| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.1949317738791423, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.003898635477582846, | |
| "eval_loss": 0.8528332114219666, | |
| "eval_runtime": 13.033, | |
| "eval_samples_per_second": 8.287, | |
| "eval_steps_per_second": 4.143, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.01949317738791423, | |
| "grad_norm": 4.2941975593566895, | |
| "learning_rate": 5e-05, | |
| "loss": 3.3908, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.03898635477582846, | |
| "grad_norm": 3.70715594291687, | |
| "learning_rate": 0.0001, | |
| "loss": 3.1215, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.03898635477582846, | |
| "eval_loss": 0.6822017431259155, | |
| "eval_runtime": 13.2646, | |
| "eval_samples_per_second": 8.142, | |
| "eval_steps_per_second": 4.071, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.05847953216374269, | |
| "grad_norm": 4.033545970916748, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 2.5946, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.07797270955165692, | |
| "grad_norm": 3.7863547801971436, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 2.411, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.07797270955165692, | |
| "eval_loss": 0.6232320070266724, | |
| "eval_runtime": 13.2904, | |
| "eval_samples_per_second": 8.126, | |
| "eval_steps_per_second": 4.063, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.09746588693957114, | |
| "grad_norm": 3.5488898754119873, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 2.5818, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.11695906432748537, | |
| "grad_norm": 3.620589017868042, | |
| "learning_rate": 5e-05, | |
| "loss": 2.5339, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.11695906432748537, | |
| "eval_loss": 0.608526349067688, | |
| "eval_runtime": 13.296, | |
| "eval_samples_per_second": 8.123, | |
| "eval_steps_per_second": 4.061, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.1364522417153996, | |
| "grad_norm": 3.582016706466675, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 2.5355, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.15594541910331383, | |
| "grad_norm": 3.544443130493164, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 2.3278, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.15594541910331383, | |
| "eval_loss": 0.6018404364585876, | |
| "eval_runtime": 13.4265, | |
| "eval_samples_per_second": 8.044, | |
| "eval_steps_per_second": 4.022, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.17543859649122806, | |
| "grad_norm": 3.317370653152466, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 2.3523, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.1949317738791423, | |
| "grad_norm": 3.9417917728424072, | |
| "learning_rate": 0.0, | |
| "loss": 2.5454, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.1949317738791423, | |
| "eval_loss": 0.6009447574615479, | |
| "eval_runtime": 13.3322, | |
| "eval_samples_per_second": 8.101, | |
| "eval_steps_per_second": 4.05, | |
| "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": 1.7439084402180096e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |