| { | |
| "best_metric": 1.332247018814087, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-20", | |
| "epoch": 0.01173192550227306, | |
| "eval_steps": 5, | |
| "global_step": 20, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.000586596275113653, | |
| "eval_loss": 2.2366702556610107, | |
| "eval_runtime": 126.6078, | |
| "eval_samples_per_second": 11.342, | |
| "eval_steps_per_second": 2.836, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0017597888253409592, | |
| "grad_norm": 3.0139377117156982, | |
| "learning_rate": 0.00012, | |
| "loss": 1.4818, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.002932981375568265, | |
| "eval_loss": 1.6316547393798828, | |
| "eval_runtime": 126.6305, | |
| "eval_samples_per_second": 11.34, | |
| "eval_steps_per_second": 2.835, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0035195776506819184, | |
| "grad_norm": 2.2505617141723633, | |
| "learning_rate": 0.0001992114701314478, | |
| "loss": 1.3489, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.005279366476022877, | |
| "grad_norm": 0.6154037117958069, | |
| "learning_rate": 0.00018763066800438636, | |
| "loss": 1.1753, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.00586596275113653, | |
| "eval_loss": 1.4374616146087646, | |
| "eval_runtime": 126.6299, | |
| "eval_samples_per_second": 11.34, | |
| "eval_steps_per_second": 2.835, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.007039155301363837, | |
| "grad_norm": 0.4109272062778473, | |
| "learning_rate": 0.000163742398974869, | |
| "loss": 1.1459, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.008798944126704795, | |
| "grad_norm": 0.48281750082969666, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 1.1612, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.008798944126704795, | |
| "eval_loss": 1.3618714809417725, | |
| "eval_runtime": 126.6869, | |
| "eval_samples_per_second": 11.335, | |
| "eval_steps_per_second": 2.834, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.010558732952045754, | |
| "grad_norm": 0.4684368371963501, | |
| "learning_rate": 9.372094804706867e-05, | |
| "loss": 1.1017, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.01173192550227306, | |
| "eval_loss": 1.332247018814087, | |
| "eval_runtime": 126.6631, | |
| "eval_samples_per_second": 11.337, | |
| "eval_steps_per_second": 2.834, | |
| "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": 1.6678153976020992e+16, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |