| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.16, |
| "eval_steps": 50, |
| "global_step": 100, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.016, |
| "grad_norm": 0.2649502456188202, |
| "learning_rate": 0.00019870967741935483, |
| "loss": 0.296, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.032, |
| "grad_norm": 0.3341752588748932, |
| "learning_rate": 0.00019548387096774195, |
| "loss": 0.278, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.048, |
| "grad_norm": 0.29673072695732117, |
| "learning_rate": 0.00019225806451612904, |
| "loss": 0.2872, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.064, |
| "grad_norm": 0.27321192622184753, |
| "learning_rate": 0.00018903225806451616, |
| "loss": 0.2884, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.08, |
| "grad_norm": 0.28777027130126953, |
| "learning_rate": 0.00018580645161290325, |
| "loss": 0.287, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.08, |
| "eval_loss": 0.2932877540588379, |
| "eval_runtime": 573.3368, |
| "eval_samples_per_second": 0.872, |
| "eval_steps_per_second": 0.218, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.096, |
| "grad_norm": 0.27004000544548035, |
| "learning_rate": 0.00018258064516129033, |
| "loss": 0.2846, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.112, |
| "grad_norm": 0.24109533429145813, |
| "learning_rate": 0.00017935483870967742, |
| "loss": 0.2828, |
| "step": 70 |
| }, |
| { |
| "epoch": 0.128, |
| "grad_norm": 0.2596932649612427, |
| "learning_rate": 0.0001761290322580645, |
| "loss": 0.277, |
| "step": 80 |
| }, |
| { |
| "epoch": 0.144, |
| "grad_norm": 0.2961156964302063, |
| "learning_rate": 0.00017290322580645163, |
| "loss": 0.29, |
| "step": 90 |
| }, |
| { |
| "epoch": 0.16, |
| "grad_norm": 0.3086676597595215, |
| "learning_rate": 0.00016967741935483872, |
| "loss": 0.2883, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.16, |
| "eval_loss": 0.28304216265678406, |
| "eval_runtime": 519.1154, |
| "eval_samples_per_second": 0.963, |
| "eval_steps_per_second": 0.241, |
| "step": 100 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 625, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 1, |
| "save_steps": 50, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 8826978008930304.0, |
| "train_batch_size": 2, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
