| { | |
| "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": 6.602066608807158, | |
| "learning_rate": 2.8571428571428573e-06, | |
| "loss": 1.0427, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.19047619047619047, | |
| "grad_norm": 6.4596785223073905, | |
| "learning_rate": 5.7142857142857145e-06, | |
| "loss": 1.0161, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.2857142857142857, | |
| "grad_norm": 5.914821050875004, | |
| "learning_rate": 8.571428571428571e-06, | |
| "loss": 1.0133, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.38095238095238093, | |
| "grad_norm": 2.9371325895672635, | |
| "learning_rate": 1.1428571428571429e-05, | |
| "loss": 0.9579, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.47619047619047616, | |
| "grad_norm": 4.065610767728431, | |
| "learning_rate": 1.4285714285714287e-05, | |
| "loss": 0.9318, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.5714285714285714, | |
| "grad_norm": 4.306293208246383, | |
| "learning_rate": 1.7142857142857142e-05, | |
| "loss": 0.9461, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.6666666666666666, | |
| "grad_norm": 4.132802247553606, | |
| "learning_rate": 2e-05, | |
| "loss": 0.8957, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.7619047619047619, | |
| "grad_norm": 2.9738859949248044, | |
| "learning_rate": 1.9987569212189224e-05, | |
| "loss": 0.8729, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.8571428571428571, | |
| "grad_norm": 2.339845864147319, | |
| "learning_rate": 1.9950307753654016e-05, | |
| "loss": 0.817, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.9523809523809523, | |
| "grad_norm": 1.6917341759438047, | |
| "learning_rate": 1.9888308262251286e-05, | |
| "loss": 0.8084, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 1.0476190476190477, | |
| "grad_norm": 2.228932216348488, | |
| "learning_rate": 1.9801724878485438e-05, | |
| "loss": 1.1971, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 1.1428571428571428, | |
| "grad_norm": 1.6116910028184446, | |
| "learning_rate": 1.969077286229078e-05, | |
| "loss": 0.7941, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 1.2380952380952381, | |
| "grad_norm": 1.2749893912365768, | |
| "learning_rate": 1.955572805786141e-05, | |
| "loss": 0.7379, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 1.3333333333333333, | |
| "grad_norm": 1.1097340740833996, | |
| "learning_rate": 1.9396926207859085e-05, | |
| "loss": 0.732, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 1.4285714285714286, | |
| "grad_norm": 1.5292746548224316, | |
| "learning_rate": 1.921476211870408e-05, | |
| "loss": 0.7256, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 1.5238095238095237, | |
| "grad_norm": 1.0421356844072758, | |
| "learning_rate": 1.900968867902419e-05, | |
| "loss": 0.6985, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 1.619047619047619, | |
| "grad_norm": 1.1676174169103304, | |
| "learning_rate": 1.8782215733702286e-05, | |
| "loss": 0.7038, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 1.7142857142857144, | |
| "grad_norm": 1.0481288459645461, | |
| "learning_rate": 1.8532908816321557e-05, | |
| "loss": 0.7448, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 1.8095238095238095, | |
| "grad_norm": 0.9003539949185758, | |
| "learning_rate": 1.826238774315995e-05, | |
| "loss": 0.691, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 1.9047619047619047, | |
| "grad_norm": 0.7238531975599491, | |
| "learning_rate": 1.7971325072229227e-05, | |
| "loss": 0.625, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 1.2709119609174564, | |
| "learning_rate": 1.766044443118978e-05, | |
| "loss": 1.074, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 2.0952380952380953, | |
| "grad_norm": 0.840379681391275, | |
| "learning_rate": 1.7330518718298263e-05, | |
| "loss": 0.644, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 2.1904761904761907, | |
| "grad_norm": 0.824887474019856, | |
| "learning_rate": 1.698236818086073e-05, | |
| "loss": 0.632, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 2.2857142857142856, | |
| "grad_norm": 0.7599038458606115, | |
| "learning_rate": 1.6616858375968596e-05, | |
| "loss": 0.6422, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 2.380952380952381, | |
| "grad_norm": 0.7815093742430651, | |
| "learning_rate": 1.6234898018587336e-05, | |
| "loss": 0.6196, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 2.4761904761904763, | |
| "grad_norm": 0.7857964195996496, | |
| "learning_rate": 1.5837436722347902e-05, | |
| "loss": 0.6348, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 2.571428571428571, | |
| "grad_norm": 0.7560609708955964, | |
| "learning_rate": 1.5425462638657597e-05, | |
| "loss": 0.6392, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 2.6666666666666665, | |
| "grad_norm": 0.6501832494541909, | |
| "learning_rate": 1.5000000000000002e-05, | |
| "loss": 0.6168, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 2.761904761904762, | |
| "grad_norm": 0.6064782952907762, | |
| "learning_rate": 1.4562106573531632e-05, | |
| "loss": 0.6305, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 2.857142857142857, | |
| "grad_norm": 0.7418469268125416, | |
| "learning_rate": 1.4112871031306118e-05, | |
| "loss": 0.607, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 2.9523809523809526, | |
| "grad_norm": 0.630562750459011, | |
| "learning_rate": 1.3653410243663953e-05, | |
| "loss": 0.6097, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 3.0476190476190474, | |
| "grad_norm": 0.7971038290101818, | |
| "learning_rate": 1.3184866502516846e-05, | |
| "loss": 0.8648, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 3.142857142857143, | |
| "grad_norm": 0.6017298717945909, | |
| "learning_rate": 1.2708404681430054e-05, | |
| "loss": 0.6065, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 3.238095238095238, | |
| "grad_norm": 0.5617542294669544, | |
| "learning_rate": 1.2225209339563144e-05, | |
| "loss": 0.5426, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 3.3333333333333335, | |
| "grad_norm": 0.4609867434639684, | |
| "learning_rate": 1.1736481776669307e-05, | |
| "loss": 0.5476, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 3.4285714285714284, | |
| "grad_norm": 0.4621200257005054, | |
| "learning_rate": 1.1243437046474854e-05, | |
| "loss": 0.5152, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 3.5238095238095237, | |
| "grad_norm": 0.5923489152605452, | |
| "learning_rate": 1.0747300935864245e-05, | |
| "loss": 0.604, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 3.619047619047619, | |
| "grad_norm": 0.466397935586939, | |
| "learning_rate": 1.0249306917380731e-05, | |
| "loss": 0.5577, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 3.7142857142857144, | |
| "grad_norm": 0.5134501807594014, | |
| "learning_rate": 9.750693082619274e-06, | |
| "loss": 0.5559, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 3.8095238095238093, | |
| "grad_norm": 0.4884894980742842, | |
| "learning_rate": 9.252699064135759e-06, | |
| "loss": 0.5447, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 3.9047619047619047, | |
| "grad_norm": 0.4560698184162794, | |
| "learning_rate": 8.756562953525151e-06, | |
| "loss": 0.575, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "grad_norm": 0.5575480498686006, | |
| "learning_rate": 8.263518223330698e-06, | |
| "loss": 0.7902, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 4.095238095238095, | |
| "grad_norm": 0.4386783568955705, | |
| "learning_rate": 7.774790660436857e-06, | |
| "loss": 0.5176, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 4.190476190476191, | |
| "grad_norm": 0.46133450898025335, | |
| "learning_rate": 7.291595318569951e-06, | |
| "loss": 0.5198, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 4.285714285714286, | |
| "grad_norm": 0.40384884535902954, | |
| "learning_rate": 6.815133497483157e-06, | |
| "loss": 0.512, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 4.380952380952381, | |
| "grad_norm": 0.36927782908690887, | |
| "learning_rate": 6.34658975633605e-06, | |
| "loss": 0.5059, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 4.476190476190476, | |
| "grad_norm": 0.4210272658281602, | |
| "learning_rate": 5.887128968693887e-06, | |
| "loss": 0.5222, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 4.571428571428571, | |
| "grad_norm": 0.44359600662457427, | |
| "learning_rate": 5.43789342646837e-06, | |
| "loss": 0.5118, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 4.666666666666667, | |
| "grad_norm": 0.37489965769300615, | |
| "learning_rate": 5.000000000000003e-06, | |
| "loss": 0.4902, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 4.761904761904762, | |
| "grad_norm": 0.36079484623530333, | |
| "learning_rate": 4.5745373613424075e-06, | |
| "loss": 0.5274, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 4.857142857142857, | |
| "grad_norm": 0.33934463784286295, | |
| "learning_rate": 4.162563277652104e-06, | |
| "loss": 0.4923, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 4.9523809523809526, | |
| "grad_norm": 0.3534561413406161, | |
| "learning_rate": 3.7651019814126656e-06, | |
| "loss": 0.4909, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 5.0476190476190474, | |
| "grad_norm": 0.5418001999306784, | |
| "learning_rate": 3.3831416240314085e-06, | |
| "loss": 0.7041, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 5.142857142857143, | |
| "grad_norm": 0.36116148017650584, | |
| "learning_rate": 3.017631819139273e-06, | |
| "loss": 0.5332, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 5.238095238095238, | |
| "grad_norm": 0.3235059205566287, | |
| "learning_rate": 2.669481281701739e-06, | |
| "loss": 0.4391, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 5.333333333333333, | |
| "grad_norm": 0.36047433992133465, | |
| "learning_rate": 2.339555568810221e-06, | |
| "loss": 0.4875, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 5.428571428571429, | |
| "grad_norm": 0.3471331536057655, | |
| "learning_rate": 2.0286749277707783e-06, | |
| "loss": 0.4775, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 5.523809523809524, | |
| "grad_norm": 0.3309620670408688, | |
| "learning_rate": 1.7376122568400533e-06, | |
| "loss": 0.4886, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 5.619047619047619, | |
| "grad_norm": 0.31631203802150437, | |
| "learning_rate": 1.467091183678444e-06, | |
| "loss": 0.4826, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 5.714285714285714, | |
| "grad_norm": 0.3030558885224168, | |
| "learning_rate": 1.2177842662977136e-06, | |
| "loss": 0.4473, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 5.809523809523809, | |
| "grad_norm": 0.3314997745140985, | |
| "learning_rate": 9.903113209758098e-07, | |
| "loss": 0.4983, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 5.904761904761905, | |
| "grad_norm": 0.3073831790267688, | |
| "learning_rate": 7.852378812959227e-07, | |
| "loss": 0.4893, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "grad_norm": 0.458940176472896, | |
| "learning_rate": 6.030737921409169e-07, | |
| "loss": 0.699, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 6.095238095238095, | |
| "grad_norm": 0.2769130876426475, | |
| "learning_rate": 4.4427194213859216e-07, | |
| "loss": 0.4527, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 6.190476190476191, | |
| "grad_norm": 0.2734724611791438, | |
| "learning_rate": 3.0922713770922155e-07, | |
| "loss": 0.4742, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 6.285714285714286, | |
| "grad_norm": 0.2868467178570867, | |
| "learning_rate": 1.9827512151456175e-07, | |
| "loss": 0.4834, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 6.380952380952381, | |
| "grad_norm": 0.2739929820637378, | |
| "learning_rate": 1.1169173774871478e-07, | |
| "loss": 0.4748, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 6.476190476190476, | |
| "grad_norm": 0.29015336317159146, | |
| "learning_rate": 4.9692246345985905e-08, | |
| "loss": 0.4669, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 6.571428571428571, | |
| "grad_norm": 0.2750680291766846, | |
| "learning_rate": 1.2430787810776556e-08, | |
| "loss": 0.4616, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 6.666666666666667, | |
| "grad_norm": 0.2601247031032157, | |
| "learning_rate": 0.0, | |
| "loss": 0.4701, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 6.666666666666667, | |
| "step": 70, | |
| "total_flos": 1.9392876799380685e+17, | |
| "train_loss": 0.6446543974535806, | |
| "train_runtime": 2862.0961, | |
| "train_samples_per_second": 2.446, | |
| "train_steps_per_second": 0.024 | |
| } | |
| ], | |
| "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": 1.9392876799380685e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |