| { | |
| "best_metric": 0.9637404580152672, | |
| "best_model_checkpoint": "vit-base-patch16-224-in21k-finetuned-lora-medmnistv2/checkpoint-516", | |
| "epoch": 9.898305084745763, | |
| "eval_steps": 500, | |
| "global_step": 730, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.13559322033898305, | |
| "grad_norm": 0.33258745074272156, | |
| "learning_rate": 0.004931506849315068, | |
| "loss": 0.4697, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.2711864406779661, | |
| "grad_norm": 0.4260016679763794, | |
| "learning_rate": 0.0048630136986301375, | |
| "loss": 0.4209, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.4067796610169492, | |
| "grad_norm": 0.335248202085495, | |
| "learning_rate": 0.004794520547945206, | |
| "loss": 0.3029, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.5423728813559322, | |
| "grad_norm": 1.0114984512329102, | |
| "learning_rate": 0.004726027397260274, | |
| "loss": 0.2765, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.6779661016949152, | |
| "grad_norm": 0.7004571557044983, | |
| "learning_rate": 0.004657534246575342, | |
| "loss": 0.2801, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.8135593220338984, | |
| "grad_norm": 0.4206073582172394, | |
| "learning_rate": 0.004589041095890411, | |
| "loss": 0.2222, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.9491525423728814, | |
| "grad_norm": 0.49781563878059387, | |
| "learning_rate": 0.00452054794520548, | |
| "loss": 0.2447, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.9898305084745763, | |
| "eval_accuracy": 0.9351145038167938, | |
| "eval_f1": 0.9199611845888442, | |
| "eval_loss": 0.15377819538116455, | |
| "eval_precision": 0.9013226562633677, | |
| "eval_recall": 0.9466247738741311, | |
| "eval_runtime": 2.598, | |
| "eval_samples_per_second": 201.69, | |
| "eval_steps_per_second": 12.702, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 1.0847457627118644, | |
| "grad_norm": 2.9151036739349365, | |
| "learning_rate": 0.004452054794520548, | |
| "loss": 0.2175, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 1.2203389830508475, | |
| "grad_norm": 0.7062793374061584, | |
| "learning_rate": 0.004383561643835616, | |
| "loss": 0.2292, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 1.3559322033898304, | |
| "grad_norm": 0.6493266820907593, | |
| "learning_rate": 0.004315068493150685, | |
| "loss": 0.2363, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.4915254237288136, | |
| "grad_norm": 0.487130343914032, | |
| "learning_rate": 0.0042465753424657535, | |
| "loss": 0.1594, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 1.6271186440677967, | |
| "grad_norm": 1.8056527376174927, | |
| "learning_rate": 0.004178082191780822, | |
| "loss": 0.2788, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 1.7627118644067796, | |
| "grad_norm": 1.6562355756759644, | |
| "learning_rate": 0.00410958904109589, | |
| "loss": 0.317, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 1.8983050847457628, | |
| "grad_norm": 3.5319395065307617, | |
| "learning_rate": 0.004041095890410959, | |
| "loss": 0.3466, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 1.993220338983051, | |
| "eval_accuracy": 0.9122137404580153, | |
| "eval_f1": 0.87496628280942, | |
| "eval_loss": 0.24509698152542114, | |
| "eval_precision": 0.9197011276895048, | |
| "eval_recall": 0.846558126249643, | |
| "eval_runtime": 2.2021, | |
| "eval_samples_per_second": 237.954, | |
| "eval_steps_per_second": 14.986, | |
| "step": 147 | |
| }, | |
| { | |
| "epoch": 2.0338983050847457, | |
| "grad_norm": 1.5860559940338135, | |
| "learning_rate": 0.003972602739726027, | |
| "loss": 0.4163, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 2.169491525423729, | |
| "grad_norm": 3.2184932231903076, | |
| "learning_rate": 0.003904109589041096, | |
| "loss": 0.3898, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 2.305084745762712, | |
| "grad_norm": 0.8964293003082275, | |
| "learning_rate": 0.0038356164383561643, | |
| "loss": 0.5784, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 2.440677966101695, | |
| "grad_norm": 0.6328169703483582, | |
| "learning_rate": 0.003767123287671233, | |
| "loss": 0.3161, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 2.576271186440678, | |
| "grad_norm": 0.5992427468299866, | |
| "learning_rate": 0.0036986301369863013, | |
| "loss": 0.2642, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 2.711864406779661, | |
| "grad_norm": 0.802533745765686, | |
| "learning_rate": 0.00363013698630137, | |
| "loss": 0.3049, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 2.847457627118644, | |
| "grad_norm": 0.41971662640571594, | |
| "learning_rate": 0.003561643835616438, | |
| "loss": 0.2395, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 2.983050847457627, | |
| "grad_norm": 1.329890489578247, | |
| "learning_rate": 0.003493150684931507, | |
| "loss": 0.2074, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 2.9966101694915253, | |
| "eval_accuracy": 0.9427480916030534, | |
| "eval_f1": 0.9203211483486406, | |
| "eval_loss": 0.17114438116550446, | |
| "eval_precision": 0.9537988351547674, | |
| "eval_recall": 0.8961439588688946, | |
| "eval_runtime": 2.5606, | |
| "eval_samples_per_second": 204.643, | |
| "eval_steps_per_second": 12.888, | |
| "step": 221 | |
| }, | |
| { | |
| "epoch": 3.1186440677966103, | |
| "grad_norm": 0.5802115797996521, | |
| "learning_rate": 0.003424657534246575, | |
| "loss": 0.2699, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 3.2542372881355934, | |
| "grad_norm": 0.4673289954662323, | |
| "learning_rate": 0.003356164383561644, | |
| "loss": 0.2138, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 3.389830508474576, | |
| "grad_norm": 0.6567840576171875, | |
| "learning_rate": 0.003287671232876712, | |
| "loss": 0.2106, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 3.5254237288135593, | |
| "grad_norm": 0.6320674419403076, | |
| "learning_rate": 0.0032191780821917808, | |
| "loss": 0.2035, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 3.6610169491525424, | |
| "grad_norm": 0.6084808707237244, | |
| "learning_rate": 0.003150684931506849, | |
| "loss": 0.1865, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 3.7966101694915255, | |
| "grad_norm": 0.4084516763687134, | |
| "learning_rate": 0.003082191780821918, | |
| "loss": 0.1982, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 3.9322033898305087, | |
| "grad_norm": 0.9839584231376648, | |
| "learning_rate": 0.0030136986301369864, | |
| "loss": 0.1928, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.9618320610687023, | |
| "eval_f1": 0.9503486961795027, | |
| "eval_loss": 0.10444469004869461, | |
| "eval_precision": 0.9482261076217959, | |
| "eval_recall": 0.9525278491859469, | |
| "eval_runtime": 2.269, | |
| "eval_samples_per_second": 230.934, | |
| "eval_steps_per_second": 14.544, | |
| "step": 295 | |
| }, | |
| { | |
| "epoch": 4.067796610169491, | |
| "grad_norm": 0.9798701405525208, | |
| "learning_rate": 0.002945205479452055, | |
| "loss": 0.161, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 4.203389830508475, | |
| "grad_norm": 0.36826208233833313, | |
| "learning_rate": 0.0028767123287671234, | |
| "loss": 0.2181, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 4.338983050847458, | |
| "grad_norm": 0.42575180530548096, | |
| "learning_rate": 0.002808219178082192, | |
| "loss": 0.1731, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 4.47457627118644, | |
| "grad_norm": 0.413644939661026, | |
| "learning_rate": 0.0027397260273972603, | |
| "loss": 0.2078, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 4.610169491525424, | |
| "grad_norm": 0.6161473989486694, | |
| "learning_rate": 0.002671232876712329, | |
| "loss": 0.1798, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 4.745762711864407, | |
| "grad_norm": 0.7980164885520935, | |
| "learning_rate": 0.0026027397260273972, | |
| "loss": 0.1803, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 4.88135593220339, | |
| "grad_norm": 0.7662364840507507, | |
| "learning_rate": 0.002534246575342466, | |
| "loss": 0.2043, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 4.989830508474577, | |
| "eval_accuracy": 0.9580152671755725, | |
| "eval_f1": 0.9445801203776705, | |
| "eval_loss": 0.100668765604496, | |
| "eval_precision": 0.9491094147582697, | |
| "eval_recall": 0.9402837284585357, | |
| "eval_runtime": 2.3077, | |
| "eval_samples_per_second": 227.062, | |
| "eval_steps_per_second": 14.3, | |
| "step": 368 | |
| }, | |
| { | |
| "epoch": 5.016949152542373, | |
| "grad_norm": 0.4770575165748596, | |
| "learning_rate": 0.002465753424657534, | |
| "loss": 0.2144, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 5.1525423728813555, | |
| "grad_norm": 0.5560809969902039, | |
| "learning_rate": 0.002397260273972603, | |
| "loss": 0.196, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 5.288135593220339, | |
| "grad_norm": 0.3539073169231415, | |
| "learning_rate": 0.002328767123287671, | |
| "loss": 0.1493, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 5.423728813559322, | |
| "grad_norm": 0.4955459237098694, | |
| "learning_rate": 0.00226027397260274, | |
| "loss": 0.1548, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 5.559322033898305, | |
| "grad_norm": 0.7003247141838074, | |
| "learning_rate": 0.002191780821917808, | |
| "loss": 0.1623, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 5.694915254237288, | |
| "grad_norm": 0.37460166215896606, | |
| "learning_rate": 0.0021232876712328768, | |
| "loss": 0.1964, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 5.830508474576272, | |
| "grad_norm": 0.7236199378967285, | |
| "learning_rate": 0.002054794520547945, | |
| "loss": 0.2222, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 5.966101694915254, | |
| "grad_norm": 0.47040122747421265, | |
| "learning_rate": 0.0019863013698630137, | |
| "loss": 0.1717, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 5.9932203389830505, | |
| "eval_accuracy": 0.9618320610687023, | |
| "eval_f1": 0.9510417639914043, | |
| "eval_loss": 0.09301359206438065, | |
| "eval_precision": 0.9431749353009196, | |
| "eval_recall": 0.9597829191659526, | |
| "eval_runtime": 2.2617, | |
| "eval_samples_per_second": 231.684, | |
| "eval_steps_per_second": 14.591, | |
| "step": 442 | |
| }, | |
| { | |
| "epoch": 6.101694915254237, | |
| "grad_norm": 0.38825348019599915, | |
| "learning_rate": 0.0019178082191780822, | |
| "loss": 0.1433, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 6.237288135593221, | |
| "grad_norm": 0.5254190564155579, | |
| "learning_rate": 0.0018493150684931506, | |
| "loss": 0.1549, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 6.372881355932203, | |
| "grad_norm": 0.369255930185318, | |
| "learning_rate": 0.001780821917808219, | |
| "loss": 0.1404, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 6.508474576271187, | |
| "grad_norm": 0.5419684648513794, | |
| "learning_rate": 0.0017123287671232876, | |
| "loss": 0.1506, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 6.6440677966101696, | |
| "grad_norm": 0.47255194187164307, | |
| "learning_rate": 0.001643835616438356, | |
| "loss": 0.1852, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 6.779661016949152, | |
| "grad_norm": 0.5880511403083801, | |
| "learning_rate": 0.0015753424657534245, | |
| "loss": 0.1386, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 6.915254237288136, | |
| "grad_norm": 0.5441922545433044, | |
| "learning_rate": 0.0015068493150684932, | |
| "loss": 0.1498, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 6.996610169491525, | |
| "eval_accuracy": 0.9637404580152672, | |
| "eval_f1": 0.9535961146766969, | |
| "eval_loss": 0.08451908081769943, | |
| "eval_precision": 0.9448099415204678, | |
| "eval_recall": 0.9634866228696563, | |
| "eval_runtime": 2.2932, | |
| "eval_samples_per_second": 228.506, | |
| "eval_steps_per_second": 14.391, | |
| "step": 516 | |
| }, | |
| { | |
| "epoch": 7.0508474576271185, | |
| "grad_norm": 0.40786656737327576, | |
| "learning_rate": 0.0014383561643835617, | |
| "loss": 0.1501, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 7.186440677966102, | |
| "grad_norm": 0.5240201950073242, | |
| "learning_rate": 0.0013698630136986301, | |
| "loss": 0.1619, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 7.322033898305085, | |
| "grad_norm": 0.4185083210468292, | |
| "learning_rate": 0.0013013698630136986, | |
| "loss": 0.1485, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 7.4576271186440675, | |
| "grad_norm": 0.4574959874153137, | |
| "learning_rate": 0.001232876712328767, | |
| "loss": 0.1372, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 7.593220338983051, | |
| "grad_norm": 0.4783307909965515, | |
| "learning_rate": 0.0011643835616438356, | |
| "loss": 0.1501, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 7.728813559322034, | |
| "grad_norm": 0.36722248792648315, | |
| "learning_rate": 0.001095890410958904, | |
| "loss": 0.1328, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 7.864406779661017, | |
| "grad_norm": 2.2450578212738037, | |
| "learning_rate": 0.0010273972602739725, | |
| "loss": 0.1672, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "grad_norm": 0.483530730009079, | |
| "learning_rate": 0.0009589041095890411, | |
| "loss": 0.1531, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.933206106870229, | |
| "eval_f1": 0.9187542915365363, | |
| "eval_loss": 0.166096031665802, | |
| "eval_precision": 0.8974050294275013, | |
| "eval_recall": 0.9525944968104352, | |
| "eval_runtime": 2.4586, | |
| "eval_samples_per_second": 213.127, | |
| "eval_steps_per_second": 13.422, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 8.135593220338983, | |
| "grad_norm": 0.6294255256652832, | |
| "learning_rate": 0.0008904109589041096, | |
| "loss": 0.1786, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 8.271186440677965, | |
| "grad_norm": 0.5834006667137146, | |
| "learning_rate": 0.000821917808219178, | |
| "loss": 0.1564, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 8.40677966101695, | |
| "grad_norm": 1.0836858749389648, | |
| "learning_rate": 0.0007534246575342466, | |
| "loss": 0.1422, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 8.542372881355933, | |
| "grad_norm": 0.4150519073009491, | |
| "learning_rate": 0.0006849315068493151, | |
| "loss": 0.1262, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 8.677966101694915, | |
| "grad_norm": 0.4896199703216553, | |
| "learning_rate": 0.0006164383561643835, | |
| "loss": 0.1024, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 8.813559322033898, | |
| "grad_norm": 0.49235931038856506, | |
| "learning_rate": 0.000547945205479452, | |
| "loss": 0.1222, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 8.94915254237288, | |
| "grad_norm": 0.7004760503768921, | |
| "learning_rate": 0.00047945205479452054, | |
| "loss": 0.1451, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 8.989830508474576, | |
| "eval_accuracy": 0.9637404580152672, | |
| "eval_f1": 0.9533823109375512, | |
| "eval_loss": 0.07597702741622925, | |
| "eval_precision": 0.9463719489713148, | |
| "eval_recall": 0.9610682662096544, | |
| "eval_runtime": 2.256, | |
| "eval_samples_per_second": 232.27, | |
| "eval_steps_per_second": 14.628, | |
| "step": 663 | |
| }, | |
| { | |
| "epoch": 9.084745762711865, | |
| "grad_norm": 0.7847811579704285, | |
| "learning_rate": 0.000410958904109589, | |
| "loss": 0.1416, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 9.220338983050848, | |
| "grad_norm": 0.4217701256275177, | |
| "learning_rate": 0.00034246575342465754, | |
| "loss": 0.1058, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 9.35593220338983, | |
| "grad_norm": 0.39670172333717346, | |
| "learning_rate": 0.000273972602739726, | |
| "loss": 0.1227, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 9.491525423728813, | |
| "grad_norm": 0.448311448097229, | |
| "learning_rate": 0.0002054794520547945, | |
| "loss": 0.1391, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 9.627118644067796, | |
| "grad_norm": 0.2346179038286209, | |
| "learning_rate": 0.00014383561643835618, | |
| "loss": 0.1029, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 9.76271186440678, | |
| "grad_norm": 0.42317041754722595, | |
| "learning_rate": 7.534246575342466e-05, | |
| "loss": 0.1341, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 9.898305084745763, | |
| "grad_norm": 2.337646484375, | |
| "learning_rate": 1.3698630136986302e-05, | |
| "loss": 0.1263, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 9.898305084745763, | |
| "eval_accuracy": 0.9580152671755725, | |
| "eval_f1": 0.9466325944854914, | |
| "eval_loss": 0.08236818760633469, | |
| "eval_precision": 0.9355455710135513, | |
| "eval_recall": 0.9596305817385509, | |
| "eval_runtime": 2.279, | |
| "eval_samples_per_second": 229.924, | |
| "eval_steps_per_second": 14.48, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 9.898305084745763, | |
| "step": 730, | |
| "total_flos": 3.6369520534486057e+18, | |
| "train_loss": 0.20677236253268097, | |
| "train_runtime": 441.3046, | |
| "train_samples_per_second": 106.684, | |
| "train_steps_per_second": 1.654 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 730, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 10, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3.6369520534486057e+18, | |
| "train_batch_size": 16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |