| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 1.0, |
| "eval_steps": 1000, |
| "global_step": 3247, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.0003079765937788728, |
| "grad_norm": 5.27286434173584, |
| "learning_rate": 0.0, |
| "loss": 3.17, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.3079765937788728, |
| "grad_norm": 3.784266710281372, |
| "learning_rate": 2.30715935334873e-05, |
| "loss": 2.2231, |
| "step": 1000 |
| }, |
| { |
| "epoch": 0.3079765937788728, |
| "eval_cosine_accuracy": 0.960388720035553, |
| "eval_loss": 1.1210521459579468, |
| "eval_runtime": 24.6573, |
| "eval_samples_per_second": 383.944, |
| "eval_steps_per_second": 1.501, |
| "step": 1000 |
| }, |
| { |
| "epoch": 0.6159531875577456, |
| "grad_norm": 4.136064052581787, |
| "learning_rate": 2.8203439130806744e-05, |
| "loss": 1.623, |
| "step": 2000 |
| }, |
| { |
| "epoch": 0.6159531875577456, |
| "eval_cosine_accuracy": 0.9700010418891907, |
| "eval_loss": 1.0202350616455078, |
| "eval_runtime": 23.9452, |
| "eval_samples_per_second": 395.361, |
| "eval_steps_per_second": 1.545, |
| "step": 2000 |
| }, |
| { |
| "epoch": 0.9239297813366184, |
| "grad_norm": 3.366196632385254, |
| "learning_rate": 2.56369236033878e-05, |
| "loss": 1.6346, |
| "step": 3000 |
| }, |
| { |
| "epoch": 0.9239297813366184, |
| "eval_cosine_accuracy": 0.9733812212944031, |
| "eval_loss": 0.8886165022850037, |
| "eval_runtime": 23.9611, |
| "eval_samples_per_second": 395.099, |
| "eval_steps_per_second": 1.544, |
| "step": 3000 |
| } |
| ], |
| "logging_steps": 1000, |
| "max_steps": 12988, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 4, |
| "save_steps": 500, |
| "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": 256, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
