| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.7238683524756298, |
| "eval_steps": 10000, |
| "global_step": 30000, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 2.412894508252099e-05, |
| "grad_norm": 4.8172993659973145, |
| "learning_rate": 0.0, |
| "loss": 3.8384, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.24128945082520992, |
| "grad_norm": 2.6814990043640137, |
| "learning_rate": 3.6183432666554063e-06, |
| "loss": 2.9764, |
| "step": 10000 |
| }, |
| { |
| "epoch": 0.24128945082520992, |
| "eval_cosine_accuracy": 0.9525219202041626, |
| "eval_loss": 1.2816005945205688, |
| "eval_runtime": 25.5253, |
| "eval_samples_per_second": 370.495, |
| "eval_steps_per_second": 0.744, |
| "step": 10000 |
| }, |
| { |
| "epoch": 0.48257890165041983, |
| "grad_norm": 2.516390323638916, |
| "learning_rate": 7.235962647491736e-06, |
| "loss": 2.3257, |
| "step": 20000 |
| }, |
| { |
| "epoch": 0.48257890165041983, |
| "eval_cosine_accuracy": 0.9563286304473877, |
| "eval_loss": 1.2216517925262451, |
| "eval_runtime": 27.1816, |
| "eval_samples_per_second": 347.919, |
| "eval_steps_per_second": 0.699, |
| "step": 20000 |
| }, |
| { |
| "epoch": 0.7238683524756298, |
| "grad_norm": 2.6789209842681885, |
| "learning_rate": 1.0854305914147143e-05, |
| "loss": 2.1003, |
| "step": 30000 |
| }, |
| { |
| "epoch": 0.7238683524756298, |
| "eval_cosine_accuracy": 0.9602410793304443, |
| "eval_loss": 1.1404365301132202, |
| "eval_runtime": 29.5686, |
| "eval_samples_per_second": 319.833, |
| "eval_steps_per_second": 0.643, |
| "step": 30000 |
| } |
| ], |
| "logging_steps": 10000, |
| "max_steps": 165776, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 4, |
| "save_steps": 30000, |
| "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": 512, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
