| { | |
| "best_metric": 0.23863911628723145, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 1.3722126929674099, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0274442538593482, | |
| "grad_norm": 19.915740966796875, | |
| "learning_rate": 5e-05, | |
| "loss": 10.4431, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0274442538593482, | |
| "eval_loss": 10.55981731414795, | |
| "eval_runtime": 16.701, | |
| "eval_samples_per_second": 14.73, | |
| "eval_steps_per_second": 1.856, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0548885077186964, | |
| "grad_norm": 20.474876403808594, | |
| "learning_rate": 0.0001, | |
| "loss": 10.4168, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0823327615780446, | |
| "grad_norm": 22.937917709350586, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 9.5155, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.1097770154373928, | |
| "grad_norm": 14.838218688964844, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 5.4029, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.137221269296741, | |
| "grad_norm": 28.438962936401367, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 3.4415, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.1646655231560892, | |
| "grad_norm": 20.646305084228516, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 2.8999, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.19210977701543738, | |
| "grad_norm": 10.955924987792969, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 1.514, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.2195540308747856, | |
| "grad_norm": 7.522963047027588, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.7446, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.2469982847341338, | |
| "grad_norm": 1.6226751804351807, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 0.37, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.274442538593482, | |
| "grad_norm": 8.978976249694824, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 0.4745, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.3018867924528302, | |
| "grad_norm": 5.780826568603516, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 0.385, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.3293310463121784, | |
| "grad_norm": 9.487486839294434, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 0.489, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.3567753001715266, | |
| "grad_norm": 9.803397178649902, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 0.5571, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.38421955403087477, | |
| "grad_norm": 6.76271390914917, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.4195, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.411663807890223, | |
| "grad_norm": 2.435741662979126, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 0.3402, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.4391080617495712, | |
| "grad_norm": 6.841069221496582, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 0.3957, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.4665523156089194, | |
| "grad_norm": 5.190651893615723, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 0.3766, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.4939965694682676, | |
| "grad_norm": 1.7494937181472778, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.3146, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.5214408233276158, | |
| "grad_norm": 4.748995304107666, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 0.3474, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.548885077186964, | |
| "grad_norm": 2.5974996089935303, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.2974, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.5763293310463122, | |
| "grad_norm": 3.3625800609588623, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 0.3052, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.6037735849056604, | |
| "grad_norm": 2.4735608100891113, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 0.2928, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.6312178387650086, | |
| "grad_norm": 3.038069009780884, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 0.3052, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.6586620926243568, | |
| "grad_norm": 2.4158358573913574, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 0.2736, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.6861063464837049, | |
| "grad_norm": 2.4881114959716797, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 0.2962, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.6861063464837049, | |
| "eval_loss": 0.3235906660556793, | |
| "eval_runtime": 16.7149, | |
| "eval_samples_per_second": 14.717, | |
| "eval_steps_per_second": 1.855, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.7135506003430532, | |
| "grad_norm": 4.143929481506348, | |
| "learning_rate": 5e-05, | |
| "loss": 0.2955, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.7409948542024014, | |
| "grad_norm": 5.077431678771973, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 0.3079, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.7684391080617495, | |
| "grad_norm": 4.211583614349365, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 0.2766, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.7958833619210978, | |
| "grad_norm": 0.8026089072227478, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 0.2658, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.823327615780446, | |
| "grad_norm": 1.9315334558486938, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 0.2468, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.8507718696397941, | |
| "grad_norm": 3.570127487182617, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 0.2819, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.8782161234991424, | |
| "grad_norm": 4.516849040985107, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.2846, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.9056603773584906, | |
| "grad_norm": 2.569342851638794, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 0.2284, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.9331046312178388, | |
| "grad_norm": 1.2318886518478394, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 0.2673, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.9605488850771869, | |
| "grad_norm": 1.3738312721252441, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 0.2403, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.9879931389365352, | |
| "grad_norm": 1.3342665433883667, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 0.2458, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 1.0154373927958833, | |
| "grad_norm": 5.593202590942383, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 0.3857, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 1.0428816466552315, | |
| "grad_norm": 3.9389874935150146, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.2243, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 1.0703259005145798, | |
| "grad_norm": 2.4002861976623535, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 0.1973, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 1.097770154373928, | |
| "grad_norm": 3.7794065475463867, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 0.2244, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.1252144082332762, | |
| "grad_norm": 1.2340718507766724, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 0.2023, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 1.1526586620926245, | |
| "grad_norm": 3.5447723865509033, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 0.2489, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 1.1801029159519725, | |
| "grad_norm": 3.310685157775879, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 0.2085, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 1.2075471698113207, | |
| "grad_norm": 2.6451849937438965, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.216, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 1.234991423670669, | |
| "grad_norm": 1.9807446002960205, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 0.2003, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 1.2624356775300172, | |
| "grad_norm": 3.840047597885132, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 0.2164, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 1.2898799313893654, | |
| "grad_norm": 1.691431999206543, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 0.1966, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 1.3173241852487134, | |
| "grad_norm": 1.0780556201934814, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 0.1978, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 1.3447684391080617, | |
| "grad_norm": 0.9177170991897583, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 0.2139, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 1.3722126929674099, | |
| "grad_norm": 2.2063517570495605, | |
| "learning_rate": 0.0, | |
| "loss": 0.2283, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.3722126929674099, | |
| "eval_loss": 0.23863911628723145, | |
| "eval_runtime": 16.7064, | |
| "eval_samples_per_second": 14.725, | |
| "eval_steps_per_second": 1.856, | |
| "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": 5.968083617316864e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |