| { | |
| "best_metric": 0.43964827060699463, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.11818584724479243, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0023637169448958487, | |
| "grad_norm": 3.9986588954925537, | |
| "learning_rate": 5e-05, | |
| "loss": 8.3657, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0023637169448958487, | |
| "eval_loss": 8.79309368133545, | |
| "eval_runtime": 72.242, | |
| "eval_samples_per_second": 39.465, | |
| "eval_steps_per_second": 4.942, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.004727433889791697, | |
| "grad_norm": 4.219733715057373, | |
| "learning_rate": 0.0001, | |
| "loss": 8.4749, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.007091150834687547, | |
| "grad_norm": 4.131906032562256, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 8.3261, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.009454867779583395, | |
| "grad_norm": 4.116415977478027, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 7.7133, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.011818584724479244, | |
| "grad_norm": 3.9392805099487305, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 7.1149, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.014182301669375093, | |
| "grad_norm": 3.6192970275878906, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 6.5341, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.016546018614270942, | |
| "grad_norm": 3.641630172729492, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 5.7381, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.01890973555916679, | |
| "grad_norm": 3.587646961212158, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 5.7776, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.021273452504062637, | |
| "grad_norm": 3.424961566925049, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 5.5181, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.023637169448958488, | |
| "grad_norm": 3.8795056343078613, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 4.8172, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.026000886393854335, | |
| "grad_norm": 3.935875177383423, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 4.2793, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.028364603338750186, | |
| "grad_norm": 3.953155994415283, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 4.3062, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.030728320283646034, | |
| "grad_norm": 4.251803398132324, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 3.6384, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.033092037228541885, | |
| "grad_norm": 4.85849142074585, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 2.4823, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.03545575417343773, | |
| "grad_norm": 4.640942096710205, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 2.1148, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.03781947111833358, | |
| "grad_norm": 4.270336151123047, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 1.5676, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.04018318806322943, | |
| "grad_norm": 3.585779905319214, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 1.3586, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.042546905008125274, | |
| "grad_norm": 3.264014959335327, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 1.0827, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.044910621953021125, | |
| "grad_norm": 2.960775852203369, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 0.9235, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.047274338897916976, | |
| "grad_norm": 2.7268998622894287, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.9182, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.04963805584281282, | |
| "grad_norm": 2.502107858657837, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 0.8455, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.05200177278770867, | |
| "grad_norm": 2.3308205604553223, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 0.8648, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.05436548973260452, | |
| "grad_norm": 2.071208953857422, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 0.9864, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.05672920667750037, | |
| "grad_norm": 2.335949659347534, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 1.0709, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.059092923622396216, | |
| "grad_norm": 4.153835773468018, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 1.3592, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.059092923622396216, | |
| "eval_loss": 0.7349157929420471, | |
| "eval_runtime": 72.0285, | |
| "eval_samples_per_second": 39.582, | |
| "eval_steps_per_second": 4.956, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.06145664056729207, | |
| "grad_norm": 6.81027364730835, | |
| "learning_rate": 5e-05, | |
| "loss": 0.7863, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.06382035751218791, | |
| "grad_norm": 6.804386615753174, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 0.6702, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.06618407445708377, | |
| "grad_norm": 3.710777521133423, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 0.5357, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.06854779140197961, | |
| "grad_norm": 1.793501853942871, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 0.5255, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.07091150834687546, | |
| "grad_norm": 2.5684709548950195, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 0.4421, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.07327522529177131, | |
| "grad_norm": 2.64495587348938, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 0.4837, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.07563894223666716, | |
| "grad_norm": 2.0679728984832764, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.5774, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.078002659181563, | |
| "grad_norm": 2.1068263053894043, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 0.5622, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.08036637612645886, | |
| "grad_norm": 1.217808723449707, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 0.547, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.0827300930713547, | |
| "grad_norm": 1.464884877204895, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 0.6351, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.08509381001625055, | |
| "grad_norm": 2.206184148788452, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 0.7301, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.0874575269611464, | |
| "grad_norm": 2.669191837310791, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 0.7922, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.08982124390604225, | |
| "grad_norm": 1.2713346481323242, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.4818, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.0921849608509381, | |
| "grad_norm": 2.1288211345672607, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 0.4209, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.09454867779583395, | |
| "grad_norm": 2.2356045246124268, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 0.4351, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0969123947407298, | |
| "grad_norm": 1.6320451498031616, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 0.3995, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.09927611168562564, | |
| "grad_norm": 1.082404613494873, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 0.3726, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.1016398286305215, | |
| "grad_norm": 0.9784598350524902, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 0.408, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.10400354557541734, | |
| "grad_norm": 1.1016899347305298, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.401, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.1063672625203132, | |
| "grad_norm": 1.2457271814346313, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 0.5021, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.10873097946520904, | |
| "grad_norm": 1.1428277492523193, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 0.4453, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.11109469641010489, | |
| "grad_norm": 1.4190499782562256, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 0.4054, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.11345841335500075, | |
| "grad_norm": 1.0377637147903442, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 0.5298, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.11582213029989659, | |
| "grad_norm": 1.4322923421859741, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 0.5594, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.11818584724479243, | |
| "grad_norm": 2.3901617527008057, | |
| "learning_rate": 0.0, | |
| "loss": 0.5083, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.11818584724479243, | |
| "eval_loss": 0.43964827060699463, | |
| "eval_runtime": 72.0723, | |
| "eval_samples_per_second": 39.558, | |
| "eval_steps_per_second": 4.953, | |
| "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": 1.059536353886208e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |