| { | |
| "best_metric": 1.1405298709869385, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.2994011976047904, | |
| "eval_steps": 25, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.011976047904191617, | |
| "grad_norm": 250.99620056152344, | |
| "learning_rate": 5e-05, | |
| "loss": 2.7117, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.011976047904191617, | |
| "eval_loss": 2.89910888671875, | |
| "eval_runtime": 16.3166, | |
| "eval_samples_per_second": 34.505, | |
| "eval_steps_per_second": 4.351, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.023952095808383235, | |
| "grad_norm": 260.1399230957031, | |
| "learning_rate": 0.0001, | |
| "loss": 2.7519, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.03592814371257485, | |
| "grad_norm": 143.50582885742188, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 1.7389, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.04790419161676647, | |
| "grad_norm": 64.88272094726562, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 1.3676, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.059880239520958084, | |
| "grad_norm": 52.95808029174805, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 1.1652, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0718562874251497, | |
| "grad_norm": 58.396331787109375, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 1.358, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.08383233532934131, | |
| "grad_norm": 45.82628631591797, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 1.3426, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.09580838323353294, | |
| "grad_norm": 49.50060272216797, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 1.2466, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.10778443113772455, | |
| "grad_norm": 43.226200103759766, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 1.2077, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.11976047904191617, | |
| "grad_norm": 43.2709846496582, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 1.228, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.1317365269461078, | |
| "grad_norm": 50.480342864990234, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 1.2581, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.1437125748502994, | |
| "grad_norm": 52.929805755615234, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 1.2654, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.15568862275449102, | |
| "grad_norm": 52.93833923339844, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 1.2596, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.16766467065868262, | |
| "grad_norm": 132.69166564941406, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 1.1978, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.17964071856287425, | |
| "grad_norm": 49.01171112060547, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 1.2157, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.19161676646706588, | |
| "grad_norm": 40.458045959472656, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 1.0361, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.20359281437125748, | |
| "grad_norm": 48.40788269042969, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 1.0716, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.2155688622754491, | |
| "grad_norm": 45.04956817626953, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 1.183, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.2275449101796407, | |
| "grad_norm": 45.99813461303711, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 1.1989, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.23952095808383234, | |
| "grad_norm": 46.90947341918945, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 1.2149, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.25149700598802394, | |
| "grad_norm": 42.52228546142578, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 1.0775, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.2634730538922156, | |
| "grad_norm": 54.70430374145508, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 1.1699, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.2754491017964072, | |
| "grad_norm": 57.11561965942383, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 1.0286, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.2874251497005988, | |
| "grad_norm": 160.43727111816406, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 1.179, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.2994011976047904, | |
| "grad_norm": 67.79126739501953, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 1.2579, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.2994011976047904, | |
| "eval_loss": 1.1405298709869385, | |
| "eval_runtime": 16.3152, | |
| "eval_samples_per_second": 34.508, | |
| "eval_steps_per_second": 4.352, | |
| "step": 25 | |
| } | |
| ], | |
| "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": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2.830247619723264e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |