ryusangwon's picture
Model save
fcdc3bf verified
raw
history blame
12.5 kB
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.697350069735007,
"eval_steps": 500,
"global_step": 1000,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.01,
"learning_rate": 4.9883774988377505e-05,
"loss": 1.7968,
"step": 10
},
{
"epoch": 0.01,
"learning_rate": 4.9767549976755e-05,
"loss": 1.745,
"step": 20
},
{
"epoch": 0.02,
"learning_rate": 4.9651324965132504e-05,
"loss": 1.6936,
"step": 30
},
{
"epoch": 0.03,
"learning_rate": 4.953509995351e-05,
"loss": 1.72,
"step": 40
},
{
"epoch": 0.03,
"learning_rate": 4.9418874941887496e-05,
"loss": 1.6769,
"step": 50
},
{
"epoch": 0.04,
"learning_rate": 4.930264993026499e-05,
"loss": 1.6031,
"step": 60
},
{
"epoch": 0.05,
"learning_rate": 4.9186424918642495e-05,
"loss": 1.606,
"step": 70
},
{
"epoch": 0.06,
"learning_rate": 4.907019990701999e-05,
"loss": 1.6362,
"step": 80
},
{
"epoch": 0.06,
"learning_rate": 4.895397489539749e-05,
"loss": 1.5938,
"step": 90
},
{
"epoch": 0.07,
"learning_rate": 4.883774988377499e-05,
"loss": 1.5678,
"step": 100
},
{
"epoch": 0.08,
"learning_rate": 4.872152487215249e-05,
"loss": 1.5751,
"step": 110
},
{
"epoch": 0.08,
"learning_rate": 4.860529986052999e-05,
"loss": 1.5708,
"step": 120
},
{
"epoch": 0.09,
"learning_rate": 4.848907484890749e-05,
"loss": 1.5404,
"step": 130
},
{
"epoch": 0.1,
"learning_rate": 4.837284983728499e-05,
"loss": 1.5682,
"step": 140
},
{
"epoch": 0.1,
"learning_rate": 4.825662482566248e-05,
"loss": 1.5564,
"step": 150
},
{
"epoch": 0.11,
"learning_rate": 4.8140399814039985e-05,
"loss": 1.6038,
"step": 160
},
{
"epoch": 0.12,
"learning_rate": 4.802417480241748e-05,
"loss": 1.6037,
"step": 170
},
{
"epoch": 0.13,
"learning_rate": 4.7907949790794984e-05,
"loss": 1.5927,
"step": 180
},
{
"epoch": 0.13,
"learning_rate": 4.779172477917248e-05,
"loss": 1.6436,
"step": 190
},
{
"epoch": 0.14,
"learning_rate": 4.767549976754998e-05,
"loss": 1.6203,
"step": 200
},
{
"epoch": 0.15,
"learning_rate": 4.755927475592748e-05,
"loss": 1.6137,
"step": 210
},
{
"epoch": 0.15,
"learning_rate": 4.744304974430498e-05,
"loss": 1.6098,
"step": 220
},
{
"epoch": 0.16,
"learning_rate": 4.732682473268247e-05,
"loss": 1.5774,
"step": 230
},
{
"epoch": 0.17,
"learning_rate": 4.7210599721059973e-05,
"loss": 1.6188,
"step": 240
},
{
"epoch": 0.17,
"learning_rate": 4.709437470943747e-05,
"loss": 1.6105,
"step": 250
},
{
"epoch": 0.18,
"learning_rate": 4.697814969781497e-05,
"loss": 1.6356,
"step": 260
},
{
"epoch": 0.19,
"learning_rate": 4.686192468619247e-05,
"loss": 1.5834,
"step": 270
},
{
"epoch": 0.2,
"learning_rate": 4.674569967456997e-05,
"loss": 1.5534,
"step": 280
},
{
"epoch": 0.2,
"learning_rate": 4.662947466294747e-05,
"loss": 1.5877,
"step": 290
},
{
"epoch": 0.21,
"learning_rate": 4.651324965132497e-05,
"loss": 1.5672,
"step": 300
},
{
"epoch": 0.22,
"learning_rate": 4.6397024639702466e-05,
"loss": 1.5725,
"step": 310
},
{
"epoch": 0.22,
"learning_rate": 4.628079962807996e-05,
"loss": 1.5749,
"step": 320
},
{
"epoch": 0.23,
"learning_rate": 4.6164574616457464e-05,
"loss": 1.5653,
"step": 330
},
{
"epoch": 0.24,
"learning_rate": 4.604834960483496e-05,
"loss": 1.5579,
"step": 340
},
{
"epoch": 0.24,
"learning_rate": 4.593212459321246e-05,
"loss": 1.6035,
"step": 350
},
{
"epoch": 0.25,
"learning_rate": 4.581589958158996e-05,
"loss": 1.5868,
"step": 360
},
{
"epoch": 0.26,
"learning_rate": 4.569967456996746e-05,
"loss": 1.5886,
"step": 370
},
{
"epoch": 0.26,
"learning_rate": 4.558344955834496e-05,
"loss": 1.5933,
"step": 380
},
{
"epoch": 0.27,
"learning_rate": 4.546722454672246e-05,
"loss": 1.5511,
"step": 390
},
{
"epoch": 0.28,
"learning_rate": 4.5350999535099956e-05,
"loss": 1.6039,
"step": 400
},
{
"epoch": 0.29,
"learning_rate": 4.523477452347745e-05,
"loss": 1.5434,
"step": 410
},
{
"epoch": 0.29,
"learning_rate": 4.5118549511854955e-05,
"loss": 1.6576,
"step": 420
},
{
"epoch": 0.3,
"learning_rate": 4.500232450023245e-05,
"loss": 1.5434,
"step": 430
},
{
"epoch": 0.31,
"learning_rate": 4.4886099488609954e-05,
"loss": 1.5774,
"step": 440
},
{
"epoch": 0.31,
"learning_rate": 4.476987447698745e-05,
"loss": 1.5882,
"step": 450
},
{
"epoch": 0.32,
"learning_rate": 4.465364946536495e-05,
"loss": 1.607,
"step": 460
},
{
"epoch": 0.33,
"learning_rate": 4.453742445374245e-05,
"loss": 1.6005,
"step": 470
},
{
"epoch": 0.33,
"learning_rate": 4.442119944211995e-05,
"loss": 1.5715,
"step": 480
},
{
"epoch": 0.34,
"learning_rate": 4.430497443049745e-05,
"loss": 1.5876,
"step": 490
},
{
"epoch": 0.35,
"learning_rate": 4.418874941887494e-05,
"loss": 1.5355,
"step": 500
},
{
"epoch": 0.36,
"learning_rate": 4.407252440725244e-05,
"loss": 1.5767,
"step": 510
},
{
"epoch": 0.36,
"learning_rate": 4.395629939562994e-05,
"loss": 1.6073,
"step": 520
},
{
"epoch": 0.37,
"learning_rate": 4.384007438400744e-05,
"loss": 1.5736,
"step": 530
},
{
"epoch": 0.38,
"learning_rate": 4.372384937238494e-05,
"loss": 1.582,
"step": 540
},
{
"epoch": 0.38,
"learning_rate": 4.3607624360762437e-05,
"loss": 1.5833,
"step": 550
},
{
"epoch": 0.39,
"learning_rate": 4.349139934913994e-05,
"loss": 1.574,
"step": 560
},
{
"epoch": 0.4,
"learning_rate": 4.3375174337517435e-05,
"loss": 1.6007,
"step": 570
},
{
"epoch": 0.4,
"learning_rate": 4.325894932589494e-05,
"loss": 1.5853,
"step": 580
},
{
"epoch": 0.41,
"learning_rate": 4.3142724314272434e-05,
"loss": 1.5949,
"step": 590
},
{
"epoch": 0.42,
"learning_rate": 4.302649930264993e-05,
"loss": 1.5795,
"step": 600
},
{
"epoch": 0.43,
"learning_rate": 4.291027429102743e-05,
"loss": 1.5985,
"step": 610
},
{
"epoch": 0.43,
"learning_rate": 4.279404927940493e-05,
"loss": 1.6253,
"step": 620
},
{
"epoch": 0.44,
"learning_rate": 4.267782426778243e-05,
"loss": 1.589,
"step": 630
},
{
"epoch": 0.45,
"learning_rate": 4.256159925615993e-05,
"loss": 1.568,
"step": 640
},
{
"epoch": 0.45,
"learning_rate": 4.244537424453743e-05,
"loss": 1.5818,
"step": 650
},
{
"epoch": 0.46,
"learning_rate": 4.2329149232914926e-05,
"loss": 1.6058,
"step": 660
},
{
"epoch": 0.47,
"learning_rate": 4.221292422129242e-05,
"loss": 1.5825,
"step": 670
},
{
"epoch": 0.47,
"learning_rate": 4.209669920966992e-05,
"loss": 1.567,
"step": 680
},
{
"epoch": 0.48,
"learning_rate": 4.198047419804742e-05,
"loss": 1.5481,
"step": 690
},
{
"epoch": 0.49,
"learning_rate": 4.186424918642492e-05,
"loss": 1.5981,
"step": 700
},
{
"epoch": 0.5,
"learning_rate": 4.174802417480242e-05,
"loss": 1.5437,
"step": 710
},
{
"epoch": 0.5,
"learning_rate": 4.1631799163179915e-05,
"loss": 1.5912,
"step": 720
},
{
"epoch": 0.51,
"learning_rate": 4.151557415155742e-05,
"loss": 1.5495,
"step": 730
},
{
"epoch": 0.52,
"learning_rate": 4.139934913993492e-05,
"loss": 1.5953,
"step": 740
},
{
"epoch": 0.52,
"learning_rate": 4.128312412831242e-05,
"loss": 1.5615,
"step": 750
},
{
"epoch": 0.53,
"learning_rate": 4.116689911668991e-05,
"loss": 1.5466,
"step": 760
},
{
"epoch": 0.54,
"learning_rate": 4.105067410506741e-05,
"loss": 1.5931,
"step": 770
},
{
"epoch": 0.54,
"learning_rate": 4.093444909344491e-05,
"loss": 1.5645,
"step": 780
},
{
"epoch": 0.55,
"learning_rate": 4.081822408182241e-05,
"loss": 1.6358,
"step": 790
},
{
"epoch": 0.56,
"learning_rate": 4.070199907019991e-05,
"loss": 1.5531,
"step": 800
},
{
"epoch": 0.56,
"learning_rate": 4.0585774058577406e-05,
"loss": 1.6038,
"step": 810
},
{
"epoch": 0.57,
"learning_rate": 4.046954904695491e-05,
"loss": 1.5844,
"step": 820
},
{
"epoch": 0.58,
"learning_rate": 4.0353324035332405e-05,
"loss": 1.5652,
"step": 830
},
{
"epoch": 0.59,
"learning_rate": 4.023709902370991e-05,
"loss": 1.545,
"step": 840
},
{
"epoch": 0.59,
"learning_rate": 4.0120874012087404e-05,
"loss": 1.5618,
"step": 850
},
{
"epoch": 0.6,
"learning_rate": 4.00046490004649e-05,
"loss": 1.5778,
"step": 860
},
{
"epoch": 0.61,
"learning_rate": 3.98884239888424e-05,
"loss": 1.6248,
"step": 870
},
{
"epoch": 0.61,
"learning_rate": 3.97721989772199e-05,
"loss": 1.6243,
"step": 880
},
{
"epoch": 0.62,
"learning_rate": 3.96559739655974e-05,
"loss": 1.5639,
"step": 890
},
{
"epoch": 0.63,
"learning_rate": 3.95397489539749e-05,
"loss": 1.6058,
"step": 900
},
{
"epoch": 0.63,
"learning_rate": 3.94235239423524e-05,
"loss": 1.5932,
"step": 910
},
{
"epoch": 0.64,
"learning_rate": 3.9307298930729896e-05,
"loss": 1.6157,
"step": 920
},
{
"epoch": 0.65,
"learning_rate": 3.91910739191074e-05,
"loss": 1.5969,
"step": 930
},
{
"epoch": 0.66,
"learning_rate": 3.907484890748489e-05,
"loss": 1.5991,
"step": 940
},
{
"epoch": 0.66,
"learning_rate": 3.895862389586239e-05,
"loss": 1.5678,
"step": 950
},
{
"epoch": 0.67,
"learning_rate": 3.8842398884239886e-05,
"loss": 1.5744,
"step": 960
},
{
"epoch": 0.68,
"learning_rate": 3.872617387261739e-05,
"loss": 1.5723,
"step": 970
},
{
"epoch": 0.68,
"learning_rate": 3.8609948860994885e-05,
"loss": 1.6042,
"step": 980
},
{
"epoch": 0.69,
"learning_rate": 3.849372384937239e-05,
"loss": 1.6093,
"step": 990
},
{
"epoch": 0.7,
"learning_rate": 3.8377498837749884e-05,
"loss": 1.5968,
"step": 1000
}
],
"logging_steps": 10,
"max_steps": 4302,
"num_input_tokens_seen": 0,
"num_train_epochs": 3,
"save_steps": 500,
"total_flos": 6.3202482192384e+17,
"train_batch_size": 4,
"trial_name": null,
"trial_params": null
}