| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.013361169102296452, | |
| "eval_steps": 2, | |
| "global_step": 4, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.003340292275574113, | |
| "grad_norm": 0.44266244769096375, | |
| "learning_rate": 1e-05, | |
| "loss": 0.9906, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.003340292275574113, | |
| "eval_loss": 1.185352087020874, | |
| "eval_runtime": 222.4699, | |
| "eval_samples_per_second": 2.27, | |
| "eval_steps_per_second": 1.137, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.006680584551148226, | |
| "grad_norm": 0.6044847369194031, | |
| "learning_rate": 2e-05, | |
| "loss": 1.1812, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.006680584551148226, | |
| "eval_loss": 1.1712839603424072, | |
| "eval_runtime": 17.0267, | |
| "eval_samples_per_second": 29.659, | |
| "eval_steps_per_second": 14.859, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.010020876826722338, | |
| "grad_norm": 0.5352935194969177, | |
| "learning_rate": 3e-05, | |
| "loss": 1.1214, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.013361169102296452, | |
| "grad_norm": 0.4383408725261688, | |
| "learning_rate": 4e-05, | |
| "loss": 0.9791, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.013361169102296452, | |
| "eval_loss": 1.1496862173080444, | |
| "eval_runtime": 16.9919, | |
| "eval_samples_per_second": 29.72, | |
| "eval_steps_per_second": 14.889, | |
| "step": 4 | |
| } | |
| ], | |
| "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": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 526984670085120.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |