| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.5181347150259067, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.010362694300518135, | |
| "eval_loss": 3.649900197982788, | |
| "eval_runtime": 0.7545, | |
| "eval_samples_per_second": 54.343, | |
| "eval_steps_per_second": 27.834, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.05181347150259067, | |
| "grad_norm": 2.8373703956604004, | |
| "learning_rate": 5e-05, | |
| "loss": 3.5652, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.10362694300518134, | |
| "grad_norm": 2.706880569458008, | |
| "learning_rate": 0.0001, | |
| "loss": 3.4354, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.10362694300518134, | |
| "eval_loss": 3.3804771900177, | |
| "eval_runtime": 0.7498, | |
| "eval_samples_per_second": 54.684, | |
| "eval_steps_per_second": 28.009, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.15544041450777202, | |
| "grad_norm": 1.4844454526901245, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 3.2829, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.20725388601036268, | |
| "grad_norm": 1.2455134391784668, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 3.0929, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.20725388601036268, | |
| "eval_loss": 3.0835258960723877, | |
| "eval_runtime": 0.7639, | |
| "eval_samples_per_second": 53.673, | |
| "eval_steps_per_second": 27.491, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.25906735751295334, | |
| "grad_norm": 0.8904907703399658, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 3.0248, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.31088082901554404, | |
| "grad_norm": 0.9830533266067505, | |
| "learning_rate": 5e-05, | |
| "loss": 2.9533, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.31088082901554404, | |
| "eval_loss": 2.9466686248779297, | |
| "eval_runtime": 0.8016, | |
| "eval_samples_per_second": 51.146, | |
| "eval_steps_per_second": 26.197, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.3626943005181347, | |
| "grad_norm": 1.1721653938293457, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 2.8659, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.41450777202072536, | |
| "grad_norm": 1.0541706085205078, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 2.863, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.41450777202072536, | |
| "eval_loss": 2.8699629306793213, | |
| "eval_runtime": 0.7571, | |
| "eval_samples_per_second": 54.151, | |
| "eval_steps_per_second": 27.736, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.46632124352331605, | |
| "grad_norm": 0.825079619884491, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 2.7591, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.5181347150259067, | |
| "grad_norm": 1.0289149284362793, | |
| "learning_rate": 0.0, | |
| "loss": 2.8184, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.5181347150259067, | |
| "eval_loss": 2.857125759124756, | |
| "eval_runtime": 0.7555, | |
| "eval_samples_per_second": 54.266, | |
| "eval_steps_per_second": 27.795, | |
| "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": 171463252377600.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |