| { | |
| "best_metric": 1.9385418891906738, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-10", | |
| "epoch": 0.004253056884635832, | |
| "eval_steps": 5, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0004253056884635832, | |
| "grad_norm": 4.933011694575157e+18, | |
| "learning_rate": 2e-05, | |
| "loss": 1.67, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0004253056884635832, | |
| "eval_loss": 1.9383187294006348, | |
| "eval_runtime": 93.2103, | |
| "eval_samples_per_second": 10.621, | |
| "eval_steps_per_second": 5.311, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0008506113769271664, | |
| "grad_norm": Infinity, | |
| "learning_rate": 4e-05, | |
| "loss": 1.8668, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0012759170653907496, | |
| "grad_norm": Infinity, | |
| "learning_rate": 6e-05, | |
| "loss": 1.6367, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0017012227538543328, | |
| "grad_norm": Infinity, | |
| "learning_rate": 8e-05, | |
| "loss": 1.9704, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.002126528442317916, | |
| "grad_norm": 6.49807413773756e+18, | |
| "learning_rate": 0.0001, | |
| "loss": 1.6378, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.002126528442317916, | |
| "eval_loss": 1.9388357400894165, | |
| "eval_runtime": 92.8879, | |
| "eval_samples_per_second": 10.658, | |
| "eval_steps_per_second": 5.329, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.002551834130781499, | |
| "grad_norm": Infinity, | |
| "learning_rate": 0.00012, | |
| "loss": 1.6715, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0029771398192450825, | |
| "grad_norm": Infinity, | |
| "learning_rate": 0.00014, | |
| "loss": 2.0158, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0034024455077086655, | |
| "grad_norm": Infinity, | |
| "learning_rate": 0.00016, | |
| "loss": 1.9724, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.003827751196172249, | |
| "grad_norm": Infinity, | |
| "learning_rate": 0.00018, | |
| "loss": 2.1071, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.004253056884635832, | |
| "grad_norm": Infinity, | |
| "learning_rate": 0.0002, | |
| "loss": 1.8591, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.004253056884635832, | |
| "eval_loss": 1.9385418891906738, | |
| "eval_runtime": 91.2179, | |
| "eval_samples_per_second": 10.853, | |
| "eval_steps_per_second": 5.427, | |
| "step": 10 | |
| } | |
| ], | |
| "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": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 511583956500480.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |