random-in-domain-5-demos-t5-small / trainer_state.json
Brendan King
Meta-training: t5 with 5 random in-domain demonstrations
f04b6a1
{
"best_metric": 0.9819265007972717,
"best_model_checkpoint": "./checkpoints/random-in-domain-5-demos-t5-small/checkpoint-70000",
"epoch": 8.970877518982475,
"global_step": 70000,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.03,
"learning_rate": 0.001,
"loss": 2.2565,
"step": 200
},
{
"epoch": 0.05,
"learning_rate": 0.001,
"loss": 1.5897,
"step": 400
},
{
"epoch": 0.08,
"learning_rate": 0.001,
"loss": 1.406,
"step": 600
},
{
"epoch": 0.1,
"learning_rate": 0.001,
"loss": 1.3023,
"step": 800
},
{
"epoch": 0.13,
"learning_rate": 0.001,
"loss": 1.2344,
"step": 1000
},
{
"epoch": 0.15,
"learning_rate": 0.001,
"loss": 1.1836,
"step": 1200
},
{
"epoch": 0.18,
"learning_rate": 0.001,
"loss": 1.1485,
"step": 1400
},
{
"epoch": 0.21,
"learning_rate": 0.001,
"loss": 1.1179,
"step": 1600
},
{
"epoch": 0.23,
"learning_rate": 0.001,
"loss": 1.0795,
"step": 1800
},
{
"epoch": 0.26,
"learning_rate": 0.001,
"loss": 1.0487,
"step": 2000
},
{
"epoch": 0.28,
"learning_rate": 0.001,
"loss": 1.0367,
"step": 2200
},
{
"epoch": 0.31,
"learning_rate": 0.001,
"loss": 1.0215,
"step": 2400
},
{
"epoch": 0.33,
"learning_rate": 0.001,
"loss": 1.0043,
"step": 2600
},
{
"epoch": 0.36,
"learning_rate": 0.001,
"loss": 0.979,
"step": 2800
},
{
"epoch": 0.38,
"learning_rate": 0.001,
"loss": 0.9705,
"step": 3000
},
{
"epoch": 0.41,
"learning_rate": 0.001,
"loss": 0.9737,
"step": 3200
},
{
"epoch": 0.44,
"learning_rate": 0.001,
"loss": 0.9429,
"step": 3400
},
{
"epoch": 0.46,
"learning_rate": 0.001,
"loss": 0.9413,
"step": 3600
},
{
"epoch": 0.49,
"learning_rate": 0.001,
"loss": 0.9282,
"step": 3800
},
{
"epoch": 0.51,
"learning_rate": 0.001,
"loss": 0.918,
"step": 4000
},
{
"epoch": 0.54,
"learning_rate": 0.001,
"loss": 0.9178,
"step": 4200
},
{
"epoch": 0.56,
"learning_rate": 0.001,
"loss": 0.903,
"step": 4400
},
{
"epoch": 0.59,
"learning_rate": 0.001,
"loss": 0.9024,
"step": 4600
},
{
"epoch": 0.62,
"learning_rate": 0.001,
"loss": 0.886,
"step": 4800
},
{
"epoch": 0.64,
"learning_rate": 0.001,
"loss": 0.8795,
"step": 5000
},
{
"epoch": 0.67,
"learning_rate": 0.001,
"loss": 0.8883,
"step": 5200
},
{
"epoch": 0.69,
"learning_rate": 0.001,
"loss": 0.8601,
"step": 5400
},
{
"epoch": 0.72,
"learning_rate": 0.001,
"loss": 0.8643,
"step": 5600
},
{
"epoch": 0.74,
"learning_rate": 0.001,
"loss": 0.8641,
"step": 5800
},
{
"epoch": 0.77,
"learning_rate": 0.001,
"loss": 0.8625,
"step": 6000
},
{
"epoch": 0.79,
"learning_rate": 0.001,
"loss": 0.8655,
"step": 6200
},
{
"epoch": 0.82,
"learning_rate": 0.001,
"loss": 0.8538,
"step": 6400
},
{
"epoch": 0.85,
"learning_rate": 0.001,
"loss": 0.8575,
"step": 6600
},
{
"epoch": 0.87,
"learning_rate": 0.001,
"loss": 0.8427,
"step": 6800
},
{
"epoch": 0.9,
"learning_rate": 0.001,
"loss": 0.8332,
"step": 7000
},
{
"epoch": 0.92,
"learning_rate": 0.001,
"loss": 0.8373,
"step": 7200
},
{
"epoch": 0.95,
"learning_rate": 0.001,
"loss": 0.845,
"step": 7400
},
{
"epoch": 0.97,
"learning_rate": 0.001,
"loss": 0.8271,
"step": 7600
},
{
"epoch": 1.0,
"learning_rate": 0.001,
"loss": 0.8159,
"step": 7800
},
{
"epoch": 1.03,
"learning_rate": 0.001,
"loss": 0.8027,
"step": 8000
},
{
"epoch": 1.05,
"learning_rate": 0.001,
"loss": 0.7981,
"step": 8200
},
{
"epoch": 1.08,
"learning_rate": 0.001,
"loss": 0.8025,
"step": 8400
},
{
"epoch": 1.1,
"learning_rate": 0.001,
"loss": 0.8008,
"step": 8600
},
{
"epoch": 1.13,
"learning_rate": 0.001,
"loss": 0.7951,
"step": 8800
},
{
"epoch": 1.15,
"learning_rate": 0.001,
"loss": 0.7945,
"step": 9000
},
{
"epoch": 1.18,
"learning_rate": 0.001,
"loss": 0.7824,
"step": 9200
},
{
"epoch": 1.2,
"learning_rate": 0.001,
"loss": 0.7945,
"step": 9400
},
{
"epoch": 1.23,
"learning_rate": 0.001,
"loss": 0.7939,
"step": 9600
},
{
"epoch": 1.26,
"learning_rate": 0.001,
"loss": 0.7971,
"step": 9800
},
{
"epoch": 1.28,
"learning_rate": 0.001,
"loss": 0.791,
"step": 10000
},
{
"epoch": 1.28,
"eval_loss": 1.0492665767669678,
"eval_runtime": 236.4668,
"eval_samples_per_second": 516.859,
"eval_steps_per_second": 2.021,
"step": 10000
},
{
"epoch": 1.31,
"learning_rate": 0.001,
"loss": 0.8019,
"step": 10200
},
{
"epoch": 1.33,
"learning_rate": 0.001,
"loss": 0.7752,
"step": 10400
},
{
"epoch": 1.36,
"learning_rate": 0.001,
"loss": 0.7862,
"step": 10600
},
{
"epoch": 1.38,
"learning_rate": 0.001,
"loss": 0.7835,
"step": 10800
},
{
"epoch": 1.41,
"learning_rate": 0.001,
"loss": 0.7751,
"step": 11000
},
{
"epoch": 1.44,
"learning_rate": 0.001,
"loss": 0.7747,
"step": 11200
},
{
"epoch": 1.46,
"learning_rate": 0.001,
"loss": 0.7623,
"step": 11400
},
{
"epoch": 1.49,
"learning_rate": 0.001,
"loss": 0.7898,
"step": 11600
},
{
"epoch": 1.51,
"learning_rate": 0.001,
"loss": 0.7629,
"step": 11800
},
{
"epoch": 1.54,
"learning_rate": 0.001,
"loss": 0.7601,
"step": 12000
},
{
"epoch": 1.56,
"learning_rate": 0.001,
"loss": 0.7698,
"step": 12200
},
{
"epoch": 1.59,
"learning_rate": 0.001,
"loss": 0.7664,
"step": 12400
},
{
"epoch": 1.61,
"learning_rate": 0.001,
"loss": 0.7616,
"step": 12600
},
{
"epoch": 1.64,
"learning_rate": 0.001,
"loss": 0.764,
"step": 12800
},
{
"epoch": 1.67,
"learning_rate": 0.001,
"loss": 0.774,
"step": 13000
},
{
"epoch": 1.69,
"learning_rate": 0.001,
"loss": 0.7524,
"step": 13200
},
{
"epoch": 1.72,
"learning_rate": 0.001,
"loss": 0.7637,
"step": 13400
},
{
"epoch": 1.74,
"learning_rate": 0.001,
"loss": 0.7615,
"step": 13600
},
{
"epoch": 1.77,
"learning_rate": 0.001,
"loss": 0.7702,
"step": 13800
},
{
"epoch": 1.79,
"learning_rate": 0.001,
"loss": 0.7453,
"step": 14000
},
{
"epoch": 1.82,
"learning_rate": 0.001,
"loss": 0.7369,
"step": 14200
},
{
"epoch": 1.85,
"learning_rate": 0.001,
"loss": 0.7499,
"step": 14400
},
{
"epoch": 1.87,
"learning_rate": 0.001,
"loss": 0.7491,
"step": 14600
},
{
"epoch": 1.9,
"learning_rate": 0.001,
"loss": 0.7607,
"step": 14800
},
{
"epoch": 1.92,
"learning_rate": 0.001,
"loss": 0.7417,
"step": 15000
},
{
"epoch": 1.95,
"learning_rate": 0.001,
"loss": 0.7312,
"step": 15200
},
{
"epoch": 1.97,
"learning_rate": 0.001,
"loss": 0.7464,
"step": 15400
},
{
"epoch": 2.0,
"learning_rate": 0.001,
"loss": 0.7555,
"step": 15600
},
{
"epoch": 2.02,
"learning_rate": 0.001,
"loss": 0.7236,
"step": 15800
},
{
"epoch": 2.05,
"learning_rate": 0.001,
"loss": 0.716,
"step": 16000
},
{
"epoch": 2.08,
"learning_rate": 0.001,
"loss": 0.7199,
"step": 16200
},
{
"epoch": 2.1,
"learning_rate": 0.001,
"loss": 0.7237,
"step": 16400
},
{
"epoch": 2.13,
"learning_rate": 0.001,
"loss": 0.7293,
"step": 16600
},
{
"epoch": 2.15,
"learning_rate": 0.001,
"loss": 0.725,
"step": 16800
},
{
"epoch": 2.18,
"learning_rate": 0.001,
"loss": 0.7262,
"step": 17000
},
{
"epoch": 2.2,
"learning_rate": 0.001,
"loss": 0.7129,
"step": 17200
},
{
"epoch": 2.23,
"learning_rate": 0.001,
"loss": 0.7205,
"step": 17400
},
{
"epoch": 2.26,
"learning_rate": 0.001,
"loss": 0.7145,
"step": 17600
},
{
"epoch": 2.28,
"learning_rate": 0.001,
"loss": 0.727,
"step": 17800
},
{
"epoch": 2.31,
"learning_rate": 0.001,
"loss": 0.7261,
"step": 18000
},
{
"epoch": 2.33,
"learning_rate": 0.001,
"loss": 0.7226,
"step": 18200
},
{
"epoch": 2.36,
"learning_rate": 0.001,
"loss": 0.7262,
"step": 18400
},
{
"epoch": 2.38,
"learning_rate": 0.001,
"loss": 0.7224,
"step": 18600
},
{
"epoch": 2.41,
"learning_rate": 0.001,
"loss": 0.7123,
"step": 18800
},
{
"epoch": 2.43,
"learning_rate": 0.001,
"loss": 0.7151,
"step": 19000
},
{
"epoch": 2.46,
"learning_rate": 0.001,
"loss": 0.7059,
"step": 19200
},
{
"epoch": 2.49,
"learning_rate": 0.001,
"loss": 0.7125,
"step": 19400
},
{
"epoch": 2.51,
"learning_rate": 0.001,
"loss": 0.7113,
"step": 19600
},
{
"epoch": 2.54,
"learning_rate": 0.001,
"loss": 0.7083,
"step": 19800
},
{
"epoch": 2.56,
"learning_rate": 0.001,
"loss": 0.7054,
"step": 20000
},
{
"epoch": 2.56,
"eval_loss": 1.007745623588562,
"eval_runtime": 236.2858,
"eval_samples_per_second": 517.255,
"eval_steps_per_second": 2.023,
"step": 20000
},
{
"epoch": 2.59,
"learning_rate": 0.001,
"loss": 0.6979,
"step": 20200
},
{
"epoch": 2.61,
"learning_rate": 0.001,
"loss": 0.7047,
"step": 20400
},
{
"epoch": 2.64,
"learning_rate": 0.001,
"loss": 0.7163,
"step": 20600
},
{
"epoch": 2.67,
"learning_rate": 0.001,
"loss": 0.7064,
"step": 20800
},
{
"epoch": 2.69,
"learning_rate": 0.001,
"loss": 0.7087,
"step": 21000
},
{
"epoch": 2.72,
"learning_rate": 0.001,
"loss": 0.7112,
"step": 21200
},
{
"epoch": 2.74,
"learning_rate": 0.001,
"loss": 0.7174,
"step": 21400
},
{
"epoch": 2.77,
"learning_rate": 0.001,
"loss": 0.7056,
"step": 21600
},
{
"epoch": 2.79,
"learning_rate": 0.001,
"loss": 0.7008,
"step": 21800
},
{
"epoch": 2.82,
"learning_rate": 0.001,
"loss": 0.7001,
"step": 22000
},
{
"epoch": 2.85,
"learning_rate": 0.001,
"loss": 0.7014,
"step": 22200
},
{
"epoch": 2.87,
"learning_rate": 0.001,
"loss": 0.7007,
"step": 22400
},
{
"epoch": 2.9,
"learning_rate": 0.001,
"loss": 0.7051,
"step": 22600
},
{
"epoch": 2.92,
"learning_rate": 0.001,
"loss": 0.7069,
"step": 22800
},
{
"epoch": 2.95,
"learning_rate": 0.001,
"loss": 0.696,
"step": 23000
},
{
"epoch": 2.97,
"learning_rate": 0.001,
"loss": 0.6893,
"step": 23200
},
{
"epoch": 3.0,
"learning_rate": 0.001,
"loss": 0.6865,
"step": 23400
},
{
"epoch": 3.02,
"learning_rate": 0.001,
"loss": 0.6848,
"step": 23600
},
{
"epoch": 3.05,
"learning_rate": 0.001,
"loss": 0.6707,
"step": 23800
},
{
"epoch": 3.08,
"learning_rate": 0.001,
"loss": 0.6826,
"step": 24000
},
{
"epoch": 3.1,
"learning_rate": 0.001,
"loss": 0.6754,
"step": 24200
},
{
"epoch": 3.13,
"learning_rate": 0.001,
"loss": 0.6722,
"step": 24400
},
{
"epoch": 3.15,
"learning_rate": 0.001,
"loss": 0.6775,
"step": 24600
},
{
"epoch": 3.18,
"learning_rate": 0.001,
"loss": 0.6796,
"step": 24800
},
{
"epoch": 3.2,
"learning_rate": 0.001,
"loss": 0.6826,
"step": 25000
},
{
"epoch": 3.23,
"learning_rate": 0.001,
"loss": 0.6778,
"step": 25200
},
{
"epoch": 3.26,
"learning_rate": 0.001,
"loss": 0.6922,
"step": 25400
},
{
"epoch": 3.28,
"learning_rate": 0.001,
"loss": 0.6706,
"step": 25600
},
{
"epoch": 3.31,
"learning_rate": 0.001,
"loss": 0.6721,
"step": 25800
},
{
"epoch": 3.33,
"learning_rate": 0.001,
"loss": 0.6737,
"step": 26000
},
{
"epoch": 3.36,
"learning_rate": 0.001,
"loss": 0.7046,
"step": 26200
},
{
"epoch": 3.38,
"learning_rate": 0.001,
"loss": 0.6754,
"step": 26400
},
{
"epoch": 3.41,
"learning_rate": 0.001,
"loss": 0.6794,
"step": 26600
},
{
"epoch": 3.43,
"learning_rate": 0.001,
"loss": 0.684,
"step": 26800
},
{
"epoch": 3.46,
"learning_rate": 0.001,
"loss": 0.6776,
"step": 27000
},
{
"epoch": 3.49,
"learning_rate": 0.001,
"loss": 0.6826,
"step": 27200
},
{
"epoch": 3.51,
"learning_rate": 0.001,
"loss": 0.6877,
"step": 27400
},
{
"epoch": 3.54,
"learning_rate": 0.001,
"loss": 0.6773,
"step": 27600
},
{
"epoch": 3.56,
"learning_rate": 0.001,
"loss": 0.6731,
"step": 27800
},
{
"epoch": 3.59,
"learning_rate": 0.001,
"loss": 0.6704,
"step": 28000
},
{
"epoch": 3.61,
"learning_rate": 0.001,
"loss": 0.681,
"step": 28200
},
{
"epoch": 3.64,
"learning_rate": 0.001,
"loss": 0.6745,
"step": 28400
},
{
"epoch": 3.67,
"learning_rate": 0.001,
"loss": 0.6734,
"step": 28600
},
{
"epoch": 3.69,
"learning_rate": 0.001,
"loss": 0.6759,
"step": 28800
},
{
"epoch": 3.72,
"learning_rate": 0.001,
"loss": 0.6729,
"step": 29000
},
{
"epoch": 3.74,
"learning_rate": 0.001,
"loss": 0.6727,
"step": 29200
},
{
"epoch": 3.77,
"learning_rate": 0.001,
"loss": 0.6734,
"step": 29400
},
{
"epoch": 3.79,
"learning_rate": 0.001,
"loss": 0.6747,
"step": 29600
},
{
"epoch": 3.82,
"learning_rate": 0.001,
"loss": 0.6739,
"step": 29800
},
{
"epoch": 3.84,
"learning_rate": 0.001,
"loss": 0.6564,
"step": 30000
},
{
"epoch": 3.84,
"eval_loss": 0.9836647510528564,
"eval_runtime": 236.2546,
"eval_samples_per_second": 517.323,
"eval_steps_per_second": 2.023,
"step": 30000
},
{
"epoch": 3.87,
"learning_rate": 0.001,
"loss": 0.6748,
"step": 30200
},
{
"epoch": 3.9,
"learning_rate": 0.001,
"loss": 0.6582,
"step": 30400
},
{
"epoch": 3.92,
"learning_rate": 0.001,
"loss": 0.6526,
"step": 30600
},
{
"epoch": 3.95,
"learning_rate": 0.001,
"loss": 0.6587,
"step": 30800
},
{
"epoch": 3.97,
"learning_rate": 0.001,
"loss": 0.6621,
"step": 31000
},
{
"epoch": 4.0,
"learning_rate": 0.001,
"loss": 0.6829,
"step": 31200
},
{
"epoch": 4.02,
"learning_rate": 0.001,
"loss": 0.6448,
"step": 31400
},
{
"epoch": 4.05,
"learning_rate": 0.001,
"loss": 0.6391,
"step": 31600
},
{
"epoch": 4.08,
"learning_rate": 0.001,
"loss": 0.6596,
"step": 31800
},
{
"epoch": 4.1,
"learning_rate": 0.001,
"loss": 0.6503,
"step": 32000
},
{
"epoch": 4.13,
"learning_rate": 0.001,
"loss": 0.6484,
"step": 32200
},
{
"epoch": 4.15,
"learning_rate": 0.001,
"loss": 0.6564,
"step": 32400
},
{
"epoch": 4.18,
"learning_rate": 0.001,
"loss": 0.655,
"step": 32600
},
{
"epoch": 4.2,
"learning_rate": 0.001,
"loss": 0.6421,
"step": 32800
},
{
"epoch": 4.23,
"learning_rate": 0.001,
"loss": 0.6537,
"step": 33000
},
{
"epoch": 4.25,
"learning_rate": 0.001,
"loss": 0.6459,
"step": 33200
},
{
"epoch": 4.28,
"learning_rate": 0.001,
"loss": 0.6525,
"step": 33400
},
{
"epoch": 4.31,
"learning_rate": 0.001,
"loss": 0.6523,
"step": 33600
},
{
"epoch": 4.33,
"learning_rate": 0.001,
"loss": 0.6496,
"step": 33800
},
{
"epoch": 4.36,
"learning_rate": 0.001,
"loss": 0.6477,
"step": 34000
},
{
"epoch": 4.38,
"learning_rate": 0.001,
"loss": 0.6455,
"step": 34200
},
{
"epoch": 4.41,
"learning_rate": 0.001,
"loss": 0.6413,
"step": 34400
},
{
"epoch": 4.43,
"learning_rate": 0.001,
"loss": 0.6414,
"step": 34600
},
{
"epoch": 4.46,
"learning_rate": 0.001,
"loss": 0.6552,
"step": 34800
},
{
"epoch": 4.49,
"learning_rate": 0.001,
"loss": 0.6496,
"step": 35000
},
{
"epoch": 4.51,
"learning_rate": 0.001,
"loss": 0.6495,
"step": 35200
},
{
"epoch": 4.54,
"learning_rate": 0.001,
"loss": 0.6495,
"step": 35400
},
{
"epoch": 4.56,
"learning_rate": 0.001,
"loss": 0.6468,
"step": 35600
},
{
"epoch": 4.59,
"learning_rate": 0.001,
"loss": 0.6583,
"step": 35800
},
{
"epoch": 4.61,
"learning_rate": 0.001,
"loss": 0.66,
"step": 36000
},
{
"epoch": 4.64,
"learning_rate": 0.001,
"loss": 0.6555,
"step": 36200
},
{
"epoch": 4.66,
"learning_rate": 0.001,
"loss": 0.6489,
"step": 36400
},
{
"epoch": 4.69,
"learning_rate": 0.001,
"loss": 0.6361,
"step": 36600
},
{
"epoch": 4.72,
"learning_rate": 0.001,
"loss": 0.6493,
"step": 36800
},
{
"epoch": 4.74,
"learning_rate": 0.001,
"loss": 0.6402,
"step": 37000
},
{
"epoch": 4.77,
"learning_rate": 0.001,
"loss": 0.647,
"step": 37200
},
{
"epoch": 4.79,
"learning_rate": 0.001,
"loss": 0.6533,
"step": 37400
},
{
"epoch": 4.82,
"learning_rate": 0.001,
"loss": 0.6426,
"step": 37600
},
{
"epoch": 4.84,
"learning_rate": 0.001,
"loss": 0.6478,
"step": 37800
},
{
"epoch": 4.87,
"learning_rate": 0.001,
"loss": 0.6441,
"step": 38000
},
{
"epoch": 4.9,
"learning_rate": 0.001,
"loss": 0.6519,
"step": 38200
},
{
"epoch": 4.92,
"learning_rate": 0.001,
"loss": 0.6358,
"step": 38400
},
{
"epoch": 4.95,
"learning_rate": 0.001,
"loss": 0.6546,
"step": 38600
},
{
"epoch": 4.97,
"learning_rate": 0.001,
"loss": 0.6545,
"step": 38800
},
{
"epoch": 5.0,
"learning_rate": 0.001,
"loss": 0.6578,
"step": 39000
},
{
"epoch": 5.02,
"learning_rate": 0.001,
"loss": 0.6233,
"step": 39200
},
{
"epoch": 5.05,
"learning_rate": 0.001,
"loss": 0.6281,
"step": 39400
},
{
"epoch": 5.07,
"learning_rate": 0.001,
"loss": 0.6272,
"step": 39600
},
{
"epoch": 5.1,
"learning_rate": 0.001,
"loss": 0.6242,
"step": 39800
},
{
"epoch": 5.13,
"learning_rate": 0.001,
"loss": 0.6112,
"step": 40000
},
{
"epoch": 5.13,
"eval_loss": 0.9964196085929871,
"eval_runtime": 236.0055,
"eval_samples_per_second": 517.869,
"eval_steps_per_second": 2.025,
"step": 40000
},
{
"epoch": 5.15,
"learning_rate": 0.001,
"loss": 0.6222,
"step": 40200
},
{
"epoch": 5.18,
"learning_rate": 0.001,
"loss": 0.6332,
"step": 40400
},
{
"epoch": 5.2,
"learning_rate": 0.001,
"loss": 0.6206,
"step": 40600
},
{
"epoch": 5.23,
"learning_rate": 0.001,
"loss": 0.6279,
"step": 40800
},
{
"epoch": 5.25,
"learning_rate": 0.001,
"loss": 0.6191,
"step": 41000
},
{
"epoch": 5.28,
"learning_rate": 0.001,
"loss": 0.6262,
"step": 41200
},
{
"epoch": 5.31,
"learning_rate": 0.001,
"loss": 0.6386,
"step": 41400
},
{
"epoch": 5.33,
"learning_rate": 0.001,
"loss": 0.6321,
"step": 41600
},
{
"epoch": 5.36,
"learning_rate": 0.001,
"loss": 0.638,
"step": 41800
},
{
"epoch": 5.38,
"learning_rate": 0.001,
"loss": 0.626,
"step": 42000
},
{
"epoch": 5.41,
"learning_rate": 0.001,
"loss": 0.6298,
"step": 42200
},
{
"epoch": 5.43,
"learning_rate": 0.001,
"loss": 0.6148,
"step": 42400
},
{
"epoch": 5.46,
"learning_rate": 0.001,
"loss": 0.6225,
"step": 42600
},
{
"epoch": 5.49,
"learning_rate": 0.001,
"loss": 0.6331,
"step": 42800
},
{
"epoch": 5.51,
"learning_rate": 0.001,
"loss": 0.6347,
"step": 43000
},
{
"epoch": 5.54,
"learning_rate": 0.001,
"loss": 0.6331,
"step": 43200
},
{
"epoch": 5.56,
"learning_rate": 0.001,
"loss": 0.6274,
"step": 43400
},
{
"epoch": 5.59,
"learning_rate": 0.001,
"loss": 0.6388,
"step": 43600
},
{
"epoch": 5.61,
"learning_rate": 0.001,
"loss": 0.6262,
"step": 43800
},
{
"epoch": 5.64,
"learning_rate": 0.001,
"loss": 0.6245,
"step": 44000
},
{
"epoch": 5.66,
"learning_rate": 0.001,
"loss": 0.6317,
"step": 44200
},
{
"epoch": 5.69,
"learning_rate": 0.001,
"loss": 0.6323,
"step": 44400
},
{
"epoch": 5.72,
"learning_rate": 0.001,
"loss": 0.6275,
"step": 44600
},
{
"epoch": 5.74,
"learning_rate": 0.001,
"loss": 0.6284,
"step": 44800
},
{
"epoch": 5.77,
"learning_rate": 0.001,
"loss": 0.6301,
"step": 45000
},
{
"epoch": 5.79,
"learning_rate": 0.001,
"loss": 0.6453,
"step": 45200
},
{
"epoch": 5.82,
"learning_rate": 0.001,
"loss": 0.6244,
"step": 45400
},
{
"epoch": 5.84,
"learning_rate": 0.001,
"loss": 0.6271,
"step": 45600
},
{
"epoch": 5.87,
"learning_rate": 0.001,
"loss": 0.6275,
"step": 45800
},
{
"epoch": 5.9,
"learning_rate": 0.001,
"loss": 0.6483,
"step": 46000
},
{
"epoch": 5.92,
"learning_rate": 0.001,
"loss": 0.6143,
"step": 46200
},
{
"epoch": 5.95,
"learning_rate": 0.001,
"loss": 0.6272,
"step": 46400
},
{
"epoch": 5.97,
"learning_rate": 0.001,
"loss": 0.6425,
"step": 46600
},
{
"epoch": 6.0,
"learning_rate": 0.001,
"loss": 0.6243,
"step": 46800
},
{
"epoch": 6.02,
"learning_rate": 0.001,
"loss": 0.6014,
"step": 47000
},
{
"epoch": 6.05,
"learning_rate": 0.001,
"loss": 0.6004,
"step": 47200
},
{
"epoch": 6.07,
"learning_rate": 0.001,
"loss": 0.611,
"step": 47400
},
{
"epoch": 6.1,
"learning_rate": 0.001,
"loss": 0.6111,
"step": 47600
},
{
"epoch": 6.13,
"learning_rate": 0.001,
"loss": 0.6101,
"step": 47800
},
{
"epoch": 6.15,
"learning_rate": 0.001,
"loss": 0.6154,
"step": 48000
},
{
"epoch": 6.18,
"learning_rate": 0.001,
"loss": 0.6094,
"step": 48200
},
{
"epoch": 6.2,
"learning_rate": 0.001,
"loss": 0.6082,
"step": 48400
},
{
"epoch": 6.23,
"learning_rate": 0.001,
"loss": 0.6013,
"step": 48600
},
{
"epoch": 6.25,
"learning_rate": 0.001,
"loss": 0.6148,
"step": 48800
},
{
"epoch": 6.28,
"learning_rate": 0.001,
"loss": 0.6049,
"step": 49000
},
{
"epoch": 6.31,
"learning_rate": 0.001,
"loss": 0.6089,
"step": 49200
},
{
"epoch": 6.33,
"learning_rate": 0.001,
"loss": 0.61,
"step": 49400
},
{
"epoch": 6.36,
"learning_rate": 0.001,
"loss": 0.6056,
"step": 49600
},
{
"epoch": 6.38,
"learning_rate": 0.001,
"loss": 0.6138,
"step": 49800
},
{
"epoch": 6.41,
"learning_rate": 0.001,
"loss": 0.6212,
"step": 50000
},
{
"epoch": 6.41,
"eval_loss": 0.9890182614326477,
"eval_runtime": 236.1033,
"eval_samples_per_second": 517.655,
"eval_steps_per_second": 2.025,
"step": 50000
},
{
"epoch": 6.43,
"learning_rate": 0.001,
"loss": 0.612,
"step": 50200
},
{
"epoch": 6.46,
"learning_rate": 0.001,
"loss": 0.6111,
"step": 50400
},
{
"epoch": 6.48,
"learning_rate": 0.001,
"loss": 0.6146,
"step": 50600
},
{
"epoch": 6.51,
"learning_rate": 0.001,
"loss": 0.615,
"step": 50800
},
{
"epoch": 6.54,
"learning_rate": 0.001,
"loss": 0.6128,
"step": 51000
},
{
"epoch": 6.56,
"learning_rate": 0.001,
"loss": 0.6183,
"step": 51200
},
{
"epoch": 6.59,
"learning_rate": 0.001,
"loss": 0.6115,
"step": 51400
},
{
"epoch": 6.61,
"learning_rate": 0.001,
"loss": 0.6068,
"step": 51600
},
{
"epoch": 6.64,
"learning_rate": 0.001,
"loss": 0.6107,
"step": 51800
},
{
"epoch": 6.66,
"learning_rate": 0.001,
"loss": 0.6256,
"step": 52000
},
{
"epoch": 6.69,
"learning_rate": 0.001,
"loss": 0.6149,
"step": 52200
},
{
"epoch": 6.72,
"learning_rate": 0.001,
"loss": 0.606,
"step": 52400
},
{
"epoch": 6.74,
"learning_rate": 0.001,
"loss": 0.6203,
"step": 52600
},
{
"epoch": 6.77,
"learning_rate": 0.001,
"loss": 0.6117,
"step": 52800
},
{
"epoch": 6.79,
"learning_rate": 0.001,
"loss": 0.6079,
"step": 53000
},
{
"epoch": 6.82,
"learning_rate": 0.001,
"loss": 0.6164,
"step": 53200
},
{
"epoch": 6.84,
"learning_rate": 0.001,
"loss": 0.6162,
"step": 53400
},
{
"epoch": 6.87,
"learning_rate": 0.001,
"loss": 0.6094,
"step": 53600
},
{
"epoch": 6.89,
"learning_rate": 0.001,
"loss": 0.6134,
"step": 53800
},
{
"epoch": 6.92,
"learning_rate": 0.001,
"loss": 0.617,
"step": 54000
},
{
"epoch": 6.95,
"learning_rate": 0.001,
"loss": 0.6165,
"step": 54200
},
{
"epoch": 6.97,
"learning_rate": 0.001,
"loss": 0.6127,
"step": 54400
},
{
"epoch": 7.0,
"learning_rate": 0.001,
"loss": 0.6127,
"step": 54600
},
{
"epoch": 7.02,
"learning_rate": 0.001,
"loss": 0.593,
"step": 54800
},
{
"epoch": 7.05,
"learning_rate": 0.001,
"loss": 0.5891,
"step": 55000
},
{
"epoch": 7.07,
"learning_rate": 0.001,
"loss": 0.6004,
"step": 55200
},
{
"epoch": 7.1,
"learning_rate": 0.001,
"loss": 0.5824,
"step": 55400
},
{
"epoch": 7.13,
"learning_rate": 0.001,
"loss": 0.5949,
"step": 55600
},
{
"epoch": 7.15,
"learning_rate": 0.001,
"loss": 0.5931,
"step": 55800
},
{
"epoch": 7.18,
"learning_rate": 0.001,
"loss": 0.5861,
"step": 56000
},
{
"epoch": 7.2,
"learning_rate": 0.001,
"loss": 0.6035,
"step": 56200
},
{
"epoch": 7.23,
"learning_rate": 0.001,
"loss": 0.5859,
"step": 56400
},
{
"epoch": 7.25,
"learning_rate": 0.001,
"loss": 0.5953,
"step": 56600
},
{
"epoch": 7.28,
"learning_rate": 0.001,
"loss": 0.6032,
"step": 56800
},
{
"epoch": 7.3,
"learning_rate": 0.001,
"loss": 0.5945,
"step": 57000
},
{
"epoch": 7.33,
"learning_rate": 0.001,
"loss": 0.598,
"step": 57200
},
{
"epoch": 7.36,
"learning_rate": 0.001,
"loss": 0.5981,
"step": 57400
},
{
"epoch": 7.38,
"learning_rate": 0.001,
"loss": 0.6034,
"step": 57600
},
{
"epoch": 7.41,
"learning_rate": 0.001,
"loss": 0.6075,
"step": 57800
},
{
"epoch": 7.43,
"learning_rate": 0.001,
"loss": 0.6065,
"step": 58000
},
{
"epoch": 7.46,
"learning_rate": 0.001,
"loss": 0.5972,
"step": 58200
},
{
"epoch": 7.48,
"learning_rate": 0.001,
"loss": 0.6048,
"step": 58400
},
{
"epoch": 7.51,
"learning_rate": 0.001,
"loss": 0.5977,
"step": 58600
},
{
"epoch": 7.54,
"learning_rate": 0.001,
"loss": 0.5998,
"step": 58800
},
{
"epoch": 7.56,
"learning_rate": 0.001,
"loss": 0.5943,
"step": 59000
},
{
"epoch": 7.59,
"learning_rate": 0.001,
"loss": 0.5883,
"step": 59200
},
{
"epoch": 7.61,
"learning_rate": 0.001,
"loss": 0.5999,
"step": 59400
},
{
"epoch": 7.64,
"learning_rate": 0.001,
"loss": 0.5957,
"step": 59600
},
{
"epoch": 7.66,
"learning_rate": 0.001,
"loss": 0.6103,
"step": 59800
},
{
"epoch": 7.69,
"learning_rate": 0.001,
"loss": 0.6078,
"step": 60000
},
{
"epoch": 7.69,
"eval_loss": 0.9891012907028198,
"eval_runtime": 236.1606,
"eval_samples_per_second": 517.529,
"eval_steps_per_second": 2.024,
"step": 60000
},
{
"epoch": 7.71,
"learning_rate": 0.001,
"loss": 0.5903,
"step": 60200
},
{
"epoch": 7.74,
"learning_rate": 0.001,
"loss": 0.6007,
"step": 60400
},
{
"epoch": 7.77,
"learning_rate": 0.001,
"loss": 0.5973,
"step": 60600
},
{
"epoch": 7.79,
"learning_rate": 0.001,
"loss": 0.596,
"step": 60800
},
{
"epoch": 7.82,
"learning_rate": 0.001,
"loss": 0.597,
"step": 61000
},
{
"epoch": 7.84,
"learning_rate": 0.001,
"loss": 0.6018,
"step": 61200
},
{
"epoch": 7.87,
"learning_rate": 0.001,
"loss": 0.6024,
"step": 61400
},
{
"epoch": 7.89,
"learning_rate": 0.001,
"loss": 0.6011,
"step": 61600
},
{
"epoch": 7.92,
"learning_rate": 0.001,
"loss": 0.5883,
"step": 61800
},
{
"epoch": 7.95,
"learning_rate": 0.001,
"loss": 0.6006,
"step": 62000
},
{
"epoch": 7.97,
"learning_rate": 0.001,
"loss": 0.6004,
"step": 62200
},
{
"epoch": 8.0,
"learning_rate": 0.001,
"loss": 0.6083,
"step": 62400
},
{
"epoch": 8.02,
"learning_rate": 0.001,
"loss": 0.5844,
"step": 62600
},
{
"epoch": 8.05,
"learning_rate": 0.001,
"loss": 0.5751,
"step": 62800
},
{
"epoch": 8.07,
"learning_rate": 0.001,
"loss": 0.5716,
"step": 63000
},
{
"epoch": 8.1,
"learning_rate": 0.001,
"loss": 0.5748,
"step": 63200
},
{
"epoch": 8.13,
"learning_rate": 0.001,
"loss": 0.5752,
"step": 63400
},
{
"epoch": 8.15,
"learning_rate": 0.001,
"loss": 0.5697,
"step": 63600
},
{
"epoch": 8.18,
"learning_rate": 0.001,
"loss": 0.5751,
"step": 63800
},
{
"epoch": 8.2,
"learning_rate": 0.001,
"loss": 0.5821,
"step": 64000
},
{
"epoch": 8.23,
"learning_rate": 0.001,
"loss": 0.578,
"step": 64200
},
{
"epoch": 8.25,
"learning_rate": 0.001,
"loss": 0.5768,
"step": 64400
},
{
"epoch": 8.28,
"learning_rate": 0.001,
"loss": 0.5807,
"step": 64600
},
{
"epoch": 8.3,
"learning_rate": 0.001,
"loss": 0.5872,
"step": 64800
},
{
"epoch": 8.33,
"learning_rate": 0.001,
"loss": 0.5802,
"step": 65000
},
{
"epoch": 8.36,
"learning_rate": 0.001,
"loss": 0.5883,
"step": 65200
},
{
"epoch": 8.38,
"learning_rate": 0.001,
"loss": 0.5792,
"step": 65400
},
{
"epoch": 8.41,
"learning_rate": 0.001,
"loss": 0.5888,
"step": 65600
},
{
"epoch": 8.43,
"learning_rate": 0.001,
"loss": 0.6033,
"step": 65800
},
{
"epoch": 8.46,
"learning_rate": 0.001,
"loss": 0.5967,
"step": 66000
},
{
"epoch": 8.48,
"learning_rate": 0.001,
"loss": 0.5909,
"step": 66200
},
{
"epoch": 8.51,
"learning_rate": 0.001,
"loss": 0.5823,
"step": 66400
},
{
"epoch": 8.54,
"learning_rate": 0.001,
"loss": 0.5883,
"step": 66600
},
{
"epoch": 8.56,
"learning_rate": 0.001,
"loss": 0.5862,
"step": 66800
},
{
"epoch": 8.59,
"learning_rate": 0.001,
"loss": 0.5924,
"step": 67000
},
{
"epoch": 8.61,
"learning_rate": 0.001,
"loss": 0.5902,
"step": 67200
},
{
"epoch": 8.64,
"learning_rate": 0.001,
"loss": 0.5841,
"step": 67400
},
{
"epoch": 8.66,
"learning_rate": 0.001,
"loss": 0.5919,
"step": 67600
},
{
"epoch": 8.69,
"learning_rate": 0.001,
"loss": 0.5889,
"step": 67800
},
{
"epoch": 8.71,
"learning_rate": 0.001,
"loss": 0.5913,
"step": 68000
},
{
"epoch": 8.74,
"learning_rate": 0.001,
"loss": 0.585,
"step": 68200
},
{
"epoch": 8.77,
"learning_rate": 0.001,
"loss": 0.5887,
"step": 68400
},
{
"epoch": 8.79,
"learning_rate": 0.001,
"loss": 0.5931,
"step": 68600
},
{
"epoch": 8.82,
"learning_rate": 0.001,
"loss": 0.5799,
"step": 68800
},
{
"epoch": 8.84,
"learning_rate": 0.001,
"loss": 0.585,
"step": 69000
},
{
"epoch": 8.87,
"learning_rate": 0.001,
"loss": 0.5765,
"step": 69200
},
{
"epoch": 8.89,
"learning_rate": 0.001,
"loss": 0.5827,
"step": 69400
},
{
"epoch": 8.92,
"learning_rate": 0.001,
"loss": 0.5875,
"step": 69600
},
{
"epoch": 8.95,
"learning_rate": 0.001,
"loss": 0.5909,
"step": 69800
},
{
"epoch": 8.97,
"learning_rate": 0.001,
"loss": 0.6049,
"step": 70000
},
{
"epoch": 8.97,
"eval_loss": 0.9819265007972717,
"eval_runtime": 236.1037,
"eval_samples_per_second": 517.654,
"eval_steps_per_second": 2.025,
"step": 70000
}
],
"max_steps": 78030,
"num_train_epochs": 10,
"total_flos": 1.0371070946901688e+18,
"trial_name": null,
"trial_params": null
}