| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.16863406408094436, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.003372681281618887, | |
| "eval_loss": 3.23850154876709, | |
| "eval_runtime": 8.5688, | |
| "eval_samples_per_second": 14.588, | |
| "eval_steps_per_second": 7.352, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.016863406408094434, | |
| "grad_norm": 1.5265541076660156, | |
| "learning_rate": 5e-05, | |
| "loss": 3.1079, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.03372681281618887, | |
| "grad_norm": 1.8242183923721313, | |
| "learning_rate": 0.0001, | |
| "loss": 3.1474, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.03372681281618887, | |
| "eval_loss": 3.142918348312378, | |
| "eval_runtime": 8.6873, | |
| "eval_samples_per_second": 14.389, | |
| "eval_steps_per_second": 7.252, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.050590219224283306, | |
| "grad_norm": 1.8662317991256714, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 2.8724, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.06745362563237774, | |
| "grad_norm": 2.8559272289276123, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 2.5334, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.06745362563237774, | |
| "eval_loss": 2.4120566844940186, | |
| "eval_runtime": 8.6744, | |
| "eval_samples_per_second": 14.41, | |
| "eval_steps_per_second": 7.263, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.08431703204047218, | |
| "grad_norm": 2.715538263320923, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 2.3448, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.10118043844856661, | |
| "grad_norm": 2.589365243911743, | |
| "learning_rate": 5e-05, | |
| "loss": 2.0925, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.10118043844856661, | |
| "eval_loss": 2.090477228164673, | |
| "eval_runtime": 8.7669, | |
| "eval_samples_per_second": 14.258, | |
| "eval_steps_per_second": 7.186, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.11804384485666104, | |
| "grad_norm": 2.8160316944122314, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 2.0775, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.13490725126475547, | |
| "grad_norm": 2.271430253982544, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 1.9698, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.13490725126475547, | |
| "eval_loss": 2.0026512145996094, | |
| "eval_runtime": 8.8025, | |
| "eval_samples_per_second": 14.2, | |
| "eval_steps_per_second": 7.157, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.15177065767284992, | |
| "grad_norm": 2.3078043460845947, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 1.9008, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.16863406408094436, | |
| "grad_norm": 2.5745885372161865, | |
| "learning_rate": 0.0, | |
| "loss": 1.9481, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.16863406408094436, | |
| "eval_loss": 1.9871878623962402, | |
| "eval_runtime": 8.8183, | |
| "eval_samples_per_second": 14.175, | |
| "eval_steps_per_second": 7.144, | |
| "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": 9247821240729600.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |