| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 18.823529411764707, | |
| "eval_steps": 10, | |
| "global_step": 80, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 2.3529411764705883, | |
| "grad_norm": 0.36976027488708496, | |
| "learning_rate": 9.722222222222223e-05, | |
| "loss": 1.5945, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 2.3529411764705883, | |
| "eval_loss": 1.4627282619476318, | |
| "eval_runtime": 8.4531, | |
| "eval_samples_per_second": 1.893, | |
| "eval_steps_per_second": 0.237, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 4.705882352941177, | |
| "grad_norm": 0.4368647336959839, | |
| "learning_rate": 8.333333333333334e-05, | |
| "loss": 1.3292, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 4.705882352941177, | |
| "eval_loss": 1.15525221824646, | |
| "eval_runtime": 8.4549, | |
| "eval_samples_per_second": 1.892, | |
| "eval_steps_per_second": 0.237, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 7.0588235294117645, | |
| "grad_norm": 0.534726619720459, | |
| "learning_rate": 6.944444444444444e-05, | |
| "loss": 0.9997, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 7.0588235294117645, | |
| "eval_loss": 0.7809390425682068, | |
| "eval_runtime": 8.4531, | |
| "eval_samples_per_second": 1.893, | |
| "eval_steps_per_second": 0.237, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 9.411764705882353, | |
| "grad_norm": 0.33240973949432373, | |
| "learning_rate": 5.555555555555556e-05, | |
| "loss": 0.671, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 9.411764705882353, | |
| "eval_loss": 0.5391466021537781, | |
| "eval_runtime": 8.4544, | |
| "eval_samples_per_second": 1.893, | |
| "eval_steps_per_second": 0.237, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 11.764705882352942, | |
| "grad_norm": 0.21125604212284088, | |
| "learning_rate": 4.166666666666667e-05, | |
| "loss": 0.5142, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 11.764705882352942, | |
| "eval_loss": 0.4500214457511902, | |
| "eval_runtime": 8.4539, | |
| "eval_samples_per_second": 1.893, | |
| "eval_steps_per_second": 0.237, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 14.117647058823529, | |
| "grad_norm": 0.1706436276435852, | |
| "learning_rate": 2.777777777777778e-05, | |
| "loss": 0.4445, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 14.117647058823529, | |
| "eval_loss": 0.4089035987854004, | |
| "eval_runtime": 8.4541, | |
| "eval_samples_per_second": 1.893, | |
| "eval_steps_per_second": 0.237, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 16.470588235294116, | |
| "grad_norm": 0.15023984014987946, | |
| "learning_rate": 1.388888888888889e-05, | |
| "loss": 0.4122, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 16.470588235294116, | |
| "eval_loss": 0.3887946605682373, | |
| "eval_runtime": 8.4524, | |
| "eval_samples_per_second": 1.893, | |
| "eval_steps_per_second": 0.237, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 18.823529411764707, | |
| "grad_norm": 0.14184406399726868, | |
| "learning_rate": 0.0, | |
| "loss": 0.3986, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 18.823529411764707, | |
| "eval_loss": 0.3825053572654724, | |
| "eval_runtime": 8.4528, | |
| "eval_samples_per_second": 1.893, | |
| "eval_steps_per_second": 0.237, | |
| "step": 80 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 80, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 20, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2.027259066504192e+16, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |