| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.013880855986119144, | |
| "eval_steps": 3, | |
| "global_step": 6, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.002313475997686524, | |
| "grad_norm": 0.009941955097019672, | |
| "learning_rate": 2e-05, | |
| "loss": 11.9345, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.002313475997686524, | |
| "eval_loss": NaN, | |
| "eval_runtime": 1.6946, | |
| "eval_samples_per_second": 54.291, | |
| "eval_steps_per_second": 54.291, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.004626951995373048, | |
| "grad_norm": 0.011387641541659832, | |
| "learning_rate": 4e-05, | |
| "loss": 11.9332, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.006940427993059572, | |
| "grad_norm": 0.011258460581302643, | |
| "learning_rate": 6e-05, | |
| "loss": 11.93, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.006940427993059572, | |
| "eval_loss": NaN, | |
| "eval_runtime": 1.7039, | |
| "eval_samples_per_second": 53.994, | |
| "eval_steps_per_second": 53.994, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.009253903990746095, | |
| "grad_norm": 0.009373195469379425, | |
| "learning_rate": 8e-05, | |
| "loss": 11.9335, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.01156737998843262, | |
| "grad_norm": 0.008356277830898762, | |
| "learning_rate": 0.0001, | |
| "loss": 11.9314, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.013880855986119144, | |
| "grad_norm": 0.01255944836884737, | |
| "learning_rate": 0.00012, | |
| "loss": 11.9327, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.013880855986119144, | |
| "eval_loss": NaN, | |
| "eval_runtime": 1.7199, | |
| "eval_samples_per_second": 53.49, | |
| "eval_steps_per_second": 53.49, | |
| "step": 6 | |
| } | |
| ], | |
| "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": 4496818176.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |