| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0027087424663100154, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00027087424663100153, | |
| "grad_norm": 5.178700923919678, | |
| "learning_rate": 2e-05, | |
| "loss": 44.4678, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00027087424663100153, | |
| "eval_loss": 11.137868881225586, | |
| "eval_runtime": 26.6049, | |
| "eval_samples_per_second": 58.448, | |
| "eval_steps_per_second": 29.243, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0005417484932620031, | |
| "grad_norm": 7.01981782913208, | |
| "learning_rate": 4e-05, | |
| "loss": 44.4444, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0008126227398930047, | |
| "grad_norm": 7.090907573699951, | |
| "learning_rate": 6e-05, | |
| "loss": 44.6979, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0008126227398930047, | |
| "eval_loss": 11.131836891174316, | |
| "eval_runtime": 26.7529, | |
| "eval_samples_per_second": 58.125, | |
| "eval_steps_per_second": 29.081, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0010834969865240061, | |
| "grad_norm": 6.078212738037109, | |
| "learning_rate": 8e-05, | |
| "loss": 44.5714, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0013543712331550077, | |
| "grad_norm": 5.919520378112793, | |
| "learning_rate": 0.0001, | |
| "loss": 44.3545, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0016252454797860093, | |
| "grad_norm": 7.104866981506348, | |
| "learning_rate": 0.00012, | |
| "loss": 44.5365, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0016252454797860093, | |
| "eval_loss": 11.10763168334961, | |
| "eval_runtime": 26.4786, | |
| "eval_samples_per_second": 58.727, | |
| "eval_steps_per_second": 29.382, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0018961197264170109, | |
| "grad_norm": 6.361030101776123, | |
| "learning_rate": 0.00014, | |
| "loss": 44.4097, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0021669939730480123, | |
| "grad_norm": 7.421581745147705, | |
| "learning_rate": 0.00016, | |
| "loss": 44.2708, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.002437868219679014, | |
| "grad_norm": 8.107527732849121, | |
| "learning_rate": 0.00018, | |
| "loss": 44.3208, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.002437868219679014, | |
| "eval_loss": 11.058432579040527, | |
| "eval_runtime": 26.4941, | |
| "eval_samples_per_second": 58.692, | |
| "eval_steps_per_second": 29.365, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0027087424663100154, | |
| "grad_norm": 6.866992473602295, | |
| "learning_rate": 0.0002, | |
| "loss": 44.0816, | |
| "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": 831982141440.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |