| { | |
| "best_global_step": null, | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "eval_steps": 2, | |
| "global_step": 14, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.14545454545454545, | |
| "grad_norm": 5.989531517028809, | |
| "learning_rate": 0.0001, | |
| "loss": 2.8214, | |
| "mean_token_accuracy": 0.7949551716446877, | |
| "num_tokens": 18590.0, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.14545454545454545, | |
| "eval_loss": 1.2452431917190552, | |
| "eval_mean_token_accuracy": 0.6979593506881169, | |
| "eval_num_tokens": 18590.0, | |
| "eval_runtime": 10.9414, | |
| "eval_samples_per_second": 5.027, | |
| "eval_steps_per_second": 1.28, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.2909090909090909, | |
| "grad_norm": 4.987532615661621, | |
| "learning_rate": 0.00019983081582712685, | |
| "loss": 2.4811, | |
| "mean_token_accuracy": 0.8189418539404869, | |
| "num_tokens": 37141.0, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.2909090909090909, | |
| "eval_loss": 1.3113545179367065, | |
| "eval_mean_token_accuracy": 0.6982744761875698, | |
| "eval_num_tokens": 37141.0, | |
| "eval_runtime": 10.3505, | |
| "eval_samples_per_second": 5.314, | |
| "eval_steps_per_second": 1.353, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.43636363636363634, | |
| "grad_norm": 6.911726474761963, | |
| "learning_rate": 0.00019848077530122083, | |
| "loss": 2.3469, | |
| "mean_token_accuracy": 0.8197802603244781, | |
| "num_tokens": 55750.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.43636363636363634, | |
| "eval_loss": 1.3598123788833618, | |
| "eval_mean_token_accuracy": 0.7003392151423863, | |
| "eval_num_tokens": 55750.0, | |
| "eval_runtime": 10.3223, | |
| "eval_samples_per_second": 5.328, | |
| "eval_steps_per_second": 1.356, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.5818181818181818, | |
| "grad_norm": 7.113568305969238, | |
| "learning_rate": 0.0001957989512315489, | |
| "loss": 2.5459, | |
| "mean_token_accuracy": 0.8071999177336693, | |
| "num_tokens": 74464.0, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.5818181818181818, | |
| "eval_loss": 1.330183744430542, | |
| "eval_mean_token_accuracy": 0.7020843710218158, | |
| "eval_num_tokens": 74464.0, | |
| "eval_runtime": 10.3053, | |
| "eval_samples_per_second": 5.337, | |
| "eval_steps_per_second": 1.359, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.7272727272727273, | |
| "grad_norm": 6.972678184509277, | |
| "learning_rate": 0.00019182161068802741, | |
| "loss": 2.7286, | |
| "mean_token_accuracy": 0.799242340028286, | |
| "num_tokens": 93229.0, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.7272727272727273, | |
| "eval_loss": 1.2857917547225952, | |
| "eval_mean_token_accuracy": 0.7042312707219806, | |
| "eval_num_tokens": 93229.0, | |
| "eval_runtime": 10.3146, | |
| "eval_samples_per_second": 5.332, | |
| "eval_steps_per_second": 1.357, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.8727272727272727, | |
| "grad_norm": 7.350575923919678, | |
| "learning_rate": 0.00018660254037844388, | |
| "loss": 2.6974, | |
| "mean_token_accuracy": 0.8019056767225266, | |
| "num_tokens": 111785.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.8727272727272727, | |
| "eval_loss": 1.267033338546753, | |
| "eval_mean_token_accuracy": 0.7043451964855194, | |
| "eval_num_tokens": 111785.0, | |
| "eval_runtime": 10.3056, | |
| "eval_samples_per_second": 5.337, | |
| "eval_steps_per_second": 1.358, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 6.314274311065674, | |
| "learning_rate": 0.0001802123192755044, | |
| "loss": 2.51, | |
| "mean_token_accuracy": 0.7953777994428363, | |
| "num_tokens": 126994.0, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 1.2424124479293823, | |
| "eval_mean_token_accuracy": 0.7082162286554065, | |
| "eval_num_tokens": 126994.0, | |
| "eval_runtime": 10.3422, | |
| "eval_samples_per_second": 5.318, | |
| "eval_steps_per_second": 1.354, | |
| "step": 14 | |
| } | |
| ], | |
| "logging_steps": 2, | |
| "max_steps": 56, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 4, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3387742653033024.0, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |