| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0026138665621120044, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0002613866562112004, | |
| "grad_norm": 0.9460879564285278, | |
| "learning_rate": 2e-05, | |
| "loss": 0.2677, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0002613866562112004, | |
| "eval_loss": 0.34498801827430725, | |
| "eval_runtime": 100.97, | |
| "eval_samples_per_second": 63.811, | |
| "eval_steps_per_second": 7.983, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0005227733124224008, | |
| "grad_norm": 0.8985543847084045, | |
| "learning_rate": 4e-05, | |
| "loss": 0.2517, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0007841599686336013, | |
| "grad_norm": 1.076340913772583, | |
| "learning_rate": 6e-05, | |
| "loss": 0.3185, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0007841599686336013, | |
| "eval_loss": 0.32654470205307007, | |
| "eval_runtime": 100.8824, | |
| "eval_samples_per_second": 63.866, | |
| "eval_steps_per_second": 7.99, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0010455466248448016, | |
| "grad_norm": 1.1910107135772705, | |
| "learning_rate": 8e-05, | |
| "loss": 0.3072, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0013069332810560022, | |
| "grad_norm": 0.855275571346283, | |
| "learning_rate": 0.0001, | |
| "loss": 0.2373, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0015683199372672025, | |
| "grad_norm": 0.7225483059883118, | |
| "learning_rate": 0.00012, | |
| "loss": 0.1783, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0015683199372672025, | |
| "eval_loss": 0.17279158532619476, | |
| "eval_runtime": 100.8564, | |
| "eval_samples_per_second": 63.883, | |
| "eval_steps_per_second": 7.992, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0018297065934784029, | |
| "grad_norm": 0.7925214767456055, | |
| "learning_rate": 0.00014, | |
| "loss": 0.1235, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0020910932496896032, | |
| "grad_norm": 0.8158267736434937, | |
| "learning_rate": 0.00016, | |
| "loss": 0.1062, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.002352479905900804, | |
| "grad_norm": 0.49643707275390625, | |
| "learning_rate": 0.00018, | |
| "loss": 0.0751, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.002352479905900804, | |
| "eval_loss": 0.05340096727013588, | |
| "eval_runtime": 100.947, | |
| "eval_samples_per_second": 63.826, | |
| "eval_steps_per_second": 7.984, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0026138665621120044, | |
| "grad_norm": 0.6194673776626587, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0491, | |
| "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": 7790166718545920.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |