| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.006755001299038711, | |
| "eval_steps": 10, | |
| "global_step": 39, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0001732051615138131, | |
| "eval_loss": 2.2006497383117676, | |
| "eval_runtime": 196.2072, | |
| "eval_samples_per_second": 12.39, | |
| "eval_steps_per_second": 6.198, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0008660258075690655, | |
| "grad_norm": 1.3223685026168823, | |
| "learning_rate": 5e-05, | |
| "loss": 2.0905, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.001732051615138131, | |
| "grad_norm": 1.441433072090149, | |
| "learning_rate": 0.0001, | |
| "loss": 2.2346, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.001732051615138131, | |
| "eval_loss": 2.063689947128296, | |
| "eval_runtime": 196.9244, | |
| "eval_samples_per_second": 12.345, | |
| "eval_steps_per_second": 6.175, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.002598077422707197, | |
| "grad_norm": 1.8071070909500122, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 1.9364, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.003464103230276262, | |
| "grad_norm": 1.5971530675888062, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 2.0111, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.003464103230276262, | |
| "eval_loss": 1.9679561853408813, | |
| "eval_runtime": 197.1497, | |
| "eval_samples_per_second": 12.331, | |
| "eval_steps_per_second": 6.168, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.004330129037845328, | |
| "grad_norm": 1.3177014589309692, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 1.9267, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.005196154845414394, | |
| "grad_norm": 1.585343360900879, | |
| "learning_rate": 5e-05, | |
| "loss": 1.8514, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.005196154845414394, | |
| "eval_loss": 1.9340301752090454, | |
| "eval_runtime": 196.9916, | |
| "eval_samples_per_second": 12.341, | |
| "eval_steps_per_second": 6.173, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.006062180652983459, | |
| "grad_norm": 1.5796632766723633, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 1.7648, | |
| "step": 35 | |
| } | |
| ], | |
| "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": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 7453256523448320.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |