| { | |
| "best_metric": 1.14642333984375, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 1.238390092879257, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.02476780185758514, | |
| "grad_norm": 1.5567643642425537, | |
| "learning_rate": 5e-05, | |
| "loss": 2.4093, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.02476780185758514, | |
| "eval_loss": 3.8088037967681885, | |
| "eval_runtime": 16.3639, | |
| "eval_samples_per_second": 16.622, | |
| "eval_steps_per_second": 2.078, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.04953560371517028, | |
| "grad_norm": 1.7001776695251465, | |
| "learning_rate": 0.0001, | |
| "loss": 2.7304, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.07430340557275542, | |
| "grad_norm": 2.0244216918945312, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 2.8004, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.09907120743034056, | |
| "grad_norm": 2.3656935691833496, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 2.6717, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.1238390092879257, | |
| "grad_norm": 2.6279189586639404, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 2.486, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.14860681114551083, | |
| "grad_norm": 2.033820152282715, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 2.3143, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.17337461300309598, | |
| "grad_norm": 2.15220308303833, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 2.3976, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.19814241486068113, | |
| "grad_norm": 2.7350785732269287, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 2.5891, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.22291021671826625, | |
| "grad_norm": 1.8252304792404175, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 2.3274, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.2476780185758514, | |
| "grad_norm": 2.6998770236968994, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 2.7403, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.2724458204334365, | |
| "grad_norm": 3.823732376098633, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 1.8616, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.29721362229102166, | |
| "grad_norm": 2.2144265174865723, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 1.7375, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.3219814241486068, | |
| "grad_norm": 1.5439705848693848, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 1.6853, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.34674922600619196, | |
| "grad_norm": 1.3234962224960327, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 1.7415, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.3715170278637771, | |
| "grad_norm": 1.3904688358306885, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 1.7179, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.39628482972136225, | |
| "grad_norm": 1.4416464567184448, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 1.7285, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.42105263157894735, | |
| "grad_norm": 1.3631139993667603, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 1.6478, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.4458204334365325, | |
| "grad_norm": 1.7176153659820557, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 1.9136, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.47058823529411764, | |
| "grad_norm": 1.8204848766326904, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 1.8961, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.4953560371517028, | |
| "grad_norm": 2.9093120098114014, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 2.2933, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.5201238390092879, | |
| "grad_norm": 1.9117921590805054, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 1.3674, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.544891640866873, | |
| "grad_norm": 1.6246362924575806, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 1.306, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.5696594427244582, | |
| "grad_norm": 1.3756625652313232, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 1.3042, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.5944272445820433, | |
| "grad_norm": 1.339489459991455, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 1.302, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.6191950464396285, | |
| "grad_norm": 1.3221358060836792, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 1.4083, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.6191950464396285, | |
| "eval_loss": 1.4920990467071533, | |
| "eval_runtime": 16.3444, | |
| "eval_samples_per_second": 16.642, | |
| "eval_steps_per_second": 2.08, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.6439628482972136, | |
| "grad_norm": 1.4375908374786377, | |
| "learning_rate": 5e-05, | |
| "loss": 1.3052, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.6687306501547987, | |
| "grad_norm": 1.6213889122009277, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 1.5831, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.6934984520123839, | |
| "grad_norm": 1.6705217361450195, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 1.3199, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.718266253869969, | |
| "grad_norm": 1.8949580192565918, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 1.3975, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.7430340557275542, | |
| "grad_norm": 2.545088291168213, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 1.6941, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.7678018575851393, | |
| "grad_norm": 1.6592068672180176, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 1.2374, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.7925696594427245, | |
| "grad_norm": 1.3235689401626587, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 1.2425, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.8173374613003096, | |
| "grad_norm": 1.3531960248947144, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 1.0226, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.8421052631578947, | |
| "grad_norm": 1.3992116451263428, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 1.009, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.8668730650154799, | |
| "grad_norm": 1.4692587852478027, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 1.2067, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.891640866873065, | |
| "grad_norm": 1.4496288299560547, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 1.065, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.9164086687306502, | |
| "grad_norm": 1.6986883878707886, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 1.3435, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.9411764705882353, | |
| "grad_norm": 1.7336461544036865, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 1.0844, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.9659442724458205, | |
| "grad_norm": 2.353813886642456, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 1.4309, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.9907120743034056, | |
| "grad_norm": 2.4746670722961426, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 1.4469, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.0154798761609907, | |
| "grad_norm": 2.405529499053955, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 1.8413, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 1.0402476780185759, | |
| "grad_norm": 1.1980689764022827, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 0.9997, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 1.065015479876161, | |
| "grad_norm": 1.176184058189392, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 0.9265, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 1.089783281733746, | |
| "grad_norm": 1.2744024991989136, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.8837, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 1.1145510835913313, | |
| "grad_norm": 1.2227189540863037, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 0.8724, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 1.1393188854489165, | |
| "grad_norm": 1.2973285913467407, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 0.8306, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 1.1640866873065017, | |
| "grad_norm": 1.4821503162384033, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 1.0709, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 1.1888544891640866, | |
| "grad_norm": 1.5012022256851196, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 0.9295, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 1.2136222910216719, | |
| "grad_norm": 1.8078975677490234, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 1.0632, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 1.238390092879257, | |
| "grad_norm": 2.235991954803467, | |
| "learning_rate": 0.0, | |
| "loss": 1.1633, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.238390092879257, | |
| "eval_loss": 1.14642333984375, | |
| "eval_runtime": 15.6309, | |
| "eval_samples_per_second": 17.401, | |
| "eval_steps_per_second": 2.175, | |
| "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 | |
| } | |