edwardgowsmith's picture
Upload with huggingface_hub
8385fbd
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 78.12415130940835,
"global_step": 10000,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.78,
"learning_rate": 1.0000000000000002e-06,
"loss": 10.1419,
"step": 100
},
{
"epoch": 1.56,
"learning_rate": 2.0000000000000003e-06,
"loss": 9.2788,
"step": 200
},
{
"epoch": 2.34,
"learning_rate": 3e-06,
"loss": 8.8011,
"step": 300
},
{
"epoch": 3.12,
"learning_rate": 4.000000000000001e-06,
"loss": 8.3846,
"step": 400
},
{
"epoch": 3.9,
"learning_rate": 5e-06,
"loss": 7.8214,
"step": 500
},
{
"epoch": 4.68,
"learning_rate": 6e-06,
"loss": 7.3094,
"step": 600
},
{
"epoch": 5.47,
"learning_rate": 7.000000000000001e-06,
"loss": 6.7911,
"step": 700
},
{
"epoch": 6.25,
"learning_rate": 8.000000000000001e-06,
"loss": 6.4144,
"step": 800
},
{
"epoch": 7.03,
"learning_rate": 9e-06,
"loss": 6.2168,
"step": 900
},
{
"epoch": 7.81,
"learning_rate": 1e-05,
"loss": 6.0642,
"step": 1000
},
{
"epoch": 8.59,
"learning_rate": 1.1000000000000001e-05,
"loss": 6.0511,
"step": 1100
},
{
"epoch": 9.37,
"learning_rate": 1.2e-05,
"loss": 5.995,
"step": 1200
},
{
"epoch": 10.16,
"learning_rate": 1.3000000000000001e-05,
"loss": 5.9539,
"step": 1300
},
{
"epoch": 10.93,
"learning_rate": 1.4000000000000001e-05,
"loss": 5.8675,
"step": 1400
},
{
"epoch": 11.71,
"learning_rate": 1.5e-05,
"loss": 5.8874,
"step": 1500
},
{
"epoch": 12.5,
"learning_rate": 1.6000000000000003e-05,
"loss": 5.8578,
"step": 1600
},
{
"epoch": 13.28,
"learning_rate": 1.7000000000000003e-05,
"loss": 5.8386,
"step": 1700
},
{
"epoch": 14.06,
"learning_rate": 1.8e-05,
"loss": 5.8138,
"step": 1800
},
{
"epoch": 14.84,
"learning_rate": 1.9e-05,
"loss": 5.7399,
"step": 1900
},
{
"epoch": 15.62,
"learning_rate": 2e-05,
"loss": 5.7753,
"step": 2000
},
{
"epoch": 16.4,
"learning_rate": 2.1e-05,
"loss": 5.7564,
"step": 2100
},
{
"epoch": 17.19,
"learning_rate": 2.2000000000000003e-05,
"loss": 5.738,
"step": 2200
},
{
"epoch": 17.96,
"learning_rate": 2.3000000000000003e-05,
"loss": 5.6753,
"step": 2300
},
{
"epoch": 18.74,
"learning_rate": 2.4e-05,
"loss": 5.7082,
"step": 2400
},
{
"epoch": 19.53,
"learning_rate": 2.5e-05,
"loss": 5.6991,
"step": 2500
},
{
"epoch": 20.31,
"learning_rate": 2.6000000000000002e-05,
"loss": 5.6801,
"step": 2600
},
{
"epoch": 21.09,
"learning_rate": 2.7000000000000002e-05,
"loss": 5.6692,
"step": 2700
},
{
"epoch": 21.87,
"learning_rate": 2.8000000000000003e-05,
"loss": 5.6063,
"step": 2800
},
{
"epoch": 22.65,
"learning_rate": 2.9e-05,
"loss": 5.6445,
"step": 2900
},
{
"epoch": 23.43,
"learning_rate": 3e-05,
"loss": 5.6328,
"step": 3000
},
{
"epoch": 24.22,
"learning_rate": 3.1e-05,
"loss": 5.6217,
"step": 3100
},
{
"epoch": 24.99,
"learning_rate": 3.2000000000000005e-05,
"loss": 5.5601,
"step": 3200
},
{
"epoch": 25.78,
"learning_rate": 3.3e-05,
"loss": 5.5976,
"step": 3300
},
{
"epoch": 26.56,
"learning_rate": 3.4000000000000007e-05,
"loss": 5.5911,
"step": 3400
},
{
"epoch": 27.34,
"learning_rate": 3.5e-05,
"loss": 5.5738,
"step": 3500
},
{
"epoch": 28.12,
"learning_rate": 3.6e-05,
"loss": 5.566,
"step": 3600
},
{
"epoch": 28.9,
"learning_rate": 3.7e-05,
"loss": 5.5071,
"step": 3700
},
{
"epoch": 29.68,
"learning_rate": 3.8e-05,
"loss": 5.5438,
"step": 3800
},
{
"epoch": 30.47,
"learning_rate": 3.9000000000000006e-05,
"loss": 5.5366,
"step": 3900
},
{
"epoch": 31.25,
"learning_rate": 4e-05,
"loss": 5.5268,
"step": 4000
},
{
"epoch": 32.03,
"learning_rate": 4.1e-05,
"loss": 5.517,
"step": 4100
},
{
"epoch": 32.81,
"learning_rate": 4.2e-05,
"loss": 5.4574,
"step": 4200
},
{
"epoch": 33.59,
"learning_rate": 4.3e-05,
"loss": 5.5002,
"step": 4300
},
{
"epoch": 34.37,
"learning_rate": 4.4000000000000006e-05,
"loss": 5.4887,
"step": 4400
},
{
"epoch": 35.16,
"learning_rate": 4.5e-05,
"loss": 5.4805,
"step": 4500
},
{
"epoch": 35.93,
"learning_rate": 4.600000000000001e-05,
"loss": 5.4265,
"step": 4600
},
{
"epoch": 36.71,
"learning_rate": 4.7e-05,
"loss": 5.4615,
"step": 4700
},
{
"epoch": 37.5,
"learning_rate": 4.8e-05,
"loss": 5.4576,
"step": 4800
},
{
"epoch": 38.28,
"learning_rate": 4.9e-05,
"loss": 5.4421,
"step": 4900
},
{
"epoch": 39.06,
"learning_rate": 5e-05,
"loss": 5.4342,
"step": 5000
},
{
"epoch": 39.84,
"learning_rate": 5.1000000000000006e-05,
"loss": 5.3641,
"step": 5100
},
{
"epoch": 40.62,
"learning_rate": 5.2000000000000004e-05,
"loss": 5.379,
"step": 5200
},
{
"epoch": 41.4,
"learning_rate": 5.300000000000001e-05,
"loss": 5.3638,
"step": 5300
},
{
"epoch": 42.19,
"learning_rate": 5.4000000000000005e-05,
"loss": 5.3441,
"step": 5400
},
{
"epoch": 42.96,
"learning_rate": 5.500000000000001e-05,
"loss": 5.2759,
"step": 5500
},
{
"epoch": 43.74,
"learning_rate": 5.6000000000000006e-05,
"loss": 5.3011,
"step": 5600
},
{
"epoch": 44.53,
"learning_rate": 5.6999999999999996e-05,
"loss": 5.2758,
"step": 5700
},
{
"epoch": 45.31,
"learning_rate": 5.8e-05,
"loss": 5.2559,
"step": 5800
},
{
"epoch": 46.09,
"learning_rate": 5.9e-05,
"loss": 5.2326,
"step": 5900
},
{
"epoch": 46.87,
"learning_rate": 6e-05,
"loss": 5.1616,
"step": 6000
},
{
"epoch": 47.65,
"learning_rate": 6.1e-05,
"loss": 5.1753,
"step": 6100
},
{
"epoch": 48.43,
"learning_rate": 6.2e-05,
"loss": 5.1378,
"step": 6200
},
{
"epoch": 49.22,
"learning_rate": 6.3e-05,
"loss": 5.1,
"step": 6300
},
{
"epoch": 49.99,
"learning_rate": 6.400000000000001e-05,
"loss": 5.015,
"step": 6400
},
{
"epoch": 50.78,
"learning_rate": 6.500000000000001e-05,
"loss": 4.9758,
"step": 6500
},
{
"epoch": 51.56,
"learning_rate": 6.6e-05,
"loss": 4.8417,
"step": 6600
},
{
"epoch": 52.34,
"learning_rate": 6.7e-05,
"loss": 4.7116,
"step": 6700
},
{
"epoch": 53.12,
"learning_rate": 6.800000000000001e-05,
"loss": 4.5582,
"step": 6800
},
{
"epoch": 53.9,
"learning_rate": 6.9e-05,
"loss": 4.3437,
"step": 6900
},
{
"epoch": 54.68,
"learning_rate": 7e-05,
"loss": 4.2114,
"step": 7000
},
{
"epoch": 55.47,
"learning_rate": 7.1e-05,
"loss": 4.1021,
"step": 7100
},
{
"epoch": 56.25,
"learning_rate": 7.2e-05,
"loss": 4.0074,
"step": 7200
},
{
"epoch": 57.03,
"learning_rate": 7.3e-05,
"loss": 3.9346,
"step": 7300
},
{
"epoch": 57.81,
"learning_rate": 7.4e-05,
"loss": 3.8289,
"step": 7400
},
{
"epoch": 58.59,
"learning_rate": 7.500000000000001e-05,
"loss": 3.8105,
"step": 7500
},
{
"epoch": 59.37,
"learning_rate": 7.6e-05,
"loss": 3.755,
"step": 7600
},
{
"epoch": 60.16,
"learning_rate": 7.7e-05,
"loss": 3.7105,
"step": 7700
},
{
"epoch": 60.93,
"learning_rate": 7.800000000000001e-05,
"loss": 3.6394,
"step": 7800
},
{
"epoch": 61.71,
"learning_rate": 7.900000000000001e-05,
"loss": 3.6262,
"step": 7900
},
{
"epoch": 62.5,
"learning_rate": 8e-05,
"loss": 3.5924,
"step": 8000
},
{
"epoch": 63.28,
"learning_rate": 8.1e-05,
"loss": 3.558,
"step": 8100
},
{
"epoch": 64.06,
"learning_rate": 8.2e-05,
"loss": 3.5255,
"step": 8200
},
{
"epoch": 64.84,
"learning_rate": 8.3e-05,
"loss": 3.4602,
"step": 8300
},
{
"epoch": 65.62,
"learning_rate": 8.4e-05,
"loss": 3.4641,
"step": 8400
},
{
"epoch": 66.4,
"learning_rate": 8.5e-05,
"loss": 3.435,
"step": 8500
},
{
"epoch": 67.19,
"learning_rate": 8.6e-05,
"loss": 3.408,
"step": 8600
},
{
"epoch": 67.96,
"learning_rate": 8.7e-05,
"loss": 3.3594,
"step": 8700
},
{
"epoch": 68.74,
"learning_rate": 8.800000000000001e-05,
"loss": 3.3593,
"step": 8800
},
{
"epoch": 69.53,
"learning_rate": 8.900000000000001e-05,
"loss": 3.3372,
"step": 8900
},
{
"epoch": 70.31,
"learning_rate": 9e-05,
"loss": 3.3217,
"step": 9000
},
{
"epoch": 71.09,
"learning_rate": 9.1e-05,
"loss": 3.2985,
"step": 9100
},
{
"epoch": 71.87,
"learning_rate": 9.200000000000001e-05,
"loss": 3.2509,
"step": 9200
},
{
"epoch": 72.65,
"learning_rate": 9.300000000000001e-05,
"loss": 3.2584,
"step": 9300
},
{
"epoch": 73.43,
"learning_rate": 9.4e-05,
"loss": 3.2386,
"step": 9400
},
{
"epoch": 74.22,
"learning_rate": 9.5e-05,
"loss": 3.2232,
"step": 9500
},
{
"epoch": 74.99,
"learning_rate": 9.6e-05,
"loss": 3.1786,
"step": 9600
},
{
"epoch": 75.78,
"learning_rate": 9.7e-05,
"loss": 3.1855,
"step": 9700
},
{
"epoch": 76.56,
"learning_rate": 9.8e-05,
"loss": 3.1737,
"step": 9800
},
{
"epoch": 77.34,
"learning_rate": 9.900000000000001e-05,
"loss": 3.1565,
"step": 9900
},
{
"epoch": 78.12,
"learning_rate": 0.0001,
"loss": 3.1442,
"step": 10000
}
],
"max_steps": 20480,
"num_train_epochs": 160,
"total_flos": 6.779220101431296e+17,
"trial_name": null,
"trial_params": null
}