| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.009955201592832254, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0009955201592832255, | |
| "grad_norm": 5.2514424324035645, | |
| "learning_rate": 2e-05, | |
| "loss": 11.2082, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0009955201592832255, | |
| "eval_loss": 2.979728937149048, | |
| "eval_runtime": 13.6224, | |
| "eval_samples_per_second": 31.052, | |
| "eval_steps_per_second": 15.563, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.001991040318566451, | |
| "grad_norm": 5.7392120361328125, | |
| "learning_rate": 4e-05, | |
| "loss": 12.1488, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0029865604778496766, | |
| "grad_norm": 5.5465803146362305, | |
| "learning_rate": 6e-05, | |
| "loss": 12.3169, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0029865604778496766, | |
| "eval_loss": 2.9808859825134277, | |
| "eval_runtime": 13.6025, | |
| "eval_samples_per_second": 31.097, | |
| "eval_steps_per_second": 15.585, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.003982080637132902, | |
| "grad_norm": 5.296531677246094, | |
| "learning_rate": 8e-05, | |
| "loss": 12.3613, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.004977600796416127, | |
| "grad_norm": 7.782174587249756, | |
| "learning_rate": 0.0001, | |
| "loss": 12.5692, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.005973120955699353, | |
| "grad_norm": 6.1341657638549805, | |
| "learning_rate": 0.00012, | |
| "loss": 11.3093, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.005973120955699353, | |
| "eval_loss": 2.911754608154297, | |
| "eval_runtime": 13.5961, | |
| "eval_samples_per_second": 31.112, | |
| "eval_steps_per_second": 15.593, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.006968641114982578, | |
| "grad_norm": 8.517732620239258, | |
| "learning_rate": 0.00014, | |
| "loss": 12.004, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.007964161274265804, | |
| "grad_norm": 5.677702903747559, | |
| "learning_rate": 0.00016, | |
| "loss": 11.1049, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.008959681433549029, | |
| "grad_norm": 6.056185722351074, | |
| "learning_rate": 0.00018, | |
| "loss": 12.0559, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.008959681433549029, | |
| "eval_loss": 2.802990674972534, | |
| "eval_runtime": 13.5913, | |
| "eval_samples_per_second": 31.123, | |
| "eval_steps_per_second": 15.598, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.009955201592832254, | |
| "grad_norm": 6.100696086883545, | |
| "learning_rate": 0.0002, | |
| "loss": 10.7305, | |
| "step": 10 | |
| } | |
| ], | |
| "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": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 75069652992000.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |