| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.06940427993059572, | |
| "eval_steps": 5, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.002313475997686524, | |
| "eval_loss": NaN, | |
| "eval_runtime": 13.8411, | |
| "eval_samples_per_second": 13.149, | |
| "eval_steps_per_second": 6.575, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.006940427993059572, | |
| "grad_norm": NaN, | |
| "learning_rate": 6e-05, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.01156737998843262, | |
| "eval_loss": NaN, | |
| "eval_runtime": 13.4131, | |
| "eval_samples_per_second": 13.569, | |
| "eval_steps_per_second": 6.784, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.013880855986119144, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00012, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.020821283979178717, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00018, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.02313475997686524, | |
| "eval_loss": NaN, | |
| "eval_runtime": 13.4398, | |
| "eval_samples_per_second": 13.542, | |
| "eval_steps_per_second": 6.771, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.027761711972238288, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019510565162951537, | |
| "loss": 0.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.03470213996529786, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.03470213996529786, | |
| "eval_loss": NaN, | |
| "eval_runtime": 13.5144, | |
| "eval_samples_per_second": 13.467, | |
| "eval_steps_per_second": 6.734, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.04164256795835743, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.04626951995373048, | |
| "eval_loss": NaN, | |
| "eval_runtime": 13.5194, | |
| "eval_samples_per_second": 13.462, | |
| "eval_steps_per_second": 6.731, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.048582995951417005, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.435655349597689e-05, | |
| "loss": 0.0, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.055523423944476576, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.12214747707527e-05, | |
| "loss": 0.0, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0578368999421631, | |
| "eval_loss": NaN, | |
| "eval_runtime": 13.5373, | |
| "eval_samples_per_second": 13.444, | |
| "eval_steps_per_second": 6.722, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.06246385193753615, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.0899347581163221e-05, | |
| "loss": 0.0, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.06940427993059572, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.06940427993059572, | |
| "eval_loss": NaN, | |
| "eval_runtime": 13.5449, | |
| "eval_samples_per_second": 13.437, | |
| "eval_steps_per_second": 6.718, | |
| "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": 1.0660340073234432e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |