| { | |
| "best_metric": 1.8831839561462402, | |
| "best_model_checkpoint": "./output/checkpoint-150", | |
| "epoch": 0.016123831022250887, | |
| "eval_steps": 150, | |
| "global_step": 150, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.001074922068150059, | |
| "grad_norm": 43.13871765136719, | |
| "learning_rate": 4.125e-06, | |
| "loss": 2.2922, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.002149844136300118, | |
| "grad_norm": 26.323883056640625, | |
| "learning_rate": 8.25e-06, | |
| "loss": 2.1328, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0032247662044501773, | |
| "grad_norm": 17.629505157470703, | |
| "learning_rate": 1.2375e-05, | |
| "loss": 2.036, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.004299688272600236, | |
| "grad_norm": 10.648378372192383, | |
| "learning_rate": 1.65e-05, | |
| "loss": 1.851, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.005374610340750295, | |
| "grad_norm": 17.73092269897461, | |
| "learning_rate": 2.0625e-05, | |
| "loss": 1.8746, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.0064495324089003546, | |
| "grad_norm": 6.716779708862305, | |
| "learning_rate": 2.475e-05, | |
| "loss": 1.8512, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.007524454477050414, | |
| "grad_norm": 15.877828598022461, | |
| "learning_rate": 2.8874999999999997e-05, | |
| "loss": 1.9416, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.008599376545200472, | |
| "grad_norm": 14.675684928894043, | |
| "learning_rate": 3.3e-05, | |
| "loss": 1.8581, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.009674298613350531, | |
| "grad_norm": 11.489137649536133, | |
| "learning_rate": 3.7125e-05, | |
| "loss": 1.9017, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.01074922068150059, | |
| "grad_norm": 7.483497619628906, | |
| "learning_rate": 4.125e-05, | |
| "loss": 1.9335, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.01182414274965065, | |
| "grad_norm": 9.6410551071167, | |
| "learning_rate": 4.12495760935163e-05, | |
| "loss": 1.7841, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.012899064817800709, | |
| "grad_norm": 7.8748979568481445, | |
| "learning_rate": 4.1248304391490334e-05, | |
| "loss": 1.8529, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.013973986885950768, | |
| "grad_norm": 9.455327987670898, | |
| "learning_rate": 4.1246184946196796e-05, | |
| "loss": 1.9366, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.015048908954100828, | |
| "grad_norm": 8.64035701751709, | |
| "learning_rate": 4.124321784475777e-05, | |
| "loss": 1.8501, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.016123831022250887, | |
| "grad_norm": 13.220332145690918, | |
| "learning_rate": 4.123940320913919e-05, | |
| "loss": 1.9095, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.016123831022250887, | |
| "eval_loss": 1.8831839561462402, | |
| "eval_runtime": 61.5136, | |
| "eval_samples_per_second": 8.128, | |
| "eval_steps_per_second": 8.128, | |
| "step": 150 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 5000, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 150, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3.941968917351629e+16, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |