| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.002618349392542941, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 5.236698785085882e-05, | |
| "eval_loss": 11.104299545288086, | |
| "eval_runtime": 62.8672, | |
| "eval_samples_per_second": 127.905, | |
| "eval_steps_per_second": 63.96, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0002618349392542941, | |
| "grad_norm": 0.9558674693107605, | |
| "learning_rate": 5e-05, | |
| "loss": 44.4239, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0005236698785085882, | |
| "grad_norm": 1.087439775466919, | |
| "learning_rate": 0.0001, | |
| "loss": 44.3971, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0005236698785085882, | |
| "eval_loss": 11.095877647399902, | |
| "eval_runtime": 60.5523, | |
| "eval_samples_per_second": 132.794, | |
| "eval_steps_per_second": 66.405, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0007855048177628823, | |
| "grad_norm": 1.113486647605896, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 44.3516, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0010473397570171764, | |
| "grad_norm": 1.2645790576934814, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 44.312, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0010473397570171764, | |
| "eval_loss": 11.073476791381836, | |
| "eval_runtime": 62.1845, | |
| "eval_samples_per_second": 129.309, | |
| "eval_steps_per_second": 64.662, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0013091746962714706, | |
| "grad_norm": 1.3341377973556519, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 44.2743, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0015710096355257646, | |
| "grad_norm": 1.2830345630645752, | |
| "learning_rate": 5e-05, | |
| "loss": 44.2385, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0015710096355257646, | |
| "eval_loss": 11.053695678710938, | |
| "eval_runtime": 62.1764, | |
| "eval_samples_per_second": 129.326, | |
| "eval_steps_per_second": 64.671, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0018328445747800588, | |
| "grad_norm": 1.3957866430282593, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 44.1994, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.0020946795140343527, | |
| "grad_norm": 1.4559333324432373, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 44.1904, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0020946795140343527, | |
| "eval_loss": 11.042880058288574, | |
| "eval_runtime": 62.11, | |
| "eval_samples_per_second": 129.464, | |
| "eval_steps_per_second": 64.74, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0023565144532886467, | |
| "grad_norm": 1.4452019929885864, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 44.1758, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.002618349392542941, | |
| "grad_norm": 1.5328729152679443, | |
| "learning_rate": 0.0, | |
| "loss": 44.1714, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.002618349392542941, | |
| "eval_loss": 11.04096794128418, | |
| "eval_runtime": 61.9724, | |
| "eval_samples_per_second": 129.751, | |
| "eval_steps_per_second": 64.884, | |
| "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": 964480204800.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |