| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.000925304772259363, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.8506095445187258e-05, | |
| "eval_loss": 2.8703367710113525, | |
| "eval_runtime": 1753.2351, | |
| "eval_samples_per_second": 12.978, | |
| "eval_steps_per_second": 6.489, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 9.25304772259363e-05, | |
| "grad_norm": 2.1783010959625244, | |
| "learning_rate": 5e-05, | |
| "loss": 2.4942, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0001850609544518726, | |
| "grad_norm": 4.921787261962891, | |
| "learning_rate": 0.0001, | |
| "loss": 2.3095, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0001850609544518726, | |
| "eval_loss": 1.9956756830215454, | |
| "eval_runtime": 1762.0825, | |
| "eval_samples_per_second": 12.913, | |
| "eval_steps_per_second": 6.457, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0002775914316778089, | |
| "grad_norm": 5.27348518371582, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 1.7876, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0003701219089037452, | |
| "grad_norm": 4.285337924957275, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 1.1182, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0003701219089037452, | |
| "eval_loss": 0.8893212676048279, | |
| "eval_runtime": 1765.1, | |
| "eval_samples_per_second": 12.89, | |
| "eval_steps_per_second": 6.446, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0004626523861296815, | |
| "grad_norm": 3.7942230701446533, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.9834, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0005551828633556178, | |
| "grad_norm": 2.5414369106292725, | |
| "learning_rate": 5e-05, | |
| "loss": 0.7072, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0005551828633556178, | |
| "eval_loss": 0.7601051330566406, | |
| "eval_runtime": 1760.643, | |
| "eval_samples_per_second": 12.923, | |
| "eval_steps_per_second": 6.462, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.000647713340581554, | |
| "grad_norm": 2.901604413986206, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.6794, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.0007402438178074904, | |
| "grad_norm": 2.6846745014190674, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.7385, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0007402438178074904, | |
| "eval_loss": 0.7256695628166199, | |
| "eval_runtime": 1763.3586, | |
| "eval_samples_per_second": 12.903, | |
| "eval_steps_per_second": 6.452, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0008327742950334266, | |
| "grad_norm": 2.203322649002075, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.5177, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.000925304772259363, | |
| "grad_norm": 2.2175235748291016, | |
| "learning_rate": 0.0, | |
| "loss": 0.4764, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.000925304772259363, | |
| "eval_loss": 0.7167384028434753, | |
| "eval_runtime": 1761.8584, | |
| "eval_samples_per_second": 12.914, | |
| "eval_steps_per_second": 6.457, | |
| "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": 1.0958668170264576e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |