| { | |
| "best_metric": NaN, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-10", | |
| "epoch": 0.008407777193904361, | |
| "eval_steps": 5, | |
| "global_step": 20, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00042038885969521806, | |
| "grad_norm": NaN, | |
| "learning_rate": 2e-05, | |
| "loss": 0.0, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00042038885969521806, | |
| "eval_loss": NaN, | |
| "eval_runtime": 239.3183, | |
| "eval_samples_per_second": 4.187, | |
| "eval_steps_per_second": 2.093, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0008407777193904361, | |
| "grad_norm": NaN, | |
| "learning_rate": 4e-05, | |
| "loss": 0.0, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0012611665790856542, | |
| "grad_norm": NaN, | |
| "learning_rate": 6e-05, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0016815554387808723, | |
| "grad_norm": NaN, | |
| "learning_rate": 8e-05, | |
| "loss": 0.0, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0021019442984760903, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0021019442984760903, | |
| "eval_loss": NaN, | |
| "eval_runtime": 232.6067, | |
| "eval_samples_per_second": 4.308, | |
| "eval_steps_per_second": 2.154, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0025223331581713084, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00012, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0029427220178665264, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00014, | |
| "loss": 0.0, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0033631108775617445, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00016, | |
| "loss": 0.0, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0037834997372569626, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00018, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.004203888596952181, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.004203888596952181, | |
| "eval_loss": NaN, | |
| "eval_runtime": 233.6373, | |
| "eval_samples_per_second": 4.289, | |
| "eval_steps_per_second": 2.144, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.004624277456647399, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019781476007338058, | |
| "loss": 0.0, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.005044666316342617, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001913545457642601, | |
| "loss": 0.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.005465055176037835, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00018090169943749476, | |
| "loss": 0.0, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.005885444035733053, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00016691306063588583, | |
| "loss": 0.0, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.006305832895428271, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.006305832895428271, | |
| "eval_loss": NaN, | |
| "eval_runtime": 239.6331, | |
| "eval_samples_per_second": 4.181, | |
| "eval_steps_per_second": 2.091, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.006726221755123489, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 0.0, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0071466106148187075, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00011045284632676536, | |
| "loss": 4.2244, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.007566999474513925, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.954715367323468e-05, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.007987388334209143, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.909830056250527e-05, | |
| "loss": 0.0, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.008407777193904361, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.000000000000002e-05, | |
| "loss": 0.0, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.008407777193904361, | |
| "eval_loss": NaN, | |
| "eval_runtime": 235.0183, | |
| "eval_samples_per_second": 4.263, | |
| "eval_steps_per_second": 2.132, | |
| "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": 2 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 5805261843333120.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |