saibala29's picture
Add fine-tuned Pokedex_T5_Engine
b8837ab
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 27.77777777777778,
"eval_steps": 500,
"global_step": 1000,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.28,
"learning_rate": 1.0000000000000002e-06,
"loss": 13.9056,
"step": 10
},
{
"epoch": 0.56,
"learning_rate": 2.0000000000000003e-06,
"loss": 14.53,
"step": 20
},
{
"epoch": 0.83,
"learning_rate": 3e-06,
"loss": 14.6503,
"step": 30
},
{
"epoch": 1.11,
"learning_rate": 4.000000000000001e-06,
"loss": 13.8701,
"step": 40
},
{
"epoch": 1.39,
"learning_rate": 5e-06,
"loss": 12.7866,
"step": 50
},
{
"epoch": 1.67,
"learning_rate": 6e-06,
"loss": 12.0329,
"step": 60
},
{
"epoch": 1.94,
"learning_rate": 7.000000000000001e-06,
"loss": 11.6797,
"step": 70
},
{
"epoch": 2.22,
"learning_rate": 8.000000000000001e-06,
"loss": 10.1652,
"step": 80
},
{
"epoch": 2.5,
"learning_rate": 9e-06,
"loss": 8.5016,
"step": 90
},
{
"epoch": 2.78,
"learning_rate": 1e-05,
"loss": 7.3051,
"step": 100
},
{
"epoch": 3.06,
"learning_rate": 1.1000000000000001e-05,
"loss": 6.5266,
"step": 110
},
{
"epoch": 3.33,
"learning_rate": 1.2e-05,
"loss": 4.9159,
"step": 120
},
{
"epoch": 3.61,
"learning_rate": 1.3000000000000001e-05,
"loss": 4.1691,
"step": 130
},
{
"epoch": 3.89,
"learning_rate": 1.4000000000000001e-05,
"loss": 2.9038,
"step": 140
},
{
"epoch": 4.17,
"learning_rate": 1.5e-05,
"loss": 2.2194,
"step": 150
},
{
"epoch": 4.44,
"learning_rate": 1.6000000000000003e-05,
"loss": 1.97,
"step": 160
},
{
"epoch": 4.72,
"learning_rate": 1.7000000000000003e-05,
"loss": 1.4839,
"step": 170
},
{
"epoch": 5.0,
"learning_rate": 1.8e-05,
"loss": 1.2807,
"step": 180
},
{
"epoch": 5.28,
"learning_rate": 1.9e-05,
"loss": 1.0124,
"step": 190
},
{
"epoch": 5.56,
"learning_rate": 2e-05,
"loss": 0.6787,
"step": 200
},
{
"epoch": 5.83,
"learning_rate": 2.1e-05,
"loss": 0.5985,
"step": 210
},
{
"epoch": 6.11,
"learning_rate": 2.2000000000000003e-05,
"loss": 0.463,
"step": 220
},
{
"epoch": 6.39,
"learning_rate": 2.3000000000000003e-05,
"loss": 0.4044,
"step": 230
},
{
"epoch": 6.67,
"learning_rate": 2.4e-05,
"loss": 0.3232,
"step": 240
},
{
"epoch": 6.94,
"learning_rate": 2.5e-05,
"loss": 0.3017,
"step": 250
},
{
"epoch": 7.22,
"learning_rate": 2.6000000000000002e-05,
"loss": 0.2714,
"step": 260
},
{
"epoch": 7.5,
"learning_rate": 2.7000000000000002e-05,
"loss": 0.2657,
"step": 270
},
{
"epoch": 7.78,
"learning_rate": 2.8000000000000003e-05,
"loss": 0.1915,
"step": 280
},
{
"epoch": 8.06,
"learning_rate": 2.9e-05,
"loss": 0.1732,
"step": 290
},
{
"epoch": 8.33,
"learning_rate": 3e-05,
"loss": 0.1623,
"step": 300
},
{
"epoch": 8.61,
"learning_rate": 3.1e-05,
"loss": 0.1401,
"step": 310
},
{
"epoch": 8.89,
"learning_rate": 3.2000000000000005e-05,
"loss": 0.1644,
"step": 320
},
{
"epoch": 9.17,
"learning_rate": 3.3e-05,
"loss": 0.1303,
"step": 330
},
{
"epoch": 9.44,
"learning_rate": 3.4000000000000007e-05,
"loss": 0.1083,
"step": 340
},
{
"epoch": 9.72,
"learning_rate": 3.5e-05,
"loss": 0.1249,
"step": 350
},
{
"epoch": 10.0,
"learning_rate": 3.6e-05,
"loss": 0.1037,
"step": 360
},
{
"epoch": 10.28,
"learning_rate": 3.7e-05,
"loss": 0.1048,
"step": 370
},
{
"epoch": 10.56,
"learning_rate": 3.8e-05,
"loss": 0.0925,
"step": 380
},
{
"epoch": 10.83,
"learning_rate": 3.9000000000000006e-05,
"loss": 0.0976,
"step": 390
},
{
"epoch": 11.11,
"learning_rate": 4e-05,
"loss": 0.0796,
"step": 400
},
{
"epoch": 11.39,
"learning_rate": 4.1e-05,
"loss": 0.0811,
"step": 410
},
{
"epoch": 11.67,
"learning_rate": 4.2e-05,
"loss": 0.0789,
"step": 420
},
{
"epoch": 11.94,
"learning_rate": 4.3e-05,
"loss": 0.0788,
"step": 430
},
{
"epoch": 12.22,
"learning_rate": 4.4000000000000006e-05,
"loss": 0.0674,
"step": 440
},
{
"epoch": 12.5,
"learning_rate": 4.5e-05,
"loss": 0.0632,
"step": 450
},
{
"epoch": 12.78,
"learning_rate": 4.600000000000001e-05,
"loss": 0.0779,
"step": 460
},
{
"epoch": 13.06,
"learning_rate": 4.7e-05,
"loss": 0.0596,
"step": 470
},
{
"epoch": 13.33,
"learning_rate": 4.8e-05,
"loss": 0.0568,
"step": 480
},
{
"epoch": 13.61,
"learning_rate": 4.9e-05,
"loss": 0.0647,
"step": 490
},
{
"epoch": 13.89,
"learning_rate": 5e-05,
"loss": 0.0574,
"step": 500
},
{
"epoch": 14.17,
"learning_rate": 4.961538461538462e-05,
"loss": 0.0584,
"step": 510
},
{
"epoch": 14.44,
"learning_rate": 4.923076923076924e-05,
"loss": 0.0468,
"step": 520
},
{
"epoch": 14.72,
"learning_rate": 4.884615384615385e-05,
"loss": 0.055,
"step": 530
},
{
"epoch": 15.0,
"learning_rate": 4.846153846153846e-05,
"loss": 0.05,
"step": 540
},
{
"epoch": 15.28,
"learning_rate": 4.8076923076923084e-05,
"loss": 0.0502,
"step": 550
},
{
"epoch": 15.56,
"learning_rate": 4.76923076923077e-05,
"loss": 0.048,
"step": 560
},
{
"epoch": 15.83,
"learning_rate": 4.730769230769231e-05,
"loss": 0.0465,
"step": 570
},
{
"epoch": 16.11,
"learning_rate": 4.692307692307693e-05,
"loss": 0.0477,
"step": 580
},
{
"epoch": 16.39,
"learning_rate": 4.653846153846154e-05,
"loss": 0.0451,
"step": 590
},
{
"epoch": 16.67,
"learning_rate": 4.615384615384616e-05,
"loss": 0.0345,
"step": 600
},
{
"epoch": 16.94,
"learning_rate": 4.576923076923077e-05,
"loss": 0.0443,
"step": 610
},
{
"epoch": 17.22,
"learning_rate": 4.538461538461539e-05,
"loss": 0.034,
"step": 620
},
{
"epoch": 17.5,
"learning_rate": 4.5e-05,
"loss": 0.0422,
"step": 630
},
{
"epoch": 17.78,
"learning_rate": 4.461538461538462e-05,
"loss": 0.0385,
"step": 640
},
{
"epoch": 18.06,
"learning_rate": 4.423076923076923e-05,
"loss": 0.0339,
"step": 650
},
{
"epoch": 18.33,
"learning_rate": 4.384615384615385e-05,
"loss": 0.0322,
"step": 660
},
{
"epoch": 18.61,
"learning_rate": 4.346153846153846e-05,
"loss": 0.0319,
"step": 670
},
{
"epoch": 18.89,
"learning_rate": 4.3076923076923084e-05,
"loss": 0.0358,
"step": 680
},
{
"epoch": 19.17,
"learning_rate": 4.269230769230769e-05,
"loss": 0.0365,
"step": 690
},
{
"epoch": 19.44,
"learning_rate": 4.230769230769231e-05,
"loss": 0.0349,
"step": 700
},
{
"epoch": 19.72,
"learning_rate": 4.192307692307693e-05,
"loss": 0.034,
"step": 710
},
{
"epoch": 20.0,
"learning_rate": 4.1538461538461544e-05,
"loss": 0.031,
"step": 720
},
{
"epoch": 20.28,
"learning_rate": 4.115384615384615e-05,
"loss": 0.0394,
"step": 730
},
{
"epoch": 20.56,
"learning_rate": 4.0769230769230773e-05,
"loss": 0.0266,
"step": 740
},
{
"epoch": 20.83,
"learning_rate": 4.038461538461539e-05,
"loss": 0.0274,
"step": 750
},
{
"epoch": 21.11,
"learning_rate": 4e-05,
"loss": 0.0227,
"step": 760
},
{
"epoch": 21.39,
"learning_rate": 3.961538461538462e-05,
"loss": 0.0299,
"step": 770
},
{
"epoch": 21.67,
"learning_rate": 3.923076923076923e-05,
"loss": 0.0262,
"step": 780
},
{
"epoch": 21.94,
"learning_rate": 3.884615384615385e-05,
"loss": 0.0218,
"step": 790
},
{
"epoch": 22.22,
"learning_rate": 3.846153846153846e-05,
"loss": 0.0253,
"step": 800
},
{
"epoch": 22.5,
"learning_rate": 3.807692307692308e-05,
"loss": 0.0336,
"step": 810
},
{
"epoch": 22.78,
"learning_rate": 3.769230769230769e-05,
"loss": 0.0288,
"step": 820
},
{
"epoch": 23.06,
"learning_rate": 3.730769230769231e-05,
"loss": 0.0233,
"step": 830
},
{
"epoch": 23.33,
"learning_rate": 3.692307692307693e-05,
"loss": 0.0276,
"step": 840
},
{
"epoch": 23.61,
"learning_rate": 3.653846153846154e-05,
"loss": 0.0184,
"step": 850
},
{
"epoch": 23.89,
"learning_rate": 3.615384615384615e-05,
"loss": 0.029,
"step": 860
},
{
"epoch": 24.17,
"learning_rate": 3.5769230769230774e-05,
"loss": 0.0197,
"step": 870
},
{
"epoch": 24.44,
"learning_rate": 3.538461538461539e-05,
"loss": 0.0224,
"step": 880
},
{
"epoch": 24.72,
"learning_rate": 3.5e-05,
"loss": 0.0248,
"step": 890
},
{
"epoch": 25.0,
"learning_rate": 3.461538461538462e-05,
"loss": 0.0286,
"step": 900
},
{
"epoch": 25.28,
"learning_rate": 3.4230769230769234e-05,
"loss": 0.0241,
"step": 910
},
{
"epoch": 25.56,
"learning_rate": 3.384615384615385e-05,
"loss": 0.0217,
"step": 920
},
{
"epoch": 25.83,
"learning_rate": 3.346153846153846e-05,
"loss": 0.021,
"step": 930
},
{
"epoch": 26.11,
"learning_rate": 3.307692307692308e-05,
"loss": 0.0229,
"step": 940
},
{
"epoch": 26.39,
"learning_rate": 3.269230769230769e-05,
"loss": 0.0246,
"step": 950
},
{
"epoch": 26.67,
"learning_rate": 3.230769230769231e-05,
"loss": 0.0238,
"step": 960
},
{
"epoch": 26.94,
"learning_rate": 3.192307692307692e-05,
"loss": 0.0216,
"step": 970
},
{
"epoch": 27.22,
"learning_rate": 3.153846153846154e-05,
"loss": 0.0257,
"step": 980
},
{
"epoch": 27.5,
"learning_rate": 3.115384615384615e-05,
"loss": 0.0193,
"step": 990
},
{
"epoch": 27.78,
"learning_rate": 3.0769230769230774e-05,
"loss": 0.017,
"step": 1000
}
],
"logging_steps": 10,
"max_steps": 1800,
"num_input_tokens_seen": 0,
"num_train_epochs": 50,
"save_steps": 500,
"total_flos": 541367205888000.0,
"train_batch_size": 4,
"trial_name": null,
"trial_params": null
}