| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 4.951768488745981, | |
| "eval_steps": 500, | |
| "global_step": 385, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.012861736334405145, | |
| "grad_norm": 359.0199890136719, | |
| "learning_rate": 8.333333333333335e-09, | |
| "loss": 7.8034, | |
| "num_input_tokens_seen": 13440, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.02572347266881029, | |
| "grad_norm": 359.18682861328125, | |
| "learning_rate": 1.666666666666667e-08, | |
| "loss": 7.7577, | |
| "num_input_tokens_seen": 26976, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.03858520900321544, | |
| "grad_norm": 368.04339599609375, | |
| "learning_rate": 2.5000000000000002e-08, | |
| "loss": 7.8132, | |
| "num_input_tokens_seen": 40800, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.05144694533762058, | |
| "grad_norm": 357.04132080078125, | |
| "learning_rate": 3.333333333333334e-08, | |
| "loss": 7.7906, | |
| "num_input_tokens_seen": 54080, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.06430868167202572, | |
| "grad_norm": 361.8187255859375, | |
| "learning_rate": 4.166666666666667e-08, | |
| "loss": 7.7763, | |
| "num_input_tokens_seen": 67552, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.07717041800643087, | |
| "grad_norm": 368.778076171875, | |
| "learning_rate": 5.0000000000000004e-08, | |
| "loss": 7.7824, | |
| "num_input_tokens_seen": 81600, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.09003215434083602, | |
| "grad_norm": 367.5040588378906, | |
| "learning_rate": 5.833333333333334e-08, | |
| "loss": 7.833, | |
| "num_input_tokens_seen": 94720, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.10289389067524116, | |
| "grad_norm": 366.2318420410156, | |
| "learning_rate": 6.666666666666668e-08, | |
| "loss": 7.6949, | |
| "num_input_tokens_seen": 107488, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.1157556270096463, | |
| "grad_norm": 366.990966796875, | |
| "learning_rate": 7.500000000000001e-08, | |
| "loss": 7.8336, | |
| "num_input_tokens_seen": 120992, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.12861736334405144, | |
| "grad_norm": 357.8764953613281, | |
| "learning_rate": 8.333333333333334e-08, | |
| "loss": 7.7282, | |
| "num_input_tokens_seen": 134272, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.1414790996784566, | |
| "grad_norm": 363.4705505371094, | |
| "learning_rate": 9.166666666666668e-08, | |
| "loss": 7.6916, | |
| "num_input_tokens_seen": 148096, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.15434083601286175, | |
| "grad_norm": 365.1483154296875, | |
| "learning_rate": 1.0000000000000001e-07, | |
| "loss": 7.7333, | |
| "num_input_tokens_seen": 160736, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.16720257234726688, | |
| "grad_norm": 353.99609375, | |
| "learning_rate": 1.0833333333333335e-07, | |
| "loss": 7.6017, | |
| "num_input_tokens_seen": 173376, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.18006430868167203, | |
| "grad_norm": 357.7409362792969, | |
| "learning_rate": 1.1666666666666668e-07, | |
| "loss": 7.644, | |
| "num_input_tokens_seen": 187136, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.19292604501607716, | |
| "grad_norm": 357.3723449707031, | |
| "learning_rate": 1.2500000000000002e-07, | |
| "loss": 7.5965, | |
| "num_input_tokens_seen": 200192, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.2057877813504823, | |
| "grad_norm": 352.3059997558594, | |
| "learning_rate": 1.3333333333333336e-07, | |
| "loss": 7.5883, | |
| "num_input_tokens_seen": 213856, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.21864951768488747, | |
| "grad_norm": 349.4331970214844, | |
| "learning_rate": 1.4166666666666668e-07, | |
| "loss": 7.2464, | |
| "num_input_tokens_seen": 226944, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.2315112540192926, | |
| "grad_norm": 346.9617004394531, | |
| "learning_rate": 1.5000000000000002e-07, | |
| "loss": 7.3133, | |
| "num_input_tokens_seen": 240640, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.24437299035369775, | |
| "grad_norm": 344.31512451171875, | |
| "learning_rate": 1.5833333333333336e-07, | |
| "loss": 7.2133, | |
| "num_input_tokens_seen": 253280, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.2572347266881029, | |
| "grad_norm": 348.57623291015625, | |
| "learning_rate": 1.6666666666666668e-07, | |
| "loss": 7.2431, | |
| "num_input_tokens_seen": 266400, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.27009646302250806, | |
| "grad_norm": 345.67694091796875, | |
| "learning_rate": 1.7500000000000002e-07, | |
| "loss": 7.1875, | |
| "num_input_tokens_seen": 280416, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.2829581993569132, | |
| "grad_norm": 336.11968994140625, | |
| "learning_rate": 1.8333333333333336e-07, | |
| "loss": 7.0659, | |
| "num_input_tokens_seen": 294368, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.2958199356913183, | |
| "grad_norm": 348.02783203125, | |
| "learning_rate": 1.9166666666666668e-07, | |
| "loss": 6.3595, | |
| "num_input_tokens_seen": 307840, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.3086816720257235, | |
| "grad_norm": 306.9109802246094, | |
| "learning_rate": 2.0000000000000002e-07, | |
| "loss": 6.0417, | |
| "num_input_tokens_seen": 322144, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.3215434083601286, | |
| "grad_norm": 308.7346496582031, | |
| "learning_rate": 2.0833333333333333e-07, | |
| "loss": 5.9894, | |
| "num_input_tokens_seen": 335424, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.33440514469453375, | |
| "grad_norm": 303.3129577636719, | |
| "learning_rate": 2.166666666666667e-07, | |
| "loss": 5.9259, | |
| "num_input_tokens_seen": 349376, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.34726688102893893, | |
| "grad_norm": 305.47637939453125, | |
| "learning_rate": 2.2500000000000002e-07, | |
| "loss": 5.8983, | |
| "num_input_tokens_seen": 362944, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.36012861736334406, | |
| "grad_norm": 306.3539123535156, | |
| "learning_rate": 2.3333333333333336e-07, | |
| "loss": 5.6848, | |
| "num_input_tokens_seen": 376352, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.3729903536977492, | |
| "grad_norm": 300.50201416015625, | |
| "learning_rate": 2.416666666666667e-07, | |
| "loss": 5.5649, | |
| "num_input_tokens_seen": 389312, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.3858520900321543, | |
| "grad_norm": 297.82757568359375, | |
| "learning_rate": 2.5000000000000004e-07, | |
| "loss": 5.4642, | |
| "num_input_tokens_seen": 402848, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.3987138263665595, | |
| "grad_norm": 348.0853271484375, | |
| "learning_rate": 2.5833333333333333e-07, | |
| "loss": 4.7955, | |
| "num_input_tokens_seen": 416352, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.4115755627009646, | |
| "grad_norm": 346.5870361328125, | |
| "learning_rate": 2.666666666666667e-07, | |
| "loss": 2.8339, | |
| "num_input_tokens_seen": 429920, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.42443729903536975, | |
| "grad_norm": 327.6314697265625, | |
| "learning_rate": 2.75e-07, | |
| "loss": 2.4477, | |
| "num_input_tokens_seen": 444064, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.43729903536977494, | |
| "grad_norm": 321.9542236328125, | |
| "learning_rate": 2.8333333333333336e-07, | |
| "loss": 2.3331, | |
| "num_input_tokens_seen": 458304, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.45016077170418006, | |
| "grad_norm": 327.8713073730469, | |
| "learning_rate": 2.916666666666667e-07, | |
| "loss": 2.2143, | |
| "num_input_tokens_seen": 471904, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.4630225080385852, | |
| "grad_norm": 317.32427978515625, | |
| "learning_rate": 3.0000000000000004e-07, | |
| "loss": 2.0067, | |
| "num_input_tokens_seen": 484768, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.4758842443729904, | |
| "grad_norm": 251.88111877441406, | |
| "learning_rate": 3.083333333333334e-07, | |
| "loss": 1.7702, | |
| "num_input_tokens_seen": 497696, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.4887459807073955, | |
| "grad_norm": 273.716064453125, | |
| "learning_rate": 3.166666666666667e-07, | |
| "loss": 1.5557, | |
| "num_input_tokens_seen": 511072, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.5016077170418006, | |
| "grad_norm": 293.1105651855469, | |
| "learning_rate": 3.25e-07, | |
| "loss": 1.3024, | |
| "num_input_tokens_seen": 524576, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.5144694533762058, | |
| "grad_norm": 243.40711975097656, | |
| "learning_rate": 3.3333333333333335e-07, | |
| "loss": 1.1652, | |
| "num_input_tokens_seen": 538112, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.5273311897106109, | |
| "grad_norm": 111.22821807861328, | |
| "learning_rate": 3.416666666666667e-07, | |
| "loss": 0.6839, | |
| "num_input_tokens_seen": 552096, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.5401929260450161, | |
| "grad_norm": 104.02100372314453, | |
| "learning_rate": 3.5000000000000004e-07, | |
| "loss": 0.4774, | |
| "num_input_tokens_seen": 565920, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.5530546623794212, | |
| "grad_norm": 32.459312438964844, | |
| "learning_rate": 3.583333333333334e-07, | |
| "loss": 0.3841, | |
| "num_input_tokens_seen": 579200, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.5659163987138264, | |
| "grad_norm": 15.353242874145508, | |
| "learning_rate": 3.666666666666667e-07, | |
| "loss": 0.3588, | |
| "num_input_tokens_seen": 592864, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.5787781350482315, | |
| "grad_norm": 48.64632034301758, | |
| "learning_rate": 3.75e-07, | |
| "loss": 0.3628, | |
| "num_input_tokens_seen": 606656, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.5916398713826366, | |
| "grad_norm": 34.02824020385742, | |
| "learning_rate": 3.8333333333333335e-07, | |
| "loss": 0.3426, | |
| "num_input_tokens_seen": 619968, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.6045016077170418, | |
| "grad_norm": 15.54571533203125, | |
| "learning_rate": 3.9166666666666675e-07, | |
| "loss": 0.3279, | |
| "num_input_tokens_seen": 633632, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.617363344051447, | |
| "grad_norm": 101.66536712646484, | |
| "learning_rate": 4.0000000000000003e-07, | |
| "loss": 0.3947, | |
| "num_input_tokens_seen": 647360, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.6302250803858521, | |
| "grad_norm": 39.69755935668945, | |
| "learning_rate": 4.083333333333334e-07, | |
| "loss": 0.3075, | |
| "num_input_tokens_seen": 661504, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.6430868167202572, | |
| "grad_norm": 23.356718063354492, | |
| "learning_rate": 4.1666666666666667e-07, | |
| "loss": 0.3236, | |
| "num_input_tokens_seen": 675424, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.6559485530546624, | |
| "grad_norm": 74.00253295898438, | |
| "learning_rate": 4.2500000000000006e-07, | |
| "loss": 0.3557, | |
| "num_input_tokens_seen": 688800, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.6688102893890675, | |
| "grad_norm": 109.3729248046875, | |
| "learning_rate": 4.333333333333334e-07, | |
| "loss": 0.4008, | |
| "num_input_tokens_seen": 702208, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.6816720257234726, | |
| "grad_norm": 81.13125610351562, | |
| "learning_rate": 4.416666666666667e-07, | |
| "loss": 0.3586, | |
| "num_input_tokens_seen": 716096, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.6945337620578779, | |
| "grad_norm": 24.126953125, | |
| "learning_rate": 4.5000000000000003e-07, | |
| "loss": 0.3023, | |
| "num_input_tokens_seen": 728672, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.707395498392283, | |
| "grad_norm": 77.53913879394531, | |
| "learning_rate": 4.583333333333333e-07, | |
| "loss": 0.3547, | |
| "num_input_tokens_seen": 742912, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.7202572347266881, | |
| "grad_norm": 95.46034240722656, | |
| "learning_rate": 4.666666666666667e-07, | |
| "loss": 0.3846, | |
| "num_input_tokens_seen": 755808, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.7331189710610932, | |
| "grad_norm": 86.11170959472656, | |
| "learning_rate": 4.7500000000000006e-07, | |
| "loss": 0.3743, | |
| "num_input_tokens_seen": 769696, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.7459807073954984, | |
| "grad_norm": 31.460582733154297, | |
| "learning_rate": 4.833333333333334e-07, | |
| "loss": 0.3091, | |
| "num_input_tokens_seen": 783680, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.7588424437299035, | |
| "grad_norm": 34.459659576416016, | |
| "learning_rate": 4.916666666666667e-07, | |
| "loss": 0.3094, | |
| "num_input_tokens_seen": 796672, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.7717041800643086, | |
| "grad_norm": 51.55731201171875, | |
| "learning_rate": 5.000000000000001e-07, | |
| "loss": 0.3309, | |
| "num_input_tokens_seen": 810304, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.7845659163987139, | |
| "grad_norm": 35.633277893066406, | |
| "learning_rate": 5.083333333333334e-07, | |
| "loss": 0.3276, | |
| "num_input_tokens_seen": 824160, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.797427652733119, | |
| "grad_norm": 9.230757713317871, | |
| "learning_rate": 5.166666666666667e-07, | |
| "loss": 0.3084, | |
| "num_input_tokens_seen": 837312, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.8102893890675241, | |
| "grad_norm": 35.229454040527344, | |
| "learning_rate": 5.250000000000001e-07, | |
| "loss": 0.3182, | |
| "num_input_tokens_seen": 851168, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.8231511254019293, | |
| "grad_norm": 47.88737487792969, | |
| "learning_rate": 5.333333333333335e-07, | |
| "loss": 0.3469, | |
| "num_input_tokens_seen": 864096, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.8360128617363344, | |
| "grad_norm": 38.481746673583984, | |
| "learning_rate": 5.416666666666667e-07, | |
| "loss": 0.3253, | |
| "num_input_tokens_seen": 878048, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.8488745980707395, | |
| "grad_norm": 11.656455993652344, | |
| "learning_rate": 5.5e-07, | |
| "loss": 0.2746, | |
| "num_input_tokens_seen": 891904, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.8617363344051447, | |
| "grad_norm": 18.758018493652344, | |
| "learning_rate": 5.583333333333333e-07, | |
| "loss": 0.2893, | |
| "num_input_tokens_seen": 906016, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.8745980707395499, | |
| "grad_norm": 19.316091537475586, | |
| "learning_rate": 5.666666666666667e-07, | |
| "loss": 0.2827, | |
| "num_input_tokens_seen": 918944, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.887459807073955, | |
| "grad_norm": 32.92877960205078, | |
| "learning_rate": 5.750000000000001e-07, | |
| "loss": 0.2978, | |
| "num_input_tokens_seen": 932672, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.9003215434083601, | |
| "grad_norm": 14.833833694458008, | |
| "learning_rate": 5.833333333333334e-07, | |
| "loss": 0.2703, | |
| "num_input_tokens_seen": 945248, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.9131832797427653, | |
| "grad_norm": 23.44466209411621, | |
| "learning_rate": 5.916666666666667e-07, | |
| "loss": 0.2968, | |
| "num_input_tokens_seen": 958784, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.9260450160771704, | |
| "grad_norm": 56.151981353759766, | |
| "learning_rate": 6.000000000000001e-07, | |
| "loss": 0.3035, | |
| "num_input_tokens_seen": 972416, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.9389067524115756, | |
| "grad_norm": 77.62692260742188, | |
| "learning_rate": 6.083333333333334e-07, | |
| "loss": 0.3211, | |
| "num_input_tokens_seen": 985888, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.9517684887459807, | |
| "grad_norm": 65.45875549316406, | |
| "learning_rate": 6.166666666666668e-07, | |
| "loss": 0.2913, | |
| "num_input_tokens_seen": 999296, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.9646302250803859, | |
| "grad_norm": 16.159313201904297, | |
| "learning_rate": 6.25e-07, | |
| "loss": 0.2817, | |
| "num_input_tokens_seen": 1012640, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.977491961414791, | |
| "grad_norm": 33.846290588378906, | |
| "learning_rate": 6.333333333333334e-07, | |
| "loss": 0.2827, | |
| "num_input_tokens_seen": 1026112, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.9903536977491961, | |
| "grad_norm": 9.542298316955566, | |
| "learning_rate": 6.416666666666667e-07, | |
| "loss": 0.229, | |
| "num_input_tokens_seen": 1039424, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 1.0032154340836013, | |
| "grad_norm": 10.284690856933594, | |
| "learning_rate": 6.5e-07, | |
| "loss": 0.2503, | |
| "num_input_tokens_seen": 1053408, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 1.0160771704180065, | |
| "grad_norm": 19.490089416503906, | |
| "learning_rate": 6.583333333333333e-07, | |
| "loss": 0.2453, | |
| "num_input_tokens_seen": 1067328, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 1.0289389067524115, | |
| "grad_norm": 18.234272003173828, | |
| "learning_rate": 6.666666666666667e-07, | |
| "loss": 0.2167, | |
| "num_input_tokens_seen": 1080288, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 1.0418006430868167, | |
| "grad_norm": 9.240696907043457, | |
| "learning_rate": 6.750000000000001e-07, | |
| "loss": 0.2361, | |
| "num_input_tokens_seen": 1093952, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 1.0546623794212218, | |
| "grad_norm": 22.255823135375977, | |
| "learning_rate": 6.833333333333334e-07, | |
| "loss": 0.2248, | |
| "num_input_tokens_seen": 1107904, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 1.067524115755627, | |
| "grad_norm": 26.029281616210938, | |
| "learning_rate": 6.916666666666668e-07, | |
| "loss": 0.2491, | |
| "num_input_tokens_seen": 1121120, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 1.0803858520900322, | |
| "grad_norm": 34.11492156982422, | |
| "learning_rate": 7.000000000000001e-07, | |
| "loss": 0.2352, | |
| "num_input_tokens_seen": 1135040, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 1.0932475884244373, | |
| "grad_norm": 65.68599700927734, | |
| "learning_rate": 7.083333333333334e-07, | |
| "loss": 0.2365, | |
| "num_input_tokens_seen": 1148992, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 1.1061093247588425, | |
| "grad_norm": 72.81002807617188, | |
| "learning_rate": 7.166666666666668e-07, | |
| "loss": 0.217, | |
| "num_input_tokens_seen": 1162592, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 1.1189710610932475, | |
| "grad_norm": 21.043798446655273, | |
| "learning_rate": 7.25e-07, | |
| "loss": 0.2258, | |
| "num_input_tokens_seen": 1175104, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 1.1318327974276527, | |
| "grad_norm": 71.2937240600586, | |
| "learning_rate": 7.333333333333334e-07, | |
| "loss": 0.245, | |
| "num_input_tokens_seen": 1189376, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 1.144694533762058, | |
| "grad_norm": 106.12057495117188, | |
| "learning_rate": 7.416666666666668e-07, | |
| "loss": 0.3132, | |
| "num_input_tokens_seen": 1202560, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 1.157556270096463, | |
| "grad_norm": 84.74403381347656, | |
| "learning_rate": 7.5e-07, | |
| "loss": 0.284, | |
| "num_input_tokens_seen": 1216832, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 1.1704180064308682, | |
| "grad_norm": 10.08238410949707, | |
| "learning_rate": 7.583333333333334e-07, | |
| "loss": 0.1933, | |
| "num_input_tokens_seen": 1230528, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 1.1832797427652733, | |
| "grad_norm": 56.27880859375, | |
| "learning_rate": 7.666666666666667e-07, | |
| "loss": 0.2154, | |
| "num_input_tokens_seen": 1244352, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 1.1961414790996785, | |
| "grad_norm": 39.58720779418945, | |
| "learning_rate": 7.750000000000001e-07, | |
| "loss": 0.2064, | |
| "num_input_tokens_seen": 1257472, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 1.2090032154340835, | |
| "grad_norm": 12.087499618530273, | |
| "learning_rate": 7.833333333333335e-07, | |
| "loss": 0.2038, | |
| "num_input_tokens_seen": 1271392, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 1.2218649517684887, | |
| "grad_norm": 29.51178550720215, | |
| "learning_rate": 7.916666666666667e-07, | |
| "loss": 0.2152, | |
| "num_input_tokens_seen": 1286432, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 1.234726688102894, | |
| "grad_norm": 12.675917625427246, | |
| "learning_rate": 8.000000000000001e-07, | |
| "loss": 0.1961, | |
| "num_input_tokens_seen": 1300096, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 1.247588424437299, | |
| "grad_norm": 11.436767578125, | |
| "learning_rate": 8.083333333333334e-07, | |
| "loss": 0.1772, | |
| "num_input_tokens_seen": 1313568, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 1.2604501607717042, | |
| "grad_norm": 25.415918350219727, | |
| "learning_rate": 8.166666666666668e-07, | |
| "loss": 0.1846, | |
| "num_input_tokens_seen": 1327328, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 1.2733118971061093, | |
| "grad_norm": 11.161438941955566, | |
| "learning_rate": 8.250000000000001e-07, | |
| "loss": 0.1823, | |
| "num_input_tokens_seen": 1340960, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 1.2861736334405145, | |
| "grad_norm": 7.966615200042725, | |
| "learning_rate": 8.333333333333333e-07, | |
| "loss": 0.1794, | |
| "num_input_tokens_seen": 1353440, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.2990353697749195, | |
| "grad_norm": 32.296085357666016, | |
| "learning_rate": 8.416666666666667e-07, | |
| "loss": 0.2106, | |
| "num_input_tokens_seen": 1367680, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 1.3118971061093248, | |
| "grad_norm": 26.521038055419922, | |
| "learning_rate": 8.500000000000001e-07, | |
| "loss": 0.2123, | |
| "num_input_tokens_seen": 1380864, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 1.32475884244373, | |
| "grad_norm": 63.48737716674805, | |
| "learning_rate": 8.583333333333334e-07, | |
| "loss": 0.2413, | |
| "num_input_tokens_seen": 1393888, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 1.337620578778135, | |
| "grad_norm": 55.781776428222656, | |
| "learning_rate": 8.666666666666668e-07, | |
| "loss": 0.2334, | |
| "num_input_tokens_seen": 1406912, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 1.3504823151125402, | |
| "grad_norm": 13.036691665649414, | |
| "learning_rate": 8.75e-07, | |
| "loss": 0.2069, | |
| "num_input_tokens_seen": 1420000, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 1.3633440514469453, | |
| "grad_norm": 45.98344421386719, | |
| "learning_rate": 8.833333333333334e-07, | |
| "loss": 0.2262, | |
| "num_input_tokens_seen": 1433440, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 1.3762057877813505, | |
| "grad_norm": 34.49677276611328, | |
| "learning_rate": 8.916666666666668e-07, | |
| "loss": 0.1718, | |
| "num_input_tokens_seen": 1446560, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 1.3890675241157555, | |
| "grad_norm": 21.14679718017578, | |
| "learning_rate": 9.000000000000001e-07, | |
| "loss": 0.204, | |
| "num_input_tokens_seen": 1460320, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 1.4019292604501608, | |
| "grad_norm": 26.53287124633789, | |
| "learning_rate": 9.083333333333335e-07, | |
| "loss": 0.1849, | |
| "num_input_tokens_seen": 1474272, | |
| "step": 109 | |
| }, | |
| { | |
| "epoch": 1.414790996784566, | |
| "grad_norm": 34.011962890625, | |
| "learning_rate": 9.166666666666666e-07, | |
| "loss": 0.2028, | |
| "num_input_tokens_seen": 1487904, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 1.427652733118971, | |
| "grad_norm": 17.4981689453125, | |
| "learning_rate": 9.25e-07, | |
| "loss": 0.179, | |
| "num_input_tokens_seen": 1501664, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 1.4405144694533762, | |
| "grad_norm": 20.183582305908203, | |
| "learning_rate": 9.333333333333334e-07, | |
| "loss": 0.1813, | |
| "num_input_tokens_seen": 1515264, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 1.4533762057877815, | |
| "grad_norm": 26.655994415283203, | |
| "learning_rate": 9.416666666666667e-07, | |
| "loss": 0.1955, | |
| "num_input_tokens_seen": 1528640, | |
| "step": 113 | |
| }, | |
| { | |
| "epoch": 1.4662379421221865, | |
| "grad_norm": 25.745370864868164, | |
| "learning_rate": 9.500000000000001e-07, | |
| "loss": 0.1577, | |
| "num_input_tokens_seen": 1541632, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 1.4790996784565915, | |
| "grad_norm": 22.924352645874023, | |
| "learning_rate": 9.583333333333334e-07, | |
| "loss": 0.1509, | |
| "num_input_tokens_seen": 1554592, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 1.4919614147909968, | |
| "grad_norm": 26.520856857299805, | |
| "learning_rate": 9.666666666666668e-07, | |
| "loss": 0.2052, | |
| "num_input_tokens_seen": 1567296, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 1.504823151125402, | |
| "grad_norm": 23.989120483398438, | |
| "learning_rate": 9.750000000000002e-07, | |
| "loss": 0.1576, | |
| "num_input_tokens_seen": 1580800, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 1.517684887459807, | |
| "grad_norm": 11.067609786987305, | |
| "learning_rate": 9.833333333333334e-07, | |
| "loss": 0.1459, | |
| "num_input_tokens_seen": 1593792, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 1.5305466237942122, | |
| "grad_norm": 41.14239501953125, | |
| "learning_rate": 9.916666666666668e-07, | |
| "loss": 0.2694, | |
| "num_input_tokens_seen": 1607648, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 1.5434083601286175, | |
| "grad_norm": 17.72841453552246, | |
| "learning_rate": 1.0000000000000002e-06, | |
| "loss": 0.1891, | |
| "num_input_tokens_seen": 1621184, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 1.5562700964630225, | |
| "grad_norm": 13.838713645935059, | |
| "learning_rate": 1.0083333333333333e-06, | |
| "loss": 0.1655, | |
| "num_input_tokens_seen": 1634240, | |
| "step": 121 | |
| }, | |
| { | |
| "epoch": 1.5691318327974275, | |
| "grad_norm": 17.73114013671875, | |
| "learning_rate": 1.0166666666666667e-06, | |
| "loss": 0.1534, | |
| "num_input_tokens_seen": 1647712, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 1.5819935691318328, | |
| "grad_norm": 7.044174671173096, | |
| "learning_rate": 1.025e-06, | |
| "loss": 0.1373, | |
| "num_input_tokens_seen": 1661344, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 1.594855305466238, | |
| "grad_norm": 13.696454048156738, | |
| "learning_rate": 1.0333333333333333e-06, | |
| "loss": 0.1528, | |
| "num_input_tokens_seen": 1674880, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 1.607717041800643, | |
| "grad_norm": 11.191144943237305, | |
| "learning_rate": 1.0416666666666667e-06, | |
| "loss": 0.2017, | |
| "num_input_tokens_seen": 1688992, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 1.6205787781350482, | |
| "grad_norm": 10.479023933410645, | |
| "learning_rate": 1.0500000000000001e-06, | |
| "loss": 0.1554, | |
| "num_input_tokens_seen": 1702944, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 1.6334405144694535, | |
| "grad_norm": 12.889703750610352, | |
| "learning_rate": 1.0583333333333335e-06, | |
| "loss": 0.1332, | |
| "num_input_tokens_seen": 1716768, | |
| "step": 127 | |
| }, | |
| { | |
| "epoch": 1.6463022508038585, | |
| "grad_norm": 8.173032760620117, | |
| "learning_rate": 1.066666666666667e-06, | |
| "loss": 0.115, | |
| "num_input_tokens_seen": 1730848, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 1.6591639871382635, | |
| "grad_norm": 14.694462776184082, | |
| "learning_rate": 1.075e-06, | |
| "loss": 0.119, | |
| "num_input_tokens_seen": 1743520, | |
| "step": 129 | |
| }, | |
| { | |
| "epoch": 1.6720257234726688, | |
| "grad_norm": 8.472253799438477, | |
| "learning_rate": 1.0833333333333335e-06, | |
| "loss": 0.1164, | |
| "num_input_tokens_seen": 1757696, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 1.684887459807074, | |
| "grad_norm": 20.757648468017578, | |
| "learning_rate": 1.0916666666666667e-06, | |
| "loss": 0.1981, | |
| "num_input_tokens_seen": 1771264, | |
| "step": 131 | |
| }, | |
| { | |
| "epoch": 1.697749196141479, | |
| "grad_norm": 20.149930953979492, | |
| "learning_rate": 1.1e-06, | |
| "loss": 0.168, | |
| "num_input_tokens_seen": 1784480, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 1.7106109324758842, | |
| "grad_norm": 9.992751121520996, | |
| "learning_rate": 1.1083333333333335e-06, | |
| "loss": 0.0741, | |
| "num_input_tokens_seen": 1798176, | |
| "step": 133 | |
| }, | |
| { | |
| "epoch": 1.7234726688102895, | |
| "grad_norm": 26.80909538269043, | |
| "learning_rate": 1.1166666666666666e-06, | |
| "loss": 0.1847, | |
| "num_input_tokens_seen": 1811264, | |
| "step": 134 | |
| }, | |
| { | |
| "epoch": 1.7363344051446945, | |
| "grad_norm": 16.494613647460938, | |
| "learning_rate": 1.125e-06, | |
| "loss": 0.108, | |
| "num_input_tokens_seen": 1825024, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 1.7491961414790995, | |
| "grad_norm": 18.742122650146484, | |
| "learning_rate": 1.1333333333333334e-06, | |
| "loss": 0.1214, | |
| "num_input_tokens_seen": 1838624, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 1.762057877813505, | |
| "grad_norm": 10.102185249328613, | |
| "learning_rate": 1.1416666666666668e-06, | |
| "loss": 0.1252, | |
| "num_input_tokens_seen": 1852288, | |
| "step": 137 | |
| }, | |
| { | |
| "epoch": 1.77491961414791, | |
| "grad_norm": 23.612730026245117, | |
| "learning_rate": 1.1500000000000002e-06, | |
| "loss": 0.144, | |
| "num_input_tokens_seen": 1865376, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 1.787781350482315, | |
| "grad_norm": 11.11936092376709, | |
| "learning_rate": 1.1583333333333334e-06, | |
| "loss": 0.1269, | |
| "num_input_tokens_seen": 1878784, | |
| "step": 139 | |
| }, | |
| { | |
| "epoch": 1.8006430868167203, | |
| "grad_norm": 7.341479778289795, | |
| "learning_rate": 1.1666666666666668e-06, | |
| "loss": 0.1283, | |
| "num_input_tokens_seen": 1892320, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 1.8135048231511255, | |
| "grad_norm": 16.097875595092773, | |
| "learning_rate": 1.175e-06, | |
| "loss": 0.0929, | |
| "num_input_tokens_seen": 1905728, | |
| "step": 141 | |
| }, | |
| { | |
| "epoch": 1.8263665594855305, | |
| "grad_norm": 18.07818603515625, | |
| "learning_rate": 1.1833333333333334e-06, | |
| "loss": 0.1349, | |
| "num_input_tokens_seen": 1918752, | |
| "step": 142 | |
| }, | |
| { | |
| "epoch": 1.8392282958199357, | |
| "grad_norm": 18.349048614501953, | |
| "learning_rate": 1.1916666666666668e-06, | |
| "loss": 0.1277, | |
| "num_input_tokens_seen": 1931808, | |
| "step": 143 | |
| }, | |
| { | |
| "epoch": 1.852090032154341, | |
| "grad_norm": 12.308938980102539, | |
| "learning_rate": 1.2000000000000002e-06, | |
| "loss": 0.1585, | |
| "num_input_tokens_seen": 1945312, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 1.864951768488746, | |
| "grad_norm": 19.95519256591797, | |
| "learning_rate": 1.2083333333333333e-06, | |
| "loss": 0.1468, | |
| "num_input_tokens_seen": 1958016, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 1.877813504823151, | |
| "grad_norm": 11.419037818908691, | |
| "learning_rate": 1.2166666666666667e-06, | |
| "loss": 0.1049, | |
| "num_input_tokens_seen": 1971392, | |
| "step": 146 | |
| }, | |
| { | |
| "epoch": 1.8906752411575563, | |
| "grad_norm": 9.492958068847656, | |
| "learning_rate": 1.2250000000000001e-06, | |
| "loss": 0.1297, | |
| "num_input_tokens_seen": 1984992, | |
| "step": 147 | |
| }, | |
| { | |
| "epoch": 1.9035369774919615, | |
| "grad_norm": 6.134005546569824, | |
| "learning_rate": 1.2333333333333335e-06, | |
| "loss": 0.1111, | |
| "num_input_tokens_seen": 1998144, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 1.9163987138263665, | |
| "grad_norm": 10.250520706176758, | |
| "learning_rate": 1.2416666666666667e-06, | |
| "loss": 0.1202, | |
| "num_input_tokens_seen": 2012032, | |
| "step": 149 | |
| }, | |
| { | |
| "epoch": 1.9292604501607717, | |
| "grad_norm": 10.018802642822266, | |
| "learning_rate": 1.25e-06, | |
| "loss": 0.0829, | |
| "num_input_tokens_seen": 2025600, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 1.942122186495177, | |
| "grad_norm": 17.175769805908203, | |
| "learning_rate": 1.2583333333333333e-06, | |
| "loss": 0.1119, | |
| "num_input_tokens_seen": 2040096, | |
| "step": 151 | |
| }, | |
| { | |
| "epoch": 1.954983922829582, | |
| "grad_norm": 18.159189224243164, | |
| "learning_rate": 1.2666666666666669e-06, | |
| "loss": 0.1144, | |
| "num_input_tokens_seen": 2053504, | |
| "step": 152 | |
| }, | |
| { | |
| "epoch": 1.967845659163987, | |
| "grad_norm": 14.536725044250488, | |
| "learning_rate": 1.275e-06, | |
| "loss": 0.117, | |
| "num_input_tokens_seen": 2065856, | |
| "step": 153 | |
| }, | |
| { | |
| "epoch": 1.9807073954983923, | |
| "grad_norm": 10.24523639678955, | |
| "learning_rate": 1.2833333333333335e-06, | |
| "loss": 0.0998, | |
| "num_input_tokens_seen": 2078656, | |
| "step": 154 | |
| }, | |
| { | |
| "epoch": 1.9935691318327975, | |
| "grad_norm": 20.030460357666016, | |
| "learning_rate": 1.2916666666666669e-06, | |
| "loss": 0.1384, | |
| "num_input_tokens_seen": 2092672, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 2.0064308681672025, | |
| "grad_norm": 12.654150009155273, | |
| "learning_rate": 1.3e-06, | |
| "loss": 0.1157, | |
| "num_input_tokens_seen": 2105728, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 2.0192926045016075, | |
| "grad_norm": 5.51693058013916, | |
| "learning_rate": 1.3083333333333334e-06, | |
| "loss": 0.0696, | |
| "num_input_tokens_seen": 2118976, | |
| "step": 157 | |
| }, | |
| { | |
| "epoch": 2.032154340836013, | |
| "grad_norm": 9.432037353515625, | |
| "learning_rate": 1.3166666666666666e-06, | |
| "loss": 0.0665, | |
| "num_input_tokens_seen": 2132352, | |
| "step": 158 | |
| }, | |
| { | |
| "epoch": 2.045016077170418, | |
| "grad_norm": 15.199766159057617, | |
| "learning_rate": 1.3250000000000002e-06, | |
| "loss": 0.0783, | |
| "num_input_tokens_seen": 2146048, | |
| "step": 159 | |
| }, | |
| { | |
| "epoch": 2.057877813504823, | |
| "grad_norm": 10.740960121154785, | |
| "learning_rate": 1.3333333333333334e-06, | |
| "loss": 0.0749, | |
| "num_input_tokens_seen": 2158752, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 2.0707395498392285, | |
| "grad_norm": 7.335105895996094, | |
| "learning_rate": 1.3416666666666666e-06, | |
| "loss": 0.0731, | |
| "num_input_tokens_seen": 2171872, | |
| "step": 161 | |
| }, | |
| { | |
| "epoch": 2.0836012861736335, | |
| "grad_norm": 14.225622177124023, | |
| "learning_rate": 1.3500000000000002e-06, | |
| "loss": 0.0913, | |
| "num_input_tokens_seen": 2184800, | |
| "step": 162 | |
| }, | |
| { | |
| "epoch": 2.0964630225080385, | |
| "grad_norm": 12.737798690795898, | |
| "learning_rate": 1.3583333333333334e-06, | |
| "loss": 0.0521, | |
| "num_input_tokens_seen": 2198176, | |
| "step": 163 | |
| }, | |
| { | |
| "epoch": 2.1093247588424435, | |
| "grad_norm": 10.609269142150879, | |
| "learning_rate": 1.3666666666666668e-06, | |
| "loss": 0.068, | |
| "num_input_tokens_seen": 2211392, | |
| "step": 164 | |
| }, | |
| { | |
| "epoch": 2.122186495176849, | |
| "grad_norm": 8.30199146270752, | |
| "learning_rate": 1.3750000000000002e-06, | |
| "loss": 0.0686, | |
| "num_input_tokens_seen": 2224480, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 2.135048231511254, | |
| "grad_norm": 6.069125175476074, | |
| "learning_rate": 1.3833333333333336e-06, | |
| "loss": 0.0545, | |
| "num_input_tokens_seen": 2237920, | |
| "step": 166 | |
| }, | |
| { | |
| "epoch": 2.147909967845659, | |
| "grad_norm": 4.639097213745117, | |
| "learning_rate": 1.3916666666666668e-06, | |
| "loss": 0.0347, | |
| "num_input_tokens_seen": 2251008, | |
| "step": 167 | |
| }, | |
| { | |
| "epoch": 2.1607717041800645, | |
| "grad_norm": 9.093743324279785, | |
| "learning_rate": 1.4000000000000001e-06, | |
| "loss": 0.0993, | |
| "num_input_tokens_seen": 2264448, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 2.1736334405144695, | |
| "grad_norm": 8.8851900100708, | |
| "learning_rate": 1.4083333333333335e-06, | |
| "loss": 0.1059, | |
| "num_input_tokens_seen": 2277568, | |
| "step": 169 | |
| }, | |
| { | |
| "epoch": 2.1864951768488745, | |
| "grad_norm": 10.823246955871582, | |
| "learning_rate": 1.4166666666666667e-06, | |
| "loss": 0.089, | |
| "num_input_tokens_seen": 2291168, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 2.19935691318328, | |
| "grad_norm": 5.454392910003662, | |
| "learning_rate": 1.425e-06, | |
| "loss": 0.0379, | |
| "num_input_tokens_seen": 2304192, | |
| "step": 171 | |
| }, | |
| { | |
| "epoch": 2.212218649517685, | |
| "grad_norm": 6.2786030769348145, | |
| "learning_rate": 1.4333333333333335e-06, | |
| "loss": 0.0626, | |
| "num_input_tokens_seen": 2317920, | |
| "step": 172 | |
| }, | |
| { | |
| "epoch": 2.22508038585209, | |
| "grad_norm": 8.764283180236816, | |
| "learning_rate": 1.4416666666666667e-06, | |
| "loss": 0.0957, | |
| "num_input_tokens_seen": 2332416, | |
| "step": 173 | |
| }, | |
| { | |
| "epoch": 2.237942122186495, | |
| "grad_norm": 10.533244132995605, | |
| "learning_rate": 1.45e-06, | |
| "loss": 0.0636, | |
| "num_input_tokens_seen": 2346112, | |
| "step": 174 | |
| }, | |
| { | |
| "epoch": 2.2508038585209005, | |
| "grad_norm": 7.398101329803467, | |
| "learning_rate": 1.4583333333333335e-06, | |
| "loss": 0.074, | |
| "num_input_tokens_seen": 2359488, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 2.2636655948553055, | |
| "grad_norm": 6.4459686279296875, | |
| "learning_rate": 1.4666666666666669e-06, | |
| "loss": 0.0685, | |
| "num_input_tokens_seen": 2372928, | |
| "step": 176 | |
| }, | |
| { | |
| "epoch": 2.2765273311897105, | |
| "grad_norm": 5.918321132659912, | |
| "learning_rate": 1.475e-06, | |
| "loss": 0.0574, | |
| "num_input_tokens_seen": 2386016, | |
| "step": 177 | |
| }, | |
| { | |
| "epoch": 2.289389067524116, | |
| "grad_norm": 7.045689582824707, | |
| "learning_rate": 1.4833333333333337e-06, | |
| "loss": 0.0619, | |
| "num_input_tokens_seen": 2399936, | |
| "step": 178 | |
| }, | |
| { | |
| "epoch": 2.302250803858521, | |
| "grad_norm": 9.59676742553711, | |
| "learning_rate": 1.4916666666666669e-06, | |
| "loss": 0.0683, | |
| "num_input_tokens_seen": 2412480, | |
| "step": 179 | |
| }, | |
| { | |
| "epoch": 2.315112540192926, | |
| "grad_norm": 7.824158668518066, | |
| "learning_rate": 1.5e-06, | |
| "loss": 0.07, | |
| "num_input_tokens_seen": 2425888, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 2.327974276527331, | |
| "grad_norm": 10.920543670654297, | |
| "learning_rate": 1.5083333333333336e-06, | |
| "loss": 0.1154, | |
| "num_input_tokens_seen": 2439168, | |
| "step": 181 | |
| }, | |
| { | |
| "epoch": 2.3408360128617365, | |
| "grad_norm": 7.014737606048584, | |
| "learning_rate": 1.5166666666666668e-06, | |
| "loss": 0.0923, | |
| "num_input_tokens_seen": 2452928, | |
| "step": 182 | |
| }, | |
| { | |
| "epoch": 2.3536977491961415, | |
| "grad_norm": 7.072991371154785, | |
| "learning_rate": 1.525e-06, | |
| "loss": 0.0777, | |
| "num_input_tokens_seen": 2465760, | |
| "step": 183 | |
| }, | |
| { | |
| "epoch": 2.3665594855305465, | |
| "grad_norm": 13.426029205322266, | |
| "learning_rate": 1.5333333333333334e-06, | |
| "loss": 0.0754, | |
| "num_input_tokens_seen": 2479744, | |
| "step": 184 | |
| }, | |
| { | |
| "epoch": 2.379421221864952, | |
| "grad_norm": 9.223447799682617, | |
| "learning_rate": 1.5416666666666668e-06, | |
| "loss": 0.0704, | |
| "num_input_tokens_seen": 2493024, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 2.392282958199357, | |
| "grad_norm": 6.772041320800781, | |
| "learning_rate": 1.5500000000000002e-06, | |
| "loss": 0.0915, | |
| "num_input_tokens_seen": 2506720, | |
| "step": 186 | |
| }, | |
| { | |
| "epoch": 2.405144694533762, | |
| "grad_norm": 7.140571117401123, | |
| "learning_rate": 1.5583333333333334e-06, | |
| "loss": 0.087, | |
| "num_input_tokens_seen": 2519776, | |
| "step": 187 | |
| }, | |
| { | |
| "epoch": 2.418006430868167, | |
| "grad_norm": 9.75447940826416, | |
| "learning_rate": 1.566666666666667e-06, | |
| "loss": 0.0566, | |
| "num_input_tokens_seen": 2533536, | |
| "step": 188 | |
| }, | |
| { | |
| "epoch": 2.4308681672025725, | |
| "grad_norm": 12.131728172302246, | |
| "learning_rate": 1.5750000000000002e-06, | |
| "loss": 0.1037, | |
| "num_input_tokens_seen": 2547520, | |
| "step": 189 | |
| }, | |
| { | |
| "epoch": 2.4437299035369775, | |
| "grad_norm": 10.324275970458984, | |
| "learning_rate": 1.5833333333333333e-06, | |
| "loss": 0.1143, | |
| "num_input_tokens_seen": 2561280, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 2.4565916398713825, | |
| "grad_norm": 15.137426376342773, | |
| "learning_rate": 1.591666666666667e-06, | |
| "loss": 0.0829, | |
| "num_input_tokens_seen": 2575136, | |
| "step": 191 | |
| }, | |
| { | |
| "epoch": 2.469453376205788, | |
| "grad_norm": 4.877906322479248, | |
| "learning_rate": 1.6000000000000001e-06, | |
| "loss": 0.0422, | |
| "num_input_tokens_seen": 2588736, | |
| "step": 192 | |
| }, | |
| { | |
| "epoch": 2.482315112540193, | |
| "grad_norm": 6.23721170425415, | |
| "learning_rate": 1.6083333333333333e-06, | |
| "loss": 0.0727, | |
| "num_input_tokens_seen": 2602400, | |
| "step": 193 | |
| }, | |
| { | |
| "epoch": 2.495176848874598, | |
| "grad_norm": 10.653412818908691, | |
| "learning_rate": 1.6166666666666667e-06, | |
| "loss": 0.0836, | |
| "num_input_tokens_seen": 2615648, | |
| "step": 194 | |
| }, | |
| { | |
| "epoch": 2.508038585209003, | |
| "grad_norm": 8.391611099243164, | |
| "learning_rate": 1.6250000000000001e-06, | |
| "loss": 0.0803, | |
| "num_input_tokens_seen": 2629024, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 2.5209003215434085, | |
| "grad_norm": 6.826237201690674, | |
| "learning_rate": 1.6333333333333335e-06, | |
| "loss": 0.0654, | |
| "num_input_tokens_seen": 2642784, | |
| "step": 196 | |
| }, | |
| { | |
| "epoch": 2.5337620578778135, | |
| "grad_norm": 7.795334339141846, | |
| "learning_rate": 1.6416666666666667e-06, | |
| "loss": 0.0587, | |
| "num_input_tokens_seen": 2656064, | |
| "step": 197 | |
| }, | |
| { | |
| "epoch": 2.5466237942122185, | |
| "grad_norm": 9.136542320251465, | |
| "learning_rate": 1.6500000000000003e-06, | |
| "loss": 0.0848, | |
| "num_input_tokens_seen": 2669472, | |
| "step": 198 | |
| }, | |
| { | |
| "epoch": 2.559485530546624, | |
| "grad_norm": 4.476882457733154, | |
| "learning_rate": 1.6583333333333335e-06, | |
| "loss": 0.0525, | |
| "num_input_tokens_seen": 2682944, | |
| "step": 199 | |
| }, | |
| { | |
| "epoch": 2.572347266881029, | |
| "grad_norm": 8.298385620117188, | |
| "learning_rate": 1.6666666666666667e-06, | |
| "loss": 0.0677, | |
| "num_input_tokens_seen": 2695968, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 2.585209003215434, | |
| "grad_norm": 9.084216117858887, | |
| "learning_rate": 1.6750000000000003e-06, | |
| "loss": 0.062, | |
| "num_input_tokens_seen": 2709504, | |
| "step": 201 | |
| }, | |
| { | |
| "epoch": 2.598070739549839, | |
| "grad_norm": 10.124899864196777, | |
| "learning_rate": 1.6833333333333335e-06, | |
| "loss": 0.0674, | |
| "num_input_tokens_seen": 2723264, | |
| "step": 202 | |
| }, | |
| { | |
| "epoch": 2.6109324758842445, | |
| "grad_norm": 5.721729755401611, | |
| "learning_rate": 1.6916666666666666e-06, | |
| "loss": 0.0533, | |
| "num_input_tokens_seen": 2736768, | |
| "step": 203 | |
| }, | |
| { | |
| "epoch": 2.6237942122186495, | |
| "grad_norm": 6.966607570648193, | |
| "learning_rate": 1.7000000000000002e-06, | |
| "loss": 0.0757, | |
| "num_input_tokens_seen": 2750816, | |
| "step": 204 | |
| }, | |
| { | |
| "epoch": 2.6366559485530545, | |
| "grad_norm": 12.730990409851074, | |
| "learning_rate": 1.7083333333333334e-06, | |
| "loss": 0.0777, | |
| "num_input_tokens_seen": 2764576, | |
| "step": 205 | |
| }, | |
| { | |
| "epoch": 2.64951768488746, | |
| "grad_norm": 13.19457721710205, | |
| "learning_rate": 1.7166666666666668e-06, | |
| "loss": 0.0921, | |
| "num_input_tokens_seen": 2778080, | |
| "step": 206 | |
| }, | |
| { | |
| "epoch": 2.662379421221865, | |
| "grad_norm": 6.583987712860107, | |
| "learning_rate": 1.725e-06, | |
| "loss": 0.0378, | |
| "num_input_tokens_seen": 2790976, | |
| "step": 207 | |
| }, | |
| { | |
| "epoch": 2.67524115755627, | |
| "grad_norm": 6.989199161529541, | |
| "learning_rate": 1.7333333333333336e-06, | |
| "loss": 0.0671, | |
| "num_input_tokens_seen": 2805152, | |
| "step": 208 | |
| }, | |
| { | |
| "epoch": 2.688102893890675, | |
| "grad_norm": 8.903035163879395, | |
| "learning_rate": 1.7416666666666668e-06, | |
| "loss": 0.0664, | |
| "num_input_tokens_seen": 2818688, | |
| "step": 209 | |
| }, | |
| { | |
| "epoch": 2.7009646302250805, | |
| "grad_norm": 10.817940711975098, | |
| "learning_rate": 1.75e-06, | |
| "loss": 0.072, | |
| "num_input_tokens_seen": 2831872, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 2.7138263665594855, | |
| "grad_norm": 9.068681716918945, | |
| "learning_rate": 1.7583333333333336e-06, | |
| "loss": 0.0883, | |
| "num_input_tokens_seen": 2845984, | |
| "step": 211 | |
| }, | |
| { | |
| "epoch": 2.7266881028938905, | |
| "grad_norm": 4.464389801025391, | |
| "learning_rate": 1.7666666666666668e-06, | |
| "loss": 0.0414, | |
| "num_input_tokens_seen": 2859232, | |
| "step": 212 | |
| }, | |
| { | |
| "epoch": 2.739549839228296, | |
| "grad_norm": 4.999591827392578, | |
| "learning_rate": 1.7750000000000002e-06, | |
| "loss": 0.031, | |
| "num_input_tokens_seen": 2872192, | |
| "step": 213 | |
| }, | |
| { | |
| "epoch": 2.752411575562701, | |
| "grad_norm": 6.336106300354004, | |
| "learning_rate": 1.7833333333333336e-06, | |
| "loss": 0.0634, | |
| "num_input_tokens_seen": 2885312, | |
| "step": 214 | |
| }, | |
| { | |
| "epoch": 2.765273311897106, | |
| "grad_norm": 7.798391819000244, | |
| "learning_rate": 1.7916666666666667e-06, | |
| "loss": 0.0837, | |
| "num_input_tokens_seen": 2899072, | |
| "step": 215 | |
| }, | |
| { | |
| "epoch": 2.778135048231511, | |
| "grad_norm": 8.36534595489502, | |
| "learning_rate": 1.8000000000000001e-06, | |
| "loss": 0.0855, | |
| "num_input_tokens_seen": 2912448, | |
| "step": 216 | |
| }, | |
| { | |
| "epoch": 2.7909967845659165, | |
| "grad_norm": 9.043126106262207, | |
| "learning_rate": 1.8083333333333335e-06, | |
| "loss": 0.0945, | |
| "num_input_tokens_seen": 2925120, | |
| "step": 217 | |
| }, | |
| { | |
| "epoch": 2.8038585209003215, | |
| "grad_norm": 5.886596202850342, | |
| "learning_rate": 1.816666666666667e-06, | |
| "loss": 0.078, | |
| "num_input_tokens_seen": 2938336, | |
| "step": 218 | |
| }, | |
| { | |
| "epoch": 2.816720257234727, | |
| "grad_norm": 6.200281620025635, | |
| "learning_rate": 1.825e-06, | |
| "loss": 0.0573, | |
| "num_input_tokens_seen": 2951264, | |
| "step": 219 | |
| }, | |
| { | |
| "epoch": 2.829581993569132, | |
| "grad_norm": 10.755176544189453, | |
| "learning_rate": 1.8333333333333333e-06, | |
| "loss": 0.0806, | |
| "num_input_tokens_seen": 2965120, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 2.842443729903537, | |
| "grad_norm": 7.736689567565918, | |
| "learning_rate": 1.8416666666666669e-06, | |
| "loss": 0.0961, | |
| "num_input_tokens_seen": 2978368, | |
| "step": 221 | |
| }, | |
| { | |
| "epoch": 2.855305466237942, | |
| "grad_norm": 8.25919246673584, | |
| "learning_rate": 1.85e-06, | |
| "loss": 0.0732, | |
| "num_input_tokens_seen": 2992000, | |
| "step": 222 | |
| }, | |
| { | |
| "epoch": 2.868167202572347, | |
| "grad_norm": 9.59769344329834, | |
| "learning_rate": 1.8583333333333335e-06, | |
| "loss": 0.0957, | |
| "num_input_tokens_seen": 3006048, | |
| "step": 223 | |
| }, | |
| { | |
| "epoch": 2.8810289389067525, | |
| "grad_norm": 7.2752485275268555, | |
| "learning_rate": 1.8666666666666669e-06, | |
| "loss": 0.0774, | |
| "num_input_tokens_seen": 3019744, | |
| "step": 224 | |
| }, | |
| { | |
| "epoch": 2.8938906752411575, | |
| "grad_norm": 5.989022731781006, | |
| "learning_rate": 1.8750000000000003e-06, | |
| "loss": 0.0691, | |
| "num_input_tokens_seen": 3033568, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 2.906752411575563, | |
| "grad_norm": 6.692146301269531, | |
| "learning_rate": 1.8833333333333334e-06, | |
| "loss": 0.0529, | |
| "num_input_tokens_seen": 3047712, | |
| "step": 226 | |
| }, | |
| { | |
| "epoch": 2.919614147909968, | |
| "grad_norm": 7.606103897094727, | |
| "learning_rate": 1.8916666666666668e-06, | |
| "loss": 0.0811, | |
| "num_input_tokens_seen": 3060800, | |
| "step": 227 | |
| }, | |
| { | |
| "epoch": 2.932475884244373, | |
| "grad_norm": 8.168295860290527, | |
| "learning_rate": 1.9000000000000002e-06, | |
| "loss": 0.1211, | |
| "num_input_tokens_seen": 3074720, | |
| "step": 228 | |
| }, | |
| { | |
| "epoch": 2.945337620578778, | |
| "grad_norm": 5.379516124725342, | |
| "learning_rate": 1.9083333333333334e-06, | |
| "loss": 0.0489, | |
| "num_input_tokens_seen": 3088448, | |
| "step": 229 | |
| }, | |
| { | |
| "epoch": 2.958199356913183, | |
| "grad_norm": 11.40697956085205, | |
| "learning_rate": 1.916666666666667e-06, | |
| "loss": 0.0947, | |
| "num_input_tokens_seen": 3103008, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 2.9710610932475885, | |
| "grad_norm": 6.254599571228027, | |
| "learning_rate": 1.925e-06, | |
| "loss": 0.0561, | |
| "num_input_tokens_seen": 3116320, | |
| "step": 231 | |
| }, | |
| { | |
| "epoch": 2.9839228295819935, | |
| "grad_norm": 6.7563300132751465, | |
| "learning_rate": 1.9333333333333336e-06, | |
| "loss": 0.0629, | |
| "num_input_tokens_seen": 3130592, | |
| "step": 232 | |
| }, | |
| { | |
| "epoch": 2.996784565916399, | |
| "grad_norm": 3.745004177093506, | |
| "learning_rate": 1.9416666666666666e-06, | |
| "loss": 0.0579, | |
| "num_input_tokens_seen": 3144000, | |
| "step": 233 | |
| }, | |
| { | |
| "epoch": 3.009646302250804, | |
| "grad_norm": 3.5915324687957764, | |
| "learning_rate": 1.9500000000000004e-06, | |
| "loss": 0.0285, | |
| "num_input_tokens_seen": 3157472, | |
| "step": 234 | |
| }, | |
| { | |
| "epoch": 3.022508038585209, | |
| "grad_norm": 2.564159631729126, | |
| "learning_rate": 1.9583333333333334e-06, | |
| "loss": 0.0256, | |
| "num_input_tokens_seen": 3170656, | |
| "step": 235 | |
| }, | |
| { | |
| "epoch": 3.035369774919614, | |
| "grad_norm": 5.488891124725342, | |
| "learning_rate": 1.9666666666666668e-06, | |
| "loss": 0.0247, | |
| "num_input_tokens_seen": 3184320, | |
| "step": 236 | |
| }, | |
| { | |
| "epoch": 3.0482315112540195, | |
| "grad_norm": 4.964622497558594, | |
| "learning_rate": 1.975e-06, | |
| "loss": 0.0325, | |
| "num_input_tokens_seen": 3197216, | |
| "step": 237 | |
| }, | |
| { | |
| "epoch": 3.0610932475884245, | |
| "grad_norm": 5.399533748626709, | |
| "learning_rate": 1.9833333333333335e-06, | |
| "loss": 0.0172, | |
| "num_input_tokens_seen": 3211008, | |
| "step": 238 | |
| }, | |
| { | |
| "epoch": 3.0739549839228295, | |
| "grad_norm": 5.841439247131348, | |
| "learning_rate": 1.991666666666667e-06, | |
| "loss": 0.05, | |
| "num_input_tokens_seen": 3225152, | |
| "step": 239 | |
| }, | |
| { | |
| "epoch": 3.0868167202572345, | |
| "grad_norm": 3.352426052093506, | |
| "learning_rate": 2.0000000000000003e-06, | |
| "loss": 0.0134, | |
| "num_input_tokens_seen": 3238752, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 3.09967845659164, | |
| "grad_norm": 8.727036476135254, | |
| "learning_rate": 2.0083333333333337e-06, | |
| "loss": 0.0434, | |
| "num_input_tokens_seen": 3252224, | |
| "step": 241 | |
| }, | |
| { | |
| "epoch": 3.112540192926045, | |
| "grad_norm": 6.6712727546691895, | |
| "learning_rate": 2.0166666666666667e-06, | |
| "loss": 0.0186, | |
| "num_input_tokens_seen": 3264832, | |
| "step": 242 | |
| }, | |
| { | |
| "epoch": 3.12540192926045, | |
| "grad_norm": 5.2496490478515625, | |
| "learning_rate": 2.025e-06, | |
| "loss": 0.0341, | |
| "num_input_tokens_seen": 3278048, | |
| "step": 243 | |
| }, | |
| { | |
| "epoch": 3.1382636655948555, | |
| "grad_norm": 6.601498126983643, | |
| "learning_rate": 2.0333333333333335e-06, | |
| "loss": 0.0386, | |
| "num_input_tokens_seen": 3291680, | |
| "step": 244 | |
| }, | |
| { | |
| "epoch": 3.1511254019292605, | |
| "grad_norm": 5.705418109893799, | |
| "learning_rate": 2.041666666666667e-06, | |
| "loss": 0.0389, | |
| "num_input_tokens_seen": 3305440, | |
| "step": 245 | |
| }, | |
| { | |
| "epoch": 3.1639871382636655, | |
| "grad_norm": 4.315848350524902, | |
| "learning_rate": 2.05e-06, | |
| "loss": 0.0227, | |
| "num_input_tokens_seen": 3319360, | |
| "step": 246 | |
| }, | |
| { | |
| "epoch": 3.176848874598071, | |
| "grad_norm": 3.5968470573425293, | |
| "learning_rate": 2.0583333333333337e-06, | |
| "loss": 0.0317, | |
| "num_input_tokens_seen": 3333088, | |
| "step": 247 | |
| }, | |
| { | |
| "epoch": 3.189710610932476, | |
| "grad_norm": 3.23504638671875, | |
| "learning_rate": 2.0666666666666666e-06, | |
| "loss": 0.0335, | |
| "num_input_tokens_seen": 3345856, | |
| "step": 248 | |
| }, | |
| { | |
| "epoch": 3.202572347266881, | |
| "grad_norm": 3.6574056148529053, | |
| "learning_rate": 2.075e-06, | |
| "loss": 0.0257, | |
| "num_input_tokens_seen": 3358880, | |
| "step": 249 | |
| }, | |
| { | |
| "epoch": 3.215434083601286, | |
| "grad_norm": 2.903745651245117, | |
| "learning_rate": 2.0833333333333334e-06, | |
| "loss": 0.0244, | |
| "num_input_tokens_seen": 3373312, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 3.2282958199356915, | |
| "grad_norm": 5.933866024017334, | |
| "learning_rate": 2.091666666666667e-06, | |
| "loss": 0.0285, | |
| "num_input_tokens_seen": 3386336, | |
| "step": 251 | |
| }, | |
| { | |
| "epoch": 3.2411575562700965, | |
| "grad_norm": 2.2281062602996826, | |
| "learning_rate": 2.1000000000000002e-06, | |
| "loss": 0.0093, | |
| "num_input_tokens_seen": 3399904, | |
| "step": 252 | |
| }, | |
| { | |
| "epoch": 3.2540192926045015, | |
| "grad_norm": 5.6479573249816895, | |
| "learning_rate": 2.1083333333333336e-06, | |
| "loss": 0.0415, | |
| "num_input_tokens_seen": 3412896, | |
| "step": 253 | |
| }, | |
| { | |
| "epoch": 3.266881028938907, | |
| "grad_norm": 3.5148093700408936, | |
| "learning_rate": 2.116666666666667e-06, | |
| "loss": 0.0239, | |
| "num_input_tokens_seen": 3426336, | |
| "step": 254 | |
| }, | |
| { | |
| "epoch": 3.279742765273312, | |
| "grad_norm": 8.129992485046387, | |
| "learning_rate": 2.125e-06, | |
| "loss": 0.0412, | |
| "num_input_tokens_seen": 3439680, | |
| "step": 255 | |
| }, | |
| { | |
| "epoch": 3.292604501607717, | |
| "grad_norm": 10.018027305603027, | |
| "learning_rate": 2.133333333333334e-06, | |
| "loss": 0.0503, | |
| "num_input_tokens_seen": 3453760, | |
| "step": 256 | |
| }, | |
| { | |
| "epoch": 3.305466237942122, | |
| "grad_norm": 1.7141941785812378, | |
| "learning_rate": 2.1416666666666668e-06, | |
| "loss": 0.0046, | |
| "num_input_tokens_seen": 3466496, | |
| "step": 257 | |
| }, | |
| { | |
| "epoch": 3.3183279742765275, | |
| "grad_norm": 4.564700126647949, | |
| "learning_rate": 2.15e-06, | |
| "loss": 0.041, | |
| "num_input_tokens_seen": 3480352, | |
| "step": 258 | |
| }, | |
| { | |
| "epoch": 3.3311897106109325, | |
| "grad_norm": 5.49994421005249, | |
| "learning_rate": 2.1583333333333336e-06, | |
| "loss": 0.0257, | |
| "num_input_tokens_seen": 3494112, | |
| "step": 259 | |
| }, | |
| { | |
| "epoch": 3.3440514469453375, | |
| "grad_norm": 4.59380578994751, | |
| "learning_rate": 2.166666666666667e-06, | |
| "loss": 0.0168, | |
| "num_input_tokens_seen": 3507520, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 3.356913183279743, | |
| "grad_norm": 5.633969306945801, | |
| "learning_rate": 2.1750000000000004e-06, | |
| "loss": 0.0439, | |
| "num_input_tokens_seen": 3520352, | |
| "step": 261 | |
| }, | |
| { | |
| "epoch": 3.369774919614148, | |
| "grad_norm": 7.95892333984375, | |
| "learning_rate": 2.1833333333333333e-06, | |
| "loss": 0.0204, | |
| "num_input_tokens_seen": 3533984, | |
| "step": 262 | |
| }, | |
| { | |
| "epoch": 3.382636655948553, | |
| "grad_norm": 4.728748798370361, | |
| "learning_rate": 2.191666666666667e-06, | |
| "loss": 0.0284, | |
| "num_input_tokens_seen": 3547072, | |
| "step": 263 | |
| }, | |
| { | |
| "epoch": 3.395498392282958, | |
| "grad_norm": 6.725067615509033, | |
| "learning_rate": 2.2e-06, | |
| "loss": 0.0684, | |
| "num_input_tokens_seen": 3559872, | |
| "step": 264 | |
| }, | |
| { | |
| "epoch": 3.4083601286173635, | |
| "grad_norm": 10.331790924072266, | |
| "learning_rate": 2.2083333333333335e-06, | |
| "loss": 0.0479, | |
| "num_input_tokens_seen": 3572832, | |
| "step": 265 | |
| }, | |
| { | |
| "epoch": 3.4212218649517685, | |
| "grad_norm": 5.8449296951293945, | |
| "learning_rate": 2.216666666666667e-06, | |
| "loss": 0.0434, | |
| "num_input_tokens_seen": 3585792, | |
| "step": 266 | |
| }, | |
| { | |
| "epoch": 3.4340836012861735, | |
| "grad_norm": 4.554612636566162, | |
| "learning_rate": 2.2250000000000003e-06, | |
| "loss": 0.0213, | |
| "num_input_tokens_seen": 3599392, | |
| "step": 267 | |
| }, | |
| { | |
| "epoch": 3.446945337620579, | |
| "grad_norm": 7.6923828125, | |
| "learning_rate": 2.2333333333333333e-06, | |
| "loss": 0.0415, | |
| "num_input_tokens_seen": 3613088, | |
| "step": 268 | |
| }, | |
| { | |
| "epoch": 3.459807073954984, | |
| "grad_norm": 5.714204788208008, | |
| "learning_rate": 2.2416666666666667e-06, | |
| "loss": 0.0404, | |
| "num_input_tokens_seen": 3626304, | |
| "step": 269 | |
| }, | |
| { | |
| "epoch": 3.472668810289389, | |
| "grad_norm": 5.449560165405273, | |
| "learning_rate": 2.25e-06, | |
| "loss": 0.0566, | |
| "num_input_tokens_seen": 3639968, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 3.485530546623794, | |
| "grad_norm": 4.743899345397949, | |
| "learning_rate": 2.2583333333333335e-06, | |
| "loss": 0.0509, | |
| "num_input_tokens_seen": 3653472, | |
| "step": 271 | |
| }, | |
| { | |
| "epoch": 3.4983922829581995, | |
| "grad_norm": 4.767292022705078, | |
| "learning_rate": 2.266666666666667e-06, | |
| "loss": 0.0385, | |
| "num_input_tokens_seen": 3667104, | |
| "step": 272 | |
| }, | |
| { | |
| "epoch": 3.5112540192926045, | |
| "grad_norm": 2.342560291290283, | |
| "learning_rate": 2.2750000000000002e-06, | |
| "loss": 0.0225, | |
| "num_input_tokens_seen": 3680480, | |
| "step": 273 | |
| }, | |
| { | |
| "epoch": 3.5241157556270095, | |
| "grad_norm": 3.9172496795654297, | |
| "learning_rate": 2.2833333333333336e-06, | |
| "loss": 0.0255, | |
| "num_input_tokens_seen": 3693568, | |
| "step": 274 | |
| }, | |
| { | |
| "epoch": 3.536977491961415, | |
| "grad_norm": 6.793405532836914, | |
| "learning_rate": 2.2916666666666666e-06, | |
| "loss": 0.0531, | |
| "num_input_tokens_seen": 3706496, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 3.54983922829582, | |
| "grad_norm": 2.142134189605713, | |
| "learning_rate": 2.3000000000000004e-06, | |
| "loss": 0.0095, | |
| "num_input_tokens_seen": 3720352, | |
| "step": 276 | |
| }, | |
| { | |
| "epoch": 3.562700964630225, | |
| "grad_norm": 6.340362071990967, | |
| "learning_rate": 2.3083333333333334e-06, | |
| "loss": 0.0229, | |
| "num_input_tokens_seen": 3734176, | |
| "step": 277 | |
| }, | |
| { | |
| "epoch": 3.57556270096463, | |
| "grad_norm": 5.204097747802734, | |
| "learning_rate": 2.316666666666667e-06, | |
| "loss": 0.038, | |
| "num_input_tokens_seen": 3748544, | |
| "step": 278 | |
| }, | |
| { | |
| "epoch": 3.5884244372990355, | |
| "grad_norm": 6.532016754150391, | |
| "learning_rate": 2.325e-06, | |
| "loss": 0.0316, | |
| "num_input_tokens_seen": 3761984, | |
| "step": 279 | |
| }, | |
| { | |
| "epoch": 3.6012861736334405, | |
| "grad_norm": 10.49596881866455, | |
| "learning_rate": 2.3333333333333336e-06, | |
| "loss": 0.0861, | |
| "num_input_tokens_seen": 3774304, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 3.6141479099678455, | |
| "grad_norm": 5.68178129196167, | |
| "learning_rate": 2.341666666666667e-06, | |
| "loss": 0.0566, | |
| "num_input_tokens_seen": 3788416, | |
| "step": 281 | |
| }, | |
| { | |
| "epoch": 3.627009646302251, | |
| "grad_norm": 6.790673732757568, | |
| "learning_rate": 2.35e-06, | |
| "loss": 0.0804, | |
| "num_input_tokens_seen": 3802112, | |
| "step": 282 | |
| }, | |
| { | |
| "epoch": 3.639871382636656, | |
| "grad_norm": 7.294980049133301, | |
| "learning_rate": 2.3583333333333338e-06, | |
| "loss": 0.046, | |
| "num_input_tokens_seen": 3815968, | |
| "step": 283 | |
| }, | |
| { | |
| "epoch": 3.652733118971061, | |
| "grad_norm": 10.37634563446045, | |
| "learning_rate": 2.3666666666666667e-06, | |
| "loss": 0.0693, | |
| "num_input_tokens_seen": 3829248, | |
| "step": 284 | |
| }, | |
| { | |
| "epoch": 3.665594855305466, | |
| "grad_norm": 4.692931652069092, | |
| "learning_rate": 2.375e-06, | |
| "loss": 0.0342, | |
| "num_input_tokens_seen": 3843072, | |
| "step": 285 | |
| }, | |
| { | |
| "epoch": 3.6784565916398715, | |
| "grad_norm": 3.5910987854003906, | |
| "learning_rate": 2.3833333333333335e-06, | |
| "loss": 0.0479, | |
| "num_input_tokens_seen": 3856288, | |
| "step": 286 | |
| }, | |
| { | |
| "epoch": 3.6913183279742765, | |
| "grad_norm": 5.858832359313965, | |
| "learning_rate": 2.391666666666667e-06, | |
| "loss": 0.0388, | |
| "num_input_tokens_seen": 3870240, | |
| "step": 287 | |
| }, | |
| { | |
| "epoch": 3.7041800643086815, | |
| "grad_norm": 4.469853401184082, | |
| "learning_rate": 2.4000000000000003e-06, | |
| "loss": 0.0274, | |
| "num_input_tokens_seen": 3884096, | |
| "step": 288 | |
| }, | |
| { | |
| "epoch": 3.717041800643087, | |
| "grad_norm": 4.967989921569824, | |
| "learning_rate": 2.4083333333333337e-06, | |
| "loss": 0.0259, | |
| "num_input_tokens_seen": 3898368, | |
| "step": 289 | |
| }, | |
| { | |
| "epoch": 3.729903536977492, | |
| "grad_norm": 6.155540943145752, | |
| "learning_rate": 2.4166666666666667e-06, | |
| "loss": 0.0367, | |
| "num_input_tokens_seen": 3911200, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 3.742765273311897, | |
| "grad_norm": 6.5608367919921875, | |
| "learning_rate": 2.425e-06, | |
| "loss": 0.0661, | |
| "num_input_tokens_seen": 3924320, | |
| "step": 291 | |
| }, | |
| { | |
| "epoch": 3.755627009646302, | |
| "grad_norm": 6.416184902191162, | |
| "learning_rate": 2.4333333333333335e-06, | |
| "loss": 0.0466, | |
| "num_input_tokens_seen": 3937632, | |
| "step": 292 | |
| }, | |
| { | |
| "epoch": 3.7684887459807075, | |
| "grad_norm": 5.672483444213867, | |
| "learning_rate": 2.441666666666667e-06, | |
| "loss": 0.0286, | |
| "num_input_tokens_seen": 3951040, | |
| "step": 293 | |
| }, | |
| { | |
| "epoch": 3.7813504823151125, | |
| "grad_norm": 9.215237617492676, | |
| "learning_rate": 2.4500000000000003e-06, | |
| "loss": 0.0586, | |
| "num_input_tokens_seen": 3963936, | |
| "step": 294 | |
| }, | |
| { | |
| "epoch": 3.7942122186495175, | |
| "grad_norm": 5.630943298339844, | |
| "learning_rate": 2.4583333333333332e-06, | |
| "loss": 0.0329, | |
| "num_input_tokens_seen": 3976832, | |
| "step": 295 | |
| }, | |
| { | |
| "epoch": 3.807073954983923, | |
| "grad_norm": 8.257805824279785, | |
| "learning_rate": 2.466666666666667e-06, | |
| "loss": 0.0582, | |
| "num_input_tokens_seen": 3990592, | |
| "step": 296 | |
| }, | |
| { | |
| "epoch": 3.819935691318328, | |
| "grad_norm": 3.351003408432007, | |
| "learning_rate": 2.475e-06, | |
| "loss": 0.0312, | |
| "num_input_tokens_seen": 4004288, | |
| "step": 297 | |
| }, | |
| { | |
| "epoch": 3.832797427652733, | |
| "grad_norm": 3.2983040809631348, | |
| "learning_rate": 2.4833333333333334e-06, | |
| "loss": 0.0329, | |
| "num_input_tokens_seen": 4017856, | |
| "step": 298 | |
| }, | |
| { | |
| "epoch": 3.845659163987138, | |
| "grad_norm": 4.082300662994385, | |
| "learning_rate": 2.491666666666667e-06, | |
| "loss": 0.0206, | |
| "num_input_tokens_seen": 4031168, | |
| "step": 299 | |
| }, | |
| { | |
| "epoch": 3.8585209003215435, | |
| "grad_norm": 3.222336530685425, | |
| "learning_rate": 2.5e-06, | |
| "loss": 0.0426, | |
| "num_input_tokens_seen": 4044416, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 3.8713826366559485, | |
| "grad_norm": 3.699768304824829, | |
| "learning_rate": 2.5083333333333336e-06, | |
| "loss": 0.0179, | |
| "num_input_tokens_seen": 4057824, | |
| "step": 301 | |
| }, | |
| { | |
| "epoch": 3.884244372990354, | |
| "grad_norm": 2.819528341293335, | |
| "learning_rate": 2.5166666666666666e-06, | |
| "loss": 0.0289, | |
| "num_input_tokens_seen": 4071936, | |
| "step": 302 | |
| }, | |
| { | |
| "epoch": 3.897106109324759, | |
| "grad_norm": 4.0458478927612305, | |
| "learning_rate": 2.5250000000000004e-06, | |
| "loss": 0.0303, | |
| "num_input_tokens_seen": 4085536, | |
| "step": 303 | |
| }, | |
| { | |
| "epoch": 3.909967845659164, | |
| "grad_norm": 11.214617729187012, | |
| "learning_rate": 2.5333333333333338e-06, | |
| "loss": 0.046, | |
| "num_input_tokens_seen": 4099552, | |
| "step": 304 | |
| }, | |
| { | |
| "epoch": 3.922829581993569, | |
| "grad_norm": 6.758171081542969, | |
| "learning_rate": 2.5416666666666668e-06, | |
| "loss": 0.0523, | |
| "num_input_tokens_seen": 4112736, | |
| "step": 305 | |
| }, | |
| { | |
| "epoch": 3.935691318327974, | |
| "grad_norm": 5.622665882110596, | |
| "learning_rate": 2.55e-06, | |
| "loss": 0.0329, | |
| "num_input_tokens_seen": 4126080, | |
| "step": 306 | |
| }, | |
| { | |
| "epoch": 3.9485530546623795, | |
| "grad_norm": 1.4951086044311523, | |
| "learning_rate": 2.558333333333334e-06, | |
| "loss": 0.0072, | |
| "num_input_tokens_seen": 4138912, | |
| "step": 307 | |
| }, | |
| { | |
| "epoch": 3.9614147909967845, | |
| "grad_norm": 5.639418601989746, | |
| "learning_rate": 2.566666666666667e-06, | |
| "loss": 0.0415, | |
| "num_input_tokens_seen": 4152768, | |
| "step": 308 | |
| }, | |
| { | |
| "epoch": 3.97427652733119, | |
| "grad_norm": 7.496403694152832, | |
| "learning_rate": 2.5750000000000003e-06, | |
| "loss": 0.0233, | |
| "num_input_tokens_seen": 4166528, | |
| "step": 309 | |
| }, | |
| { | |
| "epoch": 3.987138263665595, | |
| "grad_norm": 8.74985408782959, | |
| "learning_rate": 2.5833333333333337e-06, | |
| "loss": 0.0423, | |
| "num_input_tokens_seen": 4180832, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "grad_norm": 6.229910850524902, | |
| "learning_rate": 2.5916666666666667e-06, | |
| "loss": 0.0295, | |
| "num_input_tokens_seen": 4194048, | |
| "step": 311 | |
| }, | |
| { | |
| "epoch": 4.012861736334405, | |
| "grad_norm": 3.404331922531128, | |
| "learning_rate": 2.6e-06, | |
| "loss": 0.0327, | |
| "num_input_tokens_seen": 4207040, | |
| "step": 312 | |
| }, | |
| { | |
| "epoch": 4.02572347266881, | |
| "grad_norm": 4.214801788330078, | |
| "learning_rate": 2.608333333333333e-06, | |
| "loss": 0.0301, | |
| "num_input_tokens_seen": 4220000, | |
| "step": 313 | |
| }, | |
| { | |
| "epoch": 4.038585209003215, | |
| "grad_norm": 6.241875171661377, | |
| "learning_rate": 2.616666666666667e-06, | |
| "loss": 0.0301, | |
| "num_input_tokens_seen": 4233344, | |
| "step": 314 | |
| }, | |
| { | |
| "epoch": 4.051446945337621, | |
| "grad_norm": 3.2021894454956055, | |
| "learning_rate": 2.6250000000000003e-06, | |
| "loss": 0.0281, | |
| "num_input_tokens_seen": 4246144, | |
| "step": 315 | |
| }, | |
| { | |
| "epoch": 4.064308681672026, | |
| "grad_norm": 3.5197951793670654, | |
| "learning_rate": 2.6333333333333332e-06, | |
| "loss": 0.0136, | |
| "num_input_tokens_seen": 4260992, | |
| "step": 316 | |
| }, | |
| { | |
| "epoch": 4.077170418006431, | |
| "grad_norm": 4.2946319580078125, | |
| "learning_rate": 2.6416666666666666e-06, | |
| "loss": 0.0219, | |
| "num_input_tokens_seen": 4274112, | |
| "step": 317 | |
| }, | |
| { | |
| "epoch": 4.090032154340836, | |
| "grad_norm": 1.3583834171295166, | |
| "learning_rate": 2.6500000000000005e-06, | |
| "loss": 0.0044, | |
| "num_input_tokens_seen": 4287904, | |
| "step": 318 | |
| }, | |
| { | |
| "epoch": 4.102893890675241, | |
| "grad_norm": 5.484881401062012, | |
| "learning_rate": 2.6583333333333334e-06, | |
| "loss": 0.0335, | |
| "num_input_tokens_seen": 4301568, | |
| "step": 319 | |
| }, | |
| { | |
| "epoch": 4.115755627009646, | |
| "grad_norm": 3.5873327255249023, | |
| "learning_rate": 2.666666666666667e-06, | |
| "loss": 0.0053, | |
| "num_input_tokens_seen": 4314848, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 4.128617363344051, | |
| "grad_norm": 2.954930067062378, | |
| "learning_rate": 2.6750000000000002e-06, | |
| "loss": 0.0196, | |
| "num_input_tokens_seen": 4327456, | |
| "step": 321 | |
| }, | |
| { | |
| "epoch": 4.141479099678457, | |
| "grad_norm": 2.628854274749756, | |
| "learning_rate": 2.683333333333333e-06, | |
| "loss": 0.0309, | |
| "num_input_tokens_seen": 4341024, | |
| "step": 322 | |
| }, | |
| { | |
| "epoch": 4.154340836012862, | |
| "grad_norm": 6.691638469696045, | |
| "learning_rate": 2.691666666666667e-06, | |
| "loss": 0.0382, | |
| "num_input_tokens_seen": 4353824, | |
| "step": 323 | |
| }, | |
| { | |
| "epoch": 4.167202572347267, | |
| "grad_norm": 6.866171360015869, | |
| "learning_rate": 2.7000000000000004e-06, | |
| "loss": 0.046, | |
| "num_input_tokens_seen": 4367616, | |
| "step": 324 | |
| }, | |
| { | |
| "epoch": 4.180064308681672, | |
| "grad_norm": 4.016347408294678, | |
| "learning_rate": 2.7083333333333334e-06, | |
| "loss": 0.0133, | |
| "num_input_tokens_seen": 4380448, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 4.192926045016077, | |
| "grad_norm": 4.948652744293213, | |
| "learning_rate": 2.7166666666666668e-06, | |
| "loss": 0.0265, | |
| "num_input_tokens_seen": 4393920, | |
| "step": 326 | |
| }, | |
| { | |
| "epoch": 4.205787781350482, | |
| "grad_norm": 2.7615582942962646, | |
| "learning_rate": 2.7250000000000006e-06, | |
| "loss": 0.0084, | |
| "num_input_tokens_seen": 4407264, | |
| "step": 327 | |
| }, | |
| { | |
| "epoch": 4.218649517684887, | |
| "grad_norm": 3.0052027702331543, | |
| "learning_rate": 2.7333333333333336e-06, | |
| "loss": 0.0382, | |
| "num_input_tokens_seen": 4420352, | |
| "step": 328 | |
| }, | |
| { | |
| "epoch": 4.231511254019293, | |
| "grad_norm": 3.0679566860198975, | |
| "learning_rate": 2.741666666666667e-06, | |
| "loss": 0.0101, | |
| "num_input_tokens_seen": 4434688, | |
| "step": 329 | |
| }, | |
| { | |
| "epoch": 4.244372990353698, | |
| "grad_norm": 4.612461566925049, | |
| "learning_rate": 2.7500000000000004e-06, | |
| "loss": 0.0174, | |
| "num_input_tokens_seen": 4448160, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 4.257234726688103, | |
| "grad_norm": 4.299385070800781, | |
| "learning_rate": 2.7583333333333333e-06, | |
| "loss": 0.023, | |
| "num_input_tokens_seen": 4461184, | |
| "step": 331 | |
| }, | |
| { | |
| "epoch": 4.270096463022508, | |
| "grad_norm": 1.5578008890151978, | |
| "learning_rate": 2.766666666666667e-06, | |
| "loss": 0.0162, | |
| "num_input_tokens_seen": 4475168, | |
| "step": 332 | |
| }, | |
| { | |
| "epoch": 4.282958199356913, | |
| "grad_norm": 3.8595075607299805, | |
| "learning_rate": 2.7750000000000005e-06, | |
| "loss": 0.0261, | |
| "num_input_tokens_seen": 4487872, | |
| "step": 333 | |
| }, | |
| { | |
| "epoch": 4.295819935691318, | |
| "grad_norm": 8.00913143157959, | |
| "learning_rate": 2.7833333333333335e-06, | |
| "loss": 0.0266, | |
| "num_input_tokens_seen": 4501216, | |
| "step": 334 | |
| }, | |
| { | |
| "epoch": 4.308681672025724, | |
| "grad_norm": 2.2975409030914307, | |
| "learning_rate": 2.791666666666667e-06, | |
| "loss": 0.0194, | |
| "num_input_tokens_seen": 4514336, | |
| "step": 335 | |
| }, | |
| { | |
| "epoch": 4.321543408360129, | |
| "grad_norm": 1.9800870418548584, | |
| "learning_rate": 2.8000000000000003e-06, | |
| "loss": 0.0058, | |
| "num_input_tokens_seen": 4528288, | |
| "step": 336 | |
| }, | |
| { | |
| "epoch": 4.334405144694534, | |
| "grad_norm": 6.778807163238525, | |
| "learning_rate": 2.8083333333333333e-06, | |
| "loss": 0.0065, | |
| "num_input_tokens_seen": 4541728, | |
| "step": 337 | |
| }, | |
| { | |
| "epoch": 4.347266881028939, | |
| "grad_norm": 7.885656833648682, | |
| "learning_rate": 2.816666666666667e-06, | |
| "loss": 0.0202, | |
| "num_input_tokens_seen": 4555552, | |
| "step": 338 | |
| }, | |
| { | |
| "epoch": 4.360128617363344, | |
| "grad_norm": 9.400197982788086, | |
| "learning_rate": 2.825e-06, | |
| "loss": 0.0135, | |
| "num_input_tokens_seen": 4568768, | |
| "step": 339 | |
| }, | |
| { | |
| "epoch": 4.372990353697749, | |
| "grad_norm": 5.712286472320557, | |
| "learning_rate": 2.8333333333333335e-06, | |
| "loss": 0.01, | |
| "num_input_tokens_seen": 4582400, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 4.385852090032154, | |
| "grad_norm": 4.751468181610107, | |
| "learning_rate": 2.841666666666667e-06, | |
| "loss": 0.0051, | |
| "num_input_tokens_seen": 4595360, | |
| "step": 341 | |
| }, | |
| { | |
| "epoch": 4.39871382636656, | |
| "grad_norm": 2.9044384956359863, | |
| "learning_rate": 2.85e-06, | |
| "loss": 0.0293, | |
| "num_input_tokens_seen": 4609632, | |
| "step": 342 | |
| }, | |
| { | |
| "epoch": 4.411575562700965, | |
| "grad_norm": 5.8322224617004395, | |
| "learning_rate": 2.8583333333333336e-06, | |
| "loss": 0.046, | |
| "num_input_tokens_seen": 4623232, | |
| "step": 343 | |
| }, | |
| { | |
| "epoch": 4.42443729903537, | |
| "grad_norm": 0.7529265284538269, | |
| "learning_rate": 2.866666666666667e-06, | |
| "loss": 0.0024, | |
| "num_input_tokens_seen": 4636864, | |
| "step": 344 | |
| }, | |
| { | |
| "epoch": 4.437299035369775, | |
| "grad_norm": 4.490261554718018, | |
| "learning_rate": 2.875e-06, | |
| "loss": 0.0211, | |
| "num_input_tokens_seen": 4649600, | |
| "step": 345 | |
| }, | |
| { | |
| "epoch": 4.45016077170418, | |
| "grad_norm": 9.859882354736328, | |
| "learning_rate": 2.8833333333333334e-06, | |
| "loss": 0.0229, | |
| "num_input_tokens_seen": 4663072, | |
| "step": 346 | |
| }, | |
| { | |
| "epoch": 4.463022508038585, | |
| "grad_norm": 3.8769121170043945, | |
| "learning_rate": 2.8916666666666672e-06, | |
| "loss": 0.0103, | |
| "num_input_tokens_seen": 4676960, | |
| "step": 347 | |
| }, | |
| { | |
| "epoch": 4.47588424437299, | |
| "grad_norm": 6.608347415924072, | |
| "learning_rate": 2.9e-06, | |
| "loss": 0.0262, | |
| "num_input_tokens_seen": 4690080, | |
| "step": 348 | |
| }, | |
| { | |
| "epoch": 4.488745980707396, | |
| "grad_norm": 3.058494806289673, | |
| "learning_rate": 2.9083333333333336e-06, | |
| "loss": 0.0295, | |
| "num_input_tokens_seen": 4704064, | |
| "step": 349 | |
| }, | |
| { | |
| "epoch": 4.501607717041801, | |
| "grad_norm": 4.893054485321045, | |
| "learning_rate": 2.916666666666667e-06, | |
| "loss": 0.0149, | |
| "num_input_tokens_seen": 4717536, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 4.514469453376206, | |
| "grad_norm": 5.85437536239624, | |
| "learning_rate": 2.925e-06, | |
| "loss": 0.0337, | |
| "num_input_tokens_seen": 4731040, | |
| "step": 351 | |
| }, | |
| { | |
| "epoch": 4.527331189710611, | |
| "grad_norm": 5.814053058624268, | |
| "learning_rate": 2.9333333333333338e-06, | |
| "loss": 0.0318, | |
| "num_input_tokens_seen": 4744864, | |
| "step": 352 | |
| }, | |
| { | |
| "epoch": 4.540192926045016, | |
| "grad_norm": 6.330677509307861, | |
| "learning_rate": 2.941666666666667e-06, | |
| "loss": 0.0213, | |
| "num_input_tokens_seen": 4758240, | |
| "step": 353 | |
| }, | |
| { | |
| "epoch": 4.553054662379421, | |
| "grad_norm": 0.9806466698646545, | |
| "learning_rate": 2.95e-06, | |
| "loss": 0.0048, | |
| "num_input_tokens_seen": 4770368, | |
| "step": 354 | |
| }, | |
| { | |
| "epoch": 4.565916398713826, | |
| "grad_norm": 3.046319007873535, | |
| "learning_rate": 2.9583333333333335e-06, | |
| "loss": 0.0326, | |
| "num_input_tokens_seen": 4783328, | |
| "step": 355 | |
| }, | |
| { | |
| "epoch": 4.578778135048232, | |
| "grad_norm": 5.004611015319824, | |
| "learning_rate": 2.9666666666666673e-06, | |
| "loss": 0.013, | |
| "num_input_tokens_seen": 4797088, | |
| "step": 356 | |
| }, | |
| { | |
| "epoch": 4.591639871382637, | |
| "grad_norm": 5.062610626220703, | |
| "learning_rate": 2.9750000000000003e-06, | |
| "loss": 0.0293, | |
| "num_input_tokens_seen": 4810464, | |
| "step": 357 | |
| }, | |
| { | |
| "epoch": 4.604501607717042, | |
| "grad_norm": 9.05587100982666, | |
| "learning_rate": 2.9833333333333337e-06, | |
| "loss": 0.0411, | |
| "num_input_tokens_seen": 4823744, | |
| "step": 358 | |
| }, | |
| { | |
| "epoch": 4.617363344051447, | |
| "grad_norm": 7.2998175621032715, | |
| "learning_rate": 2.991666666666667e-06, | |
| "loss": 0.0389, | |
| "num_input_tokens_seen": 4837824, | |
| "step": 359 | |
| }, | |
| { | |
| "epoch": 4.630225080385852, | |
| "grad_norm": 6.108879566192627, | |
| "learning_rate": 3e-06, | |
| "loss": 0.0395, | |
| "num_input_tokens_seen": 4852096, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 4.643086816720257, | |
| "grad_norm": 4.677525043487549, | |
| "learning_rate": 3.0083333333333335e-06, | |
| "loss": 0.0065, | |
| "num_input_tokens_seen": 4865600, | |
| "step": 361 | |
| }, | |
| { | |
| "epoch": 4.655948553054662, | |
| "grad_norm": 9.179205894470215, | |
| "learning_rate": 3.0166666666666673e-06, | |
| "loss": 0.0294, | |
| "num_input_tokens_seen": 4878592, | |
| "step": 362 | |
| }, | |
| { | |
| "epoch": 4.668810289389068, | |
| "grad_norm": 3.478533983230591, | |
| "learning_rate": 3.0250000000000003e-06, | |
| "loss": 0.0192, | |
| "num_input_tokens_seen": 4892064, | |
| "step": 363 | |
| }, | |
| { | |
| "epoch": 4.681672025723473, | |
| "grad_norm": 6.015811443328857, | |
| "learning_rate": 3.0333333333333337e-06, | |
| "loss": 0.0179, | |
| "num_input_tokens_seen": 4906304, | |
| "step": 364 | |
| }, | |
| { | |
| "epoch": 4.694533762057878, | |
| "grad_norm": 3.1433732509613037, | |
| "learning_rate": 3.0416666666666666e-06, | |
| "loss": 0.0131, | |
| "num_input_tokens_seen": 4920480, | |
| "step": 365 | |
| }, | |
| { | |
| "epoch": 4.707395498392283, | |
| "grad_norm": 3.894927501678467, | |
| "learning_rate": 3.05e-06, | |
| "loss": 0.0216, | |
| "num_input_tokens_seen": 4933376, | |
| "step": 366 | |
| }, | |
| { | |
| "epoch": 4.720257234726688, | |
| "grad_norm": 3.4421629905700684, | |
| "learning_rate": 3.058333333333334e-06, | |
| "loss": 0.0171, | |
| "num_input_tokens_seen": 4947872, | |
| "step": 367 | |
| }, | |
| { | |
| "epoch": 4.733118971061093, | |
| "grad_norm": 2.935985803604126, | |
| "learning_rate": 3.066666666666667e-06, | |
| "loss": 0.0129, | |
| "num_input_tokens_seen": 4961280, | |
| "step": 368 | |
| }, | |
| { | |
| "epoch": 4.745980707395498, | |
| "grad_norm": 7.003020763397217, | |
| "learning_rate": 3.075e-06, | |
| "loss": 0.0268, | |
| "num_input_tokens_seen": 4975072, | |
| "step": 369 | |
| }, | |
| { | |
| "epoch": 4.758842443729904, | |
| "grad_norm": 5.833902835845947, | |
| "learning_rate": 3.0833333333333336e-06, | |
| "loss": 0.0313, | |
| "num_input_tokens_seen": 4988928, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 4.771704180064309, | |
| "grad_norm": 4.902740001678467, | |
| "learning_rate": 3.0916666666666666e-06, | |
| "loss": 0.0197, | |
| "num_input_tokens_seen": 5002656, | |
| "step": 371 | |
| }, | |
| { | |
| "epoch": 4.784565916398714, | |
| "grad_norm": 1.6855580806732178, | |
| "learning_rate": 3.1000000000000004e-06, | |
| "loss": 0.0051, | |
| "num_input_tokens_seen": 5016928, | |
| "step": 372 | |
| }, | |
| { | |
| "epoch": 4.797427652733119, | |
| "grad_norm": 3.116506814956665, | |
| "learning_rate": 3.1083333333333338e-06, | |
| "loss": 0.0107, | |
| "num_input_tokens_seen": 5030432, | |
| "step": 373 | |
| }, | |
| { | |
| "epoch": 4.810289389067524, | |
| "grad_norm": 2.606302261352539, | |
| "learning_rate": 3.1166666666666668e-06, | |
| "loss": 0.0299, | |
| "num_input_tokens_seen": 5044128, | |
| "step": 374 | |
| }, | |
| { | |
| "epoch": 4.823151125401929, | |
| "grad_norm": 5.198400497436523, | |
| "learning_rate": 3.125e-06, | |
| "loss": 0.0549, | |
| "num_input_tokens_seen": 5058592, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 4.836012861736334, | |
| "grad_norm": 3.7756950855255127, | |
| "learning_rate": 3.133333333333334e-06, | |
| "loss": 0.0163, | |
| "num_input_tokens_seen": 5071680, | |
| "step": 376 | |
| }, | |
| { | |
| "epoch": 4.84887459807074, | |
| "grad_norm": 3.266502618789673, | |
| "learning_rate": 3.141666666666667e-06, | |
| "loss": 0.0133, | |
| "num_input_tokens_seen": 5085760, | |
| "step": 377 | |
| }, | |
| { | |
| "epoch": 4.861736334405145, | |
| "grad_norm": 3.7333478927612305, | |
| "learning_rate": 3.1500000000000003e-06, | |
| "loss": 0.0338, | |
| "num_input_tokens_seen": 5099168, | |
| "step": 378 | |
| }, | |
| { | |
| "epoch": 4.87459807073955, | |
| "grad_norm": 6.106029033660889, | |
| "learning_rate": 3.1583333333333337e-06, | |
| "loss": 0.0219, | |
| "num_input_tokens_seen": 5112512, | |
| "step": 379 | |
| }, | |
| { | |
| "epoch": 4.887459807073955, | |
| "grad_norm": 3.018552541732788, | |
| "learning_rate": 3.1666666666666667e-06, | |
| "loss": 0.0113, | |
| "num_input_tokens_seen": 5125696, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 4.90032154340836, | |
| "grad_norm": 5.034224987030029, | |
| "learning_rate": 3.175e-06, | |
| "loss": 0.0297, | |
| "num_input_tokens_seen": 5138816, | |
| "step": 381 | |
| }, | |
| { | |
| "epoch": 4.913183279742765, | |
| "grad_norm": 6.260331630706787, | |
| "learning_rate": 3.183333333333334e-06, | |
| "loss": 0.0417, | |
| "num_input_tokens_seen": 5152320, | |
| "step": 382 | |
| }, | |
| { | |
| "epoch": 4.92604501607717, | |
| "grad_norm": 4.149762153625488, | |
| "learning_rate": 3.191666666666667e-06, | |
| "loss": 0.027, | |
| "num_input_tokens_seen": 5165696, | |
| "step": 383 | |
| }, | |
| { | |
| "epoch": 4.938906752411576, | |
| "grad_norm": 2.9361073970794678, | |
| "learning_rate": 3.2000000000000003e-06, | |
| "loss": 0.0271, | |
| "num_input_tokens_seen": 5178368, | |
| "step": 384 | |
| }, | |
| { | |
| "epoch": 4.951768488745981, | |
| "grad_norm": 5.155781269073486, | |
| "learning_rate": 3.2083333333333337e-06, | |
| "loss": 0.0207, | |
| "num_input_tokens_seen": 5192736, | |
| "step": 385 | |
| }, | |
| { | |
| "epoch": 4.951768488745981, | |
| "num_input_tokens_seen": 5192736, | |
| "step": 385, | |
| "total_flos": 2.3382655808988774e+17, | |
| "train_loss": 0.7082552919200585, | |
| "train_runtime": 5092.4527, | |
| "train_samples_per_second": 19.519, | |
| "train_steps_per_second": 0.076 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 385, | |
| "num_input_tokens_seen": 5192736, | |
| "num_train_epochs": 5, | |
| "save_steps": 1000, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2.3382655808988774e+17, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |