| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.5373134328358209, | |
| "eval_steps": 9, | |
| "global_step": 27, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.01990049751243781, | |
| "eval_loss": 1.5809879302978516, | |
| "eval_runtime": 5.5137, | |
| "eval_samples_per_second": 15.416, | |
| "eval_steps_per_second": 1.995, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.05970149253731343, | |
| "grad_norm": 0.7845205068588257, | |
| "learning_rate": 1.5e-05, | |
| "loss": 1.5216, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.11940298507462686, | |
| "grad_norm": 0.8492766618728638, | |
| "learning_rate": 3e-05, | |
| "loss": 1.594, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.1791044776119403, | |
| "grad_norm": 0.899258553981781, | |
| "learning_rate": 4.5e-05, | |
| "loss": 1.5144, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.1791044776119403, | |
| "eval_loss": 1.5270332098007202, | |
| "eval_runtime": 5.5991, | |
| "eval_samples_per_second": 15.181, | |
| "eval_steps_per_second": 1.965, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.23880597014925373, | |
| "grad_norm": 1.0086854696273804, | |
| "learning_rate": 4.993910125649561e-05, | |
| "loss": 1.43, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.29850746268656714, | |
| "grad_norm": 0.8446040749549866, | |
| "learning_rate": 4.962019382530521e-05, | |
| "loss": 1.3627, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.3582089552238806, | |
| "grad_norm": 0.7049321532249451, | |
| "learning_rate": 4.9031542398457974e-05, | |
| "loss": 1.2934, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.3582089552238806, | |
| "eval_loss": 1.2862956523895264, | |
| "eval_runtime": 5.6451, | |
| "eval_samples_per_second": 15.057, | |
| "eval_steps_per_second": 1.949, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.417910447761194, | |
| "grad_norm": 0.6026838421821594, | |
| "learning_rate": 4.817959636416969e-05, | |
| "loss": 1.2678, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.47761194029850745, | |
| "grad_norm": 0.6281826496124268, | |
| "learning_rate": 4.707368982147318e-05, | |
| "loss": 1.2053, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.5373134328358209, | |
| "grad_norm": 0.626505434513092, | |
| "learning_rate": 4.572593931387604e-05, | |
| "loss": 1.1997, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.5373134328358209, | |
| "eval_loss": 1.1615190505981445, | |
| "eval_runtime": 5.6361, | |
| "eval_samples_per_second": 15.081, | |
| "eval_steps_per_second": 1.952, | |
| "step": 27 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 100, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "save_steps": 9, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3.5286742902767616e+16, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |