| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.8888888888888888, | |
| "eval_steps": 2, | |
| "global_step": 6, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.14814814814814814, | |
| "grad_norm": 0.9078109860420227, | |
| "learning_rate": 2e-05, | |
| "loss": 3.7679, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.14814814814814814, | |
| "eval_loss": 3.782848358154297, | |
| "eval_runtime": 0.8037, | |
| "eval_samples_per_second": 14.931, | |
| "eval_steps_per_second": 2.488, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.2962962962962963, | |
| "grad_norm": 0.7866566181182861, | |
| "learning_rate": 4e-05, | |
| "loss": 3.8331, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.2962962962962963, | |
| "eval_loss": 3.780428886413574, | |
| "eval_runtime": 0.7927, | |
| "eval_samples_per_second": 15.139, | |
| "eval_steps_per_second": 2.523, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.4444444444444444, | |
| "grad_norm": 0.8502025008201599, | |
| "learning_rate": 6e-05, | |
| "loss": 3.7971, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.5925925925925926, | |
| "grad_norm": 0.8977667093276978, | |
| "learning_rate": 8e-05, | |
| "loss": 3.5462, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.5925925925925926, | |
| "eval_loss": 3.6698968410491943, | |
| "eval_runtime": 0.8039, | |
| "eval_samples_per_second": 14.927, | |
| "eval_steps_per_second": 2.488, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.7407407407407407, | |
| "grad_norm": 1.0905064344406128, | |
| "learning_rate": 0.0001, | |
| "loss": 3.4473, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.8888888888888888, | |
| "grad_norm": 1.466688871383667, | |
| "learning_rate": 0.00012, | |
| "loss": 3.3836, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.8888888888888888, | |
| "eval_loss": 2.982457399368286, | |
| "eval_runtime": 0.8146, | |
| "eval_samples_per_second": 14.732, | |
| "eval_steps_per_second": 2.455, | |
| "step": 6 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 6, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1085114243088384.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |