dial-t0-silicone / trainer_state.json
julep's picture
feat: Add trained model
3cbc0ff
{
"best_metric": 85.9274,
"best_model_checkpoint": "./output/checkpoint-1600",
"epoch": 1.463719512195122,
"global_step": 1600,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.02,
"learning_rate": 4.9496336996337e-05,
"loss": 0.7035,
"step": 25
},
{
"epoch": 0.05,
"learning_rate": 4.8923992673992674e-05,
"loss": 0.3973,
"step": 50
},
{
"epoch": 0.07,
"learning_rate": 4.8351648351648355e-05,
"loss": 0.3092,
"step": 75
},
{
"epoch": 0.09,
"learning_rate": 4.7779304029304036e-05,
"loss": 0.2813,
"step": 100
},
{
"epoch": 0.11,
"learning_rate": 4.720695970695971e-05,
"loss": 0.2603,
"step": 125
},
{
"epoch": 0.14,
"learning_rate": 4.6634615384615384e-05,
"loss": 0.2371,
"step": 150
},
{
"epoch": 0.16,
"learning_rate": 4.606227106227106e-05,
"loss": 0.2334,
"step": 175
},
{
"epoch": 0.18,
"learning_rate": 4.548992673992674e-05,
"loss": 0.2296,
"step": 200
},
{
"epoch": 0.21,
"learning_rate": 4.491758241758242e-05,
"loss": 0.2219,
"step": 225
},
{
"epoch": 0.23,
"learning_rate": 4.4345238095238095e-05,
"loss": 0.2078,
"step": 250
},
{
"epoch": 0.25,
"learning_rate": 4.3772893772893776e-05,
"loss": 0.2123,
"step": 275
},
{
"epoch": 0.27,
"learning_rate": 4.320054945054946e-05,
"loss": 0.2063,
"step": 300
},
{
"epoch": 0.3,
"learning_rate": 4.262820512820513e-05,
"loss": 0.2002,
"step": 325
},
{
"epoch": 0.32,
"learning_rate": 4.2055860805860806e-05,
"loss": 0.2102,
"step": 350
},
{
"epoch": 0.34,
"learning_rate": 4.148351648351649e-05,
"loss": 0.2003,
"step": 375
},
{
"epoch": 0.37,
"learning_rate": 4.091117216117216e-05,
"loss": 0.2019,
"step": 400
},
{
"epoch": 0.39,
"learning_rate": 4.033882783882784e-05,
"loss": 0.1944,
"step": 425
},
{
"epoch": 0.41,
"learning_rate": 3.9766483516483516e-05,
"loss": 0.1935,
"step": 450
},
{
"epoch": 0.43,
"learning_rate": 3.91941391941392e-05,
"loss": 0.1974,
"step": 475
},
{
"epoch": 0.46,
"learning_rate": 3.862179487179488e-05,
"loss": 0.1922,
"step": 500
},
{
"epoch": 0.48,
"learning_rate": 3.804945054945055e-05,
"loss": 0.188,
"step": 525
},
{
"epoch": 0.5,
"learning_rate": 3.747710622710623e-05,
"loss": 0.1945,
"step": 550
},
{
"epoch": 0.53,
"learning_rate": 3.690476190476191e-05,
"loss": 0.1897,
"step": 575
},
{
"epoch": 0.55,
"learning_rate": 3.633241758241758e-05,
"loss": 0.1797,
"step": 600
},
{
"epoch": 0.57,
"learning_rate": 3.576007326007326e-05,
"loss": 0.1752,
"step": 625
},
{
"epoch": 0.59,
"learning_rate": 3.5187728937728944e-05,
"loss": 0.1797,
"step": 650
},
{
"epoch": 0.62,
"learning_rate": 3.461538461538462e-05,
"loss": 0.1785,
"step": 675
},
{
"epoch": 0.64,
"learning_rate": 3.404304029304029e-05,
"loss": 0.185,
"step": 700
},
{
"epoch": 0.66,
"learning_rate": 3.347069597069597e-05,
"loss": 0.1751,
"step": 725
},
{
"epoch": 0.69,
"learning_rate": 3.289835164835165e-05,
"loss": 0.1799,
"step": 750
},
{
"epoch": 0.71,
"learning_rate": 3.232600732600733e-05,
"loss": 0.1801,
"step": 775
},
{
"epoch": 0.73,
"learning_rate": 3.1753663003663003e-05,
"loss": 0.1748,
"step": 800
},
{
"epoch": 0.73,
"eval_Bleu_1": 0.8552,
"eval_Bleu_2": 0.0009,
"eval_Bleu_3": 0.0001,
"eval_Bleu_4": 0.0,
"eval_ROUGE_L": 0.8552,
"eval_accuracy": 85.52,
"eval_f1": 85.52,
"eval_gen_len": 2.2084,
"eval_loss": 0.17816422879695892,
"eval_precision": 85.52,
"eval_recall": 85.52,
"eval_rouge1": 85.6587,
"eval_rouge2": 3.7183,
"eval_rougeL": 85.6528,
"eval_rougeLsum": 85.6348,
"eval_runtime": 1004.3102,
"eval_samples_per_second": 34.705,
"eval_steps_per_second": 4.338,
"step": 800
},
{
"epoch": 0.75,
"learning_rate": 3.1181318681318685e-05,
"loss": 0.1698,
"step": 825
},
{
"epoch": 0.78,
"learning_rate": 3.0608974358974366e-05,
"loss": 0.1763,
"step": 850
},
{
"epoch": 0.8,
"learning_rate": 3.0036630036630036e-05,
"loss": 0.1655,
"step": 875
},
{
"epoch": 0.82,
"learning_rate": 2.9464285714285718e-05,
"loss": 0.1703,
"step": 900
},
{
"epoch": 0.85,
"learning_rate": 2.8891941391941392e-05,
"loss": 0.174,
"step": 925
},
{
"epoch": 0.87,
"learning_rate": 2.831959706959707e-05,
"loss": 0.1723,
"step": 950
},
{
"epoch": 0.89,
"learning_rate": 2.774725274725275e-05,
"loss": 0.1739,
"step": 975
},
{
"epoch": 0.91,
"learning_rate": 2.7174908424908425e-05,
"loss": 0.1673,
"step": 1000
},
{
"epoch": 0.94,
"learning_rate": 2.6602564102564102e-05,
"loss": 0.1647,
"step": 1025
},
{
"epoch": 0.96,
"learning_rate": 2.6030219780219783e-05,
"loss": 0.1739,
"step": 1050
},
{
"epoch": 0.98,
"learning_rate": 2.5457875457875458e-05,
"loss": 0.1703,
"step": 1075
},
{
"epoch": 1.01,
"learning_rate": 2.488553113553114e-05,
"loss": 0.1727,
"step": 1100
},
{
"epoch": 1.03,
"learning_rate": 2.4313186813186813e-05,
"loss": 0.1603,
"step": 1125
},
{
"epoch": 1.05,
"learning_rate": 2.374084249084249e-05,
"loss": 0.1511,
"step": 1150
},
{
"epoch": 1.07,
"learning_rate": 2.3168498168498172e-05,
"loss": 0.1544,
"step": 1175
},
{
"epoch": 1.1,
"learning_rate": 2.2596153846153846e-05,
"loss": 0.1517,
"step": 1200
},
{
"epoch": 1.12,
"learning_rate": 2.2023809523809524e-05,
"loss": 0.1556,
"step": 1225
},
{
"epoch": 1.14,
"learning_rate": 2.14514652014652e-05,
"loss": 0.1688,
"step": 1250
},
{
"epoch": 1.17,
"learning_rate": 2.0879120879120882e-05,
"loss": 0.1658,
"step": 1275
},
{
"epoch": 1.19,
"learning_rate": 2.0306776556776557e-05,
"loss": 0.1587,
"step": 1300
},
{
"epoch": 1.21,
"learning_rate": 1.9734432234432234e-05,
"loss": 0.1664,
"step": 1325
},
{
"epoch": 1.24,
"learning_rate": 1.9162087912087915e-05,
"loss": 0.1558,
"step": 1350
},
{
"epoch": 1.26,
"learning_rate": 1.858974358974359e-05,
"loss": 0.1591,
"step": 1375
},
{
"epoch": 1.28,
"learning_rate": 1.8017399267399267e-05,
"loss": 0.1558,
"step": 1400
},
{
"epoch": 1.3,
"learning_rate": 1.7445054945054945e-05,
"loss": 0.1583,
"step": 1425
},
{
"epoch": 1.33,
"learning_rate": 1.6872710622710626e-05,
"loss": 0.155,
"step": 1450
},
{
"epoch": 1.35,
"learning_rate": 1.63003663003663e-05,
"loss": 0.1644,
"step": 1475
},
{
"epoch": 1.37,
"learning_rate": 1.5728021978021978e-05,
"loss": 0.1574,
"step": 1500
},
{
"epoch": 1.4,
"learning_rate": 1.5155677655677656e-05,
"loss": 0.1555,
"step": 1525
},
{
"epoch": 1.42,
"learning_rate": 1.4583333333333335e-05,
"loss": 0.1542,
"step": 1550
},
{
"epoch": 1.44,
"learning_rate": 1.4010989010989013e-05,
"loss": 0.1537,
"step": 1575
},
{
"epoch": 1.46,
"learning_rate": 1.3438644688644688e-05,
"loss": 0.1493,
"step": 1600
},
{
"epoch": 1.46,
"eval_Bleu_1": 0.8593,
"eval_Bleu_2": 0.0009,
"eval_Bleu_3": 0.0001,
"eval_Bleu_4": 0.0,
"eval_ROUGE_L": 0.8593,
"eval_accuracy": 85.9274,
"eval_f1": 85.9274,
"eval_gen_len": 2.2038,
"eval_loss": 0.1681133359670639,
"eval_precision": 85.9274,
"eval_recall": 85.9274,
"eval_rouge1": 86.0601,
"eval_rouge2": 3.5662,
"eval_rougeL": 86.0539,
"eval_rougeLsum": 86.0496,
"eval_runtime": 1001.4875,
"eval_samples_per_second": 34.803,
"eval_steps_per_second": 4.351,
"step": 1600
}
],
"max_steps": 2186,
"num_train_epochs": 2,
"total_flos": 2.7769320388994007e+18,
"trial_name": null,
"trial_params": null
}