PEFT
Safetensors
Russian
qwen2
legal
contract-extraction
information-extraction
json-generation
lora
qwen
russian
enterprise
Instructions to use zieglerd/RussianConcsExt with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use zieglerd/RussianConcsExt with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2.5-32B-Instruct") model = PeftModel.from_pretrained(base_model, "zieglerd/RussianConcsExt") - Notebooks
- Google Colab
- Kaggle
| { | |
| "best_global_step": null, | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.0, | |
| "eval_steps": 66, | |
| "global_step": 66, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.030303030303030304, | |
| "grad_norm": 0.0872589573264122, | |
| "learning_rate": 0.0, | |
| "loss": 0.2969, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.06060606060606061, | |
| "grad_norm": 0.07570399343967438, | |
| "learning_rate": 5e-06, | |
| "loss": 0.2534, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.09090909090909091, | |
| "grad_norm": 0.0646587386727333, | |
| "learning_rate": 1e-05, | |
| "loss": 0.2195, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.12121212121212122, | |
| "grad_norm": 0.08738136291503906, | |
| "learning_rate": 9.993977281025862e-06, | |
| "loss": 0.2949, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.15151515151515152, | |
| "grad_norm": 0.09267034381628036, | |
| "learning_rate": 9.975923633360985e-06, | |
| "loss": 0.3128, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.18181818181818182, | |
| "grad_norm": 0.0921434611082077, | |
| "learning_rate": 9.945882549823906e-06, | |
| "loss": 0.3027, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.21212121212121213, | |
| "grad_norm": 0.09888184815645218, | |
| "learning_rate": 9.903926402016153e-06, | |
| "loss": 0.3188, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.24242424242424243, | |
| "grad_norm": 0.09699065238237381, | |
| "learning_rate": 9.850156265972722e-06, | |
| "loss": 0.2958, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.2727272727272727, | |
| "grad_norm": 0.08493418246507645, | |
| "learning_rate": 9.784701678661045e-06, | |
| "loss": 0.2584, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.30303030303030304, | |
| "grad_norm": 0.07863851636648178, | |
| "learning_rate": 9.707720325915105e-06, | |
| "loss": 0.2457, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.3333333333333333, | |
| "grad_norm": 0.09796863794326782, | |
| "learning_rate": 9.619397662556434e-06, | |
| "loss": 0.3038, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.36363636363636365, | |
| "grad_norm": 0.06206300109624863, | |
| "learning_rate": 9.519946465617217e-06, | |
| "loss": 0.1931, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.3939393939393939, | |
| "grad_norm": 0.08884033560752869, | |
| "learning_rate": 9.409606321741776e-06, | |
| "loss": 0.2729, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.42424242424242425, | |
| "grad_norm": 0.06140454113483429, | |
| "learning_rate": 9.288643050001362e-06, | |
| "loss": 0.1844, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.45454545454545453, | |
| "grad_norm": 0.0735398381948471, | |
| "learning_rate": 9.157348061512728e-06, | |
| "loss": 0.2258, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.48484848484848486, | |
| "grad_norm": 0.08862978219985962, | |
| "learning_rate": 9.016037657403225e-06, | |
| "loss": 0.2582, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.5151515151515151, | |
| "grad_norm": 0.1046353206038475, | |
| "learning_rate": 8.865052266813686e-06, | |
| "loss": 0.3167, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.5454545454545454, | |
| "grad_norm": 0.07262540608644485, | |
| "learning_rate": 8.704755626774796e-06, | |
| "loss": 0.2139, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.5757575757575758, | |
| "grad_norm": 0.055651213973760605, | |
| "learning_rate": 8.535533905932739e-06, | |
| "loss": 0.1626, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.6060606060606061, | |
| "grad_norm": 0.06227761507034302, | |
| "learning_rate": 8.357794774235094e-06, | |
| "loss": 0.1744, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.6363636363636364, | |
| "grad_norm": 0.07962284982204437, | |
| "learning_rate": 8.171966420818227e-06, | |
| "loss": 0.2164, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.6666666666666666, | |
| "grad_norm": 0.06255478411912918, | |
| "learning_rate": 7.978496522462167e-06, | |
| "loss": 0.1726, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.696969696969697, | |
| "grad_norm": 0.05239630118012428, | |
| "learning_rate": 7.777851165098012e-06, | |
| "loss": 0.1359, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.7272727272727273, | |
| "grad_norm": 0.06619983911514282, | |
| "learning_rate": 7.570513720966108e-06, | |
| "loss": 0.1648, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.7575757575757576, | |
| "grad_norm": 0.06786537170410156, | |
| "learning_rate": 7.3569836841299905e-06, | |
| "loss": 0.1703, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.7878787878787878, | |
| "grad_norm": 0.051433369517326355, | |
| "learning_rate": 7.137775467151411e-06, | |
| "loss": 0.1162, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.8181818181818182, | |
| "grad_norm": 0.05339939147233963, | |
| "learning_rate": 6.913417161825449e-06, | |
| "loss": 0.119, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.8484848484848485, | |
| "grad_norm": 0.07627519220113754, | |
| "learning_rate": 6.684449266961101e-06, | |
| "loss": 0.1246, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.8787878787878788, | |
| "grad_norm": 0.0718780905008316, | |
| "learning_rate": 6.451423386272312e-06, | |
| "loss": 0.1373, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.9090909090909091, | |
| "grad_norm": 0.07383424788713455, | |
| "learning_rate": 6.21490089951632e-06, | |
| "loss": 0.1103, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.9393939393939394, | |
| "grad_norm": 0.08858547359704971, | |
| "learning_rate": 5.975451610080643e-06, | |
| "loss": 0.1492, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.9696969696969697, | |
| "grad_norm": 0.06277935951948166, | |
| "learning_rate": 5.733652372276809e-06, | |
| "loss": 0.1013, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 0.0857253447175026, | |
| "learning_rate": 5.490085701647805e-06, | |
| "loss": 0.1307, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 1.0303030303030303, | |
| "grad_norm": 0.0627182200551033, | |
| "learning_rate": 5.245338371637091e-06, | |
| "loss": 0.0952, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 1.0606060606060606, | |
| "grad_norm": 0.05283113196492195, | |
| "learning_rate": 5e-06, | |
| "loss": 0.0755, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 1.0909090909090908, | |
| "grad_norm": 0.04437226057052612, | |
| "learning_rate": 4.75466162836291e-06, | |
| "loss": 0.0632, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 1.121212121212121, | |
| "grad_norm": 0.058942172676324844, | |
| "learning_rate": 4.509914298352197e-06, | |
| "loss": 0.079, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 1.1515151515151516, | |
| "grad_norm": 0.0615689717233181, | |
| "learning_rate": 4.266347627723192e-06, | |
| "loss": 0.0799, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 1.1818181818181819, | |
| "grad_norm": 0.05987268686294556, | |
| "learning_rate": 4.02454838991936e-06, | |
| "loss": 0.0743, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 1.2121212121212122, | |
| "grad_norm": 0.06211871653795242, | |
| "learning_rate": 3.7850991004836813e-06, | |
| "loss": 0.0752, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.2424242424242424, | |
| "grad_norm": 0.05732128396630287, | |
| "learning_rate": 3.5485766137276894e-06, | |
| "loss": 0.0707, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 1.2727272727272727, | |
| "grad_norm": 0.05059375986456871, | |
| "learning_rate": 3.3155507330389004e-06, | |
| "loss": 0.0594, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 1.303030303030303, | |
| "grad_norm": 0.04942630976438522, | |
| "learning_rate": 3.0865828381745515e-06, | |
| "loss": 0.0567, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 1.3333333333333333, | |
| "grad_norm": 0.06048675253987312, | |
| "learning_rate": 2.862224532848591e-06, | |
| "loss": 0.0685, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 1.3636363636363638, | |
| "grad_norm": 0.039925456047058105, | |
| "learning_rate": 2.6430163158700116e-06, | |
| "loss": 0.0436, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 1.393939393939394, | |
| "grad_norm": 0.05743777006864548, | |
| "learning_rate": 2.429486279033892e-06, | |
| "loss": 0.0607, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 1.4242424242424243, | |
| "grad_norm": 0.04005807638168335, | |
| "learning_rate": 2.2221488349019903e-06, | |
| "loss": 0.0417, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 1.4545454545454546, | |
| "grad_norm": 0.050174467265605927, | |
| "learning_rate": 2.0215034775378336e-06, | |
| "loss": 0.0513, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 1.4848484848484849, | |
| "grad_norm": 0.057930007576942444, | |
| "learning_rate": 1.8280335791817733e-06, | |
| "loss": 0.0589, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 1.5151515151515151, | |
| "grad_norm": 0.07396280765533447, | |
| "learning_rate": 1.642205225764908e-06, | |
| "loss": 0.0692, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.5454545454545454, | |
| "grad_norm": 0.053840093314647675, | |
| "learning_rate": 1.4644660940672628e-06, | |
| "loss": 0.0533, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 1.5757575757575757, | |
| "grad_norm": 0.040064774453639984, | |
| "learning_rate": 1.2952443732252058e-06, | |
| "loss": 0.0386, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 1.606060606060606, | |
| "grad_norm": 0.04430682584643364, | |
| "learning_rate": 1.134947733186315e-06, | |
| "loss": 0.0411, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 1.6363636363636362, | |
| "grad_norm": 0.05869768187403679, | |
| "learning_rate": 9.83962342596776e-07, | |
| "loss": 0.0519, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 1.6666666666666665, | |
| "grad_norm": 0.04796537011861801, | |
| "learning_rate": 8.426519384872733e-07, | |
| "loss": 0.0439, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 1.696969696969697, | |
| "grad_norm": 0.04101736098527908, | |
| "learning_rate": 7.113569499986401e-07, | |
| "loss": 0.0346, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 1.7272727272727273, | |
| "grad_norm": 0.04963319003582001, | |
| "learning_rate": 5.903936782582253e-07, | |
| "loss": 0.0419, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 1.7575757575757576, | |
| "grad_norm": 0.05762108042836189, | |
| "learning_rate": 4.800535343827834e-07, | |
| "loss": 0.0487, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 1.7878787878787878, | |
| "grad_norm": 0.038197822868824005, | |
| "learning_rate": 3.8060233744356634e-07, | |
| "loss": 0.0346, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 1.8181818181818183, | |
| "grad_norm": 0.0402914397418499, | |
| "learning_rate": 2.9227967408489653e-07, | |
| "loss": 0.036, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 1.8484848484848486, | |
| "grad_norm": 0.04647289216518402, | |
| "learning_rate": 2.152983213389559e-07, | |
| "loss": 0.0391, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 1.878787878787879, | |
| "grad_norm": 0.05009330436587334, | |
| "learning_rate": 1.4984373402728014e-07, | |
| "loss": 0.0445, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 1.9090909090909092, | |
| "grad_norm": 0.049318231642246246, | |
| "learning_rate": 9.607359798384785e-08, | |
| "loss": 0.0388, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 1.9393939393939394, | |
| "grad_norm": 0.06097106263041496, | |
| "learning_rate": 5.411745017609493e-08, | |
| "loss": 0.0528, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 1.9696969696969697, | |
| "grad_norm": 0.04419880732893944, | |
| "learning_rate": 2.4076366639015914e-08, | |
| "loss": 0.0376, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 0.05926321819424629, | |
| "learning_rate": 6.022718974137976e-09, | |
| "loss": 0.0507, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 0.041032154113054276, | |
| "eval_runtime": 26.3787, | |
| "eval_samples_per_second": 1.592, | |
| "eval_steps_per_second": 0.227, | |
| "step": 66 | |
| } | |
| ], | |
| "logging_steps": 1.0, | |
| "max_steps": 66, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "save_steps": 0, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3.324201985846018e+18, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |