| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 2.0, |
| "eval_steps": 4000, |
| "global_step": 9064, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.17655172413793102, |
| "grad_norm": 0.11938353627920151, |
| "learning_rate": 8.809261300992283e-05, |
| "loss": 1.2362, |
| "step": 800 |
| }, |
| { |
| "epoch": 0.35310344827586204, |
| "grad_norm": 0.148575097322464, |
| "learning_rate": 9.823469895169365e-05, |
| "loss": 0.9159, |
| "step": 1600 |
| }, |
| { |
| "epoch": 0.5296551724137931, |
| "grad_norm": 0.21376433968544006, |
| "learning_rate": 9.19696754273079e-05, |
| "loss": 0.9125, |
| "step": 2400 |
| }, |
| { |
| "epoch": 0.7062068965517241, |
| "grad_norm": 0.09860826283693314, |
| "learning_rate": 8.175175096510351e-05, |
| "loss": 0.9134, |
| "step": 3200 |
| }, |
| { |
| "epoch": 0.8827586206896552, |
| "grad_norm": 0.11440066993236542, |
| "learning_rate": 6.854329762962416e-05, |
| "loss": 0.9108, |
| "step": 4000 |
| }, |
| { |
| "epoch": 0.8827586206896552, |
| "eval_loss": 0.9154898524284363, |
| "eval_runtime": 247.4123, |
| "eval_samples_per_second": 121.255, |
| "eval_steps_per_second": 7.578, |
| "step": 4000 |
| }, |
| { |
| "epoch": 1.059144827586207, |
| "grad_norm": 0.10314279049634933, |
| "learning_rate": 5.358834952514551e-05, |
| "loss": 0.9084, |
| "step": 4800 |
| }, |
| { |
| "epoch": 1.2356965517241378, |
| "grad_norm": 0.15208840370178223, |
| "learning_rate": 3.8295433827190085e-05, |
| "loss": 0.9046, |
| "step": 5600 |
| }, |
| { |
| "epoch": 1.412248275862069, |
| "grad_norm": 0.10573920607566833, |
| "learning_rate": 2.4104909084852035e-05, |
| "loss": 0.9043, |
| "step": 6400 |
| }, |
| { |
| "epoch": 1.5888, |
| "grad_norm": 0.2402600795030594, |
| "learning_rate": 1.2353305495017958e-05, |
| "loss": 0.9047, |
| "step": 7200 |
| }, |
| { |
| "epoch": 1.765351724137931, |
| "grad_norm": 0.10216963291168213, |
| "learning_rate": 4.147444217922592e-06, |
| "loss": 0.904, |
| "step": 8000 |
| }, |
| { |
| "epoch": 1.765351724137931, |
| "eval_loss": 0.9144690036773682, |
| "eval_runtime": 247.1254, |
| "eval_samples_per_second": 121.396, |
| "eval_steps_per_second": 7.587, |
| "step": 8000 |
| }, |
| { |
| "epoch": 1.9419034482758621, |
| "grad_norm": 0.17538346350193024, |
| "learning_rate": 2.6019176748554587e-07, |
| "loss": 0.9044, |
| "step": 8800 |
| }, |
| { |
| "epoch": 2.0, |
| "step": 9064, |
| "total_flos": 1.2106519982783857e+19, |
| "train_loss": 0.9370549143886313, |
| "train_runtime": 28045.4399, |
| "train_samples_per_second": 41.361, |
| "train_steps_per_second": 0.323 |
| } |
| ], |
| "logging_steps": 800, |
| "max_steps": 9064, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 2, |
| "save_steps": 4000, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 1.2106519982783857e+19, |
| "train_batch_size": 4, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
