| { | |
| "best_metric": 2.6402525901794434, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.22234574763757642, | |
| "eval_steps": 25, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.008893829905503057, | |
| "grad_norm": 1.4854580163955688, | |
| "learning_rate": 5e-05, | |
| "loss": 2.58, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.008893829905503057, | |
| "eval_loss": 4.211630344390869, | |
| "eval_runtime": 16.9627, | |
| "eval_samples_per_second": 2.948, | |
| "eval_steps_per_second": 2.948, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.017787659811006114, | |
| "grad_norm": 1.8155322074890137, | |
| "learning_rate": 0.0001, | |
| "loss": 2.8506, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.02668148971650917, | |
| "grad_norm": 2.220613718032837, | |
| "learning_rate": 9.958086757163489e-05, | |
| "loss": 2.9532, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.03557531962201223, | |
| "grad_norm": 2.076958417892456, | |
| "learning_rate": 9.833127793065098e-05, | |
| "loss": 2.7264, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.04446914952751529, | |
| "grad_norm": 1.6866787672042847, | |
| "learning_rate": 9.627450856774539e-05, | |
| "loss": 2.5685, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.05336297943301834, | |
| "grad_norm": 1.7478476762771606, | |
| "learning_rate": 9.3448873204592e-05, | |
| "loss": 2.5841, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0622568093385214, | |
| "grad_norm": 1.7968357801437378, | |
| "learning_rate": 8.990700808169889e-05, | |
| "loss": 2.4804, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.07115063924402446, | |
| "grad_norm": 1.6409025192260742, | |
| "learning_rate": 8.571489144483944e-05, | |
| "loss": 2.6395, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.08004446914952751, | |
| "grad_norm": 1.6168807744979858, | |
| "learning_rate": 8.095061449516903e-05, | |
| "loss": 2.6339, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.08893829905503058, | |
| "grad_norm": 1.5214190483093262, | |
| "learning_rate": 7.570292669790186e-05, | |
| "loss": 2.5538, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.09783212896053363, | |
| "grad_norm": 1.4928462505340576, | |
| "learning_rate": 7.006958254769438e-05, | |
| "loss": 2.4553, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.10672595886603668, | |
| "grad_norm": 1.6804851293563843, | |
| "learning_rate": 6.415552058736854e-05, | |
| "loss": 2.4081, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.11561978877153975, | |
| "grad_norm": 1.585455298423767, | |
| "learning_rate": 5.80709086014102e-05, | |
| "loss": 2.597, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.1245136186770428, | |
| "grad_norm": 1.6967554092407227, | |
| "learning_rate": 5.192909139858981e-05, | |
| "loss": 2.6732, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.13340744858254586, | |
| "grad_norm": 1.7670717239379883, | |
| "learning_rate": 4.584447941263149e-05, | |
| "loss": 2.773, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.1423012784880489, | |
| "grad_norm": 1.6136687994003296, | |
| "learning_rate": 3.9930417452305626e-05, | |
| "loss": 2.4929, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.15119510839355196, | |
| "grad_norm": 1.942365050315857, | |
| "learning_rate": 3.4297073302098156e-05, | |
| "loss": 2.67, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.16008893829905502, | |
| "grad_norm": 1.76591157913208, | |
| "learning_rate": 2.9049385504830985e-05, | |
| "loss": 2.6515, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.1689827682045581, | |
| "grad_norm": 1.619162678718567, | |
| "learning_rate": 2.4285108555160577e-05, | |
| "loss": 2.4974, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.17787659811006115, | |
| "grad_norm": 2.186659574508667, | |
| "learning_rate": 2.0092991918301108e-05, | |
| "loss": 2.6227, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.1867704280155642, | |
| "grad_norm": 2.200047254562378, | |
| "learning_rate": 1.6551126795408016e-05, | |
| "loss": 2.7163, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.19566425792106726, | |
| "grad_norm": 1.962228536605835, | |
| "learning_rate": 1.3725491432254624e-05, | |
| "loss": 2.7624, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.2045580878265703, | |
| "grad_norm": 2.0700416564941406, | |
| "learning_rate": 1.1668722069349041e-05, | |
| "loss": 2.7292, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.21345191773207337, | |
| "grad_norm": 2.4603474140167236, | |
| "learning_rate": 1.0419132428365116e-05, | |
| "loss": 2.7533, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.22234574763757642, | |
| "grad_norm": 2.7518861293792725, | |
| "learning_rate": 1e-05, | |
| "loss": 3.0797, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.22234574763757642, | |
| "eval_loss": 2.6402525901794434, | |
| "eval_runtime": 17.1549, | |
| "eval_samples_per_second": 2.915, | |
| "eval_steps_per_second": 2.915, | |
| "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": 8.2892273221632e+16, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |