| { | |
| "best_metric": NaN, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.049431537320810674, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0009886307464162135, | |
| "grad_norm": NaN, | |
| "learning_rate": 2e-05, | |
| "loss": 0.0, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0009886307464162135, | |
| "eval_loss": NaN, | |
| "eval_runtime": 1.5464, | |
| "eval_samples_per_second": 32.333, | |
| "eval_steps_per_second": 8.407, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.001977261492832427, | |
| "grad_norm": NaN, | |
| "learning_rate": 4e-05, | |
| "loss": 0.0, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.002965892239248641, | |
| "grad_norm": NaN, | |
| "learning_rate": 6e-05, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.003954522985664854, | |
| "grad_norm": NaN, | |
| "learning_rate": 8e-05, | |
| "loss": 0.0, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.004943153732081068, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.005931784478497282, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.997539658034168e-05, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.006920415224913495, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.990161322484486e-05, | |
| "loss": 0.0, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.007909045971329708, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.977873061452552e-05, | |
| "loss": 0.0, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.008897676717745922, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.96068831197139e-05, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.009886307464162136, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.938625865312251e-05, | |
| "loss": 0.0, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.010874938210578349, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.911709846436641e-05, | |
| "loss": 0.0, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.011863568956994563, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.879969687616027e-05, | |
| "loss": 0.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.012852199703410776, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.84344009624807e-05, | |
| "loss": 0.0, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.01384083044982699, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.80216101690461e-05, | |
| "loss": 0.0, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.014829461196243203, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.756177587652856e-05, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.015818091942659415, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.705540090697575e-05, | |
| "loss": 0.0, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.01680672268907563, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.650303897398232e-05, | |
| "loss": 0.0, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.017795353435491844, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.590529407721231e-05, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.018783984181908058, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.526281984193436e-05, | |
| "loss": 0.0, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.019772614928324272, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.4576318804292e-05, | |
| "loss": 0.0, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.020761245674740483, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.384654164309083e-05, | |
| "loss": 0.0, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.021749876421156698, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.30742863589421e-05, | |
| "loss": 0.0, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.022738507167572912, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.226039740166091e-05, | |
| "loss": 0.0, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.023727137913989126, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.140576474687264e-05, | |
| "loss": 0.0, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.024715768660405337, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.051132292283771e-05, | |
| "loss": 0.0, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.024715768660405337, | |
| "eval_loss": NaN, | |
| "eval_runtime": 1.5443, | |
| "eval_samples_per_second": 32.378, | |
| "eval_steps_per_second": 8.418, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.02570439940682155, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.957804998855866e-05, | |
| "loss": 0.0, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.026693030153237766, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.860696646428693e-05, | |
| "loss": 0.0, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.02768166089965398, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.759913421559902e-05, | |
| "loss": 0.0, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.028670291646070194, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.655565529226198e-05, | |
| "loss": 0.0, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.029658922392486405, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.547767072315835e-05, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.03064755313890262, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.436635926858759e-05, | |
| "loss": 0.0, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.03163618388531883, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.322293613130917e-05, | |
| "loss": 0.0, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.03262481463173505, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.204865162773613e-05, | |
| "loss": 0.0, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.03361344537815126, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.084478982073247e-05, | |
| "loss": 0.0, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.03460207612456748, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.961266711550922e-05, | |
| "loss": 0.0, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.03559070687098369, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.835363082015468e-05, | |
| "loss": 0.0, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.0365793376173999, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.706905767237288e-05, | |
| "loss": 0.0, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.037567968363816116, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.576035233404096e-05, | |
| "loss": 0.0, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.03855659911023233, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.442894585523218e-05, | |
| "loss": 0.0, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.039545229856648545, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.307629410938363e-05, | |
| "loss": 0.0, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.040533860603064756, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.170387620131993e-05, | |
| "loss": 0.0, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.04152249134948097, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.031319284987394e-05, | |
| "loss": 0.0, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.042511122095897184, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.890576474687263e-05, | |
| "loss": 0.0, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.043499752842313395, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.7483130894283e-05, | |
| "loss": 0.0, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.044488383588729606, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.604684692133597e-05, | |
| "loss": 0.0, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.045477014335145824, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.459848338346861e-05, | |
| "loss": 0.0, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.046465645081562035, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.313962404494496e-05, | |
| "loss": 0.0, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.04745427582797825, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.167186414703289e-05, | |
| "loss": 0.0, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.04844290657439446, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.019680866363139e-05, | |
| "loss": 0.0, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.049431537320810674, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.8716070546254966e-05, | |
| "loss": 0.0, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.049431537320810674, | |
| "eval_loss": NaN, | |
| "eval_runtime": 1.5438, | |
| "eval_samples_per_second": 32.388, | |
| "eval_steps_per_second": 8.421, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 100, | |
| "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": 1 | |
| } | |
| }, | |
| "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": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |