| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.005897771952817824, | |
| "eval_steps": 3, | |
| "global_step": 9, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.000655307994757536, | |
| "grad_norm": 0.15108448266983032, | |
| "learning_rate": 2e-05, | |
| "loss": 0.5443, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.000655307994757536, | |
| "eval_loss": 0.9055324196815491, | |
| "eval_runtime": 104.7289, | |
| "eval_samples_per_second": 24.549, | |
| "eval_steps_per_second": 3.075, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.001310615989515072, | |
| "grad_norm": NaN, | |
| "learning_rate": 2e-05, | |
| "loss": 0.629, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.001965923984272608, | |
| "grad_norm": 0.15483306348323822, | |
| "learning_rate": 4e-05, | |
| "loss": 0.5365, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.001965923984272608, | |
| "eval_loss": 0.9036340713500977, | |
| "eval_runtime": 105.1959, | |
| "eval_samples_per_second": 24.44, | |
| "eval_steps_per_second": 3.061, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.002621231979030144, | |
| "grad_norm": 0.14074499905109406, | |
| "learning_rate": 6e-05, | |
| "loss": 0.6186, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.00327653997378768, | |
| "grad_norm": 0.1980854570865631, | |
| "learning_rate": 8e-05, | |
| "loss": 0.5757, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.003931847968545216, | |
| "grad_norm": 0.21592412889003754, | |
| "learning_rate": 0.0001, | |
| "loss": 0.5379, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.003931847968545216, | |
| "eval_loss": 0.8669220209121704, | |
| "eval_runtime": 105.2477, | |
| "eval_samples_per_second": 24.428, | |
| "eval_steps_per_second": 3.059, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0045871559633027525, | |
| "grad_norm": 0.28356343507766724, | |
| "learning_rate": 0.00012, | |
| "loss": 0.6242, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.005242463958060288, | |
| "grad_norm": 0.24505580961704254, | |
| "learning_rate": 0.00014, | |
| "loss": 0.5181, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.005897771952817824, | |
| "grad_norm": 0.32702115178108215, | |
| "learning_rate": 0.00016, | |
| "loss": 0.4097, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.005897771952817824, | |
| "eval_loss": 0.7492024302482605, | |
| "eval_runtime": 105.2948, | |
| "eval_samples_per_second": 24.417, | |
| "eval_steps_per_second": 3.058, | |
| "step": 9 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 10, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 3, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 9.161227089897062e+16, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |