| { | |
| "best_metric": 0.4640245735645294, | |
| "best_model_checkpoint": "mikhail-panzo/ceb_b64_le5_s4000/checkpoint-500", | |
| "epoch": 19.801980198019802, | |
| "eval_steps": 500, | |
| "global_step": 500, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.9801980198019802, | |
| "grad_norm": 2.883972644805908, | |
| "learning_rate": 2.5000000000000004e-07, | |
| "loss": 0.8004, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 3.9603960396039604, | |
| "grad_norm": 2.5420947074890137, | |
| "learning_rate": 5.000000000000001e-07, | |
| "loss": 0.77, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 5.9405940594059405, | |
| "grad_norm": 1.3930779695510864, | |
| "learning_rate": 7.5e-07, | |
| "loss": 0.7525, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 7.920792079207921, | |
| "grad_norm": 1.8414520025253296, | |
| "learning_rate": 1.0000000000000002e-06, | |
| "loss": 0.722, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 9.900990099009901, | |
| "grad_norm": 2.0665407180786133, | |
| "learning_rate": 1.25e-06, | |
| "loss": 0.7076, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 11.881188118811881, | |
| "grad_norm": 1.2595587968826294, | |
| "learning_rate": 1.5e-06, | |
| "loss": 0.6757, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 13.861386138613861, | |
| "grad_norm": 1.4587587118148804, | |
| "learning_rate": 1.75e-06, | |
| "loss": 0.6562, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 15.841584158415841, | |
| "grad_norm": 2.241546154022217, | |
| "learning_rate": 2.0000000000000003e-06, | |
| "loss": 0.6016, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 17.821782178217823, | |
| "grad_norm": 1.4243369102478027, | |
| "learning_rate": 2.25e-06, | |
| "loss": 0.5593, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 19.801980198019802, | |
| "grad_norm": 1.6889928579330444, | |
| "learning_rate": 2.5e-06, | |
| "loss": 0.536, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 19.801980198019802, | |
| "eval_loss": 0.4640245735645294, | |
| "eval_runtime": 6.7454, | |
| "eval_samples_per_second": 26.685, | |
| "eval_steps_per_second": 3.41, | |
| "step": 500 | |
| } | |
| ], | |
| "logging_steps": 50, | |
| "max_steps": 4000, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 160, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 5396569205689728.0, | |
| "train_batch_size": 16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |