Instructions to use arelius/MedicalLM with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use arelius/MedicalLM with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("microsoft/BioGPT") model = PeftModel.from_pretrained(base_model, "arelius/MedicalLM") - Notebooks
- Google Colab
- Kaggle
| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.988236782190741, | |
| "eval_steps": 500, | |
| "global_step": 94500, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 1.9894594822497684e-05, | |
| "loss": 3.6148, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 1.9789189644995362e-05, | |
| "loss": 3.3107, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 1.9683784467493044e-05, | |
| "loss": 3.2487, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 1.9578379289990726e-05, | |
| "loss": 3.1954, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 1.947297411248841e-05, | |
| "loss": 3.1585, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 1.9367568934986087e-05, | |
| "loss": 3.1312, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 1.926216375748377e-05, | |
| "loss": 3.0709, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 1.9156758579981448e-05, | |
| "loss": 3.0622, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 1.905135340247913e-05, | |
| "loss": 3.0556, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 1.8945948224976815e-05, | |
| "loss": 3.002, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 1.8840543047474494e-05, | |
| "loss": 3.0279, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 1.8735137869972176e-05, | |
| "loss": 2.9804, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 1.8629732692469854e-05, | |
| "loss": 2.988, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 1.8524327514967536e-05, | |
| "loss": 2.9664, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 1.841892233746522e-05, | |
| "loss": 2.9649, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 1.83135171599629e-05, | |
| "loss": 2.9827, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 1.820811198246058e-05, | |
| "loss": 2.9541, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 1.810270680495826e-05, | |
| "loss": 2.955, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 1.7997301627455943e-05, | |
| "loss": 2.9489, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 1.7891896449953622e-05, | |
| "loss": 2.9415, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 1.7786491272451304e-05, | |
| "loss": 2.9453, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 1.7681086094948986e-05, | |
| "loss": 2.9273, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 1.7575680917446668e-05, | |
| "loss": 2.935, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 1.7470275739944346e-05, | |
| "loss": 2.938, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 1.736487056244203e-05, | |
| "loss": 2.9441, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 1.7259465384939707e-05, | |
| "loss": 2.9091, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 1.715406020743739e-05, | |
| "loss": 2.9037, | |
| "step": 13500 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 1.704865502993507e-05, | |
| "loss": 2.9112, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 1.6943249852432753e-05, | |
| "loss": 2.88, | |
| "step": 14500 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 1.6837844674930435e-05, | |
| "loss": 2.9045, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 1.6732439497428114e-05, | |
| "loss": 2.9221, | |
| "step": 15500 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 1.6627034319925796e-05, | |
| "loss": 2.9079, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 1.6521629142423478e-05, | |
| "loss": 2.8972, | |
| "step": 16500 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 1.641622396492116e-05, | |
| "loss": 2.8958, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 1.631081878741884e-05, | |
| "loss": 2.9097, | |
| "step": 17500 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 1.620541360991652e-05, | |
| "loss": 2.9103, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 1.6100008432414203e-05, | |
| "loss": 2.9001, | |
| "step": 18500 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 1.599460325491188e-05, | |
| "loss": 2.8897, | |
| "step": 19000 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 1.5889198077409563e-05, | |
| "loss": 2.9011, | |
| "step": 19500 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 1.5783792899907245e-05, | |
| "loss": 2.8966, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 1.5678387722404927e-05, | |
| "loss": 2.8786, | |
| "step": 20500 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 1.5572982544902606e-05, | |
| "loss": 2.8719, | |
| "step": 21000 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 1.5467577367400288e-05, | |
| "loss": 2.8824, | |
| "step": 21500 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 1.5362172189897967e-05, | |
| "loss": 2.8859, | |
| "step": 22000 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 1.525676701239565e-05, | |
| "loss": 2.8539, | |
| "step": 22500 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 1.5151361834893332e-05, | |
| "loss": 2.8895, | |
| "step": 23000 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 1.5045956657391013e-05, | |
| "loss": 2.869, | |
| "step": 23500 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 1.4940551479888695e-05, | |
| "loss": 2.8888, | |
| "step": 24000 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 1.4835146302386373e-05, | |
| "loss": 2.8637, | |
| "step": 24500 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 1.4729741124884055e-05, | |
| "loss": 2.8905, | |
| "step": 25000 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 1.4624335947381736e-05, | |
| "loss": 2.8916, | |
| "step": 25500 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 1.4518930769879418e-05, | |
| "loss": 2.8801, | |
| "step": 26000 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 1.4413525592377098e-05, | |
| "loss": 2.8854, | |
| "step": 26500 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 1.430812041487478e-05, | |
| "loss": 2.8838, | |
| "step": 27000 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 1.4202715237372462e-05, | |
| "loss": 2.8701, | |
| "step": 27500 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 1.4097310059870142e-05, | |
| "loss": 2.8749, | |
| "step": 28000 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 1.3991904882367824e-05, | |
| "loss": 2.8488, | |
| "step": 28500 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 1.3886499704865503e-05, | |
| "loss": 2.8685, | |
| "step": 29000 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 1.3781094527363185e-05, | |
| "loss": 2.8526, | |
| "step": 29500 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 1.3675689349860865e-05, | |
| "loss": 2.8521, | |
| "step": 30000 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 1.3570284172358547e-05, | |
| "loss": 2.8803, | |
| "step": 30500 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 1.3464878994856228e-05, | |
| "loss": 2.8803, | |
| "step": 31000 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 1.335947381735391e-05, | |
| "loss": 2.8807, | |
| "step": 31500 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 2.767564058303833, | |
| "eval_runtime": 6452.3126, | |
| "eval_samples_per_second": 39.209, | |
| "eval_steps_per_second": 4.901, | |
| "step": 31624 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "learning_rate": 1.3254068639851592e-05, | |
| "loss": 2.8679, | |
| "step": 32000 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "learning_rate": 1.3148663462349272e-05, | |
| "loss": 2.874, | |
| "step": 32500 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "learning_rate": 1.3043258284846954e-05, | |
| "loss": 2.8517, | |
| "step": 33000 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "learning_rate": 1.2937853107344633e-05, | |
| "loss": 2.8499, | |
| "step": 33500 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "learning_rate": 1.2832447929842315e-05, | |
| "loss": 2.8693, | |
| "step": 34000 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "learning_rate": 1.2727042752339995e-05, | |
| "loss": 2.8738, | |
| "step": 34500 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "learning_rate": 1.2621637574837677e-05, | |
| "loss": 2.8282, | |
| "step": 35000 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "learning_rate": 1.2516232397335358e-05, | |
| "loss": 2.8402, | |
| "step": 35500 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "learning_rate": 1.241082721983304e-05, | |
| "loss": 2.8686, | |
| "step": 36000 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "learning_rate": 1.2305422042330722e-05, | |
| "loss": 2.8629, | |
| "step": 36500 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "learning_rate": 1.2200016864828402e-05, | |
| "loss": 2.8643, | |
| "step": 37000 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "learning_rate": 1.2094611687326084e-05, | |
| "loss": 2.8254, | |
| "step": 37500 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "learning_rate": 1.1989206509823763e-05, | |
| "loss": 2.8569, | |
| "step": 38000 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "learning_rate": 1.1883801332321445e-05, | |
| "loss": 2.8581, | |
| "step": 38500 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "learning_rate": 1.1778396154819125e-05, | |
| "loss": 2.8454, | |
| "step": 39000 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "learning_rate": 1.1672990977316807e-05, | |
| "loss": 2.8462, | |
| "step": 39500 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "learning_rate": 1.1567585799814487e-05, | |
| "loss": 2.865, | |
| "step": 40000 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "learning_rate": 1.146218062231217e-05, | |
| "loss": 2.8448, | |
| "step": 40500 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "learning_rate": 1.1356775444809851e-05, | |
| "loss": 2.8366, | |
| "step": 41000 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "learning_rate": 1.1251370267307532e-05, | |
| "loss": 2.8472, | |
| "step": 41500 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "learning_rate": 1.1145965089805214e-05, | |
| "loss": 2.8406, | |
| "step": 42000 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "learning_rate": 1.1040559912302892e-05, | |
| "loss": 2.8612, | |
| "step": 42500 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "learning_rate": 1.0935154734800574e-05, | |
| "loss": 2.8621, | |
| "step": 43000 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "learning_rate": 1.0829749557298255e-05, | |
| "loss": 2.8466, | |
| "step": 43500 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "learning_rate": 1.0724344379795937e-05, | |
| "loss": 2.8412, | |
| "step": 44000 | |
| }, | |
| { | |
| "epoch": 1.41, | |
| "learning_rate": 1.0618939202293617e-05, | |
| "loss": 2.8483, | |
| "step": 44500 | |
| }, | |
| { | |
| "epoch": 1.42, | |
| "learning_rate": 1.0513534024791299e-05, | |
| "loss": 2.8502, | |
| "step": 45000 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "learning_rate": 1.0408128847288981e-05, | |
| "loss": 2.8451, | |
| "step": 45500 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "learning_rate": 1.0302723669786661e-05, | |
| "loss": 2.8406, | |
| "step": 46000 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "learning_rate": 1.0197318492284343e-05, | |
| "loss": 2.8499, | |
| "step": 46500 | |
| }, | |
| { | |
| "epoch": 1.49, | |
| "learning_rate": 1.0091913314782022e-05, | |
| "loss": 2.8533, | |
| "step": 47000 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "learning_rate": 9.986508137279704e-06, | |
| "loss": 2.8233, | |
| "step": 47500 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "learning_rate": 9.881102959777386e-06, | |
| "loss": 2.8373, | |
| "step": 48000 | |
| }, | |
| { | |
| "epoch": 1.53, | |
| "learning_rate": 9.775697782275066e-06, | |
| "loss": 2.8606, | |
| "step": 48500 | |
| }, | |
| { | |
| "epoch": 1.55, | |
| "learning_rate": 9.670292604772747e-06, | |
| "loss": 2.8385, | |
| "step": 49000 | |
| }, | |
| { | |
| "epoch": 1.57, | |
| "learning_rate": 9.564887427270429e-06, | |
| "loss": 2.8455, | |
| "step": 49500 | |
| }, | |
| { | |
| "epoch": 1.58, | |
| "learning_rate": 9.459482249768109e-06, | |
| "loss": 2.8701, | |
| "step": 50000 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 9.354077072265791e-06, | |
| "loss": 2.8277, | |
| "step": 50500 | |
| }, | |
| { | |
| "epoch": 1.61, | |
| "learning_rate": 9.248671894763471e-06, | |
| "loss": 2.8681, | |
| "step": 51000 | |
| }, | |
| { | |
| "epoch": 1.63, | |
| "learning_rate": 9.143266717261152e-06, | |
| "loss": 2.8445, | |
| "step": 51500 | |
| }, | |
| { | |
| "epoch": 1.64, | |
| "learning_rate": 9.037861539758834e-06, | |
| "loss": 2.8545, | |
| "step": 52000 | |
| }, | |
| { | |
| "epoch": 1.66, | |
| "learning_rate": 8.932456362256516e-06, | |
| "loss": 2.8397, | |
| "step": 52500 | |
| }, | |
| { | |
| "epoch": 1.68, | |
| "learning_rate": 8.827051184754196e-06, | |
| "loss": 2.8442, | |
| "step": 53000 | |
| }, | |
| { | |
| "epoch": 1.69, | |
| "learning_rate": 8.721646007251876e-06, | |
| "loss": 2.8288, | |
| "step": 53500 | |
| }, | |
| { | |
| "epoch": 1.71, | |
| "learning_rate": 8.616240829749558e-06, | |
| "loss": 2.8278, | |
| "step": 54000 | |
| }, | |
| { | |
| "epoch": 1.72, | |
| "learning_rate": 8.510835652247239e-06, | |
| "loss": 2.835, | |
| "step": 54500 | |
| }, | |
| { | |
| "epoch": 1.74, | |
| "learning_rate": 8.40543047474492e-06, | |
| "loss": 2.8464, | |
| "step": 55000 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "learning_rate": 8.300025297242601e-06, | |
| "loss": 2.8251, | |
| "step": 55500 | |
| }, | |
| { | |
| "epoch": 1.77, | |
| "learning_rate": 8.194620119740281e-06, | |
| "loss": 2.8414, | |
| "step": 56000 | |
| }, | |
| { | |
| "epoch": 1.79, | |
| "learning_rate": 8.089214942237964e-06, | |
| "loss": 2.8335, | |
| "step": 56500 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "learning_rate": 7.983809764735646e-06, | |
| "loss": 2.8405, | |
| "step": 57000 | |
| }, | |
| { | |
| "epoch": 1.82, | |
| "learning_rate": 7.878404587233326e-06, | |
| "loss": 2.835, | |
| "step": 57500 | |
| }, | |
| { | |
| "epoch": 1.83, | |
| "learning_rate": 7.772999409731006e-06, | |
| "loss": 2.8239, | |
| "step": 58000 | |
| }, | |
| { | |
| "epoch": 1.85, | |
| "learning_rate": 7.667594232228688e-06, | |
| "loss": 2.8322, | |
| "step": 58500 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "learning_rate": 7.5621890547263685e-06, | |
| "loss": 2.8366, | |
| "step": 59000 | |
| }, | |
| { | |
| "epoch": 1.88, | |
| "learning_rate": 7.45678387722405e-06, | |
| "loss": 2.8391, | |
| "step": 59500 | |
| }, | |
| { | |
| "epoch": 1.9, | |
| "learning_rate": 7.351378699721731e-06, | |
| "loss": 2.8396, | |
| "step": 60000 | |
| }, | |
| { | |
| "epoch": 1.91, | |
| "learning_rate": 7.245973522219411e-06, | |
| "loss": 2.824, | |
| "step": 60500 | |
| }, | |
| { | |
| "epoch": 1.93, | |
| "learning_rate": 7.140568344717092e-06, | |
| "loss": 2.8282, | |
| "step": 61000 | |
| }, | |
| { | |
| "epoch": 1.94, | |
| "learning_rate": 7.035163167214774e-06, | |
| "loss": 2.8341, | |
| "step": 61500 | |
| }, | |
| { | |
| "epoch": 1.96, | |
| "learning_rate": 6.929757989712456e-06, | |
| "loss": 2.8247, | |
| "step": 62000 | |
| }, | |
| { | |
| "epoch": 1.98, | |
| "learning_rate": 6.824352812210137e-06, | |
| "loss": 2.837, | |
| "step": 62500 | |
| }, | |
| { | |
| "epoch": 1.99, | |
| "learning_rate": 6.718947634707817e-06, | |
| "loss": 2.8199, | |
| "step": 63000 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 2.7402868270874023, | |
| "eval_runtime": 6430.6551, | |
| "eval_samples_per_second": 39.341, | |
| "eval_steps_per_second": 4.918, | |
| "step": 63248 | |
| }, | |
| { | |
| "epoch": 2.01, | |
| "learning_rate": 6.613542457205498e-06, | |
| "loss": 2.8177, | |
| "step": 63500 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "learning_rate": 6.5081372797031795e-06, | |
| "loss": 2.8361, | |
| "step": 64000 | |
| }, | |
| { | |
| "epoch": 2.04, | |
| "learning_rate": 6.402732102200861e-06, | |
| "loss": 2.8109, | |
| "step": 64500 | |
| }, | |
| { | |
| "epoch": 2.06, | |
| "learning_rate": 6.297326924698541e-06, | |
| "loss": 2.8399, | |
| "step": 65000 | |
| }, | |
| { | |
| "epoch": 2.07, | |
| "learning_rate": 6.191921747196222e-06, | |
| "loss": 2.8311, | |
| "step": 65500 | |
| }, | |
| { | |
| "epoch": 2.09, | |
| "learning_rate": 6.086516569693904e-06, | |
| "loss": 2.8227, | |
| "step": 66000 | |
| }, | |
| { | |
| "epoch": 2.1, | |
| "learning_rate": 5.981111392191585e-06, | |
| "loss": 2.8347, | |
| "step": 66500 | |
| }, | |
| { | |
| "epoch": 2.12, | |
| "learning_rate": 5.8757062146892665e-06, | |
| "loss": 2.8259, | |
| "step": 67000 | |
| }, | |
| { | |
| "epoch": 2.13, | |
| "learning_rate": 5.770301037186947e-06, | |
| "loss": 2.8554, | |
| "step": 67500 | |
| }, | |
| { | |
| "epoch": 2.15, | |
| "learning_rate": 5.664895859684628e-06, | |
| "loss": 2.8385, | |
| "step": 68000 | |
| }, | |
| { | |
| "epoch": 2.17, | |
| "learning_rate": 5.559490682182309e-06, | |
| "loss": 2.8042, | |
| "step": 68500 | |
| }, | |
| { | |
| "epoch": 2.18, | |
| "learning_rate": 5.45408550467999e-06, | |
| "loss": 2.8222, | |
| "step": 69000 | |
| }, | |
| { | |
| "epoch": 2.2, | |
| "learning_rate": 5.348680327177671e-06, | |
| "loss": 2.8209, | |
| "step": 69500 | |
| }, | |
| { | |
| "epoch": 2.21, | |
| "learning_rate": 5.243275149675352e-06, | |
| "loss": 2.836, | |
| "step": 70000 | |
| }, | |
| { | |
| "epoch": 2.23, | |
| "learning_rate": 5.137869972173034e-06, | |
| "loss": 2.8291, | |
| "step": 70500 | |
| }, | |
| { | |
| "epoch": 2.25, | |
| "learning_rate": 5.032464794670715e-06, | |
| "loss": 2.8257, | |
| "step": 71000 | |
| }, | |
| { | |
| "epoch": 2.26, | |
| "learning_rate": 4.927059617168396e-06, | |
| "loss": 2.8353, | |
| "step": 71500 | |
| }, | |
| { | |
| "epoch": 2.28, | |
| "learning_rate": 4.8216544396660766e-06, | |
| "loss": 2.8184, | |
| "step": 72000 | |
| }, | |
| { | |
| "epoch": 2.29, | |
| "learning_rate": 4.716249262163758e-06, | |
| "loss": 2.8308, | |
| "step": 72500 | |
| }, | |
| { | |
| "epoch": 2.31, | |
| "learning_rate": 4.610844084661439e-06, | |
| "loss": 2.8321, | |
| "step": 73000 | |
| }, | |
| { | |
| "epoch": 2.32, | |
| "learning_rate": 4.50543890715912e-06, | |
| "loss": 2.8366, | |
| "step": 73500 | |
| }, | |
| { | |
| "epoch": 2.34, | |
| "learning_rate": 4.400033729656801e-06, | |
| "loss": 2.8133, | |
| "step": 74000 | |
| }, | |
| { | |
| "epoch": 2.36, | |
| "learning_rate": 4.2946285521544825e-06, | |
| "loss": 2.8063, | |
| "step": 74500 | |
| }, | |
| { | |
| "epoch": 2.37, | |
| "learning_rate": 4.189223374652164e-06, | |
| "loss": 2.8334, | |
| "step": 75000 | |
| }, | |
| { | |
| "epoch": 2.39, | |
| "learning_rate": 4.083818197149844e-06, | |
| "loss": 2.8103, | |
| "step": 75500 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "learning_rate": 3.978413019647526e-06, | |
| "loss": 2.8221, | |
| "step": 76000 | |
| }, | |
| { | |
| "epoch": 2.42, | |
| "learning_rate": 3.873007842145206e-06, | |
| "loss": 2.817, | |
| "step": 76500 | |
| }, | |
| { | |
| "epoch": 2.43, | |
| "learning_rate": 3.7676026646428875e-06, | |
| "loss": 2.8334, | |
| "step": 77000 | |
| }, | |
| { | |
| "epoch": 2.45, | |
| "learning_rate": 3.6621974871405687e-06, | |
| "loss": 2.8423, | |
| "step": 77500 | |
| }, | |
| { | |
| "epoch": 2.47, | |
| "learning_rate": 3.5567923096382494e-06, | |
| "loss": 2.8247, | |
| "step": 78000 | |
| }, | |
| { | |
| "epoch": 2.48, | |
| "learning_rate": 3.451387132135931e-06, | |
| "loss": 2.8373, | |
| "step": 78500 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "learning_rate": 3.3459819546336118e-06, | |
| "loss": 2.8324, | |
| "step": 79000 | |
| }, | |
| { | |
| "epoch": 2.51, | |
| "learning_rate": 3.240576777131293e-06, | |
| "loss": 2.8312, | |
| "step": 79500 | |
| }, | |
| { | |
| "epoch": 2.53, | |
| "learning_rate": 3.1351715996289737e-06, | |
| "loss": 2.8452, | |
| "step": 80000 | |
| }, | |
| { | |
| "epoch": 2.55, | |
| "learning_rate": 3.029766422126655e-06, | |
| "loss": 2.8331, | |
| "step": 80500 | |
| }, | |
| { | |
| "epoch": 2.56, | |
| "learning_rate": 2.9243612446243365e-06, | |
| "loss": 2.8209, | |
| "step": 81000 | |
| }, | |
| { | |
| "epoch": 2.58, | |
| "learning_rate": 2.8189560671220172e-06, | |
| "loss": 2.8289, | |
| "step": 81500 | |
| }, | |
| { | |
| "epoch": 2.59, | |
| "learning_rate": 2.7135508896196984e-06, | |
| "loss": 2.8415, | |
| "step": 82000 | |
| }, | |
| { | |
| "epoch": 2.61, | |
| "learning_rate": 2.608145712117379e-06, | |
| "loss": 2.8256, | |
| "step": 82500 | |
| }, | |
| { | |
| "epoch": 2.62, | |
| "learning_rate": 2.5027405346150608e-06, | |
| "loss": 2.8257, | |
| "step": 83000 | |
| }, | |
| { | |
| "epoch": 2.64, | |
| "learning_rate": 2.3973353571127415e-06, | |
| "loss": 2.833, | |
| "step": 83500 | |
| }, | |
| { | |
| "epoch": 2.66, | |
| "learning_rate": 2.2919301796104227e-06, | |
| "loss": 2.8348, | |
| "step": 84000 | |
| }, | |
| { | |
| "epoch": 2.67, | |
| "learning_rate": 2.186525002108104e-06, | |
| "loss": 2.8292, | |
| "step": 84500 | |
| }, | |
| { | |
| "epoch": 2.69, | |
| "learning_rate": 2.081119824605785e-06, | |
| "loss": 2.8259, | |
| "step": 85000 | |
| }, | |
| { | |
| "epoch": 2.7, | |
| "learning_rate": 1.9757146471034658e-06, | |
| "loss": 2.8319, | |
| "step": 85500 | |
| }, | |
| { | |
| "epoch": 2.72, | |
| "learning_rate": 1.870309469601147e-06, | |
| "loss": 2.8094, | |
| "step": 86000 | |
| }, | |
| { | |
| "epoch": 2.74, | |
| "learning_rate": 1.764904292098828e-06, | |
| "loss": 2.8276, | |
| "step": 86500 | |
| }, | |
| { | |
| "epoch": 2.75, | |
| "learning_rate": 1.659499114596509e-06, | |
| "loss": 2.8325, | |
| "step": 87000 | |
| }, | |
| { | |
| "epoch": 2.77, | |
| "learning_rate": 1.55409393709419e-06, | |
| "loss": 2.8247, | |
| "step": 87500 | |
| }, | |
| { | |
| "epoch": 2.78, | |
| "learning_rate": 1.4486887595918715e-06, | |
| "loss": 2.8363, | |
| "step": 88000 | |
| }, | |
| { | |
| "epoch": 2.8, | |
| "learning_rate": 1.3432835820895524e-06, | |
| "loss": 2.8343, | |
| "step": 88500 | |
| }, | |
| { | |
| "epoch": 2.81, | |
| "learning_rate": 1.2378784045872334e-06, | |
| "loss": 2.8325, | |
| "step": 89000 | |
| }, | |
| { | |
| "epoch": 2.83, | |
| "learning_rate": 1.1324732270849146e-06, | |
| "loss": 2.8316, | |
| "step": 89500 | |
| }, | |
| { | |
| "epoch": 2.85, | |
| "learning_rate": 1.0270680495825955e-06, | |
| "loss": 2.8232, | |
| "step": 90000 | |
| }, | |
| { | |
| "epoch": 2.86, | |
| "learning_rate": 9.216628720802767e-07, | |
| "loss": 2.8241, | |
| "step": 90500 | |
| }, | |
| { | |
| "epoch": 2.88, | |
| "learning_rate": 8.162576945779577e-07, | |
| "loss": 2.8203, | |
| "step": 91000 | |
| }, | |
| { | |
| "epoch": 2.89, | |
| "learning_rate": 7.108525170756387e-07, | |
| "loss": 2.8356, | |
| "step": 91500 | |
| }, | |
| { | |
| "epoch": 2.91, | |
| "learning_rate": 6.054473395733199e-07, | |
| "loss": 2.8509, | |
| "step": 92000 | |
| }, | |
| { | |
| "epoch": 2.92, | |
| "learning_rate": 5.00042162071001e-07, | |
| "loss": 2.8315, | |
| "step": 92500 | |
| }, | |
| { | |
| "epoch": 2.94, | |
| "learning_rate": 3.9463698456868205e-07, | |
| "loss": 2.8223, | |
| "step": 93000 | |
| }, | |
| { | |
| "epoch": 2.96, | |
| "learning_rate": 2.892318070663631e-07, | |
| "loss": 2.8368, | |
| "step": 93500 | |
| }, | |
| { | |
| "epoch": 2.97, | |
| "learning_rate": 1.838266295640442e-07, | |
| "loss": 2.8271, | |
| "step": 94000 | |
| }, | |
| { | |
| "epoch": 2.99, | |
| "learning_rate": 7.842145206172527e-08, | |
| "loss": 2.8375, | |
| "step": 94500 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 94872, | |
| "num_train_epochs": 3, | |
| "save_steps": 500, | |
| "total_flos": 7.025524751644754e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |