| { | |
| "best_metric": 2.9358365535736084, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.021088704362725714, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0004217740872545143, | |
| "grad_norm": 0.8324286937713623, | |
| "learning_rate": 5e-05, | |
| "loss": 3.2017, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0004217740872545143, | |
| "eval_loss": 3.472999334335327, | |
| "eval_runtime": 16.679, | |
| "eval_samples_per_second": 957.67, | |
| "eval_steps_per_second": 119.731, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0008435481745090286, | |
| "grad_norm": 0.8818132877349854, | |
| "learning_rate": 0.0001, | |
| "loss": 3.1734, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0012653222617635428, | |
| "grad_norm": 0.8758675456047058, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 3.1582, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0016870963490180572, | |
| "grad_norm": 0.8394220471382141, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 3.1616, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0021088704362725716, | |
| "grad_norm": 0.7973480224609375, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 3.1463, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0025306445235270857, | |
| "grad_norm": 0.7849558591842651, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 3.1726, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0029524186107816003, | |
| "grad_norm": 0.7341298460960388, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 3.1508, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0033741926980361144, | |
| "grad_norm": 0.7489524483680725, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 3.2076, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0037959667852906285, | |
| "grad_norm": 0.7985512614250183, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 3.2566, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.004217740872545143, | |
| "grad_norm": 0.9550576210021973, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 3.3, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.004639514959799657, | |
| "grad_norm": 1.1436842679977417, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 3.5108, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.005061289047054171, | |
| "grad_norm": 1.5524193048477173, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 3.7296, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0054830631343086855, | |
| "grad_norm": 0.8335721492767334, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 3.173, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0059048372215632005, | |
| "grad_norm": 0.6035977602005005, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 3.0286, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.006326611308817715, | |
| "grad_norm": 0.5597878694534302, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 2.9801, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.006748385396072229, | |
| "grad_norm": 0.6098695993423462, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 2.9878, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.007170159483326743, | |
| "grad_norm": 0.5748940110206604, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 3.0225, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.007591933570581257, | |
| "grad_norm": 0.5988448262214661, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 2.9493, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.008013707657835772, | |
| "grad_norm": 0.6316302418708801, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 2.9329, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.008435481745090286, | |
| "grad_norm": 0.6827861070632935, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 2.8969, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0088572558323448, | |
| "grad_norm": 0.7063604593276978, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 2.9683, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.009279029919599315, | |
| "grad_norm": 0.8146556615829468, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 3.056, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.009700804006853829, | |
| "grad_norm": 1.012282133102417, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 3.1182, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.010122578094108343, | |
| "grad_norm": 1.3914183378219604, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 3.2075, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.010544352181362857, | |
| "grad_norm": 2.2603302001953125, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 3.6382, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.010544352181362857, | |
| "eval_loss": 3.039661407470703, | |
| "eval_runtime": 16.675, | |
| "eval_samples_per_second": 957.9, | |
| "eval_steps_per_second": 119.76, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.010966126268617371, | |
| "grad_norm": 0.6945227980613708, | |
| "learning_rate": 5e-05, | |
| "loss": 3.0267, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.011387900355871887, | |
| "grad_norm": 0.5000008344650269, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 2.9196, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.011809674443126401, | |
| "grad_norm": 0.5593349933624268, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 2.9161, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.012231448530380915, | |
| "grad_norm": 0.5635783672332764, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 2.8508, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.01265322261763543, | |
| "grad_norm": 0.5942121744155884, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 2.8305, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.013074996704889943, | |
| "grad_norm": 0.6179705858230591, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 2.9744, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.013496770792144458, | |
| "grad_norm": 0.6652650237083435, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 2.8616, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.013918544879398972, | |
| "grad_norm": 0.7393981218338013, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 2.8417, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.014340318966653486, | |
| "grad_norm": 0.8105101585388184, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 2.884, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.014762093053908, | |
| "grad_norm": 0.9532318115234375, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 2.9122, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.015183867141162514, | |
| "grad_norm": 1.1143500804901123, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 3.0373, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.015605641228417028, | |
| "grad_norm": 1.7676771879196167, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 3.1322, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.016027415315671544, | |
| "grad_norm": 0.8338384628295898, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 3.1115, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.016449189402926057, | |
| "grad_norm": 0.7096328735351562, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 2.9343, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.016870963490180572, | |
| "grad_norm": 0.6258676052093506, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 2.9199, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.017292737577435085, | |
| "grad_norm": 0.6693423986434937, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 2.9096, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.0177145116646896, | |
| "grad_norm": 0.6548720598220825, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 2.8909, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.018136285751944117, | |
| "grad_norm": 0.6232032179832458, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 2.8113, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.01855805983919863, | |
| "grad_norm": 0.635509729385376, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 2.833, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.018979833926453145, | |
| "grad_norm": 0.6656838655471802, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 2.8582, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.019401608013707657, | |
| "grad_norm": 0.6782405972480774, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 2.8453, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.019823382100962173, | |
| "grad_norm": 0.7922999858856201, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 2.8731, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.020245156188216686, | |
| "grad_norm": 1.054076075553894, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 2.9465, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.0206669302754712, | |
| "grad_norm": 1.4955496788024902, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 3.024, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.021088704362725714, | |
| "grad_norm": 2.4454047679901123, | |
| "learning_rate": 0.0, | |
| "loss": 3.3793, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.021088704362725714, | |
| "eval_loss": 2.9358365535736084, | |
| "eval_runtime": 16.702, | |
| "eval_samples_per_second": 956.35, | |
| "eval_steps_per_second": 119.566, | |
| "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 | |
| } | |