| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 2.9879518072289155, |
| "eval_steps": 500, |
| "global_step": 186, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.1606425702811245, |
| "grad_norm": 0.1789746880531311, |
| "learning_rate": 0.0002, |
| "loss": 0.9249, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.321285140562249, |
| "grad_norm": 0.143571138381958, |
| "learning_rate": 0.0002, |
| "loss": 0.6491, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.4819277108433735, |
| "grad_norm": 0.12150721997022629, |
| "learning_rate": 0.0002, |
| "loss": 0.5985, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.642570281124498, |
| "grad_norm": 0.10915827751159668, |
| "learning_rate": 0.0002, |
| "loss": 0.644, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.8032128514056225, |
| "grad_norm": 0.10958955436944962, |
| "learning_rate": 0.0002, |
| "loss": 0.5759, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.963855421686747, |
| "grad_norm": 0.08871103078126907, |
| "learning_rate": 0.0002, |
| "loss": 0.5609, |
| "step": 60 |
| }, |
| { |
| "epoch": 1.1244979919678715, |
| "grad_norm": 0.08688271045684814, |
| "learning_rate": 0.0002, |
| "loss": 0.5088, |
| "step": 70 |
| }, |
| { |
| "epoch": 1.285140562248996, |
| "grad_norm": 0.088297538459301, |
| "learning_rate": 0.0002, |
| "loss": 0.4951, |
| "step": 80 |
| }, |
| { |
| "epoch": 1.4457831325301205, |
| "grad_norm": 0.09266702085733414, |
| "learning_rate": 0.0002, |
| "loss": 0.4808, |
| "step": 90 |
| }, |
| { |
| "epoch": 1.606425702811245, |
| "grad_norm": 0.08945482224225998, |
| "learning_rate": 0.0002, |
| "loss": 0.4818, |
| "step": 100 |
| }, |
| { |
| "epoch": 1.7670682730923695, |
| "grad_norm": 0.08632655441761017, |
| "learning_rate": 0.0002, |
| "loss": 0.4836, |
| "step": 110 |
| }, |
| { |
| "epoch": 1.927710843373494, |
| "grad_norm": 0.09446747601032257, |
| "learning_rate": 0.0002, |
| "loss": 0.4791, |
| "step": 120 |
| }, |
| { |
| "epoch": 2.0883534136546187, |
| "grad_norm": 0.11169935017824173, |
| "learning_rate": 0.0002, |
| "loss": 0.4373, |
| "step": 130 |
| }, |
| { |
| "epoch": 2.248995983935743, |
| "grad_norm": 0.11277974396944046, |
| "learning_rate": 0.0002, |
| "loss": 0.3987, |
| "step": 140 |
| }, |
| { |
| "epoch": 2.4096385542168672, |
| "grad_norm": 0.11896611750125885, |
| "learning_rate": 0.0002, |
| "loss": 0.4026, |
| "step": 150 |
| }, |
| { |
| "epoch": 2.570281124497992, |
| "grad_norm": 0.11799568682909012, |
| "learning_rate": 0.0002, |
| "loss": 0.4035, |
| "step": 160 |
| }, |
| { |
| "epoch": 2.7309236947791167, |
| "grad_norm": 0.10658109933137894, |
| "learning_rate": 0.0002, |
| "loss": 0.4003, |
| "step": 170 |
| }, |
| { |
| "epoch": 2.891566265060241, |
| "grad_norm": 0.12032566964626312, |
| "learning_rate": 0.0002, |
| "loss": 0.4095, |
| "step": 180 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 186, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 3, |
| "save_steps": 500, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 1.4949482493483418e+17, |
| "train_batch_size": 1, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
