Instructions to use modrill/qwen3_4b_base_lingcoder_shortcot_4k_lora with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use modrill/qwen3_4b_base_lingcoder_shortcot_4k_lora with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="modrill/qwen3_4b_base_lingcoder_shortcot_4k_lora") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("modrill/qwen3_4b_base_lingcoder_shortcot_4k_lora", dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use modrill/qwen3_4b_base_lingcoder_shortcot_4k_lora with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "modrill/qwen3_4b_base_lingcoder_shortcot_4k_lora" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "modrill/qwen3_4b_base_lingcoder_shortcot_4k_lora", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/modrill/qwen3_4b_base_lingcoder_shortcot_4k_lora
- SGLang
How to use modrill/qwen3_4b_base_lingcoder_shortcot_4k_lora with SGLang:
Install from pip and serve model
# Install SGLang from pip: pip install sglang # Start the SGLang server: python3 -m sglang.launch_server \ --model-path "modrill/qwen3_4b_base_lingcoder_shortcot_4k_lora" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "modrill/qwen3_4b_base_lingcoder_shortcot_4k_lora", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker images
docker run --gpus all \ --shm-size 32g \ -p 30000:30000 \ -v ~/.cache/huggingface:/root/.cache/huggingface \ --env "HF_TOKEN=<secret>" \ --ipc=host \ lmsysorg/sglang:latest \ python3 -m sglang.launch_server \ --model-path "modrill/qwen3_4b_base_lingcoder_shortcot_4k_lora" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "modrill/qwen3_4b_base_lingcoder_shortcot_4k_lora", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use modrill/qwen3_4b_base_lingcoder_shortcot_4k_lora with Docker Model Runner:
docker model run hf.co/modrill/qwen3_4b_base_lingcoder_shortcot_4k_lora
| { | |
| "best_global_step": null, | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "eval_steps": 200, | |
| "global_step": 3094, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0032323232323232323, | |
| "grad_norm": 0.032284051179885864, | |
| "learning_rate": 5.806451612903226e-06, | |
| "loss": 0.6013355255126953, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.006464646464646465, | |
| "grad_norm": 0.01937970519065857, | |
| "learning_rate": 1.2258064516129032e-05, | |
| "loss": 0.5758121490478516, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.009696969696969697, | |
| "grad_norm": 0.014327733777463436, | |
| "learning_rate": 1.870967741935484e-05, | |
| "loss": 0.5787662506103516, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.01292929292929293, | |
| "grad_norm": 0.012254982255399227, | |
| "learning_rate": 2.5161290322580645e-05, | |
| "loss": 0.5327143669128418, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.01616161616161616, | |
| "grad_norm": 0.014536243863403797, | |
| "learning_rate": 3.161290322580645e-05, | |
| "loss": 0.5393171310424805, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.019393939393939394, | |
| "grad_norm": 0.011900736019015312, | |
| "learning_rate": 3.8064516129032254e-05, | |
| "loss": 0.5058945178985595, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.022626262626262626, | |
| "grad_norm": 0.01210293360054493, | |
| "learning_rate": 4.451612903225807e-05, | |
| "loss": 0.517607593536377, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.02585858585858586, | |
| "grad_norm": 0.017207792028784752, | |
| "learning_rate": 5.096774193548387e-05, | |
| "loss": 0.5269095420837402, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.02909090909090909, | |
| "grad_norm": 0.013736969791352749, | |
| "learning_rate": 5.7419354838709685e-05, | |
| "loss": 0.5040688514709473, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.03232323232323232, | |
| "grad_norm": 0.011664404533803463, | |
| "learning_rate": 6.387096774193548e-05, | |
| "loss": 0.5147775173187256, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.035555555555555556, | |
| "grad_norm": 0.014052552171051502, | |
| "learning_rate": 7.03225806451613e-05, | |
| "loss": 0.5230005741119385, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.03878787878787879, | |
| "grad_norm": 0.011644740588963032, | |
| "learning_rate": 7.67741935483871e-05, | |
| "loss": 0.5105222702026367, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.04202020202020202, | |
| "grad_norm": 0.011730308644473553, | |
| "learning_rate": 8.32258064516129e-05, | |
| "loss": 0.4989170074462891, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.04525252525252525, | |
| "grad_norm": 0.012009115889668465, | |
| "learning_rate": 8.967741935483871e-05, | |
| "loss": 0.5003124713897705, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.048484848484848485, | |
| "grad_norm": 0.012424134649336338, | |
| "learning_rate": 9.612903225806452e-05, | |
| "loss": 0.5077538013458252, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.05171717171717172, | |
| "grad_norm": 0.011461800895631313, | |
| "learning_rate": 9.999954295400999e-05, | |
| "loss": 0.5061477661132813, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.05494949494949495, | |
| "grad_norm": 0.011583201587200165, | |
| "learning_rate": 9.999440128258112e-05, | |
| "loss": 0.5013481140136719, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.05818181818181818, | |
| "grad_norm": 0.011583367362618446, | |
| "learning_rate": 9.998354722168459e-05, | |
| "loss": 0.48343815803527834, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.061414141414141414, | |
| "grad_norm": 0.011094105429947376, | |
| "learning_rate": 9.996698201151175e-05, | |
| "loss": 0.507840633392334, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.06464646464646465, | |
| "grad_norm": 0.011715452186763287, | |
| "learning_rate": 9.994470754481315e-05, | |
| "loss": 0.49884777069091796, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.06787878787878789, | |
| "grad_norm": 0.010746965184807777, | |
| "learning_rate": 9.991672636668239e-05, | |
| "loss": 0.5068713188171386, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.07111111111111111, | |
| "grad_norm": 0.012883410789072514, | |
| "learning_rate": 9.988304167426519e-05, | |
| "loss": 0.4920186519622803, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.07434343434343435, | |
| "grad_norm": 0.011187366209924221, | |
| "learning_rate": 9.984365731639419e-05, | |
| "loss": 0.5021648406982422, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.07757575757575758, | |
| "grad_norm": 0.010671757161617279, | |
| "learning_rate": 9.979857779314906e-05, | |
| "loss": 0.5038897514343261, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.08080808080808081, | |
| "grad_norm": 0.01044373121112585, | |
| "learning_rate": 9.974780825534246e-05, | |
| "loss": 0.4965065956115723, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.08404040404040404, | |
| "grad_norm": 0.010565251111984253, | |
| "learning_rate": 9.969135450393141e-05, | |
| "loss": 0.5145994186401367, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.08727272727272728, | |
| "grad_norm": 0.010024026967585087, | |
| "learning_rate": 9.96292229893545e-05, | |
| "loss": 0.505019235610962, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.0905050505050505, | |
| "grad_norm": 0.010430407710373402, | |
| "learning_rate": 9.956142081079484e-05, | |
| "loss": 0.5115808010101318, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.09373737373737374, | |
| "grad_norm": 0.010048807598650455, | |
| "learning_rate": 9.948795571536891e-05, | |
| "loss": 0.48525152206420896, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.09696969696969697, | |
| "grad_norm": 0.010108387097716331, | |
| "learning_rate": 9.94088360972414e-05, | |
| "loss": 0.5002010822296142, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.10020202020202021, | |
| "grad_norm": 0.010273640975356102, | |
| "learning_rate": 9.932407099666608e-05, | |
| "loss": 0.49662046432495116, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.10343434343434343, | |
| "grad_norm": 0.00995971355587244, | |
| "learning_rate": 9.923367009895274e-05, | |
| "loss": 0.48578290939331054, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.10666666666666667, | |
| "grad_norm": 0.010459775105118752, | |
| "learning_rate": 9.913764373336079e-05, | |
| "loss": 0.48862767219543457, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.1098989898989899, | |
| "grad_norm": 0.009838269092142582, | |
| "learning_rate": 9.903600287191875e-05, | |
| "loss": 0.5034208774566651, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.11313131313131314, | |
| "grad_norm": 0.00978950597345829, | |
| "learning_rate": 9.892875912817079e-05, | |
| "loss": 0.4870161533355713, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.11636363636363636, | |
| "grad_norm": 0.01030043140053749, | |
| "learning_rate": 9.881592475584964e-05, | |
| "loss": 0.5026071548461915, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.1195959595959596, | |
| "grad_norm": 0.010531975887715816, | |
| "learning_rate": 9.869751264747656e-05, | |
| "loss": 0.4883917808532715, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.12282828282828283, | |
| "grad_norm": 0.00986825954169035, | |
| "learning_rate": 9.857353633288814e-05, | |
| "loss": 0.4927018165588379, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.12606060606060607, | |
| "grad_norm": 0.009432349354028702, | |
| "learning_rate": 9.844400997769043e-05, | |
| "loss": 0.4908174514770508, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.1292929292929293, | |
| "grad_norm": 0.01057665515691042, | |
| "learning_rate": 9.83089483816404e-05, | |
| "loss": 0.5069625854492188, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.13252525252525252, | |
| "grad_norm": 0.010007908567786217, | |
| "learning_rate": 9.816836697695482e-05, | |
| "loss": 0.4988056182861328, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.13575757575757577, | |
| "grad_norm": 0.010027808137238026, | |
| "learning_rate": 9.802228182654702e-05, | |
| "loss": 0.5007385730743408, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.138989898989899, | |
| "grad_norm": 0.009953738190233707, | |
| "learning_rate": 9.787070962219156e-05, | |
| "loss": 0.5130783081054687, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.14222222222222222, | |
| "grad_norm": 0.010204462334513664, | |
| "learning_rate": 9.771366768261696e-05, | |
| "loss": 0.4947535514831543, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.14545454545454545, | |
| "grad_norm": 0.009612451307475567, | |
| "learning_rate": 9.755117395152689e-05, | |
| "loss": 0.4917112350463867, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.1486868686868687, | |
| "grad_norm": 0.00995573028922081, | |
| "learning_rate": 9.73832469955499e-05, | |
| "loss": 0.4882859230041504, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.15191919191919193, | |
| "grad_norm": 0.009584570303559303, | |
| "learning_rate": 9.720990600211797e-05, | |
| "loss": 0.500526762008667, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 0.15515151515151515, | |
| "grad_norm": 0.010585076175630093, | |
| "learning_rate": 9.703117077727419e-05, | |
| "loss": 0.496882963180542, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.15838383838383838, | |
| "grad_norm": 0.009859723038971424, | |
| "learning_rate": 9.684706174340965e-05, | |
| "loss": 0.48728485107421876, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 0.16161616161616163, | |
| "grad_norm": 0.010212041437625885, | |
| "learning_rate": 9.665759993693e-05, | |
| "loss": 0.49378366470336915, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.16484848484848486, | |
| "grad_norm": 0.009744231589138508, | |
| "learning_rate": 9.646280700585185e-05, | |
| "loss": 0.4663555145263672, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 0.16808080808080808, | |
| "grad_norm": 0.009789686650037766, | |
| "learning_rate": 9.626270520732916e-05, | |
| "loss": 0.4879913330078125, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 0.1713131313131313, | |
| "grad_norm": 0.009891769848763943, | |
| "learning_rate": 9.605731740511022e-05, | |
| "loss": 0.48809428215026857, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 0.17454545454545456, | |
| "grad_norm": 0.01002143882215023, | |
| "learning_rate": 9.584666706692517e-05, | |
| "loss": 0.4959606170654297, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 0.17777777777777778, | |
| "grad_norm": 0.009208496659994125, | |
| "learning_rate": 9.56307782618046e-05, | |
| "loss": 0.4878594398498535, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.181010101010101, | |
| "grad_norm": 0.009645081125199795, | |
| "learning_rate": 9.540967565732937e-05, | |
| "loss": 0.4769869804382324, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 0.18424242424242424, | |
| "grad_norm": 0.010497638955712318, | |
| "learning_rate": 9.51833845168121e-05, | |
| "loss": 0.4970097064971924, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 0.1874747474747475, | |
| "grad_norm": 0.010612033307552338, | |
| "learning_rate": 9.495193069641057e-05, | |
| "loss": 0.4945381164550781, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 0.1907070707070707, | |
| "grad_norm": 0.009433986619114876, | |
| "learning_rate": 9.47153406421734e-05, | |
| "loss": 0.4860210418701172, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 0.19393939393939394, | |
| "grad_norm": 0.009995914995670319, | |
| "learning_rate": 9.447364138701823e-05, | |
| "loss": 0.4904911994934082, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.19717171717171716, | |
| "grad_norm": 0.009814019314944744, | |
| "learning_rate": 9.422686054764302e-05, | |
| "loss": 0.4915336608886719, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 0.20040404040404042, | |
| "grad_norm": 0.010199982672929764, | |
| "learning_rate": 9.397502632137055e-05, | |
| "loss": 0.4805011749267578, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 0.20363636363636364, | |
| "grad_norm": 0.010121874511241913, | |
| "learning_rate": 9.371816748292641e-05, | |
| "loss": 0.47633209228515627, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 0.20686868686868687, | |
| "grad_norm": 0.009638865478336811, | |
| "learning_rate": 9.345631338115141e-05, | |
| "loss": 0.48993511199951173, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 0.2101010101010101, | |
| "grad_norm": 0.010041174478828907, | |
| "learning_rate": 9.318949393564807e-05, | |
| "loss": 0.4798978328704834, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.21333333333333335, | |
| "grad_norm": 0.010145517997443676, | |
| "learning_rate": 9.291773963336193e-05, | |
| "loss": 0.4696659564971924, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 0.21656565656565657, | |
| "grad_norm": 0.01043335534632206, | |
| "learning_rate": 9.264108152509816e-05, | |
| "loss": 0.4955574035644531, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 0.2197979797979798, | |
| "grad_norm": 0.010406569577753544, | |
| "learning_rate": 9.235955122197368e-05, | |
| "loss": 0.48659563064575195, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 0.22303030303030302, | |
| "grad_norm": 0.009870355017483234, | |
| "learning_rate": 9.207318089180524e-05, | |
| "loss": 0.4766091823577881, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 0.22626262626262628, | |
| "grad_norm": 0.009980005212128162, | |
| "learning_rate": 9.178200325543384e-05, | |
| "loss": 0.5022068023681641, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.2294949494949495, | |
| "grad_norm": 0.009765878319740295, | |
| "learning_rate": 9.148605158298621e-05, | |
| "loss": 0.48309478759765623, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 0.23272727272727273, | |
| "grad_norm": 0.009879437275230885, | |
| "learning_rate": 9.118535969007314e-05, | |
| "loss": 0.4793684959411621, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 0.23595959595959595, | |
| "grad_norm": 0.009907045401632786, | |
| "learning_rate": 9.087996193392578e-05, | |
| "loss": 0.49844112396240237, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 0.2391919191919192, | |
| "grad_norm": 0.009958872571587563, | |
| "learning_rate": 9.056989320947e-05, | |
| "loss": 0.48113102912902833, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 0.24242424242424243, | |
| "grad_norm": 0.010206855833530426, | |
| "learning_rate": 9.025518894533921e-05, | |
| "loss": 0.5048784255981446, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.24565656565656566, | |
| "grad_norm": 0.009286429733037949, | |
| "learning_rate": 8.99358850998263e-05, | |
| "loss": 0.4862624168395996, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 0.24888888888888888, | |
| "grad_norm": 0.009919015690684319, | |
| "learning_rate": 8.9612018156775e-05, | |
| "loss": 0.48739056587219237, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 0.25212121212121213, | |
| "grad_norm": 0.010435211472213268, | |
| "learning_rate": 8.928362512141124e-05, | |
| "loss": 0.48689990043640136, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 0.25535353535353533, | |
| "grad_norm": 0.009992080740630627, | |
| "learning_rate": 8.895074351611488e-05, | |
| "loss": 0.4848791599273682, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 0.2585858585858586, | |
| "grad_norm": 0.010449117980897427, | |
| "learning_rate": 8.861341137613242e-05, | |
| "loss": 0.49130568504333494, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.26181818181818184, | |
| "grad_norm": 0.010061345063149929, | |
| "learning_rate": 8.827166724523105e-05, | |
| "loss": 0.49056081771850585, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 0.26505050505050504, | |
| "grad_norm": 0.009908635169267654, | |
| "learning_rate": 8.792555017129461e-05, | |
| "loss": 0.4706866264343262, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 0.2682828282828283, | |
| "grad_norm": 0.010003669187426567, | |
| "learning_rate": 8.757509970186196e-05, | |
| "loss": 0.48719348907470705, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 0.27151515151515154, | |
| "grad_norm": 0.009513127617537975, | |
| "learning_rate": 8.722035587960826e-05, | |
| "loss": 0.48200483322143556, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 0.27474747474747474, | |
| "grad_norm": 0.009142451919615269, | |
| "learning_rate": 8.686135923776969e-05, | |
| "loss": 0.48613176345825193, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 0.277979797979798, | |
| "grad_norm": 0.00980432890355587, | |
| "learning_rate": 8.649815079551205e-05, | |
| "loss": 0.4976047515869141, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 0.2812121212121212, | |
| "grad_norm": 0.010442109778523445, | |
| "learning_rate": 8.613077205324389e-05, | |
| "loss": 0.48451838493347166, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 0.28444444444444444, | |
| "grad_norm": 0.009309548884630203, | |
| "learning_rate": 8.575926498787476e-05, | |
| "loss": 0.5115366458892823, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 0.2876767676767677, | |
| "grad_norm": 0.009093924425542355, | |
| "learning_rate": 8.538367204801872e-05, | |
| "loss": 0.48187432289123533, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 0.2909090909090909, | |
| "grad_norm": 0.009757987223565578, | |
| "learning_rate": 8.500403614914432e-05, | |
| "loss": 0.4882505416870117, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.29414141414141415, | |
| "grad_norm": 0.010261048562824726, | |
| "learning_rate": 8.462040066867089e-05, | |
| "loss": 0.49068965911865237, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 0.2973737373737374, | |
| "grad_norm": 0.009317740797996521, | |
| "learning_rate": 8.423280944101233e-05, | |
| "loss": 0.4966132164001465, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 0.3006060606060606, | |
| "grad_norm": 0.009787693619728088, | |
| "learning_rate": 8.384130675256852e-05, | |
| "loss": 0.4754981994628906, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 0.30383838383838385, | |
| "grad_norm": 0.010005015879869461, | |
| "learning_rate": 8.34459373366651e-05, | |
| "loss": 0.4735103130340576, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 0.30707070707070705, | |
| "grad_norm": 0.009837017394602299, | |
| "learning_rate": 8.304674636844231e-05, | |
| "loss": 0.4809592247009277, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 0.3103030303030303, | |
| "grad_norm": 0.009590484201908112, | |
| "learning_rate": 8.264377945969312e-05, | |
| "loss": 0.48206100463867185, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 0.31353535353535356, | |
| "grad_norm": 0.009699508547782898, | |
| "learning_rate": 8.223708265365174e-05, | |
| "loss": 0.48718748092651365, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 0.31676767676767675, | |
| "grad_norm": 0.010278215631842613, | |
| "learning_rate": 8.182670241973253e-05, | |
| "loss": 0.4952278137207031, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "grad_norm": 0.010104077868163586, | |
| "learning_rate": 8.141268564822053e-05, | |
| "loss": 0.47769975662231445, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 0.32323232323232326, | |
| "grad_norm": 0.009301737882196903, | |
| "learning_rate": 8.099507964491369e-05, | |
| "loss": 0.4862718105316162, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.32646464646464646, | |
| "grad_norm": 0.009307135827839375, | |
| "learning_rate": 8.057393212571767e-05, | |
| "loss": 0.49833106994628906, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 0.3296969696969697, | |
| "grad_norm": 0.009420682676136494, | |
| "learning_rate": 8.014929121119378e-05, | |
| "loss": 0.48829941749572753, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 0.3329292929292929, | |
| "grad_norm": 0.010058379732072353, | |
| "learning_rate": 7.972120542106077e-05, | |
| "loss": 0.46506147384643554, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 0.33616161616161616, | |
| "grad_norm": 0.009461579844355583, | |
| "learning_rate": 7.92897236686508e-05, | |
| "loss": 0.47866268157958985, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 0.3393939393939394, | |
| "grad_norm": 0.010341835208237171, | |
| "learning_rate": 7.885489525532075e-05, | |
| "loss": 0.4966601371765137, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 0.3426262626262626, | |
| "grad_norm": 0.01042103860527277, | |
| "learning_rate": 7.84167698648189e-05, | |
| "loss": 0.49251084327697753, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 0.34585858585858587, | |
| "grad_norm": 0.010442749597132206, | |
| "learning_rate": 7.797539755760805e-05, | |
| "loss": 0.4816086769104004, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 0.3490909090909091, | |
| "grad_norm": 0.010256553068757057, | |
| "learning_rate": 7.753082876514562e-05, | |
| "loss": 0.47102947235107423, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 0.3523232323232323, | |
| "grad_norm": 0.009399017319083214, | |
| "learning_rate": 7.708311428412129e-05, | |
| "loss": 0.4810478210449219, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 0.35555555555555557, | |
| "grad_norm": 0.009499317966401577, | |
| "learning_rate": 7.663230527065293e-05, | |
| "loss": 0.47051143646240234, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.35878787878787877, | |
| "grad_norm": 0.009759469889104366, | |
| "learning_rate": 7.617845323444156e-05, | |
| "loss": 0.4780744552612305, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 0.362020202020202, | |
| "grad_norm": 0.00987281370908022, | |
| "learning_rate": 7.572161003288565e-05, | |
| "loss": 0.4804032325744629, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 0.3652525252525253, | |
| "grad_norm": 0.00963522493839264, | |
| "learning_rate": 7.526182786515609e-05, | |
| "loss": 0.48206367492675783, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 0.36848484848484847, | |
| "grad_norm": 0.009587026201188564, | |
| "learning_rate": 7.479915926623165e-05, | |
| "loss": 0.49240264892578123, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 0.3717171717171717, | |
| "grad_norm": 0.009810036048293114, | |
| "learning_rate": 7.433365710089646e-05, | |
| "loss": 0.48599681854248045, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 0.374949494949495, | |
| "grad_norm": 0.00978278461843729, | |
| "learning_rate": 7.386537455769963e-05, | |
| "loss": 0.4688436031341553, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 0.3781818181818182, | |
| "grad_norm": 0.00925996620208025, | |
| "learning_rate": 7.339436514287783e-05, | |
| "loss": 0.47986507415771484, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 0.3814141414141414, | |
| "grad_norm": 0.010006657801568508, | |
| "learning_rate": 7.292068267424165e-05, | |
| "loss": 0.4771553993225098, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 0.3846464646464646, | |
| "grad_norm": 0.010299976915121078, | |
| "learning_rate": 7.244438127502647e-05, | |
| "loss": 0.4854436874389648, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 0.3878787878787879, | |
| "grad_norm": 0.009807374328374863, | |
| "learning_rate": 7.196551536770807e-05, | |
| "loss": 0.4763533592224121, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.39111111111111113, | |
| "grad_norm": 0.010062369517982006, | |
| "learning_rate": 7.148413966778451e-05, | |
| "loss": 0.47457141876220704, | |
| "step": 1210 | |
| }, | |
| { | |
| "epoch": 0.39434343434343433, | |
| "grad_norm": 0.009904388338327408, | |
| "learning_rate": 7.100030917752423e-05, | |
| "loss": 0.4732469081878662, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 0.3975757575757576, | |
| "grad_norm": 0.009578046388924122, | |
| "learning_rate": 7.051407917968138e-05, | |
| "loss": 0.47551660537719725, | |
| "step": 1230 | |
| }, | |
| { | |
| "epoch": 0.40080808080808084, | |
| "grad_norm": 0.010024272836744785, | |
| "learning_rate": 7.002550523117926e-05, | |
| "loss": 0.4835049629211426, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 0.40404040404040403, | |
| "grad_norm": 0.010056886821985245, | |
| "learning_rate": 6.953464315676241e-05, | |
| "loss": 0.4909071922302246, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 0.4072727272727273, | |
| "grad_norm": 0.009707778692245483, | |
| "learning_rate": 6.904154904261792e-05, | |
| "loss": 0.4842695236206055, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 0.4105050505050505, | |
| "grad_norm": 0.00976107269525528, | |
| "learning_rate": 6.8546279229967e-05, | |
| "loss": 0.48967390060424804, | |
| "step": 1270 | |
| }, | |
| { | |
| "epoch": 0.41373737373737374, | |
| "grad_norm": 0.010392800904810429, | |
| "learning_rate": 6.804889030862753e-05, | |
| "loss": 0.48658218383789065, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 0.416969696969697, | |
| "grad_norm": 0.009267269633710384, | |
| "learning_rate": 6.754943911054793e-05, | |
| "loss": 0.48893008232116697, | |
| "step": 1290 | |
| }, | |
| { | |
| "epoch": 0.4202020202020202, | |
| "grad_norm": 0.009753459133207798, | |
| "learning_rate": 6.704798270331358e-05, | |
| "loss": 0.49384117126464844, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 0.42343434343434344, | |
| "grad_norm": 0.011121846735477448, | |
| "learning_rate": 6.654457838362621e-05, | |
| "loss": 0.47458324432373045, | |
| "step": 1310 | |
| }, | |
| { | |
| "epoch": 0.4266666666666667, | |
| "grad_norm": 0.009406324476003647, | |
| "learning_rate": 6.603928367075718e-05, | |
| "loss": 0.4703402519226074, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 0.4298989898989899, | |
| "grad_norm": 0.010009719990193844, | |
| "learning_rate": 6.553215629997529e-05, | |
| "loss": 0.4851715087890625, | |
| "step": 1330 | |
| }, | |
| { | |
| "epoch": 0.43313131313131314, | |
| "grad_norm": 0.009798573330044746, | |
| "learning_rate": 6.502325421594988e-05, | |
| "loss": 0.4779622554779053, | |
| "step": 1340 | |
| }, | |
| { | |
| "epoch": 0.43636363636363634, | |
| "grad_norm": 0.0098969591781497, | |
| "learning_rate": 6.451263556613007e-05, | |
| "loss": 0.4708548545837402, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 0.4395959595959596, | |
| "grad_norm": 0.009853474795818329, | |
| "learning_rate": 6.40003586941008e-05, | |
| "loss": 0.4721970558166504, | |
| "step": 1360 | |
| }, | |
| { | |
| "epoch": 0.44282828282828285, | |
| "grad_norm": 0.009663710370659828, | |
| "learning_rate": 6.348648213291642e-05, | |
| "loss": 0.4798272132873535, | |
| "step": 1370 | |
| }, | |
| { | |
| "epoch": 0.44606060606060605, | |
| "grad_norm": 0.009419051930308342, | |
| "learning_rate": 6.297106459841272e-05, | |
| "loss": 0.471483039855957, | |
| "step": 1380 | |
| }, | |
| { | |
| "epoch": 0.4492929292929293, | |
| "grad_norm": 0.009978282265365124, | |
| "learning_rate": 6.245416498249801e-05, | |
| "loss": 0.4772329330444336, | |
| "step": 1390 | |
| }, | |
| { | |
| "epoch": 0.45252525252525255, | |
| "grad_norm": 0.009491856209933758, | |
| "learning_rate": 6.193584234642403e-05, | |
| "loss": 0.48812179565429686, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.45575757575757575, | |
| "grad_norm": 0.010496517643332481, | |
| "learning_rate": 6.141615591403771e-05, | |
| "loss": 0.48897976875305177, | |
| "step": 1410 | |
| }, | |
| { | |
| "epoch": 0.458989898989899, | |
| "grad_norm": 0.01015474647283554, | |
| "learning_rate": 6.0895165065014106e-05, | |
| "loss": 0.4850447654724121, | |
| "step": 1420 | |
| }, | |
| { | |
| "epoch": 0.4622222222222222, | |
| "grad_norm": 0.009763741865754128, | |
| "learning_rate": 6.037292932807167e-05, | |
| "loss": 0.4857158660888672, | |
| "step": 1430 | |
| }, | |
| { | |
| "epoch": 0.46545454545454545, | |
| "grad_norm": 0.009874231182038784, | |
| "learning_rate": 5.984950837417048e-05, | |
| "loss": 0.4844364166259766, | |
| "step": 1440 | |
| }, | |
| { | |
| "epoch": 0.4686868686868687, | |
| "grad_norm": 0.010104037821292877, | |
| "learning_rate": 5.932496200969422e-05, | |
| "loss": 0.47542514801025393, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 0.4719191919191919, | |
| "grad_norm": 0.009445435367524624, | |
| "learning_rate": 5.879935016961661e-05, | |
| "loss": 0.48579182624816897, | |
| "step": 1460 | |
| }, | |
| { | |
| "epoch": 0.47515151515151516, | |
| "grad_norm": 0.010507128201425076, | |
| "learning_rate": 5.827273291065326e-05, | |
| "loss": 0.48273677825927735, | |
| "step": 1470 | |
| }, | |
| { | |
| "epoch": 0.4783838383838384, | |
| "grad_norm": 0.009411566890776157, | |
| "learning_rate": 5.7745170404399484e-05, | |
| "loss": 0.46429009437561036, | |
| "step": 1480 | |
| }, | |
| { | |
| "epoch": 0.4816161616161616, | |
| "grad_norm": 0.010377817787230015, | |
| "learning_rate": 5.721672293045518e-05, | |
| "loss": 0.49172677993774416, | |
| "step": 1490 | |
| }, | |
| { | |
| "epoch": 0.48484848484848486, | |
| "grad_norm": 0.009920118376612663, | |
| "learning_rate": 5.668745086953712e-05, | |
| "loss": 0.4934688568115234, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.48808080808080806, | |
| "grad_norm": 0.012272641994059086, | |
| "learning_rate": 5.615741469657985e-05, | |
| "loss": 0.4826413631439209, | |
| "step": 1510 | |
| }, | |
| { | |
| "epoch": 0.4913131313131313, | |
| "grad_norm": 0.00981989037245512, | |
| "learning_rate": 5.562667497382582e-05, | |
| "loss": 0.48468503952026365, | |
| "step": 1520 | |
| }, | |
| { | |
| "epoch": 0.49454545454545457, | |
| "grad_norm": 0.010148138739168644, | |
| "learning_rate": 5.509529234390553e-05, | |
| "loss": 0.47773942947387693, | |
| "step": 1530 | |
| }, | |
| { | |
| "epoch": 0.49777777777777776, | |
| "grad_norm": 0.010528397746384144, | |
| "learning_rate": 5.456332752290837e-05, | |
| "loss": 0.47507562637329104, | |
| "step": 1540 | |
| }, | |
| { | |
| "epoch": 0.501010101010101, | |
| "grad_norm": 0.01076479908078909, | |
| "learning_rate": 5.4030841293445244e-05, | |
| "loss": 0.486495304107666, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 0.5042424242424243, | |
| "grad_norm": 0.009976644068956375, | |
| "learning_rate": 5.349789449770351e-05, | |
| "loss": 0.48320484161376953, | |
| "step": 1560 | |
| }, | |
| { | |
| "epoch": 0.5074747474747475, | |
| "grad_norm": 0.010504718869924545, | |
| "learning_rate": 5.2964548030495065e-05, | |
| "loss": 0.48847188949584963, | |
| "step": 1570 | |
| }, | |
| { | |
| "epoch": 0.5107070707070707, | |
| "grad_norm": 0.010325642302632332, | |
| "learning_rate": 5.243086283229852e-05, | |
| "loss": 0.47591514587402345, | |
| "step": 1580 | |
| }, | |
| { | |
| "epoch": 0.5139393939393939, | |
| "grad_norm": 0.010260741226375103, | |
| "learning_rate": 5.18968998822961e-05, | |
| "loss": 0.48136124610900877, | |
| "step": 1590 | |
| }, | |
| { | |
| "epoch": 0.5171717171717172, | |
| "grad_norm": 0.010797196067869663, | |
| "learning_rate": 5.1362720191406065e-05, | |
| "loss": 0.48076438903808594, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 0.5204040404040404, | |
| "grad_norm": 0.010010522790253162, | |
| "learning_rate": 5.082838479531169e-05, | |
| "loss": 0.5004307270050049, | |
| "step": 1610 | |
| }, | |
| { | |
| "epoch": 0.5236363636363637, | |
| "grad_norm": 0.010120037943124771, | |
| "learning_rate": 5.029395474748714e-05, | |
| "loss": 0.4812767028808594, | |
| "step": 1620 | |
| }, | |
| { | |
| "epoch": 0.5268686868686868, | |
| "grad_norm": 0.009431752376258373, | |
| "learning_rate": 4.975949111222158e-05, | |
| "loss": 0.4887521743774414, | |
| "step": 1630 | |
| }, | |
| { | |
| "epoch": 0.5301010101010101, | |
| "grad_norm": 0.010080527514219284, | |
| "learning_rate": 4.9225054957641916e-05, | |
| "loss": 0.48248910903930664, | |
| "step": 1640 | |
| }, | |
| { | |
| "epoch": 0.5333333333333333, | |
| "grad_norm": 0.009522376582026482, | |
| "learning_rate": 4.8690707348735035e-05, | |
| "loss": 0.4855649948120117, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 0.5365656565656566, | |
| "grad_norm": 0.009686745703220367, | |
| "learning_rate": 4.8156509340370605e-05, | |
| "loss": 0.47187280654907227, | |
| "step": 1660 | |
| }, | |
| { | |
| "epoch": 0.5397979797979798, | |
| "grad_norm": 0.011875285767018795, | |
| "learning_rate": 4.762252197032482e-05, | |
| "loss": 0.46579513549804685, | |
| "step": 1670 | |
| }, | |
| { | |
| "epoch": 0.5430303030303031, | |
| "grad_norm": 0.009932303801178932, | |
| "learning_rate": 4.7088806252306224e-05, | |
| "loss": 0.47946829795837403, | |
| "step": 1680 | |
| }, | |
| { | |
| "epoch": 0.5462626262626262, | |
| "grad_norm": 0.017099183052778244, | |
| "learning_rate": 4.655542316898423e-05, | |
| "loss": 0.4593667030334473, | |
| "step": 1690 | |
| }, | |
| { | |
| "epoch": 0.5494949494949495, | |
| "grad_norm": 0.010512005537748337, | |
| "learning_rate": 4.6022433665021246e-05, | |
| "loss": 0.48582897186279295, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 0.5527272727272727, | |
| "grad_norm": 0.00989206787198782, | |
| "learning_rate": 4.548989864010902e-05, | |
| "loss": 0.4849580764770508, | |
| "step": 1710 | |
| }, | |
| { | |
| "epoch": 0.555959595959596, | |
| "grad_norm": 0.010284029878675938, | |
| "learning_rate": 4.495787894201031e-05, | |
| "loss": 0.49089298248291013, | |
| "step": 1720 | |
| }, | |
| { | |
| "epoch": 0.5591919191919192, | |
| "grad_norm": 0.00992760993540287, | |
| "learning_rate": 4.442643535960631e-05, | |
| "loss": 0.48010549545288084, | |
| "step": 1730 | |
| }, | |
| { | |
| "epoch": 0.5624242424242424, | |
| "grad_norm": 0.00978371873497963, | |
| "learning_rate": 4.3895628615950864e-05, | |
| "loss": 0.47594566345214845, | |
| "step": 1740 | |
| }, | |
| { | |
| "epoch": 0.5656565656565656, | |
| "grad_norm": 0.00981004349887371, | |
| "learning_rate": 4.3365519361332345e-05, | |
| "loss": 0.48056421279907224, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 0.5688888888888889, | |
| "grad_norm": 0.010216868482530117, | |
| "learning_rate": 4.283616816634353e-05, | |
| "loss": 0.47501134872436523, | |
| "step": 1760 | |
| }, | |
| { | |
| "epoch": 0.5721212121212121, | |
| "grad_norm": 0.010267022997140884, | |
| "learning_rate": 4.230763551496089e-05, | |
| "loss": 0.478366756439209, | |
| "step": 1770 | |
| }, | |
| { | |
| "epoch": 0.5753535353535354, | |
| "grad_norm": 0.009910739958286285, | |
| "learning_rate": 4.1779981797633645e-05, | |
| "loss": 0.478058385848999, | |
| "step": 1780 | |
| }, | |
| { | |
| "epoch": 0.5785858585858585, | |
| "grad_norm": 0.011339185759425163, | |
| "learning_rate": 4.1253267304383455e-05, | |
| "loss": 0.48466057777404786, | |
| "step": 1790 | |
| }, | |
| { | |
| "epoch": 0.5818181818181818, | |
| "grad_norm": 0.009522072039544582, | |
| "learning_rate": 4.072755221791572e-05, | |
| "loss": 0.4769908905029297, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 0.585050505050505, | |
| "grad_norm": 0.009808518923819065, | |
| "learning_rate": 4.020289660674306e-05, | |
| "loss": 0.47162666320800783, | |
| "step": 1810 | |
| }, | |
| { | |
| "epoch": 0.5882828282828283, | |
| "grad_norm": 0.009962448850274086, | |
| "learning_rate": 3.967936041832173e-05, | |
| "loss": 0.46282405853271485, | |
| "step": 1820 | |
| }, | |
| { | |
| "epoch": 0.5915151515151515, | |
| "grad_norm": 0.009498678147792816, | |
| "learning_rate": 3.9157003472202246e-05, | |
| "loss": 0.4794480323791504, | |
| "step": 1830 | |
| }, | |
| { | |
| "epoch": 0.5947474747474748, | |
| "grad_norm": 0.009407177567481995, | |
| "learning_rate": 3.863588545319407e-05, | |
| "loss": 0.4729412078857422, | |
| "step": 1840 | |
| }, | |
| { | |
| "epoch": 0.597979797979798, | |
| "grad_norm": 0.009899895638227463, | |
| "learning_rate": 3.8116065904546196e-05, | |
| "loss": 0.47380704879760743, | |
| "step": 1850 | |
| }, | |
| { | |
| "epoch": 0.6012121212121212, | |
| "grad_norm": 0.009560837410390377, | |
| "learning_rate": 3.759760422114362e-05, | |
| "loss": 0.47751388549804685, | |
| "step": 1860 | |
| }, | |
| { | |
| "epoch": 0.6044444444444445, | |
| "grad_norm": 0.010970192961394787, | |
| "learning_rate": 3.708055964272088e-05, | |
| "loss": 0.47801823616027833, | |
| "step": 1870 | |
| }, | |
| { | |
| "epoch": 0.6076767676767677, | |
| "grad_norm": 0.00964390765875578, | |
| "learning_rate": 3.6564991247093234e-05, | |
| "loss": 0.4800426483154297, | |
| "step": 1880 | |
| }, | |
| { | |
| "epoch": 0.610909090909091, | |
| "grad_norm": 0.009764602407813072, | |
| "learning_rate": 3.6050957943406465e-05, | |
| "loss": 0.4812753677368164, | |
| "step": 1890 | |
| }, | |
| { | |
| "epoch": 0.6141414141414141, | |
| "grad_norm": 0.009959314949810505, | |
| "learning_rate": 3.553851846540584e-05, | |
| "loss": 0.47804956436157225, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 0.6173737373737374, | |
| "grad_norm": 0.010666392743587494, | |
| "learning_rate": 3.50277313647252e-05, | |
| "loss": 0.4772273063659668, | |
| "step": 1910 | |
| }, | |
| { | |
| "epoch": 0.6206060606060606, | |
| "grad_norm": 0.009173358790576458, | |
| "learning_rate": 3.451865500419676e-05, | |
| "loss": 0.4892144203186035, | |
| "step": 1920 | |
| }, | |
| { | |
| "epoch": 0.6238383838383839, | |
| "grad_norm": 0.010000358335673809, | |
| "learning_rate": 3.401134755118256e-05, | |
| "loss": 0.48959059715270997, | |
| "step": 1930 | |
| }, | |
| { | |
| "epoch": 0.6270707070707071, | |
| "grad_norm": 0.010190536268055439, | |
| "learning_rate": 3.350586697092826e-05, | |
| "loss": 0.46478729248046874, | |
| "step": 1940 | |
| }, | |
| { | |
| "epoch": 0.6303030303030303, | |
| "grad_norm": 0.010812178254127502, | |
| "learning_rate": 3.300227101993998e-05, | |
| "loss": 0.5046152114868164, | |
| "step": 1950 | |
| }, | |
| { | |
| "epoch": 0.6335353535353535, | |
| "grad_norm": 0.01017849799245596, | |
| "learning_rate": 3.2500617239384947e-05, | |
| "loss": 0.4698008060455322, | |
| "step": 1960 | |
| }, | |
| { | |
| "epoch": 0.6367676767676768, | |
| "grad_norm": 0.011103908531367779, | |
| "learning_rate": 3.200096294851691e-05, | |
| "loss": 0.4716217041015625, | |
| "step": 1970 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "grad_norm": 0.009982883930206299, | |
| "learning_rate": 3.150336523812674e-05, | |
| "loss": 0.47135162353515625, | |
| "step": 1980 | |
| }, | |
| { | |
| "epoch": 0.6432323232323233, | |
| "grad_norm": 0.01043197326362133, | |
| "learning_rate": 3.100788096401925e-05, | |
| "loss": 0.4799614906311035, | |
| "step": 1990 | |
| }, | |
| { | |
| "epoch": 0.6464646464646465, | |
| "grad_norm": 0.010667623952031136, | |
| "learning_rate": 3.051456674051677e-05, | |
| "loss": 0.4682164192199707, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.6496969696969697, | |
| "grad_norm": 0.010620036162436008, | |
| "learning_rate": 3.0023478933990347e-05, | |
| "loss": 0.4750208854675293, | |
| "step": 2010 | |
| }, | |
| { | |
| "epoch": 0.6529292929292929, | |
| "grad_norm": 0.010374991223216057, | |
| "learning_rate": 2.9534673656419377e-05, | |
| "loss": 0.48034076690673827, | |
| "step": 2020 | |
| }, | |
| { | |
| "epoch": 0.6561616161616162, | |
| "grad_norm": 0.011932817287743092, | |
| "learning_rate": 2.9048206758980136e-05, | |
| "loss": 0.46314101219177245, | |
| "step": 2030 | |
| }, | |
| { | |
| "epoch": 0.6593939393939394, | |
| "grad_norm": 0.01039852574467659, | |
| "learning_rate": 2.856413382566425e-05, | |
| "loss": 0.4783937454223633, | |
| "step": 2040 | |
| }, | |
| { | |
| "epoch": 0.6626262626262627, | |
| "grad_norm": 0.010200604796409607, | |
| "learning_rate": 2.8082510166927583e-05, | |
| "loss": 0.4792025089263916, | |
| "step": 2050 | |
| }, | |
| { | |
| "epoch": 0.6658585858585858, | |
| "grad_norm": 0.009561127051711082, | |
| "learning_rate": 2.760339081337041e-05, | |
| "loss": 0.4722686767578125, | |
| "step": 2060 | |
| }, | |
| { | |
| "epoch": 0.6690909090909091, | |
| "grad_norm": 0.00924921128898859, | |
| "learning_rate": 2.7126830509449773e-05, | |
| "loss": 0.4884464263916016, | |
| "step": 2070 | |
| }, | |
| { | |
| "epoch": 0.6723232323232323, | |
| "grad_norm": 0.00991444569081068, | |
| "learning_rate": 2.6652883707224075e-05, | |
| "loss": 0.4804549217224121, | |
| "step": 2080 | |
| }, | |
| { | |
| "epoch": 0.6755555555555556, | |
| "grad_norm": 0.009902069345116615, | |
| "learning_rate": 2.618160456013153e-05, | |
| "loss": 0.4781071186065674, | |
| "step": 2090 | |
| }, | |
| { | |
| "epoch": 0.6787878787878788, | |
| "grad_norm": 0.010504493489861488, | |
| "learning_rate": 2.571304691680255e-05, | |
| "loss": 0.48059587478637694, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 0.682020202020202, | |
| "grad_norm": 0.009641965851187706, | |
| "learning_rate": 2.5247264314906917e-05, | |
| "loss": 0.4706240177154541, | |
| "step": 2110 | |
| }, | |
| { | |
| "epoch": 0.6852525252525252, | |
| "grad_norm": 0.010276644490659237, | |
| "learning_rate": 2.4784309975036513e-05, | |
| "loss": 0.4885101318359375, | |
| "step": 2120 | |
| }, | |
| { | |
| "epoch": 0.6884848484848485, | |
| "grad_norm": 0.010960405692458153, | |
| "learning_rate": 2.4324236794624456e-05, | |
| "loss": 0.4882383346557617, | |
| "step": 2130 | |
| }, | |
| { | |
| "epoch": 0.6917171717171717, | |
| "grad_norm": 0.010282796807587147, | |
| "learning_rate": 2.386709734190079e-05, | |
| "loss": 0.4768857479095459, | |
| "step": 2140 | |
| }, | |
| { | |
| "epoch": 0.694949494949495, | |
| "grad_norm": 0.010104385204613209, | |
| "learning_rate": 2.34129438498862e-05, | |
| "loss": 0.4802837371826172, | |
| "step": 2150 | |
| }, | |
| { | |
| "epoch": 0.6981818181818182, | |
| "grad_norm": 0.010027035139501095, | |
| "learning_rate": 2.296182821042374e-05, | |
| "loss": 0.4874839782714844, | |
| "step": 2160 | |
| }, | |
| { | |
| "epoch": 0.7014141414141414, | |
| "grad_norm": 0.010018851608037949, | |
| "learning_rate": 2.2513801968249644e-05, | |
| "loss": 0.4758561134338379, | |
| "step": 2170 | |
| }, | |
| { | |
| "epoch": 0.7046464646464646, | |
| "grad_norm": 0.009862969629466534, | |
| "learning_rate": 2.2068916315103783e-05, | |
| "loss": 0.4686488151550293, | |
| "step": 2180 | |
| }, | |
| { | |
| "epoch": 0.7078787878787879, | |
| "grad_norm": 0.00952910166233778, | |
| "learning_rate": 2.162722208388057e-05, | |
| "loss": 0.4782154083251953, | |
| "step": 2190 | |
| }, | |
| { | |
| "epoch": 0.7111111111111111, | |
| "grad_norm": 0.010213647037744522, | |
| "learning_rate": 2.1188769742820625e-05, | |
| "loss": 0.4773773193359375, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 0.7143434343434344, | |
| "grad_norm": 0.010498392395675182, | |
| "learning_rate": 2.075360938974429e-05, | |
| "loss": 0.4733907222747803, | |
| "step": 2210 | |
| }, | |
| { | |
| "epoch": 0.7175757575757575, | |
| "grad_norm": 0.009394815191626549, | |
| "learning_rate": 2.03217907463275e-05, | |
| "loss": 0.47564210891723635, | |
| "step": 2220 | |
| }, | |
| { | |
| "epoch": 0.7208080808080808, | |
| "grad_norm": 0.010383618995547295, | |
| "learning_rate": 1.989336315242048e-05, | |
| "loss": 0.4784512519836426, | |
| "step": 2230 | |
| }, | |
| { | |
| "epoch": 0.724040404040404, | |
| "grad_norm": 0.01043599285185337, | |
| "learning_rate": 1.9468375560410117e-05, | |
| "loss": 0.4808964729309082, | |
| "step": 2240 | |
| }, | |
| { | |
| "epoch": 0.7272727272727273, | |
| "grad_norm": 0.009953988716006279, | |
| "learning_rate": 1.90468765296267e-05, | |
| "loss": 0.49031834602355956, | |
| "step": 2250 | |
| }, | |
| { | |
| "epoch": 0.7305050505050505, | |
| "grad_norm": 0.010356656275689602, | |
| "learning_rate": 1.8628914220795494e-05, | |
| "loss": 0.48055601119995117, | |
| "step": 2260 | |
| }, | |
| { | |
| "epoch": 0.7337373737373737, | |
| "grad_norm": 0.009841440245509148, | |
| "learning_rate": 1.8214536390533822e-05, | |
| "loss": 0.47170586585998536, | |
| "step": 2270 | |
| }, | |
| { | |
| "epoch": 0.7369696969696969, | |
| "grad_norm": 0.010102550499141216, | |
| "learning_rate": 1.7803790385894387e-05, | |
| "loss": 0.4660043716430664, | |
| "step": 2280 | |
| }, | |
| { | |
| "epoch": 0.7402020202020202, | |
| "grad_norm": 0.010421738028526306, | |
| "learning_rate": 1.7396723138955428e-05, | |
| "loss": 0.4599196434020996, | |
| "step": 2290 | |
| }, | |
| { | |
| "epoch": 0.7434343434343434, | |
| "grad_norm": 0.009896540082991123, | |
| "learning_rate": 1.699338116145811e-05, | |
| "loss": 0.46491589546203616, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 0.7466666666666667, | |
| "grad_norm": 0.010468855500221252, | |
| "learning_rate": 1.6593810539492195e-05, | |
| "loss": 0.47761125564575196, | |
| "step": 2310 | |
| }, | |
| { | |
| "epoch": 0.74989898989899, | |
| "grad_norm": 0.010416937991976738, | |
| "learning_rate": 1.619805692823016e-05, | |
| "loss": 0.49956817626953126, | |
| "step": 2320 | |
| }, | |
| { | |
| "epoch": 0.7531313131313131, | |
| "grad_norm": 0.010007611475884914, | |
| "learning_rate": 1.580616554671057e-05, | |
| "loss": 0.4716916084289551, | |
| "step": 2330 | |
| }, | |
| { | |
| "epoch": 0.7563636363636363, | |
| "grad_norm": 0.010231648571789265, | |
| "learning_rate": 1.5418181172671382e-05, | |
| "loss": 0.4909040451049805, | |
| "step": 2340 | |
| }, | |
| { | |
| "epoch": 0.7595959595959596, | |
| "grad_norm": 0.010324012488126755, | |
| "learning_rate": 1.5034148137433623e-05, | |
| "loss": 0.47939190864562986, | |
| "step": 2350 | |
| }, | |
| { | |
| "epoch": 0.7628282828282829, | |
| "grad_norm": 0.011009547859430313, | |
| "learning_rate": 1.4654110320836017e-05, | |
| "loss": 0.48291826248168945, | |
| "step": 2360 | |
| }, | |
| { | |
| "epoch": 0.7660606060606061, | |
| "grad_norm": 0.010392943397164345, | |
| "learning_rate": 1.4278111146221263e-05, | |
| "loss": 0.49179973602294924, | |
| "step": 2370 | |
| }, | |
| { | |
| "epoch": 0.7692929292929293, | |
| "grad_norm": 0.010355197824537754, | |
| "learning_rate": 1.3906193575474508e-05, | |
| "loss": 0.4716278076171875, | |
| "step": 2380 | |
| }, | |
| { | |
| "epoch": 0.7725252525252525, | |
| "grad_norm": 0.009932084940373898, | |
| "learning_rate": 1.3538400104114446e-05, | |
| "loss": 0.47190055847167967, | |
| "step": 2390 | |
| }, | |
| { | |
| "epoch": 0.7757575757575758, | |
| "grad_norm": 0.010710643604397774, | |
| "learning_rate": 1.3174772756437742e-05, | |
| "loss": 0.4703176498413086, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 0.778989898989899, | |
| "grad_norm": 0.010614068247377872, | |
| "learning_rate": 1.2815353080717379e-05, | |
| "loss": 0.47541141510009766, | |
| "step": 2410 | |
| }, | |
| { | |
| "epoch": 0.7822222222222223, | |
| "grad_norm": 0.011346950195729733, | |
| "learning_rate": 1.246018214445525e-05, | |
| "loss": 0.4860015869140625, | |
| "step": 2420 | |
| }, | |
| { | |
| "epoch": 0.7854545454545454, | |
| "grad_norm": 0.009824907407164574, | |
| "learning_rate": 1.210930052968981e-05, | |
| "loss": 0.49062480926513674, | |
| "step": 2430 | |
| }, | |
| { | |
| "epoch": 0.7886868686868687, | |
| "grad_norm": 0.010624224320054054, | |
| "learning_rate": 1.1762748328359152e-05, | |
| "loss": 0.4694485664367676, | |
| "step": 2440 | |
| }, | |
| { | |
| "epoch": 0.7919191919191919, | |
| "grad_norm": 0.01044746395200491, | |
| "learning_rate": 1.1420565137720045e-05, | |
| "loss": 0.47275629043579104, | |
| "step": 2450 | |
| }, | |
| { | |
| "epoch": 0.7951515151515152, | |
| "grad_norm": 0.010226710699498653, | |
| "learning_rate": 1.1082790055823533e-05, | |
| "loss": 0.4670067310333252, | |
| "step": 2460 | |
| }, | |
| { | |
| "epoch": 0.7983838383838384, | |
| "grad_norm": 0.010427460074424744, | |
| "learning_rate": 1.0749461677047624e-05, | |
| "loss": 0.4700475692749023, | |
| "step": 2470 | |
| }, | |
| { | |
| "epoch": 0.8016161616161617, | |
| "grad_norm": 0.010494428686797619, | |
| "learning_rate": 1.0420618087687418e-05, | |
| "loss": 0.46589016914367676, | |
| "step": 2480 | |
| }, | |
| { | |
| "epoch": 0.8048484848484848, | |
| "grad_norm": 0.010100893676280975, | |
| "learning_rate": 1.0096296861603321e-05, | |
| "loss": 0.4704419136047363, | |
| "step": 2490 | |
| }, | |
| { | |
| "epoch": 0.8080808080808081, | |
| "grad_norm": 0.010682797059416771, | |
| "learning_rate": 9.776535055927931e-06, | |
| "loss": 0.47326183319091797, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.8113131313131313, | |
| "grad_norm": 0.00972407590597868, | |
| "learning_rate": 9.461369206831772e-06, | |
| "loss": 0.48441619873046876, | |
| "step": 2510 | |
| }, | |
| { | |
| "epoch": 0.8145454545454546, | |
| "grad_norm": 0.010327558033168316, | |
| "learning_rate": 9.150835325348678e-06, | |
| "loss": 0.45856351852416993, | |
| "step": 2520 | |
| }, | |
| { | |
| "epoch": 0.8177777777777778, | |
| "grad_norm": 0.010118944570422173, | |
| "learning_rate": 8.844968893261197e-06, | |
| "loss": 0.48114948272705077, | |
| "step": 2530 | |
| }, | |
| { | |
| "epoch": 0.821010101010101, | |
| "grad_norm": 0.010876161977648735, | |
| "learning_rate": 8.543804859046345e-06, | |
| "loss": 0.4930680274963379, | |
| "step": 2540 | |
| }, | |
| { | |
| "epoch": 0.8242424242424242, | |
| "grad_norm": 0.010722608305513859, | |
| "learning_rate": 8.247377633882463e-06, | |
| "loss": 0.46875743865966796, | |
| "step": 2550 | |
| }, | |
| { | |
| "epoch": 0.8274747474747475, | |
| "grad_norm": 0.01088438369333744, | |
| "learning_rate": 7.95572108771726e-06, | |
| "loss": 0.4768000602722168, | |
| "step": 2560 | |
| }, | |
| { | |
| "epoch": 0.8307070707070707, | |
| "grad_norm": 0.01026720181107521, | |
| "learning_rate": 7.66886854539795e-06, | |
| "loss": 0.479974365234375, | |
| "step": 2570 | |
| }, | |
| { | |
| "epoch": 0.833939393939394, | |
| "grad_norm": 0.009710075333714485, | |
| "learning_rate": 7.386852782863407e-06, | |
| "loss": 0.4684715270996094, | |
| "step": 2580 | |
| }, | |
| { | |
| "epoch": 0.8371717171717171, | |
| "grad_norm": 0.009966167621314526, | |
| "learning_rate": 7.109706023399232e-06, | |
| "loss": 0.47191972732543946, | |
| "step": 2590 | |
| }, | |
| { | |
| "epoch": 0.8404040404040404, | |
| "grad_norm": 0.010125650092959404, | |
| "learning_rate": 6.837459933955936e-06, | |
| "loss": 0.4766803741455078, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 0.8436363636363636, | |
| "grad_norm": 0.009984518401324749, | |
| "learning_rate": 6.5701456215305656e-06, | |
| "loss": 0.4592133045196533, | |
| "step": 2610 | |
| }, | |
| { | |
| "epoch": 0.8468686868686869, | |
| "grad_norm": 0.010836348868906498, | |
| "learning_rate": 6.307793629612452e-06, | |
| "loss": 0.4658504009246826, | |
| "step": 2620 | |
| }, | |
| { | |
| "epoch": 0.8501010101010101, | |
| "grad_norm": 0.010431919246912003, | |
| "learning_rate": 6.050433934693339e-06, | |
| "loss": 0.4936856269836426, | |
| "step": 2630 | |
| }, | |
| { | |
| "epoch": 0.8533333333333334, | |
| "grad_norm": 0.01049034669995308, | |
| "learning_rate": 5.798095942842141e-06, | |
| "loss": 0.4765117645263672, | |
| "step": 2640 | |
| }, | |
| { | |
| "epoch": 0.8565656565656565, | |
| "grad_norm": 0.009596607647836208, | |
| "learning_rate": 5.550808486345072e-06, | |
| "loss": 0.47063379287719725, | |
| "step": 2650 | |
| }, | |
| { | |
| "epoch": 0.8597979797979798, | |
| "grad_norm": 0.01032214518636465, | |
| "learning_rate": 5.308599820411247e-06, | |
| "loss": 0.4614537715911865, | |
| "step": 2660 | |
| }, | |
| { | |
| "epoch": 0.863030303030303, | |
| "grad_norm": 0.009960100054740906, | |
| "learning_rate": 5.071497619944171e-06, | |
| "loss": 0.48136143684387206, | |
| "step": 2670 | |
| }, | |
| { | |
| "epoch": 0.8662626262626263, | |
| "grad_norm": 0.010326167568564415, | |
| "learning_rate": 4.839528976379648e-06, | |
| "loss": 0.47299985885620116, | |
| "step": 2680 | |
| }, | |
| { | |
| "epoch": 0.8694949494949495, | |
| "grad_norm": 0.010867294855415821, | |
| "learning_rate": 4.612720394590286e-06, | |
| "loss": 0.4829209327697754, | |
| "step": 2690 | |
| }, | |
| { | |
| "epoch": 0.8727272727272727, | |
| "grad_norm": 0.01050047017633915, | |
| "learning_rate": 4.391097789856985e-06, | |
| "loss": 0.4762550354003906, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 0.8759595959595959, | |
| "grad_norm": 0.010378929786384106, | |
| "learning_rate": 4.174686484907908e-06, | |
| "loss": 0.4898251533508301, | |
| "step": 2710 | |
| }, | |
| { | |
| "epoch": 0.8791919191919192, | |
| "grad_norm": 0.01060938648879528, | |
| "learning_rate": 3.963511207025078e-06, | |
| "loss": 0.47261548042297363, | |
| "step": 2720 | |
| }, | |
| { | |
| "epoch": 0.8824242424242424, | |
| "grad_norm": 0.01075353566557169, | |
| "learning_rate": 3.7575960852189728e-06, | |
| "loss": 0.4839645862579346, | |
| "step": 2730 | |
| }, | |
| { | |
| "epoch": 0.8856565656565657, | |
| "grad_norm": 0.010416378267109394, | |
| "learning_rate": 3.5569646474715722e-06, | |
| "loss": 0.46989760398864744, | |
| "step": 2740 | |
| }, | |
| { | |
| "epoch": 0.8888888888888888, | |
| "grad_norm": 0.010806340724229813, | |
| "learning_rate": 3.361639818048068e-06, | |
| "loss": 0.47272281646728515, | |
| "step": 2750 | |
| }, | |
| { | |
| "epoch": 0.8921212121212121, | |
| "grad_norm": 0.009753530845046043, | |
| "learning_rate": 3.1716439148774534e-06, | |
| "loss": 0.47122917175292967, | |
| "step": 2760 | |
| }, | |
| { | |
| "epoch": 0.8953535353535353, | |
| "grad_norm": 0.01022200658917427, | |
| "learning_rate": 2.986998647002498e-06, | |
| "loss": 0.4727674961090088, | |
| "step": 2770 | |
| }, | |
| { | |
| "epoch": 0.8985858585858586, | |
| "grad_norm": 0.010225590318441391, | |
| "learning_rate": 2.8077251120992742e-06, | |
| "loss": 0.46461896896362304, | |
| "step": 2780 | |
| }, | |
| { | |
| "epoch": 0.9018181818181819, | |
| "grad_norm": 0.010752941481769085, | |
| "learning_rate": 2.633843794066515e-06, | |
| "loss": 0.46602635383605956, | |
| "step": 2790 | |
| }, | |
| { | |
| "epoch": 0.9050505050505051, | |
| "grad_norm": 0.011064955033361912, | |
| "learning_rate": 2.465374560685091e-06, | |
| "loss": 0.4705932140350342, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 0.9082828282828282, | |
| "grad_norm": 0.00982996542006731, | |
| "learning_rate": 2.302336661347926e-06, | |
| "loss": 0.4687389373779297, | |
| "step": 2810 | |
| }, | |
| { | |
| "epoch": 0.9115151515151515, | |
| "grad_norm": 0.010190518572926521, | |
| "learning_rate": 2.1447487248605513e-06, | |
| "loss": 0.4906333923339844, | |
| "step": 2820 | |
| }, | |
| { | |
| "epoch": 0.9147474747474748, | |
| "grad_norm": 0.01034579798579216, | |
| "learning_rate": 1.9926287573125537e-06, | |
| "loss": 0.47768077850341795, | |
| "step": 2830 | |
| }, | |
| { | |
| "epoch": 0.917979797979798, | |
| "grad_norm": 0.010615529492497444, | |
| "learning_rate": 1.845994140020213e-06, | |
| "loss": 0.47643141746520995, | |
| "step": 2840 | |
| }, | |
| { | |
| "epoch": 0.9212121212121213, | |
| "grad_norm": 0.010776858776807785, | |
| "learning_rate": 1.7048616275404771e-06, | |
| "loss": 0.4636590003967285, | |
| "step": 2850 | |
| }, | |
| { | |
| "epoch": 0.9244444444444444, | |
| "grad_norm": 0.010271280072629452, | |
| "learning_rate": 1.5692473457565748e-06, | |
| "loss": 0.4707911014556885, | |
| "step": 2860 | |
| }, | |
| { | |
| "epoch": 0.9276767676767677, | |
| "grad_norm": 0.009596684016287327, | |
| "learning_rate": 1.439166790035501e-06, | |
| "loss": 0.45751228332519533, | |
| "step": 2870 | |
| }, | |
| { | |
| "epoch": 0.9309090909090909, | |
| "grad_norm": 0.009914812631905079, | |
| "learning_rate": 1.3146348234574724e-06, | |
| "loss": 0.4842953681945801, | |
| "step": 2880 | |
| }, | |
| { | |
| "epoch": 0.9341414141414142, | |
| "grad_norm": 0.01014726422727108, | |
| "learning_rate": 1.1956656751176577e-06, | |
| "loss": 0.482682991027832, | |
| "step": 2890 | |
| }, | |
| { | |
| "epoch": 0.9373737373737374, | |
| "grad_norm": 0.010660757310688496, | |
| "learning_rate": 1.0822729385003727e-06, | |
| "loss": 0.48476057052612304, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 0.9406060606060606, | |
| "grad_norm": 0.010105855762958527, | |
| "learning_rate": 9.744695699258955e-07, | |
| "loss": 0.4767448425292969, | |
| "step": 2910 | |
| }, | |
| { | |
| "epoch": 0.9438383838383838, | |
| "grad_norm": 0.010221844539046288, | |
| "learning_rate": 8.722678870700274e-07, | |
| "loss": 0.4663360118865967, | |
| "step": 2920 | |
| }, | |
| { | |
| "epoch": 0.9470707070707071, | |
| "grad_norm": 0.011003104969859123, | |
| "learning_rate": 7.756795675566919e-07, | |
| "loss": 0.48151307106018065, | |
| "step": 2930 | |
| }, | |
| { | |
| "epoch": 0.9503030303030303, | |
| "grad_norm": 0.01029619574546814, | |
| "learning_rate": 6.847156476236516e-07, | |
| "loss": 0.48086977005004883, | |
| "step": 2940 | |
| }, | |
| { | |
| "epoch": 0.9535353535353536, | |
| "grad_norm": 0.010033480823040009, | |
| "learning_rate": 5.993865208614835e-07, | |
| "loss": 0.4648440361022949, | |
| "step": 2950 | |
| }, | |
| { | |
| "epoch": 0.9567676767676768, | |
| "grad_norm": 0.010539564304053783, | |
| "learning_rate": 5.197019370260125e-07, | |
| "loss": 0.46828551292419435, | |
| "step": 2960 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "grad_norm": 0.009619071148335934, | |
| "learning_rate": 4.4567100092429704e-07, | |
| "loss": 0.48481130599975586, | |
| "step": 2970 | |
| }, | |
| { | |
| "epoch": 0.9632323232323232, | |
| "grad_norm": 0.010197056457400322, | |
| "learning_rate": 3.7730217137428857e-07, | |
| "loss": 0.47917518615722654, | |
| "step": 2980 | |
| }, | |
| { | |
| "epoch": 0.9664646464646465, | |
| "grad_norm": 0.01057458110153675, | |
| "learning_rate": 3.1460326023836083e-07, | |
| "loss": 0.48064794540405276, | |
| "step": 2990 | |
| }, | |
| { | |
| "epoch": 0.9696969696969697, | |
| "grad_norm": 0.01009963545948267, | |
| "learning_rate": 2.575814315306846e-07, | |
| "loss": 0.4831876754760742, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.972929292929293, | |
| "grad_norm": 0.010343736037611961, | |
| "learning_rate": 2.0624320059869918e-07, | |
| "loss": 0.4821047306060791, | |
| "step": 3010 | |
| }, | |
| { | |
| "epoch": 0.9761616161616161, | |
| "grad_norm": 0.010384611785411835, | |
| "learning_rate": 1.6059443337861912e-07, | |
| "loss": 0.46325201988220216, | |
| "step": 3020 | |
| }, | |
| { | |
| "epoch": 0.9793939393939394, | |
| "grad_norm": 0.010477159172296524, | |
| "learning_rate": 1.2064034572523142e-07, | |
| "loss": 0.4779689788818359, | |
| "step": 3030 | |
| }, | |
| { | |
| "epoch": 0.9826262626262626, | |
| "grad_norm": 0.010612626560032368, | |
| "learning_rate": 8.638550281591107e-08, | |
| "loss": 0.4866930484771729, | |
| "step": 3040 | |
| }, | |
| { | |
| "epoch": 0.9858585858585859, | |
| "grad_norm": 0.01027057133615017, | |
| "learning_rate": 5.7833818629005054e-08, | |
| "loss": 0.48350844383239744, | |
| "step": 3050 | |
| }, | |
| { | |
| "epoch": 0.9890909090909091, | |
| "grad_norm": 0.010666116140782833, | |
| "learning_rate": 3.498855549660118e-08, | |
| "loss": 0.4722591400146484, | |
| "step": 3060 | |
| }, | |
| { | |
| "epoch": 0.9923232323232323, | |
| "grad_norm": 0.009852438233792782, | |
| "learning_rate": 1.785232373180401e-08, | |
| "loss": 0.48914670944213867, | |
| "step": 3070 | |
| }, | |
| { | |
| "epoch": 0.9955555555555555, | |
| "grad_norm": 0.010089240968227386, | |
| "learning_rate": 6.427081330456774e-09, | |
| "loss": 0.4730827331542969, | |
| "step": 3080 | |
| }, | |
| { | |
| "epoch": 0.9987878787878788, | |
| "grad_norm": 0.010913597419857979, | |
| "learning_rate": 7.141337474148025e-10, | |
| "loss": 0.4666846752166748, | |
| "step": 3090 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "step": 3094, | |
| "total_flos": 4.3887930550675046e+18, | |
| "train_loss": 0.4842414558126453, | |
| "train_runtime": 8903.7116, | |
| "train_samples_per_second": 22.238, | |
| "train_steps_per_second": 0.347 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 3094, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 200, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 4.3887930550675046e+18, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |