| { | |
| "best_metric": 2.027435064315796, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-20", | |
| "epoch": 0.0017236550104496584, | |
| "eval_steps": 5, | |
| "global_step": 20, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 8.618275052248293e-05, | |
| "eval_loss": 2.57096529006958, | |
| "eval_runtime": 724.3902, | |
| "eval_samples_per_second": 6.745, | |
| "eval_steps_per_second": 3.372, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0002585482515674488, | |
| "grad_norm": 1.1678370237350464, | |
| "learning_rate": 3e-05, | |
| "loss": 2.5973, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0004309137526124146, | |
| "eval_loss": 2.531855344772339, | |
| "eval_runtime": 727.2568, | |
| "eval_samples_per_second": 6.718, | |
| "eval_steps_per_second": 3.359, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0005170965031348976, | |
| "grad_norm": 0.9036294221878052, | |
| "learning_rate": 6e-05, | |
| "loss": 2.6077, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0007756447547023463, | |
| "grad_norm": 0.9021340608596802, | |
| "learning_rate": 9e-05, | |
| "loss": 2.5392, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0008618275052248292, | |
| "eval_loss": 2.293621778488159, | |
| "eval_runtime": 727.6181, | |
| "eval_samples_per_second": 6.715, | |
| "eval_steps_per_second": 3.358, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.001034193006269795, | |
| "grad_norm": 1.4376518726348877, | |
| "learning_rate": 9.755282581475769e-05, | |
| "loss": 2.1546, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0012927412578372438, | |
| "grad_norm": 0.8561299443244934, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 2.0008, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0012927412578372438, | |
| "eval_loss": 2.138024091720581, | |
| "eval_runtime": 726.3131, | |
| "eval_samples_per_second": 6.727, | |
| "eval_steps_per_second": 3.364, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0015512895094046927, | |
| "grad_norm": 0.7144878506660461, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 2.1058, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0017236550104496584, | |
| "eval_loss": 2.027435064315796, | |
| "eval_runtime": 726.536, | |
| "eval_samples_per_second": 6.725, | |
| "eval_steps_per_second": 3.363, | |
| "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": 3745437159260160.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |