| { | |
| "best_global_step": null, | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "eval_steps": 11, | |
| "global_step": 11, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.09090909090909091, | |
| "grad_norm": 1.0177257061004639, | |
| "learning_rate": 1e-05, | |
| "loss": 2.2647, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.18181818181818182, | |
| "grad_norm": 0.9801989793777466, | |
| "learning_rate": 9.090909090909091e-06, | |
| "loss": 2.276, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.2727272727272727, | |
| "grad_norm": 0.9282708168029785, | |
| "learning_rate": 8.181818181818183e-06, | |
| "loss": 2.2371, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.36363636363636365, | |
| "grad_norm": 0.8848165273666382, | |
| "learning_rate": 7.272727272727273e-06, | |
| "loss": 2.2429, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.45454545454545453, | |
| "grad_norm": 0.8310409784317017, | |
| "learning_rate": 6.363636363636364e-06, | |
| "loss": 2.1339, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.5454545454545454, | |
| "grad_norm": 0.8064534068107605, | |
| "learning_rate": 5.4545454545454545e-06, | |
| "loss": 2.1214, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.6363636363636364, | |
| "grad_norm": 0.8168641924858093, | |
| "learning_rate": 4.5454545454545455e-06, | |
| "loss": 2.1803, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.7272727272727273, | |
| "grad_norm": 0.769072413444519, | |
| "learning_rate": 3.6363636363636366e-06, | |
| "loss": 2.0829, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.8181818181818182, | |
| "grad_norm": 0.7420956492424011, | |
| "learning_rate": 2.7272727272727272e-06, | |
| "loss": 2.0589, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.9090909090909091, | |
| "grad_norm": 0.7859477996826172, | |
| "learning_rate": 1.8181818181818183e-06, | |
| "loss": 2.1755, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 0.7540016174316406, | |
| "learning_rate": 9.090909090909091e-07, | |
| "loss": 2.1153, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 2.170610189437866, | |
| "eval_runtime": 17.3811, | |
| "eval_samples_per_second": 0.173, | |
| "eval_steps_per_second": 0.058, | |
| "step": 11 | |
| } | |
| ], | |
| "logging_steps": 1.0, | |
| "max_steps": 11, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 0, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 6.601629035501978e+16, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |