| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.020372822654578793, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0004074564530915758, | |
| "eval_loss": 2.328631639480591, | |
| "eval_runtime": 74.3707, | |
| "eval_samples_per_second": 13.903, | |
| "eval_steps_per_second": 6.952, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0020372822654578793, | |
| "grad_norm": 32.55160140991211, | |
| "learning_rate": 5e-05, | |
| "loss": 8.5454, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0040745645309157585, | |
| "grad_norm": 14.240496635437012, | |
| "learning_rate": 0.0001, | |
| "loss": 6.4219, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0040745645309157585, | |
| "eval_loss": 1.3548425436019897, | |
| "eval_runtime": 74.9166, | |
| "eval_samples_per_second": 13.802, | |
| "eval_steps_per_second": 6.901, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.006111846796373638, | |
| "grad_norm": 15.140237808227539, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 4.7768, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.008149129061831517, | |
| "grad_norm": 13.341498374938965, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 4.1123, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.008149129061831517, | |
| "eval_loss": 1.10359525680542, | |
| "eval_runtime": 74.9369, | |
| "eval_samples_per_second": 13.798, | |
| "eval_steps_per_second": 6.899, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.010186411327289396, | |
| "grad_norm": 12.279659271240234, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 4.4021, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.012223693592747276, | |
| "grad_norm": 12.776435852050781, | |
| "learning_rate": 5e-05, | |
| "loss": 4.1317, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.012223693592747276, | |
| "eval_loss": 1.0448427200317383, | |
| "eval_runtime": 75.0361, | |
| "eval_samples_per_second": 13.78, | |
| "eval_steps_per_second": 6.89, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.014260975858205155, | |
| "grad_norm": 9.15871524810791, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 3.9519, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.016298258123663034, | |
| "grad_norm": 13.718193054199219, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 4.3358, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.016298258123663034, | |
| "eval_loss": 1.0276206731796265, | |
| "eval_runtime": 75.3406, | |
| "eval_samples_per_second": 13.724, | |
| "eval_steps_per_second": 6.862, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.018335540389120913, | |
| "grad_norm": 8.468703269958496, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 3.4373, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.020372822654578793, | |
| "grad_norm": 10.509159088134766, | |
| "learning_rate": 0.0, | |
| "loss": 4.6255, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.020372822654578793, | |
| "eval_loss": 1.0231385231018066, | |
| "eval_runtime": 75.3527, | |
| "eval_samples_per_second": 13.722, | |
| "eval_steps_per_second": 6.861, | |
| "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": 9683500567363584.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |