Sven00's picture
Upload 21 files
586807d
raw
history blame
56.4 kB
{
"best_metric": 1.9635850191116333,
"best_model_checkpoint": "./results/redpj7B-lora-cnn-dailymail-results_fine_tune_test/checkpoint-600",
"epoch": 2.9187396351575456,
"global_step": 8800,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.01,
"learning_rate": 0.00027082228116710874,
"loss": 1.8654,
"step": 20
},
{
"epoch": 0.01,
"learning_rate": 0.0002681697612732095,
"loss": 1.8124,
"step": 40
},
{
"epoch": 0.02,
"learning_rate": 0.0002655172413793103,
"loss": 1.8231,
"step": 60
},
{
"epoch": 0.03,
"learning_rate": 0.0002628647214854111,
"loss": 1.7818,
"step": 80
},
{
"epoch": 0.03,
"learning_rate": 0.00026021220159151194,
"loss": 1.8446,
"step": 100
},
{
"epoch": 0.04,
"learning_rate": 0.0002575596816976127,
"loss": 1.9001,
"step": 120
},
{
"epoch": 0.05,
"learning_rate": 0.0002549071618037135,
"loss": 1.8073,
"step": 140
},
{
"epoch": 0.05,
"learning_rate": 0.0002522546419098143,
"loss": 1.8506,
"step": 160
},
{
"epoch": 0.06,
"learning_rate": 0.0002496021220159151,
"loss": 1.8471,
"step": 180
},
{
"epoch": 0.07,
"learning_rate": 0.0002469496021220159,
"loss": 1.8647,
"step": 200
},
{
"epoch": 0.07,
"eval_loss": 1.966022253036499,
"eval_runtime": 12002.3952,
"eval_samples_per_second": 1.114,
"eval_steps_per_second": 0.139,
"step": 200
},
{
"epoch": 0.07,
"learning_rate": 0.00024429708222811666,
"loss": 1.8578,
"step": 220
},
{
"epoch": 0.08,
"learning_rate": 0.0002416445623342175,
"loss": 1.8329,
"step": 240
},
{
"epoch": 0.09,
"learning_rate": 0.0002389920424403183,
"loss": 1.8119,
"step": 260
},
{
"epoch": 0.09,
"learning_rate": 0.0002363395225464191,
"loss": 1.8884,
"step": 280
},
{
"epoch": 0.1,
"learning_rate": 0.00023368700265251986,
"loss": 1.9077,
"step": 300
},
{
"epoch": 0.11,
"learning_rate": 0.00023103448275862065,
"loss": 1.8092,
"step": 320
},
{
"epoch": 0.11,
"learning_rate": 0.00022838196286472146,
"loss": 1.9237,
"step": 340
},
{
"epoch": 0.12,
"learning_rate": 0.00022572944297082225,
"loss": 1.8701,
"step": 360
},
{
"epoch": 0.13,
"learning_rate": 0.00022307692307692306,
"loss": 1.8933,
"step": 380
},
{
"epoch": 0.13,
"learning_rate": 0.00022042440318302385,
"loss": 1.8453,
"step": 400
},
{
"epoch": 0.13,
"eval_loss": 1.9667036533355713,
"eval_runtime": 11991.8036,
"eval_samples_per_second": 1.115,
"eval_steps_per_second": 0.139,
"step": 400
},
{
"epoch": 0.14,
"learning_rate": 0.00021777188328912466,
"loss": 1.8272,
"step": 420
},
{
"epoch": 0.15,
"learning_rate": 0.00021511936339522545,
"loss": 1.8149,
"step": 440
},
{
"epoch": 0.15,
"learning_rate": 0.00021246684350132626,
"loss": 1.8565,
"step": 460
},
{
"epoch": 0.16,
"learning_rate": 0.00020981432360742705,
"loss": 1.8139,
"step": 480
},
{
"epoch": 0.17,
"learning_rate": 0.0002071618037135278,
"loss": 1.802,
"step": 500
},
{
"epoch": 0.17,
"learning_rate": 0.00020450928381962862,
"loss": 1.8795,
"step": 520
},
{
"epoch": 0.18,
"learning_rate": 0.0002018567639257294,
"loss": 1.8621,
"step": 540
},
{
"epoch": 0.19,
"learning_rate": 0.00019920424403183022,
"loss": 1.8363,
"step": 560
},
{
"epoch": 0.19,
"learning_rate": 0.000196551724137931,
"loss": 1.8746,
"step": 580
},
{
"epoch": 0.2,
"learning_rate": 0.00019389920424403182,
"loss": 1.7763,
"step": 600
},
{
"epoch": 0.2,
"eval_loss": 1.9635850191116333,
"eval_runtime": 11976.5234,
"eval_samples_per_second": 1.116,
"eval_steps_per_second": 0.14,
"step": 600
},
{
"epoch": 0.21,
"learning_rate": 0.0001912466843501326,
"loss": 1.8423,
"step": 620
},
{
"epoch": 0.21,
"learning_rate": 0.00018859416445623343,
"loss": 1.8998,
"step": 640
},
{
"epoch": 0.22,
"learning_rate": 0.0001859416445623342,
"loss": 1.8131,
"step": 660
},
{
"epoch": 0.23,
"learning_rate": 0.00018328912466843497,
"loss": 1.8656,
"step": 680
},
{
"epoch": 0.23,
"learning_rate": 0.00018063660477453579,
"loss": 1.8181,
"step": 700
},
{
"epoch": 0.24,
"learning_rate": 0.00017798408488063657,
"loss": 1.8425,
"step": 720
},
{
"epoch": 0.25,
"learning_rate": 0.00017533156498673739,
"loss": 1.7883,
"step": 740
},
{
"epoch": 0.25,
"learning_rate": 0.00017267904509283817,
"loss": 1.8469,
"step": 760
},
{
"epoch": 0.26,
"learning_rate": 0.000170026525198939,
"loss": 1.8447,
"step": 780
},
{
"epoch": 0.27,
"learning_rate": 0.00016737400530503977,
"loss": 1.7872,
"step": 800
},
{
"epoch": 0.27,
"eval_loss": 1.9704641103744507,
"eval_runtime": 11963.7945,
"eval_samples_per_second": 1.117,
"eval_steps_per_second": 0.14,
"step": 800
},
{
"epoch": 0.27,
"learning_rate": 0.0001647214854111406,
"loss": 1.8032,
"step": 820
},
{
"epoch": 0.28,
"learning_rate": 0.00016206896551724137,
"loss": 1.8709,
"step": 840
},
{
"epoch": 0.29,
"learning_rate": 0.00015941644562334216,
"loss": 1.8801,
"step": 860
},
{
"epoch": 0.29,
"learning_rate": 0.00015676392572944298,
"loss": 1.8535,
"step": 880
},
{
"epoch": 0.3,
"learning_rate": 0.00015411140583554373,
"loss": 1.8631,
"step": 900
},
{
"epoch": 0.31,
"learning_rate": 0.00015145888594164455,
"loss": 1.752,
"step": 920
},
{
"epoch": 0.31,
"learning_rate": 0.00014880636604774534,
"loss": 1.8705,
"step": 940
},
{
"epoch": 0.32,
"learning_rate": 0.00014615384615384615,
"loss": 1.8301,
"step": 960
},
{
"epoch": 0.33,
"learning_rate": 0.00014350132625994694,
"loss": 1.7892,
"step": 980
},
{
"epoch": 0.33,
"learning_rate": 0.00014084880636604772,
"loss": 1.8671,
"step": 1000
},
{
"epoch": 0.33,
"eval_loss": 1.9677250385284424,
"eval_runtime": 11951.074,
"eval_samples_per_second": 1.119,
"eval_steps_per_second": 0.14,
"step": 1000
},
{
"epoch": 0.34,
"learning_rate": 0.00013819628647214854,
"loss": 1.8168,
"step": 1020
},
{
"epoch": 0.34,
"learning_rate": 0.00013554376657824932,
"loss": 1.8268,
"step": 1040
},
{
"epoch": 0.35,
"learning_rate": 0.00013289124668435014,
"loss": 1.8073,
"step": 1060
},
{
"epoch": 0.36,
"learning_rate": 0.0001302387267904509,
"loss": 1.9313,
"step": 1080
},
{
"epoch": 0.36,
"learning_rate": 0.0001275862068965517,
"loss": 1.9097,
"step": 1100
},
{
"epoch": 0.37,
"learning_rate": 0.0001249336870026525,
"loss": 1.9032,
"step": 1120
},
{
"epoch": 0.38,
"learning_rate": 0.0001222811671087533,
"loss": 1.8207,
"step": 1140
},
{
"epoch": 0.38,
"learning_rate": 0.0001196286472148541,
"loss": 1.8815,
"step": 1160
},
{
"epoch": 0.39,
"learning_rate": 0.0001169761273209549,
"loss": 1.8297,
"step": 1180
},
{
"epoch": 0.4,
"learning_rate": 0.0001143236074270557,
"loss": 1.8899,
"step": 1200
},
{
"epoch": 0.4,
"eval_loss": 1.9722812175750732,
"eval_runtime": 11951.1639,
"eval_samples_per_second": 1.119,
"eval_steps_per_second": 0.14,
"step": 1200
},
{
"epoch": 0.4,
"learning_rate": 0.0001116710875331565,
"loss": 1.8803,
"step": 1220
},
{
"epoch": 0.41,
"learning_rate": 0.00010901856763925729,
"loss": 1.8548,
"step": 1240
},
{
"epoch": 0.42,
"learning_rate": 0.00010636604774535807,
"loss": 1.8498,
"step": 1260
},
{
"epoch": 0.42,
"learning_rate": 0.00010371352785145887,
"loss": 1.8057,
"step": 1280
},
{
"epoch": 0.43,
"learning_rate": 0.00010106100795755967,
"loss": 1.8572,
"step": 1300
},
{
"epoch": 0.44,
"learning_rate": 9.840848806366047e-05,
"loss": 1.8469,
"step": 1320
},
{
"epoch": 0.44,
"learning_rate": 9.575596816976126e-05,
"loss": 1.8405,
"step": 1340
},
{
"epoch": 0.45,
"learning_rate": 9.310344827586206e-05,
"loss": 1.8193,
"step": 1360
},
{
"epoch": 0.46,
"learning_rate": 9.045092838196286e-05,
"loss": 1.7731,
"step": 1380
},
{
"epoch": 0.46,
"learning_rate": 8.779840848806366e-05,
"loss": 1.8329,
"step": 1400
},
{
"epoch": 0.46,
"eval_loss": 1.9736511707305908,
"eval_runtime": 11956.5916,
"eval_samples_per_second": 1.118,
"eval_steps_per_second": 0.14,
"step": 1400
},
{
"epoch": 0.47,
"learning_rate": 8.514588859416444e-05,
"loss": 1.8872,
"step": 1420
},
{
"epoch": 0.48,
"learning_rate": 8.249336870026524e-05,
"loss": 1.8511,
"step": 1440
},
{
"epoch": 0.48,
"learning_rate": 7.984084880636604e-05,
"loss": 1.7523,
"step": 1460
},
{
"epoch": 0.49,
"learning_rate": 7.718832891246684e-05,
"loss": 1.8619,
"step": 1480
},
{
"epoch": 0.5,
"learning_rate": 7.453580901856764e-05,
"loss": 1.8363,
"step": 1500
},
{
"epoch": 0.5,
"learning_rate": 7.188328912466844e-05,
"loss": 1.7745,
"step": 1520
},
{
"epoch": 0.51,
"learning_rate": 6.923076923076922e-05,
"loss": 1.8164,
"step": 1540
},
{
"epoch": 0.52,
"learning_rate": 6.657824933687002e-05,
"loss": 1.7997,
"step": 1560
},
{
"epoch": 0.52,
"learning_rate": 6.392572944297081e-05,
"loss": 1.8377,
"step": 1580
},
{
"epoch": 0.53,
"learning_rate": 6.127320954907161e-05,
"loss": 1.851,
"step": 1600
},
{
"epoch": 0.53,
"eval_loss": 1.9729183912277222,
"eval_runtime": 11970.5767,
"eval_samples_per_second": 1.117,
"eval_steps_per_second": 0.14,
"step": 1600
},
{
"epoch": 0.54,
"learning_rate": 5.862068965517241e-05,
"loss": 1.8382,
"step": 1620
},
{
"epoch": 0.54,
"learning_rate": 5.59681697612732e-05,
"loss": 1.8863,
"step": 1640
},
{
"epoch": 0.55,
"learning_rate": 5.3315649867374e-05,
"loss": 1.762,
"step": 1660
},
{
"epoch": 0.56,
"learning_rate": 5.06631299734748e-05,
"loss": 1.822,
"step": 1680
},
{
"epoch": 0.56,
"learning_rate": 4.801061007957559e-05,
"loss": 1.7776,
"step": 1700
},
{
"epoch": 0.57,
"learning_rate": 4.5358090185676386e-05,
"loss": 1.809,
"step": 1720
},
{
"epoch": 0.58,
"learning_rate": 4.2705570291777186e-05,
"loss": 1.912,
"step": 1740
},
{
"epoch": 0.58,
"learning_rate": 4.005305039787798e-05,
"loss": 1.7557,
"step": 1760
},
{
"epoch": 0.59,
"learning_rate": 3.7400530503978774e-05,
"loss": 1.8232,
"step": 1780
},
{
"epoch": 0.6,
"learning_rate": 3.4748010610079574e-05,
"loss": 1.8613,
"step": 1800
},
{
"epoch": 0.6,
"eval_loss": 1.9704504013061523,
"eval_runtime": 11980.5334,
"eval_samples_per_second": 1.116,
"eval_steps_per_second": 0.139,
"step": 1800
},
{
"epoch": 0.6,
"learning_rate": 3.209549071618037e-05,
"loss": 1.8378,
"step": 1820
},
{
"epoch": 0.61,
"learning_rate": 2.9442970822281164e-05,
"loss": 1.8871,
"step": 1840
},
{
"epoch": 0.62,
"learning_rate": 2.679045092838196e-05,
"loss": 1.8821,
"step": 1860
},
{
"epoch": 0.62,
"learning_rate": 2.4137931034482755e-05,
"loss": 1.8487,
"step": 1880
},
{
"epoch": 0.63,
"learning_rate": 2.1485411140583555e-05,
"loss": 1.8439,
"step": 1900
},
{
"epoch": 0.64,
"learning_rate": 1.883289124668435e-05,
"loss": 1.8469,
"step": 1920
},
{
"epoch": 0.64,
"learning_rate": 1.6180371352785142e-05,
"loss": 1.7797,
"step": 1940
},
{
"epoch": 0.65,
"learning_rate": 1.352785145888594e-05,
"loss": 1.7795,
"step": 1960
},
{
"epoch": 0.66,
"learning_rate": 1.0875331564986736e-05,
"loss": 1.8483,
"step": 1980
},
{
"epoch": 0.66,
"learning_rate": 8.222811671087533e-06,
"loss": 1.8321,
"step": 2000
},
{
"epoch": 0.66,
"eval_loss": 1.9704707860946655,
"eval_runtime": 11964.4776,
"eval_samples_per_second": 1.117,
"eval_steps_per_second": 0.14,
"step": 2000
},
{
"epoch": 0.67,
"learning_rate": 5.5702917771883284e-06,
"loss": 1.7708,
"step": 2020
},
{
"epoch": 0.68,
"learning_rate": 2.9177718832891245e-06,
"loss": 1.8731,
"step": 2040
},
{
"epoch": 0.68,
"learning_rate": 2.652519893899204e-07,
"loss": 1.8181,
"step": 2060
},
{
"epoch": 0.69,
"learning_rate": 0.0,
"loss": 1.8692,
"step": 2080
},
{
"epoch": 0.7,
"learning_rate": 0.0,
"loss": 1.8602,
"step": 2100
},
{
"epoch": 0.7,
"learning_rate": 0.0,
"loss": 1.8891,
"step": 2120
},
{
"epoch": 0.71,
"learning_rate": 0.0,
"loss": 1.8205,
"step": 2140
},
{
"epoch": 0.72,
"learning_rate": 0.0,
"loss": 1.8242,
"step": 2160
},
{
"epoch": 0.72,
"learning_rate": 0.0,
"loss": 1.8661,
"step": 2180
},
{
"epoch": 0.73,
"learning_rate": 0.0,
"loss": 1.7982,
"step": 2200
},
{
"epoch": 0.73,
"eval_loss": 1.970503568649292,
"eval_runtime": 11950.1314,
"eval_samples_per_second": 1.119,
"eval_steps_per_second": 0.14,
"step": 2200
},
{
"epoch": 0.74,
"learning_rate": 0.0,
"loss": 1.7967,
"step": 2220
},
{
"epoch": 0.74,
"learning_rate": 0.0,
"loss": 1.8346,
"step": 2240
},
{
"epoch": 0.75,
"learning_rate": 0.0,
"loss": 1.8242,
"step": 2260
},
{
"epoch": 0.76,
"learning_rate": 0.0,
"loss": 1.8429,
"step": 2280
},
{
"epoch": 0.76,
"learning_rate": 0.0,
"loss": 1.8795,
"step": 2300
},
{
"epoch": 0.77,
"learning_rate": 0.0,
"loss": 1.8967,
"step": 2320
},
{
"epoch": 0.78,
"learning_rate": 0.0,
"loss": 1.815,
"step": 2340
},
{
"epoch": 0.78,
"learning_rate": 0.0,
"loss": 1.8165,
"step": 2360
},
{
"epoch": 0.79,
"learning_rate": 0.0,
"loss": 1.838,
"step": 2380
},
{
"epoch": 0.8,
"learning_rate": 0.0,
"loss": 1.7798,
"step": 2400
},
{
"epoch": 0.8,
"eval_loss": 1.970503568649292,
"eval_runtime": 11951.0888,
"eval_samples_per_second": 1.119,
"eval_steps_per_second": 0.14,
"step": 2400
},
{
"epoch": 0.8,
"learning_rate": 0.0,
"loss": 1.7999,
"step": 2420
},
{
"epoch": 0.81,
"learning_rate": 0.0,
"loss": 1.7957,
"step": 2440
},
{
"epoch": 0.82,
"learning_rate": 0.0,
"loss": 1.8306,
"step": 2460
},
{
"epoch": 0.82,
"learning_rate": 0.0,
"loss": 1.87,
"step": 2480
},
{
"epoch": 0.83,
"learning_rate": 0.0,
"loss": 1.8046,
"step": 2500
},
{
"epoch": 0.84,
"learning_rate": 0.0,
"loss": 1.76,
"step": 2520
},
{
"epoch": 0.84,
"learning_rate": 0.0,
"loss": 1.869,
"step": 2540
},
{
"epoch": 0.85,
"learning_rate": 0.0,
"loss": 1.8684,
"step": 2560
},
{
"epoch": 0.86,
"learning_rate": 0.0,
"loss": 1.8757,
"step": 2580
},
{
"epoch": 0.86,
"learning_rate": 0.0,
"loss": 1.868,
"step": 2600
},
{
"epoch": 0.86,
"eval_loss": 1.970503568649292,
"eval_runtime": 11952.488,
"eval_samples_per_second": 1.118,
"eval_steps_per_second": 0.14,
"step": 2600
},
{
"epoch": 0.87,
"learning_rate": 0.0,
"loss": 1.8228,
"step": 2620
},
{
"epoch": 0.88,
"learning_rate": 0.0,
"loss": 1.8721,
"step": 2640
},
{
"epoch": 0.88,
"learning_rate": 0.0,
"loss": 1.8557,
"step": 2660
},
{
"epoch": 0.89,
"learning_rate": 0.0,
"loss": 1.8545,
"step": 2680
},
{
"epoch": 0.9,
"learning_rate": 0.0,
"loss": 1.8366,
"step": 2700
},
{
"epoch": 0.9,
"learning_rate": 0.0,
"loss": 1.8381,
"step": 2720
},
{
"epoch": 0.91,
"learning_rate": 0.0,
"loss": 1.8305,
"step": 2740
},
{
"epoch": 0.92,
"learning_rate": 0.0,
"loss": 1.8162,
"step": 2760
},
{
"epoch": 0.92,
"learning_rate": 0.0,
"loss": 1.8109,
"step": 2780
},
{
"epoch": 0.93,
"learning_rate": 0.0,
"loss": 1.8694,
"step": 2800
},
{
"epoch": 0.93,
"eval_loss": 1.970503568649292,
"eval_runtime": 11969.9504,
"eval_samples_per_second": 1.117,
"eval_steps_per_second": 0.14,
"step": 2800
},
{
"epoch": 0.94,
"learning_rate": 0.0,
"loss": 1.8201,
"step": 2820
},
{
"epoch": 0.94,
"learning_rate": 0.0,
"loss": 1.848,
"step": 2840
},
{
"epoch": 0.95,
"learning_rate": 0.0,
"loss": 1.8138,
"step": 2860
},
{
"epoch": 0.96,
"learning_rate": 0.0,
"loss": 1.8554,
"step": 2880
},
{
"epoch": 0.96,
"learning_rate": 0.0,
"loss": 1.8321,
"step": 2900
},
{
"epoch": 0.97,
"learning_rate": 0.0,
"loss": 1.8404,
"step": 2920
},
{
"epoch": 0.98,
"learning_rate": 0.0,
"loss": 1.7883,
"step": 2940
},
{
"epoch": 0.98,
"learning_rate": 0.0,
"loss": 1.8733,
"step": 2960
},
{
"epoch": 0.99,
"learning_rate": 0.0,
"loss": 1.8074,
"step": 2980
},
{
"epoch": 1.0,
"learning_rate": 0.0,
"loss": 1.887,
"step": 3000
},
{
"epoch": 1.0,
"eval_loss": 1.970503568649292,
"eval_runtime": 11974.5637,
"eval_samples_per_second": 1.116,
"eval_steps_per_second": 0.14,
"step": 3000
},
{
"epoch": 1.0,
"learning_rate": 0.0,
"loss": 1.7165,
"step": 3020
},
{
"epoch": 1.01,
"learning_rate": 0.0,
"loss": 1.8041,
"step": 3040
},
{
"epoch": 1.01,
"learning_rate": 0.0,
"loss": 1.8031,
"step": 3060
},
{
"epoch": 1.02,
"learning_rate": 0.0,
"loss": 1.8493,
"step": 3080
},
{
"epoch": 1.03,
"learning_rate": 0.0,
"loss": 1.8475,
"step": 3100
},
{
"epoch": 1.03,
"learning_rate": 0.0,
"loss": 1.7994,
"step": 3120
},
{
"epoch": 1.04,
"learning_rate": 0.0,
"loss": 1.7904,
"step": 3140
},
{
"epoch": 1.05,
"learning_rate": 0.0,
"loss": 1.8078,
"step": 3160
},
{
"epoch": 1.05,
"learning_rate": 0.0,
"loss": 1.8625,
"step": 3180
},
{
"epoch": 1.06,
"learning_rate": 0.0,
"loss": 1.7874,
"step": 3200
},
{
"epoch": 1.06,
"eval_loss": 1.970503568649292,
"eval_runtime": 11966.566,
"eval_samples_per_second": 1.117,
"eval_steps_per_second": 0.14,
"step": 3200
},
{
"epoch": 1.07,
"learning_rate": 0.0,
"loss": 1.7956,
"step": 3220
},
{
"epoch": 1.07,
"learning_rate": 0.0,
"loss": 1.7517,
"step": 3240
},
{
"epoch": 1.08,
"learning_rate": 0.0,
"loss": 1.7861,
"step": 3260
},
{
"epoch": 1.09,
"learning_rate": 0.0,
"loss": 1.7957,
"step": 3280
},
{
"epoch": 1.09,
"learning_rate": 0.0,
"loss": 1.8147,
"step": 3300
},
{
"epoch": 1.1,
"learning_rate": 0.0,
"loss": 1.7795,
"step": 3320
},
{
"epoch": 1.11,
"learning_rate": 0.0,
"loss": 1.7532,
"step": 3340
},
{
"epoch": 1.11,
"learning_rate": 0.0,
"loss": 1.8414,
"step": 3360
},
{
"epoch": 1.12,
"learning_rate": 0.0,
"loss": 1.771,
"step": 3380
},
{
"epoch": 1.13,
"learning_rate": 0.0,
"loss": 1.8119,
"step": 3400
},
{
"epoch": 1.13,
"eval_loss": 1.970503568649292,
"eval_runtime": 11954.7549,
"eval_samples_per_second": 1.118,
"eval_steps_per_second": 0.14,
"step": 3400
},
{
"epoch": 1.13,
"learning_rate": 0.0,
"loss": 1.7944,
"step": 3420
},
{
"epoch": 1.14,
"learning_rate": 0.0,
"loss": 1.7855,
"step": 3440
},
{
"epoch": 1.15,
"learning_rate": 0.0,
"loss": 1.8574,
"step": 3460
},
{
"epoch": 1.15,
"learning_rate": 0.0,
"loss": 1.8189,
"step": 3480
},
{
"epoch": 1.16,
"learning_rate": 0.0,
"loss": 1.8033,
"step": 3500
},
{
"epoch": 1.17,
"learning_rate": 0.0,
"loss": 1.7689,
"step": 3520
},
{
"epoch": 1.17,
"learning_rate": 0.0,
"loss": 1.8455,
"step": 3540
},
{
"epoch": 1.18,
"learning_rate": 0.0,
"loss": 1.8255,
"step": 3560
},
{
"epoch": 1.19,
"learning_rate": 0.0,
"loss": 1.8431,
"step": 3580
},
{
"epoch": 1.19,
"learning_rate": 0.0,
"loss": 1.7924,
"step": 3600
},
{
"epoch": 1.19,
"eval_loss": 1.970503568649292,
"eval_runtime": 11953.5885,
"eval_samples_per_second": 1.118,
"eval_steps_per_second": 0.14,
"step": 3600
},
{
"epoch": 1.2,
"learning_rate": 0.0,
"loss": 1.8475,
"step": 3620
},
{
"epoch": 1.21,
"learning_rate": 0.0,
"loss": 1.6746,
"step": 3640
},
{
"epoch": 1.21,
"learning_rate": 0.0,
"loss": 1.8006,
"step": 3660
},
{
"epoch": 1.22,
"learning_rate": 0.0,
"loss": 1.816,
"step": 3680
},
{
"epoch": 1.23,
"learning_rate": 0.0,
"loss": 1.7486,
"step": 3700
},
{
"epoch": 1.23,
"learning_rate": 0.0,
"loss": 1.8086,
"step": 3720
},
{
"epoch": 1.24,
"learning_rate": 0.0,
"loss": 1.8241,
"step": 3740
},
{
"epoch": 1.25,
"learning_rate": 0.0,
"loss": 1.823,
"step": 3760
},
{
"epoch": 1.25,
"learning_rate": 0.0,
"loss": 1.7365,
"step": 3780
},
{
"epoch": 1.26,
"learning_rate": 0.0,
"loss": 1.801,
"step": 3800
},
{
"epoch": 1.26,
"eval_loss": 1.970503568649292,
"eval_runtime": 11952.013,
"eval_samples_per_second": 1.118,
"eval_steps_per_second": 0.14,
"step": 3800
},
{
"epoch": 1.27,
"learning_rate": 0.0,
"loss": 1.8497,
"step": 3820
},
{
"epoch": 1.27,
"learning_rate": 0.0,
"loss": 1.7803,
"step": 3840
},
{
"epoch": 1.28,
"learning_rate": 0.0,
"loss": 1.6921,
"step": 3860
},
{
"epoch": 1.29,
"learning_rate": 0.0,
"loss": 1.8508,
"step": 3880
},
{
"epoch": 1.29,
"learning_rate": 0.0,
"loss": 1.8816,
"step": 3900
},
{
"epoch": 1.3,
"learning_rate": 0.0,
"loss": 1.8105,
"step": 3920
},
{
"epoch": 1.31,
"learning_rate": 0.0,
"loss": 1.8477,
"step": 3940
},
{
"epoch": 1.31,
"learning_rate": 0.0,
"loss": 1.841,
"step": 3960
},
{
"epoch": 1.32,
"learning_rate": 0.0,
"loss": 1.7599,
"step": 3980
},
{
"epoch": 1.33,
"learning_rate": 0.0,
"loss": 1.7074,
"step": 4000
},
{
"epoch": 1.33,
"eval_loss": 1.970503568649292,
"eval_runtime": 11952.3623,
"eval_samples_per_second": 1.118,
"eval_steps_per_second": 0.14,
"step": 4000
},
{
"epoch": 1.33,
"learning_rate": 0.0,
"loss": 1.7529,
"step": 4020
},
{
"epoch": 1.34,
"learning_rate": 0.0,
"loss": 1.8928,
"step": 4040
},
{
"epoch": 1.35,
"learning_rate": 0.0,
"loss": 1.8585,
"step": 4060
},
{
"epoch": 1.35,
"learning_rate": 0.0,
"loss": 1.8279,
"step": 4080
},
{
"epoch": 1.36,
"learning_rate": 0.0,
"loss": 1.7949,
"step": 4100
},
{
"epoch": 1.37,
"learning_rate": 0.0,
"loss": 1.8488,
"step": 4120
},
{
"epoch": 1.37,
"learning_rate": 0.0,
"loss": 1.7572,
"step": 4140
},
{
"epoch": 1.38,
"learning_rate": 0.0,
"loss": 1.7533,
"step": 4160
},
{
"epoch": 1.39,
"learning_rate": 0.0,
"loss": 1.772,
"step": 4180
},
{
"epoch": 1.39,
"learning_rate": 0.0,
"loss": 1.8338,
"step": 4200
},
{
"epoch": 1.39,
"eval_loss": 1.970503568649292,
"eval_runtime": 11954.2113,
"eval_samples_per_second": 1.118,
"eval_steps_per_second": 0.14,
"step": 4200
},
{
"epoch": 1.4,
"learning_rate": 0.0,
"loss": 1.8084,
"step": 4220
},
{
"epoch": 1.41,
"learning_rate": 0.0,
"loss": 1.8791,
"step": 4240
},
{
"epoch": 1.41,
"learning_rate": 0.0,
"loss": 1.7906,
"step": 4260
},
{
"epoch": 1.42,
"learning_rate": 0.0,
"loss": 1.8669,
"step": 4280
},
{
"epoch": 1.43,
"learning_rate": 0.0,
"loss": 1.8108,
"step": 4300
},
{
"epoch": 1.43,
"learning_rate": 0.0,
"loss": 1.7769,
"step": 4320
},
{
"epoch": 1.44,
"learning_rate": 0.0,
"loss": 1.7599,
"step": 4340
},
{
"epoch": 1.45,
"learning_rate": 0.0,
"loss": 1.843,
"step": 4360
},
{
"epoch": 1.45,
"learning_rate": 0.0,
"loss": 1.8608,
"step": 4380
},
{
"epoch": 1.46,
"learning_rate": 0.0,
"loss": 1.8382,
"step": 4400
},
{
"epoch": 1.46,
"eval_loss": 1.970503568649292,
"eval_runtime": 11958.7166,
"eval_samples_per_second": 1.118,
"eval_steps_per_second": 0.14,
"step": 4400
},
{
"epoch": 1.47,
"learning_rate": 0.0,
"loss": 1.8002,
"step": 4420
},
{
"epoch": 1.47,
"learning_rate": 0.0,
"loss": 1.8292,
"step": 4440
},
{
"epoch": 1.48,
"learning_rate": 0.0,
"loss": 1.8184,
"step": 4460
},
{
"epoch": 1.49,
"learning_rate": 0.0,
"loss": 1.7712,
"step": 4480
},
{
"epoch": 1.49,
"learning_rate": 0.0,
"loss": 1.8307,
"step": 4500
},
{
"epoch": 1.5,
"learning_rate": 0.0,
"loss": 1.7883,
"step": 4520
},
{
"epoch": 1.51,
"learning_rate": 0.0,
"loss": 1.8106,
"step": 4540
},
{
"epoch": 1.51,
"learning_rate": 0.0,
"loss": 1.7999,
"step": 4560
},
{
"epoch": 1.52,
"learning_rate": 0.0,
"loss": 1.8353,
"step": 4580
},
{
"epoch": 1.53,
"learning_rate": 0.0,
"loss": 1.8366,
"step": 4600
},
{
"epoch": 1.53,
"eval_loss": 1.970503568649292,
"eval_runtime": 11971.0491,
"eval_samples_per_second": 1.117,
"eval_steps_per_second": 0.14,
"step": 4600
},
{
"epoch": 1.53,
"learning_rate": 0.0,
"loss": 1.8018,
"step": 4620
},
{
"epoch": 1.54,
"learning_rate": 0.0,
"loss": 1.84,
"step": 4640
},
{
"epoch": 1.55,
"learning_rate": 0.0,
"loss": 1.7784,
"step": 4660
},
{
"epoch": 1.55,
"learning_rate": 0.0,
"loss": 1.794,
"step": 4680
},
{
"epoch": 1.56,
"learning_rate": 0.0,
"loss": 1.8237,
"step": 4700
},
{
"epoch": 1.57,
"learning_rate": 0.0,
"loss": 1.7697,
"step": 4720
},
{
"epoch": 1.57,
"learning_rate": 0.0,
"loss": 1.8482,
"step": 4740
},
{
"epoch": 1.58,
"learning_rate": 0.0,
"loss": 1.8008,
"step": 4760
},
{
"epoch": 1.59,
"learning_rate": 0.0,
"loss": 1.8082,
"step": 4780
},
{
"epoch": 1.59,
"learning_rate": 0.0,
"loss": 1.7799,
"step": 4800
},
{
"epoch": 1.59,
"eval_loss": 1.970503568649292,
"eval_runtime": 11955.9821,
"eval_samples_per_second": 1.118,
"eval_steps_per_second": 0.14,
"step": 4800
},
{
"epoch": 1.6,
"learning_rate": 0.0,
"loss": 1.8339,
"step": 4820
},
{
"epoch": 1.61,
"learning_rate": 0.0,
"loss": 1.8072,
"step": 4840
},
{
"epoch": 1.61,
"learning_rate": 0.0,
"loss": 1.8024,
"step": 4860
},
{
"epoch": 1.62,
"learning_rate": 0.0,
"loss": 1.8609,
"step": 4880
},
{
"epoch": 1.63,
"learning_rate": 0.0,
"loss": 1.8769,
"step": 4900
},
{
"epoch": 1.63,
"learning_rate": 0.0,
"loss": 1.808,
"step": 4920
},
{
"epoch": 1.64,
"learning_rate": 0.0,
"loss": 1.8482,
"step": 4940
},
{
"epoch": 1.65,
"learning_rate": 0.0,
"loss": 1.8116,
"step": 4960
},
{
"epoch": 1.65,
"learning_rate": 0.0,
"loss": 1.7922,
"step": 4980
},
{
"epoch": 1.66,
"learning_rate": 0.0,
"loss": 1.8409,
"step": 5000
},
{
"epoch": 1.66,
"eval_loss": 1.970503568649292,
"eval_runtime": 11953.6568,
"eval_samples_per_second": 1.118,
"eval_steps_per_second": 0.14,
"step": 5000
},
{
"epoch": 1.67,
"learning_rate": 0.0,
"loss": 1.867,
"step": 5020
},
{
"epoch": 1.67,
"learning_rate": 0.0,
"loss": 1.8902,
"step": 5040
},
{
"epoch": 1.68,
"learning_rate": 0.0,
"loss": 1.8835,
"step": 5060
},
{
"epoch": 1.68,
"learning_rate": 0.0,
"loss": 1.741,
"step": 5080
},
{
"epoch": 1.69,
"learning_rate": 0.0,
"loss": 1.7543,
"step": 5100
},
{
"epoch": 1.7,
"learning_rate": 0.0,
"loss": 1.7913,
"step": 5120
},
{
"epoch": 1.7,
"learning_rate": 0.0,
"loss": 1.829,
"step": 5140
},
{
"epoch": 1.71,
"learning_rate": 0.0,
"loss": 1.7915,
"step": 5160
},
{
"epoch": 1.72,
"learning_rate": 0.0,
"loss": 1.767,
"step": 5180
},
{
"epoch": 1.72,
"learning_rate": 0.0,
"loss": 1.7809,
"step": 5200
},
{
"epoch": 1.72,
"eval_loss": 1.970503568649292,
"eval_runtime": 11951.295,
"eval_samples_per_second": 1.119,
"eval_steps_per_second": 0.14,
"step": 5200
},
{
"epoch": 1.73,
"learning_rate": 0.0,
"loss": 1.8715,
"step": 5220
},
{
"epoch": 1.74,
"learning_rate": 0.0,
"loss": 1.8517,
"step": 5240
},
{
"epoch": 1.74,
"learning_rate": 0.0,
"loss": 1.8255,
"step": 5260
},
{
"epoch": 1.75,
"learning_rate": 0.0,
"loss": 1.7973,
"step": 5280
},
{
"epoch": 1.76,
"learning_rate": 0.0,
"loss": 1.7912,
"step": 5300
},
{
"epoch": 1.76,
"learning_rate": 0.0,
"loss": 1.8331,
"step": 5320
},
{
"epoch": 1.77,
"learning_rate": 0.0,
"loss": 1.835,
"step": 5340
},
{
"epoch": 1.78,
"learning_rate": 0.0,
"loss": 1.8051,
"step": 5360
},
{
"epoch": 1.78,
"learning_rate": 0.0,
"loss": 1.8007,
"step": 5380
},
{
"epoch": 1.79,
"learning_rate": 0.0,
"loss": 1.8069,
"step": 5400
},
{
"epoch": 1.79,
"eval_loss": 1.970503568649292,
"eval_runtime": 11948.5086,
"eval_samples_per_second": 1.119,
"eval_steps_per_second": 0.14,
"step": 5400
},
{
"epoch": 1.8,
"learning_rate": 0.0,
"loss": 1.784,
"step": 5420
},
{
"epoch": 1.8,
"learning_rate": 0.0,
"loss": 1.7557,
"step": 5440
},
{
"epoch": 1.81,
"learning_rate": 0.0,
"loss": 1.8011,
"step": 5460
},
{
"epoch": 1.82,
"learning_rate": 0.0,
"loss": 1.8392,
"step": 5480
},
{
"epoch": 1.82,
"learning_rate": 0.0,
"loss": 1.7507,
"step": 5500
},
{
"epoch": 1.83,
"learning_rate": 0.0,
"loss": 1.8043,
"step": 5520
},
{
"epoch": 1.84,
"learning_rate": 0.0,
"loss": 1.7804,
"step": 5540
},
{
"epoch": 1.84,
"learning_rate": 0.0,
"loss": 1.811,
"step": 5560
},
{
"epoch": 1.85,
"learning_rate": 0.0,
"loss": 1.806,
"step": 5580
},
{
"epoch": 1.86,
"learning_rate": 0.0,
"loss": 1.8103,
"step": 5600
},
{
"epoch": 1.86,
"eval_loss": 1.970503568649292,
"eval_runtime": 11953.5582,
"eval_samples_per_second": 1.118,
"eval_steps_per_second": 0.14,
"step": 5600
},
{
"epoch": 1.86,
"learning_rate": 0.0,
"loss": 1.7947,
"step": 5620
},
{
"epoch": 1.87,
"learning_rate": 0.0,
"loss": 1.8062,
"step": 5640
},
{
"epoch": 1.88,
"learning_rate": 0.0,
"loss": 1.7997,
"step": 5660
},
{
"epoch": 1.88,
"learning_rate": 0.0,
"loss": 1.843,
"step": 5680
},
{
"epoch": 1.89,
"learning_rate": 0.0,
"loss": 1.848,
"step": 5700
},
{
"epoch": 1.9,
"learning_rate": 0.0,
"loss": 1.8393,
"step": 5720
},
{
"epoch": 1.9,
"learning_rate": 0.0,
"loss": 1.8187,
"step": 5740
},
{
"epoch": 1.91,
"learning_rate": 0.0,
"loss": 1.802,
"step": 5760
},
{
"epoch": 1.92,
"learning_rate": 0.0,
"loss": 1.7646,
"step": 5780
},
{
"epoch": 1.92,
"learning_rate": 0.0,
"loss": 1.7993,
"step": 5800
},
{
"epoch": 1.92,
"eval_loss": 1.970503568649292,
"eval_runtime": 11953.0956,
"eval_samples_per_second": 1.118,
"eval_steps_per_second": 0.14,
"step": 5800
},
{
"epoch": 1.93,
"learning_rate": 0.0,
"loss": 1.7962,
"step": 5820
},
{
"epoch": 1.94,
"learning_rate": 0.0,
"loss": 1.849,
"step": 5840
},
{
"epoch": 1.94,
"learning_rate": 0.0,
"loss": 1.8254,
"step": 5860
},
{
"epoch": 1.95,
"learning_rate": 0.0,
"loss": 1.8583,
"step": 5880
},
{
"epoch": 1.96,
"learning_rate": 0.0,
"loss": 1.8398,
"step": 5900
},
{
"epoch": 1.96,
"learning_rate": 0.0,
"loss": 1.7306,
"step": 5920
},
{
"epoch": 1.97,
"learning_rate": 0.0,
"loss": 1.81,
"step": 5940
},
{
"epoch": 1.98,
"learning_rate": 0.0,
"loss": 1.7762,
"step": 5960
},
{
"epoch": 1.98,
"learning_rate": 0.0,
"loss": 1.8549,
"step": 5980
},
{
"epoch": 1.99,
"learning_rate": 0.0,
"loss": 1.84,
"step": 6000
},
{
"epoch": 1.99,
"eval_loss": 1.970503568649292,
"eval_runtime": 11950.3766,
"eval_samples_per_second": 1.119,
"eval_steps_per_second": 0.14,
"step": 6000
},
{
"epoch": 2.0,
"learning_rate": 0.0,
"loss": 1.7897,
"step": 6020
},
{
"epoch": 2.0,
"learning_rate": 0.0,
"loss": 1.7844,
"step": 6040
},
{
"epoch": 2.01,
"learning_rate": 0.0,
"loss": 1.8453,
"step": 6060
},
{
"epoch": 2.02,
"learning_rate": 0.0,
"loss": 1.8268,
"step": 6080
},
{
"epoch": 2.02,
"learning_rate": 0.0,
"loss": 1.7932,
"step": 6100
},
{
"epoch": 2.03,
"learning_rate": 0.0,
"loss": 1.8005,
"step": 6120
},
{
"epoch": 2.04,
"learning_rate": 0.0,
"loss": 1.773,
"step": 6140
},
{
"epoch": 2.04,
"learning_rate": 0.0,
"loss": 1.8029,
"step": 6160
},
{
"epoch": 2.05,
"learning_rate": 0.0,
"loss": 1.8283,
"step": 6180
},
{
"epoch": 2.06,
"learning_rate": 0.0,
"loss": 1.8167,
"step": 6200
},
{
"epoch": 2.06,
"eval_loss": 1.970503568649292,
"eval_runtime": 11950.9199,
"eval_samples_per_second": 1.119,
"eval_steps_per_second": 0.14,
"step": 6200
},
{
"epoch": 2.06,
"learning_rate": 0.0,
"loss": 1.8465,
"step": 6220
},
{
"epoch": 2.07,
"learning_rate": 0.0,
"loss": 1.8747,
"step": 6240
},
{
"epoch": 2.08,
"learning_rate": 0.0,
"loss": 1.8031,
"step": 6260
},
{
"epoch": 2.08,
"learning_rate": 0.0,
"loss": 1.8366,
"step": 6280
},
{
"epoch": 2.09,
"learning_rate": 0.0,
"loss": 1.7998,
"step": 6300
},
{
"epoch": 2.1,
"learning_rate": 0.0,
"loss": 1.8143,
"step": 6320
},
{
"epoch": 2.1,
"learning_rate": 0.0,
"loss": 1.8586,
"step": 6340
},
{
"epoch": 2.11,
"learning_rate": 0.0,
"loss": 1.836,
"step": 6360
},
{
"epoch": 2.12,
"learning_rate": 0.0,
"loss": 1.863,
"step": 6380
},
{
"epoch": 2.12,
"learning_rate": 0.0,
"loss": 1.7667,
"step": 6400
},
{
"epoch": 2.12,
"eval_loss": 1.970503568649292,
"eval_runtime": 11949.7143,
"eval_samples_per_second": 1.119,
"eval_steps_per_second": 0.14,
"step": 6400
},
{
"epoch": 2.13,
"learning_rate": 0.0,
"loss": 1.8187,
"step": 6420
},
{
"epoch": 2.14,
"learning_rate": 0.0,
"loss": 1.7883,
"step": 6440
},
{
"epoch": 2.14,
"learning_rate": 0.0,
"loss": 1.9299,
"step": 6460
},
{
"epoch": 2.15,
"learning_rate": 0.0,
"loss": 1.8286,
"step": 6480
},
{
"epoch": 2.16,
"learning_rate": 0.0,
"loss": 1.8181,
"step": 6500
},
{
"epoch": 2.16,
"learning_rate": 0.0,
"loss": 1.7856,
"step": 6520
},
{
"epoch": 2.17,
"learning_rate": 0.0,
"loss": 1.7192,
"step": 6540
},
{
"epoch": 2.18,
"learning_rate": 0.0,
"loss": 1.7715,
"step": 6560
},
{
"epoch": 2.18,
"learning_rate": 0.0,
"loss": 1.8359,
"step": 6580
},
{
"epoch": 2.19,
"learning_rate": 0.0,
"loss": 1.7989,
"step": 6600
},
{
"epoch": 2.19,
"eval_loss": 1.970503568649292,
"eval_runtime": 11949.8024,
"eval_samples_per_second": 1.119,
"eval_steps_per_second": 0.14,
"step": 6600
},
{
"epoch": 2.2,
"learning_rate": 0.0,
"loss": 1.7869,
"step": 6620
},
{
"epoch": 2.2,
"learning_rate": 0.0,
"loss": 1.7855,
"step": 6640
},
{
"epoch": 2.21,
"learning_rate": 0.0,
"loss": 1.8312,
"step": 6660
},
{
"epoch": 2.22,
"learning_rate": 0.0,
"loss": 1.7717,
"step": 6680
},
{
"epoch": 2.22,
"learning_rate": 0.0,
"loss": 1.7621,
"step": 6700
},
{
"epoch": 2.23,
"learning_rate": 0.0,
"loss": 1.8031,
"step": 6720
},
{
"epoch": 2.24,
"learning_rate": 0.0,
"loss": 1.8061,
"step": 6740
},
{
"epoch": 2.24,
"learning_rate": 0.0,
"loss": 1.8063,
"step": 6760
},
{
"epoch": 2.25,
"learning_rate": 0.0,
"loss": 1.7469,
"step": 6780
},
{
"epoch": 2.26,
"learning_rate": 0.0,
"loss": 1.7543,
"step": 6800
},
{
"epoch": 2.26,
"eval_loss": 1.970503568649292,
"eval_runtime": 11954.2042,
"eval_samples_per_second": 1.118,
"eval_steps_per_second": 0.14,
"step": 6800
},
{
"epoch": 2.26,
"learning_rate": 0.0,
"loss": 1.8659,
"step": 6820
},
{
"epoch": 2.27,
"learning_rate": 0.0,
"loss": 1.7935,
"step": 6840
},
{
"epoch": 2.28,
"learning_rate": 0.0,
"loss": 1.8247,
"step": 6860
},
{
"epoch": 2.28,
"learning_rate": 0.0,
"loss": 1.8339,
"step": 6880
},
{
"epoch": 2.29,
"learning_rate": 0.0,
"loss": 1.8419,
"step": 6900
},
{
"epoch": 2.3,
"learning_rate": 0.0,
"loss": 1.7978,
"step": 6920
},
{
"epoch": 2.3,
"learning_rate": 0.0,
"loss": 1.8048,
"step": 6940
},
{
"epoch": 2.31,
"learning_rate": 0.0,
"loss": 1.8523,
"step": 6960
},
{
"epoch": 2.32,
"learning_rate": 0.0,
"loss": 1.7875,
"step": 6980
},
{
"epoch": 2.32,
"learning_rate": 0.0,
"loss": 1.8262,
"step": 7000
},
{
"epoch": 2.32,
"eval_loss": 1.970503568649292,
"eval_runtime": 11967.8262,
"eval_samples_per_second": 1.117,
"eval_steps_per_second": 0.14,
"step": 7000
},
{
"epoch": 2.33,
"learning_rate": 0.0,
"loss": 1.8661,
"step": 7020
},
{
"epoch": 2.33,
"learning_rate": 0.0,
"loss": 1.8136,
"step": 7040
},
{
"epoch": 2.34,
"learning_rate": 0.0,
"loss": 1.8066,
"step": 7060
},
{
"epoch": 2.35,
"learning_rate": 0.0,
"loss": 1.8355,
"step": 7080
},
{
"epoch": 2.35,
"learning_rate": 0.0,
"loss": 1.7598,
"step": 7100
},
{
"epoch": 2.36,
"learning_rate": 0.0,
"loss": 1.8384,
"step": 7120
},
{
"epoch": 2.37,
"learning_rate": 0.0,
"loss": 1.7768,
"step": 7140
},
{
"epoch": 2.37,
"learning_rate": 0.0,
"loss": 1.8371,
"step": 7160
},
{
"epoch": 2.38,
"learning_rate": 0.0,
"loss": 1.7989,
"step": 7180
},
{
"epoch": 2.39,
"learning_rate": 0.0,
"loss": 1.8204,
"step": 7200
},
{
"epoch": 2.39,
"eval_loss": 1.970503568649292,
"eval_runtime": 11959.9088,
"eval_samples_per_second": 1.118,
"eval_steps_per_second": 0.14,
"step": 7200
},
{
"epoch": 2.39,
"learning_rate": 0.0,
"loss": 1.8632,
"step": 7220
},
{
"epoch": 2.4,
"learning_rate": 0.0,
"loss": 1.838,
"step": 7240
},
{
"epoch": 2.41,
"learning_rate": 0.0,
"loss": 1.8492,
"step": 7260
},
{
"epoch": 2.41,
"learning_rate": 0.0,
"loss": 1.8213,
"step": 7280
},
{
"epoch": 2.42,
"learning_rate": 0.0,
"loss": 1.7367,
"step": 7300
},
{
"epoch": 2.43,
"learning_rate": 0.0,
"loss": 1.9046,
"step": 7320
},
{
"epoch": 2.43,
"learning_rate": 0.0,
"loss": 1.7799,
"step": 7340
},
{
"epoch": 2.44,
"learning_rate": 0.0,
"loss": 1.793,
"step": 7360
},
{
"epoch": 2.45,
"learning_rate": 0.0,
"loss": 1.7864,
"step": 7380
},
{
"epoch": 2.45,
"learning_rate": 0.0,
"loss": 1.8071,
"step": 7400
},
{
"epoch": 2.45,
"eval_loss": 1.970503568649292,
"eval_runtime": 11949.9374,
"eval_samples_per_second": 1.119,
"eval_steps_per_second": 0.14,
"step": 7400
},
{
"epoch": 2.46,
"learning_rate": 0.0,
"loss": 1.7708,
"step": 7420
},
{
"epoch": 2.47,
"learning_rate": 0.0,
"loss": 1.8234,
"step": 7440
},
{
"epoch": 2.47,
"learning_rate": 0.0,
"loss": 1.8214,
"step": 7460
},
{
"epoch": 2.48,
"learning_rate": 0.0,
"loss": 1.8468,
"step": 7480
},
{
"epoch": 2.49,
"learning_rate": 0.0,
"loss": 1.784,
"step": 7500
},
{
"epoch": 2.49,
"learning_rate": 0.0,
"loss": 1.8571,
"step": 7520
},
{
"epoch": 2.5,
"learning_rate": 0.0,
"loss": 1.7871,
"step": 7540
},
{
"epoch": 2.51,
"learning_rate": 0.0,
"loss": 1.7819,
"step": 7560
},
{
"epoch": 2.51,
"learning_rate": 0.0,
"loss": 1.8035,
"step": 7580
},
{
"epoch": 2.52,
"learning_rate": 0.0,
"loss": 1.801,
"step": 7600
},
{
"epoch": 2.52,
"eval_loss": 1.970503568649292,
"eval_runtime": 11949.3183,
"eval_samples_per_second": 1.119,
"eval_steps_per_second": 0.14,
"step": 7600
},
{
"epoch": 2.53,
"learning_rate": 0.0,
"loss": 1.8302,
"step": 7620
},
{
"epoch": 2.53,
"learning_rate": 0.0,
"loss": 1.8208,
"step": 7640
},
{
"epoch": 2.54,
"learning_rate": 0.0,
"loss": 1.917,
"step": 7660
},
{
"epoch": 2.55,
"learning_rate": 0.0,
"loss": 1.8184,
"step": 7680
},
{
"epoch": 2.55,
"learning_rate": 0.0,
"loss": 1.7462,
"step": 7700
},
{
"epoch": 2.56,
"learning_rate": 0.0,
"loss": 1.7699,
"step": 7720
},
{
"epoch": 2.57,
"learning_rate": 0.0,
"loss": 1.8377,
"step": 7740
},
{
"epoch": 2.57,
"learning_rate": 0.0,
"loss": 1.7713,
"step": 7760
},
{
"epoch": 2.58,
"learning_rate": 0.0,
"loss": 1.798,
"step": 7780
},
{
"epoch": 2.59,
"learning_rate": 0.0,
"loss": 1.8425,
"step": 7800
},
{
"epoch": 2.59,
"eval_loss": 1.970503568649292,
"eval_runtime": 11947.7265,
"eval_samples_per_second": 1.119,
"eval_steps_per_second": 0.14,
"step": 7800
},
{
"epoch": 2.59,
"learning_rate": 0.0,
"loss": 1.7816,
"step": 7820
},
{
"epoch": 2.6,
"learning_rate": 0.0,
"loss": 1.8193,
"step": 7840
},
{
"epoch": 2.61,
"learning_rate": 0.0,
"loss": 1.8044,
"step": 7860
},
{
"epoch": 2.61,
"learning_rate": 0.0,
"loss": 1.7937,
"step": 7880
},
{
"epoch": 2.62,
"learning_rate": 0.0,
"loss": 1.8224,
"step": 7900
},
{
"epoch": 2.63,
"learning_rate": 0.0,
"loss": 1.7937,
"step": 7920
},
{
"epoch": 2.63,
"learning_rate": 0.0,
"loss": 1.7988,
"step": 7940
},
{
"epoch": 2.64,
"learning_rate": 0.0,
"loss": 1.8622,
"step": 7960
},
{
"epoch": 2.65,
"learning_rate": 0.0,
"loss": 1.8407,
"step": 7980
},
{
"epoch": 2.65,
"learning_rate": 0.0,
"loss": 1.7578,
"step": 8000
},
{
"epoch": 2.65,
"eval_loss": 1.970503568649292,
"eval_runtime": 11948.4274,
"eval_samples_per_second": 1.119,
"eval_steps_per_second": 0.14,
"step": 8000
},
{
"epoch": 2.66,
"learning_rate": 0.0,
"loss": 1.789,
"step": 8020
},
{
"epoch": 2.67,
"learning_rate": 0.0,
"loss": 1.7939,
"step": 8040
},
{
"epoch": 2.67,
"learning_rate": 0.0,
"loss": 1.7694,
"step": 8060
},
{
"epoch": 2.68,
"learning_rate": 0.0,
"loss": 1.7917,
"step": 8080
},
{
"epoch": 2.69,
"learning_rate": 0.0,
"loss": 1.7737,
"step": 8100
},
{
"epoch": 2.69,
"learning_rate": 0.0,
"loss": 1.8049,
"step": 8120
},
{
"epoch": 2.7,
"learning_rate": 0.0,
"loss": 1.8419,
"step": 8140
},
{
"epoch": 2.71,
"learning_rate": 0.0,
"loss": 1.7835,
"step": 8160
},
{
"epoch": 2.71,
"learning_rate": 0.0,
"loss": 1.7898,
"step": 8180
},
{
"epoch": 2.72,
"learning_rate": 0.0,
"loss": 1.7798,
"step": 8200
},
{
"epoch": 2.72,
"eval_loss": 1.970503568649292,
"eval_runtime": 11959.3563,
"eval_samples_per_second": 1.118,
"eval_steps_per_second": 0.14,
"step": 8200
},
{
"epoch": 2.73,
"learning_rate": 0.0,
"loss": 1.7904,
"step": 8220
},
{
"epoch": 2.73,
"learning_rate": 0.0,
"loss": 1.8054,
"step": 8240
},
{
"epoch": 2.74,
"learning_rate": 0.0,
"loss": 1.8316,
"step": 8260
},
{
"epoch": 2.75,
"learning_rate": 0.0,
"loss": 1.8059,
"step": 8280
},
{
"epoch": 2.75,
"learning_rate": 0.0,
"loss": 1.7908,
"step": 8300
},
{
"epoch": 2.76,
"learning_rate": 0.0,
"loss": 1.8092,
"step": 8320
},
{
"epoch": 2.77,
"learning_rate": 0.0,
"loss": 1.8954,
"step": 8340
},
{
"epoch": 2.77,
"learning_rate": 0.0,
"loss": 1.835,
"step": 8360
},
{
"epoch": 2.78,
"learning_rate": 0.0,
"loss": 1.8018,
"step": 8380
},
{
"epoch": 2.79,
"learning_rate": 0.0,
"loss": 1.8474,
"step": 8400
},
{
"epoch": 2.79,
"eval_loss": 1.970503568649292,
"eval_runtime": 11978.111,
"eval_samples_per_second": 1.116,
"eval_steps_per_second": 0.14,
"step": 8400
},
{
"epoch": 2.79,
"learning_rate": 0.0,
"loss": 1.7878,
"step": 8420
},
{
"epoch": 2.8,
"learning_rate": 0.0,
"loss": 1.7629,
"step": 8440
},
{
"epoch": 2.81,
"learning_rate": 0.0,
"loss": 1.8068,
"step": 8460
},
{
"epoch": 2.81,
"learning_rate": 0.0,
"loss": 1.7907,
"step": 8480
},
{
"epoch": 2.82,
"learning_rate": 0.0,
"loss": 1.7598,
"step": 8500
},
{
"epoch": 2.83,
"learning_rate": 0.0,
"loss": 1.7964,
"step": 8520
},
{
"epoch": 2.83,
"learning_rate": 0.0,
"loss": 1.7951,
"step": 8540
},
{
"epoch": 2.84,
"learning_rate": 0.0,
"loss": 1.7962,
"step": 8560
},
{
"epoch": 2.85,
"learning_rate": 0.0,
"loss": 1.7908,
"step": 8580
},
{
"epoch": 2.85,
"learning_rate": 0.0,
"loss": 1.7525,
"step": 8600
},
{
"epoch": 2.85,
"eval_loss": 1.970503568649292,
"eval_runtime": 11977.8941,
"eval_samples_per_second": 1.116,
"eval_steps_per_second": 0.14,
"step": 8600
},
{
"epoch": 2.86,
"learning_rate": 0.0,
"loss": 1.7268,
"step": 8620
},
{
"epoch": 2.87,
"learning_rate": 0.0,
"loss": 1.7716,
"step": 8640
},
{
"epoch": 2.87,
"learning_rate": 0.0,
"loss": 1.8214,
"step": 8660
},
{
"epoch": 2.88,
"learning_rate": 0.0,
"loss": 1.8116,
"step": 8680
},
{
"epoch": 2.89,
"learning_rate": 0.0,
"loss": 1.8204,
"step": 8700
},
{
"epoch": 2.89,
"learning_rate": 0.0,
"loss": 1.7878,
"step": 8720
},
{
"epoch": 2.9,
"learning_rate": 0.0,
"loss": 1.8828,
"step": 8740
},
{
"epoch": 2.91,
"learning_rate": 0.0,
"loss": 1.8015,
"step": 8760
},
{
"epoch": 2.91,
"learning_rate": 0.0,
"loss": 1.7989,
"step": 8780
},
{
"epoch": 2.92,
"learning_rate": 0.0,
"loss": 1.7467,
"step": 8800
},
{
"epoch": 2.92,
"eval_loss": 1.970503568649292,
"eval_runtime": 11960.8065,
"eval_samples_per_second": 1.118,
"eval_steps_per_second": 0.14,
"step": 8800
}
],
"max_steps": 9045,
"num_train_epochs": 3,
"total_flos": 5.4879340491679334e+17,
"trial_name": null,
"trial_params": null
}