| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.0016209294409414358, |
| "eval_steps": 13, |
| "global_step": 50, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 3.241858881882872e-05, |
| "eval_loss": 2.248764753341675, |
| "eval_runtime": 206.9215, |
| "eval_samples_per_second": 62.768, |
| "eval_steps_per_second": 31.384, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.0003241858881882872, |
| "grad_norm": 1.310923457145691, |
| "learning_rate": 0.0002, |
| "loss": 2.0525, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.00042144165464477333, |
| "eval_loss": 1.8687516450881958, |
| "eval_runtime": 206.448, |
| "eval_samples_per_second": 62.912, |
| "eval_steps_per_second": 31.456, |
| "step": 13 |
| }, |
| { |
| "epoch": 0.0006483717763765744, |
| "grad_norm": 0.7833124995231628, |
| "learning_rate": 0.0002, |
| "loss": 1.8226, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.0008428833092895467, |
| "eval_loss": 1.802367925643921, |
| "eval_runtime": 207.0854, |
| "eval_samples_per_second": 62.718, |
| "eval_steps_per_second": 31.359, |
| "step": 26 |
| }, |
| { |
| "epoch": 0.0009725576645648615, |
| "grad_norm": 0.9726564884185791, |
| "learning_rate": 0.0002, |
| "loss": 1.7184, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.00126432496393432, |
| "eval_loss": 1.7781810760498047, |
| "eval_runtime": 206.9688, |
| "eval_samples_per_second": 62.753, |
| "eval_steps_per_second": 31.377, |
| "step": 39 |
| }, |
| { |
| "epoch": 0.0012967435527531487, |
| "grad_norm": 0.8452262878417969, |
| "learning_rate": 0.0002, |
| "loss": 1.5871, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.0016209294409414358, |
| "grad_norm": 0.884437620639801, |
| "learning_rate": 0.0002, |
| "loss": 1.7649, |
| "step": 50 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 50, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 1, |
| "save_steps": 13, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 1906577736990720.0, |
| "train_batch_size": 2, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
