| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.007152308407538533, |
| "eval_steps": 10, |
| "global_step": 50, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.00014304616815077065, |
| "eval_loss": 0.6253636479377747, |
| "eval_runtime": 324.4199, |
| "eval_samples_per_second": 9.075, |
| "eval_steps_per_second": 4.537, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.0007152308407538533, |
| "grad_norm": 0.3303487300872803, |
| "learning_rate": 5e-05, |
| "loss": 0.6582, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.0014304616815077067, |
| "grad_norm": 0.3911873698234558, |
| "learning_rate": 0.0001, |
| "loss": 0.5993, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.0014304616815077067, |
| "eval_loss": 0.6021842360496521, |
| "eval_runtime": 326.4286, |
| "eval_samples_per_second": 9.019, |
| "eval_steps_per_second": 4.509, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.0021456925222615598, |
| "grad_norm": 0.422364205121994, |
| "learning_rate": 9.619397662556435e-05, |
| "loss": 0.6168, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.0028609233630154133, |
| "grad_norm": 0.5429507493972778, |
| "learning_rate": 8.535533905932738e-05, |
| "loss": 0.5604, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.0028609233630154133, |
| "eval_loss": 0.5377101302146912, |
| "eval_runtime": 326.9891, |
| "eval_samples_per_second": 9.003, |
| "eval_steps_per_second": 4.502, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.0035761542037692664, |
| "grad_norm": 0.4650879204273224, |
| "learning_rate": 6.91341716182545e-05, |
| "loss": 0.5675, |
| "step": 25 |
| }, |
| { |
| "epoch": 0.0042913850445231196, |
| "grad_norm": 0.5144455432891846, |
| "learning_rate": 5e-05, |
| "loss": 0.5051, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.0042913850445231196, |
| "eval_loss": 0.5181494355201721, |
| "eval_runtime": 326.6443, |
| "eval_samples_per_second": 9.013, |
| "eval_steps_per_second": 4.506, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.005006615885276973, |
| "grad_norm": 0.4639596939086914, |
| "learning_rate": 3.086582838174551e-05, |
| "loss": 0.5149, |
| "step": 35 |
| }, |
| { |
| "epoch": 0.005721846726030827, |
| "grad_norm": 0.5504866242408752, |
| "learning_rate": 1.4644660940672627e-05, |
| "loss": 0.4772, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.005721846726030827, |
| "eval_loss": 0.5107699036598206, |
| "eval_runtime": 326.5743, |
| "eval_samples_per_second": 9.015, |
| "eval_steps_per_second": 4.507, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.006437077566784679, |
| "grad_norm": 0.49994632601737976, |
| "learning_rate": 3.8060233744356633e-06, |
| "loss": 0.5116, |
| "step": 45 |
| }, |
| { |
| "epoch": 0.007152308407538533, |
| "grad_norm": 0.47652333974838257, |
| "learning_rate": 0.0, |
| "loss": 0.508, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.007152308407538533, |
| "eval_loss": 0.5095760822296143, |
| "eval_runtime": 327.094, |
| "eval_samples_per_second": 9.0, |
| "eval_steps_per_second": 4.5, |
| "step": 50 |
| } |
| ], |
| "logging_steps": 5, |
| "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": 1.6229926277480448e+16, |
| "train_batch_size": 2, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
