| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.11958146487294469, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.01195814648729447, | |
| "grad_norm": 14.490328788757324, | |
| "learning_rate": 1e-05, | |
| "loss": 35.7522, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.01195814648729447, | |
| "eval_loss": 2.004462242126465, | |
| "eval_runtime": 28.4736, | |
| "eval_samples_per_second": 4.952, | |
| "eval_steps_per_second": 2.494, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.02391629297458894, | |
| "grad_norm": 11.366060256958008, | |
| "learning_rate": 2e-05, | |
| "loss": 30.9888, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.03587443946188341, | |
| "grad_norm": 11.150002479553223, | |
| "learning_rate": 3e-05, | |
| "loss": 26.9533, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.03587443946188341, | |
| "eval_loss": 1.9517086744308472, | |
| "eval_runtime": 6.5209, | |
| "eval_samples_per_second": 21.623, | |
| "eval_steps_per_second": 10.888, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.04783258594917788, | |
| "grad_norm": 12.718278884887695, | |
| "learning_rate": 4e-05, | |
| "loss": 33.9918, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.059790732436472344, | |
| "grad_norm": 12.853529930114746, | |
| "learning_rate": 5e-05, | |
| "loss": 32.5199, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.07174887892376682, | |
| "grad_norm": 13.096259117126465, | |
| "learning_rate": 6e-05, | |
| "loss": 32.7244, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.07174887892376682, | |
| "eval_loss": 1.8910431861877441, | |
| "eval_runtime": 6.5162, | |
| "eval_samples_per_second": 21.638, | |
| "eval_steps_per_second": 10.896, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.08370702541106129, | |
| "grad_norm": 12.865381240844727, | |
| "learning_rate": 7e-05, | |
| "loss": 28.8971, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.09566517189835576, | |
| "grad_norm": 14.876195907592773, | |
| "learning_rate": 8e-05, | |
| "loss": 30.2847, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.10762331838565023, | |
| "grad_norm": 15.215254783630371, | |
| "learning_rate": 9e-05, | |
| "loss": 26.7162, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.10762331838565023, | |
| "eval_loss": 1.742897391319275, | |
| "eval_runtime": 6.4966, | |
| "eval_samples_per_second": 21.704, | |
| "eval_steps_per_second": 10.929, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.11958146487294469, | |
| "grad_norm": 15.960527420043945, | |
| "learning_rate": 0.0001, | |
| "loss": 30.5932, | |
| "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": 1.2704118460121088e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |