| { | |
| "best_metric": 0.9751908396946565, | |
| "best_model_checkpoint": "vit-base-patch16-224-in21k-finetuned-lora-medmnistv2/checkpoint-221", | |
| "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": 0.5722031593322754, | |
| "learning_rate": 0.004931506849315068, | |
| "loss": 0.4736, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.2711864406779661, | |
| "grad_norm": 2.089559316635132, | |
| "learning_rate": 0.0048630136986301375, | |
| "loss": 0.4462, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.4067796610169492, | |
| "grad_norm": 3.0388331413269043, | |
| "learning_rate": 0.004794520547945206, | |
| "loss": 0.2969, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.5423728813559322, | |
| "grad_norm": 0.4622490406036377, | |
| "learning_rate": 0.004726027397260274, | |
| "loss": 0.309, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.6779661016949152, | |
| "grad_norm": 1.2164361476898193, | |
| "learning_rate": 0.004657534246575342, | |
| "loss": 0.2817, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.8135593220338984, | |
| "grad_norm": 0.30212166905403137, | |
| "learning_rate": 0.004589041095890411, | |
| "loss": 0.24, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.9491525423728814, | |
| "grad_norm": 0.9486951231956482, | |
| "learning_rate": 0.00452054794520548, | |
| "loss": 0.2447, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.9898305084745763, | |
| "eval_accuracy": 0.9561068702290076, | |
| "eval_f1": 0.9445770389275943, | |
| "eval_loss": 0.11798465996980667, | |
| "eval_precision": 0.9313190730837789, | |
| "eval_recall": 0.9607635913548509, | |
| "eval_runtime": 2.3492, | |
| "eval_samples_per_second": 223.055, | |
| "eval_steps_per_second": 14.047, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 1.0847457627118644, | |
| "grad_norm": 1.1987316608428955, | |
| "learning_rate": 0.004452054794520548, | |
| "loss": 0.2017, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 1.2203389830508475, | |
| "grad_norm": 0.6783656477928162, | |
| "learning_rate": 0.004383561643835616, | |
| "loss": 0.2214, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 1.3559322033898304, | |
| "grad_norm": 1.073630452156067, | |
| "learning_rate": 0.004315068493150685, | |
| "loss": 0.1989, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.4915254237288136, | |
| "grad_norm": 0.3175281584262848, | |
| "learning_rate": 0.0042465753424657535, | |
| "loss": 0.1857, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 1.6271186440677967, | |
| "grad_norm": 0.6710169911384583, | |
| "learning_rate": 0.004178082191780822, | |
| "loss": 0.2305, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 1.7627118644067796, | |
| "grad_norm": 0.8543218374252319, | |
| "learning_rate": 0.00410958904109589, | |
| "loss": 0.2111, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 1.8983050847457628, | |
| "grad_norm": 0.6326661109924316, | |
| "learning_rate": 0.004041095890410959, | |
| "loss": 0.2136, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 1.993220338983051, | |
| "eval_accuracy": 0.9637404580152672, | |
| "eval_f1": 0.9529434006853362, | |
| "eval_loss": 0.10151813924312592, | |
| "eval_precision": 0.9497822332357138, | |
| "eval_recall": 0.9562315528896506, | |
| "eval_runtime": 2.4266, | |
| "eval_samples_per_second": 215.944, | |
| "eval_steps_per_second": 13.6, | |
| "step": 147 | |
| }, | |
| { | |
| "epoch": 2.0338983050847457, | |
| "grad_norm": 0.40849238634109497, | |
| "learning_rate": 0.003972602739726027, | |
| "loss": 0.2148, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 2.169491525423729, | |
| "grad_norm": 1.0935662984848022, | |
| "learning_rate": 0.003904109589041096, | |
| "loss": 0.2106, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 2.305084745762712, | |
| "grad_norm": 0.6485463380813599, | |
| "learning_rate": 0.0038356164383561643, | |
| "loss": 0.2205, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 2.440677966101695, | |
| "grad_norm": 0.5151948928833008, | |
| "learning_rate": 0.003767123287671233, | |
| "loss": 0.2018, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 2.576271186440678, | |
| "grad_norm": 0.5166621804237366, | |
| "learning_rate": 0.0036986301369863013, | |
| "loss": 0.1827, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 2.711864406779661, | |
| "grad_norm": 0.8355435729026794, | |
| "learning_rate": 0.00363013698630137, | |
| "loss": 0.2171, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 2.847457627118644, | |
| "grad_norm": 0.558962881565094, | |
| "learning_rate": 0.003561643835616438, | |
| "loss": 0.1845, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 2.983050847457627, | |
| "grad_norm": 0.6180588603019714, | |
| "learning_rate": 0.003493150684931507, | |
| "loss": 0.1431, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 2.9966101694915253, | |
| "eval_accuracy": 0.9751908396946565, | |
| "eval_f1": 0.9671702932600785, | |
| "eval_loss": 0.07291658967733383, | |
| "eval_precision": 0.9731940648184303, | |
| "eval_recall": 0.9615252784918595, | |
| "eval_runtime": 2.3109, | |
| "eval_samples_per_second": 226.748, | |
| "eval_steps_per_second": 14.28, | |
| "step": 221 | |
| }, | |
| { | |
| "epoch": 3.1186440677966103, | |
| "grad_norm": 0.4949386715888977, | |
| "learning_rate": 0.003424657534246575, | |
| "loss": 0.2148, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 3.2542372881355934, | |
| "grad_norm": 0.5671024918556213, | |
| "learning_rate": 0.003356164383561644, | |
| "loss": 0.172, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 3.389830508474576, | |
| "grad_norm": 0.515737771987915, | |
| "learning_rate": 0.003287671232876712, | |
| "loss": 0.1962, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 3.5254237288135593, | |
| "grad_norm": 0.42013198137283325, | |
| "learning_rate": 0.0032191780821917808, | |
| "loss": 0.1571, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 3.6610169491525424, | |
| "grad_norm": 0.41014379262924194, | |
| "learning_rate": 0.003150684931506849, | |
| "loss": 0.1905, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 3.7966101694915255, | |
| "grad_norm": 0.48967182636260986, | |
| "learning_rate": 0.003082191780821918, | |
| "loss": 0.1344, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 3.9322033898305087, | |
| "grad_norm": 0.3962344229221344, | |
| "learning_rate": 0.0030136986301369864, | |
| "loss": 0.1576, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.9637404580152672, | |
| "eval_f1": 0.9531647653769258, | |
| "eval_loss": 0.08732008934020996, | |
| "eval_precision": 0.9480282738095238, | |
| "eval_recall": 0.9586499095496526, | |
| "eval_runtime": 2.3116, | |
| "eval_samples_per_second": 226.687, | |
| "eval_steps_per_second": 14.276, | |
| "step": 295 | |
| }, | |
| { | |
| "epoch": 4.067796610169491, | |
| "grad_norm": 0.28995221853256226, | |
| "learning_rate": 0.002945205479452055, | |
| "loss": 0.1319, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 4.203389830508475, | |
| "grad_norm": 0.5315499901771545, | |
| "learning_rate": 0.0028767123287671234, | |
| "loss": 0.2781, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 4.338983050847458, | |
| "grad_norm": 0.24718379974365234, | |
| "learning_rate": 0.002808219178082192, | |
| "loss": 0.1896, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 4.47457627118644, | |
| "grad_norm": 0.404805988073349, | |
| "learning_rate": 0.0027397260273972603, | |
| "loss": 0.1829, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 4.610169491525424, | |
| "grad_norm": 0.5308801531791687, | |
| "learning_rate": 0.002671232876712329, | |
| "loss": 0.1665, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 4.745762711864407, | |
| "grad_norm": 0.7429054975509644, | |
| "learning_rate": 0.0026027397260273972, | |
| "loss": 0.1646, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 4.88135593220339, | |
| "grad_norm": 0.6361825466156006, | |
| "learning_rate": 0.002534246575342466, | |
| "loss": 0.2072, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 4.989830508474577, | |
| "eval_accuracy": 0.9713740458015268, | |
| "eval_f1": 0.9626722135947228, | |
| "eval_loss": 0.076077401638031, | |
| "eval_precision": 0.9615676167374165, | |
| "eval_recall": 0.9637912977244597, | |
| "eval_runtime": 2.3751, | |
| "eval_samples_per_second": 220.624, | |
| "eval_steps_per_second": 13.894, | |
| "step": 368 | |
| }, | |
| { | |
| "epoch": 5.016949152542373, | |
| "grad_norm": 0.6114002466201782, | |
| "learning_rate": 0.002465753424657534, | |
| "loss": 0.1943, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 5.1525423728813555, | |
| "grad_norm": 0.32443058490753174, | |
| "learning_rate": 0.002397260273972603, | |
| "loss": 0.1541, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 5.288135593220339, | |
| "grad_norm": 0.44808831810951233, | |
| "learning_rate": 0.002328767123287671, | |
| "loss": 0.1397, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 5.423728813559322, | |
| "grad_norm": 0.478524386882782, | |
| "learning_rate": 0.00226027397260274, | |
| "loss": 0.1647, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 5.559322033898305, | |
| "grad_norm": 0.8286917805671692, | |
| "learning_rate": 0.002191780821917808, | |
| "loss": 0.1532, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 5.694915254237288, | |
| "grad_norm": 0.7862728238105774, | |
| "learning_rate": 0.0021232876712328768, | |
| "loss": 0.1474, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 5.830508474576272, | |
| "grad_norm": 1.1601946353912354, | |
| "learning_rate": 0.002054794520547945, | |
| "loss": 0.2347, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 5.966101694915254, | |
| "grad_norm": 1.3851842880249023, | |
| "learning_rate": 0.0019863013698630137, | |
| "loss": 0.1908, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 5.9932203389830505, | |
| "eval_accuracy": 0.9599236641221374, | |
| "eval_f1": 0.9496169994551458, | |
| "eval_loss": 0.10439441353082657, | |
| "eval_precision": 0.9348118279569892, | |
| "eval_recall": 0.9681709987622584, | |
| "eval_runtime": 2.3199, | |
| "eval_samples_per_second": 225.87, | |
| "eval_steps_per_second": 14.225, | |
| "step": 442 | |
| }, | |
| { | |
| "epoch": 6.101694915254237, | |
| "grad_norm": 0.6037909388542175, | |
| "learning_rate": 0.0019178082191780822, | |
| "loss": 0.1326, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 6.237288135593221, | |
| "grad_norm": 0.6797343492507935, | |
| "learning_rate": 0.0018493150684931506, | |
| "loss": 0.1909, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 6.372881355932203, | |
| "grad_norm": 0.5503271222114563, | |
| "learning_rate": 0.0017876712328767123, | |
| "loss": 0.1328, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 6.508474576271187, | |
| "grad_norm": 0.46364396810531616, | |
| "learning_rate": 0.0017191780821917808, | |
| "loss": 0.1586, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 6.6440677966101696, | |
| "grad_norm": 0.7383654713630676, | |
| "learning_rate": 0.0016506849315068492, | |
| "loss": 0.1393, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 6.779661016949152, | |
| "grad_norm": 0.7454331517219543, | |
| "learning_rate": 0.0015821917808219177, | |
| "loss": 0.163, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 6.915254237288136, | |
| "grad_norm": 0.7943591475486755, | |
| "learning_rate": 0.0015136986301369862, | |
| "loss": 0.1637, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 6.996610169491525, | |
| "eval_accuracy": 0.9675572519083969, | |
| "eval_f1": 0.9582894361020196, | |
| "eval_loss": 0.07422558218240738, | |
| "eval_precision": 0.9512019762554385, | |
| "eval_recall": 0.9660573169570599, | |
| "eval_runtime": 2.67, | |
| "eval_samples_per_second": 196.256, | |
| "eval_steps_per_second": 12.36, | |
| "step": 516 | |
| }, | |
| { | |
| "epoch": 7.0508474576271185, | |
| "grad_norm": 0.5350046753883362, | |
| "learning_rate": 0.0014452054794520546, | |
| "loss": 0.1415, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 7.186440677966102, | |
| "grad_norm": 0.9918954372406006, | |
| "learning_rate": 0.001376712328767123, | |
| "loss": 0.1548, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 7.322033898305085, | |
| "grad_norm": 2.7371268272399902, | |
| "learning_rate": 0.0013082191780821918, | |
| "loss": 0.1583, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 7.4576271186440675, | |
| "grad_norm": 1.9455125331878662, | |
| "learning_rate": 0.0012397260273972603, | |
| "loss": 0.1399, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 7.593220338983051, | |
| "grad_norm": 1.1810232400894165, | |
| "learning_rate": 0.0011712328767123287, | |
| "loss": 0.1535, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 7.728813559322034, | |
| "grad_norm": 0.5082597136497498, | |
| "learning_rate": 0.0011027397260273974, | |
| "loss": 0.1395, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 7.864406779661017, | |
| "grad_norm": 0.435004860162735, | |
| "learning_rate": 0.001034246575342466, | |
| "loss": 0.1443, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "grad_norm": 0.4963846504688263, | |
| "learning_rate": 0.0009657534246575344, | |
| "loss": 0.1385, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.9312977099236641, | |
| "eval_f1": 0.9169177104804185, | |
| "eval_loss": 0.18427740037441254, | |
| "eval_precision": 0.8947368421052632, | |
| "eval_recall": 0.9537275064267352, | |
| "eval_runtime": 2.338, | |
| "eval_samples_per_second": 224.121, | |
| "eval_steps_per_second": 14.115, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 8.135593220338983, | |
| "grad_norm": 0.5249541997909546, | |
| "learning_rate": 0.0008972602739726028, | |
| "loss": 0.1574, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 8.271186440677965, | |
| "grad_norm": 0.4605633020401001, | |
| "learning_rate": 0.0008287671232876713, | |
| "loss": 0.1543, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 8.40677966101695, | |
| "grad_norm": 0.3483382761478424, | |
| "learning_rate": 0.0007602739726027398, | |
| "loss": 0.131, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 8.542372881355933, | |
| "grad_norm": 0.21878492832183838, | |
| "learning_rate": 0.0006917808219178081, | |
| "loss": 0.1158, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 8.677966101694915, | |
| "grad_norm": 0.6566260457038879, | |
| "learning_rate": 0.0006232876712328767, | |
| "loss": 0.1018, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 8.813559322033898, | |
| "grad_norm": 0.3624425232410431, | |
| "learning_rate": 0.0005547945205479452, | |
| "loss": 0.1137, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 8.94915254237288, | |
| "grad_norm": 0.8725977540016174, | |
| "learning_rate": 0.0004863013698630137, | |
| "loss": 0.1335, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 8.989830508474576, | |
| "eval_accuracy": 0.9751908396946565, | |
| "eval_f1": 0.9679548394684229, | |
| "eval_loss": 0.0676569938659668, | |
| "eval_precision": 0.9626488095238095, | |
| "eval_recall": 0.9736170617918689, | |
| "eval_runtime": 2.3252, | |
| "eval_samples_per_second": 225.358, | |
| "eval_steps_per_second": 14.192, | |
| "step": 663 | |
| }, | |
| { | |
| "epoch": 9.084745762711865, | |
| "grad_norm": 0.46945634484291077, | |
| "learning_rate": 0.00041780821917808224, | |
| "loss": 0.1348, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 9.220338983050848, | |
| "grad_norm": 0.33705276250839233, | |
| "learning_rate": 0.0003493150684931507, | |
| "loss": 0.0968, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 9.35593220338983, | |
| "grad_norm": 0.554704487323761, | |
| "learning_rate": 0.0002808219178082192, | |
| "loss": 0.1379, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 9.491525423728813, | |
| "grad_norm": 0.5419002175331116, | |
| "learning_rate": 0.00021232876712328768, | |
| "loss": 0.128, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 9.627118644067796, | |
| "grad_norm": 0.32422158122062683, | |
| "learning_rate": 0.00014383561643835618, | |
| "loss": 0.1065, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 9.76271186440678, | |
| "grad_norm": 0.3378284275531769, | |
| "learning_rate": 7.534246575342466e-05, | |
| "loss": 0.1354, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 9.898305084745763, | |
| "grad_norm": 0.2171776294708252, | |
| "learning_rate": 6.849315068493151e-06, | |
| "loss": 0.1186, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 9.898305084745763, | |
| "eval_accuracy": 0.9751908396946565, | |
| "eval_f1": 0.9679548394684229, | |
| "eval_loss": 0.0765310674905777, | |
| "eval_precision": 0.9626488095238095, | |
| "eval_recall": 0.9736170617918689, | |
| "eval_runtime": 2.3291, | |
| "eval_samples_per_second": 224.984, | |
| "eval_steps_per_second": 14.169, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 9.898305084745763, | |
| "step": 730, | |
| "total_flos": 3.6369520534486057e+18, | |
| "train_loss": 0.18177251358554788, | |
| "train_runtime": 459.6522, | |
| "train_samples_per_second": 102.425, | |
| "train_steps_per_second": 1.588 | |
| } | |
| ], | |
| "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 | |
| } | |