| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0003470715835140998, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 3.470715835140998e-05, | |
| "grad_norm": 7.366649627685547, | |
| "learning_rate": 2e-05, | |
| "loss": 6.754, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 3.470715835140998e-05, | |
| "eval_loss": 1.3082431554794312, | |
| "eval_runtime": 323.5438, | |
| "eval_samples_per_second": 37.497, | |
| "eval_steps_per_second": 18.749, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 6.941431670281996e-05, | |
| "grad_norm": 2.6472208499908447, | |
| "learning_rate": 4e-05, | |
| "loss": 5.6375, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.00010412147505422994, | |
| "grad_norm": 2.7043254375457764, | |
| "learning_rate": 6e-05, | |
| "loss": 4.9946, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00010412147505422994, | |
| "eval_loss": 1.3049659729003906, | |
| "eval_runtime": 320.7522, | |
| "eval_samples_per_second": 37.824, | |
| "eval_steps_per_second": 18.912, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00013882863340563992, | |
| "grad_norm": 2.3599693775177, | |
| "learning_rate": 8e-05, | |
| "loss": 5.1925, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0001735357917570499, | |
| "grad_norm": 5.262383937835693, | |
| "learning_rate": 0.0001, | |
| "loss": 6.9685, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00020824295010845987, | |
| "grad_norm": 2.1987497806549072, | |
| "learning_rate": 0.00012, | |
| "loss": 4.5352, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00020824295010845987, | |
| "eval_loss": 1.2795846462249756, | |
| "eval_runtime": 322.719, | |
| "eval_samples_per_second": 37.593, | |
| "eval_steps_per_second": 18.797, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00024295010845986985, | |
| "grad_norm": 2.4121720790863037, | |
| "learning_rate": 0.00014, | |
| "loss": 4.9644, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.00027765726681127983, | |
| "grad_norm": 2.359161138534546, | |
| "learning_rate": 0.00016, | |
| "loss": 4.4947, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0003123644251626898, | |
| "grad_norm": 4.865494251251221, | |
| "learning_rate": 0.00018, | |
| "loss": 5.1167, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0003123644251626898, | |
| "eval_loss": 1.2180023193359375, | |
| "eval_runtime": 321.3039, | |
| "eval_samples_per_second": 37.759, | |
| "eval_steps_per_second": 18.879, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0003470715835140998, | |
| "grad_norm": 3.2266299724578857, | |
| "learning_rate": 0.0002, | |
| "loss": 5.1224, | |
| "step": 10 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 10, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 3, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1110013850419200.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |