| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0035537865595792317, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 7.107573119158464e-05, | |
| "eval_loss": 2.738691806793213, | |
| "eval_runtime": 395.8619, | |
| "eval_samples_per_second": 14.965, | |
| "eval_steps_per_second": 7.482, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0003553786559579232, | |
| "grad_norm": 83.14938354492188, | |
| "learning_rate": 5e-05, | |
| "loss": 11.2519, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0007107573119158464, | |
| "grad_norm": 47.0615234375, | |
| "learning_rate": 0.0001, | |
| "loss": 6.3236, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0007107573119158464, | |
| "eval_loss": 1.474220633506775, | |
| "eval_runtime": 396.755, | |
| "eval_samples_per_second": 14.931, | |
| "eval_steps_per_second": 7.466, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0010661359678737696, | |
| "grad_norm": 58.601806640625, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 5.6438, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0014215146238316927, | |
| "grad_norm": 38.64629364013672, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 4.9843, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0014215146238316927, | |
| "eval_loss": 1.0445603132247925, | |
| "eval_runtime": 395.5604, | |
| "eval_samples_per_second": 14.976, | |
| "eval_steps_per_second": 7.488, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0017768932797896158, | |
| "grad_norm": 37.211456298828125, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 3.3916, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.002132271935747539, | |
| "grad_norm": 32.019588470458984, | |
| "learning_rate": 5e-05, | |
| "loss": 3.6857, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.002132271935747539, | |
| "eval_loss": 0.9380649328231812, | |
| "eval_runtime": 396.5294, | |
| "eval_samples_per_second": 14.94, | |
| "eval_steps_per_second": 7.47, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.002487650591705462, | |
| "grad_norm": 14.430593490600586, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 2.3664, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.0028430292476633854, | |
| "grad_norm": 56.26362991333008, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 5.3614, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0028430292476633854, | |
| "eval_loss": 0.9288716912269592, | |
| "eval_runtime": 397.2443, | |
| "eval_samples_per_second": 14.913, | |
| "eval_steps_per_second": 7.456, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0031984079036213083, | |
| "grad_norm": 25.66505241394043, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 4.2842, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.0035537865595792317, | |
| "grad_norm": 42.632633209228516, | |
| "learning_rate": 0.0, | |
| "loss": 3.7495, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.0035537865595792317, | |
| "eval_loss": 0.9020283222198486, | |
| "eval_runtime": 395.2916, | |
| "eval_samples_per_second": 14.986, | |
| "eval_steps_per_second": 7.493, | |
| "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": 9070232840699904.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |