Instructions to use bbytxt/19f15561-92e1-4bf4-8d65-5b532fafa1e2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use bbytxt/19f15561-92e1-4bf4-8d65-5b532fafa1e2 with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("unsloth/Qwen2-7B-Instruct") model = PeftModel.from_pretrained(base_model, "bbytxt/19f15561-92e1-4bf4-8d65-5b532fafa1e2") - Notebooks
- Google Colab
- Kaggle
| { | |
| "best_metric": 0.980871319770813, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-100", | |
| "epoch": 1.8475750577367207, | |
| "eval_steps": 50, | |
| "global_step": 200, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.009237875288683603, | |
| "grad_norm": 0.9624943137168884, | |
| "learning_rate": 1e-05, | |
| "loss": 1.6953, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.009237875288683603, | |
| "eval_loss": 1.5332071781158447, | |
| "eval_runtime": 14.0529, | |
| "eval_samples_per_second": 12.951, | |
| "eval_steps_per_second": 3.273, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.018475750577367205, | |
| "grad_norm": 1.1498544216156006, | |
| "learning_rate": 2e-05, | |
| "loss": 1.6017, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.02771362586605081, | |
| "grad_norm": 1.3203157186508179, | |
| "learning_rate": 3e-05, | |
| "loss": 1.6891, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.03695150115473441, | |
| "grad_norm": 1.3441493511199951, | |
| "learning_rate": 4e-05, | |
| "loss": 1.4696, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.046189376443418015, | |
| "grad_norm": 1.0900921821594238, | |
| "learning_rate": 5e-05, | |
| "loss": 1.6002, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.05542725173210162, | |
| "grad_norm": 1.103299617767334, | |
| "learning_rate": 6e-05, | |
| "loss": 1.4737, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.06466512702078522, | |
| "grad_norm": 1.1934887170791626, | |
| "learning_rate": 7e-05, | |
| "loss": 1.5775, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.07390300230946882, | |
| "grad_norm": 1.0997755527496338, | |
| "learning_rate": 8e-05, | |
| "loss": 1.382, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.08314087759815242, | |
| "grad_norm": 0.884574294090271, | |
| "learning_rate": 9e-05, | |
| "loss": 1.1767, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.09237875288683603, | |
| "grad_norm": 0.7020560503005981, | |
| "learning_rate": 0.0001, | |
| "loss": 1.2327, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.10161662817551963, | |
| "grad_norm": 0.712772786617279, | |
| "learning_rate": 9.999316524962345e-05, | |
| "loss": 1.0904, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.11085450346420324, | |
| "grad_norm": 0.7114707231521606, | |
| "learning_rate": 9.997266286704631e-05, | |
| "loss": 1.2084, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.12009237875288684, | |
| "grad_norm": 0.8405084609985352, | |
| "learning_rate": 9.993849845741524e-05, | |
| "loss": 1.3265, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.12933025404157045, | |
| "grad_norm": 0.6452769041061401, | |
| "learning_rate": 9.989068136093873e-05, | |
| "loss": 1.156, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.13856812933025403, | |
| "grad_norm": 0.6267441511154175, | |
| "learning_rate": 9.98292246503335e-05, | |
| "loss": 1.1191, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.14780600461893764, | |
| "grad_norm": 0.646516740322113, | |
| "learning_rate": 9.975414512725057e-05, | |
| "loss": 1.0441, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.15704387990762125, | |
| "grad_norm": 0.6149029731750488, | |
| "learning_rate": 9.966546331768191e-05, | |
| "loss": 1.1163, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.16628175519630484, | |
| "grad_norm": 0.6015509366989136, | |
| "learning_rate": 9.956320346634876e-05, | |
| "loss": 1.0861, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.17551963048498845, | |
| "grad_norm": 0.6039507389068604, | |
| "learning_rate": 9.944739353007344e-05, | |
| "loss": 0.9787, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.18475750577367206, | |
| "grad_norm": 0.6223618984222412, | |
| "learning_rate": 9.931806517013612e-05, | |
| "loss": 1.0715, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.19399538106235567, | |
| "grad_norm": 0.5716590285301208, | |
| "learning_rate": 9.917525374361912e-05, | |
| "loss": 0.9894, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.20323325635103925, | |
| "grad_norm": 0.5965876579284668, | |
| "learning_rate": 9.901899829374047e-05, | |
| "loss": 1.0717, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.21247113163972287, | |
| "grad_norm": 0.730262041091919, | |
| "learning_rate": 9.884934153917997e-05, | |
| "loss": 1.1629, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.22170900692840648, | |
| "grad_norm": 0.654342532157898, | |
| "learning_rate": 9.86663298624003e-05, | |
| "loss": 0.8397, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.23094688221709006, | |
| "grad_norm": 0.6148257255554199, | |
| "learning_rate": 9.847001329696653e-05, | |
| "loss": 0.7981, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.24018475750577367, | |
| "grad_norm": 0.5430189967155457, | |
| "learning_rate": 9.826044551386744e-05, | |
| "loss": 0.5594, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.24942263279445728, | |
| "grad_norm": 0.6212301850318909, | |
| "learning_rate": 9.803768380684242e-05, | |
| "loss": 0.8103, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.2586605080831409, | |
| "grad_norm": 0.6506611108779907, | |
| "learning_rate": 9.780178907671789e-05, | |
| "loss": 1.2625, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.2678983833718245, | |
| "grad_norm": 0.5362969636917114, | |
| "learning_rate": 9.755282581475769e-05, | |
| "loss": 1.0143, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.27713625866050806, | |
| "grad_norm": 0.5695696473121643, | |
| "learning_rate": 9.729086208503174e-05, | |
| "loss": 1.0934, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.2863741339491917, | |
| "grad_norm": 0.5289963483810425, | |
| "learning_rate": 9.701596950580806e-05, | |
| "loss": 1.1791, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.2956120092378753, | |
| "grad_norm": 0.465656578540802, | |
| "learning_rate": 9.672822322997305e-05, | |
| "loss": 1.0622, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.30484988452655887, | |
| "grad_norm": 0.5989323854446411, | |
| "learning_rate": 9.642770192448536e-05, | |
| "loss": 1.0992, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.3140877598152425, | |
| "grad_norm": 0.6166355013847351, | |
| "learning_rate": 9.611448774886924e-05, | |
| "loss": 1.2012, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.3233256351039261, | |
| "grad_norm": 0.48977911472320557, | |
| "learning_rate": 9.578866633275288e-05, | |
| "loss": 1.1693, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.3325635103926097, | |
| "grad_norm": 0.5046831965446472, | |
| "learning_rate": 9.545032675245813e-05, | |
| "loss": 1.0459, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.3418013856812933, | |
| "grad_norm": 0.4951150119304657, | |
| "learning_rate": 9.509956150664796e-05, | |
| "loss": 1.185, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.3510392609699769, | |
| "grad_norm": 0.5021021366119385, | |
| "learning_rate": 9.473646649103818e-05, | |
| "loss": 1.1459, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.36027713625866054, | |
| "grad_norm": 0.5116178393363953, | |
| "learning_rate": 9.43611409721806e-05, | |
| "loss": 1.1502, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.3695150115473441, | |
| "grad_norm": 0.4844975173473358, | |
| "learning_rate": 9.397368756032445e-05, | |
| "loss": 1.0636, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.3787528868360277, | |
| "grad_norm": 0.5217158794403076, | |
| "learning_rate": 9.357421218136386e-05, | |
| "loss": 1.0657, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.38799076212471134, | |
| "grad_norm": 0.5075217485427856, | |
| "learning_rate": 9.316282404787871e-05, | |
| "loss": 1.0734, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.3972286374133949, | |
| "grad_norm": 0.4766087830066681, | |
| "learning_rate": 9.273963562927695e-05, | |
| "loss": 1.0645, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.4064665127020785, | |
| "grad_norm": 0.5414215326309204, | |
| "learning_rate": 9.230476262104677e-05, | |
| "loss": 1.035, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.41570438799076215, | |
| "grad_norm": 0.5103603005409241, | |
| "learning_rate": 9.185832391312644e-05, | |
| "loss": 1.1142, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.42494226327944573, | |
| "grad_norm": 0.5284842252731323, | |
| "learning_rate": 9.140044155740101e-05, | |
| "loss": 1.077, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.4341801385681293, | |
| "grad_norm": 0.5277894139289856, | |
| "learning_rate": 9.093124073433463e-05, | |
| "loss": 1.0427, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.44341801385681295, | |
| "grad_norm": 0.5197007060050964, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 0.9855, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.45265588914549654, | |
| "grad_norm": 0.5461387634277344, | |
| "learning_rate": 8.995939984474624e-05, | |
| "loss": 0.9706, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.4618937644341801, | |
| "grad_norm": 0.5533607006072998, | |
| "learning_rate": 8.945702546981969e-05, | |
| "loss": 0.8861, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.4618937644341801, | |
| "eval_loss": 0.9937018156051636, | |
| "eval_runtime": 14.2796, | |
| "eval_samples_per_second": 12.745, | |
| "eval_steps_per_second": 3.221, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.47113163972286376, | |
| "grad_norm": 0.574066698551178, | |
| "learning_rate": 8.894386393810563e-05, | |
| "loss": 0.8831, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.48036951501154734, | |
| "grad_norm": 0.5090445876121521, | |
| "learning_rate": 8.842005554284296e-05, | |
| "loss": 0.6299, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.4896073903002309, | |
| "grad_norm": 0.5428777933120728, | |
| "learning_rate": 8.788574348801675e-05, | |
| "loss": 0.6964, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.49884526558891457, | |
| "grad_norm": 0.5807305574417114, | |
| "learning_rate": 8.73410738492077e-05, | |
| "loss": 0.731, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.5080831408775982, | |
| "grad_norm": 0.5206661224365234, | |
| "learning_rate": 8.678619553365659e-05, | |
| "loss": 1.036, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.5173210161662818, | |
| "grad_norm": 0.49318259954452515, | |
| "learning_rate": 8.622126023955446e-05, | |
| "loss": 0.983, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.5265588914549654, | |
| "grad_norm": 0.4860965311527252, | |
| "learning_rate": 8.564642241456986e-05, | |
| "loss": 0.9702, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.535796766743649, | |
| "grad_norm": 0.48459872603416443, | |
| "learning_rate": 8.506183921362443e-05, | |
| "loss": 1.0301, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.5450346420323325, | |
| "grad_norm": 0.4511547088623047, | |
| "learning_rate": 8.44676704559283e-05, | |
| "loss": 1.0705, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.5542725173210161, | |
| "grad_norm": 0.44512757658958435, | |
| "learning_rate": 8.386407858128706e-05, | |
| "loss": 1.1311, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.5635103926096998, | |
| "grad_norm": 0.4721827805042267, | |
| "learning_rate": 8.32512286056924e-05, | |
| "loss": 1.1538, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.5727482678983834, | |
| "grad_norm": 0.5589929819107056, | |
| "learning_rate": 8.262928807620843e-05, | |
| "loss": 1.1642, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.581986143187067, | |
| "grad_norm": 0.44079118967056274, | |
| "learning_rate": 8.199842702516583e-05, | |
| "loss": 1.0793, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.5912240184757506, | |
| "grad_norm": 0.4991376996040344, | |
| "learning_rate": 8.135881792367686e-05, | |
| "loss": 1.1517, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.6004618937644342, | |
| "grad_norm": 0.4457406997680664, | |
| "learning_rate": 8.07106356344834e-05, | |
| "loss": 1.0946, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.6096997690531177, | |
| "grad_norm": 0.4820258915424347, | |
| "learning_rate": 8.005405736415126e-05, | |
| "loss": 1.0471, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.6189376443418014, | |
| "grad_norm": 0.4880450367927551, | |
| "learning_rate": 7.938926261462366e-05, | |
| "loss": 1.0518, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.628175519630485, | |
| "grad_norm": 0.5054741501808167, | |
| "learning_rate": 7.871643313414718e-05, | |
| "loss": 1.0773, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.6374133949191686, | |
| "grad_norm": 0.4769134819507599, | |
| "learning_rate": 7.803575286758364e-05, | |
| "loss": 1.0183, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.6466512702078522, | |
| "grad_norm": 0.5023130774497986, | |
| "learning_rate": 7.734740790612136e-05, | |
| "loss": 1.1295, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.6558891454965358, | |
| "grad_norm": 0.47621455788612366, | |
| "learning_rate": 7.66515864363997e-05, | |
| "loss": 1.0192, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.6651270207852193, | |
| "grad_norm": 0.5380384922027588, | |
| "learning_rate": 7.594847868906076e-05, | |
| "loss": 1.0307, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.674364896073903, | |
| "grad_norm": 0.5159346461296082, | |
| "learning_rate": 7.52382768867422e-05, | |
| "loss": 0.9428, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.6836027713625866, | |
| "grad_norm": 0.5815796852111816, | |
| "learning_rate": 7.452117519152542e-05, | |
| "loss": 1.0794, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.6928406466512702, | |
| "grad_norm": 0.5210710167884827, | |
| "learning_rate": 7.379736965185368e-05, | |
| "loss": 1.1288, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.7020785219399538, | |
| "grad_norm": 0.5079061985015869, | |
| "learning_rate": 7.30670581489344e-05, | |
| "loss": 0.9561, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.7113163972286374, | |
| "grad_norm": 0.528100311756134, | |
| "learning_rate": 7.233044034264034e-05, | |
| "loss": 1.0103, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.7205542725173211, | |
| "grad_norm": 0.50440514087677, | |
| "learning_rate": 7.158771761692464e-05, | |
| "loss": 0.8677, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.7297921478060047, | |
| "grad_norm": 0.5465642809867859, | |
| "learning_rate": 7.083909302476453e-05, | |
| "loss": 0.8766, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 0.7390300230946882, | |
| "grad_norm": 0.5434725880622864, | |
| "learning_rate": 7.008477123264848e-05, | |
| "loss": 0.6777, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.7482678983833718, | |
| "grad_norm": 0.605277419090271, | |
| "learning_rate": 6.932495846462261e-05, | |
| "loss": 0.6921, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.7575057736720554, | |
| "grad_norm": 0.49150773882865906, | |
| "learning_rate": 6.855986244591104e-05, | |
| "loss": 1.074, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.766743648960739, | |
| "grad_norm": 0.44630295038223267, | |
| "learning_rate": 6.778969234612584e-05, | |
| "loss": 0.9474, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 0.7759815242494227, | |
| "grad_norm": 0.48014646768569946, | |
| "learning_rate": 6.701465872208216e-05, | |
| "loss": 1.1471, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.7852193995381063, | |
| "grad_norm": 0.4384217858314514, | |
| "learning_rate": 6.623497346023418e-05, | |
| "loss": 1.039, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.7944572748267898, | |
| "grad_norm": 0.4348272383213043, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 1.0814, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.8036951501154734, | |
| "grad_norm": 0.4352071285247803, | |
| "learning_rate": 6.466250186922325e-05, | |
| "loss": 1.013, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.812933025404157, | |
| "grad_norm": 0.46225348114967346, | |
| "learning_rate": 6.387014543809223e-05, | |
| "loss": 1.0472, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.8221709006928406, | |
| "grad_norm": 0.5161978602409363, | |
| "learning_rate": 6.307399704769099e-05, | |
| "loss": 1.0412, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 0.8314087759815243, | |
| "grad_norm": 0.5392142534255981, | |
| "learning_rate": 6.227427435703997e-05, | |
| "loss": 1.0285, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.8406466512702079, | |
| "grad_norm": 0.4627595841884613, | |
| "learning_rate": 6.147119600233758e-05, | |
| "loss": 0.9377, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 0.8498845265588915, | |
| "grad_norm": 0.4607517123222351, | |
| "learning_rate": 6.066498153718735e-05, | |
| "loss": 0.9809, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.859122401847575, | |
| "grad_norm": 0.4755471348762512, | |
| "learning_rate": 5.985585137257401e-05, | |
| "loss": 1.0864, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.8683602771362586, | |
| "grad_norm": 0.46870455145835876, | |
| "learning_rate": 5.90440267166055e-05, | |
| "loss": 1.0855, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 0.8775981524249422, | |
| "grad_norm": 0.4941107928752899, | |
| "learning_rate": 5.8229729514036705e-05, | |
| "loss": 1.0547, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.8868360277136259, | |
| "grad_norm": 0.5224566459655762, | |
| "learning_rate": 5.74131823855921e-05, | |
| "loss": 1.0804, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.8960739030023095, | |
| "grad_norm": 0.48611992597579956, | |
| "learning_rate": 5.6594608567103456e-05, | |
| "loss": 1.0894, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 0.9053117782909931, | |
| "grad_norm": 0.4762772023677826, | |
| "learning_rate": 5.577423184847932e-05, | |
| "loss": 0.9408, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 0.9145496535796767, | |
| "grad_norm": 0.45591628551483154, | |
| "learning_rate": 5.495227651252315e-05, | |
| "loss": 0.9617, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.9237875288683602, | |
| "grad_norm": 0.4984215497970581, | |
| "learning_rate": 5.4128967273616625e-05, | |
| "loss": 1.0903, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.9237875288683602, | |
| "eval_loss": 0.980871319770813, | |
| "eval_runtime": 14.296, | |
| "eval_samples_per_second": 12.731, | |
| "eval_steps_per_second": 3.218, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.9330254041570438, | |
| "grad_norm": 0.4805242717266083, | |
| "learning_rate": 5.330452921628497e-05, | |
| "loss": 0.9952, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 0.9422632794457275, | |
| "grad_norm": 0.5048471093177795, | |
| "learning_rate": 5.247918773366112e-05, | |
| "loss": 1.0026, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 0.9515011547344111, | |
| "grad_norm": 0.47761252522468567, | |
| "learning_rate": 5.165316846586541e-05, | |
| "loss": 0.9011, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 0.9607390300230947, | |
| "grad_norm": 0.4814421832561493, | |
| "learning_rate": 5.0826697238317935e-05, | |
| "loss": 0.8254, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 0.9699769053117783, | |
| "grad_norm": 0.5181447863578796, | |
| "learning_rate": 5e-05, | |
| "loss": 0.904, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.9792147806004619, | |
| "grad_norm": 0.5766104459762573, | |
| "learning_rate": 4.917330276168208e-05, | |
| "loss": 0.9142, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 0.9884526558891455, | |
| "grad_norm": 0.5293551683425903, | |
| "learning_rate": 4.834683153413459e-05, | |
| "loss": 0.5918, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 0.9976905311778291, | |
| "grad_norm": 0.6035276651382446, | |
| "learning_rate": 4.7520812266338885e-05, | |
| "loss": 0.5776, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 1.0069284064665127, | |
| "grad_norm": 1.762345552444458, | |
| "learning_rate": 4.669547078371504e-05, | |
| "loss": 2.3342, | |
| "step": 109 | |
| }, | |
| { | |
| "epoch": 1.0161662817551964, | |
| "grad_norm": 0.4589715003967285, | |
| "learning_rate": 4.5871032726383386e-05, | |
| "loss": 0.8737, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 1.0254041570438799, | |
| "grad_norm": 0.4868597388267517, | |
| "learning_rate": 4.504772348747687e-05, | |
| "loss": 0.9334, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 1.0346420323325636, | |
| "grad_norm": 0.45352888107299805, | |
| "learning_rate": 4.4225768151520694e-05, | |
| "loss": 0.9114, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 1.043879907621247, | |
| "grad_norm": 0.42857691645622253, | |
| "learning_rate": 4.3405391432896555e-05, | |
| "loss": 0.9495, | |
| "step": 113 | |
| }, | |
| { | |
| "epoch": 1.0531177829099307, | |
| "grad_norm": 0.4715206027030945, | |
| "learning_rate": 4.2586817614407895e-05, | |
| "loss": 1.0239, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 1.0623556581986142, | |
| "grad_norm": 0.4415227174758911, | |
| "learning_rate": 4.17702704859633e-05, | |
| "loss": 0.9095, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 1.071593533487298, | |
| "grad_norm": 0.45675861835479736, | |
| "learning_rate": 4.095597328339452e-05, | |
| "loss": 0.9564, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 1.0808314087759816, | |
| "grad_norm": 0.48127785325050354, | |
| "learning_rate": 4.0144148627425993e-05, | |
| "loss": 1.0065, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 1.090069284064665, | |
| "grad_norm": 0.4654565751552582, | |
| "learning_rate": 3.933501846281267e-05, | |
| "loss": 0.8241, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 1.0993071593533488, | |
| "grad_norm": 0.4536269009113312, | |
| "learning_rate": 3.852880399766243e-05, | |
| "loss": 0.9397, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 1.1085450346420322, | |
| "grad_norm": 0.4648246765136719, | |
| "learning_rate": 3.772572564296005e-05, | |
| "loss": 0.8345, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 1.117782909930716, | |
| "grad_norm": 0.5024539828300476, | |
| "learning_rate": 3.6926002952309016e-05, | |
| "loss": 0.9244, | |
| "step": 121 | |
| }, | |
| { | |
| "epoch": 1.1270207852193996, | |
| "grad_norm": 0.5198694467544556, | |
| "learning_rate": 3.612985456190778e-05, | |
| "loss": 0.9949, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 1.136258660508083, | |
| "grad_norm": 0.4957815706729889, | |
| "learning_rate": 3.533749813077677e-05, | |
| "loss": 0.8453, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 1.1454965357967668, | |
| "grad_norm": 0.49513280391693115, | |
| "learning_rate": 3.4549150281252636e-05, | |
| "loss": 0.8812, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 1.1547344110854503, | |
| "grad_norm": 0.5386441349983215, | |
| "learning_rate": 3.3765026539765834e-05, | |
| "loss": 0.9466, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 1.163972286374134, | |
| "grad_norm": 0.4993761479854584, | |
| "learning_rate": 3.298534127791785e-05, | |
| "loss": 0.7875, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 1.1732101616628174, | |
| "grad_norm": 0.5003873705863953, | |
| "learning_rate": 3.221030765387417e-05, | |
| "loss": 0.7028, | |
| "step": 127 | |
| }, | |
| { | |
| "epoch": 1.1824480369515011, | |
| "grad_norm": 0.5584290027618408, | |
| "learning_rate": 3.144013755408895e-05, | |
| "loss": 0.8541, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 1.1916859122401848, | |
| "grad_norm": 0.5487212538719177, | |
| "learning_rate": 3.0675041535377405e-05, | |
| "loss": 0.7948, | |
| "step": 129 | |
| }, | |
| { | |
| "epoch": 1.2009237875288683, | |
| "grad_norm": 0.5893298983573914, | |
| "learning_rate": 2.991522876735154e-05, | |
| "loss": 0.8519, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 1.210161662817552, | |
| "grad_norm": 0.543730616569519, | |
| "learning_rate": 2.916090697523549e-05, | |
| "loss": 0.7096, | |
| "step": 131 | |
| }, | |
| { | |
| "epoch": 1.2193995381062355, | |
| "grad_norm": 0.5713210105895996, | |
| "learning_rate": 2.8412282383075363e-05, | |
| "loss": 0.6255, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 1.2286374133949192, | |
| "grad_norm": 0.5193185210227966, | |
| "learning_rate": 2.766955965735968e-05, | |
| "loss": 0.4859, | |
| "step": 133 | |
| }, | |
| { | |
| "epoch": 1.2378752886836029, | |
| "grad_norm": 0.5890741944313049, | |
| "learning_rate": 2.693294185106562e-05, | |
| "loss": 0.5351, | |
| "step": 134 | |
| }, | |
| { | |
| "epoch": 1.2471131639722863, | |
| "grad_norm": 0.4918690025806427, | |
| "learning_rate": 2.6202630348146324e-05, | |
| "loss": 0.4152, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 1.25635103926097, | |
| "grad_norm": 0.5401874780654907, | |
| "learning_rate": 2.547882480847461e-05, | |
| "loss": 0.759, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 1.2655889145496535, | |
| "grad_norm": 0.5788339972496033, | |
| "learning_rate": 2.476172311325783e-05, | |
| "loss": 0.9309, | |
| "step": 137 | |
| }, | |
| { | |
| "epoch": 1.2748267898383372, | |
| "grad_norm": 0.5869746208190918, | |
| "learning_rate": 2.405152131093926e-05, | |
| "loss": 0.9346, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 1.2840646651270209, | |
| "grad_norm": 0.5651271343231201, | |
| "learning_rate": 2.3348413563600325e-05, | |
| "loss": 0.961, | |
| "step": 139 | |
| }, | |
| { | |
| "epoch": 1.2933025404157044, | |
| "grad_norm": 0.5636593103408813, | |
| "learning_rate": 2.2652592093878666e-05, | |
| "loss": 0.9401, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 1.302540415704388, | |
| "grad_norm": 0.5589775443077087, | |
| "learning_rate": 2.196424713241637e-05, | |
| "loss": 0.9476, | |
| "step": 141 | |
| }, | |
| { | |
| "epoch": 1.3117782909930715, | |
| "grad_norm": 0.5839599370956421, | |
| "learning_rate": 2.128356686585282e-05, | |
| "loss": 1.1028, | |
| "step": 142 | |
| }, | |
| { | |
| "epoch": 1.3210161662817552, | |
| "grad_norm": 0.5257271528244019, | |
| "learning_rate": 2.061073738537635e-05, | |
| "loss": 0.8983, | |
| "step": 143 | |
| }, | |
| { | |
| "epoch": 1.3302540415704387, | |
| "grad_norm": 0.5780817270278931, | |
| "learning_rate": 1.9945942635848748e-05, | |
| "loss": 0.9686, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 1.3394919168591224, | |
| "grad_norm": 0.5114372968673706, | |
| "learning_rate": 1.928936436551661e-05, | |
| "loss": 0.8995, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 1.348729792147806, | |
| "grad_norm": 0.5757182240486145, | |
| "learning_rate": 1.8641182076323148e-05, | |
| "loss": 0.9519, | |
| "step": 146 | |
| }, | |
| { | |
| "epoch": 1.3579676674364896, | |
| "grad_norm": 0.5221604704856873, | |
| "learning_rate": 1.800157297483417e-05, | |
| "loss": 0.8794, | |
| "step": 147 | |
| }, | |
| { | |
| "epoch": 1.3672055427251733, | |
| "grad_norm": 0.5381840467453003, | |
| "learning_rate": 1.7370711923791567e-05, | |
| "loss": 0.9415, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 1.376443418013857, | |
| "grad_norm": 0.5394565463066101, | |
| "learning_rate": 1.6748771394307585e-05, | |
| "loss": 0.8801, | |
| "step": 149 | |
| }, | |
| { | |
| "epoch": 1.3856812933025404, | |
| "grad_norm": 0.5812250971794128, | |
| "learning_rate": 1.6135921418712956e-05, | |
| "loss": 0.8667, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 1.3856812933025404, | |
| "eval_loss": 0.9954066276550293, | |
| "eval_runtime": 14.0288, | |
| "eval_samples_per_second": 12.973, | |
| "eval_steps_per_second": 3.279, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 1.394919168591224, | |
| "grad_norm": 0.5564768314361572, | |
| "learning_rate": 1.553232954407171e-05, | |
| "loss": 0.8799, | |
| "step": 151 | |
| }, | |
| { | |
| "epoch": 1.4041570438799076, | |
| "grad_norm": 0.5519217252731323, | |
| "learning_rate": 1.4938160786375572e-05, | |
| "loss": 0.848, | |
| "step": 152 | |
| }, | |
| { | |
| "epoch": 1.4133949191685913, | |
| "grad_norm": 0.5858139395713806, | |
| "learning_rate": 1.435357758543015e-05, | |
| "loss": 0.8235, | |
| "step": 153 | |
| }, | |
| { | |
| "epoch": 1.4226327944572748, | |
| "grad_norm": 0.5981034636497498, | |
| "learning_rate": 1.3778739760445552e-05, | |
| "loss": 0.8567, | |
| "step": 154 | |
| }, | |
| { | |
| "epoch": 1.4318706697459584, | |
| "grad_norm": 0.5710499882698059, | |
| "learning_rate": 1.3213804466343421e-05, | |
| "loss": 0.8539, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 1.4411085450346421, | |
| "grad_norm": 0.6137874722480774, | |
| "learning_rate": 1.2658926150792322e-05, | |
| "loss": 0.8585, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 1.4503464203233256, | |
| "grad_norm": 0.5579916834831238, | |
| "learning_rate": 1.2114256511983274e-05, | |
| "loss": 0.8183, | |
| "step": 157 | |
| }, | |
| { | |
| "epoch": 1.4595842956120093, | |
| "grad_norm": 0.6351567506790161, | |
| "learning_rate": 1.157994445715706e-05, | |
| "loss": 0.7588, | |
| "step": 158 | |
| }, | |
| { | |
| "epoch": 1.4688221709006928, | |
| "grad_norm": 0.6081944704055786, | |
| "learning_rate": 1.1056136061894384e-05, | |
| "loss": 0.7034, | |
| "step": 159 | |
| }, | |
| { | |
| "epoch": 1.4780600461893765, | |
| "grad_norm": 0.6982226967811584, | |
| "learning_rate": 1.0542974530180327e-05, | |
| "loss": 0.7258, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 1.48729792147806, | |
| "grad_norm": 0.5053288340568542, | |
| "learning_rate": 1.0040600155253765e-05, | |
| "loss": 0.3214, | |
| "step": 161 | |
| }, | |
| { | |
| "epoch": 1.4965357967667436, | |
| "grad_norm": 0.5263621211051941, | |
| "learning_rate": 9.549150281252633e-06, | |
| "loss": 0.3937, | |
| "step": 162 | |
| }, | |
| { | |
| "epoch": 1.5057736720554273, | |
| "grad_norm": 0.6361817121505737, | |
| "learning_rate": 9.068759265665384e-06, | |
| "loss": 0.9496, | |
| "step": 163 | |
| }, | |
| { | |
| "epoch": 1.5150115473441108, | |
| "grad_norm": 0.5198244452476501, | |
| "learning_rate": 8.599558442598998e-06, | |
| "loss": 0.7847, | |
| "step": 164 | |
| }, | |
| { | |
| "epoch": 1.5242494226327945, | |
| "grad_norm": 0.5897130966186523, | |
| "learning_rate": 8.141676086873572e-06, | |
| "loss": 1.0171, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 1.5334872979214782, | |
| "grad_norm": 0.5903618931770325, | |
| "learning_rate": 7.695237378953223e-06, | |
| "loss": 0.8996, | |
| "step": 166 | |
| }, | |
| { | |
| "epoch": 1.5427251732101617, | |
| "grad_norm": 0.5763500332832336, | |
| "learning_rate": 7.260364370723044e-06, | |
| "loss": 0.8975, | |
| "step": 167 | |
| }, | |
| { | |
| "epoch": 1.5519630484988451, | |
| "grad_norm": 0.6155166625976562, | |
| "learning_rate": 6.837175952121306e-06, | |
| "loss": 0.9855, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 1.5612009237875288, | |
| "grad_norm": 0.5877078175544739, | |
| "learning_rate": 6.425787818636131e-06, | |
| "loss": 0.8937, | |
| "step": 169 | |
| }, | |
| { | |
| "epoch": 1.5704387990762125, | |
| "grad_norm": 0.6422519087791443, | |
| "learning_rate": 6.026312439675552e-06, | |
| "loss": 0.9982, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 1.579676674364896, | |
| "grad_norm": 0.586499035358429, | |
| "learning_rate": 5.6388590278194096e-06, | |
| "loss": 0.8593, | |
| "step": 171 | |
| }, | |
| { | |
| "epoch": 1.5889145496535797, | |
| "grad_norm": 0.606075644493103, | |
| "learning_rate": 5.263533508961827e-06, | |
| "loss": 0.9633, | |
| "step": 172 | |
| }, | |
| { | |
| "epoch": 1.5981524249422634, | |
| "grad_norm": 0.5850546360015869, | |
| "learning_rate": 4.900438493352055e-06, | |
| "loss": 0.9115, | |
| "step": 173 | |
| }, | |
| { | |
| "epoch": 1.6073903002309469, | |
| "grad_norm": 0.5581844449043274, | |
| "learning_rate": 4.549673247541875e-06, | |
| "loss": 0.86, | |
| "step": 174 | |
| }, | |
| { | |
| "epoch": 1.6166281755196303, | |
| "grad_norm": 0.6025592684745789, | |
| "learning_rate": 4.2113336672471245e-06, | |
| "loss": 0.93, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 1.625866050808314, | |
| "grad_norm": 0.592785656452179, | |
| "learning_rate": 3.885512251130763e-06, | |
| "loss": 0.9364, | |
| "step": 176 | |
| }, | |
| { | |
| "epoch": 1.6351039260969977, | |
| "grad_norm": 0.5996099710464478, | |
| "learning_rate": 3.5722980755146517e-06, | |
| "loss": 0.9017, | |
| "step": 177 | |
| }, | |
| { | |
| "epoch": 1.6443418013856812, | |
| "grad_norm": 0.559090256690979, | |
| "learning_rate": 3.271776770026963e-06, | |
| "loss": 0.7272, | |
| "step": 178 | |
| }, | |
| { | |
| "epoch": 1.653579676674365, | |
| "grad_norm": 0.5872829556465149, | |
| "learning_rate": 2.9840304941919415e-06, | |
| "loss": 0.8419, | |
| "step": 179 | |
| }, | |
| { | |
| "epoch": 1.6628175519630486, | |
| "grad_norm": 0.6141781806945801, | |
| "learning_rate": 2.7091379149682685e-06, | |
| "loss": 0.9121, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 1.672055427251732, | |
| "grad_norm": 0.595081090927124, | |
| "learning_rate": 2.4471741852423237e-06, | |
| "loss": 0.7961, | |
| "step": 181 | |
| }, | |
| { | |
| "epoch": 1.6812933025404158, | |
| "grad_norm": 0.5730736255645752, | |
| "learning_rate": 2.1982109232821178e-06, | |
| "loss": 0.7908, | |
| "step": 182 | |
| }, | |
| { | |
| "epoch": 1.6905311778290995, | |
| "grad_norm": 0.5923240780830383, | |
| "learning_rate": 1.962316193157593e-06, | |
| "loss": 0.7856, | |
| "step": 183 | |
| }, | |
| { | |
| "epoch": 1.699769053117783, | |
| "grad_norm": 0.6565060615539551, | |
| "learning_rate": 1.7395544861325718e-06, | |
| "loss": 0.8155, | |
| "step": 184 | |
| }, | |
| { | |
| "epoch": 1.7090069284064664, | |
| "grad_norm": 0.6182951331138611, | |
| "learning_rate": 1.5299867030334814e-06, | |
| "loss": 0.8105, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 1.71824480369515, | |
| "grad_norm": 0.6440560817718506, | |
| "learning_rate": 1.333670137599713e-06, | |
| "loss": 0.77, | |
| "step": 186 | |
| }, | |
| { | |
| "epoch": 1.7274826789838338, | |
| "grad_norm": 0.6410927176475525, | |
| "learning_rate": 1.1506584608200367e-06, | |
| "loss": 0.675, | |
| "step": 187 | |
| }, | |
| { | |
| "epoch": 1.7367205542725173, | |
| "grad_norm": 0.5390146374702454, | |
| "learning_rate": 9.810017062595322e-07, | |
| "loss": 0.4107, | |
| "step": 188 | |
| }, | |
| { | |
| "epoch": 1.745958429561201, | |
| "grad_norm": 0.6029218435287476, | |
| "learning_rate": 8.247462563808817e-07, | |
| "loss": 0.4305, | |
| "step": 189 | |
| }, | |
| { | |
| "epoch": 1.7551963048498846, | |
| "grad_norm": 0.5874188542366028, | |
| "learning_rate": 6.819348298638839e-07, | |
| "loss": 0.8913, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 1.7644341801385681, | |
| "grad_norm": 0.5208359360694885, | |
| "learning_rate": 5.526064699265753e-07, | |
| "loss": 0.8099, | |
| "step": 191 | |
| }, | |
| { | |
| "epoch": 1.7736720554272516, | |
| "grad_norm": 0.5271393060684204, | |
| "learning_rate": 4.367965336512403e-07, | |
| "loss": 0.8423, | |
| "step": 192 | |
| }, | |
| { | |
| "epoch": 1.7829099307159353, | |
| "grad_norm": 0.5395892262458801, | |
| "learning_rate": 3.3453668231809286e-07, | |
| "loss": 0.934, | |
| "step": 193 | |
| }, | |
| { | |
| "epoch": 1.792147806004619, | |
| "grad_norm": 0.5424866676330566, | |
| "learning_rate": 2.458548727494292e-07, | |
| "loss": 0.8678, | |
| "step": 194 | |
| }, | |
| { | |
| "epoch": 1.8013856812933025, | |
| "grad_norm": 0.5203055739402771, | |
| "learning_rate": 1.7077534966650766e-07, | |
| "loss": 0.887, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 1.8106235565819861, | |
| "grad_norm": 0.5708828568458557, | |
| "learning_rate": 1.0931863906127327e-07, | |
| "loss": 1.0469, | |
| "step": 196 | |
| }, | |
| { | |
| "epoch": 1.8198614318706698, | |
| "grad_norm": 0.5658224821090698, | |
| "learning_rate": 6.150154258476315e-08, | |
| "loss": 0.899, | |
| "step": 197 | |
| }, | |
| { | |
| "epoch": 1.8290993071593533, | |
| "grad_norm": 0.5406971573829651, | |
| "learning_rate": 2.7337132953697554e-08, | |
| "loss": 0.8121, | |
| "step": 198 | |
| }, | |
| { | |
| "epoch": 1.8383371824480368, | |
| "grad_norm": 0.5786592960357666, | |
| "learning_rate": 6.834750376549792e-09, | |
| "loss": 0.9724, | |
| "step": 199 | |
| }, | |
| { | |
| "epoch": 1.8475750577367207, | |
| "grad_norm": 0.566459059715271, | |
| "learning_rate": 0.0, | |
| "loss": 0.9211, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.8475750577367207, | |
| "eval_loss": 0.9947918653488159, | |
| "eval_runtime": 14.302, | |
| "eval_samples_per_second": 12.725, | |
| "eval_steps_per_second": 3.216, | |
| "step": 200 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 200, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "save_steps": 50, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 5, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 2 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2.937088815661056e+17, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |