| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.716161158895428, | |
| "eval_steps": 1000, | |
| "global_step": 6000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.22634676324128564, | |
| "grad_norm": 1076.2171630859375, | |
| "learning_rate": 3.770739064856712e-06, | |
| "loss": 160.1889, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.4526935264825713, | |
| "grad_norm": 881.1419677734375, | |
| "learning_rate": 7.541478129713424e-06, | |
| "loss": 96.3458, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.4526935264825713, | |
| "eval_loss": 76.46768188476562, | |
| "eval_runtime": 176.6442, | |
| "eval_samples_per_second": 11.118, | |
| "eval_steps_per_second": 1.393, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.679040289723857, | |
| "grad_norm": 794.5887451171875, | |
| "learning_rate": 9.854124748490947e-06, | |
| "loss": 80.5069, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.9053870529651425, | |
| "grad_norm": 963.1815795898438, | |
| "learning_rate": 9.43494299128102e-06, | |
| "loss": 72.5744, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.9053870529651425, | |
| "eval_loss": 61.90445327758789, | |
| "eval_runtime": 183.6264, | |
| "eval_samples_per_second": 10.696, | |
| "eval_steps_per_second": 1.34, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 1.1317338162064283, | |
| "grad_norm": 921.5068359375, | |
| "learning_rate": 9.015761234071095e-06, | |
| "loss": 65.6815, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 1.358080579447714, | |
| "grad_norm": 855.2803955078125, | |
| "learning_rate": 8.596579476861168e-06, | |
| "loss": 61.6207, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 1.358080579447714, | |
| "eval_loss": 57.32611846923828, | |
| "eval_runtime": 184.8952, | |
| "eval_samples_per_second": 10.622, | |
| "eval_steps_per_second": 1.33, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 1.5844273426889997, | |
| "grad_norm": 1172.0072021484375, | |
| "learning_rate": 8.177397719651241e-06, | |
| "loss": 61.3402, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 1.8107741059302853, | |
| "grad_norm": 979.0298461914062, | |
| "learning_rate": 7.758215962441316e-06, | |
| "loss": 63.4637, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 1.8107741059302853, | |
| "eval_loss": 54.714115142822266, | |
| "eval_runtime": 178.8924, | |
| "eval_samples_per_second": 10.979, | |
| "eval_steps_per_second": 1.375, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 2.037120869171571, | |
| "grad_norm": 2496.968017578125, | |
| "learning_rate": 7.339034205231389e-06, | |
| "loss": 57.3627, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 2.2634676324128566, | |
| "grad_norm": 965.2960815429688, | |
| "learning_rate": 6.919852448021462e-06, | |
| "loss": 55.2798, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 2.2634676324128566, | |
| "eval_loss": 52.85610580444336, | |
| "eval_runtime": 175.63, | |
| "eval_samples_per_second": 11.183, | |
| "eval_steps_per_second": 1.401, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 2.4898143956541423, | |
| "grad_norm": 1013.7318115234375, | |
| "learning_rate": 6.500670690811537e-06, | |
| "loss": 54.6516, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 2.716161158895428, | |
| "grad_norm": 995.4374389648438, | |
| "learning_rate": 6.08148893360161e-06, | |
| "loss": 54.9203, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 2.716161158895428, | |
| "eval_loss": 53.687313079833984, | |
| "eval_runtime": 173.1278, | |
| "eval_samples_per_second": 11.344, | |
| "eval_steps_per_second": 1.421, | |
| "step": 6000 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 13254, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 6, | |
| "save_steps": 1000, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 0.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |