| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.007340796476417691, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00014681592952835382, | |
| "eval_loss": 3.165564775466919, | |
| "eval_runtime": 104.0179, | |
| "eval_samples_per_second": 27.572, | |
| "eval_steps_per_second": 13.786, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0007340796476417691, | |
| "grad_norm": 1.3405300378799438, | |
| "learning_rate": 5e-05, | |
| "loss": 2.9764, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0014681592952835382, | |
| "grad_norm": 0.9374517798423767, | |
| "learning_rate": 0.0001, | |
| "loss": 2.9779, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0014681592952835382, | |
| "eval_loss": 3.068479537963867, | |
| "eval_runtime": 102.1255, | |
| "eval_samples_per_second": 28.083, | |
| "eval_steps_per_second": 14.042, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0022022389429253073, | |
| "grad_norm": 1.071268081665039, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 2.8653, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0029363185905670764, | |
| "grad_norm": 1.1812461614608765, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 2.9802, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0029363185905670764, | |
| "eval_loss": 2.9501028060913086, | |
| "eval_runtime": 102.1663, | |
| "eval_samples_per_second": 28.072, | |
| "eval_steps_per_second": 14.036, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0036703982382088455, | |
| "grad_norm": 1.3783600330352783, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 2.7701, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.004404477885850615, | |
| "grad_norm": 1.5364112854003906, | |
| "learning_rate": 5e-05, | |
| "loss": 2.9963, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.004404477885850615, | |
| "eval_loss": 2.9349489212036133, | |
| "eval_runtime": 103.4049, | |
| "eval_samples_per_second": 27.736, | |
| "eval_steps_per_second": 13.868, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.005138557533492384, | |
| "grad_norm": 1.593353033065796, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 3.1426, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.005872637181134153, | |
| "grad_norm": 1.596264123916626, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 2.793, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.005872637181134153, | |
| "eval_loss": 2.929900646209717, | |
| "eval_runtime": 103.2968, | |
| "eval_samples_per_second": 27.765, | |
| "eval_steps_per_second": 13.882, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.006606716828775922, | |
| "grad_norm": 1.112859845161438, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 2.9454, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.007340796476417691, | |
| "grad_norm": 0.8456483483314514, | |
| "learning_rate": 0.0, | |
| "loss": 2.7399, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.007340796476417691, | |
| "eval_loss": 2.9293360710144043, | |
| "eval_runtime": 102.8064, | |
| "eval_samples_per_second": 27.897, | |
| "eval_steps_per_second": 13.949, | |
| "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": 601007605678080.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |