| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0187952260125928, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.000375904520251856, | |
| "eval_loss": 0.21463054418563843, | |
| "eval_runtime": 36.1147, | |
| "eval_samples_per_second": 31.04, | |
| "eval_steps_per_second": 15.534, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0018795226012592802, | |
| "grad_norm": 0.2339801788330078, | |
| "learning_rate": 5e-05, | |
| "loss": 0.2231, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0037590452025185604, | |
| "grad_norm": 0.2417314499616623, | |
| "learning_rate": 0.0001, | |
| "loss": 0.1748, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0037590452025185604, | |
| "eval_loss": 0.19670066237449646, | |
| "eval_runtime": 36.3366, | |
| "eval_samples_per_second": 30.85, | |
| "eval_steps_per_second": 15.439, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.00563856780377784, | |
| "grad_norm": 0.23296763002872467, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.1673, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.007518090405037121, | |
| "grad_norm": 1.240827202796936, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.2802, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.007518090405037121, | |
| "eval_loss": 0.15440116822719574, | |
| "eval_runtime": 36.498, | |
| "eval_samples_per_second": 30.714, | |
| "eval_steps_per_second": 15.371, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0093976130062964, | |
| "grad_norm": 0.27838045358657837, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.1353, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.01127713560755568, | |
| "grad_norm": 0.20593693852424622, | |
| "learning_rate": 5e-05, | |
| "loss": 0.1406, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.01127713560755568, | |
| "eval_loss": 0.13961468636989594, | |
| "eval_runtime": 36.6273, | |
| "eval_samples_per_second": 30.606, | |
| "eval_steps_per_second": 15.316, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.013156658208814962, | |
| "grad_norm": 0.2440294474363327, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.1878, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.015036180810074242, | |
| "grad_norm": 1.2875986099243164, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.2164, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.015036180810074242, | |
| "eval_loss": 0.13373848795890808, | |
| "eval_runtime": 36.5736, | |
| "eval_samples_per_second": 30.651, | |
| "eval_steps_per_second": 15.339, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.01691570341133352, | |
| "grad_norm": 0.1800977885723114, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.1561, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.0187952260125928, | |
| "grad_norm": 0.278409481048584, | |
| "learning_rate": 0.0, | |
| "loss": 0.125, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.0187952260125928, | |
| "eval_loss": 0.13275748491287231, | |
| "eval_runtime": 36.656, | |
| "eval_samples_per_second": 30.582, | |
| "eval_steps_per_second": 15.304, | |
| "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": 2468392590114816.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |