| { | |
| "best_metric": 1.7265019416809082, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.0052999788000848, | |
| "eval_steps": 5, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00021199915200339198, | |
| "grad_norm": 1.0395910739898682, | |
| "learning_rate": 1e-05, | |
| "loss": 2.2386, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00021199915200339198, | |
| "eval_loss": 2.108657121658325, | |
| "eval_runtime": 276.9162, | |
| "eval_samples_per_second": 7.175, | |
| "eval_steps_per_second": 3.59, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00042399830400678397, | |
| "grad_norm": 1.0399056673049927, | |
| "learning_rate": 2e-05, | |
| "loss": 2.3599, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0006359974560101759, | |
| "grad_norm": 1.052390694618225, | |
| "learning_rate": 3e-05, | |
| "loss": 2.1135, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0008479966080135679, | |
| "grad_norm": 1.0873916149139404, | |
| "learning_rate": 4e-05, | |
| "loss": 1.9912, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.00105999576001696, | |
| "grad_norm": 1.0538489818572998, | |
| "learning_rate": 5e-05, | |
| "loss": 2.2384, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00105999576001696, | |
| "eval_loss": 2.0780763626098633, | |
| "eval_runtime": 278.1139, | |
| "eval_samples_per_second": 7.145, | |
| "eval_steps_per_second": 3.574, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0012719949120203519, | |
| "grad_norm": 0.9845679998397827, | |
| "learning_rate": 6e-05, | |
| "loss": 2.0122, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.001483994064023744, | |
| "grad_norm": 0.9107600450515747, | |
| "learning_rate": 7e-05, | |
| "loss": 1.9534, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0016959932160271359, | |
| "grad_norm": 0.9601123929023743, | |
| "learning_rate": 8e-05, | |
| "loss": 1.6085, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0019079923680305278, | |
| "grad_norm": 0.7956514954566956, | |
| "learning_rate": 9e-05, | |
| "loss": 2.171, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.00211999152003392, | |
| "grad_norm": 0.6652023196220398, | |
| "learning_rate": 0.0001, | |
| "loss": 1.9525, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.00211999152003392, | |
| "eval_loss": 1.8938112258911133, | |
| "eval_runtime": 278.2742, | |
| "eval_samples_per_second": 7.14, | |
| "eval_steps_per_second": 3.572, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.002331990672037312, | |
| "grad_norm": 0.7144079208374023, | |
| "learning_rate": 9.890738003669029e-05, | |
| "loss": 1.7174, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0025439898240407037, | |
| "grad_norm": 0.8546844720840454, | |
| "learning_rate": 9.567727288213005e-05, | |
| "loss": 1.903, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.002755988976044096, | |
| "grad_norm": 0.8503435254096985, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 2.1831, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.002967988128047488, | |
| "grad_norm": 1.2312841415405273, | |
| "learning_rate": 8.345653031794292e-05, | |
| "loss": 1.8006, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0031799872800508796, | |
| "grad_norm": 0.9335196018218994, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 1.74, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0031799872800508796, | |
| "eval_loss": 1.8009980916976929, | |
| "eval_runtime": 279.0929, | |
| "eval_samples_per_second": 7.119, | |
| "eval_steps_per_second": 3.562, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0033919864320542717, | |
| "grad_norm": 1.0158390998840332, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 2.1792, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.003603985584057664, | |
| "grad_norm": 0.8165982365608215, | |
| "learning_rate": 5.522642316338268e-05, | |
| "loss": 1.6872, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.0038159847360610556, | |
| "grad_norm": 0.8424365520477295, | |
| "learning_rate": 4.477357683661734e-05, | |
| "loss": 1.8862, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.004027983888064448, | |
| "grad_norm": 0.8149735331535339, | |
| "learning_rate": 3.4549150281252636e-05, | |
| "loss": 1.6499, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.00423998304006784, | |
| "grad_norm": 0.8468019962310791, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 1.816, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.00423998304006784, | |
| "eval_loss": 1.739220380783081, | |
| "eval_runtime": 281.1808, | |
| "eval_samples_per_second": 7.067, | |
| "eval_steps_per_second": 3.535, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0044519821920712315, | |
| "grad_norm": 0.87850421667099, | |
| "learning_rate": 1.6543469682057106e-05, | |
| "loss": 1.7883, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.004663981344074624, | |
| "grad_norm": 0.8680698871612549, | |
| "learning_rate": 9.549150281252633e-06, | |
| "loss": 1.4036, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.004875980496078016, | |
| "grad_norm": 0.7863142490386963, | |
| "learning_rate": 4.322727117869951e-06, | |
| "loss": 1.8092, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.005087979648081407, | |
| "grad_norm": 0.7802051305770874, | |
| "learning_rate": 1.0926199633097157e-06, | |
| "loss": 1.7099, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0052999788000848, | |
| "grad_norm": 0.744226336479187, | |
| "learning_rate": 0.0, | |
| "loss": 1.5709, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0052999788000848, | |
| "eval_loss": 1.7265019416809082, | |
| "eval_runtime": 281.6034, | |
| "eval_samples_per_second": 7.056, | |
| "eval_steps_per_second": 3.53, | |
| "step": 25 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 25, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 10, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 2, | |
| "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": 2500486653542400.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |