| { | |
| "best_metric": 4.15083646774292, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.15464913976416006, | |
| "eval_steps": 25, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.006185965590566402, | |
| "grad_norm": 2.5477283000946045, | |
| "learning_rate": 5e-05, | |
| "loss": 6.6482, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.006185965590566402, | |
| "eval_loss": 7.445623397827148, | |
| "eval_runtime": 1.1521, | |
| "eval_samples_per_second": 43.398, | |
| "eval_steps_per_second": 11.283, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.012371931181132804, | |
| "grad_norm": 2.552290916442871, | |
| "learning_rate": 0.0001, | |
| "loss": 6.698, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.01855789677169921, | |
| "grad_norm": 2.510174512863159, | |
| "learning_rate": 9.958086757163489e-05, | |
| "loss": 6.6771, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.02474386236226561, | |
| "grad_norm": 2.597166061401367, | |
| "learning_rate": 9.833127793065098e-05, | |
| "loss": 6.4593, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.03092982795283201, | |
| "grad_norm": 3.833125352859497, | |
| "learning_rate": 9.627450856774539e-05, | |
| "loss": 6.094, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.03711579354339842, | |
| "grad_norm": 4.519044876098633, | |
| "learning_rate": 9.3448873204592e-05, | |
| "loss": 5.9672, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.04330175913396482, | |
| "grad_norm": 4.09713888168335, | |
| "learning_rate": 8.990700808169889e-05, | |
| "loss": 5.614, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.04948772472453122, | |
| "grad_norm": 4.108787536621094, | |
| "learning_rate": 8.571489144483944e-05, | |
| "loss": 5.4328, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.05567369031509762, | |
| "grad_norm": 4.960999011993408, | |
| "learning_rate": 8.095061449516903e-05, | |
| "loss": 5.4678, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.06185965590566402, | |
| "grad_norm": 5.027029514312744, | |
| "learning_rate": 7.570292669790186e-05, | |
| "loss": 5.5436, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.06804562149623043, | |
| "grad_norm": 7.315838813781738, | |
| "learning_rate": 7.006958254769438e-05, | |
| "loss": 5.3467, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.07423158708679684, | |
| "grad_norm": 6.530706405639648, | |
| "learning_rate": 6.415552058736854e-05, | |
| "loss": 5.085, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.08041755267736324, | |
| "grad_norm": 4.7399468421936035, | |
| "learning_rate": 5.80709086014102e-05, | |
| "loss": 4.7524, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.08660351826792964, | |
| "grad_norm": 4.180176258087158, | |
| "learning_rate": 5.192909139858981e-05, | |
| "loss": 4.3949, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.09278948385849603, | |
| "grad_norm": 3.9656221866607666, | |
| "learning_rate": 4.584447941263149e-05, | |
| "loss": 4.5407, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.09897544944906243, | |
| "grad_norm": 4.055225849151611, | |
| "learning_rate": 3.9930417452305626e-05, | |
| "loss": 4.2622, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.10516141503962884, | |
| "grad_norm": 3.3067731857299805, | |
| "learning_rate": 3.4297073302098156e-05, | |
| "loss": 4.257, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.11134738063019524, | |
| "grad_norm": 3.142115831375122, | |
| "learning_rate": 2.9049385504830985e-05, | |
| "loss": 4.2038, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.11753334622076164, | |
| "grad_norm": 3.1884546279907227, | |
| "learning_rate": 2.4285108555160577e-05, | |
| "loss": 3.8296, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.12371931181132804, | |
| "grad_norm": 3.3455166816711426, | |
| "learning_rate": 2.0092991918301108e-05, | |
| "loss": 4.1016, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.12990527740189445, | |
| "grad_norm": 2.9816372394561768, | |
| "learning_rate": 1.6551126795408016e-05, | |
| "loss": 4.1039, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.13609124299246086, | |
| "grad_norm": 2.851116895675659, | |
| "learning_rate": 1.3725491432254624e-05, | |
| "loss": 4.0206, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.14227720858302725, | |
| "grad_norm": 2.5876739025115967, | |
| "learning_rate": 1.1668722069349041e-05, | |
| "loss": 4.0313, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.14846317417359367, | |
| "grad_norm": 3.046825885772705, | |
| "learning_rate": 1.0419132428365116e-05, | |
| "loss": 4.2366, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.15464913976416006, | |
| "grad_norm": 2.80592942237854, | |
| "learning_rate": 1e-05, | |
| "loss": 4.2007, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.15464913976416006, | |
| "eval_loss": 4.15083646774292, | |
| "eval_runtime": 1.1756, | |
| "eval_samples_per_second": 42.533, | |
| "eval_steps_per_second": 11.059, | |
| "step": 25 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 25, | |
| "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": 5.29768176943104e+16, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |