| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0006520286240565961, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 6.520286240565961e-05, | |
| "grad_norm": 4.248133336659521e-05, | |
| "learning_rate": 2e-05, | |
| "loss": 46.0, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 6.520286240565961e-05, | |
| "eval_loss": 11.5, | |
| "eval_runtime": 35.8323, | |
| "eval_samples_per_second": 180.228, | |
| "eval_steps_per_second": 90.114, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00013040572481131922, | |
| "grad_norm": 1.802958649932407e-05, | |
| "learning_rate": 4e-05, | |
| "loss": 46.0, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.00019560858721697882, | |
| "grad_norm": 4.447318860911764e-05, | |
| "learning_rate": 6e-05, | |
| "loss": 46.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00019560858721697882, | |
| "eval_loss": 11.5, | |
| "eval_runtime": 35.7745, | |
| "eval_samples_per_second": 180.52, | |
| "eval_steps_per_second": 90.26, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00026081144962263844, | |
| "grad_norm": 4.1639279515948147e-05, | |
| "learning_rate": 8e-05, | |
| "loss": 46.0, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.00032601431202829807, | |
| "grad_norm": 3.165311136399396e-05, | |
| "learning_rate": 0.0001, | |
| "loss": 46.0, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00039121717443395764, | |
| "grad_norm": 3.059555820073001e-05, | |
| "learning_rate": 0.00012, | |
| "loss": 46.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00039121717443395764, | |
| "eval_loss": 11.5, | |
| "eval_runtime": 36.1716, | |
| "eval_samples_per_second": 178.538, | |
| "eval_steps_per_second": 89.269, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00045642003683961726, | |
| "grad_norm": 2.9665452530025505e-05, | |
| "learning_rate": 0.00014, | |
| "loss": 46.0, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0005216228992452769, | |
| "grad_norm": 1.7811524230637588e-05, | |
| "learning_rate": 0.00016, | |
| "loss": 46.0, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0005868257616509365, | |
| "grad_norm": 2.4538920115446672e-05, | |
| "learning_rate": 0.00018, | |
| "loss": 46.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0005868257616509365, | |
| "eval_loss": 11.5, | |
| "eval_runtime": 36.0651, | |
| "eval_samples_per_second": 179.065, | |
| "eval_steps_per_second": 89.532, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0006520286240565961, | |
| "grad_norm": 3.9854181522969157e-05, | |
| "learning_rate": 0.0002, | |
| "loss": 46.0, | |
| "step": 10 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 10, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 3, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 199228784640.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |