| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.012227181023415051, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00024454362046830104, | |
| "eval_loss": 7.183546543121338, | |
| "eval_runtime": 187.0794, | |
| "eval_samples_per_second": 9.205, | |
| "eval_steps_per_second": 4.602, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.001222718102341505, | |
| "grad_norm": 17.202749252319336, | |
| "learning_rate": 5e-05, | |
| "loss": 7.3138, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00244543620468301, | |
| "grad_norm": 14.147286415100098, | |
| "learning_rate": 0.0001, | |
| "loss": 5.2795, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.00244543620468301, | |
| "eval_loss": 3.5840988159179688, | |
| "eval_runtime": 190.3052, | |
| "eval_samples_per_second": 9.049, | |
| "eval_steps_per_second": 4.524, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0036681543070245155, | |
| "grad_norm": 16.83527946472168, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 2.4507, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.00489087240936602, | |
| "grad_norm": 5.885318756103516, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.5604, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.00489087240936602, | |
| "eval_loss": 0.14171117544174194, | |
| "eval_runtime": 190.6068, | |
| "eval_samples_per_second": 9.034, | |
| "eval_steps_per_second": 4.517, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.006113590511707526, | |
| "grad_norm": 3.527186632156372, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.1274, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.007336308614049031, | |
| "grad_norm": 1.249354362487793, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0513, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.007336308614049031, | |
| "eval_loss": 0.04599830508232117, | |
| "eval_runtime": 190.4146, | |
| "eval_samples_per_second": 9.043, | |
| "eval_steps_per_second": 4.522, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.008559026716390536, | |
| "grad_norm": 17.15851402282715, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.0512, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.00978174481873204, | |
| "grad_norm": 0.4459174573421478, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.0019, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.00978174481873204, | |
| "eval_loss": 0.019245758652687073, | |
| "eval_runtime": 190.3106, | |
| "eval_samples_per_second": 9.048, | |
| "eval_steps_per_second": 4.524, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.011004462921073547, | |
| "grad_norm": 8.879000663757324, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.0188, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.012227181023415051, | |
| "grad_norm": 0.0182019229978323, | |
| "learning_rate": 0.0, | |
| "loss": 0.0188, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.012227181023415051, | |
| "eval_loss": 0.013666636310517788, | |
| "eval_runtime": 190.2885, | |
| "eval_samples_per_second": 9.049, | |
| "eval_steps_per_second": 4.525, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 13, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 9555457081344000.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |