led-large-book-summary / trainer_state.json
pszemraj's picture
add additional 2-epoch checkpoint, better regularization
665558b
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 2.9914638001896936,
"global_step": 294,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.05,
"learning_rate": 7.5e-06,
"loss": 0.481,
"step": 5
},
{
"epoch": 0.1,
"learning_rate": 1.5e-05,
"loss": 0.5091,
"step": 10
},
{
"epoch": 0.15,
"learning_rate": 2.25e-05,
"loss": 0.4303,
"step": 15
},
{
"epoch": 0.2,
"learning_rate": 3e-05,
"loss": 0.4055,
"step": 20
},
{
"epoch": 0.25,
"learning_rate": 2.998662940889891e-05,
"loss": 0.4338,
"step": 25
},
{
"epoch": 0.3,
"learning_rate": 2.9946541471956496e-05,
"loss": 0.4793,
"step": 30
},
{
"epoch": 0.35,
"learning_rate": 2.9879807655761145e-05,
"loss": 0.4291,
"step": 35
},
{
"epoch": 0.4,
"learning_rate": 2.9786546929722055e-05,
"loss": 0.4908,
"step": 40
},
{
"epoch": 0.46,
"learning_rate": 2.966692555397705e-05,
"loss": 0.463,
"step": 45
},
{
"epoch": 0.51,
"learning_rate": 2.9521156782993066e-05,
"loss": 0.528,
"step": 50
},
{
"epoch": 0.56,
"learning_rate": 2.9349500485387718e-05,
"loss": 0.5178,
"step": 55
},
{
"epoch": 0.61,
"learning_rate": 2.9152262680649704e-05,
"loss": 0.4602,
"step": 60
},
{
"epoch": 0.66,
"learning_rate": 2.8929794993583937e-05,
"loss": 0.5044,
"step": 65
},
{
"epoch": 0.71,
"learning_rate": 2.8682494027454e-05,
"loss": 0.4217,
"step": 70
},
{
"epoch": 0.76,
"learning_rate": 2.8410800656939512e-05,
"loss": 0.502,
"step": 75
},
{
"epoch": 0.81,
"learning_rate": 2.811519924216873e-05,
"loss": 0.4549,
"step": 80
},
{
"epoch": 0.86,
"learning_rate": 2.779621676522777e-05,
"loss": 0.5692,
"step": 85
},
{
"epoch": 0.91,
"learning_rate": 2.7454421890685647e-05,
"loss": 0.4312,
"step": 90
},
{
"epoch": 0.96,
"learning_rate": 2.709042395181008e-05,
"loss": 0.4938,
"step": 95
},
{
"epoch": 1.02,
"learning_rate": 2.6704871864281377e-05,
"loss": 0.5433,
"step": 100
},
{
"epoch": 1.07,
"learning_rate": 2.6298452969340952e-05,
"loss": 0.3459,
"step": 105
},
{
"epoch": 1.12,
"learning_rate": 2.58718918084368e-05,
"loss": 0.3739,
"step": 110
},
{
"epoch": 1.17,
"learning_rate": 2.5425948831550528e-05,
"loss": 0.375,
"step": 115
},
{
"epoch": 1.22,
"learning_rate": 2.496141904150859e-05,
"loss": 0.3809,
"step": 120
},
{
"epoch": 1.27,
"learning_rate": 2.447913057669456e-05,
"loss": 0.4183,
"step": 125
},
{
"epoch": 1.32,
"learning_rate": 2.3979943234689226e-05,
"loss": 0.4207,
"step": 130
},
{
"epoch": 1.37,
"learning_rate": 2.3464746939470288e-05,
"loss": 0.3767,
"step": 135
},
{
"epoch": 1.42,
"learning_rate": 2.2934460154904436e-05,
"loss": 0.4248,
"step": 140
},
{
"epoch": 1.48,
"learning_rate": 2.2390028247360042e-05,
"loss": 0.3374,
"step": 145
},
{
"epoch": 1.53,
"learning_rate": 2.183242180035951e-05,
"loss": 0.4582,
"step": 150
},
{
"epoch": 1.58,
"learning_rate": 2.1262634884275948e-05,
"loss": 0.4153,
"step": 155
},
{
"epoch": 1.63,
"learning_rate": 2.068168328415864e-05,
"loss": 0.409,
"step": 160
},
{
"epoch": 1.68,
"learning_rate": 2.0090602688846884e-05,
"loss": 0.4023,
"step": 165
},
{
"epoch": 1.73,
"learning_rate": 1.9490446844600375e-05,
"loss": 0.3426,
"step": 170
},
{
"epoch": 1.78,
"learning_rate": 1.888228567653781e-05,
"loss": 0.4059,
"step": 175
},
{
"epoch": 1.83,
"learning_rate": 1.8267203381232774e-05,
"loss": 0.4449,
"step": 180
},
{
"epoch": 1.88,
"learning_rate": 1.764629649386713e-05,
"loss": 0.4362,
"step": 185
},
{
"epoch": 1.93,
"learning_rate": 1.7020671933387917e-05,
"loss": 0.4874,
"step": 190
},
{
"epoch": 1.98,
"learning_rate": 1.63914450291526e-05,
"loss": 0.3326,
"step": 195
},
{
"epoch": 2.04,
"learning_rate": 1.5633197410233404e-05,
"loss": 0.4035,
"step": 200
},
{
"epoch": 2.09,
"learning_rate": 1.5e-05,
"loss": 0.3291,
"step": 205
},
{
"epoch": 2.14,
"learning_rate": 1.4366802589766598e-05,
"loss": 0.353,
"step": 210
},
{
"epoch": 2.19,
"learning_rate": 1.373473400935433e-05,
"loss": 0.319,
"step": 215
},
{
"epoch": 2.24,
"learning_rate": 1.3104921076168065e-05,
"loss": 0.341,
"step": 220
},
{
"epoch": 2.29,
"learning_rate": 1.247848658636778e-05,
"loss": 0.3276,
"step": 225
},
{
"epoch": 2.34,
"learning_rate": 1.185654731320877e-05,
"loss": 0.3628,
"step": 230
},
{
"epoch": 2.39,
"learning_rate": 1.124021201611919e-05,
"loss": 0.2727,
"step": 235
},
{
"epoch": 2.45,
"learning_rate": 1.0630579464064182e-05,
"loss": 0.3466,
"step": 240
},
{
"epoch": 2.5,
"learning_rate": 1.0028736476720464e-05,
"loss": 0.3187,
"step": 245
},
{
"epoch": 2.55,
"learning_rate": 9.435755986953485e-06,
"loss": 0.3837,
"step": 250
},
{
"epoch": 2.6,
"learning_rate": 8.852695128051192e-06,
"loss": 0.2955,
"step": 255
},
{
"epoch": 2.65,
"learning_rate": 8.280593349124432e-06,
"loss": 0.3793,
"step": 260
},
{
"epoch": 2.7,
"learning_rate": 7.720470562033787e-06,
"loss": 0.3443,
"step": 265
},
{
"epoch": 2.75,
"learning_rate": 7.17332532314626e-06,
"loss": 0.2915,
"step": 270
},
{
"epoch": 2.8,
"learning_rate": 6.640133053163455e-06,
"loss": 0.3514,
"step": 275
},
{
"epoch": 2.85,
"learning_rate": 6.12184429819474e-06,
"loss": 0.3221,
"step": 280
},
{
"epoch": 2.9,
"learning_rate": 5.619383035175448e-06,
"loss": 0.2903,
"step": 285
},
{
"epoch": 2.95,
"learning_rate": 5.133645024651171e-06,
"loss": 0.3397,
"step": 290
}
],
"max_steps": 392,
"num_train_epochs": 4,
"total_flos": 1.821325738775675e+17,
"trial_name": null,
"trial_params": null
}