| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.006367398917542184, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00012734797835084368, | |
| "eval_loss": 2.5662894248962402, | |
| "eval_runtime": 162.3491, | |
| "eval_samples_per_second": 20.37, | |
| "eval_steps_per_second": 10.188, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0006367398917542184, | |
| "grad_norm": 0.610783576965332, | |
| "learning_rate": 5e-05, | |
| "loss": 1.9454, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0012734797835084368, | |
| "grad_norm": 0.5147393941879272, | |
| "learning_rate": 0.0001, | |
| "loss": 1.518, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0012734797835084368, | |
| "eval_loss": 2.484592914581299, | |
| "eval_runtime": 161.1375, | |
| "eval_samples_per_second": 20.523, | |
| "eval_steps_per_second": 10.265, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0019102196752626551, | |
| "grad_norm": 0.5668697953224182, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 1.806, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0025469595670168737, | |
| "grad_norm": 0.5659977197647095, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 1.6358, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0025469595670168737, | |
| "eval_loss": 2.3336341381073, | |
| "eval_runtime": 162.3412, | |
| "eval_samples_per_second": 20.371, | |
| "eval_steps_per_second": 10.188, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.003183699458771092, | |
| "grad_norm": 0.5387349128723145, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 1.4841, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0038204393505253103, | |
| "grad_norm": 0.6737701892852783, | |
| "learning_rate": 5e-05, | |
| "loss": 1.8006, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0038204393505253103, | |
| "eval_loss": 2.275390625, | |
| "eval_runtime": 161.8295, | |
| "eval_samples_per_second": 20.435, | |
| "eval_steps_per_second": 10.221, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.004457179242279528, | |
| "grad_norm": 0.6395950317382812, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 1.7372, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.005093919134033747, | |
| "grad_norm": 0.9296777248382568, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 1.5463, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.005093919134033747, | |
| "eval_loss": 2.25455641746521, | |
| "eval_runtime": 163.7581, | |
| "eval_samples_per_second": 20.194, | |
| "eval_steps_per_second": 10.1, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0057306590257879654, | |
| "grad_norm": 0.7359820008277893, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 1.7395, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.006367398917542184, | |
| "grad_norm": 1.552220106124878, | |
| "learning_rate": 0.0, | |
| "loss": 1.9366, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.006367398917542184, | |
| "eval_loss": 2.252518892288208, | |
| "eval_runtime": 165.9093, | |
| "eval_samples_per_second": 19.933, | |
| "eval_steps_per_second": 9.969, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 13, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 4209124426383360.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |