| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.008360427310729215, | |
| "eval_steps": 3, | |
| "global_step": 9, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0009289363678588017, | |
| "grad_norm": 0.374651700258255, | |
| "learning_rate": 2e-05, | |
| "loss": 0.407, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0009289363678588017, | |
| "eval_loss": 0.4839384853839874, | |
| "eval_runtime": 16.8213, | |
| "eval_samples_per_second": 26.99, | |
| "eval_steps_per_second": 13.495, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0018578727357176034, | |
| "grad_norm": 0.4575123190879822, | |
| "learning_rate": 4e-05, | |
| "loss": 0.4579, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.002786809103576405, | |
| "grad_norm": 0.45436957478523254, | |
| "learning_rate": 6e-05, | |
| "loss": 0.6066, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.002786809103576405, | |
| "eval_loss": 0.4798922836780548, | |
| "eval_runtime": 16.8182, | |
| "eval_samples_per_second": 26.995, | |
| "eval_steps_per_second": 13.497, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0037157454714352067, | |
| "grad_norm": 0.48997998237609863, | |
| "learning_rate": 8e-05, | |
| "loss": 0.6382, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.004644681839294009, | |
| "grad_norm": 0.43039506673812866, | |
| "learning_rate": 0.0001, | |
| "loss": 0.4727, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00557361820715281, | |
| "grad_norm": 0.4800651967525482, | |
| "learning_rate": 0.00012, | |
| "loss": 0.612, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00557361820715281, | |
| "eval_loss": 0.43572765588760376, | |
| "eval_runtime": 16.8769, | |
| "eval_samples_per_second": 26.901, | |
| "eval_steps_per_second": 13.45, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.006502554575011612, | |
| "grad_norm": 0.3915104269981384, | |
| "learning_rate": 0.00014, | |
| "loss": 0.4111, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0074314909428704135, | |
| "grad_norm": 0.3610092103481293, | |
| "learning_rate": 0.00016, | |
| "loss": 0.362, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.008360427310729215, | |
| "grad_norm": 0.43476492166519165, | |
| "learning_rate": 0.00018, | |
| "loss": 0.4626, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.008360427310729215, | |
| "eval_loss": 0.384464293718338, | |
| "eval_runtime": 16.859, | |
| "eval_samples_per_second": 26.929, | |
| "eval_steps_per_second": 13.465, | |
| "step": 9 | |
| } | |
| ], | |
| "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": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 800155729133568.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |