 0.44848495721817017, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 0.9688, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 1.0780141843971631, | |
| "grad_norm": 0.3469182550907135, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.8563, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 1.1063829787234043, | |
| "grad_norm": 0.3276442885398865, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 0.7992, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 1.1347517730496455, | |
| "grad_norm": 0.3271907866001129, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 0.7209, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.1631205673758864, | |
| "grad_norm": 0.30662497878074646, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 0.6576, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 1.1914893617021276, | |
| "grad_norm": 0.3411548435688019, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 0.6093, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 1.2198581560283688, | |
| "grad_norm": 0.4294974207878113, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 0.5507, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 1.24822695035461, | |
| "grad_norm": 0.3823366165161133, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.307, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 1.2765957446808511, | |
| "grad_norm": 0.6564927101135254, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 1.454, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 1.3049645390070923, | |
| "grad_norm": 0.41464975476264954, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 0.9198, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 1.3333333333333333, | |
| "grad_norm": 0.3397634029388428, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 0.8463, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 1.3617021276595744, | |
| "grad_norm": 0.34161895513534546, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 0.7787, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 1.3900709219858156, | |
| "grad_norm": 0.2931356132030487, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 0.7096, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 1.4184397163120568, | |
| "grad_norm": 0.3229428231716156, | |
| "learning_rate": 0.0, | |
| "loss": 0.672, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.4184397163120568, | |
| "eval_loss": 0.7745351195335388, | |
| "eval_runtime": 2.2071, | |
| "eval_samples_per_second": 107.834, | |
| "eval_steps_per_second": 13.592, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "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": 8.33416392081408e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |