trainer_state.json

{
 "best_metric": null,
 "best_model_checkpoint": null,
 "epoch": 14.349775784753364,
 "global_step": 3200,
 "is_hyper_param_search": false,
 "is_local_process_zero": true,
 "is_world_process_zero": true,
 "log_history": [
 {
 "epoch": 0.22,
 "learning_rate": 0.0002,
 "loss": 0.6202,
 "step": 50
 },
 {
 "epoch": 0.45,
 "learning_rate": 0.0002,
 "loss": 0.4487,
 "step": 100
 },
 {
 "epoch": 0.67,
 "learning_rate": 0.0002,
 "loss": 0.419,
 "step": 150
 },
 {
 "epoch": 0.9,
 "learning_rate": 0.0002,
 "loss": 0.4151,
 "step": 200
 },
 {
 "epoch": 1.12,
 "learning_rate": 0.0002,
 "loss": 0.3933,
 "step": 250
 },
 {
 "epoch": 1.35,
 "learning_rate": 0.0002,
 "loss": 0.3797,
 "step": 300
 },
 {
 "epoch": 1.57,
 "learning_rate": 0.0002,
 "loss": 0.3688,
 "step": 350
 },
 {
 "epoch": 1.79,
 "learning_rate": 0.0002,
 "loss": 0.3749,
 "step": 400
 },
 {
 "epoch": 2.02,
 "learning_rate": 0.0002,
 "loss": 0.3624,
 "step": 450
 },
 {
 "epoch": 2.24,
 "learning_rate": 0.0002,
 "loss": 0.3331,
 "step": 500
 },
 {
 "epoch": 2.47,
 "learning_rate": 0.0002,
 "loss": 0.3347,
 "step": 550
 },
 {
 "epoch": 2.69,
 "learning_rate": 0.0002,
 "loss": 0.3533,
 "step": 600
 },
 {
 "epoch": 2.91,
 "learning_rate": 0.0002,
 "loss": 0.3413,
 "step": 650
 },
 {
 "epoch": 3.14,
 "learning_rate": 0.0002,
 "loss": 0.3242,
 "step": 700
 },
 {
 "epoch": 3.36,
 "learning_rate": 0.0002,
 "loss": 0.3091,
 "step": 750
 },
 {
 "epoch": 3.59,
 "learning_rate": 0.0002,
 "loss": 0.3166,
 "step": 800
 },
 {
 "epoch": 3.81,
 "learning_rate": 0.0002,
 "loss": 0.3121,
 "step": 850
 },
 {
 "epoch": 4.04,
 "learning_rate": 0.0002,
 "loss": 0.304,
 "step": 900
 },
 {
 "epoch": 4.26,
 "learning_rate": 0.0002,
 "loss": 0.2776,
 "step": 950
 },
 {
 "epoch": 4.48,
 "learning_rate": 0.0002,
 "loss": 0.2783,
 "step": 1000
 },
 {
 "epoch": 4.71,
 "learning_rate": 0.0002,
 "loss": 0.2836,
 "step": 1050
 },
 {
 "epoch": 4.93,
 "learning_rate": 0.0002,
 "loss": 0.2931,
 "step": 1100
 },
 {
 "epoch": 5.16,
 "learning_rate": 0.0002,
 "loss": 0.2589,
 "step": 1150
 },
 {
 "epoch": 5.38,
 "learning_rate": 0.0002,
 "loss": 0.2525,
 "step": 1200
 },
 {
 "epoch": 5.61,
 "learning_rate": 0.0002,
 "loss": 0.255,
 "step": 1250
 },
 {
 "epoch": 5.83,
 "learning_rate": 0.0002,
 "loss": 0.2564,
 "step": 1300
 },
 {
 "epoch": 6.05,
 "learning_rate": 0.0002,
 "loss": 0.242,
 "step": 1350
 },
 {
 "epoch": 6.28,
 "learning_rate": 0.0002,
 "loss": 0.2092,
 "step": 1400
 },
 {
 "epoch": 6.5,
 "learning_rate": 0.0002,
 "loss": 0.2172,
 "step": 1450
 },
 {
 "epoch": 6.73,
 "learning_rate": 0.0002,
 "loss": 0.2233,
 "step": 1500
 },
 {
 "epoch": 6.95,
 "learning_rate": 0.0002,
 "loss": 0.2261,
 "step": 1550
 },
 {
 "epoch": 7.17,
 "learning_rate": 0.0002,
 "loss": 0.1944,
 "step": 1600
 },
 {
 "epoch": 7.4,
 "learning_rate": 0.0002,
 "loss": 0.1803,
 "step": 1650
 },
 {
 "epoch": 7.62,
 "learning_rate": 0.0002,
 "loss": 0.1852,
 "step": 1700
 },
 {
 "epoch": 7.85,
 "learning_rate": 0.0002,
 "loss": 0.1931,
 "step": 1750
 },
 {
 "epoch": 8.07,
 "learning_rate": 0.0002,
 "loss": 0.1755,
 "step": 1800
 },
 {
 "epoch": 8.3,
 "learning_rate": 0.0002,
 "loss": 0.1465,
 "step": 1850
 },
 {
 "epoch": 8.52,
 "learning_rate": 0.0002,
 "loss": 0.1535,
 "step": 1900
 },
 {
 "epoch": 8.74,
 "learning_rate": 0.0002,
 "loss": 0.1542,
 "step": 1950
 },
 {
 "epoch": 8.97,
 "learning_rate": 0.0002,
 "loss": 0.161,
 "step": 2000
 },
 {
 "epoch": 9.19,
 "learning_rate": 0.0002,
 "loss": 0.1205,
 "step": 2050
 },
 {
 "epoch": 9.42,
 "learning_rate": 0.0002,
 "loss": 0.1197,
 "step": 2100
 },
 {
 "epoch": 9.64,
 "learning_rate": 0.0002,
 "loss": 0.1242,
 "step": 2150
 },
 {
 "epoch": 9.87,
 "learning_rate": 0.0002,
 "loss": 0.1277,
 "step": 2200
 },
 {
 "epoch": 10.09,
 "learning_rate": 0.0002,
 "loss": 0.1151,
 "step": 2250
 },
 {
 "epoch": 10.31,
 "learning_rate": 0.0002,
 "loss": 0.0925,
 "step": 2300
 },
 {
 "epoch": 10.54,
 "learning_rate": 0.0002,
 "loss": 0.0969,
 "step": 2350
 },
 {
 "epoch": 10.76,
 "learning_rate": 0.0002,
 "loss": 0.1023,
 "step": 2400
 },
 {
 "epoch": 10.99,
 "learning_rate": 0.0002,
 "loss": 0.1016,
 "step": 2450
 },
 {
 "epoch": 11.21,
 "learning_rate": 0.0002,
 "loss": 0.0708,
 "step": 2500
 },
 {
 "epoch": 11.43,
 "learning_rate": 0.0002,
 "loss": 0.0735,
 "step": 2550
 },
 {
 "epoch": 11.66,
 "learning_rate": 0.0002,
 "loss": 0.0804,
 "step": 2600
 },
 {
 "epoch": 11.88,
 "learning_rate": 0.0002,
 "loss": 0.0833,
 "step": 2650
 },
 {
 "epoch": 12.11,
 "learning_rate": 0.0002,
 "loss": 0.072,
 "step": 2700
 },
 {
 "epoch": 12.33,
 "learning_rate": 0.0002,
 "loss": 0.0592,
 "step": 2750
 },
 {
 "epoch": 12.56,
 "learning_rate": 0.0002,
 "loss": 0.0585,
 "step": 2800
 },
 {
 "epoch": 12.78,
 "learning_rate": 0.0002,
 "loss": 0.0647,
 "step": 2850
 },
 {
 "epoch": 13.0,
 "learning_rate": 0.0002,
 "loss": 0.0656,
 "step": 2900
 },
 {
 "epoch": 13.23,
 "learning_rate": 0.0002,
 "loss": 0.0473,
 "step": 2950
 },
 {
 "epoch": 13.45,
 "learning_rate": 0.0002,
 "loss": 0.0509,
 "step": 3000
 },
 {
 "epoch": 13.68,
 "learning_rate": 0.0002,
 "loss": 0.0523,
 "step": 3050
 },
 {
 "epoch": 13.9,
 "learning_rate": 0.0002,
 "loss": 0.0531,
 "step": 3100
 },
 {
 "epoch": 14.13,
 "learning_rate": 0.0002,
 "loss": 0.0455,
 "step": 3150
 },
 {
 "epoch": 14.35,
 "learning_rate": 0.0002,
 "loss": 0.0407,
 "step": 3200
 }
 ],
 "max_steps": 3345,
 "num_train_epochs": 15,
 "total_flos": 5.0781774924831744e+17,
 "trial_name": null,
 "trial_params": null
}