| { | |
| "best_metric": 0.9026717557251909, | |
| "best_model_checkpoint": "deit-base-patch16-224-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": 0.6092599034309387, | |
| "learning_rate": 0.004931506849315068, | |
| "loss": 0.6182, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.2711864406779661, | |
| "grad_norm": 9.652957916259766, | |
| "learning_rate": 0.0048630136986301375, | |
| "loss": 0.6302, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.4067796610169492, | |
| "grad_norm": 1.760549783706665, | |
| "learning_rate": 0.004794520547945206, | |
| "loss": 0.645, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.5423728813559322, | |
| "grad_norm": 0.8188679814338684, | |
| "learning_rate": 0.004726027397260274, | |
| "loss": 0.4782, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.6779661016949152, | |
| "grad_norm": 3.1816465854644775, | |
| "learning_rate": 0.004657534246575342, | |
| "loss": 0.7114, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.8135593220338984, | |
| "grad_norm": 3.094874858856201, | |
| "learning_rate": 0.004589041095890411, | |
| "loss": 0.5755, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.9491525423728814, | |
| "grad_norm": 1.603766918182373, | |
| "learning_rate": 0.00452054794520548, | |
| "loss": 0.6158, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.9898305084745763, | |
| "eval_accuracy": 0.7423664122137404, | |
| "eval_f1": 0.42606790799561883, | |
| "eval_loss": 0.567380964756012, | |
| "eval_precision": 0.3711832061068702, | |
| "eval_recall": 0.5, | |
| "eval_runtime": 2.2609, | |
| "eval_samples_per_second": 231.762, | |
| "eval_steps_per_second": 14.596, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 1.0847457627118644, | |
| "grad_norm": 3.2192718982696533, | |
| "learning_rate": 0.004452054794520548, | |
| "loss": 0.5565, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 1.2203389830508475, | |
| "grad_norm": 1.6243762969970703, | |
| "learning_rate": 0.004383561643835616, | |
| "loss": 0.5592, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 1.3559322033898304, | |
| "grad_norm": 2.504822015762329, | |
| "learning_rate": 0.004315068493150685, | |
| "loss": 0.62, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.4915254237288136, | |
| "grad_norm": 1.8308496475219727, | |
| "learning_rate": 0.0042465753424657535, | |
| "loss": 0.5712, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 1.6271186440677967, | |
| "grad_norm": 0.7807316184043884, | |
| "learning_rate": 0.004178082191780822, | |
| "loss": 0.531, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 1.7627118644067796, | |
| "grad_norm": 2.2005345821380615, | |
| "learning_rate": 0.00410958904109589, | |
| "loss": 0.5394, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 1.8983050847457628, | |
| "grad_norm": 1.179870843887329, | |
| "learning_rate": 0.004041095890410959, | |
| "loss": 0.5322, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 1.993220338983051, | |
| "eval_accuracy": 0.7729007633587787, | |
| "eval_f1": 0.5396280463945307, | |
| "eval_loss": 0.48395079374313354, | |
| "eval_precision": 0.8828740157480315, | |
| "eval_recall": 0.5592592592592592, | |
| "eval_runtime": 2.4443, | |
| "eval_samples_per_second": 214.373, | |
| "eval_steps_per_second": 13.501, | |
| "step": 147 | |
| }, | |
| { | |
| "epoch": 2.0338983050847457, | |
| "grad_norm": 0.4185134768486023, | |
| "learning_rate": 0.003972602739726027, | |
| "loss": 0.5459, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 2.169491525423729, | |
| "grad_norm": 3.1739585399627686, | |
| "learning_rate": 0.003904109589041096, | |
| "loss": 0.5155, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 2.305084745762712, | |
| "grad_norm": 1.602779507637024, | |
| "learning_rate": 0.0038356164383561643, | |
| "loss": 0.5648, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 2.440677966101695, | |
| "grad_norm": 0.7795351147651672, | |
| "learning_rate": 0.003767123287671233, | |
| "loss": 0.4647, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 2.576271186440678, | |
| "grad_norm": 0.20109909772872925, | |
| "learning_rate": 0.0036986301369863013, | |
| "loss": 0.4323, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 2.711864406779661, | |
| "grad_norm": 3.717724561691284, | |
| "learning_rate": 0.00363013698630137, | |
| "loss": 0.5199, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 2.847457627118644, | |
| "grad_norm": 1.0907886028289795, | |
| "learning_rate": 0.003561643835616438, | |
| "loss": 0.4441, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 2.983050847457627, | |
| "grad_norm": 1.0848020315170288, | |
| "learning_rate": 0.003493150684931507, | |
| "loss": 0.4139, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 2.9966101694915253, | |
| "eval_accuracy": 0.7938931297709924, | |
| "eval_f1": 0.6057185854025584, | |
| "eval_loss": 0.3726596534252167, | |
| "eval_precision": 0.8913480885311871, | |
| "eval_recall": 0.6, | |
| "eval_runtime": 2.2564, | |
| "eval_samples_per_second": 232.227, | |
| "eval_steps_per_second": 14.625, | |
| "step": 221 | |
| }, | |
| { | |
| "epoch": 3.1186440677966103, | |
| "grad_norm": 0.5923116207122803, | |
| "learning_rate": 0.003424657534246575, | |
| "loss": 0.4562, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 3.2542372881355934, | |
| "grad_norm": 0.6732156872749329, | |
| "learning_rate": 0.003356164383561644, | |
| "loss": 0.4198, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 3.389830508474576, | |
| "grad_norm": 0.44104114174842834, | |
| "learning_rate": 0.003287671232876712, | |
| "loss": 0.4247, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 3.5254237288135593, | |
| "grad_norm": 1.1133421659469604, | |
| "learning_rate": 0.0032191780821917808, | |
| "loss": 0.4094, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 3.6610169491525424, | |
| "grad_norm": 0.5410763621330261, | |
| "learning_rate": 0.003150684931506849, | |
| "loss": 0.4489, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 3.7966101694915255, | |
| "grad_norm": 1.290757656097412, | |
| "learning_rate": 0.003082191780821918, | |
| "loss": 0.4028, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 3.9322033898305087, | |
| "grad_norm": 1.2204492092132568, | |
| "learning_rate": 0.0030136986301369864, | |
| "loss": 0.3979, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.7309160305343512, | |
| "eval_f1": 0.7167969274053518, | |
| "eval_loss": 0.5270416736602783, | |
| "eval_precision": 0.7405170401493931, | |
| "eval_recall": 0.8139293535180425, | |
| "eval_runtime": 2.2872, | |
| "eval_samples_per_second": 229.106, | |
| "eval_steps_per_second": 14.428, | |
| "step": 295 | |
| }, | |
| { | |
| "epoch": 4.067796610169491, | |
| "grad_norm": 0.5202679634094238, | |
| "learning_rate": 0.002945205479452055, | |
| "loss": 0.3858, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 4.203389830508475, | |
| "grad_norm": 0.20694881677627563, | |
| "learning_rate": 0.0028767123287671234, | |
| "loss": 0.426, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 4.338983050847458, | |
| "grad_norm": 0.9228326678276062, | |
| "learning_rate": 0.002808219178082192, | |
| "loss": 0.3419, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 4.47457627118644, | |
| "grad_norm": 0.5701133608818054, | |
| "learning_rate": 0.0027397260273972603, | |
| "loss": 0.4407, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 4.610169491525424, | |
| "grad_norm": 0.5276753306388855, | |
| "learning_rate": 0.002671232876712329, | |
| "loss": 0.3626, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 4.745762711864407, | |
| "grad_norm": 0.3167065680027008, | |
| "learning_rate": 0.0026027397260273972, | |
| "loss": 0.4012, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 4.88135593220339, | |
| "grad_norm": 0.9251042008399963, | |
| "learning_rate": 0.002534246575342466, | |
| "loss": 0.3858, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 4.989830508474577, | |
| "eval_accuracy": 0.8530534351145038, | |
| "eval_f1": 0.825253903289374, | |
| "eval_loss": 0.30624744296073914, | |
| "eval_precision": 0.8072997416020672, | |
| "eval_recall": 0.8623345710749311, | |
| "eval_runtime": 2.5426, | |
| "eval_samples_per_second": 206.091, | |
| "eval_steps_per_second": 12.979, | |
| "step": 368 | |
| }, | |
| { | |
| "epoch": 5.016949152542373, | |
| "grad_norm": 0.33929237723350525, | |
| "learning_rate": 0.002465753424657534, | |
| "loss": 0.362, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 5.1525423728813555, | |
| "grad_norm": 1.5055538415908813, | |
| "learning_rate": 0.002397260273972603, | |
| "loss": 0.4396, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 5.288135593220339, | |
| "grad_norm": 0.318695992231369, | |
| "learning_rate": 0.002328767123287671, | |
| "loss": 0.3909, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 5.423728813559322, | |
| "grad_norm": 1.0506914854049683, | |
| "learning_rate": 0.00226027397260274, | |
| "loss": 0.3563, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 5.559322033898305, | |
| "grad_norm": 1.1333622932434082, | |
| "learning_rate": 0.002191780821917808, | |
| "loss": 0.3737, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 5.694915254237288, | |
| "grad_norm": 0.3602863550186157, | |
| "learning_rate": 0.0021232876712328768, | |
| "loss": 0.4139, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 5.830508474576272, | |
| "grad_norm": 0.9611266851425171, | |
| "learning_rate": 0.002054794520547945, | |
| "loss": 0.3851, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 5.966101694915254, | |
| "grad_norm": 0.3874049186706543, | |
| "learning_rate": 0.0019863013698630137, | |
| "loss": 0.3704, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 5.9932203389830505, | |
| "eval_accuracy": 0.8263358778625954, | |
| "eval_f1": 0.8056371899647421, | |
| "eval_loss": 0.37736260890960693, | |
| "eval_precision": 0.793922767883912, | |
| "eval_recall": 0.8733599923831286, | |
| "eval_runtime": 2.2589, | |
| "eval_samples_per_second": 231.974, | |
| "eval_steps_per_second": 14.609, | |
| "step": 442 | |
| }, | |
| { | |
| "epoch": 6.101694915254237, | |
| "grad_norm": 0.6873330473899841, | |
| "learning_rate": 0.0019178082191780822, | |
| "loss": 0.3314, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 6.237288135593221, | |
| "grad_norm": 0.4017014801502228, | |
| "learning_rate": 0.0018493150684931506, | |
| "loss": 0.3821, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 6.372881355932203, | |
| "grad_norm": 0.4146214723587036, | |
| "learning_rate": 0.001780821917808219, | |
| "loss": 0.336, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 6.508474576271187, | |
| "grad_norm": 0.4829295873641968, | |
| "learning_rate": 0.0017123287671232876, | |
| "loss": 0.333, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 6.6440677966101696, | |
| "grad_norm": 0.31482774019241333, | |
| "learning_rate": 0.001643835616438356, | |
| "loss": 0.4051, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 6.779661016949152, | |
| "grad_norm": 1.6030710935592651, | |
| "learning_rate": 0.0015753424657534245, | |
| "loss": 0.4016, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 6.915254237288136, | |
| "grad_norm": 0.41512808203697205, | |
| "learning_rate": 0.0015068493150684932, | |
| "loss": 0.3345, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 6.996610169491525, | |
| "eval_accuracy": 0.9026717557251909, | |
| "eval_f1": 0.8748683083060584, | |
| "eval_loss": 0.2403312772512436, | |
| "eval_precision": 0.8690915124253373, | |
| "eval_recall": 0.8812434542511663, | |
| "eval_runtime": 2.2592, | |
| "eval_samples_per_second": 231.938, | |
| "eval_steps_per_second": 14.607, | |
| "step": 516 | |
| }, | |
| { | |
| "epoch": 7.0508474576271185, | |
| "grad_norm": 0.654947817325592, | |
| "learning_rate": 0.0014383561643835617, | |
| "loss": 0.3406, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 7.186440677966102, | |
| "grad_norm": 0.7446631193161011, | |
| "learning_rate": 0.0013698630136986301, | |
| "loss": 0.3591, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 7.322033898305085, | |
| "grad_norm": 1.3772833347320557, | |
| "learning_rate": 0.0013013698630136986, | |
| "loss": 0.3704, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 7.4576271186440675, | |
| "grad_norm": 0.2521153688430786, | |
| "learning_rate": 0.001232876712328767, | |
| "loss": 0.3506, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 7.593220338983051, | |
| "grad_norm": 0.48469170928001404, | |
| "learning_rate": 0.0011643835616438356, | |
| "loss": 0.336, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 7.728813559322034, | |
| "grad_norm": 0.30622732639312744, | |
| "learning_rate": 0.001095890410958904, | |
| "loss": 0.3283, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 7.864406779661017, | |
| "grad_norm": 0.34153249859809875, | |
| "learning_rate": 0.0010273972602739725, | |
| "loss": 0.3413, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "grad_norm": 0.6064002513885498, | |
| "learning_rate": 0.0009589041095890411, | |
| "loss": 0.3875, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.8816793893129771, | |
| "eval_f1": 0.8590395529252504, | |
| "eval_loss": 0.3021100163459778, | |
| "eval_precision": 0.8389118290017004, | |
| "eval_recall": 0.8985432733504712, | |
| "eval_runtime": 2.6546, | |
| "eval_samples_per_second": 197.396, | |
| "eval_steps_per_second": 12.431, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 8.135593220338983, | |
| "grad_norm": 0.49543967843055725, | |
| "learning_rate": 0.0008904109589041096, | |
| "loss": 0.3826, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 8.271186440677965, | |
| "grad_norm": 0.29732996225357056, | |
| "learning_rate": 0.000821917808219178, | |
| "loss": 0.358, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 8.40677966101695, | |
| "grad_norm": 0.3708488345146179, | |
| "learning_rate": 0.0007534246575342466, | |
| "loss": 0.3239, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 8.542372881355933, | |
| "grad_norm": 0.37521126866340637, | |
| "learning_rate": 0.0006849315068493151, | |
| "loss": 0.3074, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 8.677966101694915, | |
| "grad_norm": 0.8718960285186768, | |
| "learning_rate": 0.0006164383561643835, | |
| "loss": 0.3114, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 8.813559322033898, | |
| "grad_norm": 0.8521252274513245, | |
| "learning_rate": 0.000547945205479452, | |
| "loss": 0.3076, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 8.94915254237288, | |
| "grad_norm": 0.501818060874939, | |
| "learning_rate": 0.00047945205479452054, | |
| "loss": 0.3673, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 8.989830508474576, | |
| "eval_accuracy": 0.8969465648854962, | |
| "eval_f1": 0.8748938879456707, | |
| "eval_loss": 0.28653448820114136, | |
| "eval_precision": 0.8557379781648471, | |
| "eval_recall": 0.9064076930400837, | |
| "eval_runtime": 2.2474, | |
| "eval_samples_per_second": 233.156, | |
| "eval_steps_per_second": 14.683, | |
| "step": 663 | |
| }, | |
| { | |
| "epoch": 9.084745762711865, | |
| "grad_norm": 0.47983425855636597, | |
| "learning_rate": 0.000410958904109589, | |
| "loss": 0.3276, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 9.220338983050848, | |
| "grad_norm": 0.24815304577350616, | |
| "learning_rate": 0.00034246575342465754, | |
| "loss": 0.2874, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 9.35593220338983, | |
| "grad_norm": 0.5116902589797974, | |
| "learning_rate": 0.000273972602739726, | |
| "loss": 0.3645, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 9.491525423728813, | |
| "grad_norm": 0.34429872035980225, | |
| "learning_rate": 0.0002054794520547945, | |
| "loss": 0.3231, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 9.627118644067796, | |
| "grad_norm": 0.31422099471092224, | |
| "learning_rate": 0.000136986301369863, | |
| "loss": 0.2665, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 9.76271186440678, | |
| "grad_norm": 0.44704005122184753, | |
| "learning_rate": 6.84931506849315e-05, | |
| "loss": 0.3432, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 9.898305084745763, | |
| "grad_norm": 0.49681413173675537, | |
| "learning_rate": 0.0, | |
| "loss": 0.3493, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 9.898305084745763, | |
| "eval_accuracy": 0.8740458015267175, | |
| "eval_f1": 0.8515453296703297, | |
| "eval_loss": 0.3024097681045532, | |
| "eval_precision": 0.8314438332137447, | |
| "eval_recall": 0.895820241835666, | |
| "eval_runtime": 2.2783, | |
| "eval_samples_per_second": 229.992, | |
| "eval_steps_per_second": 14.484, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 9.898305084745763, | |
| "step": 730, | |
| "total_flos": 3.6369520534486057e+18, | |
| "train_loss": 0.4224395229391856, | |
| "train_runtime": 449.3032, | |
| "train_samples_per_second": 104.784, | |
| "train_steps_per_second": 1.625 | |
| } | |
| ], | |
| "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 | |
| } | |