nekomata-14b-gozaru / trainer_state.json
ayousanz's picture
Upload folder using huggingface_hub
2956f85 verified
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.13320013320013321,
"eval_steps": 187.0,
"global_step": 1000,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 1.4123,
"step": 10
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 1.5921,
"step": 20
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 1.3871,
"step": 30
},
{
"epoch": 0.01,
"learning_rate": 0.0002,
"loss": 1.1673,
"step": 40
},
{
"epoch": 0.01,
"learning_rate": 0.0002,
"loss": 0.9691,
"step": 50
},
{
"epoch": 0.01,
"learning_rate": 0.0002,
"loss": 1.2454,
"step": 60
},
{
"epoch": 0.01,
"learning_rate": 0.0002,
"loss": 1.3059,
"step": 70
},
{
"epoch": 0.01,
"learning_rate": 0.0002,
"loss": 1.1246,
"step": 80
},
{
"epoch": 0.01,
"learning_rate": 0.0002,
"loss": 1.1568,
"step": 90
},
{
"epoch": 0.01,
"learning_rate": 0.0002,
"loss": 1.4594,
"step": 100
},
{
"epoch": 0.01,
"learning_rate": 0.0002,
"loss": 1.87,
"step": 110
},
{
"epoch": 0.02,
"learning_rate": 0.0002,
"loss": 1.9312,
"step": 120
},
{
"epoch": 0.02,
"learning_rate": 0.0002,
"loss": 1.6632,
"step": 130
},
{
"epoch": 0.02,
"learning_rate": 0.0002,
"loss": 2.0367,
"step": 140
},
{
"epoch": 0.02,
"learning_rate": 0.0002,
"loss": 1.8595,
"step": 150
},
{
"epoch": 0.02,
"learning_rate": 0.0002,
"loss": 1.8836,
"step": 160
},
{
"epoch": 0.02,
"learning_rate": 0.0002,
"loss": 1.7736,
"step": 170
},
{
"epoch": 0.02,
"learning_rate": 0.0002,
"loss": 1.8143,
"step": 180
},
{
"epoch": 0.03,
"learning_rate": 0.0002,
"loss": 1.7943,
"step": 190
},
{
"epoch": 0.03,
"learning_rate": 0.0002,
"loss": 2.0146,
"step": 200
},
{
"epoch": 0.03,
"learning_rate": 0.0002,
"loss": 1.7404,
"step": 210
},
{
"epoch": 0.03,
"learning_rate": 0.0002,
"loss": 2.1082,
"step": 220
},
{
"epoch": 0.03,
"learning_rate": 0.0002,
"loss": 1.7506,
"step": 230
},
{
"epoch": 0.03,
"learning_rate": 0.0002,
"loss": 1.6864,
"step": 240
},
{
"epoch": 0.03,
"learning_rate": 0.0002,
"loss": 1.9186,
"step": 250
},
{
"epoch": 0.03,
"learning_rate": 0.0002,
"loss": 1.8506,
"step": 260
},
{
"epoch": 0.04,
"learning_rate": 0.0002,
"loss": 1.9558,
"step": 270
},
{
"epoch": 0.04,
"learning_rate": 0.0002,
"loss": 1.6685,
"step": 280
},
{
"epoch": 0.04,
"learning_rate": 0.0002,
"loss": 1.9273,
"step": 290
},
{
"epoch": 0.04,
"learning_rate": 0.0002,
"loss": 1.8136,
"step": 300
},
{
"epoch": 0.04,
"learning_rate": 0.0002,
"loss": 1.7864,
"step": 310
},
{
"epoch": 0.04,
"learning_rate": 0.0002,
"loss": 1.5767,
"step": 320
},
{
"epoch": 0.04,
"learning_rate": 0.0002,
"loss": 1.8496,
"step": 330
},
{
"epoch": 0.05,
"learning_rate": 0.0002,
"loss": 1.7255,
"step": 340
},
{
"epoch": 0.05,
"learning_rate": 0.0002,
"loss": 1.9739,
"step": 350
},
{
"epoch": 0.05,
"learning_rate": 0.0002,
"loss": 2.0508,
"step": 360
},
{
"epoch": 0.05,
"learning_rate": 0.0002,
"loss": 1.8155,
"step": 370
},
{
"epoch": 0.05,
"learning_rate": 0.0002,
"loss": 1.5596,
"step": 380
},
{
"epoch": 0.05,
"learning_rate": 0.0002,
"loss": 1.5386,
"step": 390
},
{
"epoch": 0.05,
"learning_rate": 0.0002,
"loss": 1.8442,
"step": 400
},
{
"epoch": 0.05,
"learning_rate": 0.0002,
"loss": 1.6421,
"step": 410
},
{
"epoch": 0.06,
"learning_rate": 0.0002,
"loss": 1.7501,
"step": 420
},
{
"epoch": 0.06,
"learning_rate": 0.0002,
"loss": 1.6787,
"step": 430
},
{
"epoch": 0.06,
"learning_rate": 0.0002,
"loss": 1.8486,
"step": 440
},
{
"epoch": 0.06,
"learning_rate": 0.0002,
"loss": 1.96,
"step": 450
},
{
"epoch": 0.06,
"learning_rate": 0.0002,
"loss": 1.6794,
"step": 460
},
{
"epoch": 0.06,
"learning_rate": 0.0002,
"loss": 1.6503,
"step": 470
},
{
"epoch": 0.06,
"learning_rate": 0.0002,
"loss": 1.7336,
"step": 480
},
{
"epoch": 0.07,
"learning_rate": 0.0002,
"loss": 1.649,
"step": 490
},
{
"epoch": 0.07,
"learning_rate": 0.0002,
"loss": 1.8043,
"step": 500
},
{
"epoch": 0.07,
"learning_rate": 0.0002,
"loss": 1.7038,
"step": 510
},
{
"epoch": 0.07,
"learning_rate": 0.0002,
"loss": 1.7559,
"step": 520
},
{
"epoch": 0.07,
"learning_rate": 0.0002,
"loss": 1.8022,
"step": 530
},
{
"epoch": 0.07,
"learning_rate": 0.0002,
"loss": 1.6923,
"step": 540
},
{
"epoch": 0.07,
"learning_rate": 0.0002,
"loss": 2.0974,
"step": 550
},
{
"epoch": 0.07,
"learning_rate": 0.0002,
"loss": 1.7751,
"step": 560
},
{
"epoch": 0.08,
"learning_rate": 0.0002,
"loss": 1.8643,
"step": 570
},
{
"epoch": 0.08,
"learning_rate": 0.0002,
"loss": 1.6191,
"step": 580
},
{
"epoch": 0.08,
"learning_rate": 0.0002,
"loss": 1.51,
"step": 590
},
{
"epoch": 0.08,
"learning_rate": 0.0002,
"loss": 2.0246,
"step": 600
},
{
"epoch": 0.08,
"learning_rate": 0.0002,
"loss": 1.6109,
"step": 610
},
{
"epoch": 0.08,
"learning_rate": 0.0002,
"loss": 1.909,
"step": 620
},
{
"epoch": 0.08,
"learning_rate": 0.0002,
"loss": 1.9507,
"step": 630
},
{
"epoch": 0.09,
"learning_rate": 0.0002,
"loss": 1.6672,
"step": 640
},
{
"epoch": 0.09,
"learning_rate": 0.0002,
"loss": 1.8075,
"step": 650
},
{
"epoch": 0.09,
"learning_rate": 0.0002,
"loss": 1.6956,
"step": 660
},
{
"epoch": 0.09,
"learning_rate": 0.0002,
"loss": 1.8209,
"step": 670
},
{
"epoch": 0.09,
"learning_rate": 0.0002,
"loss": 1.6925,
"step": 680
},
{
"epoch": 0.09,
"learning_rate": 0.0002,
"loss": 1.9247,
"step": 690
},
{
"epoch": 0.09,
"learning_rate": 0.0002,
"loss": 1.922,
"step": 700
},
{
"epoch": 0.09,
"learning_rate": 0.0002,
"loss": 1.926,
"step": 710
},
{
"epoch": 0.1,
"learning_rate": 0.0002,
"loss": 1.6429,
"step": 720
},
{
"epoch": 0.1,
"learning_rate": 0.0002,
"loss": 1.793,
"step": 730
},
{
"epoch": 0.1,
"learning_rate": 0.0002,
"loss": 1.7654,
"step": 740
},
{
"epoch": 0.1,
"learning_rate": 0.0002,
"loss": 1.8836,
"step": 750
},
{
"epoch": 0.1,
"learning_rate": 0.0002,
"loss": 1.643,
"step": 760
},
{
"epoch": 0.1,
"learning_rate": 0.0002,
"loss": 2.0208,
"step": 770
},
{
"epoch": 0.1,
"learning_rate": 0.0002,
"loss": 1.6414,
"step": 780
},
{
"epoch": 0.11,
"learning_rate": 0.0002,
"loss": 1.6817,
"step": 790
},
{
"epoch": 0.11,
"learning_rate": 0.0002,
"loss": 1.9908,
"step": 800
},
{
"epoch": 0.11,
"learning_rate": 0.0002,
"loss": 1.6128,
"step": 810
},
{
"epoch": 0.11,
"learning_rate": 0.0002,
"loss": 1.7682,
"step": 820
},
{
"epoch": 0.11,
"learning_rate": 0.0002,
"loss": 1.7711,
"step": 830
},
{
"epoch": 0.11,
"learning_rate": 0.0002,
"loss": 1.6622,
"step": 840
},
{
"epoch": 0.11,
"learning_rate": 0.0002,
"loss": 1.8117,
"step": 850
},
{
"epoch": 0.11,
"learning_rate": 0.0002,
"loss": 1.795,
"step": 860
},
{
"epoch": 0.12,
"learning_rate": 0.0002,
"loss": 1.5294,
"step": 870
},
{
"epoch": 0.12,
"learning_rate": 0.0002,
"loss": 1.7137,
"step": 880
},
{
"epoch": 0.12,
"learning_rate": 0.0002,
"loss": 1.5968,
"step": 890
},
{
"epoch": 0.12,
"learning_rate": 0.0002,
"loss": 1.6621,
"step": 900
},
{
"epoch": 0.12,
"learning_rate": 0.0002,
"loss": 1.742,
"step": 910
},
{
"epoch": 0.12,
"learning_rate": 0.0002,
"loss": 1.6632,
"step": 920
},
{
"epoch": 0.12,
"learning_rate": 0.0002,
"loss": 1.684,
"step": 930
},
{
"epoch": 0.13,
"learning_rate": 0.0002,
"loss": 1.6469,
"step": 940
},
{
"epoch": 0.13,
"learning_rate": 0.0002,
"loss": 1.9193,
"step": 950
},
{
"epoch": 0.13,
"learning_rate": 0.0002,
"loss": 1.7879,
"step": 960
},
{
"epoch": 0.13,
"learning_rate": 0.0002,
"loss": 1.8277,
"step": 970
},
{
"epoch": 0.13,
"learning_rate": 0.0002,
"loss": 1.8026,
"step": 980
},
{
"epoch": 0.13,
"learning_rate": 0.0002,
"loss": 1.8083,
"step": 990
},
{
"epoch": 0.13,
"learning_rate": 0.0002,
"loss": 1.7618,
"step": 1000
}
],
"logging_steps": 10,
"max_steps": 1000,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 100,
"total_flos": 2.025659089287168e+16,
"train_batch_size": 1,
"trial_name": null,
"trial_params": null
}