| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "eval_steps": 7, | |
| "global_step": 34, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.029411764705882353, | |
| "eval_loss": 7.964369297027588, | |
| "eval_runtime": 12.1692, | |
| "eval_samples_per_second": 18.9, | |
| "eval_steps_per_second": 2.383, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.20588235294117646, | |
| "eval_loss": 0.220572829246521, | |
| "eval_runtime": 12.2392, | |
| "eval_samples_per_second": 18.792, | |
| "eval_steps_per_second": 2.369, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.29411764705882354, | |
| "grad_norm": 0.879223108291626, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 3.6996, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.4117647058823529, | |
| "eval_loss": 5.680652247974649e-05, | |
| "eval_runtime": 12.2214, | |
| "eval_samples_per_second": 18.82, | |
| "eval_steps_per_second": 2.373, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.5882352941176471, | |
| "grad_norm": 0.011018212884664536, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 0.0005, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.6176470588235294, | |
| "eval_loss": 3.617151014623232e-05, | |
| "eval_runtime": 12.2504, | |
| "eval_samples_per_second": 18.775, | |
| "eval_steps_per_second": 2.367, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.8235294117647058, | |
| "eval_loss": 2.1168278180994093e-05, | |
| "eval_runtime": 12.3009, | |
| "eval_samples_per_second": 18.698, | |
| "eval_steps_per_second": 2.358, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.8823529411764706, | |
| "grad_norm": 0.0023900624364614487, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.0, | |
| "step": 30 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 34, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 9, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 9.532338273150566e+16, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |