| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0007853917141174161, | |
| "eval_steps": 8, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 2.617972380391387e-05, | |
| "eval_loss": NaN, | |
| "eval_runtime": 1800.5185, | |
| "eval_samples_per_second": 8.933, | |
| "eval_steps_per_second": 4.466, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 7.85391714117416e-05, | |
| "grad_norm": NaN, | |
| "learning_rate": 3e-05, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0001570783428234832, | |
| "grad_norm": NaN, | |
| "learning_rate": 6e-05, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00020943779043131096, | |
| "eval_loss": NaN, | |
| "eval_runtime": 1802.1586, | |
| "eval_samples_per_second": 8.925, | |
| "eval_steps_per_second": 4.462, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.00023561751423522483, | |
| "grad_norm": NaN, | |
| "learning_rate": 9e-05, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0003141566856469664, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.755282581475769e-05, | |
| "loss": 0.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.00039269585705870805, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0004188755808626219, | |
| "eval_loss": NaN, | |
| "eval_runtime": 1801.2233, | |
| "eval_samples_per_second": 8.929, | |
| "eval_steps_per_second": 4.465, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.00047123502847044965, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0005497741998821913, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.2178276747988446e-05, | |
| "loss": 0.0, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0006283133712939328, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.061073738537635e-05, | |
| "loss": 0.0, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0006283133712939328, | |
| "eval_loss": NaN, | |
| "eval_runtime": 1802.9035, | |
| "eval_samples_per_second": 8.921, | |
| "eval_steps_per_second": 4.461, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0007068525427056745, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.449673790581611e-06, | |
| "loss": 0.0, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.0007853917141174161, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0, | |
| "loss": 0.0, | |
| "step": 30 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 30, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 10, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 9801969665310720.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |