| { | |
| "best_metric": 2.2831292152404785, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 2.4691358024691357, | |
| "eval_steps": 25, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.09876543209876543, | |
| "grad_norm": 14.623797416687012, | |
| "learning_rate": 5e-05, | |
| "loss": 7.5337, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.09876543209876543, | |
| "eval_loss": 10.742631912231445, | |
| "eval_runtime": 5.2829, | |
| "eval_samples_per_second": 12.872, | |
| "eval_steps_per_second": 1.704, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.19753086419753085, | |
| "grad_norm": 27.85564422607422, | |
| "learning_rate": 0.0001, | |
| "loss": 10.5036, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.2962962962962963, | |
| "grad_norm": 12.45125961303711, | |
| "learning_rate": 9.970689785771798e-05, | |
| "loss": 6.7979, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.3950617283950617, | |
| "grad_norm": 12.469840049743652, | |
| "learning_rate": 9.883102778550434e-05, | |
| "loss": 5.1353, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.49382716049382713, | |
| "grad_norm": 15.238787651062012, | |
| "learning_rate": 9.738265855914013e-05, | |
| "loss": 5.5656, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.5925925925925926, | |
| "grad_norm": 10.915773391723633, | |
| "learning_rate": 9.537877098354786e-05, | |
| "loss": 3.8511, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.691358024691358, | |
| "grad_norm": 8.755463600158691, | |
| "learning_rate": 9.284285880837946e-05, | |
| "loss": 3.4919, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.7901234567901234, | |
| "grad_norm": 8.051730155944824, | |
| "learning_rate": 8.980465328528219e-05, | |
| "loss": 3.0887, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.8888888888888888, | |
| "grad_norm": 9.991663932800293, | |
| "learning_rate": 8.629977459615655e-05, | |
| "loss": 2.9206, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.9876543209876543, | |
| "grad_norm": 20.298383712768555, | |
| "learning_rate": 8.236931423909138e-05, | |
| "loss": 3.5936, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 1.0864197530864197, | |
| "grad_norm": 10.432004928588867, | |
| "learning_rate": 7.805935326811912e-05, | |
| "loss": 3.9563, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 1.1851851851851851, | |
| "grad_norm": 10.243212699890137, | |
| "learning_rate": 7.342042203498951e-05, | |
| "loss": 2.5073, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 1.2839506172839505, | |
| "grad_norm": 4.740253448486328, | |
| "learning_rate": 6.850690776699573e-05, | |
| "loss": 2.2223, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 1.382716049382716, | |
| "grad_norm": 7.063598155975342, | |
| "learning_rate": 6.337641692646106e-05, | |
| "loss": 2.3266, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 1.4814814814814814, | |
| "grad_norm": 14.406518936157227, | |
| "learning_rate": 5.808909982763825e-05, | |
| "loss": 3.1728, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 1.5802469135802468, | |
| "grad_norm": 4.407171726226807, | |
| "learning_rate": 5.270694542927088e-05, | |
| "loss": 1.9873, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 1.6790123456790123, | |
| "grad_norm": 6.828210830688477, | |
| "learning_rate": 4.729305457072913e-05, | |
| "loss": 2.0366, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 1.7777777777777777, | |
| "grad_norm": 4.3996453285217285, | |
| "learning_rate": 4.1910900172361764e-05, | |
| "loss": 1.7066, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 1.876543209876543, | |
| "grad_norm": 7.602293014526367, | |
| "learning_rate": 3.6623583073538966e-05, | |
| "loss": 2.0355, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 1.9753086419753085, | |
| "grad_norm": 13.495161056518555, | |
| "learning_rate": 3.149309223300428e-05, | |
| "loss": 2.7242, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 2.074074074074074, | |
| "grad_norm": 7.631489276885986, | |
| "learning_rate": 2.65795779650105e-05, | |
| "loss": 2.8692, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 2.1728395061728394, | |
| "grad_norm": 6.936291694641113, | |
| "learning_rate": 2.194064673188089e-05, | |
| "loss": 1.9845, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 2.271604938271605, | |
| "grad_norm": 3.4804110527038574, | |
| "learning_rate": 1.7630685760908622e-05, | |
| "loss": 1.3974, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 2.3703703703703702, | |
| "grad_norm": 7.088866710662842, | |
| "learning_rate": 1.3700225403843469e-05, | |
| "loss": 1.7832, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 2.4691358024691357, | |
| "grad_norm": 9.134029388427734, | |
| "learning_rate": 1.0195346714717813e-05, | |
| "loss": 2.3225, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 2.4691358024691357, | |
| "eval_loss": 2.2831292152404785, | |
| "eval_runtime": 5.2633, | |
| "eval_samples_per_second": 12.92, | |
| "eval_steps_per_second": 1.71, | |
| "step": 25 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 31, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 4, | |
| "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": 3.087239672233984e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |