coedit-large / trainer_state.json
ddhruvkr's picture
Upload 9 files
f522bae
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 4.999775432292836,
"global_step": 27830,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.01,
"learning_rate": 0.0001,
"loss": 0.9801,
"step": 50
},
{
"epoch": 0.02,
"learning_rate": 0.0001,
"loss": 0.9375,
"step": 100
},
{
"epoch": 0.03,
"learning_rate": 0.0001,
"loss": 0.8924,
"step": 150
},
{
"epoch": 0.04,
"learning_rate": 0.0001,
"loss": 0.8901,
"step": 200
},
{
"epoch": 0.04,
"learning_rate": 0.0001,
"loss": 0.8608,
"step": 250
},
{
"epoch": 0.05,
"learning_rate": 0.0001,
"loss": 0.8033,
"step": 300
},
{
"epoch": 0.06,
"learning_rate": 0.0001,
"loss": 0.826,
"step": 350
},
{
"epoch": 0.07,
"learning_rate": 0.0001,
"loss": 0.8897,
"step": 400
},
{
"epoch": 0.08,
"learning_rate": 0.0001,
"loss": 0.8379,
"step": 450
},
{
"epoch": 0.09,
"learning_rate": 0.0001,
"loss": 0.8547,
"step": 500
},
{
"epoch": 0.1,
"learning_rate": 0.0001,
"loss": 0.8092,
"step": 550
},
{
"epoch": 0.11,
"learning_rate": 0.0001,
"loss": 0.8155,
"step": 600
},
{
"epoch": 0.12,
"learning_rate": 0.0001,
"loss": 0.7923,
"step": 650
},
{
"epoch": 0.13,
"learning_rate": 0.0001,
"loss": 0.8267,
"step": 700
},
{
"epoch": 0.13,
"learning_rate": 0.0001,
"loss": 0.8055,
"step": 750
},
{
"epoch": 0.14,
"learning_rate": 0.0001,
"loss": 0.8084,
"step": 800
},
{
"epoch": 0.15,
"learning_rate": 0.0001,
"loss": 0.8232,
"step": 850
},
{
"epoch": 0.16,
"learning_rate": 0.0001,
"loss": 0.7805,
"step": 900
},
{
"epoch": 0.17,
"learning_rate": 0.0001,
"loss": 0.8009,
"step": 950
},
{
"epoch": 0.18,
"learning_rate": 0.0001,
"loss": 0.7566,
"step": 1000
},
{
"epoch": 0.19,
"learning_rate": 0.0001,
"loss": 0.7745,
"step": 1050
},
{
"epoch": 0.2,
"learning_rate": 0.0001,
"loss": 0.7858,
"step": 1100
},
{
"epoch": 0.21,
"learning_rate": 0.0001,
"loss": 0.7508,
"step": 1150
},
{
"epoch": 0.22,
"learning_rate": 0.0001,
"loss": 0.8148,
"step": 1200
},
{
"epoch": 0.22,
"learning_rate": 0.0001,
"loss": 0.8054,
"step": 1250
},
{
"epoch": 0.23,
"learning_rate": 0.0001,
"loss": 0.8149,
"step": 1300
},
{
"epoch": 0.24,
"learning_rate": 0.0001,
"loss": 0.7903,
"step": 1350
},
{
"epoch": 0.25,
"learning_rate": 0.0001,
"loss": 0.7937,
"step": 1400
},
{
"epoch": 0.26,
"learning_rate": 0.0001,
"loss": 0.7489,
"step": 1450
},
{
"epoch": 0.27,
"learning_rate": 0.0001,
"loss": 0.7783,
"step": 1500
},
{
"epoch": 0.28,
"learning_rate": 0.0001,
"loss": 0.7757,
"step": 1550
},
{
"epoch": 0.29,
"learning_rate": 0.0001,
"loss": 0.7746,
"step": 1600
},
{
"epoch": 0.3,
"learning_rate": 0.0001,
"loss": 0.778,
"step": 1650
},
{
"epoch": 0.31,
"learning_rate": 0.0001,
"loss": 0.7951,
"step": 1700
},
{
"epoch": 0.31,
"learning_rate": 0.0001,
"loss": 0.7764,
"step": 1750
},
{
"epoch": 0.32,
"learning_rate": 0.0001,
"loss": 0.7385,
"step": 1800
},
{
"epoch": 0.33,
"learning_rate": 0.0001,
"loss": 0.7503,
"step": 1850
},
{
"epoch": 0.34,
"learning_rate": 0.0001,
"loss": 0.7673,
"step": 1900
},
{
"epoch": 0.35,
"learning_rate": 0.0001,
"loss": 0.7718,
"step": 1950
},
{
"epoch": 0.36,
"learning_rate": 0.0001,
"loss": 0.7988,
"step": 2000
},
{
"epoch": 0.37,
"learning_rate": 0.0001,
"loss": 0.7394,
"step": 2050
},
{
"epoch": 0.38,
"learning_rate": 0.0001,
"loss": 0.7757,
"step": 2100
},
{
"epoch": 0.39,
"learning_rate": 0.0001,
"loss": 0.7381,
"step": 2150
},
{
"epoch": 0.4,
"learning_rate": 0.0001,
"loss": 0.7857,
"step": 2200
},
{
"epoch": 0.4,
"learning_rate": 0.0001,
"loss": 0.798,
"step": 2250
},
{
"epoch": 0.41,
"learning_rate": 0.0001,
"loss": 0.7987,
"step": 2300
},
{
"epoch": 0.42,
"learning_rate": 0.0001,
"loss": 0.74,
"step": 2350
},
{
"epoch": 0.43,
"learning_rate": 0.0001,
"loss": 0.7832,
"step": 2400
},
{
"epoch": 0.44,
"learning_rate": 0.0001,
"loss": 0.7566,
"step": 2450
},
{
"epoch": 0.45,
"learning_rate": 0.0001,
"loss": 0.7863,
"step": 2500
},
{
"epoch": 0.46,
"learning_rate": 0.0001,
"loss": 0.7419,
"step": 2550
},
{
"epoch": 0.47,
"learning_rate": 0.0001,
"loss": 0.7553,
"step": 2600
},
{
"epoch": 0.48,
"learning_rate": 0.0001,
"loss": 0.7749,
"step": 2650
},
{
"epoch": 0.49,
"learning_rate": 0.0001,
"loss": 0.8235,
"step": 2700
},
{
"epoch": 0.49,
"learning_rate": 0.0001,
"loss": 0.7366,
"step": 2750
},
{
"epoch": 0.5,
"learning_rate": 0.0001,
"loss": 0.802,
"step": 2800
},
{
"epoch": 0.51,
"learning_rate": 0.0001,
"loss": 0.7669,
"step": 2850
},
{
"epoch": 0.52,
"learning_rate": 0.0001,
"loss": 0.7899,
"step": 2900
},
{
"epoch": 0.53,
"learning_rate": 0.0001,
"loss": 0.7651,
"step": 2950
},
{
"epoch": 0.54,
"learning_rate": 0.0001,
"loss": 0.7202,
"step": 3000
},
{
"epoch": 0.55,
"learning_rate": 0.0001,
"loss": 0.7423,
"step": 3050
},
{
"epoch": 0.56,
"learning_rate": 0.0001,
"loss": 0.7732,
"step": 3100
},
{
"epoch": 0.57,
"learning_rate": 0.0001,
"loss": 0.7635,
"step": 3150
},
{
"epoch": 0.57,
"learning_rate": 0.0001,
"loss": 0.7664,
"step": 3200
},
{
"epoch": 0.58,
"learning_rate": 0.0001,
"loss": 0.7623,
"step": 3250
},
{
"epoch": 0.59,
"learning_rate": 0.0001,
"loss": 0.7787,
"step": 3300
},
{
"epoch": 0.6,
"learning_rate": 0.0001,
"loss": 0.7563,
"step": 3350
},
{
"epoch": 0.61,
"learning_rate": 0.0001,
"loss": 0.7318,
"step": 3400
},
{
"epoch": 0.62,
"learning_rate": 0.0001,
"loss": 0.762,
"step": 3450
},
{
"epoch": 0.63,
"learning_rate": 0.0001,
"loss": 0.782,
"step": 3500
},
{
"epoch": 0.64,
"learning_rate": 0.0001,
"loss": 0.8114,
"step": 3550
},
{
"epoch": 0.65,
"learning_rate": 0.0001,
"loss": 0.7182,
"step": 3600
},
{
"epoch": 0.66,
"learning_rate": 0.0001,
"loss": 0.7546,
"step": 3650
},
{
"epoch": 0.66,
"learning_rate": 0.0001,
"loss": 0.7953,
"step": 3700
},
{
"epoch": 0.67,
"learning_rate": 0.0001,
"loss": 0.7772,
"step": 3750
},
{
"epoch": 0.68,
"learning_rate": 0.0001,
"loss": 0.7737,
"step": 3800
},
{
"epoch": 0.69,
"learning_rate": 0.0001,
"loss": 0.7334,
"step": 3850
},
{
"epoch": 0.7,
"learning_rate": 0.0001,
"loss": 0.7713,
"step": 3900
},
{
"epoch": 0.71,
"learning_rate": 0.0001,
"loss": 0.772,
"step": 3950
},
{
"epoch": 0.72,
"learning_rate": 0.0001,
"loss": 0.7964,
"step": 4000
},
{
"epoch": 0.73,
"learning_rate": 0.0001,
"loss": 0.7997,
"step": 4050
},
{
"epoch": 0.74,
"learning_rate": 0.0001,
"loss": 0.7341,
"step": 4100
},
{
"epoch": 0.75,
"learning_rate": 0.0001,
"loss": 0.7837,
"step": 4150
},
{
"epoch": 0.75,
"learning_rate": 0.0001,
"loss": 0.7973,
"step": 4200
},
{
"epoch": 0.76,
"learning_rate": 0.0001,
"loss": 0.775,
"step": 4250
},
{
"epoch": 0.77,
"learning_rate": 0.0001,
"loss": 0.7599,
"step": 4300
},
{
"epoch": 0.78,
"learning_rate": 0.0001,
"loss": 0.7406,
"step": 4350
},
{
"epoch": 0.79,
"learning_rate": 0.0001,
"loss": 0.7875,
"step": 4400
},
{
"epoch": 0.8,
"learning_rate": 0.0001,
"loss": 0.7264,
"step": 4450
},
{
"epoch": 0.81,
"learning_rate": 0.0001,
"loss": 0.7318,
"step": 4500
},
{
"epoch": 0.82,
"learning_rate": 0.0001,
"loss": 0.7532,
"step": 4550
},
{
"epoch": 0.83,
"learning_rate": 0.0001,
"loss": 0.7386,
"step": 4600
},
{
"epoch": 0.84,
"learning_rate": 0.0001,
"loss": 0.7729,
"step": 4650
},
{
"epoch": 0.84,
"learning_rate": 0.0001,
"loss": 0.7428,
"step": 4700
},
{
"epoch": 0.85,
"learning_rate": 0.0001,
"loss": 0.7561,
"step": 4750
},
{
"epoch": 0.86,
"learning_rate": 0.0001,
"loss": 0.7798,
"step": 4800
},
{
"epoch": 0.87,
"learning_rate": 0.0001,
"loss": 0.7675,
"step": 4850
},
{
"epoch": 0.88,
"learning_rate": 0.0001,
"loss": 0.7443,
"step": 4900
},
{
"epoch": 0.89,
"learning_rate": 0.0001,
"loss": 0.7992,
"step": 4950
},
{
"epoch": 0.9,
"learning_rate": 0.0001,
"loss": 0.7841,
"step": 5000
},
{
"epoch": 0.91,
"learning_rate": 0.0001,
"loss": 0.7626,
"step": 5050
},
{
"epoch": 0.92,
"learning_rate": 0.0001,
"loss": 0.7272,
"step": 5100
},
{
"epoch": 0.93,
"learning_rate": 0.0001,
"loss": 0.7563,
"step": 5150
},
{
"epoch": 0.93,
"learning_rate": 0.0001,
"loss": 0.732,
"step": 5200
},
{
"epoch": 0.94,
"learning_rate": 0.0001,
"loss": 0.7397,
"step": 5250
},
{
"epoch": 0.95,
"learning_rate": 0.0001,
"loss": 0.723,
"step": 5300
},
{
"epoch": 0.96,
"learning_rate": 0.0001,
"loss": 0.7764,
"step": 5350
},
{
"epoch": 0.97,
"learning_rate": 0.0001,
"loss": 0.7605,
"step": 5400
},
{
"epoch": 0.98,
"learning_rate": 0.0001,
"loss": 0.7118,
"step": 5450
},
{
"epoch": 0.99,
"learning_rate": 0.0001,
"loss": 0.7386,
"step": 5500
},
{
"epoch": 1.0,
"learning_rate": 0.0001,
"loss": 0.7196,
"step": 5550
},
{
"epoch": 1.0,
"eval_loss": 0.7622227668762207,
"eval_runtime": 209.9187,
"eval_samples_per_second": 15.306,
"eval_steps_per_second": 0.958,
"step": 5566
},
{
"epoch": 1.01,
"learning_rate": 0.0001,
"loss": 0.6938,
"step": 5600
},
{
"epoch": 1.02,
"learning_rate": 0.0001,
"loss": 0.6087,
"step": 5650
},
{
"epoch": 1.02,
"learning_rate": 0.0001,
"loss": 0.6136,
"step": 5700
},
{
"epoch": 1.03,
"learning_rate": 0.0001,
"loss": 0.6061,
"step": 5750
},
{
"epoch": 1.04,
"learning_rate": 0.0001,
"loss": 0.6124,
"step": 5800
},
{
"epoch": 1.05,
"learning_rate": 0.0001,
"loss": 0.5955,
"step": 5850
},
{
"epoch": 1.06,
"learning_rate": 0.0001,
"loss": 0.6269,
"step": 5900
},
{
"epoch": 1.07,
"learning_rate": 0.0001,
"loss": 0.6517,
"step": 5950
},
{
"epoch": 1.08,
"learning_rate": 0.0001,
"loss": 0.6251,
"step": 6000
},
{
"epoch": 1.09,
"learning_rate": 0.0001,
"loss": 0.6702,
"step": 6050
},
{
"epoch": 1.1,
"learning_rate": 0.0001,
"loss": 0.6072,
"step": 6100
},
{
"epoch": 1.1,
"learning_rate": 0.0001,
"loss": 0.6186,
"step": 6150
},
{
"epoch": 1.11,
"learning_rate": 0.0001,
"loss": 0.6037,
"step": 6200
},
{
"epoch": 1.12,
"learning_rate": 0.0001,
"loss": 0.5849,
"step": 6250
},
{