| { | |
| "best_metric": 0.7647151947021484, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-20", | |
| "epoch": 0.005028600163429505, | |
| "eval_steps": 5, | |
| "global_step": 20, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00025143000817147524, | |
| "eval_loss": 1.4811348915100098, | |
| "eval_runtime": 140.8611, | |
| "eval_samples_per_second": 11.891, | |
| "eval_steps_per_second": 5.949, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0007542900245144258, | |
| "grad_norm": 0.8739008903503418, | |
| "learning_rate": 6e-05, | |
| "loss": 1.3297, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0012571500408573764, | |
| "eval_loss": 1.3272086381912231, | |
| "eval_runtime": 141.7597, | |
| "eval_samples_per_second": 11.816, | |
| "eval_steps_per_second": 5.911, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0015085800490288515, | |
| "grad_norm": 0.7082861065864563, | |
| "learning_rate": 0.00012, | |
| "loss": 1.2271, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0022628700735432775, | |
| "grad_norm": 0.7618117332458496, | |
| "learning_rate": 0.00018, | |
| "loss": 1.1496, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0025143000817147527, | |
| "eval_loss": 0.8945090770721436, | |
| "eval_runtime": 141.9135, | |
| "eval_samples_per_second": 11.803, | |
| "eval_steps_per_second": 5.905, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.003017160098057703, | |
| "grad_norm": 1.0146321058273315, | |
| "learning_rate": 0.00019510565162951537, | |
| "loss": 0.9425, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.003771450122572129, | |
| "grad_norm": 0.5241138339042664, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 0.8438, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.003771450122572129, | |
| "eval_loss": 0.7839879989624023, | |
| "eval_runtime": 141.9579, | |
| "eval_samples_per_second": 11.799, | |
| "eval_steps_per_second": 5.903, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.004525740147086555, | |
| "grad_norm": 0.33658936619758606, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 0.6818, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.005028600163429505, | |
| "eval_loss": 0.7647151947021484, | |
| "eval_runtime": 141.8458, | |
| "eval_samples_per_second": 11.809, | |
| "eval_steps_per_second": 5.908, | |
| "step": 20 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 30, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 10, | |
| "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": 7418872835604480.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |