| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.027900488258544524, | |
| "eval_steps": 8, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0009300162752848175, | |
| "eval_loss": 2.124025344848633, | |
| "eval_runtime": 88.5751, | |
| "eval_samples_per_second": 5.114, | |
| "eval_steps_per_second": 2.563, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0027900488258544524, | |
| "grad_norm": 5.161037921905518, | |
| "learning_rate": 6e-05, | |
| "loss": 2.0161, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.005580097651708905, | |
| "grad_norm": 1.55072820186615, | |
| "learning_rate": 0.00012, | |
| "loss": 1.7504, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00744013020227854, | |
| "eval_loss": 1.6678786277770996, | |
| "eval_runtime": 89.6936, | |
| "eval_samples_per_second": 5.051, | |
| "eval_steps_per_second": 2.531, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.008370146477563357, | |
| "grad_norm": 1.5047965049743652, | |
| "learning_rate": 0.00018, | |
| "loss": 1.671, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.01116019530341781, | |
| "grad_norm": 1.5108683109283447, | |
| "learning_rate": 0.00019510565162951537, | |
| "loss": 1.5883, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.013950244129272262, | |
| "grad_norm": 1.0921416282653809, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 1.5418, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.01488026040455708, | |
| "eval_loss": 1.5838655233383179, | |
| "eval_runtime": 89.5798, | |
| "eval_samples_per_second": 5.057, | |
| "eval_steps_per_second": 2.534, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.016740292955126714, | |
| "grad_norm": 1.2232215404510498, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 1.5445, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.01953034178098117, | |
| "grad_norm": 1.3080086708068848, | |
| "learning_rate": 8.435655349597689e-05, | |
| "loss": 1.6126, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.02232039060683562, | |
| "grad_norm": 1.3865599632263184, | |
| "learning_rate": 4.12214747707527e-05, | |
| "loss": 1.604, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.02232039060683562, | |
| "eval_loss": 1.5507044792175293, | |
| "eval_runtime": 89.9086, | |
| "eval_samples_per_second": 5.038, | |
| "eval_steps_per_second": 2.525, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.025110439432690073, | |
| "grad_norm": 0.9281854033470154, | |
| "learning_rate": 1.0899347581163221e-05, | |
| "loss": 1.4299, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.027900488258544524, | |
| "grad_norm": 0.8828859925270081, | |
| "learning_rate": 0.0, | |
| "loss": 1.4655, | |
| "step": 30 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 30, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 10, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.235418813038592e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |