| { | |
| "best_metric": 0.1798376888036728, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-20", | |
| "epoch": 0.021923814743765414, | |
| "eval_steps": 5, | |
| "global_step": 20, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0010961907371882709, | |
| "grad_norm": 0.7432473301887512, | |
| "learning_rate": 2e-05, | |
| "loss": 1.3221, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0010961907371882709, | |
| "eval_loss": 0.9627979397773743, | |
| "eval_runtime": 122.6531, | |
| "eval_samples_per_second": 3.139, | |
| "eval_steps_per_second": 1.574, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0021923814743765417, | |
| "grad_norm": 1.157194972038269, | |
| "learning_rate": 4e-05, | |
| "loss": 0.8248, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.003288572211564812, | |
| "grad_norm": 0.6122922301292419, | |
| "learning_rate": 6e-05, | |
| "loss": 0.5875, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.004384762948753083, | |
| "grad_norm": 0.9995917677879333, | |
| "learning_rate": 8e-05, | |
| "loss": 0.609, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.005480953685941353, | |
| "grad_norm": 0.9849070906639099, | |
| "learning_rate": 0.0001, | |
| "loss": 0.7534, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.005480953685941353, | |
| "eval_loss": 0.8763314485549927, | |
| "eval_runtime": 119.8858, | |
| "eval_samples_per_second": 3.211, | |
| "eval_steps_per_second": 1.61, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.006577144423129624, | |
| "grad_norm": 0.7117393612861633, | |
| "learning_rate": 0.00012, | |
| "loss": 0.4431, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.007673335160317895, | |
| "grad_norm": 1.7479251623153687, | |
| "learning_rate": 0.00014, | |
| "loss": 0.6953, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.008769525897506167, | |
| "grad_norm": 0.9761279225349426, | |
| "learning_rate": 0.00016, | |
| "loss": 0.2648, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.009865716634694436, | |
| "grad_norm": 0.8875803351402283, | |
| "learning_rate": 0.00018, | |
| "loss": 1.0292, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.010961907371882707, | |
| "grad_norm": 0.708978533744812, | |
| "learning_rate": 0.0002, | |
| "loss": 0.1298, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.010961907371882707, | |
| "eval_loss": 0.30446988344192505, | |
| "eval_runtime": 118.346, | |
| "eval_samples_per_second": 3.253, | |
| "eval_steps_per_second": 1.631, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.012058098109070978, | |
| "grad_norm": 0.9388976693153381, | |
| "learning_rate": 0.00019781476007338058, | |
| "loss": 0.1843, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.013154288846259249, | |
| "grad_norm": 1.1695252656936646, | |
| "learning_rate": 0.0001913545457642601, | |
| "loss": 0.1949, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.01425047958344752, | |
| "grad_norm": 1.5253500938415527, | |
| "learning_rate": 0.00018090169943749476, | |
| "loss": 0.2296, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.01534667032063579, | |
| "grad_norm": 0.8718650937080383, | |
| "learning_rate": 0.00016691306063588583, | |
| "loss": 0.1098, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.01644286105782406, | |
| "grad_norm": 0.8161805272102356, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 0.1306, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.01644286105782406, | |
| "eval_loss": 0.20339640974998474, | |
| "eval_runtime": 117.3158, | |
| "eval_samples_per_second": 3.282, | |
| "eval_steps_per_second": 1.645, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.017539051795012334, | |
| "grad_norm": 0.4280713200569153, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 0.0685, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.018635242532200603, | |
| "grad_norm": 0.41537296772003174, | |
| "learning_rate": 0.00011045284632676536, | |
| "loss": 0.0388, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.019731433269388872, | |
| "grad_norm": 4.0038371086120605, | |
| "learning_rate": 8.954715367323468e-05, | |
| "loss": 1.7503, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.020827624006577145, | |
| "grad_norm": 0.3152463138103485, | |
| "learning_rate": 6.909830056250527e-05, | |
| "loss": 0.0241, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.021923814743765414, | |
| "grad_norm": 0.960701048374176, | |
| "learning_rate": 5.000000000000002e-05, | |
| "loss": 0.1267, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.021923814743765414, | |
| "eval_loss": 0.1798376888036728, | |
| "eval_runtime": 118.1391, | |
| "eval_samples_per_second": 3.259, | |
| "eval_steps_per_second": 1.634, | |
| "step": 20 | |
| } | |
| ], | |
| "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": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 5363736319623168.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |