| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "eval_steps": 100, | |
| "global_step": 204, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.004901960784313725, | |
| "grad_norm": 4.354541415718554e+17, | |
| "learning_rate": 9.523809523809525e-07, | |
| "loss": 1.8316, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.24509803921568626, | |
| "grad_norm": 0.6281739182438495, | |
| "learning_rate": 1.8786122450571485e-05, | |
| "loss": 1.4365, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.49019607843137253, | |
| "grad_norm": 0.48423706509595926, | |
| "learning_rate": 1.2129465199384158e-05, | |
| "loss": 1.2304, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.49019607843137253, | |
| "eval_loss": 1.217398762702942, | |
| "eval_runtime": 2.3219, | |
| "eval_samples_per_second": 88.721, | |
| "eval_steps_per_second": 3.015, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.7352941176470589, | |
| "grad_norm": 0.45972785208467654, | |
| "learning_rate": 3.997857194516319e-06, | |
| "loss": 1.1994, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.9803921568627451, | |
| "grad_norm": 0.4300550081300119, | |
| "learning_rate": 2.3567683139936736e-08, | |
| "loss": 1.1813, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.9803921568627451, | |
| "eval_loss": 1.1812692880630493, | |
| "eval_runtime": 2.2306, | |
| "eval_samples_per_second": 92.351, | |
| "eval_steps_per_second": 3.138, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "step": 204, | |
| "total_flos": 42608759930880.0, | |
| "train_loss": 1.261282390239192, | |
| "train_runtime": 737.9605, | |
| "train_samples_per_second": 17.676, | |
| "train_steps_per_second": 0.276 | |
| } | |
| ], | |
| "logging_steps": 50, | |
| "max_steps": 204, | |
| "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": 42608759930880.0, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |