| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0014127065102225013, | |
| "eval_steps": 3, | |
| "global_step": 9, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00015696739002472236, | |
| "grad_norm": 0.5885064601898193, | |
| "learning_rate": 2e-05, | |
| "loss": 6.2097, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00015696739002472236, | |
| "eval_loss": 1.5108346939086914, | |
| "eval_runtime": 124.6799, | |
| "eval_samples_per_second": 21.519, | |
| "eval_steps_per_second": 10.764, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0003139347800494447, | |
| "grad_norm": 0.7580665946006775, | |
| "learning_rate": 4e-05, | |
| "loss": 6.3247, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0004709021700741671, | |
| "grad_norm": 0.3595629632472992, | |
| "learning_rate": 6e-05, | |
| "loss": 6.4287, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0004709021700741671, | |
| "eval_loss": 1.5107760429382324, | |
| "eval_runtime": 125.1669, | |
| "eval_samples_per_second": 21.435, | |
| "eval_steps_per_second": 10.722, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0006278695600988894, | |
| "grad_norm": 0.9399296045303345, | |
| "learning_rate": 8e-05, | |
| "loss": 8.3116, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0007848369501236119, | |
| "grad_norm": 0.78465336561203, | |
| "learning_rate": 0.0001, | |
| "loss": 5.4298, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0009418043401483342, | |
| "grad_norm": 0.6433153748512268, | |
| "learning_rate": 0.00012, | |
| "loss": 6.2516, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0009418043401483342, | |
| "eval_loss": 1.5095309019088745, | |
| "eval_runtime": 125.2633, | |
| "eval_samples_per_second": 21.419, | |
| "eval_steps_per_second": 10.713, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0010987717301730565, | |
| "grad_norm": 0.404464989900589, | |
| "learning_rate": 0.00014, | |
| "loss": 5.5203, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0012557391201977789, | |
| "grad_norm": 0.4325326681137085, | |
| "learning_rate": 0.00016, | |
| "loss": 5.0508, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0014127065102225013, | |
| "grad_norm": 0.6805629134178162, | |
| "learning_rate": 0.00018, | |
| "loss": 6.1022, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0014127065102225013, | |
| "eval_loss": 1.501906156539917, | |
| "eval_runtime": 126.4651, | |
| "eval_samples_per_second": 21.215, | |
| "eval_steps_per_second": 10.612, | |
| "step": 9 | |
| } | |
| ], | |
| "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": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 410752930283520.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |