meta-baseline-t5-small / trainer_state.json
Brendan King
using new run, 70k checkpoint (should be the same but this guarantees)
35243e0
{
"best_metric": 0.9769449234008789,
"best_model_checkpoint": "./checkpoints/meta-baseline-t5-small/checkpoint-70000",
"epoch": 8.968516798513916,
"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": 2.3828,
"step": 200
},
{
"epoch": 0.05,
"learning_rate": 0.001,
"loss": 1.6006,
"step": 400
},
{
"epoch": 0.08,
"learning_rate": 0.001,
"loss": 1.4131,
"step": 600
},
{
"epoch": 0.1,
"learning_rate": 0.001,
"loss": 1.3124,
"step": 800
},
{
"epoch": 0.13,
"learning_rate": 0.001,
"loss": 1.2434,
"step": 1000
},
{
"epoch": 0.15,
"learning_rate": 0.001,
"loss": 1.1786,
"step": 1200
},
{
"epoch": 0.18,
"learning_rate": 0.001,
"loss": 1.1193,
"step": 1400
},
{
"epoch": 0.2,
"learning_rate": 0.001,
"loss": 1.1045,
"step": 1600
},
{
"epoch": 0.23,
"learning_rate": 0.001,
"loss": 1.0873,
"step": 1800
},
{
"epoch": 0.26,
"learning_rate": 0.001,
"loss": 1.0495,
"step": 2000
},
{
"epoch": 0.28,
"learning_rate": 0.001,
"loss": 1.0346,
"step": 2200
},
{
"epoch": 0.31,
"learning_rate": 0.001,
"loss": 1.0245,
"step": 2400
},
{
"epoch": 0.33,
"learning_rate": 0.001,
"loss": 0.9973,
"step": 2600
},
{
"epoch": 0.36,
"learning_rate": 0.001,
"loss": 0.9785,
"step": 2800
},
{
"epoch": 0.38,
"learning_rate": 0.001,
"loss": 0.9696,
"step": 3000
},
{
"epoch": 0.41,
"learning_rate": 0.001,
"loss": 0.9684,
"step": 3200
},
{
"epoch": 0.44,
"learning_rate": 0.001,
"loss": 0.9425,
"step": 3400
},
{
"epoch": 0.46,
"learning_rate": 0.001,
"loss": 0.9437,
"step": 3600
},
{
"epoch": 0.49,
"learning_rate": 0.001,
"loss": 0.9376,
"step": 3800
},
{
"epoch": 0.51,
"learning_rate": 0.001,
"loss": 0.9247,
"step": 4000
},
{
"epoch": 0.54,
"learning_rate": 0.001,
"loss": 0.9127,
"step": 4200
},
{
"epoch": 0.56,
"learning_rate": 0.001,
"loss": 0.9133,
"step": 4400
},
{
"epoch": 0.59,
"learning_rate": 0.001,
"loss": 0.9021,
"step": 4600
},
{
"epoch": 0.61,
"learning_rate": 0.001,
"loss": 0.9021,
"step": 4800
},
{
"epoch": 0.64,
"learning_rate": 0.001,
"loss": 0.8922,
"step": 5000
},
{
"epoch": 0.64,
"eval_loss": 1.1090599298477173,
"eval_runtime": 226.6186,
"eval_samples_per_second": 539.567,
"eval_steps_per_second": 2.109,
"step": 5000
},
{
"epoch": 0.67,
"learning_rate": 0.001,
"loss": 0.884,
"step": 5200
},
{
"epoch": 0.69,
"learning_rate": 0.001,
"loss": 0.8681,
"step": 5400
},
{
"epoch": 0.72,
"learning_rate": 0.001,
"loss": 0.8732,
"step": 5600
},
{
"epoch": 0.74,
"learning_rate": 0.001,
"loss": 0.869,
"step": 5800
},
{
"epoch": 0.77,
"learning_rate": 0.001,
"loss": 0.8467,
"step": 6000
},
{
"epoch": 0.79,
"learning_rate": 0.001,
"loss": 0.8578,
"step": 6200
},
{
"epoch": 0.82,
"learning_rate": 0.001,
"loss": 0.8621,
"step": 6400
},
{
"epoch": 0.85,
"learning_rate": 0.001,
"loss": 0.8484,
"step": 6600
},
{
"epoch": 0.87,
"learning_rate": 0.001,
"loss": 0.8449,
"step": 6800
},
{
"epoch": 0.9,
"learning_rate": 0.001,
"loss": 0.8432,
"step": 7000
},
{
"epoch": 0.92,
"learning_rate": 0.001,
"loss": 0.8481,
"step": 7200
},
{
"epoch": 0.95,
"learning_rate": 0.001,
"loss": 0.8388,
"step": 7400
},
{
"epoch": 0.97,
"learning_rate": 0.001,
"loss": 0.8402,
"step": 7600
},
{
"epoch": 1.0,
"learning_rate": 0.001,
"loss": 0.8175,
"step": 7800
},
{
"epoch": 1.02,
"learning_rate": 0.001,
"loss": 0.7903,
"step": 8000
},
{
"epoch": 1.05,
"learning_rate": 0.001,
"loss": 0.7977,
"step": 8200
},
{
"epoch": 1.08,
"learning_rate": 0.001,
"loss": 0.8082,
"step": 8400
},
{
"epoch": 1.1,
"learning_rate": 0.001,
"loss": 0.7975,
"step": 8600
},
{
"epoch": 1.13,
"learning_rate": 0.001,
"loss": 0.8046,
"step": 8800
},
{
"epoch": 1.15,
"learning_rate": 0.001,
"loss": 0.7912,
"step": 9000
},
{
"epoch": 1.18,
"learning_rate": 0.001,
"loss": 0.7875,
"step": 9200
},
{
"epoch": 1.2,
"learning_rate": 0.001,
"loss": 0.7894,
"step": 9400
},
{
"epoch": 1.23,
"learning_rate": 0.001,
"loss": 0.7886,
"step": 9600
},
{
"epoch": 1.26,
"learning_rate": 0.001,
"loss": 0.7847,
"step": 9800
},
{
"epoch": 1.28,
"learning_rate": 0.001,
"loss": 0.7906,
"step": 10000
},
{
"epoch": 1.28,
"eval_loss": 1.0378576517105103,
"eval_runtime": 226.2892,
"eval_samples_per_second": 540.353,
"eval_steps_per_second": 2.112,
"step": 10000
},
{
"epoch": 1.31,
"learning_rate": 0.001,
"loss": 0.7796,
"step": 10200
},
{
"epoch": 1.33,
"learning_rate": 0.001,
"loss": 0.7873,
"step": 10400
},
{
"epoch": 1.36,
"learning_rate": 0.001,
"loss": 0.7796,
"step": 10600
},
{
"epoch": 1.38,
"learning_rate": 0.001,
"loss": 0.7661,
"step": 10800
},
{
"epoch": 1.41,
"learning_rate": 0.001,
"loss": 0.7901,
"step": 11000
},
{
"epoch": 1.43,
"learning_rate": 0.001,
"loss": 0.7852,
"step": 11200
},
{
"epoch": 1.46,
"learning_rate": 0.001,
"loss": 0.7722,
"step": 11400
},
{
"epoch": 1.49,
"learning_rate": 0.001,
"loss": 0.7879,
"step": 11600
},
{
"epoch": 1.51,
"learning_rate": 0.001,
"loss": 0.7616,
"step": 11800
},
{
"epoch": 1.54,
"learning_rate": 0.001,
"loss": 0.7645,
"step": 12000
},
{
"epoch": 1.56,
"learning_rate": 0.001,
"loss": 0.7783,
"step": 12200
},
{
"epoch": 1.59,
"learning_rate": 0.001,
"loss": 0.7725,
"step": 12400
},
{
"epoch": 1.61,
"learning_rate": 0.001,
"loss": 0.7664,
"step": 12600
},
{
"epoch": 1.64,
"learning_rate": 0.001,
"loss": 0.7632,
"step": 12800
},
{
"epoch": 1.67,
"learning_rate": 0.001,
"loss": 0.7702,
"step": 13000
},
{
"epoch": 1.69,
"learning_rate": 0.001,
"loss": 0.7695,
"step": 13200
},
{
"epoch": 1.72,
"learning_rate": 0.001,
"loss": 0.7498,
"step": 13400
},
{
"epoch": 1.74,
"learning_rate": 0.001,
"loss": 0.7583,
"step": 13600
},
{
"epoch": 1.77,
"learning_rate": 0.001,
"loss": 0.7556,
"step": 13800
},
{
"epoch": 1.79,
"learning_rate": 0.001,
"loss": 0.7401,
"step": 14000
},
{
"epoch": 1.82,
"learning_rate": 0.001,
"loss": 0.7408,
"step": 14200
},
{
"epoch": 1.84,
"learning_rate": 0.001,
"loss": 0.7474,
"step": 14400
},
{
"epoch": 1.87,
"learning_rate": 0.001,
"loss": 0.7509,
"step": 14600
},
{
"epoch": 1.9,
"learning_rate": 0.001,
"loss": 0.7588,
"step": 14800
},
{
"epoch": 1.92,
"learning_rate": 0.001,
"loss": 0.7486,
"step": 15000
},
{
"epoch": 1.92,
"eval_loss": 1.012812852859497,
"eval_runtime": 226.2966,
"eval_samples_per_second": 540.335,
"eval_steps_per_second": 2.112,
"step": 15000
},
{
"epoch": 1.95,
"learning_rate": 0.001,
"loss": 0.7529,
"step": 15200
},
{
"epoch": 1.97,
"learning_rate": 0.001,
"loss": 0.7405,
"step": 15400
},
{
"epoch": 2.0,
"learning_rate": 0.001,
"loss": 0.7443,
"step": 15600
},
{
"epoch": 2.02,
"learning_rate": 0.001,
"loss": 0.7358,
"step": 15800
},
{
"epoch": 2.05,
"learning_rate": 0.001,
"loss": 0.7161,
"step": 16000
},
{
"epoch": 2.08,
"learning_rate": 0.001,
"loss": 0.7292,
"step": 16200
},
{
"epoch": 2.1,
"learning_rate": 0.001,
"loss": 0.7187,
"step": 16400
},
{
"epoch": 2.13,
"learning_rate": 0.001,
"loss": 0.7228,
"step": 16600
},
{
"epoch": 2.15,
"learning_rate": 0.001,
"loss": 0.7212,
"step": 16800
},
{
"epoch": 2.18,
"learning_rate": 0.001,
"loss": 0.7183,
"step": 17000
},
{
"epoch": 2.2,
"learning_rate": 0.001,
"loss": 0.7293,
"step": 17200
},
{
"epoch": 2.23,
"learning_rate": 0.001,
"loss": 0.7164,
"step": 17400
},
{
"epoch": 2.25,
"learning_rate": 0.001,
"loss": 0.7169,
"step": 17600
},
{
"epoch": 2.28,
"learning_rate": 0.001,
"loss": 0.7262,
"step": 17800
},
{
"epoch": 2.31,
"learning_rate": 0.001,
"loss": 0.7206,
"step": 18000
},
{
"epoch": 2.33,
"learning_rate": 0.001,
"loss": 0.7075,
"step": 18200
},
{
"epoch": 2.36,
"learning_rate": 0.001,
"loss": 0.7111,
"step": 18400
},
{
"epoch": 2.38,
"learning_rate": 0.001,
"loss": 0.708,
"step": 18600
},
{
"epoch": 2.41,
"learning_rate": 0.001,
"loss": 0.7205,
"step": 18800
},
{
"epoch": 2.43,
"learning_rate": 0.001,
"loss": 0.716,
"step": 19000
},
{
"epoch": 2.46,
"learning_rate": 0.001,
"loss": 0.7092,
"step": 19200
},
{
"epoch": 2.49,
"learning_rate": 0.001,
"loss": 0.7145,
"step": 19400
},
{
"epoch": 2.51,
"learning_rate": 0.001,
"loss": 0.7079,
"step": 19600
},
{
"epoch": 2.54,
"learning_rate": 0.001,
"loss": 0.7091,
"step": 19800
},
{
"epoch": 2.56,
"learning_rate": 0.001,
"loss": 0.7069,
"step": 20000
},
{
"epoch": 2.56,
"eval_loss": 1.0125058889389038,
"eval_runtime": 226.3642,
"eval_samples_per_second": 540.174,
"eval_steps_per_second": 2.112,
"step": 20000
},
{
"epoch": 2.59,
"learning_rate": 0.001,
"loss": 0.7227,
"step": 20200
},
{
"epoch": 2.61,
"learning_rate": 0.001,
"loss": 0.7131,
"step": 20400
},
{
"epoch": 2.64,
"learning_rate": 0.001,
"loss": 0.718,
"step": 20600
},
{
"epoch": 2.66,
"learning_rate": 0.001,
"loss": 0.7079,
"step": 20800
},
{
"epoch": 2.69,
"learning_rate": 0.001,
"loss": 0.7029,
"step": 21000
},
{
"epoch": 2.72,
"learning_rate": 0.001,
"loss": 0.7052,
"step": 21200
},
{
"epoch": 2.74,
"learning_rate": 0.001,
"loss": 0.7023,
"step": 21400
},
{
"epoch": 2.77,
"learning_rate": 0.001,
"loss": 0.6946,
"step": 21600
},
{
"epoch": 2.79,
"learning_rate": 0.001,
"loss": 0.7007,
"step": 21800
},
{
"epoch": 2.82,
"learning_rate": 0.001,
"loss": 0.7065,
"step": 22000
},
{
"epoch": 2.84,
"learning_rate": 0.001,
"loss": 0.7129,
"step": 22200
},
{
"epoch": 2.87,
"learning_rate": 0.001,
"loss": 0.7115,
"step": 22400
},
{
"epoch": 2.9,
"learning_rate": 0.001,
"loss": 0.7002,
"step": 22600
},
{
"epoch": 2.92,
"learning_rate": 0.001,
"loss": 0.7048,
"step": 22800
},
{
"epoch": 2.95,
"learning_rate": 0.001,
"loss": 0.7051,
"step": 23000
},
{
"epoch": 2.97,
"learning_rate": 0.001,
"loss": 0.6826,
"step": 23200
},
{
"epoch": 3.0,
"learning_rate": 0.001,
"loss": 0.707,
"step": 23400
},
{
"epoch": 3.02,
"learning_rate": 0.001,
"loss": 0.6763,
"step": 23600
},
{
"epoch": 3.05,
"learning_rate": 0.001,
"loss": 0.6645,
"step": 23800
},
{
"epoch": 3.07,
"learning_rate": 0.001,
"loss": 0.6786,
"step": 24000
},
{
"epoch": 3.1,
"learning_rate": 0.001,
"loss": 0.6786,
"step": 24200
},
{
"epoch": 3.13,
"learning_rate": 0.001,
"loss": 0.6867,
"step": 24400
},
{
"epoch": 3.15,
"learning_rate": 0.001,
"loss": 0.6748,
"step": 24600
},
{
"epoch": 3.18,
"learning_rate": 0.001,
"loss": 0.6754,
"step": 24800
},
{
"epoch": 3.2,
"learning_rate": 0.001,
"loss": 0.6766,
"step": 25000
},
{
"epoch": 3.2,
"eval_loss": 1.0152596235275269,
"eval_runtime": 226.4668,
"eval_samples_per_second": 539.929,
"eval_steps_per_second": 2.111,
"step": 25000
},
{
"epoch": 3.23,
"learning_rate": 0.001,
"loss": 0.6852,
"step": 25200
},
{
"epoch": 3.25,
"learning_rate": 0.001,
"loss": 0.6736,
"step": 25400
},
{
"epoch": 3.28,
"learning_rate": 0.001,
"loss": 0.6859,
"step": 25600
},
{
"epoch": 3.31,
"learning_rate": 0.001,
"loss": 0.6754,
"step": 25800
},
{
"epoch": 3.33,
"learning_rate": 0.001,
"loss": 0.6789,
"step": 26000
},
{
"epoch": 3.36,
"learning_rate": 0.001,
"loss": 0.6725,
"step": 26200
},
{
"epoch": 3.38,
"learning_rate": 0.001,
"loss": 0.6826,
"step": 26400
},
{
"epoch": 3.41,
"learning_rate": 0.001,
"loss": 0.6852,
"step": 26600
},
{
"epoch": 3.43,
"learning_rate": 0.001,
"loss": 0.6767,
"step": 26800
},
{
"epoch": 3.46,
"learning_rate": 0.001,
"loss": 0.6584,
"step": 27000
},
{
"epoch": 3.48,
"learning_rate": 0.001,
"loss": 0.6642,
"step": 27200
},
{
"epoch": 3.51,
"learning_rate": 0.001,
"loss": 0.6732,
"step": 27400
},
{
"epoch": 3.54,
"learning_rate": 0.001,
"loss": 0.6832,
"step": 27600
},
{
"epoch": 3.56,
"learning_rate": 0.001,
"loss": 0.6746,
"step": 27800
},
{
"epoch": 3.59,
"learning_rate": 0.001,
"loss": 0.6803,
"step": 28000
},
{
"epoch": 3.61,
"learning_rate": 0.001,
"loss": 0.6753,
"step": 28200
},
{
"epoch": 3.64,
"learning_rate": 0.001,
"loss": 0.6901,
"step": 28400
},
{
"epoch": 3.66,
"learning_rate": 0.001,
"loss": 0.6717,
"step": 28600
},
{
"epoch": 3.69,
"learning_rate": 0.001,
"loss": 0.6761,
"step": 28800
},
{
"epoch": 3.72,
"learning_rate": 0.001,
"loss": 0.6698,
"step": 29000
},
{
"epoch": 3.74,
"learning_rate": 0.001,
"loss": 0.6737,
"step": 29200
},
{
"epoch": 3.77,
"learning_rate": 0.001,
"loss": 0.6832,
"step": 29400
},
{
"epoch": 3.79,
"learning_rate": 0.001,
"loss": 0.6699,
"step": 29600
},
{
"epoch": 3.82,
"learning_rate": 0.001,
"loss": 0.6686,
"step": 29800
},
{
"epoch": 3.84,
"learning_rate": 0.001,
"loss": 0.6624,
"step": 30000
},
{
"epoch": 3.84,
"eval_loss": 0.9890710711479187,
"eval_runtime": 226.6603,
"eval_samples_per_second": 539.468,
"eval_steps_per_second": 2.109,
"step": 30000
},
{
"epoch": 3.87,
"learning_rate": 0.001,
"loss": 0.6739,
"step": 30200
},
{
"epoch": 3.89,
"learning_rate": 0.001,
"loss": 0.672,
"step": 30400
},
{
"epoch": 3.92,
"learning_rate": 0.001,
"loss": 0.6728,
"step": 30600
},
{
"epoch": 3.95,
"learning_rate": 0.001,
"loss": 0.6767,
"step": 30800
},
{
"epoch": 3.97,
"learning_rate": 0.001,
"loss": 0.6808,
"step": 31000
},
{
"epoch": 4.0,
"learning_rate": 0.001,
"loss": 0.6644,
"step": 31200
},
{
"epoch": 4.02,
"learning_rate": 0.001,
"loss": 0.6459,
"step": 31400
},
{
"epoch": 4.05,
"learning_rate": 0.001,
"loss": 0.6548,
"step": 31600
},
{
"epoch": 4.07,
"learning_rate": 0.001,
"loss": 0.6486,
"step": 31800
},
{
"epoch": 4.1,
"learning_rate": 0.001,
"loss": 0.6516,
"step": 32000
},
{
"epoch": 4.13,
"learning_rate": 0.001,
"loss": 0.6533,
"step": 32200
},
{
"epoch": 4.15,
"learning_rate": 0.001,
"loss": 0.6496,
"step": 32400
},
{
"epoch": 4.18,
"learning_rate": 0.001,
"loss": 0.6478,
"step": 32600
},
{
"epoch": 4.2,
"learning_rate": 0.001,
"loss": 0.6498,
"step": 32800
},
{
"epoch": 4.23,
"learning_rate": 0.001,
"loss": 0.6345,
"step": 33000
},
{
"epoch": 4.25,
"learning_rate": 0.001,
"loss": 0.6451,
"step": 33200
},
{
"epoch": 4.28,
"learning_rate": 0.001,
"loss": 0.6465,
"step": 33400
},
{
"epoch": 4.3,
"learning_rate": 0.001,
"loss": 0.643,
"step": 33600
},
{
"epoch": 4.33,
"learning_rate": 0.001,
"loss": 0.6573,
"step": 33800
},
{
"epoch": 4.36,
"learning_rate": 0.001,
"loss": 0.6473,
"step": 34000
},
{
"epoch": 4.38,
"learning_rate": 0.001,
"loss": 0.6523,
"step": 34200
},
{
"epoch": 4.41,
"learning_rate": 0.001,
"loss": 0.6507,
"step": 34400
},
{
"epoch": 4.43,
"learning_rate": 0.001,
"loss": 0.6478,
"step": 34600
},
{
"epoch": 4.46,
"learning_rate": 0.001,
"loss": 0.658,
"step": 34800
},
{
"epoch": 4.48,
"learning_rate": 0.001,
"loss": 0.6458,
"step": 35000
},
{
"epoch": 4.48,
"eval_loss": 0.9963102340698242,
"eval_runtime": 226.814,
"eval_samples_per_second": 539.103,
"eval_steps_per_second": 2.107,
"step": 35000
},
{
"epoch": 4.51,
"learning_rate": 0.001,
"loss": 0.6567,
"step": 35200
},
{
"epoch": 4.54,
"learning_rate": 0.001,
"loss": 0.6474,
"step": 35400
},
{
"epoch": 4.56,
"learning_rate": 0.001,
"loss": 0.6518,
"step": 35600
},
{
"epoch": 4.59,
"learning_rate": 0.001,
"loss": 0.6509,
"step": 35800
},
{
"epoch": 4.61,
"learning_rate": 0.001,
"loss": 0.6512,
"step": 36000
},
{
"epoch": 4.64,
"learning_rate": 0.001,
"loss": 0.6501,
"step": 36200
},
{
"epoch": 4.66,
"learning_rate": 0.001,
"loss": 0.65,
"step": 36400
},
{
"epoch": 4.69,
"learning_rate": 0.001,
"loss": 0.6505,
"step": 36600
},
{
"epoch": 4.71,
"learning_rate": 0.001,
"loss": 0.6426,
"step": 36800
},
{
"epoch": 4.74,
"learning_rate": 0.001,
"loss": 0.6593,
"step": 37000
},
{
"epoch": 4.77,
"learning_rate": 0.001,
"loss": 0.6488,
"step": 37200
},
{
"epoch": 4.79,
"learning_rate": 0.001,
"loss": 0.6402,
"step": 37400
},
{
"epoch": 4.82,
"learning_rate": 0.001,
"loss": 0.6515,
"step": 37600
},
{
"epoch": 4.84,
"learning_rate": 0.001,
"loss": 0.6453,
"step": 37800
},
{
"epoch": 4.87,
"learning_rate": 0.001,
"loss": 0.6581,
"step": 38000
},
{
"epoch": 4.89,
"learning_rate": 0.001,
"loss": 0.6408,
"step": 38200
},
{
"epoch": 4.92,
"learning_rate": 0.001,
"loss": 0.6452,
"step": 38400
},
{
"epoch": 4.95,
"learning_rate": 0.001,
"loss": 0.6445,
"step": 38600
},
{
"epoch": 4.97,
"learning_rate": 0.001,
"loss": 0.6455,
"step": 38800
},
{
"epoch": 5.0,
"learning_rate": 0.001,
"loss": 0.6505,
"step": 39000
},
{
"epoch": 5.02,
"learning_rate": 0.001,
"loss": 0.6246,
"step": 39200
},
{
"epoch": 5.05,
"learning_rate": 0.001,
"loss": 0.6119,
"step": 39400
},
{
"epoch": 5.07,
"learning_rate": 0.001,
"loss": 0.622,
"step": 39600
},
{
"epoch": 5.1,
"learning_rate": 0.001,
"loss": 0.6278,
"step": 39800
},
{
"epoch": 5.12,
"learning_rate": 0.001,
"loss": 0.6233,
"step": 40000
},
{
"epoch": 5.12,
"eval_loss": 0.9902318716049194,
"eval_runtime": 227.3177,
"eval_samples_per_second": 537.908,
"eval_steps_per_second": 2.103,
"step": 40000
},
{
"epoch": 5.15,
"learning_rate": 0.001,
"loss": 0.6309,
"step": 40200
},
{
"epoch": 5.18,
"learning_rate": 0.001,
"loss": 0.6308,
"step": 40400
},
{
"epoch": 5.2,
"learning_rate": 0.001,
"loss": 0.6173,
"step": 40600
},
{
"epoch": 5.23,
"learning_rate": 0.001,
"loss": 0.6188,
"step": 40800
},
{
"epoch": 5.25,
"learning_rate": 0.001,
"loss": 0.6412,
"step": 41000
},
{
"epoch": 5.28,
"learning_rate": 0.001,
"loss": 0.6232,
"step": 41200
},
{
"epoch": 5.3,
"learning_rate": 0.001,
"loss": 0.6393,
"step": 41400
},
{
"epoch": 5.33,
"learning_rate": 0.001,
"loss": 0.6305,
"step": 41600
},
{
"epoch": 5.36,
"learning_rate": 0.001,
"loss": 0.632,
"step": 41800
},
{
"epoch": 5.38,
"learning_rate": 0.001,
"loss": 0.6308,
"step": 42000
},
{
"epoch": 5.41,
"learning_rate": 0.001,
"loss": 0.6307,
"step": 42200
},
{
"epoch": 5.43,
"learning_rate": 0.001,
"loss": 0.6321,
"step": 42400
},
{
"epoch": 5.46,
"learning_rate": 0.001,
"loss": 0.6337,
"step": 42600
},
{
"epoch": 5.48,
"learning_rate": 0.001,
"loss": 0.6281,
"step": 42800
},
{
"epoch": 5.51,
"learning_rate": 0.001,
"loss": 0.633,
"step": 43000
},
{
"epoch": 5.53,
"learning_rate": 0.001,
"loss": 0.6208,
"step": 43200
},
{
"epoch": 5.56,
"learning_rate": 0.001,
"loss": 0.6217,
"step": 43400
},
{
"epoch": 5.59,
"learning_rate": 0.001,
"loss": 0.6229,
"step": 43600
},
{
"epoch": 5.61,
"learning_rate": 0.001,
"loss": 0.6253,
"step": 43800
},
{
"epoch": 5.64,
"learning_rate": 0.001,
"loss": 0.6315,
"step": 44000
},
{
"epoch": 5.66,
"learning_rate": 0.001,
"loss": 0.6354,
"step": 44200
},
{
"epoch": 5.69,
"learning_rate": 0.001,
"loss": 0.6314,
"step": 44400
},
{
"epoch": 5.71,
"learning_rate": 0.001,
"loss": 0.6346,
"step": 44600
},
{
"epoch": 5.74,
"learning_rate": 0.001,
"loss": 0.6293,
"step": 44800
},
{
"epoch": 5.77,
"learning_rate": 0.001,
"loss": 0.6393,
"step": 45000
},
{
"epoch": 5.77,
"eval_loss": 0.9893815517425537,
"eval_runtime": 226.9791,
"eval_samples_per_second": 538.71,
"eval_steps_per_second": 2.106,
"step": 45000
},
{
"epoch": 5.79,
"learning_rate": 0.001,
"loss": 0.629,
"step": 45200
},
{
"epoch": 5.82,
"learning_rate": 0.001,
"loss": 0.6381,
"step": 45400
},
{
"epoch": 5.84,
"learning_rate": 0.001,
"loss": 0.6327,
"step": 45600
},
{
"epoch": 5.87,
"learning_rate": 0.001,
"loss": 0.6272,
"step": 45800
},
{
"epoch": 5.89,
"learning_rate": 0.001,
"loss": 0.6266,
"step": 46000
},
{
"epoch": 5.92,
"learning_rate": 0.001,
"loss": 0.628,
"step": 46200
},
{
"epoch": 5.94,
"learning_rate": 0.001,
"loss": 0.6211,
"step": 46400
},
{
"epoch": 5.97,
"learning_rate": 0.001,
"loss": 0.628,
"step": 46600
},
{
"epoch": 6.0,
"learning_rate": 0.001,
"loss": 0.6351,
"step": 46800
},
{
"epoch": 6.02,
"learning_rate": 0.001,
"loss": 0.6172,
"step": 47000
},
{
"epoch": 6.05,
"learning_rate": 0.001,
"loss": 0.5967,
"step": 47200
},
{
"epoch": 6.07,
"learning_rate": 0.001,
"loss": 0.603,
"step": 47400
},
{
"epoch": 6.1,
"learning_rate": 0.001,
"loss": 0.614,
"step": 47600
},
{
"epoch": 6.12,
"learning_rate": 0.001,
"loss": 0.6204,
"step": 47800
},
{
"epoch": 6.15,
"learning_rate": 0.001,
"loss": 0.6075,
"step": 48000
},
{
"epoch": 6.18,
"learning_rate": 0.001,
"loss": 0.612,
"step": 48200
},
{
"epoch": 6.2,
"learning_rate": 0.001,
"loss": 0.6184,
"step": 48400
},
{
"epoch": 6.23,
"learning_rate": 0.001,
"loss": 0.6062,
"step": 48600
},
{
"epoch": 6.25,
"learning_rate": 0.001,
"loss": 0.6146,
"step": 48800
},
{
"epoch": 6.28,
"learning_rate": 0.001,
"loss": 0.6172,
"step": 49000
},
{
"epoch": 6.3,
"learning_rate": 0.001,
"loss": 0.6066,
"step": 49200
},
{
"epoch": 6.33,
"learning_rate": 0.001,
"loss": 0.6185,
"step": 49400
},
{
"epoch": 6.35,
"learning_rate": 0.001,
"loss": 0.6121,
"step": 49600
},
{
"epoch": 6.38,
"learning_rate": 0.001,
"loss": 0.6054,
"step": 49800
},
{
"epoch": 6.41,
"learning_rate": 0.001,
"loss": 0.6035,
"step": 50000
},
{
"epoch": 6.41,
"eval_loss": 0.9930422902107239,
"eval_runtime": 227.4872,
"eval_samples_per_second": 537.507,
"eval_steps_per_second": 2.101,
"step": 50000
},
{
"epoch": 6.43,
"learning_rate": 0.001,
"loss": 0.6172,
"step": 50200
},
{
"epoch": 6.46,
"learning_rate": 0.001,
"loss": 0.6118,
"step": 50400
},
{
"epoch": 6.48,
"learning_rate": 0.001,
"loss": 0.6193,
"step": 50600
},
{
"epoch": 6.51,
"learning_rate": 0.001,
"loss": 0.6235,
"step": 50800
},
{
"epoch": 6.53,
"learning_rate": 0.001,
"loss": 0.6267,
"step": 51000
},
{
"epoch": 6.56,
"learning_rate": 0.001,
"loss": 0.6125,
"step": 51200
},
{
"epoch": 6.59,
"learning_rate": 0.001,
"loss": 0.6075,
"step": 51400
},
{
"epoch": 6.61,
"learning_rate": 0.001,
"loss": 0.6147,
"step": 51600
},
{
"epoch": 6.64,
"learning_rate": 0.001,
"loss": 0.6022,
"step": 51800
},
{
"epoch": 6.66,
"learning_rate": 0.001,
"loss": 0.6039,
"step": 52000
},
{
"epoch": 6.69,
"learning_rate": 0.001,
"loss": 0.6087,
"step": 52200
},
{
"epoch": 6.71,
"learning_rate": 0.001,
"loss": 0.611,
"step": 52400
},
{
"epoch": 6.74,
"learning_rate": 0.001,
"loss": 0.6122,
"step": 52600
},
{
"epoch": 6.76,
"learning_rate": 0.001,
"loss": 0.6038,
"step": 52800
},
{
"epoch": 6.79,
"learning_rate": 0.001,
"loss": 0.617,
"step": 53000
},
{
"epoch": 6.82,
"learning_rate": 0.001,
"loss": 0.6068,
"step": 53200
},
{
"epoch": 6.84,
"learning_rate": 0.001,
"loss": 0.6186,
"step": 53400
},
{
"epoch": 6.87,
"learning_rate": 0.001,
"loss": 0.6131,
"step": 53600
},
{
"epoch": 6.89,
"learning_rate": 0.001,
"loss": 0.612,
"step": 53800
},
{
"epoch": 6.92,
"learning_rate": 0.001,
"loss": 0.6101,
"step": 54000
},
{
"epoch": 6.94,
"learning_rate": 0.001,
"loss": 0.6087,
"step": 54200
},
{
"epoch": 6.97,
"learning_rate": 0.001,
"loss": 0.6093,
"step": 54400
},
{
"epoch": 7.0,
"learning_rate": 0.001,
"loss": 0.6139,
"step": 54600
},
{
"epoch": 7.02,
"learning_rate": 0.001,
"loss": 0.6001,
"step": 54800
},
{
"epoch": 7.05,
"learning_rate": 0.001,
"loss": 0.5916,
"step": 55000
},
{
"epoch": 7.05,
"eval_loss": 0.9893601536750793,
"eval_runtime": 227.4715,
"eval_samples_per_second": 537.544,
"eval_steps_per_second": 2.101,
"step": 55000
},
{
"epoch": 7.07,
"learning_rate": 0.001,
"loss": 0.5944,
"step": 55200
},
{
"epoch": 7.1,
"learning_rate": 0.001,
"loss": 0.59,
"step": 55400
},
{
"epoch": 7.12,
"learning_rate": 0.001,
"loss": 0.5999,
"step": 55600
},
{
"epoch": 7.15,
"learning_rate": 0.001,
"loss": 0.5887,
"step": 55800
},
{
"epoch": 7.17,
"learning_rate": 0.001,
"loss": 0.5939,
"step": 56000
},
{
"epoch": 7.2,
"learning_rate": 0.001,
"loss": 0.5941,
"step": 56200
},
{
"epoch": 7.23,
"learning_rate": 0.001,
"loss": 0.6025,
"step": 56400
},
{
"epoch": 7.25,
"learning_rate": 0.001,
"loss": 0.5955,
"step": 56600
},
{
"epoch": 7.28,
"learning_rate": 0.001,
"loss": 0.6038,
"step": 56800
},
{
"epoch": 7.3,
"learning_rate": 0.001,
"loss": 0.5878,
"step": 57000
},
{
"epoch": 7.33,
"learning_rate": 0.001,
"loss": 0.5974,
"step": 57200
},
{
"epoch": 7.35,
"learning_rate": 0.001,
"loss": 0.6144,
"step": 57400
},
{
"epoch": 7.38,
"learning_rate": 0.001,
"loss": 0.5916,
"step": 57600
},
{
"epoch": 7.41,
"learning_rate": 0.001,
"loss": 0.5897,
"step": 57800
},
{
"epoch": 7.43,
"learning_rate": 0.001,
"loss": 0.5954,
"step": 58000
},
{
"epoch": 7.46,
"learning_rate": 0.001,
"loss": 0.5975,
"step": 58200
},
{
"epoch": 7.48,
"learning_rate": 0.001,
"loss": 0.5953,
"step": 58400
},
{
"epoch": 7.51,
"learning_rate": 0.001,
"loss": 0.5967,
"step": 58600
},
{
"epoch": 7.53,
"learning_rate": 0.001,
"loss": 0.5988,
"step": 58800
},
{
"epoch": 7.56,
"learning_rate": 0.001,
"loss": 0.6058,
"step": 59000
},
{
"epoch": 7.58,
"learning_rate": 0.001,
"loss": 0.6007,
"step": 59200
},
{
"epoch": 7.61,
"learning_rate": 0.001,
"loss": 0.606,
"step": 59400
},
{
"epoch": 7.64,
"learning_rate": 0.001,
"loss": 0.5885,
"step": 59600
},
{
"epoch": 7.66,
"learning_rate": 0.001,
"loss": 0.5968,
"step": 59800
},
{
"epoch": 7.69,
"learning_rate": 0.001,
"loss": 0.6073,
"step": 60000
},
{
"epoch": 7.69,
"eval_loss": 0.9817278981208801,
"eval_runtime": 227.2904,
"eval_samples_per_second": 537.973,
"eval_steps_per_second": 2.103,
"step": 60000
},
{
"epoch": 7.71,
"learning_rate": 0.001,
"loss": 0.5998,
"step": 60200
},
{
"epoch": 7.74,
"learning_rate": 0.001,
"loss": 0.5959,
"step": 60400
},
{
"epoch": 7.76,
"learning_rate": 0.001,
"loss": 0.5946,
"step": 60600
},
{
"epoch": 7.79,
"learning_rate": 0.001,
"loss": 0.601,
"step": 60800
},
{
"epoch": 7.82,
"learning_rate": 0.001,
"loss": 0.5963,
"step": 61000
},
{
"epoch": 7.84,
"learning_rate": 0.001,
"loss": 0.5996,
"step": 61200
},
{
"epoch": 7.87,
"learning_rate": 0.001,
"loss": 0.5981,
"step": 61400
},
{
"epoch": 7.89,
"learning_rate": 0.001,
"loss": 0.5945,
"step": 61600
},
{
"epoch": 7.92,
"learning_rate": 0.001,
"loss": 0.6057,
"step": 61800
},
{
"epoch": 7.94,
"learning_rate": 0.001,
"loss": 0.5952,
"step": 62000
},
{
"epoch": 7.97,
"learning_rate": 0.001,
"loss": 0.6012,
"step": 62200
},
{
"epoch": 7.99,
"learning_rate": 0.001,
"loss": 0.5979,
"step": 62400
},
{
"epoch": 8.02,
"learning_rate": 0.001,
"loss": 0.5965,
"step": 62600
},
{
"epoch": 8.05,
"learning_rate": 0.001,
"loss": 0.5767,
"step": 62800
},
{
"epoch": 8.07,
"learning_rate": 0.001,
"loss": 0.5697,
"step": 63000
},
{
"epoch": 8.1,
"learning_rate": 0.001,
"loss": 0.5761,
"step": 63200
},
{
"epoch": 8.12,
"learning_rate": 0.001,
"loss": 0.5808,
"step": 63400
},
{
"epoch": 8.15,
"learning_rate": 0.001,
"loss": 0.5734,
"step": 63600
},
{
"epoch": 8.17,
"learning_rate": 0.001,
"loss": 0.5767,
"step": 63800
},
{
"epoch": 8.2,
"learning_rate": 0.001,
"loss": 0.5874,
"step": 64000
},
{
"epoch": 8.23,
"learning_rate": 0.001,
"loss": 0.5773,
"step": 64200
},
{
"epoch": 8.25,
"learning_rate": 0.001,
"loss": 0.587,
"step": 64400
},
{
"epoch": 8.28,
"learning_rate": 0.001,
"loss": 0.5882,
"step": 64600
},
{
"epoch": 8.3,
"learning_rate": 0.001,
"loss": 0.5815,
"step": 64800
},
{
"epoch": 8.33,
"learning_rate": 0.001,
"loss": 0.5928,
"step": 65000
},
{
"epoch": 8.33,
"eval_loss": 0.9951310753822327,
"eval_runtime": 227.2886,
"eval_samples_per_second": 537.977,
"eval_steps_per_second": 2.103,
"step": 65000
},
{
"epoch": 8.35,
"learning_rate": 0.001,
"loss": 0.5827,
"step": 65200
},
{
"epoch": 8.38,
"learning_rate": 0.001,
"loss": 0.5733,
"step": 65400
},
{
"epoch": 8.4,
"learning_rate": 0.001,
"loss": 0.5889,
"step": 65600
},
{
"epoch": 8.43,
"learning_rate": 0.001,
"loss": 0.589,
"step": 65800
},
{
"epoch": 8.46,
"learning_rate": 0.001,
"loss": 0.5902,
"step": 66000
},
{
"epoch": 8.48,
"learning_rate": 0.001,
"loss": 0.5899,
"step": 66200
},
{
"epoch": 8.51,
"learning_rate": 0.001,
"loss": 0.586,
"step": 66400
},
{
"epoch": 8.53,
"learning_rate": 0.001,
"loss": 0.585,
"step": 66600
},
{
"epoch": 8.56,
"learning_rate": 0.001,
"loss": 0.5968,
"step": 66800
},
{
"epoch": 8.58,
"learning_rate": 0.001,
"loss": 0.5916,
"step": 67000
},
{
"epoch": 8.61,
"learning_rate": 0.001,
"loss": 0.5773,
"step": 67200
},
{
"epoch": 8.64,
"learning_rate": 0.001,
"loss": 0.5737,
"step": 67400
},
{
"epoch": 8.66,
"learning_rate": 0.001,
"loss": 0.5806,
"step": 67600
},
{
"epoch": 8.69,
"learning_rate": 0.001,
"loss": 0.5891,
"step": 67800
},
{
"epoch": 8.71,
"learning_rate": 0.001,
"loss": 0.5984,
"step": 68000
},
{
"epoch": 8.74,
"learning_rate": 0.001,
"loss": 0.599,
"step": 68200
},
{
"epoch": 8.76,
"learning_rate": 0.001,
"loss": 0.5892,
"step": 68400
},
{
"epoch": 8.79,
"learning_rate": 0.001,
"loss": 0.5785,
"step": 68600
},
{
"epoch": 8.81,
"learning_rate": 0.001,
"loss": 0.5892,
"step": 68800
},
{
"epoch": 8.84,
"learning_rate": 0.001,
"loss": 0.5812,
"step": 69000
},
{
"epoch": 8.87,
"learning_rate": 0.001,
"loss": 0.5943,
"step": 69200
},
{
"epoch": 8.89,
"learning_rate": 0.001,
"loss": 0.5926,
"step": 69400
},
{
"epoch": 8.92,
"learning_rate": 0.001,
"loss": 0.5798,
"step": 69600
},
{
"epoch": 8.94,
"learning_rate": 0.001,
"loss": 0.5911,
"step": 69800
},
{
"epoch": 8.97,
"learning_rate": 0.001,
"loss": 0.5846,
"step": 70000
},
{
"epoch": 8.97,
"eval_loss": 0.9769449234008789,
"eval_runtime": 227.0836,
"eval_samples_per_second": 538.462,
"eval_steps_per_second": 2.105,
"step": 70000
}
],
"max_steps": 78050,
"num_train_epochs": 10,
"total_flos": 9.84005748927529e+17,
"trial_name": null,
"trial_params": null
}