| { | |
| "best_metric": 0.7112417817115784, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.014154281670205236, | |
| "eval_steps": 5, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0005661712668082095, | |
| "grad_norm": 6.893179416656494, | |
| "learning_rate": 2e-05, | |
| "loss": 9.7345, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0005661712668082095, | |
| "eval_loss": 2.4691267013549805, | |
| "eval_runtime": 66.9785, | |
| "eval_samples_per_second": 11.108, | |
| "eval_steps_per_second": 5.554, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.001132342533616419, | |
| "grad_norm": 7.401860237121582, | |
| "learning_rate": 4e-05, | |
| "loss": 9.7301, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0016985138004246285, | |
| "grad_norm": 6.326348781585693, | |
| "learning_rate": 6e-05, | |
| "loss": 9.7752, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.002264685067232838, | |
| "grad_norm": 7.359543323516846, | |
| "learning_rate": 8e-05, | |
| "loss": 9.7648, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0028308563340410475, | |
| "grad_norm": 5.7005534172058105, | |
| "learning_rate": 0.0001, | |
| "loss": 9.771, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0028308563340410475, | |
| "eval_loss": 2.268273115158081, | |
| "eval_runtime": 65.8811, | |
| "eval_samples_per_second": 11.293, | |
| "eval_steps_per_second": 5.647, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.003397027600849257, | |
| "grad_norm": 5.248284339904785, | |
| "learning_rate": 0.00012, | |
| "loss": 9.2951, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.003963198867657466, | |
| "grad_norm": 5.4823479652404785, | |
| "learning_rate": 0.00014, | |
| "loss": 8.897, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.004529370134465676, | |
| "grad_norm": 4.635613918304443, | |
| "learning_rate": 0.00016, | |
| "loss": 9.3992, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.005095541401273885, | |
| "grad_norm": 4.913173198699951, | |
| "learning_rate": 0.00018, | |
| "loss": 8.5348, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.005661712668082095, | |
| "grad_norm": 5.657349109649658, | |
| "learning_rate": 0.0002, | |
| "loss": 7.9999, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.005661712668082095, | |
| "eval_loss": 1.7862831354141235, | |
| "eval_runtime": 68.8635, | |
| "eval_samples_per_second": 10.804, | |
| "eval_steps_per_second": 5.402, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.006227883934890304, | |
| "grad_norm": 5.412608623504639, | |
| "learning_rate": 0.00019781476007338058, | |
| "loss": 7.4962, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.006794055201698514, | |
| "grad_norm": 5.102894306182861, | |
| "learning_rate": 0.0001913545457642601, | |
| "loss": 6.8861, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.007360226468506723, | |
| "grad_norm": 5.137663841247559, | |
| "learning_rate": 0.00018090169943749476, | |
| "loss": 6.1707, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.007926397735314932, | |
| "grad_norm": 5.414005279541016, | |
| "learning_rate": 0.00016691306063588583, | |
| "loss": 5.8843, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.008492569002123142, | |
| "grad_norm": 5.985206604003906, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 5.6437, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.008492569002123142, | |
| "eval_loss": 1.1910098791122437, | |
| "eval_runtime": 64.8249, | |
| "eval_samples_per_second": 11.477, | |
| "eval_steps_per_second": 5.739, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.009058740268931352, | |
| "grad_norm": 5.626407623291016, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 5.4147, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.009624911535739562, | |
| "grad_norm": 7.213871002197266, | |
| "learning_rate": 0.00011045284632676536, | |
| "loss": 4.4015, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.01019108280254777, | |
| "grad_norm": 8.790801048278809, | |
| "learning_rate": 8.954715367323468e-05, | |
| "loss": 4.0033, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.01075725406935598, | |
| "grad_norm": 8.310179710388184, | |
| "learning_rate": 6.909830056250527e-05, | |
| "loss": 3.6232, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.01132342533616419, | |
| "grad_norm": 7.666447162628174, | |
| "learning_rate": 5.000000000000002e-05, | |
| "loss": 4.209, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.01132342533616419, | |
| "eval_loss": 0.7890741229057312, | |
| "eval_runtime": 70.6274, | |
| "eval_samples_per_second": 10.534, | |
| "eval_steps_per_second": 5.267, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0118895966029724, | |
| "grad_norm": 7.1569929122924805, | |
| "learning_rate": 3.308693936411421e-05, | |
| "loss": 3.4385, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.012455767869780608, | |
| "grad_norm": 6.962759494781494, | |
| "learning_rate": 1.9098300562505266e-05, | |
| "loss": 3.2144, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.013021939136588818, | |
| "grad_norm": 6.44915246963501, | |
| "learning_rate": 8.645454235739903e-06, | |
| "loss": 3.2704, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.013588110403397028, | |
| "grad_norm": 6.162975788116455, | |
| "learning_rate": 2.1852399266194314e-06, | |
| "loss": 4.0834, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.014154281670205236, | |
| "grad_norm": 6.5062994956970215, | |
| "learning_rate": 0.0, | |
| "loss": 2.7477, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.014154281670205236, | |
| "eval_loss": 0.7112417817115784, | |
| "eval_runtime": 73.5084, | |
| "eval_samples_per_second": 10.121, | |
| "eval_steps_per_second": 5.061, | |
| "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": 769321529769984.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |