| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.9965714285714286, | |
| "eval_steps": 500, | |
| "global_step": 109, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.009142857142857144, | |
| "grad_norm": 2.635891914367676, | |
| "learning_rate": 1.8181818181818183e-06, | |
| "loss": 9.7005, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.045714285714285714, | |
| "grad_norm": 2.669848680496216, | |
| "learning_rate": 9.090909090909091e-06, | |
| "loss": 9.3658, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.09142857142857143, | |
| "grad_norm": 2.1069536209106445, | |
| "learning_rate": 1.8181818181818182e-05, | |
| "loss": 9.1556, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.13714285714285715, | |
| "grad_norm": 1.8738576173782349, | |
| "learning_rate": 1.991790013823246e-05, | |
| "loss": 8.9444, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.18285714285714286, | |
| "grad_norm": 1.5760283470153809, | |
| "learning_rate": 1.9586678530366607e-05, | |
| "loss": 8.5402, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.22857142857142856, | |
| "grad_norm": 1.3902924060821533, | |
| "learning_rate": 1.900968867902419e-05, | |
| "loss": 8.4052, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.2742857142857143, | |
| "grad_norm": 1.3036909103393555, | |
| "learning_rate": 1.820172254596956e-05, | |
| "loss": 8.5012, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "grad_norm": 1.4191102981567383, | |
| "learning_rate": 1.7183493500977277e-05, | |
| "loss": 8.3836, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.3657142857142857, | |
| "grad_norm": 1.3017487525939941, | |
| "learning_rate": 1.598110530491216e-05, | |
| "loss": 8.376, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.4114285714285714, | |
| "grad_norm": 0.9578719139099121, | |
| "learning_rate": 1.4625382902408356e-05, | |
| "loss": 8.346, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.45714285714285713, | |
| "grad_norm": 0.884999692440033, | |
| "learning_rate": 1.315108218023621e-05, | |
| "loss": 8.1656, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.5028571428571429, | |
| "grad_norm": 0.8994832634925842, | |
| "learning_rate": 1.1595998950333794e-05, | |
| "loss": 8.2717, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.5485714285714286, | |
| "grad_norm": 0.8586516976356506, | |
| "learning_rate": 1e-05, | |
| "loss": 8.2746, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.5942857142857143, | |
| "grad_norm": 0.8844101428985596, | |
| "learning_rate": 8.404001049666211e-06, | |
| "loss": 8.1344, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "grad_norm": 0.857933521270752, | |
| "learning_rate": 6.848917819763794e-06, | |
| "loss": 8.0928, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.6857142857142857, | |
| "grad_norm": 0.8832647204399109, | |
| "learning_rate": 5.37461709759165e-06, | |
| "loss": 8.2155, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.7314285714285714, | |
| "grad_norm": 0.8684210777282715, | |
| "learning_rate": 4.01889469508784e-06, | |
| "loss": 8.1696, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.7771428571428571, | |
| "grad_norm": 0.8870261311531067, | |
| "learning_rate": 2.8165064990227255e-06, | |
| "loss": 8.0587, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.8228571428571428, | |
| "grad_norm": 0.8674476146697998, | |
| "learning_rate": 1.7982774540304404e-06, | |
| "loss": 8.2368, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.8685714285714285, | |
| "grad_norm": 0.8507274985313416, | |
| "learning_rate": 9.903113209758098e-07, | |
| "loss": 8.081, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.9142857142857143, | |
| "grad_norm": 0.8538458347320557, | |
| "learning_rate": 4.133214696333943e-07, | |
| "loss": 8.2492, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "grad_norm": 0.8556557893753052, | |
| "learning_rate": 8.209986176753947e-08, | |
| "loss": 8.2279, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.9965714285714286, | |
| "eval_loss": 1.0207911729812622, | |
| "eval_runtime": 10395.2442, | |
| "eval_samples_per_second": 1.484, | |
| "eval_steps_per_second": 0.186, | |
| "step": 109 | |
| }, | |
| { | |
| "epoch": 0.9965714285714286, | |
| "step": 109, | |
| "total_flos": 6.131289443249684e+17, | |
| "train_loss": 8.393078707773752, | |
| "train_runtime": 26246.6491, | |
| "train_samples_per_second": 0.267, | |
| "train_steps_per_second": 0.004 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 109, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 100, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 6.131289443249684e+17, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |