| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0028310566919102554, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00028310566919102553, | |
| "grad_norm": 1.647526502609253, | |
| "learning_rate": 2e-05, | |
| "loss": 2.7262, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00028310566919102553, | |
| "eval_loss": 3.0604050159454346, | |
| "eval_runtime": 44.3269, | |
| "eval_samples_per_second": 33.569, | |
| "eval_steps_per_second": 16.784, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0005662113383820511, | |
| "grad_norm": 1.445365309715271, | |
| "learning_rate": 4e-05, | |
| "loss": 2.9804, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0008493170075730766, | |
| "grad_norm": 1.494797706604004, | |
| "learning_rate": 6e-05, | |
| "loss": 2.8563, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0008493170075730766, | |
| "eval_loss": 3.037546396255493, | |
| "eval_runtime": 42.9577, | |
| "eval_samples_per_second": 34.639, | |
| "eval_steps_per_second": 17.319, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0011324226767641021, | |
| "grad_norm": 1.684383749961853, | |
| "learning_rate": 8e-05, | |
| "loss": 2.692, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0014155283459551277, | |
| "grad_norm": 1.8259694576263428, | |
| "learning_rate": 0.0001, | |
| "loss": 2.532, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0016986340151461533, | |
| "grad_norm": 1.6125636100769043, | |
| "learning_rate": 0.00012, | |
| "loss": 2.522, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0016986340151461533, | |
| "eval_loss": 2.802492141723633, | |
| "eval_runtime": 43.2406, | |
| "eval_samples_per_second": 34.412, | |
| "eval_steps_per_second": 17.206, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0019817396843371787, | |
| "grad_norm": 4.680022716522217, | |
| "learning_rate": 0.00014, | |
| "loss": 2.4138, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0022648453535282042, | |
| "grad_norm": 8.197466850280762, | |
| "learning_rate": 0.00016, | |
| "loss": 2.3978, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.00254795102271923, | |
| "grad_norm": 3.309487819671631, | |
| "learning_rate": 0.00018, | |
| "loss": 2.2049, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.00254795102271923, | |
| "eval_loss": 2.314793586730957, | |
| "eval_runtime": 43.1924, | |
| "eval_samples_per_second": 34.451, | |
| "eval_steps_per_second": 17.225, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0028310566919102554, | |
| "grad_norm": 2.3940236568450928, | |
| "learning_rate": 0.0002, | |
| "loss": 1.7763, | |
| "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": 1647822923366400.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |