| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 6.666666666666667, | |
| "eval_steps": 500, | |
| "global_step": 70, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.09523809523809523, | |
| "grad_norm": 6.758038256733847, | |
| "learning_rate": 2.8571428571428573e-06, | |
| "loss": 0.8722, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.19047619047619047, | |
| "grad_norm": 7.0365358758693315, | |
| "learning_rate": 5.7142857142857145e-06, | |
| "loss": 0.8835, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.2857142857142857, | |
| "grad_norm": 7.260260852302525, | |
| "learning_rate": 8.571428571428571e-06, | |
| "loss": 0.8854, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.38095238095238093, | |
| "grad_norm": 3.0289925776618585, | |
| "learning_rate": 1.1428571428571429e-05, | |
| "loss": 0.7555, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.47619047619047616, | |
| "grad_norm": 3.652421052717974, | |
| "learning_rate": 1.4285714285714287e-05, | |
| "loss": 0.7248, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.5714285714285714, | |
| "grad_norm": 3.7682566842373246, | |
| "learning_rate": 1.7142857142857142e-05, | |
| "loss": 0.7053, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.6666666666666666, | |
| "grad_norm": 4.64841596399953, | |
| "learning_rate": 2e-05, | |
| "loss": 0.6667, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.7619047619047619, | |
| "grad_norm": 3.4592465377117634, | |
| "learning_rate": 1.9987569212189224e-05, | |
| "loss": 0.6305, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.8571428571428571, | |
| "grad_norm": 3.077279728656568, | |
| "learning_rate": 1.9950307753654016e-05, | |
| "loss": 0.5928, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.9523809523809523, | |
| "grad_norm": 2.731855722040133, | |
| "learning_rate": 1.9888308262251286e-05, | |
| "loss": 0.6055, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 1.0476190476190477, | |
| "grad_norm": 1.6152695281168339, | |
| "learning_rate": 1.9801724878485438e-05, | |
| "loss": 0.5637, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 1.1428571428571428, | |
| "grad_norm": 1.6489193151176011, | |
| "learning_rate": 1.969077286229078e-05, | |
| "loss": 0.5364, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 1.2380952380952381, | |
| "grad_norm": 1.7771694950929857, | |
| "learning_rate": 1.955572805786141e-05, | |
| "loss": 0.5187, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 1.3333333333333333, | |
| "grad_norm": 1.1130920573502374, | |
| "learning_rate": 1.9396926207859085e-05, | |
| "loss": 0.5465, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 1.4285714285714286, | |
| "grad_norm": 0.9292937117747838, | |
| "learning_rate": 1.921476211870408e-05, | |
| "loss": 0.4866, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 1.5238095238095237, | |
| "grad_norm": 1.282976301854182, | |
| "learning_rate": 1.900968867902419e-05, | |
| "loss": 0.4938, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 1.619047619047619, | |
| "grad_norm": 0.9593133231649431, | |
| "learning_rate": 1.8782215733702286e-05, | |
| "loss": 0.4797, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 1.7142857142857144, | |
| "grad_norm": 0.8569214115769678, | |
| "learning_rate": 1.8532908816321557e-05, | |
| "loss": 0.4754, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 1.8095238095238095, | |
| "grad_norm": 0.907146656017202, | |
| "learning_rate": 1.826238774315995e-05, | |
| "loss": 0.4427, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 1.9047619047619047, | |
| "grad_norm": 0.7614040956946755, | |
| "learning_rate": 1.7971325072229227e-05, | |
| "loss": 0.4607, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 0.6867766519981378, | |
| "learning_rate": 1.766044443118978e-05, | |
| "loss": 0.4646, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 2.0952380952380953, | |
| "grad_norm": 0.7935863177231807, | |
| "learning_rate": 1.7330518718298263e-05, | |
| "loss": 0.381, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 2.1904761904761907, | |
| "grad_norm": 0.7245011381878015, | |
| "learning_rate": 1.698236818086073e-05, | |
| "loss": 0.3837, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 2.2857142857142856, | |
| "grad_norm": 0.6510461430338607, | |
| "learning_rate": 1.6616858375968596e-05, | |
| "loss": 0.3962, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 2.380952380952381, | |
| "grad_norm": 1.6977358828065254, | |
| "learning_rate": 1.6234898018587336e-05, | |
| "loss": 0.3705, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 2.4761904761904763, | |
| "grad_norm": 0.7908737714943238, | |
| "learning_rate": 1.5837436722347902e-05, | |
| "loss": 0.3542, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 2.571428571428571, | |
| "grad_norm": 0.6778558520761946, | |
| "learning_rate": 1.5425462638657597e-05, | |
| "loss": 0.3604, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 2.6666666666666665, | |
| "grad_norm": 0.7962060412186942, | |
| "learning_rate": 1.5000000000000002e-05, | |
| "loss": 0.3424, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 2.761904761904762, | |
| "grad_norm": 0.8268290840593088, | |
| "learning_rate": 1.4562106573531632e-05, | |
| "loss": 0.3412, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 2.857142857142857, | |
| "grad_norm": 0.5670331792119254, | |
| "learning_rate": 1.4112871031306118e-05, | |
| "loss": 0.3316, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 2.9523809523809526, | |
| "grad_norm": 0.6508986532232802, | |
| "learning_rate": 1.3653410243663953e-05, | |
| "loss": 0.3165, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 3.0476190476190474, | |
| "grad_norm": 0.6711456597845395, | |
| "learning_rate": 1.3184866502516846e-05, | |
| "loss": 0.2769, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 3.142857142857143, | |
| "grad_norm": 0.5839096100982227, | |
| "learning_rate": 1.2708404681430054e-05, | |
| "loss": 0.2887, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 3.238095238095238, | |
| "grad_norm": 0.5670482675192495, | |
| "learning_rate": 1.2225209339563144e-05, | |
| "loss": 0.2825, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 3.3333333333333335, | |
| "grad_norm": 0.5210927307591159, | |
| "learning_rate": 1.1736481776669307e-05, | |
| "loss": 0.2316, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 3.4285714285714284, | |
| "grad_norm": 0.5938051285030442, | |
| "learning_rate": 1.1243437046474854e-05, | |
| "loss": 0.2647, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 3.5238095238095237, | |
| "grad_norm": 0.5491400249099003, | |
| "learning_rate": 1.0747300935864245e-05, | |
| "loss": 0.2414, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 3.619047619047619, | |
| "grad_norm": 0.5744988994140534, | |
| "learning_rate": 1.0249306917380731e-05, | |
| "loss": 0.2817, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 3.7142857142857144, | |
| "grad_norm": 0.536714067735154, | |
| "learning_rate": 9.750693082619274e-06, | |
| "loss": 0.2455, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 3.8095238095238093, | |
| "grad_norm": 0.4845899247347522, | |
| "learning_rate": 9.252699064135759e-06, | |
| "loss": 0.2564, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 3.9047619047619047, | |
| "grad_norm": 0.5505036873107119, | |
| "learning_rate": 8.756562953525151e-06, | |
| "loss": 0.2483, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "grad_norm": 0.517265204051327, | |
| "learning_rate": 8.263518223330698e-06, | |
| "loss": 0.2364, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 4.095238095238095, | |
| "grad_norm": 0.4950259496341646, | |
| "learning_rate": 7.774790660436857e-06, | |
| "loss": 0.2149, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 4.190476190476191, | |
| "grad_norm": 0.47177317958532644, | |
| "learning_rate": 7.291595318569951e-06, | |
| "loss": 0.2378, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 4.285714285714286, | |
| "grad_norm": 0.4488056472571763, | |
| "learning_rate": 6.815133497483157e-06, | |
| "loss": 0.1971, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 4.380952380952381, | |
| "grad_norm": 0.46532840975151385, | |
| "learning_rate": 6.34658975633605e-06, | |
| "loss": 0.2102, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 4.476190476190476, | |
| "grad_norm": 0.528833776376275, | |
| "learning_rate": 5.887128968693887e-06, | |
| "loss": 0.1968, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 4.571428571428571, | |
| "grad_norm": 0.4437826137987985, | |
| "learning_rate": 5.43789342646837e-06, | |
| "loss": 0.1904, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 4.666666666666667, | |
| "grad_norm": 0.4512821448447588, | |
| "learning_rate": 5.000000000000003e-06, | |
| "loss": 0.1865, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 4.761904761904762, | |
| "grad_norm": 0.4598196264866205, | |
| "learning_rate": 4.5745373613424075e-06, | |
| "loss": 0.1748, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 4.857142857142857, | |
| "grad_norm": 0.42169249985517493, | |
| "learning_rate": 4.162563277652104e-06, | |
| "loss": 0.1672, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 4.9523809523809526, | |
| "grad_norm": 0.3901076743104791, | |
| "learning_rate": 3.7651019814126656e-06, | |
| "loss": 0.1941, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 5.0476190476190474, | |
| "grad_norm": 0.37578260509047834, | |
| "learning_rate": 3.3831416240314085e-06, | |
| "loss": 0.1631, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 5.142857142857143, | |
| "grad_norm": 0.3765155913554938, | |
| "learning_rate": 3.017631819139273e-06, | |
| "loss": 0.1847, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 5.238095238095238, | |
| "grad_norm": 0.32844330050101583, | |
| "learning_rate": 2.669481281701739e-06, | |
| "loss": 0.1626, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 5.333333333333333, | |
| "grad_norm": 0.34979061149880697, | |
| "learning_rate": 2.339555568810221e-06, | |
| "loss": 0.1512, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 5.428571428571429, | |
| "grad_norm": 0.36493462774853774, | |
| "learning_rate": 2.0286749277707783e-06, | |
| "loss": 0.1708, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 5.523809523809524, | |
| "grad_norm": 0.35209699525523674, | |
| "learning_rate": 1.7376122568400533e-06, | |
| "loss": 0.1864, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 5.619047619047619, | |
| "grad_norm": 0.3206536299150041, | |
| "learning_rate": 1.467091183678444e-06, | |
| "loss": 0.1478, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 5.714285714285714, | |
| "grad_norm": 0.3857558493104273, | |
| "learning_rate": 1.2177842662977136e-06, | |
| "loss": 0.1831, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 5.809523809523809, | |
| "grad_norm": 0.3258013062545114, | |
| "learning_rate": 9.903113209758098e-07, | |
| "loss": 0.1748, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 5.904761904761905, | |
| "grad_norm": 0.3022670371189457, | |
| "learning_rate": 7.852378812959227e-07, | |
| "loss": 0.1358, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "grad_norm": 0.319140815349133, | |
| "learning_rate": 6.030737921409169e-07, | |
| "loss": 0.1422, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 6.095238095238095, | |
| "grad_norm": 0.2996528808585056, | |
| "learning_rate": 4.4427194213859216e-07, | |
| "loss": 0.1369, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 6.190476190476191, | |
| "grad_norm": 0.3121733730318617, | |
| "learning_rate": 3.0922713770922155e-07, | |
| "loss": 0.1862, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 6.285714285714286, | |
| "grad_norm": 0.29051046445629997, | |
| "learning_rate": 1.9827512151456175e-07, | |
| "loss": 0.155, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 6.380952380952381, | |
| "grad_norm": 0.29269242399791506, | |
| "learning_rate": 1.1169173774871478e-07, | |
| "loss": 0.1545, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 6.476190476190476, | |
| "grad_norm": 0.297015091472824, | |
| "learning_rate": 4.9692246345985905e-08, | |
| "loss": 0.1286, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 6.571428571428571, | |
| "grad_norm": 0.2894368635929035, | |
| "learning_rate": 1.2430787810776556e-08, | |
| "loss": 0.1596, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 6.666666666666667, | |
| "grad_norm": 0.3071190956379776, | |
| "learning_rate": 0.0, | |
| "loss": 0.142, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 6.666666666666667, | |
| "step": 70, | |
| "total_flos": 7.211721962605773e+16, | |
| "train_loss": 0.3436877076114927, | |
| "train_runtime": 2253.009, | |
| "train_samples_per_second": 3.107, | |
| "train_steps_per_second": 0.031 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 70, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 7, | |
| "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": 7.211721962605773e+16, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |