| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.10922992900054615, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.002184598580010923, | |
| "eval_loss": 7.941990852355957, | |
| "eval_runtime": 14.7533, | |
| "eval_samples_per_second": 13.082, | |
| "eval_steps_per_second": 6.575, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.010922992900054615, | |
| "grad_norm": 29.248445510864258, | |
| "learning_rate": 5e-05, | |
| "loss": 7.938, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.02184598580010923, | |
| "grad_norm": 20.712759017944336, | |
| "learning_rate": 0.0001, | |
| "loss": 5.6982, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.02184598580010923, | |
| "eval_loss": 3.3715083599090576, | |
| "eval_runtime": 14.9999, | |
| "eval_samples_per_second": 12.867, | |
| "eval_steps_per_second": 6.467, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.03276897870016385, | |
| "grad_norm": 16.86937713623047, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 2.1047, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.04369197160021846, | |
| "grad_norm": 8.117836952209473, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 1.0811, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.04369197160021846, | |
| "eval_loss": 0.9471554160118103, | |
| "eval_runtime": 15.0355, | |
| "eval_samples_per_second": 12.836, | |
| "eval_steps_per_second": 6.451, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.054614964500273075, | |
| "grad_norm": 12.76759147644043, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.9381, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0655379574003277, | |
| "grad_norm": 6.152534008026123, | |
| "learning_rate": 5e-05, | |
| "loss": 0.9934, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0655379574003277, | |
| "eval_loss": 0.8336125612258911, | |
| "eval_runtime": 15.1256, | |
| "eval_samples_per_second": 12.76, | |
| "eval_steps_per_second": 6.413, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0764609503003823, | |
| "grad_norm": 14.56964111328125, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.7678, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.08738394320043692, | |
| "grad_norm": 14.080451965332031, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.8416, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.08738394320043692, | |
| "eval_loss": 0.8112453818321228, | |
| "eval_runtime": 15.2147, | |
| "eval_samples_per_second": 12.685, | |
| "eval_steps_per_second": 6.375, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.09830693610049153, | |
| "grad_norm": 9.87679386138916, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.9493, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.10922992900054615, | |
| "grad_norm": 12.29512882232666, | |
| "learning_rate": 0.0, | |
| "loss": 0.7734, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.10922992900054615, | |
| "eval_loss": 0.8227449059486389, | |
| "eval_runtime": 15.1364, | |
| "eval_samples_per_second": 12.751, | |
| "eval_steps_per_second": 6.408, | |
| "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": 9603234366750720.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |