| { | |
| "best_metric": 0.5042373538017273, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-30", | |
| "epoch": 0.03810733566211496, | |
| "eval_steps": 5, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0012702445220704986, | |
| "eval_loss": 1.0383965969085693, | |
| "eval_runtime": 159.0773, | |
| "eval_samples_per_second": 4.168, | |
| "eval_steps_per_second": 1.044, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.003810733566211496, | |
| "grad_norm": 0.4340018033981323, | |
| "learning_rate": 0.00012, | |
| "loss": 2.0343, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.006351222610352493, | |
| "eval_loss": 1.0253185033798218, | |
| "eval_runtime": 159.8973, | |
| "eval_samples_per_second": 4.146, | |
| "eval_steps_per_second": 1.038, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.007621467132422992, | |
| "grad_norm": 0.6041859984397888, | |
| "learning_rate": 0.0001992114701314478, | |
| "loss": 2.7689, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.011432200698634487, | |
| "grad_norm": 0.8470184206962585, | |
| "learning_rate": 0.00018763066800438636, | |
| "loss": 3.0703, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.012702445220704985, | |
| "eval_loss": 0.8574949502944946, | |
| "eval_runtime": 159.9181, | |
| "eval_samples_per_second": 4.146, | |
| "eval_steps_per_second": 1.038, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.015242934264845983, | |
| "grad_norm": 1.0055904388427734, | |
| "learning_rate": 0.000163742398974869, | |
| "loss": 3.0939, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.01905366783105748, | |
| "grad_norm": 1.397754192352295, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 3.0024, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.01905366783105748, | |
| "eval_loss": 0.6791817545890808, | |
| "eval_runtime": 159.9577, | |
| "eval_samples_per_second": 4.145, | |
| "eval_steps_per_second": 1.038, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.022864401397268974, | |
| "grad_norm": 1.4741846323013306, | |
| "learning_rate": 9.372094804706867e-05, | |
| "loss": 2.5871, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.02540489044140997, | |
| "eval_loss": 0.5654808282852173, | |
| "eval_runtime": 159.9867, | |
| "eval_samples_per_second": 4.144, | |
| "eval_steps_per_second": 1.038, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.02667513496348047, | |
| "grad_norm": 1.394364356994629, | |
| "learning_rate": 5.7422070843492734e-05, | |
| "loss": 2.3204, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.030485868529691967, | |
| "grad_norm": 1.2767504453659058, | |
| "learning_rate": 2.7103137257858868e-05, | |
| "loss": 2.2627, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.031756113051762465, | |
| "eval_loss": 0.5138222575187683, | |
| "eval_runtime": 160.168, | |
| "eval_samples_per_second": 4.139, | |
| "eval_steps_per_second": 1.036, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.03429660209590346, | |
| "grad_norm": 1.2673128843307495, | |
| "learning_rate": 7.022351411174866e-06, | |
| "loss": 2.1764, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.03810733566211496, | |
| "grad_norm": 1.3284103870391846, | |
| "learning_rate": 0.0, | |
| "loss": 2.2597, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.03810733566211496, | |
| "eval_loss": 0.5042373538017273, | |
| "eval_runtime": 160.3023, | |
| "eval_samples_per_second": 4.136, | |
| "eval_steps_per_second": 1.036, | |
| "step": 30 | |
| } | |
| ], | |
| "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": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 4.11081451241472e+16, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |