| { | |
| "best_metric": 1.6321067810058594, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.038834951456310676, | |
| "eval_steps": 25, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0015533980582524273, | |
| "grad_norm": 35.25758361816406, | |
| "learning_rate": 5e-05, | |
| "loss": 3.0259, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0015533980582524273, | |
| "eval_loss": 4.107137680053711, | |
| "eval_runtime": 209.9967, | |
| "eval_samples_per_second": 20.653, | |
| "eval_steps_per_second": 2.586, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0031067961165048546, | |
| "grad_norm": 36.201961517333984, | |
| "learning_rate": 0.0001, | |
| "loss": 3.322, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.004660194174757282, | |
| "grad_norm": 72.65341186523438, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 3.3622, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.006213592233009709, | |
| "grad_norm": 80.07931518554688, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 3.2321, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.007766990291262136, | |
| "grad_norm": 51.960609436035156, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 2.8344, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.009320388349514564, | |
| "grad_norm": 24.241085052490234, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 2.4333, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.01087378640776699, | |
| "grad_norm": 22.98873519897461, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 2.2032, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.012427184466019418, | |
| "grad_norm": 17.33381462097168, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 1.9328, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.013980582524271845, | |
| "grad_norm": 21.930910110473633, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 1.9503, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.015533980582524271, | |
| "grad_norm": 18.39818000793457, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 1.7156, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0170873786407767, | |
| "grad_norm": 24.997177124023438, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 1.6001, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.018640776699029128, | |
| "grad_norm": 22.53193473815918, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 1.8581, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.020194174757281552, | |
| "grad_norm": 30.289710998535156, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 2.174, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.02174757281553398, | |
| "grad_norm": 25.095487594604492, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 2.3926, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.02330097087378641, | |
| "grad_norm": 26.95841407775879, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 2.3023, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.024854368932038837, | |
| "grad_norm": 27.92445182800293, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 2.1503, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.02640776699029126, | |
| "grad_norm": 23.141477584838867, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 1.8264, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.02796116504854369, | |
| "grad_norm": 17.3289737701416, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 1.8123, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.029514563106796118, | |
| "grad_norm": 13.11138916015625, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 1.6586, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.031067961165048542, | |
| "grad_norm": 10.37010383605957, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 1.6644, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.03262135922330097, | |
| "grad_norm": 10.554218292236328, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 1.4856, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0341747572815534, | |
| "grad_norm": 10.677726745605469, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 1.4201, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.03572815533980583, | |
| "grad_norm": 12.029129028320312, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 1.2421, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.037281553398058255, | |
| "grad_norm": 12.465231895446777, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 1.4446, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.038834951456310676, | |
| "grad_norm": 24.94623565673828, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 1.9841, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.038834951456310676, | |
| "eval_loss": 1.6321067810058594, | |
| "eval_runtime": 210.2155, | |
| "eval_samples_per_second": 20.631, | |
| "eval_steps_per_second": 2.583, | |
| "step": 25 | |
| } | |
| ], | |
| "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": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 5.476375360176128e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |