| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.00027107800947417644, | |
| "eval_steps": 2, | |
| "global_step": 5, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 5.4215601894835285e-05, | |
| "grad_norm": 0.3117355704307556, | |
| "learning_rate": 1e-05, | |
| "loss": 0.4411, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 5.4215601894835285e-05, | |
| "eval_loss": 0.833586573600769, | |
| "eval_runtime": 6510.0206, | |
| "eval_samples_per_second": 4.772, | |
| "eval_steps_per_second": 2.386, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00010843120378967057, | |
| "grad_norm": 0.313480019569397, | |
| "learning_rate": 2e-05, | |
| "loss": 0.4611, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.00010843120378967057, | |
| "eval_loss": 0.819469153881073, | |
| "eval_runtime": 6521.0863, | |
| "eval_samples_per_second": 4.764, | |
| "eval_steps_per_second": 2.382, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.00016264680568450586, | |
| "grad_norm": 0.38713642954826355, | |
| "learning_rate": 3e-05, | |
| "loss": 0.4911, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00021686240757934114, | |
| "grad_norm": 0.2709786891937256, | |
| "learning_rate": 4e-05, | |
| "loss": 0.3997, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.00021686240757934114, | |
| "eval_loss": 0.8031126856803894, | |
| "eval_runtime": 4941.352, | |
| "eval_samples_per_second": 6.287, | |
| "eval_steps_per_second": 3.143, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.00027107800947417644, | |
| "grad_norm": 0.2664385437965393, | |
| "learning_rate": 5e-05, | |
| "loss": 0.3663, | |
| "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": 3833799301398528.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |