| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.048028817290374226, | |
| "eval_steps": 50, | |
| "global_step": 300, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 2.272727272727273e-05, | |
| "loss": 1.2333, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "eval_loss": 0.9392214417457581, | |
| "eval_runtime": 4053.3544, | |
| "eval_samples_per_second": 12.328, | |
| "eval_steps_per_second": 1.541, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 2.0202020202020203e-05, | |
| "loss": 0.9153, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "eval_loss": 0.8664643168449402, | |
| "eval_runtime": 4052.1353, | |
| "eval_samples_per_second": 12.332, | |
| "eval_steps_per_second": 1.542, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 1.7676767676767676e-05, | |
| "loss": 0.8489, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "eval_loss": 0.8392552733421326, | |
| "eval_runtime": 4051.5661, | |
| "eval_samples_per_second": 12.333, | |
| "eval_steps_per_second": 1.542, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 1.5151515151515153e-05, | |
| "loss": 0.8405, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "eval_loss": 0.8204770684242249, | |
| "eval_runtime": 4049.9004, | |
| "eval_samples_per_second": 12.338, | |
| "eval_steps_per_second": 1.543, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 1.2626262626262628e-05, | |
| "loss": 0.826, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "eval_loss": 0.8067930340766907, | |
| "eval_runtime": 4050.2988, | |
| "eval_samples_per_second": 12.337, | |
| "eval_steps_per_second": 1.542, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 1.0101010101010101e-05, | |
| "loss": 0.8077, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "eval_loss": 0.7965855002403259, | |
| "eval_runtime": 4052.9604, | |
| "eval_samples_per_second": 12.329, | |
| "eval_steps_per_second": 1.541, | |
| "step": 300 | |
| } | |
| ], | |
| "logging_steps": 50, | |
| "max_steps": 500, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 50, | |
| "total_flos": 5.25822226071552e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |