| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.006368300017689722, | |
| "eval_steps": 3, | |
| "global_step": 9, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0007075888908544136, | |
| "grad_norm": 0.5103349089622498, | |
| "learning_rate": 2e-05, | |
| "loss": 0.7616, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0007075888908544136, | |
| "eval_loss": 0.9489719271659851, | |
| "eval_runtime": 37.1823, | |
| "eval_samples_per_second": 16.002, | |
| "eval_steps_per_second": 8.015, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0014151777817088271, | |
| "grad_norm": 0.5722439885139465, | |
| "learning_rate": 4e-05, | |
| "loss": 0.8606, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0021227666725632407, | |
| "grad_norm": 0.6717545390129089, | |
| "learning_rate": 6e-05, | |
| "loss": 0.9956, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0021227666725632407, | |
| "eval_loss": 0.946592390537262, | |
| "eval_runtime": 37.4431, | |
| "eval_samples_per_second": 15.891, | |
| "eval_steps_per_second": 7.959, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0028303555634176542, | |
| "grad_norm": 0.6546880602836609, | |
| "learning_rate": 8e-05, | |
| "loss": 0.9462, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0035379444542720678, | |
| "grad_norm": 0.6106970310211182, | |
| "learning_rate": 0.0001, | |
| "loss": 0.9038, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.004245533345126481, | |
| "grad_norm": 0.4324353039264679, | |
| "learning_rate": 0.00012, | |
| "loss": 0.6771, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.004245533345126481, | |
| "eval_loss": 0.9147760272026062, | |
| "eval_runtime": 37.5096, | |
| "eval_samples_per_second": 15.863, | |
| "eval_steps_per_second": 7.945, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.004953122235980895, | |
| "grad_norm": 0.6149312257766724, | |
| "learning_rate": 0.00014, | |
| "loss": 0.8125, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0056607111268353084, | |
| "grad_norm": 0.556087076663971, | |
| "learning_rate": 0.00016, | |
| "loss": 0.8279, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.006368300017689722, | |
| "grad_norm": 0.4917399287223816, | |
| "learning_rate": 0.00018, | |
| "loss": 0.6637, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.006368300017689722, | |
| "eval_loss": 0.8577017188072205, | |
| "eval_runtime": 37.799, | |
| "eval_samples_per_second": 15.741, | |
| "eval_steps_per_second": 7.884, | |
| "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": 637624096653312.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |