| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 3.699453551912568, | |
| "eval_steps": 25, | |
| "global_step": 44, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.08743169398907104, | |
| "grad_norm": 22.347578048706055, | |
| "learning_rate": 0.00019545454545454548, | |
| "loss": 9.5025, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.17486338797814208, | |
| "grad_norm": 25.239198684692383, | |
| "learning_rate": 0.00019090909090909092, | |
| "loss": 9.3395, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.26229508196721313, | |
| "grad_norm": 32.5155143737793, | |
| "learning_rate": 0.00018636363636363636, | |
| "loss": 9.064, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.34972677595628415, | |
| "grad_norm": 52.9838752746582, | |
| "learning_rate": 0.00018181818181818183, | |
| "loss": 8.4152, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.4371584699453552, | |
| "grad_norm": 37.703086853027344, | |
| "learning_rate": 0.00017727272727272728, | |
| "loss": 8.2592, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.5245901639344263, | |
| "grad_norm": 51.64411926269531, | |
| "learning_rate": 0.00017272727272727275, | |
| "loss": 7.5229, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.6120218579234973, | |
| "grad_norm": 51.453033447265625, | |
| "learning_rate": 0.0001681818181818182, | |
| "loss": 7.8703, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.6994535519125683, | |
| "grad_norm": 49.968597412109375, | |
| "learning_rate": 0.00016363636363636366, | |
| "loss": 7.4822, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.7868852459016393, | |
| "grad_norm": 51.338375091552734, | |
| "learning_rate": 0.0001590909090909091, | |
| "loss": 7.1884, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.8743169398907104, | |
| "grad_norm": 31.432743072509766, | |
| "learning_rate": 0.00015454545454545454, | |
| "loss": 6.8064, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.9617486338797814, | |
| "grad_norm": 38.92168045043945, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 7.1349, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 29.082275390625, | |
| "learning_rate": 0.00014545454545454546, | |
| "loss": 2.7656, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 1.0874316939890711, | |
| "grad_norm": 45.3143424987793, | |
| "learning_rate": 0.00014090909090909093, | |
| "loss": 6.6156, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 1.174863387978142, | |
| "grad_norm": 21.88313865661621, | |
| "learning_rate": 0.00013636363636363637, | |
| "loss": 6.798, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 1.2622950819672132, | |
| "grad_norm": 17.01368522644043, | |
| "learning_rate": 0.0001318181818181818, | |
| "loss": 6.6264, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 1.349726775956284, | |
| "grad_norm": 34.124168395996094, | |
| "learning_rate": 0.00012727272727272728, | |
| "loss": 6.2059, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 1.4371584699453552, | |
| "grad_norm": 13.495098114013672, | |
| "learning_rate": 0.00012272727272727272, | |
| "loss": 6.5543, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 1.5245901639344264, | |
| "grad_norm": 15.081934928894043, | |
| "learning_rate": 0.0001181818181818182, | |
| "loss": 6.5956, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 1.6120218579234973, | |
| "grad_norm": 16.291242599487305, | |
| "learning_rate": 0.00011363636363636365, | |
| "loss": 6.4254, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 1.6994535519125682, | |
| "grad_norm": 26.84221839904785, | |
| "learning_rate": 0.00010909090909090909, | |
| "loss": 6.2627, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.7868852459016393, | |
| "grad_norm": 22.350202560424805, | |
| "learning_rate": 0.00010454545454545455, | |
| "loss": 6.1832, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 1.8743169398907105, | |
| "grad_norm": 16.34981346130371, | |
| "learning_rate": 0.0001, | |
| "loss": 6.6073, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 1.9617486338797814, | |
| "grad_norm": 18.4270076751709, | |
| "learning_rate": 9.545454545454546e-05, | |
| "loss": 6.5258, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 15.420706748962402, | |
| "learning_rate": 9.090909090909092e-05, | |
| "loss": 2.5959, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 2.087431693989071, | |
| "grad_norm": 11.540351867675781, | |
| "learning_rate": 8.636363636363637e-05, | |
| "loss": 6.334, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 2.087431693989071, | |
| "eval_clap": 0.18773917853832245, | |
| "eval_loss": 6.105246543884277, | |
| "eval_runtime": 83.5333, | |
| "eval_samples_per_second": 0.096, | |
| "eval_steps_per_second": 0.096, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 2.1748633879781423, | |
| "grad_norm": 21.185924530029297, | |
| "learning_rate": 8.181818181818183e-05, | |
| "loss": 6.109, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 2.262295081967213, | |
| "grad_norm": 13.807082176208496, | |
| "learning_rate": 7.727272727272727e-05, | |
| "loss": 6.4383, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 2.349726775956284, | |
| "grad_norm": 17.374765396118164, | |
| "learning_rate": 7.272727272727273e-05, | |
| "loss": 6.0599, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 2.4371584699453552, | |
| "grad_norm": 12.8378324508667, | |
| "learning_rate": 6.818181818181818e-05, | |
| "loss": 6.2779, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 2.5245901639344264, | |
| "grad_norm": 16.53411865234375, | |
| "learning_rate": 6.363636363636364e-05, | |
| "loss": 6.3555, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 2.612021857923497, | |
| "grad_norm": 13.256036758422852, | |
| "learning_rate": 5.90909090909091e-05, | |
| "loss": 6.1763, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 2.699453551912568, | |
| "grad_norm": 19.911523818969727, | |
| "learning_rate": 5.4545454545454546e-05, | |
| "loss": 6.5248, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 2.7868852459016393, | |
| "grad_norm": 12.554062843322754, | |
| "learning_rate": 5e-05, | |
| "loss": 6.0678, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 2.8743169398907105, | |
| "grad_norm": 9.20517635345459, | |
| "learning_rate": 4.545454545454546e-05, | |
| "loss": 6.2365, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 2.9617486338797816, | |
| "grad_norm": 19.72951316833496, | |
| "learning_rate": 4.0909090909090915e-05, | |
| "loss": 6.5335, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "grad_norm": 7.918391704559326, | |
| "learning_rate": 3.6363636363636364e-05, | |
| "loss": 2.8033, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 3.087431693989071, | |
| "grad_norm": 10.007157325744629, | |
| "learning_rate": 3.181818181818182e-05, | |
| "loss": 6.2187, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 3.1748633879781423, | |
| "grad_norm": 18.43683433532715, | |
| "learning_rate": 2.7272727272727273e-05, | |
| "loss": 6.1133, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 3.262295081967213, | |
| "grad_norm": 11.159557342529297, | |
| "learning_rate": 2.272727272727273e-05, | |
| "loss": 6.1788, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 3.349726775956284, | |
| "grad_norm": 15.116974830627441, | |
| "learning_rate": 1.8181818181818182e-05, | |
| "loss": 6.1412, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 3.4371584699453552, | |
| "grad_norm": 14.885272026062012, | |
| "learning_rate": 1.3636363636363637e-05, | |
| "loss": 6.2777, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 3.5245901639344264, | |
| "grad_norm": 9.910028457641602, | |
| "learning_rate": 9.090909090909091e-06, | |
| "loss": 6.4341, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 3.612021857923497, | |
| "grad_norm": 15.322835922241211, | |
| "learning_rate": 4.5454545454545455e-06, | |
| "loss": 6.0193, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 3.699453551912568, | |
| "grad_norm": 20.181869506835938, | |
| "learning_rate": 0.0, | |
| "loss": 6.1425, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 3.699453551912568, | |
| "step": 44, | |
| "total_flos": 212119392152640.0, | |
| "train_loss": 6.517944124611941, | |
| "train_runtime": 2793.5932, | |
| "train_samples_per_second": 0.262, | |
| "train_steps_per_second": 0.016 | |
| } | |
| ], | |
| "logging_steps": 1.0, | |
| "max_steps": 44, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 4, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 212119392152640.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |