| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0485319097306479, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.000970638194612958, | |
| "eval_loss": 2.2291553020477295, | |
| "eval_runtime": 14.4912, | |
| "eval_samples_per_second": 29.949, | |
| "eval_steps_per_second": 14.975, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0048531909730647905, | |
| "grad_norm": 1.095381498336792, | |
| "learning_rate": 5e-05, | |
| "loss": 2.2359, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.009706381946129581, | |
| "grad_norm": 0.7277218103408813, | |
| "learning_rate": 0.0001, | |
| "loss": 2.1487, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.009706381946129581, | |
| "eval_loss": 2.1091368198394775, | |
| "eval_runtime": 14.5705, | |
| "eval_samples_per_second": 29.786, | |
| "eval_steps_per_second": 14.893, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.01455957291919437, | |
| "grad_norm": 0.7657337784767151, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 2.1049, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.019412763892259162, | |
| "grad_norm": 0.8005470633506775, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 1.9949, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.019412763892259162, | |
| "eval_loss": 1.9761087894439697, | |
| "eval_runtime": 14.7541, | |
| "eval_samples_per_second": 29.416, | |
| "eval_steps_per_second": 14.708, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.02426595486532395, | |
| "grad_norm": 0.6035395264625549, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 2.0049, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.02911914583838874, | |
| "grad_norm": 0.9888164401054382, | |
| "learning_rate": 5e-05, | |
| "loss": 1.9446, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.02911914583838874, | |
| "eval_loss": 1.9136253595352173, | |
| "eval_runtime": 14.7115, | |
| "eval_samples_per_second": 29.501, | |
| "eval_steps_per_second": 14.75, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.03397233681145353, | |
| "grad_norm": 0.6257792115211487, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 1.8295, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.038825527784518324, | |
| "grad_norm": 0.7209451198577881, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 1.9043, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.038825527784518324, | |
| "eval_loss": 1.8833268880844116, | |
| "eval_runtime": 14.8456, | |
| "eval_samples_per_second": 29.234, | |
| "eval_steps_per_second": 14.617, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.04367871875758311, | |
| "grad_norm": 0.6183915734291077, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 1.8511, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.0485319097306479, | |
| "grad_norm": 0.6538072228431702, | |
| "learning_rate": 0.0, | |
| "loss": 1.8676, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.0485319097306479, | |
| "eval_loss": 1.8793177604675293, | |
| "eval_runtime": 14.6525, | |
| "eval_samples_per_second": 29.62, | |
| "eval_steps_per_second": 14.81, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 13, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1995177430351872.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |