Sentence Similarity
sentence-transformers
TensorBoard
Safetensors
bert
feature-extraction
text-embeddings-inference
Instructions to use Jjzzzz/finetuned_bge-small-en-v1.5 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sentence-transformers
How to use Jjzzzz/finetuned_bge-small-en-v1.5 with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("Jjzzzz/finetuned_bge-small-en-v1.5") sentences = [ "The weather is lovely today.", "It's so sunny outside!", "He drove to the stadium." ] embeddings = model.encode(sentences) similarities = model.similarity(embeddings, embeddings) print(similarities.shape) # [3, 3] - Notebooks
- Google Colab
- Kaggle
| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 4.081632653061225, | |
| "eval_steps": 500, | |
| "global_step": 1000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.04081632653061224, | |
| "grad_norm": 7.114395618438721, | |
| "learning_rate": 9.981632653061225e-06, | |
| "loss": 0.7362, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.08163265306122448, | |
| "grad_norm": 11.572301864624023, | |
| "learning_rate": 9.961224489795919e-06, | |
| "loss": 0.8729, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.12244897959183673, | |
| "grad_norm": 9.383491516113281, | |
| "learning_rate": 9.940816326530614e-06, | |
| "loss": 0.773, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.16326530612244897, | |
| "grad_norm": 7.83120059967041, | |
| "learning_rate": 9.920408163265307e-06, | |
| "loss": 0.7817, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.20408163265306123, | |
| "grad_norm": 10.92087173461914, | |
| "learning_rate": 9.9e-06, | |
| "loss": 0.6256, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.24489795918367346, | |
| "grad_norm": 3.8826725482940674, | |
| "learning_rate": 9.879591836734695e-06, | |
| "loss": 0.5759, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.2857142857142857, | |
| "grad_norm": 11.15483283996582, | |
| "learning_rate": 9.859183673469388e-06, | |
| "loss": 0.7333, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.32653061224489793, | |
| "grad_norm": 11.470726013183594, | |
| "learning_rate": 9.838775510204083e-06, | |
| "loss": 0.5943, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.3673469387755102, | |
| "grad_norm": 13.159674644470215, | |
| "learning_rate": 9.818367346938777e-06, | |
| "loss": 0.7804, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.40816326530612246, | |
| "grad_norm": 9.58558464050293, | |
| "learning_rate": 9.79795918367347e-06, | |
| "loss": 0.6491, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.4489795918367347, | |
| "grad_norm": 9.653897285461426, | |
| "learning_rate": 9.777551020408163e-06, | |
| "loss": 0.5919, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.4897959183673469, | |
| "grad_norm": 8.117432594299316, | |
| "learning_rate": 9.757142857142858e-06, | |
| "loss": 0.4571, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.5306122448979592, | |
| "grad_norm": 6.9328460693359375, | |
| "learning_rate": 9.736734693877551e-06, | |
| "loss": 0.6597, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.5714285714285714, | |
| "grad_norm": 7.962501049041748, | |
| "learning_rate": 9.716326530612246e-06, | |
| "loss": 0.5132, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.6122448979591837, | |
| "grad_norm": 10.508763313293457, | |
| "learning_rate": 9.69591836734694e-06, | |
| "loss": 0.6893, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.6530612244897959, | |
| "grad_norm": 7.637253761291504, | |
| "learning_rate": 9.675510204081635e-06, | |
| "loss": 0.6142, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.6938775510204082, | |
| "grad_norm": 10.0332670211792, | |
| "learning_rate": 9.655102040816328e-06, | |
| "loss": 0.582, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.7346938775510204, | |
| "grad_norm": 8.150875091552734, | |
| "learning_rate": 9.634693877551021e-06, | |
| "loss": 0.477, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.7755102040816326, | |
| "grad_norm": 10.330913543701172, | |
| "learning_rate": 9.614285714285714e-06, | |
| "loss": 0.5916, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.8163265306122449, | |
| "grad_norm": 11.654999732971191, | |
| "learning_rate": 9.593877551020408e-06, | |
| "loss": 0.6236, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.8571428571428571, | |
| "grad_norm": 8.048078536987305, | |
| "learning_rate": 9.573469387755103e-06, | |
| "loss": 0.6142, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.8979591836734694, | |
| "grad_norm": 9.869592666625977, | |
| "learning_rate": 9.553061224489798e-06, | |
| "loss": 0.625, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.9387755102040817, | |
| "grad_norm": 8.321409225463867, | |
| "learning_rate": 9.532653061224491e-06, | |
| "loss": 0.5767, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.9795918367346939, | |
| "grad_norm": 7.6769256591796875, | |
| "learning_rate": 9.512244897959184e-06, | |
| "loss": 0.5134, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 1.0204081632653061, | |
| "grad_norm": 9.609123229980469, | |
| "learning_rate": 9.491836734693877e-06, | |
| "loss": 0.5868, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 1.0612244897959184, | |
| "grad_norm": 9.19683837890625, | |
| "learning_rate": 9.471428571428572e-06, | |
| "loss": 0.5215, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 1.1020408163265305, | |
| "grad_norm": 7.328164577484131, | |
| "learning_rate": 9.451020408163266e-06, | |
| "loss": 0.5422, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 1.1428571428571428, | |
| "grad_norm": 6.913904190063477, | |
| "learning_rate": 9.430612244897959e-06, | |
| "loss": 0.5214, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 1.183673469387755, | |
| "grad_norm": 9.28811264038086, | |
| "learning_rate": 9.410204081632654e-06, | |
| "loss": 0.5319, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 1.2244897959183674, | |
| "grad_norm": 9.132966041564941, | |
| "learning_rate": 9.389795918367349e-06, | |
| "loss": 0.5581, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 1.2653061224489797, | |
| "grad_norm": 6.9722065925598145, | |
| "learning_rate": 9.369387755102042e-06, | |
| "loss": 0.431, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 1.306122448979592, | |
| "grad_norm": 5.06177282333374, | |
| "learning_rate": 9.348979591836736e-06, | |
| "loss": 0.4583, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 1.346938775510204, | |
| "grad_norm": 7.732840538024902, | |
| "learning_rate": 9.328571428571429e-06, | |
| "loss": 0.4194, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 1.3877551020408163, | |
| "grad_norm": 8.94101333618164, | |
| "learning_rate": 9.308163265306122e-06, | |
| "loss": 0.4519, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 1.4285714285714286, | |
| "grad_norm": 7.5437750816345215, | |
| "learning_rate": 9.287755102040817e-06, | |
| "loss": 0.5095, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 1.469387755102041, | |
| "grad_norm": 5.702700138092041, | |
| "learning_rate": 9.26734693877551e-06, | |
| "loss": 0.3936, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 1.510204081632653, | |
| "grad_norm": 9.153871536254883, | |
| "learning_rate": 9.246938775510205e-06, | |
| "loss": 0.4566, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 1.5510204081632653, | |
| "grad_norm": 13.249794006347656, | |
| "learning_rate": 9.226530612244899e-06, | |
| "loss": 0.5216, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 1.5918367346938775, | |
| "grad_norm": 7.065913200378418, | |
| "learning_rate": 9.206122448979594e-06, | |
| "loss": 0.4562, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 1.6326530612244898, | |
| "grad_norm": 7.559301853179932, | |
| "learning_rate": 9.185714285714287e-06, | |
| "loss": 0.3883, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 1.6734693877551021, | |
| "grad_norm": 12.103629112243652, | |
| "learning_rate": 9.16530612244898e-06, | |
| "loss": 0.4149, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 1.7142857142857144, | |
| "grad_norm": 7.9720072746276855, | |
| "learning_rate": 9.144897959183673e-06, | |
| "loss": 0.4718, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 1.7551020408163265, | |
| "grad_norm": 4.845782279968262, | |
| "learning_rate": 9.124489795918368e-06, | |
| "loss": 0.4304, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 1.7959183673469388, | |
| "grad_norm": 6.954368591308594, | |
| "learning_rate": 9.104081632653062e-06, | |
| "loss": 0.3436, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 1.836734693877551, | |
| "grad_norm": 4.751299858093262, | |
| "learning_rate": 9.083673469387757e-06, | |
| "loss": 0.4366, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 1.8775510204081631, | |
| "grad_norm": 6.507364273071289, | |
| "learning_rate": 9.06326530612245e-06, | |
| "loss": 0.5794, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 1.9183673469387754, | |
| "grad_norm": 8.891802787780762, | |
| "learning_rate": 9.042857142857143e-06, | |
| "loss": 0.4616, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 1.9591836734693877, | |
| "grad_norm": 10.056327819824219, | |
| "learning_rate": 9.022448979591838e-06, | |
| "loss": 0.4946, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 7.899660110473633, | |
| "learning_rate": 9.002040816326531e-06, | |
| "loss": 0.4437, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 2.0408163265306123, | |
| "grad_norm": 6.761326313018799, | |
| "learning_rate": 8.981632653061225e-06, | |
| "loss": 0.4303, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 2.0816326530612246, | |
| "grad_norm": 8.639615058898926, | |
| "learning_rate": 8.96122448979592e-06, | |
| "loss": 0.3267, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 2.122448979591837, | |
| "grad_norm": 7.710758209228516, | |
| "learning_rate": 8.940816326530613e-06, | |
| "loss": 0.3559, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 2.163265306122449, | |
| "grad_norm": 6.812905311584473, | |
| "learning_rate": 8.920408163265308e-06, | |
| "loss": 0.4761, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 2.204081632653061, | |
| "grad_norm": 7.2431511878967285, | |
| "learning_rate": 8.900000000000001e-06, | |
| "loss": 0.405, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 2.2448979591836733, | |
| "grad_norm": 7.230724811553955, | |
| "learning_rate": 8.879591836734694e-06, | |
| "loss": 0.3638, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 2.2857142857142856, | |
| "grad_norm": 9.520208358764648, | |
| "learning_rate": 8.859183673469388e-06, | |
| "loss": 0.3473, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 2.326530612244898, | |
| "grad_norm": 7.048585414886475, | |
| "learning_rate": 8.838775510204083e-06, | |
| "loss": 0.3652, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 2.36734693877551, | |
| "grad_norm": 6.979404449462891, | |
| "learning_rate": 8.818367346938776e-06, | |
| "loss": 0.3855, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 2.4081632653061225, | |
| "grad_norm": 3.765305280685425, | |
| "learning_rate": 8.797959183673471e-06, | |
| "loss": 0.3452, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 2.4489795918367347, | |
| "grad_norm": 10.533697128295898, | |
| "learning_rate": 8.777551020408164e-06, | |
| "loss": 0.3874, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 2.489795918367347, | |
| "grad_norm": 8.108145713806152, | |
| "learning_rate": 8.757142857142858e-06, | |
| "loss": 0.3695, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 2.5306122448979593, | |
| "grad_norm": 7.947360992431641, | |
| "learning_rate": 8.736734693877552e-06, | |
| "loss": 0.408, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 2.571428571428571, | |
| "grad_norm": 7.8081374168396, | |
| "learning_rate": 8.716326530612246e-06, | |
| "loss": 0.4059, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 2.612244897959184, | |
| "grad_norm": 8.579155921936035, | |
| "learning_rate": 8.695918367346939e-06, | |
| "loss": 0.3934, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 2.6530612244897958, | |
| "grad_norm": 6.4387712478637695, | |
| "learning_rate": 8.675510204081632e-06, | |
| "loss": 0.4256, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 2.693877551020408, | |
| "grad_norm": 8.415692329406738, | |
| "learning_rate": 8.655102040816327e-06, | |
| "loss": 0.3453, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 2.7346938775510203, | |
| "grad_norm": 8.50904369354248, | |
| "learning_rate": 8.63469387755102e-06, | |
| "loss": 0.4766, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 2.7755102040816326, | |
| "grad_norm": 4.662519931793213, | |
| "learning_rate": 8.614285714285716e-06, | |
| "loss": 0.3973, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 2.816326530612245, | |
| "grad_norm": 6.288435935974121, | |
| "learning_rate": 8.593877551020409e-06, | |
| "loss": 0.4408, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 2.857142857142857, | |
| "grad_norm": 6.625838279724121, | |
| "learning_rate": 8.573469387755102e-06, | |
| "loss": 0.2908, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 2.8979591836734695, | |
| "grad_norm": 8.510032653808594, | |
| "learning_rate": 8.553061224489797e-06, | |
| "loss": 0.3813, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 2.938775510204082, | |
| "grad_norm": 11.82463264465332, | |
| "learning_rate": 8.53265306122449e-06, | |
| "loss": 0.4352, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 2.979591836734694, | |
| "grad_norm": 8.821819305419922, | |
| "learning_rate": 8.512244897959184e-06, | |
| "loss": 0.4318, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 3.020408163265306, | |
| "grad_norm": 8.010713577270508, | |
| "learning_rate": 8.491836734693879e-06, | |
| "loss": 0.2323, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 3.061224489795918, | |
| "grad_norm": 9.03991985321045, | |
| "learning_rate": 8.471428571428572e-06, | |
| "loss": 0.3603, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 3.1020408163265305, | |
| "grad_norm": 10.94204044342041, | |
| "learning_rate": 8.451020408163267e-06, | |
| "loss": 0.3576, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 3.142857142857143, | |
| "grad_norm": 7.89410924911499, | |
| "learning_rate": 8.43061224489796e-06, | |
| "loss": 0.2851, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 3.183673469387755, | |
| "grad_norm": 6.53656005859375, | |
| "learning_rate": 8.410204081632653e-06, | |
| "loss": 0.318, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 3.2244897959183674, | |
| "grad_norm": 6.487284183502197, | |
| "learning_rate": 8.389795918367347e-06, | |
| "loss": 0.317, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 3.2653061224489797, | |
| "grad_norm": 6.947931289672852, | |
| "learning_rate": 8.369387755102042e-06, | |
| "loss": 0.2879, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 3.306122448979592, | |
| "grad_norm": 4.166048526763916, | |
| "learning_rate": 8.348979591836735e-06, | |
| "loss": 0.3392, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 3.3469387755102042, | |
| "grad_norm": 9.974846839904785, | |
| "learning_rate": 8.32857142857143e-06, | |
| "loss": 0.3663, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 3.387755102040816, | |
| "grad_norm": 9.668428421020508, | |
| "learning_rate": 8.308163265306123e-06, | |
| "loss": 0.3212, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 3.4285714285714284, | |
| "grad_norm": 11.81507396697998, | |
| "learning_rate": 8.287755102040816e-06, | |
| "loss": 0.3241, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 3.4693877551020407, | |
| "grad_norm": 13.690321922302246, | |
| "learning_rate": 8.267346938775511e-06, | |
| "loss": 0.4535, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 3.510204081632653, | |
| "grad_norm": 11.042778968811035, | |
| "learning_rate": 8.246938775510205e-06, | |
| "loss": 0.3826, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 3.5510204081632653, | |
| "grad_norm": 8.57719612121582, | |
| "learning_rate": 8.226530612244898e-06, | |
| "loss": 0.3905, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 3.5918367346938775, | |
| "grad_norm": 7.843425750732422, | |
| "learning_rate": 8.206122448979591e-06, | |
| "loss": 0.3125, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 3.63265306122449, | |
| "grad_norm": 5.9236931800842285, | |
| "learning_rate": 8.185714285714286e-06, | |
| "loss": 0.3512, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 3.673469387755102, | |
| "grad_norm": 8.213603973388672, | |
| "learning_rate": 8.165306122448981e-06, | |
| "loss": 0.4094, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 3.7142857142857144, | |
| "grad_norm": 3.8083949089050293, | |
| "learning_rate": 8.144897959183674e-06, | |
| "loss": 0.2751, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 3.7551020408163263, | |
| "grad_norm": 12.339240074157715, | |
| "learning_rate": 8.124489795918368e-06, | |
| "loss": 0.3296, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 3.795918367346939, | |
| "grad_norm": 9.532052040100098, | |
| "learning_rate": 8.104081632653061e-06, | |
| "loss": 0.3033, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 3.836734693877551, | |
| "grad_norm": 6.307032108306885, | |
| "learning_rate": 8.083673469387756e-06, | |
| "loss": 0.3765, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 3.877551020408163, | |
| "grad_norm": 7.3003010749816895, | |
| "learning_rate": 8.06326530612245e-06, | |
| "loss": 0.2161, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 3.9183673469387754, | |
| "grad_norm": 7.6572699546813965, | |
| "learning_rate": 8.042857142857143e-06, | |
| "loss": 0.2886, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 3.9591836734693877, | |
| "grad_norm": 6.745776176452637, | |
| "learning_rate": 8.022448979591838e-06, | |
| "loss": 0.3376, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "grad_norm": 10.482270240783691, | |
| "learning_rate": 8.002040816326533e-06, | |
| "loss": 0.2657, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 4.040816326530612, | |
| "grad_norm": 6.213717460632324, | |
| "learning_rate": 7.981632653061226e-06, | |
| "loss": 0.2596, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 4.081632653061225, | |
| "grad_norm": 10.256094932556152, | |
| "learning_rate": 7.961224489795919e-06, | |
| "loss": 0.2338, | |
| "step": 1000 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 4900, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 20, | |
| "save_steps": 1000, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 0.0, | |
| "train_batch_size": 30, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |