| { | |
| "best_metric": 0.3359534740447998, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 2.477064220183486, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.04892966360856269, | |
| "grad_norm": 860.2722778320312, | |
| "learning_rate": 5e-05, | |
| "loss": 8.2572, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.04892966360856269, | |
| "eval_loss": 7.375894069671631, | |
| "eval_runtime": 9.3559, | |
| "eval_samples_per_second": 14.75, | |
| "eval_steps_per_second": 1.924, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.09785932721712538, | |
| "grad_norm": 805.065185546875, | |
| "learning_rate": 0.0001, | |
| "loss": 8.5249, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.14678899082568808, | |
| "grad_norm": 521.0182495117188, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 4.8112, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.19571865443425077, | |
| "grad_norm": 288.8603820800781, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 3.0428, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.24464831804281345, | |
| "grad_norm": 291.7355041503906, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 2.0672, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.29357798165137616, | |
| "grad_norm": 205.27493286132812, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 1.1652, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.3425076452599388, | |
| "grad_norm": 125.26005554199219, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 0.8289, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.39143730886850153, | |
| "grad_norm": 83.22518920898438, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.5171, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.44036697247706424, | |
| "grad_norm": 156.4967041015625, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 0.4905, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.4892966360856269, | |
| "grad_norm": 159.6315460205078, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 0.4991, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.5382262996941896, | |
| "grad_norm": 90.45294189453125, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 0.6751, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.5871559633027523, | |
| "grad_norm": 65.43336486816406, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 0.4683, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.636085626911315, | |
| "grad_norm": 73.60994720458984, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 0.448, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.6850152905198776, | |
| "grad_norm": 51.45248031616211, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.4062, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.7339449541284404, | |
| "grad_norm": 55.65335464477539, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 0.3956, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.7828746177370031, | |
| "grad_norm": 55.53349304199219, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 0.5444, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.8318042813455657, | |
| "grad_norm": 38.786128997802734, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 0.4223, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.8807339449541285, | |
| "grad_norm": 38.95067596435547, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.3362, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.9296636085626911, | |
| "grad_norm": 30.522335052490234, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 0.3267, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.9785932721712538, | |
| "grad_norm": 77.3564224243164, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.4163, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.0428134556574924, | |
| "grad_norm": 81.9765853881836, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 0.5787, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 1.091743119266055, | |
| "grad_norm": 91.37242126464844, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 0.4669, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 1.1406727828746177, | |
| "grad_norm": 53.006507873535156, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 0.3037, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 1.1896024464831805, | |
| "grad_norm": 31.78158187866211, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 0.268, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 1.238532110091743, | |
| "grad_norm": 58.46190643310547, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 0.2589, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.238532110091743, | |
| "eval_loss": 0.344561368227005, | |
| "eval_runtime": 9.3281, | |
| "eval_samples_per_second": 14.794, | |
| "eval_steps_per_second": 1.93, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.2874617737003058, | |
| "grad_norm": 73.28158569335938, | |
| "learning_rate": 5e-05, | |
| "loss": 0.5206, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 1.3363914373088686, | |
| "grad_norm": 84.08252716064453, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 0.4166, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 1.385321100917431, | |
| "grad_norm": 95.0881118774414, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 0.3284, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 1.4342507645259939, | |
| "grad_norm": 84.19164276123047, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 0.3914, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 1.4831804281345566, | |
| "grad_norm": 86.7741470336914, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 0.3869, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.5321100917431192, | |
| "grad_norm": 67.30615997314453, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 0.5661, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 1.581039755351682, | |
| "grad_norm": 38.15361404418945, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.363, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 1.6299694189602447, | |
| "grad_norm": 62.01075744628906, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 0.3029, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 1.6788990825688073, | |
| "grad_norm": 23.574642181396484, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 0.289, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 1.72782874617737, | |
| "grad_norm": 39.977779388427734, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 0.2959, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 1.7767584097859328, | |
| "grad_norm": 53.3297004699707, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 0.4495, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 1.8256880733944953, | |
| "grad_norm": 35.10194778442383, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 0.3355, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 1.8746177370030581, | |
| "grad_norm": 26.82624626159668, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.2645, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 1.9235474006116209, | |
| "grad_norm": 57.93483352661133, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 0.2688, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 1.9724770642201834, | |
| "grad_norm": 33.57123565673828, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 0.2798, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 2.036697247706422, | |
| "grad_norm": 44.15616989135742, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 0.4424, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 2.085626911314985, | |
| "grad_norm": 36.59967041015625, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 0.3808, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 2.1345565749235473, | |
| "grad_norm": 58.102577209472656, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 0.2978, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 2.18348623853211, | |
| "grad_norm": 26.42946434020996, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.2555, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 2.232415902140673, | |
| "grad_norm": 69.52690124511719, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 0.2367, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 2.2813455657492354, | |
| "grad_norm": 53.76517105102539, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 0.5083, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 2.330275229357798, | |
| "grad_norm": 37.09881591796875, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 0.3288, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 2.379204892966361, | |
| "grad_norm": 33.916202545166016, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 0.3584, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 2.4281345565749235, | |
| "grad_norm": 34.20186233520508, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 0.2662, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 2.477064220183486, | |
| "grad_norm": 34.20256805419922, | |
| "learning_rate": 0.0, | |
| "loss": 0.2307, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 2.477064220183486, | |
| "eval_loss": 0.3359534740447998, | |
| "eval_runtime": 9.3234, | |
| "eval_samples_per_second": 14.801, | |
| "eval_steps_per_second": 1.931, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "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": 5.660495239446528e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |