| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.07797270955165692, | |
| "eval_steps": 2, | |
| "global_step": 5, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.015594541910331383, | |
| "grad_norm": 1.8912264108657837, | |
| "learning_rate": 1e-05, | |
| "loss": 15.8027, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.015594541910331383, | |
| "eval_loss": 0.9421585202217102, | |
| "eval_runtime": 19.262, | |
| "eval_samples_per_second": 5.607, | |
| "eval_steps_per_second": 2.803, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.031189083820662766, | |
| "grad_norm": 1.960965871810913, | |
| "learning_rate": 2e-05, | |
| "loss": 14.639, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.031189083820662766, | |
| "eval_loss": 0.9335685968399048, | |
| "eval_runtime": 8.0878, | |
| "eval_samples_per_second": 13.353, | |
| "eval_steps_per_second": 6.677, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.04678362573099415, | |
| "grad_norm": 2.17221999168396, | |
| "learning_rate": 3e-05, | |
| "loss": 15.2007, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.06237816764132553, | |
| "grad_norm": 2.0967655181884766, | |
| "learning_rate": 4e-05, | |
| "loss": 14.3259, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.06237816764132553, | |
| "eval_loss": 0.9278036952018738, | |
| "eval_runtime": 13.6763, | |
| "eval_samples_per_second": 7.897, | |
| "eval_steps_per_second": 3.948, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.07797270955165692, | |
| "grad_norm": 1.8220391273498535, | |
| "learning_rate": 5e-05, | |
| "loss": 13.5549, | |
| "step": 5 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 5, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 2, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.258566158647296e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |