| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.888888888888889, | |
| "eval_steps": 500, | |
| "global_step": 24, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 9.999999999999999e-06, | |
| "loss": 1.7694, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 1.9999999999999998e-05, | |
| "loss": 1.9243, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 3e-05, | |
| "loss": 2.0994, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 2.875e-05, | |
| "loss": 1.8787, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 2.75e-05, | |
| "loss": 1.9916, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 2.625e-05, | |
| "loss": 1.9369, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 2.5e-05, | |
| "loss": 1.9494, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 2.3749999999999998e-05, | |
| "loss": 2.0855, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "learning_rate": 2.25e-05, | |
| "loss": 2.0216, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "learning_rate": 2.125e-05, | |
| "loss": 1.8724, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "learning_rate": 1.9999999999999998e-05, | |
| "loss": 1.8561, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "learning_rate": 1.8750000000000002e-05, | |
| "loss": 1.9997, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "learning_rate": 1.7500000000000002e-05, | |
| "loss": 1.7089, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 1.67, | |
| "learning_rate": 1.625e-05, | |
| "loss": 1.9458, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 1.78, | |
| "learning_rate": 1.5e-05, | |
| "loss": 1.7845, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 1.89, | |
| "learning_rate": 1.375e-05, | |
| "loss": 1.9242, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 2.11, | |
| "learning_rate": 1.25e-05, | |
| "loss": 1.6615, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 2.22, | |
| "learning_rate": 1.125e-05, | |
| "loss": 1.9213, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 2.33, | |
| "learning_rate": 9.999999999999999e-06, | |
| "loss": 1.8328, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 2.44, | |
| "learning_rate": 8.750000000000001e-06, | |
| "loss": 1.8141, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 2.56, | |
| "learning_rate": 7.5e-06, | |
| "loss": 1.9057, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 2.67, | |
| "learning_rate": 6.25e-06, | |
| "loss": 1.7507, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 2.78, | |
| "learning_rate": 4.9999999999999996e-06, | |
| "loss": 1.9675, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 2.89, | |
| "learning_rate": 3.75e-06, | |
| "loss": 1.9288, | |
| "step": 24 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 27, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 500, | |
| "total_flos": 1967839720243200.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |