| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.004260123117558097, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 8.520246235116194e-05, | |
| "eval_loss": 1.6328990459442139, | |
| "eval_runtime": 162.4379, | |
| "eval_samples_per_second": 30.424, | |
| "eval_steps_per_second": 15.212, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0004260123117558097, | |
| "grad_norm": 10.057034492492676, | |
| "learning_rate": 5e-05, | |
| "loss": 1.3902, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0008520246235116195, | |
| "grad_norm": 10.038150787353516, | |
| "learning_rate": 0.0001, | |
| "loss": 1.0394, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0008520246235116195, | |
| "eval_loss": 0.6274666786193848, | |
| "eval_runtime": 161.1379, | |
| "eval_samples_per_second": 30.669, | |
| "eval_steps_per_second": 15.335, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0012780369352674292, | |
| "grad_norm": 2.184178113937378, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.3294, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.001704049247023239, | |
| "grad_norm": 3.0842185020446777, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.2273, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.001704049247023239, | |
| "eval_loss": 0.27254608273506165, | |
| "eval_runtime": 158.6755, | |
| "eval_samples_per_second": 31.145, | |
| "eval_steps_per_second": 15.573, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0021300615587790486, | |
| "grad_norm": 5.116786003112793, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.2787, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0025560738705348585, | |
| "grad_norm": 2.0868818759918213, | |
| "learning_rate": 5e-05, | |
| "loss": 0.2157, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0025560738705348585, | |
| "eval_loss": 0.25301042199134827, | |
| "eval_runtime": 160.8932, | |
| "eval_samples_per_second": 30.716, | |
| "eval_steps_per_second": 15.358, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0029820861822906683, | |
| "grad_norm": 2.4985568523406982, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.2086, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.003408098494046478, | |
| "grad_norm": 3.0704267024993896, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.2071, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.003408098494046478, | |
| "eval_loss": 0.25280508399009705, | |
| "eval_runtime": 158.765, | |
| "eval_samples_per_second": 31.128, | |
| "eval_steps_per_second": 15.564, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0038341108058022877, | |
| "grad_norm": 1.9233769178390503, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.1697, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.004260123117558097, | |
| "grad_norm": 5.35168981552124, | |
| "learning_rate": 0.0, | |
| "loss": 0.2624, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.004260123117558097, | |
| "eval_loss": 0.2518482506275177, | |
| "eval_runtime": 158.7971, | |
| "eval_samples_per_second": 31.121, | |
| "eval_steps_per_second": 15.561, | |
| "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": 445190819020800.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |