scottglover020's picture
End of training
bd54712
{
"best_metric": 0.6380597014925373,
"best_model_checkpoint": "convnextv2-tiny-1k-224-finetuned-beans/checkpoint-1883",
"epoch": 10.0,
"eval_steps": 500,
"global_step": 2690,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.04,
"learning_rate": 4.9814126394052045e-05,
"loss": 0.8864,
"step": 10
},
{
"epoch": 0.07,
"learning_rate": 4.962825278810409e-05,
"loss": 0.7181,
"step": 20
},
{
"epoch": 0.11,
"learning_rate": 4.944237918215613e-05,
"loss": 0.731,
"step": 30
},
{
"epoch": 0.15,
"learning_rate": 4.925650557620818e-05,
"loss": 0.8049,
"step": 40
},
{
"epoch": 0.19,
"learning_rate": 4.907063197026023e-05,
"loss": 0.7471,
"step": 50
},
{
"epoch": 0.22,
"learning_rate": 4.8884758364312274e-05,
"loss": 0.7461,
"step": 60
},
{
"epoch": 0.26,
"learning_rate": 4.869888475836432e-05,
"loss": 0.7432,
"step": 70
},
{
"epoch": 0.3,
"learning_rate": 4.851301115241636e-05,
"loss": 0.726,
"step": 80
},
{
"epoch": 0.33,
"learning_rate": 4.83271375464684e-05,
"loss": 0.6687,
"step": 90
},
{
"epoch": 0.37,
"learning_rate": 4.8141263940520446e-05,
"loss": 0.7631,
"step": 100
},
{
"epoch": 0.41,
"learning_rate": 4.795539033457249e-05,
"loss": 0.7284,
"step": 110
},
{
"epoch": 0.45,
"learning_rate": 4.776951672862454e-05,
"loss": 0.7516,
"step": 120
},
{
"epoch": 0.48,
"learning_rate": 4.758364312267658e-05,
"loss": 0.7579,
"step": 130
},
{
"epoch": 0.52,
"learning_rate": 4.739776951672863e-05,
"loss": 0.723,
"step": 140
},
{
"epoch": 0.56,
"learning_rate": 4.7211895910780675e-05,
"loss": 0.7566,
"step": 150
},
{
"epoch": 0.59,
"learning_rate": 4.702602230483272e-05,
"loss": 0.7669,
"step": 160
},
{
"epoch": 0.63,
"learning_rate": 4.684014869888476e-05,
"loss": 0.9366,
"step": 170
},
{
"epoch": 0.67,
"learning_rate": 4.6654275092936804e-05,
"loss": 0.6604,
"step": 180
},
{
"epoch": 0.71,
"learning_rate": 4.646840148698885e-05,
"loss": 0.6656,
"step": 190
},
{
"epoch": 0.74,
"learning_rate": 4.6282527881040897e-05,
"loss": 0.7292,
"step": 200
},
{
"epoch": 0.78,
"learning_rate": 4.609665427509294e-05,
"loss": 0.7268,
"step": 210
},
{
"epoch": 0.82,
"learning_rate": 4.591078066914498e-05,
"loss": 0.6916,
"step": 220
},
{
"epoch": 0.86,
"learning_rate": 4.5724907063197026e-05,
"loss": 0.8112,
"step": 230
},
{
"epoch": 0.89,
"learning_rate": 4.5539033457249075e-05,
"loss": 0.7209,
"step": 240
},
{
"epoch": 0.93,
"learning_rate": 4.535315985130112e-05,
"loss": 0.7132,
"step": 250
},
{
"epoch": 0.97,
"learning_rate": 4.516728624535316e-05,
"loss": 0.7177,
"step": 260
},
{
"epoch": 1.0,
"eval_accuracy": 0.5223880597014925,
"eval_loss": 0.6938973665237427,
"eval_runtime": 5.6738,
"eval_samples_per_second": 94.47,
"eval_steps_per_second": 15.863,
"step": 269
},
{
"epoch": 1.0,
"learning_rate": 4.4981412639405204e-05,
"loss": 0.6926,
"step": 270
},
{
"epoch": 1.04,
"learning_rate": 4.4795539033457254e-05,
"loss": 0.7133,
"step": 280
},
{
"epoch": 1.08,
"learning_rate": 4.46096654275093e-05,
"loss": 0.7041,
"step": 290
},
{
"epoch": 1.12,
"learning_rate": 4.442379182156134e-05,
"loss": 0.6854,
"step": 300
},
{
"epoch": 1.15,
"learning_rate": 4.423791821561338e-05,
"loss": 0.749,
"step": 310
},
{
"epoch": 1.19,
"learning_rate": 4.4052044609665426e-05,
"loss": 0.6899,
"step": 320
},
{
"epoch": 1.23,
"learning_rate": 4.3866171003717476e-05,
"loss": 0.6929,
"step": 330
},
{
"epoch": 1.26,
"learning_rate": 4.368029739776952e-05,
"loss": 0.6526,
"step": 340
},
{
"epoch": 1.3,
"learning_rate": 4.349442379182156e-05,
"loss": 0.6927,
"step": 350
},
{
"epoch": 1.34,
"learning_rate": 4.330855018587361e-05,
"loss": 0.6877,
"step": 360
},
{
"epoch": 1.38,
"learning_rate": 4.3122676579925655e-05,
"loss": 0.6808,
"step": 370
},
{
"epoch": 1.41,
"learning_rate": 4.29368029739777e-05,
"loss": 0.6482,
"step": 380
},
{
"epoch": 1.45,
"learning_rate": 4.275092936802974e-05,
"loss": 0.7385,
"step": 390
},
{
"epoch": 1.49,
"learning_rate": 4.2565055762081784e-05,
"loss": 0.7002,
"step": 400
},
{
"epoch": 1.52,
"learning_rate": 4.237918215613383e-05,
"loss": 0.6465,
"step": 410
},
{
"epoch": 1.56,
"learning_rate": 4.219330855018588e-05,
"loss": 0.7034,
"step": 420
},
{
"epoch": 1.6,
"learning_rate": 4.200743494423792e-05,
"loss": 0.6164,
"step": 430
},
{
"epoch": 1.64,
"learning_rate": 4.182156133828997e-05,
"loss": 0.7048,
"step": 440
},
{
"epoch": 1.67,
"learning_rate": 4.163568773234201e-05,
"loss": 0.7023,
"step": 450
},
{
"epoch": 1.71,
"learning_rate": 4.1449814126394056e-05,
"loss": 0.6443,
"step": 460
},
{
"epoch": 1.75,
"learning_rate": 4.12639405204461e-05,
"loss": 0.8055,
"step": 470
},
{
"epoch": 1.78,
"learning_rate": 4.107806691449814e-05,
"loss": 0.6772,
"step": 480
},
{
"epoch": 1.82,
"learning_rate": 4.0892193308550185e-05,
"loss": 0.6921,
"step": 490
},
{
"epoch": 1.86,
"learning_rate": 4.070631970260223e-05,
"loss": 0.7103,
"step": 500
},
{
"epoch": 1.9,
"learning_rate": 4.052044609665428e-05,
"loss": 0.6161,
"step": 510
},
{
"epoch": 1.93,
"learning_rate": 4.033457249070633e-05,
"loss": 0.6699,
"step": 520
},
{
"epoch": 1.97,
"learning_rate": 4.014869888475837e-05,
"loss": 0.6132,
"step": 530
},
{
"epoch": 2.0,
"eval_accuracy": 0.6100746268656716,
"eval_loss": 0.6691508293151855,
"eval_runtime": 5.6707,
"eval_samples_per_second": 94.522,
"eval_steps_per_second": 15.871,
"step": 538
},
{
"epoch": 2.01,
"learning_rate": 3.996282527881041e-05,
"loss": 0.5673,
"step": 540
},
{
"epoch": 2.04,
"learning_rate": 3.9776951672862456e-05,
"loss": 0.6385,
"step": 550
},
{
"epoch": 2.08,
"learning_rate": 3.95910780669145e-05,
"loss": 0.5089,
"step": 560
},
{
"epoch": 2.12,
"learning_rate": 3.940520446096654e-05,
"loss": 0.5526,
"step": 570
},
{
"epoch": 2.16,
"learning_rate": 3.9219330855018585e-05,
"loss": 0.5757,
"step": 580
},
{
"epoch": 2.19,
"learning_rate": 3.9033457249070635e-05,
"loss": 0.6253,
"step": 590
},
{
"epoch": 2.23,
"learning_rate": 3.884758364312268e-05,
"loss": 0.7398,
"step": 600
},
{
"epoch": 2.27,
"learning_rate": 3.866171003717473e-05,
"loss": 0.7099,
"step": 610
},
{
"epoch": 2.3,
"learning_rate": 3.847583643122677e-05,
"loss": 0.5023,
"step": 620
},
{
"epoch": 2.34,
"learning_rate": 3.8289962825278814e-05,
"loss": 0.5528,
"step": 630
},
{
"epoch": 2.38,
"learning_rate": 3.810408921933086e-05,
"loss": 0.662,
"step": 640
},
{
"epoch": 2.42,
"learning_rate": 3.79182156133829e-05,
"loss": 0.512,
"step": 650
},
{
"epoch": 2.45,
"learning_rate": 3.773234200743494e-05,
"loss": 0.5331,
"step": 660
},
{
"epoch": 2.49,
"learning_rate": 3.754646840148699e-05,
"loss": 0.412,
"step": 670
},
{
"epoch": 2.53,
"learning_rate": 3.7360594795539036e-05,
"loss": 0.5171,
"step": 680
},
{
"epoch": 2.57,
"learning_rate": 3.717472118959108e-05,
"loss": 0.3604,
"step": 690
},
{
"epoch": 2.6,
"learning_rate": 3.698884758364313e-05,
"loss": 0.7274,
"step": 700
},
{
"epoch": 2.64,
"learning_rate": 3.680297397769517e-05,
"loss": 0.6956,
"step": 710
},
{
"epoch": 2.68,
"learning_rate": 3.6617100371747215e-05,
"loss": 0.6492,
"step": 720
},
{
"epoch": 2.71,
"learning_rate": 3.643122676579926e-05,
"loss": 0.5249,
"step": 730
},
{
"epoch": 2.75,
"learning_rate": 3.62453531598513e-05,
"loss": 0.485,
"step": 740
},
{
"epoch": 2.79,
"learning_rate": 3.6059479553903344e-05,
"loss": 0.4983,
"step": 750
},
{
"epoch": 2.83,
"learning_rate": 3.5873605947955393e-05,
"loss": 0.5527,
"step": 760
},
{
"epoch": 2.86,
"learning_rate": 3.5687732342007436e-05,
"loss": 0.474,
"step": 770
},
{
"epoch": 2.9,
"learning_rate": 3.550185873605948e-05,
"loss": 0.6361,
"step": 780
},
{
"epoch": 2.94,
"learning_rate": 3.531598513011153e-05,
"loss": 0.4852,
"step": 790
},
{
"epoch": 2.97,
"learning_rate": 3.513011152416357e-05,
"loss": 0.642,
"step": 800
},
{
"epoch": 3.0,
"eval_accuracy": 0.5951492537313433,
"eval_loss": 0.6728847622871399,
"eval_runtime": 7.6109,
"eval_samples_per_second": 70.425,
"eval_steps_per_second": 11.825,
"step": 807
},
{
"epoch": 3.01,
"learning_rate": 3.4944237918215615e-05,
"loss": 0.447,
"step": 810
},
{
"epoch": 3.05,
"learning_rate": 3.475836431226766e-05,
"loss": 0.4809,
"step": 820
},
{
"epoch": 3.09,
"learning_rate": 3.45724907063197e-05,
"loss": 0.4529,
"step": 830
},
{
"epoch": 3.12,
"learning_rate": 3.438661710037175e-05,
"loss": 0.4244,
"step": 840
},
{
"epoch": 3.16,
"learning_rate": 3.4200743494423794e-05,
"loss": 0.4605,
"step": 850
},
{
"epoch": 3.2,
"learning_rate": 3.401486988847584e-05,
"loss": 0.636,
"step": 860
},
{
"epoch": 3.23,
"learning_rate": 3.382899628252788e-05,
"loss": 0.4105,
"step": 870
},
{
"epoch": 3.27,
"learning_rate": 3.364312267657992e-05,
"loss": 0.4607,
"step": 880
},
{
"epoch": 3.31,
"learning_rate": 3.345724907063197e-05,
"loss": 0.3694,
"step": 890
},
{
"epoch": 3.35,
"learning_rate": 3.3271375464684016e-05,
"loss": 0.3316,
"step": 900
},
{
"epoch": 3.38,
"learning_rate": 3.308550185873606e-05,
"loss": 0.3896,
"step": 910
},
{
"epoch": 3.42,
"learning_rate": 3.289962825278811e-05,
"loss": 0.6064,
"step": 920
},
{
"epoch": 3.46,
"learning_rate": 3.271375464684015e-05,
"loss": 0.4522,
"step": 930
},
{
"epoch": 3.49,
"learning_rate": 3.2527881040892195e-05,
"loss": 0.2951,
"step": 940
},
{
"epoch": 3.53,
"learning_rate": 3.234200743494424e-05,
"loss": 0.3321,
"step": 950
},
{
"epoch": 3.57,
"learning_rate": 3.215613382899628e-05,
"loss": 0.3755,
"step": 960
},
{
"epoch": 3.61,
"learning_rate": 3.1970260223048324e-05,
"loss": 0.4872,
"step": 970
},
{
"epoch": 3.64,
"learning_rate": 3.1784386617100374e-05,
"loss": 0.7994,
"step": 980
},
{
"epoch": 3.68,
"learning_rate": 3.1598513011152417e-05,
"loss": 0.4673,
"step": 990
},
{
"epoch": 3.72,
"learning_rate": 3.1412639405204466e-05,
"loss": 0.3712,
"step": 1000
},
{
"epoch": 3.75,
"learning_rate": 3.122676579925651e-05,
"loss": 0.4688,
"step": 1010
},
{
"epoch": 3.79,
"learning_rate": 3.104089219330855e-05,
"loss": 0.4393,
"step": 1020
},
{
"epoch": 3.83,
"learning_rate": 3.0855018587360595e-05,
"loss": 0.4471,
"step": 1030
},
{
"epoch": 3.87,
"learning_rate": 3.066914498141264e-05,
"loss": 0.5707,
"step": 1040
},
{
"epoch": 3.9,
"learning_rate": 3.0483271375464685e-05,
"loss": 0.4092,
"step": 1050
},
{
"epoch": 3.94,
"learning_rate": 3.0297397769516728e-05,
"loss": 0.6516,
"step": 1060
},
{
"epoch": 3.98,
"learning_rate": 3.0111524163568778e-05,
"loss": 0.6431,
"step": 1070
},
{
"epoch": 4.0,
"eval_accuracy": 0.5690298507462687,
"eval_loss": 0.6699710488319397,
"eval_runtime": 4.8825,
"eval_samples_per_second": 109.78,
"eval_steps_per_second": 18.433,
"step": 1076
},
{
"epoch": 4.01,
"learning_rate": 2.992565055762082e-05,
"loss": 0.4114,
"step": 1080
},
{
"epoch": 4.05,
"learning_rate": 2.9739776951672864e-05,
"loss": 0.3278,
"step": 1090
},
{
"epoch": 4.09,
"learning_rate": 2.955390334572491e-05,
"loss": 0.282,
"step": 1100
},
{
"epoch": 4.13,
"learning_rate": 2.9368029739776953e-05,
"loss": 0.4411,
"step": 1110
},
{
"epoch": 4.16,
"learning_rate": 2.9182156133828996e-05,
"loss": 0.3877,
"step": 1120
},
{
"epoch": 4.2,
"learning_rate": 2.8996282527881043e-05,
"loss": 0.3529,
"step": 1130
},
{
"epoch": 4.24,
"learning_rate": 2.8810408921933086e-05,
"loss": 0.4784,
"step": 1140
},
{
"epoch": 4.28,
"learning_rate": 2.862453531598513e-05,
"loss": 0.3331,
"step": 1150
},
{
"epoch": 4.31,
"learning_rate": 2.843866171003718e-05,
"loss": 0.333,
"step": 1160
},
{
"epoch": 4.35,
"learning_rate": 2.825278810408922e-05,
"loss": 0.229,
"step": 1170
},
{
"epoch": 4.39,
"learning_rate": 2.8066914498141268e-05,
"loss": 0.4836,
"step": 1180
},
{
"epoch": 4.42,
"learning_rate": 2.788104089219331e-05,
"loss": 0.3867,
"step": 1190
},
{
"epoch": 4.46,
"learning_rate": 2.7695167286245354e-05,
"loss": 0.4889,
"step": 1200
},
{
"epoch": 4.5,
"learning_rate": 2.75092936802974e-05,
"loss": 0.3486,
"step": 1210
},
{
"epoch": 4.54,
"learning_rate": 2.7323420074349443e-05,
"loss": 0.5418,
"step": 1220
},
{
"epoch": 4.57,
"learning_rate": 2.7137546468401486e-05,
"loss": 0.5474,
"step": 1230
},
{
"epoch": 4.61,
"learning_rate": 2.695167286245353e-05,
"loss": 0.2895,
"step": 1240
},
{
"epoch": 4.65,
"learning_rate": 2.6765799256505576e-05,
"loss": 0.4961,
"step": 1250
},
{
"epoch": 4.68,
"learning_rate": 2.6579925650557625e-05,
"loss": 0.4748,
"step": 1260
},
{
"epoch": 4.72,
"learning_rate": 2.639405204460967e-05,
"loss": 0.4066,
"step": 1270
},
{
"epoch": 4.76,
"learning_rate": 2.620817843866171e-05,
"loss": 0.2847,
"step": 1280
},
{
"epoch": 4.8,
"learning_rate": 2.6022304832713758e-05,
"loss": 0.2828,
"step": 1290
},
{
"epoch": 4.83,
"learning_rate": 2.58364312267658e-05,
"loss": 0.3473,
"step": 1300
},
{
"epoch": 4.87,
"learning_rate": 2.5650557620817844e-05,
"loss": 0.4106,
"step": 1310
},
{
"epoch": 4.91,
"learning_rate": 2.5464684014869887e-05,
"loss": 0.5531,
"step": 1320
},
{
"epoch": 4.94,
"learning_rate": 2.5278810408921933e-05,
"loss": 0.537,
"step": 1330
},
{
"epoch": 4.98,
"learning_rate": 2.5092936802973976e-05,
"loss": 0.5081,
"step": 1340
},
{
"epoch": 5.0,
"eval_accuracy": 0.621268656716418,
"eval_loss": 0.7537009716033936,
"eval_runtime": 4.9189,
"eval_samples_per_second": 108.968,
"eval_steps_per_second": 18.297,
"step": 1345
},
{
"epoch": 5.02,
"learning_rate": 2.4907063197026023e-05,
"loss": 0.1346,
"step": 1350
},
{
"epoch": 5.06,
"learning_rate": 2.4721189591078066e-05,
"loss": 0.2534,
"step": 1360
},
{
"epoch": 5.09,
"learning_rate": 2.4535315985130116e-05,
"loss": 0.396,
"step": 1370
},
{
"epoch": 5.13,
"learning_rate": 2.434944237918216e-05,
"loss": 0.336,
"step": 1380
},
{
"epoch": 5.17,
"learning_rate": 2.41635687732342e-05,
"loss": 0.2851,
"step": 1390
},
{
"epoch": 5.2,
"learning_rate": 2.3977695167286245e-05,
"loss": 0.3815,
"step": 1400
},
{
"epoch": 5.24,
"learning_rate": 2.379182156133829e-05,
"loss": 0.2494,
"step": 1410
},
{
"epoch": 5.28,
"learning_rate": 2.3605947955390337e-05,
"loss": 0.2749,
"step": 1420
},
{
"epoch": 5.32,
"learning_rate": 2.342007434944238e-05,
"loss": 0.3111,
"step": 1430
},
{
"epoch": 5.35,
"learning_rate": 2.3234200743494423e-05,
"loss": 0.5944,
"step": 1440
},
{
"epoch": 5.39,
"learning_rate": 2.304832713754647e-05,
"loss": 0.2278,
"step": 1450
},
{
"epoch": 5.43,
"learning_rate": 2.2862453531598513e-05,
"loss": 0.3026,
"step": 1460
},
{
"epoch": 5.46,
"learning_rate": 2.267657992565056e-05,
"loss": 0.1595,
"step": 1470
},
{
"epoch": 5.5,
"learning_rate": 2.2490706319702602e-05,
"loss": 0.2316,
"step": 1480
},
{
"epoch": 5.54,
"learning_rate": 2.230483271375465e-05,
"loss": 0.3516,
"step": 1490
},
{
"epoch": 5.58,
"learning_rate": 2.211895910780669e-05,
"loss": 0.4393,
"step": 1500
},
{
"epoch": 5.61,
"learning_rate": 2.1933085501858738e-05,
"loss": 0.2632,
"step": 1510
},
{
"epoch": 5.65,
"learning_rate": 2.174721189591078e-05,
"loss": 0.2464,
"step": 1520
},
{
"epoch": 5.69,
"learning_rate": 2.1561338289962827e-05,
"loss": 0.3096,
"step": 1530
},
{
"epoch": 5.72,
"learning_rate": 2.137546468401487e-05,
"loss": 0.6077,
"step": 1540
},
{
"epoch": 5.76,
"learning_rate": 2.1189591078066913e-05,
"loss": 0.338,
"step": 1550
},
{
"epoch": 5.8,
"learning_rate": 2.100371747211896e-05,
"loss": 0.5448,
"step": 1560
},
{
"epoch": 5.84,
"learning_rate": 2.0817843866171006e-05,
"loss": 0.4206,
"step": 1570
},
{
"epoch": 5.87,
"learning_rate": 2.063197026022305e-05,
"loss": 0.2484,
"step": 1580
},
{
"epoch": 5.91,
"learning_rate": 2.0446096654275092e-05,
"loss": 0.2526,
"step": 1590
},
{
"epoch": 5.95,
"learning_rate": 2.026022304832714e-05,
"loss": 0.304,
"step": 1600
},
{
"epoch": 5.99,
"learning_rate": 2.0074349442379185e-05,
"loss": 0.4114,
"step": 1610
},
{
"epoch": 6.0,
"eval_accuracy": 0.6175373134328358,
"eval_loss": 0.9249094724655151,
"eval_runtime": 4.9293,
"eval_samples_per_second": 108.739,
"eval_steps_per_second": 18.258,
"step": 1614
},
{
"epoch": 6.02,
"learning_rate": 1.9888475836431228e-05,
"loss": 0.2368,
"step": 1620
},
{
"epoch": 6.06,
"learning_rate": 1.970260223048327e-05,
"loss": 0.4407,
"step": 1630
},
{
"epoch": 6.1,
"learning_rate": 1.9516728624535318e-05,
"loss": 0.2919,
"step": 1640
},
{
"epoch": 6.13,
"learning_rate": 1.9330855018587364e-05,
"loss": 0.448,
"step": 1650
},
{
"epoch": 6.17,
"learning_rate": 1.9144981412639407e-05,
"loss": 0.1191,
"step": 1660
},
{
"epoch": 6.21,
"learning_rate": 1.895910780669145e-05,
"loss": 0.0392,
"step": 1670
},
{
"epoch": 6.25,
"learning_rate": 1.8773234200743496e-05,
"loss": 0.1173,
"step": 1680
},
{
"epoch": 6.28,
"learning_rate": 1.858736059479554e-05,
"loss": 0.563,
"step": 1690
},
{
"epoch": 6.32,
"learning_rate": 1.8401486988847586e-05,
"loss": 0.0517,
"step": 1700
},
{
"epoch": 6.36,
"learning_rate": 1.821561338289963e-05,
"loss": 0.2913,
"step": 1710
},
{
"epoch": 6.39,
"learning_rate": 1.8029739776951672e-05,
"loss": 0.4507,
"step": 1720
},
{
"epoch": 6.43,
"learning_rate": 1.7843866171003718e-05,
"loss": 0.5469,
"step": 1730
},
{
"epoch": 6.47,
"learning_rate": 1.7657992565055765e-05,
"loss": 0.4643,
"step": 1740
},
{
"epoch": 6.51,
"learning_rate": 1.7472118959107808e-05,
"loss": 0.1686,
"step": 1750
},
{
"epoch": 6.54,
"learning_rate": 1.728624535315985e-05,
"loss": 0.0685,
"step": 1760
},
{
"epoch": 6.58,
"learning_rate": 1.7100371747211897e-05,
"loss": 0.3367,
"step": 1770
},
{
"epoch": 6.62,
"learning_rate": 1.691449814126394e-05,
"loss": 0.1368,
"step": 1780
},
{
"epoch": 6.65,
"learning_rate": 1.6728624535315986e-05,
"loss": 0.2455,
"step": 1790
},
{
"epoch": 6.69,
"learning_rate": 1.654275092936803e-05,
"loss": 0.3655,
"step": 1800
},
{
"epoch": 6.73,
"learning_rate": 1.6356877323420076e-05,
"loss": 0.3373,
"step": 1810
},
{
"epoch": 6.77,
"learning_rate": 1.617100371747212e-05,
"loss": 0.3152,
"step": 1820
},
{
"epoch": 6.8,
"learning_rate": 1.5985130111524162e-05,
"loss": 0.5365,
"step": 1830
},
{
"epoch": 6.84,
"learning_rate": 1.5799256505576208e-05,
"loss": 0.1659,
"step": 1840
},
{
"epoch": 6.88,
"learning_rate": 1.5613382899628255e-05,
"loss": 0.3763,
"step": 1850
},
{
"epoch": 6.91,
"learning_rate": 1.5427509293680298e-05,
"loss": 0.4083,
"step": 1860
},
{
"epoch": 6.95,
"learning_rate": 1.5241635687732342e-05,
"loss": 0.2691,
"step": 1870
},
{
"epoch": 6.99,
"learning_rate": 1.5055762081784389e-05,
"loss": 0.3991,
"step": 1880
},
{
"epoch": 7.0,
"eval_accuracy": 0.6380597014925373,
"eval_loss": 0.9836869835853577,
"eval_runtime": 4.8663,
"eval_samples_per_second": 110.145,
"eval_steps_per_second": 18.495,
"step": 1883
},
{
"epoch": 7.03,
"learning_rate": 1.4869888475836432e-05,
"loss": 0.2571,
"step": 1890
},
{
"epoch": 7.06,
"learning_rate": 1.4684014869888477e-05,
"loss": 0.1307,
"step": 1900
},
{
"epoch": 7.1,
"learning_rate": 1.4498141263940521e-05,
"loss": 0.1222,
"step": 1910
},
{
"epoch": 7.14,
"learning_rate": 1.4312267657992564e-05,
"loss": 0.276,
"step": 1920
},
{
"epoch": 7.17,
"learning_rate": 1.412639405204461e-05,
"loss": 0.5438,
"step": 1930
},
{
"epoch": 7.21,
"learning_rate": 1.3940520446096655e-05,
"loss": 0.1835,
"step": 1940
},
{
"epoch": 7.25,
"learning_rate": 1.37546468401487e-05,
"loss": 0.136,
"step": 1950
},
{
"epoch": 7.29,
"learning_rate": 1.3568773234200743e-05,
"loss": 0.3315,
"step": 1960
},
{
"epoch": 7.32,
"learning_rate": 1.3382899628252788e-05,
"loss": 0.3154,
"step": 1970
},
{
"epoch": 7.36,
"learning_rate": 1.3197026022304834e-05,
"loss": 0.1583,
"step": 1980
},
{
"epoch": 7.4,
"learning_rate": 1.3011152416356879e-05,
"loss": 0.3539,
"step": 1990
},
{
"epoch": 7.43,
"learning_rate": 1.2825278810408922e-05,
"loss": 0.2128,
"step": 2000
},
{
"epoch": 7.47,
"learning_rate": 1.2639405204460967e-05,
"loss": 0.2219,
"step": 2010
},
{
"epoch": 7.51,
"learning_rate": 1.2453531598513011e-05,
"loss": 0.1671,
"step": 2020
},
{
"epoch": 7.55,
"learning_rate": 1.2267657992565058e-05,
"loss": 0.1404,
"step": 2030
},
{
"epoch": 7.58,
"learning_rate": 1.20817843866171e-05,
"loss": 0.1204,
"step": 2040
},
{
"epoch": 7.62,
"learning_rate": 1.1895910780669145e-05,
"loss": 0.1877,
"step": 2050
},
{
"epoch": 7.66,
"learning_rate": 1.171003717472119e-05,
"loss": 0.2447,
"step": 2060
},
{
"epoch": 7.7,
"learning_rate": 1.1524163568773235e-05,
"loss": 0.2406,
"step": 2070
},
{
"epoch": 7.73,
"learning_rate": 1.133828996282528e-05,
"loss": 0.0305,
"step": 2080
},
{
"epoch": 7.77,
"learning_rate": 1.1152416356877324e-05,
"loss": 0.4781,
"step": 2090
},
{
"epoch": 7.81,
"learning_rate": 1.0966542750929369e-05,
"loss": 0.6367,
"step": 2100
},
{
"epoch": 7.84,
"learning_rate": 1.0780669144981414e-05,
"loss": 0.2427,
"step": 2110
},
{
"epoch": 7.88,
"learning_rate": 1.0594795539033457e-05,
"loss": 0.359,
"step": 2120
},
{
"epoch": 7.92,
"learning_rate": 1.0408921933085503e-05,
"loss": 0.3237,
"step": 2130
},
{
"epoch": 7.96,
"learning_rate": 1.0223048327137546e-05,
"loss": 0.161,
"step": 2140
},
{
"epoch": 7.99,
"learning_rate": 1.0037174721189593e-05,
"loss": 0.2194,
"step": 2150
},
{
"epoch": 8.0,
"eval_accuracy": 0.5802238805970149,
"eval_loss": 1.4350043535232544,
"eval_runtime": 5.1084,
"eval_samples_per_second": 104.925,
"eval_steps_per_second": 17.618,
"step": 2152
},
{
"epoch": 8.03,
"learning_rate": 9.851301115241636e-06,
"loss": 0.304,
"step": 2160
},
{
"epoch": 8.07,
"learning_rate": 9.665427509293682e-06,
"loss": 0.4776,
"step": 2170
},
{
"epoch": 8.1,
"learning_rate": 9.479553903345725e-06,
"loss": 0.113,
"step": 2180
},
{
"epoch": 8.14,
"learning_rate": 9.29368029739777e-06,
"loss": 0.3168,
"step": 2190
},
{
"epoch": 8.18,
"learning_rate": 9.107806691449814e-06,
"loss": 0.2094,
"step": 2200
},
{
"epoch": 8.22,
"learning_rate": 8.921933085501859e-06,
"loss": 0.1155,
"step": 2210
},
{
"epoch": 8.25,
"learning_rate": 8.736059479553904e-06,
"loss": 0.1741,
"step": 2220
},
{
"epoch": 8.29,
"learning_rate": 8.550185873605949e-06,
"loss": 0.3574,
"step": 2230
},
{
"epoch": 8.33,
"learning_rate": 8.364312267657993e-06,
"loss": 0.1843,
"step": 2240
},
{
"epoch": 8.36,
"learning_rate": 8.178438661710038e-06,
"loss": 0.4902,
"step": 2250
},
{
"epoch": 8.4,
"learning_rate": 7.992565055762081e-06,
"loss": 0.3588,
"step": 2260
},
{
"epoch": 8.44,
"learning_rate": 7.806691449814127e-06,
"loss": 0.2261,
"step": 2270
},
{
"epoch": 8.48,
"learning_rate": 7.620817843866171e-06,
"loss": 0.2937,
"step": 2280
},
{
"epoch": 8.51,
"learning_rate": 7.434944237918216e-06,
"loss": 0.1844,
"step": 2290
},
{
"epoch": 8.55,
"learning_rate": 7.249070631970261e-06,
"loss": 0.1538,
"step": 2300
},
{
"epoch": 8.59,
"learning_rate": 7.063197026022305e-06,
"loss": 0.0564,
"step": 2310
},
{
"epoch": 8.62,
"learning_rate": 6.87732342007435e-06,
"loss": 0.0752,
"step": 2320
},
{
"epoch": 8.66,
"learning_rate": 6.691449814126394e-06,
"loss": 0.2735,
"step": 2330
},
{
"epoch": 8.7,
"learning_rate": 6.5055762081784395e-06,
"loss": 0.1708,
"step": 2340
},
{
"epoch": 8.74,
"learning_rate": 6.319702602230483e-06,
"loss": 0.1134,
"step": 2350
},
{
"epoch": 8.77,
"learning_rate": 6.133828996282529e-06,
"loss": 0.3347,
"step": 2360
},
{
"epoch": 8.81,
"learning_rate": 5.947955390334573e-06,
"loss": 0.0905,
"step": 2370
},
{
"epoch": 8.85,
"learning_rate": 5.7620817843866174e-06,
"loss": 0.6311,
"step": 2380
},
{
"epoch": 8.88,
"learning_rate": 5.576208178438662e-06,
"loss": 0.1654,
"step": 2390
},
{
"epoch": 8.92,
"learning_rate": 5.390334572490707e-06,
"loss": 0.4053,
"step": 2400
},
{
"epoch": 8.96,
"learning_rate": 5.2044609665427516e-06,
"loss": 0.0912,
"step": 2410
},
{
"epoch": 9.0,
"learning_rate": 5.018587360594796e-06,
"loss": 0.0834,
"step": 2420
},
{
"epoch": 9.0,
"eval_accuracy": 0.6138059701492538,
"eval_loss": 1.3807860612869263,
"eval_runtime": 5.3599,
"eval_samples_per_second": 100.002,
"eval_steps_per_second": 16.791,
"step": 2421
},
{
"epoch": 9.03,
"learning_rate": 4.832713754646841e-06,
"loss": 0.0566,
"step": 2430
},
{
"epoch": 9.07,
"learning_rate": 4.646840148698885e-06,
"loss": 0.3705,
"step": 2440
},
{
"epoch": 9.11,
"learning_rate": 4.4609665427509296e-06,
"loss": 0.2529,
"step": 2450
},
{
"epoch": 9.14,
"learning_rate": 4.275092936802974e-06,
"loss": 0.0952,
"step": 2460
},
{
"epoch": 9.18,
"learning_rate": 4.089219330855019e-06,
"loss": 0.1959,
"step": 2470
},
{
"epoch": 9.22,
"learning_rate": 3.903345724907064e-06,
"loss": 0.2592,
"step": 2480
},
{
"epoch": 9.26,
"learning_rate": 3.717472118959108e-06,
"loss": 0.1467,
"step": 2490
},
{
"epoch": 9.29,
"learning_rate": 3.5315985130111527e-06,
"loss": 0.3126,
"step": 2500
},
{
"epoch": 9.33,
"learning_rate": 3.345724907063197e-06,
"loss": 0.1853,
"step": 2510
},
{
"epoch": 9.37,
"learning_rate": 3.1598513011152417e-06,
"loss": 0.3267,
"step": 2520
},
{
"epoch": 9.41,
"learning_rate": 2.9739776951672864e-06,
"loss": 0.1253,
"step": 2530
},
{
"epoch": 9.44,
"learning_rate": 2.788104089219331e-06,
"loss": 0.0585,
"step": 2540
},
{
"epoch": 9.48,
"learning_rate": 2.6022304832713758e-06,
"loss": 0.3812,
"step": 2550
},
{
"epoch": 9.52,
"learning_rate": 2.4163568773234205e-06,
"loss": 0.136,
"step": 2560
},
{
"epoch": 9.55,
"learning_rate": 2.2304832713754648e-06,
"loss": 0.1899,
"step": 2570
},
{
"epoch": 9.59,
"learning_rate": 2.0446096654275095e-06,
"loss": 0.3092,
"step": 2580
},
{
"epoch": 9.63,
"learning_rate": 1.858736059479554e-06,
"loss": 0.2287,
"step": 2590
},
{
"epoch": 9.67,
"learning_rate": 1.6728624535315985e-06,
"loss": 0.1593,
"step": 2600
},
{
"epoch": 9.7,
"learning_rate": 1.4869888475836432e-06,
"loss": 0.0521,
"step": 2610
},
{
"epoch": 9.74,
"learning_rate": 1.3011152416356879e-06,
"loss": 0.5016,
"step": 2620
},
{
"epoch": 9.78,
"learning_rate": 1.1152416356877324e-06,
"loss": 0.1367,
"step": 2630
},
{
"epoch": 9.81,
"learning_rate": 9.29368029739777e-07,
"loss": 0.4205,
"step": 2640
},
{
"epoch": 9.85,
"learning_rate": 7.434944237918216e-07,
"loss": 0.1077,
"step": 2650
},
{
"epoch": 9.89,
"learning_rate": 5.576208178438662e-07,
"loss": 0.4551,
"step": 2660
},
{
"epoch": 9.93,
"learning_rate": 3.717472118959108e-07,
"loss": 0.0785,
"step": 2670
},
{
"epoch": 9.96,
"learning_rate": 1.858736059479554e-07,
"loss": 0.1772,
"step": 2680
},
{
"epoch": 10.0,
"learning_rate": 0.0,
"loss": 0.15,
"step": 2690
},
{
"epoch": 10.0,
"eval_accuracy": 0.6305970149253731,
"eval_loss": 1.3277170658111572,
"eval_runtime": 5.7368,
"eval_samples_per_second": 93.432,
"eval_steps_per_second": 15.688,
"step": 2690
},
{
"epoch": 10.0,
"step": 2690,
"total_flos": 1.2914180359776e+18,
"train_loss": 0.42039277555774135,
"train_runtime": 1313.1112,
"train_samples_per_second": 12.253,
"train_steps_per_second": 2.049
}
],
"logging_steps": 10,
"max_steps": 2690,
"num_train_epochs": 10,
"save_steps": 500,
"total_flos": 1.2914180359776e+18,
"trial_name": null,
"trial_params": null
}