Instructions to use Kaipengm2/u4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use Kaipengm2/u4 with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("/inspire/hdd/global_user/zhengkaipeng-240108120123/models/OneReason-0.8B-pretrain-competition") model = PeftModel.from_pretrained(base_model, "Kaipengm2/u4") - Transformers
How to use Kaipengm2/u4 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="Kaipengm2/u4") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("Kaipengm2/u4", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use Kaipengm2/u4 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Kaipengm2/u4" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Kaipengm2/u4", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/Kaipengm2/u4
- SGLang
How to use Kaipengm2/u4 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 "Kaipengm2/u4" \ --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": "Kaipengm2/u4", "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 "Kaipengm2/u4" \ --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": "Kaipengm2/u4", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use Kaipengm2/u4 with Docker Model Runner:
docker model run hf.co/Kaipengm2/u4
| { | |
| "best_global_step": null, | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "eval_steps": 500, | |
| "global_step": 2359, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00211954217888936, | |
| "grad_norm": 1.2627108097076416, | |
| "learning_rate": 2.8169014084507042e-06, | |
| "loss": 2.9677703857421873, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00423908435777872, | |
| "grad_norm": 1.191653847694397, | |
| "learning_rate": 6.338028169014085e-06, | |
| "loss": 3.0035427093505858, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.00635862653666808, | |
| "grad_norm": 1.20098876953125, | |
| "learning_rate": 9.859154929577465e-06, | |
| "loss": 2.8465225219726564, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.00847816871555744, | |
| "grad_norm": 0.667493999004364, | |
| "learning_rate": 1.3380281690140845e-05, | |
| "loss": 2.7270103454589845, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0105977108944468, | |
| "grad_norm": 0.3920593559741974, | |
| "learning_rate": 1.6901408450704224e-05, | |
| "loss": 2.6357650756835938, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.01271725307333616, | |
| "grad_norm": 0.2567223906517029, | |
| "learning_rate": 2.0422535211267607e-05, | |
| "loss": 2.566595458984375, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.01483679525222552, | |
| "grad_norm": 0.29579898715019226, | |
| "learning_rate": 2.3943661971830986e-05, | |
| "loss": 2.4728137969970705, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.01695633743111488, | |
| "grad_norm": 0.2799825966358185, | |
| "learning_rate": 2.746478873239437e-05, | |
| "loss": 2.4795864105224608, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.01907587961000424, | |
| "grad_norm": 0.24245746433734894, | |
| "learning_rate": 3.0985915492957744e-05, | |
| "loss": 2.3617233276367187, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.0211954217888936, | |
| "grad_norm": 0.26466789841651917, | |
| "learning_rate": 3.450704225352113e-05, | |
| "loss": 2.3377412796020507, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.02331496396778296, | |
| "grad_norm": 0.20035089552402496, | |
| "learning_rate": 3.802816901408451e-05, | |
| "loss": 2.2229198455810546, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.02543450614667232, | |
| "grad_norm": 0.20318864285945892, | |
| "learning_rate": 4.154929577464789e-05, | |
| "loss": 2.150411605834961, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.02755404832556168, | |
| "grad_norm": 0.22973288595676422, | |
| "learning_rate": 4.507042253521127e-05, | |
| "loss": 2.1534542083740233, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.02967359050445104, | |
| "grad_norm": 0.23651933670043945, | |
| "learning_rate": 4.8591549295774653e-05, | |
| "loss": 2.107556915283203, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.0317931326833404, | |
| "grad_norm": 0.21380475163459778, | |
| "learning_rate": 4.999978790051525e-05, | |
| "loss": 2.0433422088623048, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.03391267486222976, | |
| "grad_norm": 0.23727920651435852, | |
| "learning_rate": 4.9998491750030315e-05, | |
| "loss": 2.043216514587402, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.03603221704111912, | |
| "grad_norm": 0.2114669680595398, | |
| "learning_rate": 4.9996017343125085e-05, | |
| "loss": 1.9753223419189454, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.03815175922000848, | |
| "grad_norm": 0.24019302427768707, | |
| "learning_rate": 4.9992364796426016e-05, | |
| "loss": 1.9112619400024413, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.04027130139889784, | |
| "grad_norm": 0.19553841650485992, | |
| "learning_rate": 4.998753428208896e-05, | |
| "loss": 1.9021766662597657, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.0423908435777872, | |
| "grad_norm": 0.19863514602184296, | |
| "learning_rate": 4.9981526027791036e-05, | |
| "loss": 1.8693302154541016, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.04451038575667656, | |
| "grad_norm": 0.2501365840435028, | |
| "learning_rate": 4.9974340316719906e-05, | |
| "loss": 1.863976287841797, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.04662992793556592, | |
| "grad_norm": 0.24813759326934814, | |
| "learning_rate": 4.996597748756039e-05, | |
| "loss": 1.8154861450195312, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.048749470114455275, | |
| "grad_norm": 0.18998175859451294, | |
| "learning_rate": 4.9956437934478565e-05, | |
| "loss": 1.864649772644043, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.05086901229334464, | |
| "grad_norm": 0.2037823349237442, | |
| "learning_rate": 4.994572210710315e-05, | |
| "loss": 1.8139299392700194, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.052988554472233995, | |
| "grad_norm": 0.31202712655067444, | |
| "learning_rate": 4.9933830510504306e-05, | |
| "loss": 1.7872890472412108, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.05510809665112336, | |
| "grad_norm": 0.20074909925460815, | |
| "learning_rate": 4.992076370516985e-05, | |
| "loss": 1.7648876190185547, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.057227638830012716, | |
| "grad_norm": 0.2484038770198822, | |
| "learning_rate": 4.990652230697882e-05, | |
| "loss": 1.7551593780517578, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.05934718100890208, | |
| "grad_norm": 0.1958741992712021, | |
| "learning_rate": 4.989110698717248e-05, | |
| "loss": 1.806509780883789, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.061466723187791436, | |
| "grad_norm": 0.23278304934501648, | |
| "learning_rate": 4.987451847232264e-05, | |
| "loss": 1.795139694213867, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.0635862653666808, | |
| "grad_norm": 0.2521565854549408, | |
| "learning_rate": 4.985675754429744e-05, | |
| "loss": 1.7268384933471679, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.06570580754557016, | |
| "grad_norm": 0.2129758596420288, | |
| "learning_rate": 4.983782504022447e-05, | |
| "loss": 1.7406164169311524, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 0.06782534972445951, | |
| "grad_norm": 0.30819347500801086, | |
| "learning_rate": 4.981772185245135e-05, | |
| "loss": 1.7424068450927734, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.06994489190334888, | |
| "grad_norm": 0.24479681253433228, | |
| "learning_rate": 4.979644892850366e-05, | |
| "loss": 1.7084796905517579, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 0.07206443408223824, | |
| "grad_norm": 0.2507385313510895, | |
| "learning_rate": 4.977400727104024e-05, | |
| "loss": 1.763153076171875, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.07418397626112759, | |
| "grad_norm": 0.2552284896373749, | |
| "learning_rate": 4.9750397937805994e-05, | |
| "loss": 1.7396835327148437, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.07630351844001695, | |
| "grad_norm": 0.2502050995826721, | |
| "learning_rate": 4.972562204158199e-05, | |
| "loss": 1.7223161697387694, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.07842306061890632, | |
| "grad_norm": 0.24536821246147156, | |
| "learning_rate": 4.9699680750133035e-05, | |
| "loss": 1.7282117843627929, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 0.08054260279779568, | |
| "grad_norm": 0.26911792159080505, | |
| "learning_rate": 4.967257528615261e-05, | |
| "loss": 1.6887802124023437, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.08266214497668503, | |
| "grad_norm": 0.2593395411968231, | |
| "learning_rate": 4.964430692720529e-05, | |
| "loss": 1.6920608520507812, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 0.0847816871555744, | |
| "grad_norm": 0.30473580956459045, | |
| "learning_rate": 4.961487700566646e-05, | |
| "loss": 1.7394495010375977, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.08690122933446376, | |
| "grad_norm": 0.24422238767147064, | |
| "learning_rate": 4.958428690865957e-05, | |
| "loss": 1.6826156616210937, | |
| "step": 205 | |
| }, | |
| { | |
| "epoch": 0.08902077151335312, | |
| "grad_norm": 0.2919021248817444, | |
| "learning_rate": 4.955253807799073e-05, | |
| "loss": 1.662032699584961, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.09114031369224247, | |
| "grad_norm": 0.2528785467147827, | |
| "learning_rate": 4.951963201008076e-05, | |
| "loss": 1.653702735900879, | |
| "step": 215 | |
| }, | |
| { | |
| "epoch": 0.09325985587113184, | |
| "grad_norm": 0.25239700078964233, | |
| "learning_rate": 4.948557025589467e-05, | |
| "loss": 1.6823293685913085, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.0953793980500212, | |
| "grad_norm": 0.2692783772945404, | |
| "learning_rate": 4.945035442086853e-05, | |
| "loss": 1.662485122680664, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 0.09749894022891055, | |
| "grad_norm": 0.34489408135414124, | |
| "learning_rate": 4.941398616483382e-05, | |
| "loss": 1.6724514007568358, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.09961848240779991, | |
| "grad_norm": 0.30428117513656616, | |
| "learning_rate": 4.9376467201939214e-05, | |
| "loss": 1.5900728225708007, | |
| "step": 235 | |
| }, | |
| { | |
| "epoch": 0.10173802458668928, | |
| "grad_norm": 0.29412388801574707, | |
| "learning_rate": 4.933779930056975e-05, | |
| "loss": 1.670862579345703, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.10385756676557864, | |
| "grad_norm": 0.2694248855113983, | |
| "learning_rate": 4.9297984283263495e-05, | |
| "loss": 1.5947572708129882, | |
| "step": 245 | |
| }, | |
| { | |
| "epoch": 0.10597710894446799, | |
| "grad_norm": 0.2736397683620453, | |
| "learning_rate": 4.925702402662567e-05, | |
| "loss": 1.6181406021118163, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.10809665112335735, | |
| "grad_norm": 0.3378549814224243, | |
| "learning_rate": 4.921492046124017e-05, | |
| "loss": 1.6386375427246094, | |
| "step": 255 | |
| }, | |
| { | |
| "epoch": 0.11021619330224672, | |
| "grad_norm": 0.2974691092967987, | |
| "learning_rate": 4.917167557157854e-05, | |
| "loss": 1.6755428314208984, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.11233573548113608, | |
| "grad_norm": 0.32609519362449646, | |
| "learning_rate": 4.9127291395906515e-05, | |
| "loss": 1.6801631927490235, | |
| "step": 265 | |
| }, | |
| { | |
| "epoch": 0.11445527766002543, | |
| "grad_norm": 0.24628759920597076, | |
| "learning_rate": 4.9081770026187914e-05, | |
| "loss": 1.6314002990722656, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.1165748198389148, | |
| "grad_norm": 0.26794254779815674, | |
| "learning_rate": 4.9035113607986e-05, | |
| "loss": 1.5924458503723145, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 0.11869436201780416, | |
| "grad_norm": 0.2846653461456299, | |
| "learning_rate": 4.898732434036244e-05, | |
| "loss": 1.6042055130004882, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.12081390419669351, | |
| "grad_norm": 0.2645551562309265, | |
| "learning_rate": 4.893840447577356e-05, | |
| "loss": 1.621147918701172, | |
| "step": 285 | |
| }, | |
| { | |
| "epoch": 0.12293344637558287, | |
| "grad_norm": 0.30818238854408264, | |
| "learning_rate": 4.8888356319964254e-05, | |
| "loss": 1.5948877334594727, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.12505298855447222, | |
| "grad_norm": 0.2990403473377228, | |
| "learning_rate": 4.883718223185928e-05, | |
| "loss": 1.577207374572754, | |
| "step": 295 | |
| }, | |
| { | |
| "epoch": 0.1271725307333616, | |
| "grad_norm": 0.3122386932373047, | |
| "learning_rate": 4.878488462345206e-05, | |
| "loss": 1.6142730712890625, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.12929207291225095, | |
| "grad_norm": 0.3009199798107147, | |
| "learning_rate": 4.8731465959691016e-05, | |
| "loss": 1.6076532363891602, | |
| "step": 305 | |
| }, | |
| { | |
| "epoch": 0.13141161509114033, | |
| "grad_norm": 0.2573906183242798, | |
| "learning_rate": 4.8676928758363395e-05, | |
| "loss": 1.6024646759033203, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.13353115727002968, | |
| "grad_norm": 0.3035835027694702, | |
| "learning_rate": 4.862127558997658e-05, | |
| "loss": 1.639517593383789, | |
| "step": 315 | |
| }, | |
| { | |
| "epoch": 0.13565069944891903, | |
| "grad_norm": 0.2850736677646637, | |
| "learning_rate": 4.856450907763693e-05, | |
| "loss": 1.615229034423828, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.1377702416278084, | |
| "grad_norm": 0.30992159247398376, | |
| "learning_rate": 4.850663189692619e-05, | |
| "loss": 1.5542035102844238, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 0.13988978380669775, | |
| "grad_norm": 0.3271218538284302, | |
| "learning_rate": 4.844764677577531e-05, | |
| "loss": 1.597575855255127, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.1420093259855871, | |
| "grad_norm": 0.3106955289840698, | |
| "learning_rate": 4.838755649433592e-05, | |
| "loss": 1.5419929504394532, | |
| "step": 335 | |
| }, | |
| { | |
| "epoch": 0.14412886816447648, | |
| "grad_norm": 0.29612240195274353, | |
| "learning_rate": 4.83263638848493e-05, | |
| "loss": 1.536618137359619, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.14624841034336583, | |
| "grad_norm": 0.30592891573905945, | |
| "learning_rate": 4.826407183151284e-05, | |
| "loss": 1.5756213188171386, | |
| "step": 345 | |
| }, | |
| { | |
| "epoch": 0.14836795252225518, | |
| "grad_norm": 0.33485713601112366, | |
| "learning_rate": 4.820068327034415e-05, | |
| "loss": 1.592369270324707, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.15048749470114456, | |
| "grad_norm": 0.2578089237213135, | |
| "learning_rate": 4.8136201189042654e-05, | |
| "loss": 1.5892847061157227, | |
| "step": 355 | |
| }, | |
| { | |
| "epoch": 0.1526070368800339, | |
| "grad_norm": 0.2957204282283783, | |
| "learning_rate": 4.8070628626848735e-05, | |
| "loss": 1.605149269104004, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.15472657905892329, | |
| "grad_norm": 0.3159475326538086, | |
| "learning_rate": 4.800396867440057e-05, | |
| "loss": 1.587290096282959, | |
| "step": 365 | |
| }, | |
| { | |
| "epoch": 0.15684612123781264, | |
| "grad_norm": 0.34729769825935364, | |
| "learning_rate": 4.793622447358837e-05, | |
| "loss": 1.5416847229003907, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.15896566341670199, | |
| "grad_norm": 0.28477686643600464, | |
| "learning_rate": 4.786739921740636e-05, | |
| "loss": 1.5681907653808593, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 0.16108520559559136, | |
| "grad_norm": 0.29855579137802124, | |
| "learning_rate": 4.7797496149802256e-05, | |
| "loss": 1.5755675315856934, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.1632047477744807, | |
| "grad_norm": 0.2577330470085144, | |
| "learning_rate": 4.772651856552434e-05, | |
| "loss": 1.554960060119629, | |
| "step": 385 | |
| }, | |
| { | |
| "epoch": 0.16532428995337006, | |
| "grad_norm": 0.27646929025650024, | |
| "learning_rate": 4.765446980996622e-05, | |
| "loss": 1.5569202423095703, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.16744383213225944, | |
| "grad_norm": 0.28694725036621094, | |
| "learning_rate": 4.758135327900913e-05, | |
| "loss": 1.5758183479309082, | |
| "step": 395 | |
| }, | |
| { | |
| "epoch": 0.1695633743111488, | |
| "grad_norm": 0.3029310703277588, | |
| "learning_rate": 4.750717241886185e-05, | |
| "loss": 1.5932780265808106, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.17168291649003814, | |
| "grad_norm": 0.29603368043899536, | |
| "learning_rate": 4.7431930725898316e-05, | |
| "loss": 1.5787503242492675, | |
| "step": 405 | |
| }, | |
| { | |
| "epoch": 0.17380245866892752, | |
| "grad_norm": 0.27431562542915344, | |
| "learning_rate": 4.735563174649278e-05, | |
| "loss": 1.5800468444824218, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.17592200084781687, | |
| "grad_norm": 0.3525899648666382, | |
| "learning_rate": 4.727827907685271e-05, | |
| "loss": 1.6060297012329101, | |
| "step": 415 | |
| }, | |
| { | |
| "epoch": 0.17804154302670624, | |
| "grad_norm": 0.27093273401260376, | |
| "learning_rate": 4.719987636284924e-05, | |
| "loss": 1.5518156051635743, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.1801610852055956, | |
| "grad_norm": 0.3056223392486572, | |
| "learning_rate": 4.712042729984535e-05, | |
| "loss": 1.5476662635803222, | |
| "step": 425 | |
| }, | |
| { | |
| "epoch": 0.18228062738448494, | |
| "grad_norm": 0.337060809135437, | |
| "learning_rate": 4.703993563252172e-05, | |
| "loss": 1.5014581680297852, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.18440016956337432, | |
| "grad_norm": 0.30914735794067383, | |
| "learning_rate": 4.6958405154700154e-05, | |
| "loss": 1.559280776977539, | |
| "step": 435 | |
| }, | |
| { | |
| "epoch": 0.18651971174226367, | |
| "grad_norm": 0.30741581320762634, | |
| "learning_rate": 4.687583970916487e-05, | |
| "loss": 1.572512435913086, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.18863925392115302, | |
| "grad_norm": 0.2929278314113617, | |
| "learning_rate": 4.6792243187481276e-05, | |
| "loss": 1.5990943908691406, | |
| "step": 445 | |
| }, | |
| { | |
| "epoch": 0.1907587961000424, | |
| "grad_norm": 0.28744083642959595, | |
| "learning_rate": 4.670761952981264e-05, | |
| "loss": 1.5713401794433595, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.19287833827893175, | |
| "grad_norm": 0.3523147702217102, | |
| "learning_rate": 4.66219727247343e-05, | |
| "loss": 1.5218050003051757, | |
| "step": 455 | |
| }, | |
| { | |
| "epoch": 0.1949978804578211, | |
| "grad_norm": 0.3180658519268036, | |
| "learning_rate": 4.6535306809045706e-05, | |
| "loss": 1.5314140319824219, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.19711742263671048, | |
| "grad_norm": 0.309996098279953, | |
| "learning_rate": 4.644762586758018e-05, | |
| "loss": 1.528353500366211, | |
| "step": 465 | |
| }, | |
| { | |
| "epoch": 0.19923696481559983, | |
| "grad_norm": 0.3016054928302765, | |
| "learning_rate": 4.6358934033012324e-05, | |
| "loss": 1.530618953704834, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 0.2013565069944892, | |
| "grad_norm": 0.3114764988422394, | |
| "learning_rate": 4.626923548566328e-05, | |
| "loss": 1.5334035873413085, | |
| "step": 475 | |
| }, | |
| { | |
| "epoch": 0.20347604917337855, | |
| "grad_norm": 0.32303884625434875, | |
| "learning_rate": 4.6178534453303666e-05, | |
| "loss": 1.4971452713012696, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.2055955913522679, | |
| "grad_norm": 0.2908444106578827, | |
| "learning_rate": 4.608683521095436e-05, | |
| "loss": 1.5206520080566406, | |
| "step": 485 | |
| }, | |
| { | |
| "epoch": 0.20771513353115728, | |
| "grad_norm": 0.31474727392196655, | |
| "learning_rate": 4.599414208068495e-05, | |
| "loss": 1.5497597694396972, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 0.20983467571004663, | |
| "grad_norm": 0.28293105959892273, | |
| "learning_rate": 4.590045943141005e-05, | |
| "loss": 1.5145391464233398, | |
| "step": 495 | |
| }, | |
| { | |
| "epoch": 0.21195421788893598, | |
| "grad_norm": 0.3312336504459381, | |
| "learning_rate": 4.5805791678683356e-05, | |
| "loss": 1.5232769012451173, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.21407376006782536, | |
| "grad_norm": 0.3230695128440857, | |
| "learning_rate": 4.5710143284489574e-05, | |
| "loss": 1.5313811302185059, | |
| "step": 505 | |
| }, | |
| { | |
| "epoch": 0.2161933022467147, | |
| "grad_norm": 0.3052259683609009, | |
| "learning_rate": 4.561351875703406e-05, | |
| "loss": 1.5196274757385253, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 0.21831284442560406, | |
| "grad_norm": 0.29532384872436523, | |
| "learning_rate": 4.551592265053035e-05, | |
| "loss": 1.5265583038330077, | |
| "step": 515 | |
| }, | |
| { | |
| "epoch": 0.22043238660449344, | |
| "grad_norm": 0.3254035413265228, | |
| "learning_rate": 4.541735956498554e-05, | |
| "loss": 1.5671276092529296, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 0.22255192878338279, | |
| "grad_norm": 0.2924773693084717, | |
| "learning_rate": 4.531783414598344e-05, | |
| "loss": 1.4971593856811523, | |
| "step": 525 | |
| }, | |
| { | |
| "epoch": 0.22467147096227216, | |
| "grad_norm": 0.3421560823917389, | |
| "learning_rate": 4.5217351084465595e-05, | |
| "loss": 1.4904352188110352, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 0.2267910131411615, | |
| "grad_norm": 0.35325103998184204, | |
| "learning_rate": 4.511591511651023e-05, | |
| "loss": 1.4939480781555177, | |
| "step": 535 | |
| }, | |
| { | |
| "epoch": 0.22891055532005086, | |
| "grad_norm": 0.35536128282546997, | |
| "learning_rate": 4.5013531023109014e-05, | |
| "loss": 1.524225902557373, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 0.23103009749894024, | |
| "grad_norm": 0.26406627893447876, | |
| "learning_rate": 4.491020362994168e-05, | |
| "loss": 1.5059543609619142, | |
| "step": 545 | |
| }, | |
| { | |
| "epoch": 0.2331496396778296, | |
| "grad_norm": 0.337251752614975, | |
| "learning_rate": 4.4805937807148624e-05, | |
| "loss": 1.536135768890381, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.23526918185671894, | |
| "grad_norm": 0.3772444427013397, | |
| "learning_rate": 4.470073846910134e-05, | |
| "loss": 1.505116081237793, | |
| "step": 555 | |
| }, | |
| { | |
| "epoch": 0.23738872403560832, | |
| "grad_norm": 0.29593414068222046, | |
| "learning_rate": 4.459461057417078e-05, | |
| "loss": 1.534307861328125, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 0.23950826621449767, | |
| "grad_norm": 0.33957546949386597, | |
| "learning_rate": 4.448755912449367e-05, | |
| "loss": 1.4901400566101075, | |
| "step": 565 | |
| }, | |
| { | |
| "epoch": 0.24162780839338702, | |
| "grad_norm": 0.3504094183444977, | |
| "learning_rate": 4.4379589165736736e-05, | |
| "loss": 1.5271312713623046, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 0.2437473505722764, | |
| "grad_norm": 0.27951934933662415, | |
| "learning_rate": 4.4270705786858856e-05, | |
| "loss": 1.532707691192627, | |
| "step": 575 | |
| }, | |
| { | |
| "epoch": 0.24586689275116574, | |
| "grad_norm": 0.3029629588127136, | |
| "learning_rate": 4.416091411987128e-05, | |
| "loss": 1.5073426246643067, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 0.24798643493005512, | |
| "grad_norm": 0.3880954384803772, | |
| "learning_rate": 4.4050219339595654e-05, | |
| "loss": 1.4650937080383302, | |
| "step": 585 | |
| }, | |
| { | |
| "epoch": 0.25010597710894444, | |
| "grad_norm": 0.3036402463912964, | |
| "learning_rate": 4.393862666342017e-05, | |
| "loss": 1.4957613945007324, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 0.2522255192878338, | |
| "grad_norm": 0.3283858001232147, | |
| "learning_rate": 4.382614135105362e-05, | |
| "loss": 1.486557960510254, | |
| "step": 595 | |
| }, | |
| { | |
| "epoch": 0.2543450614667232, | |
| "grad_norm": 0.309688538312912, | |
| "learning_rate": 4.371276870427753e-05, | |
| "loss": 1.482859992980957, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.2564646036456125, | |
| "grad_norm": 0.3528952896595001, | |
| "learning_rate": 4.359851406669624e-05, | |
| "loss": 1.5194265365600585, | |
| "step": 605 | |
| }, | |
| { | |
| "epoch": 0.2585841458245019, | |
| "grad_norm": 0.3889414072036743, | |
| "learning_rate": 4.348338282348504e-05, | |
| "loss": 1.5033191680908202, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 0.2607036880033913, | |
| "grad_norm": 0.3206349313259125, | |
| "learning_rate": 4.336738040113638e-05, | |
| "loss": 1.512582492828369, | |
| "step": 615 | |
| }, | |
| { | |
| "epoch": 0.26282323018228065, | |
| "grad_norm": 0.32717958092689514, | |
| "learning_rate": 4.3250512267204066e-05, | |
| "loss": 1.4875495910644532, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 0.26494277236117, | |
| "grad_norm": 0.3436799645423889, | |
| "learning_rate": 4.3132783930045586e-05, | |
| "loss": 1.45267972946167, | |
| "step": 625 | |
| }, | |
| { | |
| "epoch": 0.26706231454005935, | |
| "grad_norm": 0.31014230847358704, | |
| "learning_rate": 4.301420093856247e-05, | |
| "loss": 1.4968060493469237, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 0.26918185671894873, | |
| "grad_norm": 0.301690012216568, | |
| "learning_rate": 4.289476888193875e-05, | |
| "loss": 1.4709239959716798, | |
| "step": 635 | |
| }, | |
| { | |
| "epoch": 0.27130139889783805, | |
| "grad_norm": 0.3319621980190277, | |
| "learning_rate": 4.2774493389377545e-05, | |
| "loss": 1.4488658905029297, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 0.27342094107672743, | |
| "grad_norm": 0.32282739877700806, | |
| "learning_rate": 4.2653380129835717e-05, | |
| "loss": 1.530065155029297, | |
| "step": 645 | |
| }, | |
| { | |
| "epoch": 0.2755404832556168, | |
| "grad_norm": 0.33359354734420776, | |
| "learning_rate": 4.253143481175667e-05, | |
| "loss": 1.4877628326416015, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.27766002543450613, | |
| "grad_norm": 0.3241269886493683, | |
| "learning_rate": 4.240866318280132e-05, | |
| "loss": 1.4772957801818847, | |
| "step": 655 | |
| }, | |
| { | |
| "epoch": 0.2797795676133955, | |
| "grad_norm": 0.3526093363761902, | |
| "learning_rate": 4.228507102957719e-05, | |
| "loss": 1.4755789756774902, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 0.2818991097922849, | |
| "grad_norm": 0.3347538709640503, | |
| "learning_rate": 4.216066417736563e-05, | |
| "loss": 1.4994415283203124, | |
| "step": 665 | |
| }, | |
| { | |
| "epoch": 0.2840186519711742, | |
| "grad_norm": 0.3497408926486969, | |
| "learning_rate": 4.2035448489847284e-05, | |
| "loss": 1.4655439376831054, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 0.2861381941500636, | |
| "grad_norm": 0.31812217831611633, | |
| "learning_rate": 4.1909429868825724e-05, | |
| "loss": 1.5188154220581054, | |
| "step": 675 | |
| }, | |
| { | |
| "epoch": 0.28825773632895296, | |
| "grad_norm": 0.33787310123443604, | |
| "learning_rate": 4.178261425394926e-05, | |
| "loss": 1.4583572387695312, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 0.2903772785078423, | |
| "grad_norm": 0.2770048975944519, | |
| "learning_rate": 4.1655007622431e-05, | |
| "loss": 1.5133068084716796, | |
| "step": 685 | |
| }, | |
| { | |
| "epoch": 0.29249682068673166, | |
| "grad_norm": 0.34181419014930725, | |
| "learning_rate": 4.15266159887671e-05, | |
| "loss": 1.4053072929382324, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 0.29461636286562104, | |
| "grad_norm": 0.29658618569374084, | |
| "learning_rate": 4.139744540445333e-05, | |
| "loss": 1.4844340324401855, | |
| "step": 695 | |
| }, | |
| { | |
| "epoch": 0.29673590504451036, | |
| "grad_norm": 0.37891045212745667, | |
| "learning_rate": 4.126750195769978e-05, | |
| "loss": 1.4527671813964844, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.29885544722339974, | |
| "grad_norm": 0.3364844024181366, | |
| "learning_rate": 4.1136791773144e-05, | |
| "loss": 1.4433229446411133, | |
| "step": 705 | |
| }, | |
| { | |
| "epoch": 0.3009749894022891, | |
| "grad_norm": 0.30445531010627747, | |
| "learning_rate": 4.1005321011562206e-05, | |
| "loss": 1.4879029273986817, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 0.30309453158117844, | |
| "grad_norm": 0.33308008313179016, | |
| "learning_rate": 4.0873095869579006e-05, | |
| "loss": 1.4281834602355956, | |
| "step": 715 | |
| }, | |
| { | |
| "epoch": 0.3052140737600678, | |
| "grad_norm": 0.3354891538619995, | |
| "learning_rate": 4.0740122579375286e-05, | |
| "loss": 1.4260257720947265, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 0.3073336159389572, | |
| "grad_norm": 0.37197941541671753, | |
| "learning_rate": 4.060640740839448e-05, | |
| "loss": 1.4761240005493164, | |
| "step": 725 | |
| }, | |
| { | |
| "epoch": 0.30945315811784657, | |
| "grad_norm": 0.3524804413318634, | |
| "learning_rate": 4.047195665904716e-05, | |
| "loss": 1.434666061401367, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 0.3115727002967359, | |
| "grad_norm": 0.3222479820251465, | |
| "learning_rate": 4.033677666841399e-05, | |
| "loss": 1.540536880493164, | |
| "step": 735 | |
| }, | |
| { | |
| "epoch": 0.31369224247562527, | |
| "grad_norm": 0.3168013095855713, | |
| "learning_rate": 4.020087380794703e-05, | |
| "loss": 1.4318754196166992, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 0.31581178465451465, | |
| "grad_norm": 0.3820805549621582, | |
| "learning_rate": 4.0064254483169436e-05, | |
| "loss": 1.498759651184082, | |
| "step": 745 | |
| }, | |
| { | |
| "epoch": 0.31793132683340397, | |
| "grad_norm": 0.2964789569377899, | |
| "learning_rate": 3.992692513337356e-05, | |
| "loss": 1.527662754058838, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.32005086901229335, | |
| "grad_norm": 0.3057907521724701, | |
| "learning_rate": 3.9788892231317426e-05, | |
| "loss": 1.4950136184692382, | |
| "step": 755 | |
| }, | |
| { | |
| "epoch": 0.3221704111911827, | |
| "grad_norm": 0.3189552426338196, | |
| "learning_rate": 3.9650162282919655e-05, | |
| "loss": 1.4683143615722656, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 0.32428995337007205, | |
| "grad_norm": 0.30757245421409607, | |
| "learning_rate": 3.951074182695284e-05, | |
| "loss": 1.4613779067993165, | |
| "step": 765 | |
| }, | |
| { | |
| "epoch": 0.3264094955489614, | |
| "grad_norm": 0.32456260919570923, | |
| "learning_rate": 3.9370637434735296e-05, | |
| "loss": 1.4599506378173828, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 0.3285290377278508, | |
| "grad_norm": 0.3549198806285858, | |
| "learning_rate": 3.922985570982143e-05, | |
| "loss": 1.5035252571105957, | |
| "step": 775 | |
| }, | |
| { | |
| "epoch": 0.3306485799067401, | |
| "grad_norm": 0.39085710048675537, | |
| "learning_rate": 3.908840328769039e-05, | |
| "loss": 1.4349940299987793, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 0.3327681220856295, | |
| "grad_norm": 0.30678218603134155, | |
| "learning_rate": 3.8946286835433385e-05, | |
| "loss": 1.4624643325805664, | |
| "step": 785 | |
| }, | |
| { | |
| "epoch": 0.3348876642645189, | |
| "grad_norm": 0.30047479271888733, | |
| "learning_rate": 3.880351305143944e-05, | |
| "loss": 1.4413408279418944, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 0.3370072064434082, | |
| "grad_norm": 0.3476318418979645, | |
| "learning_rate": 3.8660088665079625e-05, | |
| "loss": 1.4477258682250977, | |
| "step": 795 | |
| }, | |
| { | |
| "epoch": 0.3391267486222976, | |
| "grad_norm": 0.3539160192012787, | |
| "learning_rate": 3.851602043638994e-05, | |
| "loss": 1.4559927940368653, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.34124629080118696, | |
| "grad_norm": 0.34642767906188965, | |
| "learning_rate": 3.837131515575267e-05, | |
| "loss": 1.5193279266357422, | |
| "step": 805 | |
| }, | |
| { | |
| "epoch": 0.3433658329800763, | |
| "grad_norm": 0.31490349769592285, | |
| "learning_rate": 3.822597964357632e-05, | |
| "loss": 1.4556001663208007, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 0.34548537515896566, | |
| "grad_norm": 0.29931655526161194, | |
| "learning_rate": 3.808002074997418e-05, | |
| "loss": 1.4616708755493164, | |
| "step": 815 | |
| }, | |
| { | |
| "epoch": 0.34760491733785503, | |
| "grad_norm": 0.33116403222084045, | |
| "learning_rate": 3.793344535444142e-05, | |
| "loss": 1.4830537796020509, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 0.34972445951674436, | |
| "grad_norm": 0.30214810371398926, | |
| "learning_rate": 3.778626036553087e-05, | |
| "loss": 1.4755599975585938, | |
| "step": 825 | |
| }, | |
| { | |
| "epoch": 0.35184400169563373, | |
| "grad_norm": 0.3481181859970093, | |
| "learning_rate": 3.7638472720527396e-05, | |
| "loss": 1.4625129699707031, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 0.3539635438745231, | |
| "grad_norm": 0.3253694176673889, | |
| "learning_rate": 3.7490089385120875e-05, | |
| "loss": 1.4626951217651367, | |
| "step": 835 | |
| }, | |
| { | |
| "epoch": 0.3560830860534125, | |
| "grad_norm": 0.3241185247898102, | |
| "learning_rate": 3.7341117353077966e-05, | |
| "loss": 1.4410079956054687, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 0.3582026282323018, | |
| "grad_norm": 0.35993415117263794, | |
| "learning_rate": 3.719156364591239e-05, | |
| "loss": 1.4571613311767577, | |
| "step": 845 | |
| }, | |
| { | |
| "epoch": 0.3603221704111912, | |
| "grad_norm": 0.3607555627822876, | |
| "learning_rate": 3.704143531255405e-05, | |
| "loss": 1.4589347839355469, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 0.36244171259008057, | |
| "grad_norm": 0.39332181215286255, | |
| "learning_rate": 3.689073942901674e-05, | |
| "loss": 1.4809041023254395, | |
| "step": 855 | |
| }, | |
| { | |
| "epoch": 0.3645612547689699, | |
| "grad_norm": 0.28656336665153503, | |
| "learning_rate": 3.673948309806466e-05, | |
| "loss": 1.4662458419799804, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 0.36668079694785927, | |
| "grad_norm": 0.30544522404670715, | |
| "learning_rate": 3.658767344887764e-05, | |
| "loss": 1.4558723449707032, | |
| "step": 865 | |
| }, | |
| { | |
| "epoch": 0.36880033912674864, | |
| "grad_norm": 0.36737823486328125, | |
| "learning_rate": 3.643531763671511e-05, | |
| "loss": 1.4233319282531738, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 0.37091988130563797, | |
| "grad_norm": 0.35188379883766174, | |
| "learning_rate": 3.6282422842578845e-05, | |
| "loss": 1.4094632148742676, | |
| "step": 875 | |
| }, | |
| { | |
| "epoch": 0.37303942348452734, | |
| "grad_norm": 0.32954302430152893, | |
| "learning_rate": 3.612899627287452e-05, | |
| "loss": 1.484145450592041, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 0.3751589656634167, | |
| "grad_norm": 0.31332382559776306, | |
| "learning_rate": 3.5975045159072066e-05, | |
| "loss": 1.443262481689453, | |
| "step": 885 | |
| }, | |
| { | |
| "epoch": 0.37727850784230604, | |
| "grad_norm": 0.305828332901001, | |
| "learning_rate": 3.582057675736474e-05, | |
| "loss": 1.4672741889953613, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 0.3793980500211954, | |
| "grad_norm": 0.3055178225040436, | |
| "learning_rate": 3.566559834832726e-05, | |
| "loss": 1.4507486343383789, | |
| "step": 895 | |
| }, | |
| { | |
| "epoch": 0.3815175922000848, | |
| "grad_norm": 0.3712921738624573, | |
| "learning_rate": 3.5510117236572505e-05, | |
| "loss": 1.4402458190917968, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.3836371343789741, | |
| "grad_norm": 0.32003694772720337, | |
| "learning_rate": 3.535414075040733e-05, | |
| "loss": 1.477198028564453, | |
| "step": 905 | |
| }, | |
| { | |
| "epoch": 0.3857566765578635, | |
| "grad_norm": 0.3671673536300659, | |
| "learning_rate": 3.51976762414871e-05, | |
| "loss": 1.4311531066894532, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 0.3878762187367529, | |
| "grad_norm": 0.36391517519950867, | |
| "learning_rate": 3.5040731084469225e-05, | |
| "loss": 1.4245489120483399, | |
| "step": 915 | |
| }, | |
| { | |
| "epoch": 0.3899957609156422, | |
| "grad_norm": 0.31420671939849854, | |
| "learning_rate": 3.4883312676665536e-05, | |
| "loss": 1.4455132484436035, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 0.3921153030945316, | |
| "grad_norm": 0.30178841948509216, | |
| "learning_rate": 3.472542843769365e-05, | |
| "loss": 1.4458664894104003, | |
| "step": 925 | |
| }, | |
| { | |
| "epoch": 0.39423484527342095, | |
| "grad_norm": 0.33379727602005005, | |
| "learning_rate": 3.456708580912725e-05, | |
| "loss": 1.4618202209472657, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 0.3963543874523103, | |
| "grad_norm": 0.36524608731269836, | |
| "learning_rate": 3.4408292254145316e-05, | |
| "loss": 1.465505599975586, | |
| "step": 935 | |
| }, | |
| { | |
| "epoch": 0.39847392963119965, | |
| "grad_norm": 0.38167238235473633, | |
| "learning_rate": 3.424905525718044e-05, | |
| "loss": 1.4671090126037598, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 0.40059347181008903, | |
| "grad_norm": 0.316228985786438, | |
| "learning_rate": 3.408938232356596e-05, | |
| "loss": 1.4349556922912599, | |
| "step": 945 | |
| }, | |
| { | |
| "epoch": 0.4027130139889784, | |
| "grad_norm": 0.38427093625068665, | |
| "learning_rate": 3.392928097918229e-05, | |
| "loss": 1.4386041641235352, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 0.40483255616786773, | |
| "grad_norm": 0.31572654843330383, | |
| "learning_rate": 3.376875877010215e-05, | |
| "loss": 1.4454322814941407, | |
| "step": 955 | |
| }, | |
| { | |
| "epoch": 0.4069520983467571, | |
| "grad_norm": 0.32369595766067505, | |
| "learning_rate": 3.360782326223493e-05, | |
| "loss": 1.4582254409790039, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 0.4090716405256465, | |
| "grad_norm": 0.3515062630176544, | |
| "learning_rate": 3.344648204097009e-05, | |
| "loss": 1.4595697402954102, | |
| "step": 965 | |
| }, | |
| { | |
| "epoch": 0.4111911827045358, | |
| "grad_norm": 0.323845773935318, | |
| "learning_rate": 3.328474271081959e-05, | |
| "loss": 1.4764064788818358, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 0.4133107248834252, | |
| "grad_norm": 0.3325927257537842, | |
| "learning_rate": 3.31226128950595e-05, | |
| "loss": 1.390408420562744, | |
| "step": 975 | |
| }, | |
| { | |
| "epoch": 0.41543026706231456, | |
| "grad_norm": 0.4071347713470459, | |
| "learning_rate": 3.296010023537072e-05, | |
| "loss": 1.473273754119873, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 0.4175498092412039, | |
| "grad_norm": 0.32389792799949646, | |
| "learning_rate": 3.2797212391478724e-05, | |
| "loss": 1.4286162376403808, | |
| "step": 985 | |
| }, | |
| { | |
| "epoch": 0.41966935142009326, | |
| "grad_norm": 0.32580631971359253, | |
| "learning_rate": 3.263395704079262e-05, | |
| "loss": 1.4330024719238281, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 0.42178889359898264, | |
| "grad_norm": 0.40598928928375244, | |
| "learning_rate": 3.247034187804323e-05, | |
| "loss": 1.4660273551940919, | |
| "step": 995 | |
| }, | |
| { | |
| "epoch": 0.42390843577787196, | |
| "grad_norm": 0.3778379559516907, | |
| "learning_rate": 3.230637461492043e-05, | |
| "loss": 1.4563278198242187, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.42602797795676134, | |
| "grad_norm": 0.361782431602478, | |
| "learning_rate": 3.21420629797097e-05, | |
| "loss": 1.4022197723388672, | |
| "step": 1005 | |
| }, | |
| { | |
| "epoch": 0.4281475201356507, | |
| "grad_norm": 0.3978794813156128, | |
| "learning_rate": 3.1977414716927834e-05, | |
| "loss": 1.4684802055358888, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 0.43026706231454004, | |
| "grad_norm": 0.3353826105594635, | |
| "learning_rate": 3.1812437586957906e-05, | |
| "loss": 1.4319665908813477, | |
| "step": 1015 | |
| }, | |
| { | |
| "epoch": 0.4323866044934294, | |
| "grad_norm": 0.33617663383483887, | |
| "learning_rate": 3.164713936568355e-05, | |
| "loss": 1.4109307289123536, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 0.4345061466723188, | |
| "grad_norm": 0.32695916295051575, | |
| "learning_rate": 3.148152784412242e-05, | |
| "loss": 1.3964502334594726, | |
| "step": 1025 | |
| }, | |
| { | |
| "epoch": 0.4366256888512081, | |
| "grad_norm": 0.30757060647010803, | |
| "learning_rate": 3.131561082805898e-05, | |
| "loss": 1.4351747512817383, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 0.4387452310300975, | |
| "grad_norm": 0.2952488660812378, | |
| "learning_rate": 3.114939613767659e-05, | |
| "loss": 1.4623651504516602, | |
| "step": 1035 | |
| }, | |
| { | |
| "epoch": 0.44086477320898687, | |
| "grad_norm": 0.4161355197429657, | |
| "learning_rate": 3.098289160718895e-05, | |
| "loss": 1.430048942565918, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 0.4429843153878762, | |
| "grad_norm": 0.3415408730506897, | |
| "learning_rate": 3.081610508447078e-05, | |
| "loss": 1.4523229598999023, | |
| "step": 1045 | |
| }, | |
| { | |
| "epoch": 0.44510385756676557, | |
| "grad_norm": 0.30131658911705017, | |
| "learning_rate": 3.0649044430688015e-05, | |
| "loss": 1.4635979652404785, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 0.44722339974565495, | |
| "grad_norm": 0.4548901617527008, | |
| "learning_rate": 3.04817175199272e-05, | |
| "loss": 1.4288576126098633, | |
| "step": 1055 | |
| }, | |
| { | |
| "epoch": 0.4493429419245443, | |
| "grad_norm": 0.37679925560951233, | |
| "learning_rate": 3.0314132238824415e-05, | |
| "loss": 1.4383837699890136, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 0.45146248410343365, | |
| "grad_norm": 0.33068764209747314, | |
| "learning_rate": 3.0146296486193543e-05, | |
| "loss": 1.4239488601684571, | |
| "step": 1065 | |
| }, | |
| { | |
| "epoch": 0.453582026282323, | |
| "grad_norm": 0.3112558126449585, | |
| "learning_rate": 2.9978218172653937e-05, | |
| "loss": 1.3929532051086426, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 0.4557015684612124, | |
| "grad_norm": 0.37434667348861694, | |
| "learning_rate": 2.9809905220257627e-05, | |
| "loss": 1.3818506240844726, | |
| "step": 1075 | |
| }, | |
| { | |
| "epoch": 0.4578211106401017, | |
| "grad_norm": 0.4044923782348633, | |
| "learning_rate": 2.9641365562115887e-05, | |
| "loss": 1.4261232376098634, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 0.4599406528189911, | |
| "grad_norm": 0.36570364236831665, | |
| "learning_rate": 2.9472607142025333e-05, | |
| "loss": 1.426250171661377, | |
| "step": 1085 | |
| }, | |
| { | |
| "epoch": 0.4620601949978805, | |
| "grad_norm": 0.32114356756210327, | |
| "learning_rate": 2.9303637914093528e-05, | |
| "loss": 1.4296778678894042, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 0.4641797371767698, | |
| "grad_norm": 0.4690103530883789, | |
| "learning_rate": 2.9134465842364035e-05, | |
| "loss": 1.4105006217956544, | |
| "step": 1095 | |
| }, | |
| { | |
| "epoch": 0.4662992793556592, | |
| "grad_norm": 0.30322685837745667, | |
| "learning_rate": 2.8965098900441084e-05, | |
| "loss": 1.430894660949707, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.46841882153454856, | |
| "grad_norm": 0.35242918133735657, | |
| "learning_rate": 2.879554507111376e-05, | |
| "loss": 1.401798152923584, | |
| "step": 1105 | |
| }, | |
| { | |
| "epoch": 0.4705383637134379, | |
| "grad_norm": 0.3394680321216583, | |
| "learning_rate": 2.8625812345979714e-05, | |
| "loss": 1.4297598838806151, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 0.47265790589232726, | |
| "grad_norm": 0.46491190791130066, | |
| "learning_rate": 2.84559087250685e-05, | |
| "loss": 1.3740580558776856, | |
| "step": 1115 | |
| }, | |
| { | |
| "epoch": 0.47477744807121663, | |
| "grad_norm": 0.35912927985191345, | |
| "learning_rate": 2.8285842216464543e-05, | |
| "loss": 1.4331014633178711, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 0.47689699025010596, | |
| "grad_norm": 0.35514596104621887, | |
| "learning_rate": 2.811562083592965e-05, | |
| "loss": 1.3862857818603516, | |
| "step": 1125 | |
| }, | |
| { | |
| "epoch": 0.47901653242899533, | |
| "grad_norm": 0.3689481317996979, | |
| "learning_rate": 2.794525260652524e-05, | |
| "loss": 1.4163013458251954, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 0.4811360746078847, | |
| "grad_norm": 0.3514903783798218, | |
| "learning_rate": 2.777474555823417e-05, | |
| "loss": 1.4395673751831055, | |
| "step": 1135 | |
| }, | |
| { | |
| "epoch": 0.48325561678677403, | |
| "grad_norm": 0.3377491235733032, | |
| "learning_rate": 2.760410772758225e-05, | |
| "loss": 1.3892290115356445, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 0.4853751589656634, | |
| "grad_norm": 0.2856961786746979, | |
| "learning_rate": 2.7433347157259482e-05, | |
| "loss": 1.4275176048278808, | |
| "step": 1145 | |
| }, | |
| { | |
| "epoch": 0.4874947011445528, | |
| "grad_norm": 0.43130624294281006, | |
| "learning_rate": 2.726247189574095e-05, | |
| "loss": 1.3762901306152344, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 0.4896142433234421, | |
| "grad_norm": 0.4302266240119934, | |
| "learning_rate": 2.7091489996907516e-05, | |
| "loss": 1.4246488571166993, | |
| "step": 1155 | |
| }, | |
| { | |
| "epoch": 0.4917337855023315, | |
| "grad_norm": 0.41944217681884766, | |
| "learning_rate": 2.6920409519666174e-05, | |
| "loss": 1.3586502075195312, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 0.49385332768122087, | |
| "grad_norm": 0.4111734628677368, | |
| "learning_rate": 2.6749238527570224e-05, | |
| "loss": 1.3931678771972655, | |
| "step": 1165 | |
| }, | |
| { | |
| "epoch": 0.49597286986011024, | |
| "grad_norm": 0.32171934843063354, | |
| "learning_rate": 2.6577985088439212e-05, | |
| "loss": 1.4106029510498046, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 0.49809241203899957, | |
| "grad_norm": 0.36163389682769775, | |
| "learning_rate": 2.6406657273978673e-05, | |
| "loss": 1.41438570022583, | |
| "step": 1175 | |
| }, | |
| { | |
| "epoch": 0.5002119542178889, | |
| "grad_norm": 0.33984363079071045, | |
| "learning_rate": 2.6235263159399683e-05, | |
| "loss": 1.4315521240234375, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 0.5023314963967783, | |
| "grad_norm": 0.2997186779975891, | |
| "learning_rate": 2.606381082303824e-05, | |
| "loss": 1.4000054359436036, | |
| "step": 1185 | |
| }, | |
| { | |
| "epoch": 0.5044510385756676, | |
| "grad_norm": 0.35598525404930115, | |
| "learning_rate": 2.5892308345974515e-05, | |
| "loss": 1.447204303741455, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 0.506570580754557, | |
| "grad_norm": 0.41978952288627625, | |
| "learning_rate": 2.5720763811651973e-05, | |
| "loss": 1.388357925415039, | |
| "step": 1195 | |
| }, | |
| { | |
| "epoch": 0.5086901229334464, | |
| "grad_norm": 0.33993276953697205, | |
| "learning_rate": 2.554918530549637e-05, | |
| "loss": 1.4028491973876953, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.5108096651123357, | |
| "grad_norm": 0.34009379148483276, | |
| "learning_rate": 2.5377580914534647e-05, | |
| "loss": 1.3822345733642578, | |
| "step": 1205 | |
| }, | |
| { | |
| "epoch": 0.512929207291225, | |
| "grad_norm": 0.34809765219688416, | |
| "learning_rate": 2.520595872701379e-05, | |
| "loss": 1.4081857681274415, | |
| "step": 1210 | |
| }, | |
| { | |
| "epoch": 0.5150487494701145, | |
| "grad_norm": 0.32554712891578674, | |
| "learning_rate": 2.503432683201959e-05, | |
| "loss": 1.397074031829834, | |
| "step": 1215 | |
| }, | |
| { | |
| "epoch": 0.5171682916490038, | |
| "grad_norm": 0.41591504216194153, | |
| "learning_rate": 2.4862693319095366e-05, | |
| "loss": 1.3957890510559081, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 0.5192878338278932, | |
| "grad_norm": 0.3247075378894806, | |
| "learning_rate": 2.4691066277860717e-05, | |
| "loss": 1.4188478469848633, | |
| "step": 1225 | |
| }, | |
| { | |
| "epoch": 0.5214073760067826, | |
| "grad_norm": 0.3462647497653961, | |
| "learning_rate": 2.4519453797630187e-05, | |
| "loss": 1.401095199584961, | |
| "step": 1230 | |
| }, | |
| { | |
| "epoch": 0.5235269181856719, | |
| "grad_norm": 0.385743647813797, | |
| "learning_rate": 2.434786396703204e-05, | |
| "loss": 1.421084213256836, | |
| "step": 1235 | |
| }, | |
| { | |
| "epoch": 0.5256464603645613, | |
| "grad_norm": 0.3461378812789917, | |
| "learning_rate": 2.4176304873626985e-05, | |
| "loss": 1.386674976348877, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 0.5277660025434506, | |
| "grad_norm": 0.36817705631256104, | |
| "learning_rate": 2.400478460352697e-05, | |
| "loss": 1.4099712371826172, | |
| "step": 1245 | |
| }, | |
| { | |
| "epoch": 0.52988554472234, | |
| "grad_norm": 0.31477874517440796, | |
| "learning_rate": 2.3833311241014116e-05, | |
| "loss": 1.3745742797851563, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 0.5320050869012294, | |
| "grad_norm": 0.3593701422214508, | |
| "learning_rate": 2.3661892868159622e-05, | |
| "loss": 1.3869762420654297, | |
| "step": 1255 | |
| }, | |
| { | |
| "epoch": 0.5341246290801187, | |
| "grad_norm": 0.3667784035205841, | |
| "learning_rate": 2.3490537564442847e-05, | |
| "loss": 1.4052553176879883, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 0.536244171259008, | |
| "grad_norm": 0.3318742513656616, | |
| "learning_rate": 2.331925340637053e-05, | |
| "loss": 1.3741485595703125, | |
| "step": 1265 | |
| }, | |
| { | |
| "epoch": 0.5383637134378975, | |
| "grad_norm": 0.33908259868621826, | |
| "learning_rate": 2.3148048467096075e-05, | |
| "loss": 1.4085769653320312, | |
| "step": 1270 | |
| }, | |
| { | |
| "epoch": 0.5404832556167868, | |
| "grad_norm": 0.3236868679523468, | |
| "learning_rate": 2.2976930816039065e-05, | |
| "loss": 1.4606010437011718, | |
| "step": 1275 | |
| }, | |
| { | |
| "epoch": 0.5426027977956761, | |
| "grad_norm": 0.3292027711868286, | |
| "learning_rate": 2.280590851850493e-05, | |
| "loss": 1.3969609260559082, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 0.5447223399745655, | |
| "grad_norm": 0.3910142779350281, | |
| "learning_rate": 2.2634989635304766e-05, | |
| "loss": 1.3941945075988769, | |
| "step": 1285 | |
| }, | |
| { | |
| "epoch": 0.5468418821534549, | |
| "grad_norm": 0.35102784633636475, | |
| "learning_rate": 2.2464182222375464e-05, | |
| "loss": 1.365629005432129, | |
| "step": 1290 | |
| }, | |
| { | |
| "epoch": 0.5489614243323442, | |
| "grad_norm": 0.3326789438724518, | |
| "learning_rate": 2.2293494330399942e-05, | |
| "loss": 1.4161523818969726, | |
| "step": 1295 | |
| }, | |
| { | |
| "epoch": 0.5510809665112336, | |
| "grad_norm": 0.29885074496269226, | |
| "learning_rate": 2.2122934004427754e-05, | |
| "loss": 1.4199028015136719, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 0.5532005086901229, | |
| "grad_norm": 0.37626752257347107, | |
| "learning_rate": 2.1952509283495844e-05, | |
| "loss": 1.4125182151794433, | |
| "step": 1305 | |
| }, | |
| { | |
| "epoch": 0.5553200508690123, | |
| "grad_norm": 0.4020308554172516, | |
| "learning_rate": 2.1782228200249705e-05, | |
| "loss": 1.4047032356262208, | |
| "step": 1310 | |
| }, | |
| { | |
| "epoch": 0.5574395930479017, | |
| "grad_norm": 0.3470950722694397, | |
| "learning_rate": 2.1612098780564714e-05, | |
| "loss": 1.4171363830566406, | |
| "step": 1315 | |
| }, | |
| { | |
| "epoch": 0.559559135226791, | |
| "grad_norm": 0.2894577980041504, | |
| "learning_rate": 2.1442129043167874e-05, | |
| "loss": 1.4088871002197265, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 0.5616786774056803, | |
| "grad_norm": 0.32362833619117737, | |
| "learning_rate": 2.1272326999259893e-05, | |
| "loss": 1.3945621490478515, | |
| "step": 1325 | |
| }, | |
| { | |
| "epoch": 0.5637982195845698, | |
| "grad_norm": 0.40644723176956177, | |
| "learning_rate": 2.1102700652137527e-05, | |
| "loss": 1.3447763442993164, | |
| "step": 1330 | |
| }, | |
| { | |
| "epoch": 0.5659177617634591, | |
| "grad_norm": 0.3256324231624603, | |
| "learning_rate": 2.0933257996816427e-05, | |
| "loss": 1.396995449066162, | |
| "step": 1335 | |
| }, | |
| { | |
| "epoch": 0.5680373039423484, | |
| "grad_norm": 0.3380388915538788, | |
| "learning_rate": 2.0764007019654274e-05, | |
| "loss": 1.3864919662475585, | |
| "step": 1340 | |
| }, | |
| { | |
| "epoch": 0.5701568461212378, | |
| "grad_norm": 0.34916234016418457, | |
| "learning_rate": 2.059495569797435e-05, | |
| "loss": 1.3748540878295898, | |
| "step": 1345 | |
| }, | |
| { | |
| "epoch": 0.5722763883001272, | |
| "grad_norm": 0.41968318819999695, | |
| "learning_rate": 2.0426111999689566e-05, | |
| "loss": 1.3800813674926757, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 0.5743959304790165, | |
| "grad_norm": 0.33327922224998474, | |
| "learning_rate": 2.0257483882926908e-05, | |
| "loss": 1.416623306274414, | |
| "step": 1355 | |
| }, | |
| { | |
| "epoch": 0.5765154726579059, | |
| "grad_norm": 0.35726067423820496, | |
| "learning_rate": 2.0089079295652306e-05, | |
| "loss": 1.3936123847961426, | |
| "step": 1360 | |
| }, | |
| { | |
| "epoch": 0.5786350148367952, | |
| "grad_norm": 0.3922523558139801, | |
| "learning_rate": 1.99209061752961e-05, | |
| "loss": 1.3783675193786622, | |
| "step": 1365 | |
| }, | |
| { | |
| "epoch": 0.5807545570156846, | |
| "grad_norm": 0.36284339427948, | |
| "learning_rate": 1.9752972448378814e-05, | |
| "loss": 1.390543556213379, | |
| "step": 1370 | |
| }, | |
| { | |
| "epoch": 0.582874099194574, | |
| "grad_norm": 0.3313068449497223, | |
| "learning_rate": 1.958528603013767e-05, | |
| "loss": 1.4089311599731444, | |
| "step": 1375 | |
| }, | |
| { | |
| "epoch": 0.5849936413734633, | |
| "grad_norm": 0.34787797927856445, | |
| "learning_rate": 1.941785482415346e-05, | |
| "loss": 1.4137891769409179, | |
| "step": 1380 | |
| }, | |
| { | |
| "epoch": 0.5871131835523526, | |
| "grad_norm": 0.3903313875198364, | |
| "learning_rate": 1.925068672197799e-05, | |
| "loss": 1.410212230682373, | |
| "step": 1385 | |
| }, | |
| { | |
| "epoch": 0.5892327257312421, | |
| "grad_norm": 0.3307342529296875, | |
| "learning_rate": 1.908378960276221e-05, | |
| "loss": 1.4303800582885742, | |
| "step": 1390 | |
| }, | |
| { | |
| "epoch": 0.5913522679101314, | |
| "grad_norm": 0.39230242371559143, | |
| "learning_rate": 1.891717133288479e-05, | |
| "loss": 1.3843820571899415, | |
| "step": 1395 | |
| }, | |
| { | |
| "epoch": 0.5934718100890207, | |
| "grad_norm": 0.37388232350349426, | |
| "learning_rate": 1.875083976558136e-05, | |
| "loss": 1.3867924690246582, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.5955913522679102, | |
| "grad_norm": 0.33515098690986633, | |
| "learning_rate": 1.858480274057438e-05, | |
| "loss": 1.35939302444458, | |
| "step": 1405 | |
| }, | |
| { | |
| "epoch": 0.5977108944467995, | |
| "grad_norm": 0.3862181007862091, | |
| "learning_rate": 1.84190680837036e-05, | |
| "loss": 1.3928054809570312, | |
| "step": 1410 | |
| }, | |
| { | |
| "epoch": 0.5998304366256888, | |
| "grad_norm": 0.3670431673526764, | |
| "learning_rate": 1.8253643606557243e-05, | |
| "loss": 1.4012739181518554, | |
| "step": 1415 | |
| }, | |
| { | |
| "epoch": 0.6019499788045782, | |
| "grad_norm": 0.38886359333992004, | |
| "learning_rate": 1.808853710610379e-05, | |
| "loss": 1.446358871459961, | |
| "step": 1420 | |
| }, | |
| { | |
| "epoch": 0.6040695209834676, | |
| "grad_norm": 0.3320871889591217, | |
| "learning_rate": 1.7923756364324492e-05, | |
| "loss": 1.4594743728637696, | |
| "step": 1425 | |
| }, | |
| { | |
| "epoch": 0.6061890631623569, | |
| "grad_norm": 0.41714829206466675, | |
| "learning_rate": 1.7759309147846588e-05, | |
| "loss": 1.4263699531555176, | |
| "step": 1430 | |
| }, | |
| { | |
| "epoch": 0.6083086053412463, | |
| "grad_norm": 0.36470603942871094, | |
| "learning_rate": 1.7595203207577244e-05, | |
| "loss": 1.4173831939697266, | |
| "step": 1435 | |
| }, | |
| { | |
| "epoch": 0.6104281475201356, | |
| "grad_norm": 0.318233460187912, | |
| "learning_rate": 1.7431446278338197e-05, | |
| "loss": 1.4444591522216796, | |
| "step": 1440 | |
| }, | |
| { | |
| "epoch": 0.612547689699025, | |
| "grad_norm": 0.3951033651828766, | |
| "learning_rate": 1.7268046078501242e-05, | |
| "loss": 1.3867953300476075, | |
| "step": 1445 | |
| }, | |
| { | |
| "epoch": 0.6146672318779144, | |
| "grad_norm": 0.3975803256034851, | |
| "learning_rate": 1.710501030962438e-05, | |
| "loss": 1.3645260810852051, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 0.6167867740568037, | |
| "grad_norm": 0.3299221992492676, | |
| "learning_rate": 1.694234665608887e-05, | |
| "loss": 1.4172224044799804, | |
| "step": 1455 | |
| }, | |
| { | |
| "epoch": 0.6189063162356931, | |
| "grad_norm": 0.4213244318962097, | |
| "learning_rate": 1.6780062784737026e-05, | |
| "loss": 1.3753522872924804, | |
| "step": 1460 | |
| }, | |
| { | |
| "epoch": 0.6210258584145825, | |
| "grad_norm": 0.39747563004493713, | |
| "learning_rate": 1.6618166344510834e-05, | |
| "loss": 1.3593328475952149, | |
| "step": 1465 | |
| }, | |
| { | |
| "epoch": 0.6231454005934718, | |
| "grad_norm": 0.3689986765384674, | |
| "learning_rate": 1.645666496609146e-05, | |
| "loss": 1.4128448486328125, | |
| "step": 1470 | |
| }, | |
| { | |
| "epoch": 0.6252649427723612, | |
| "grad_norm": 0.363003134727478, | |
| "learning_rate": 1.6295566261539587e-05, | |
| "loss": 1.3633504867553712, | |
| "step": 1475 | |
| }, | |
| { | |
| "epoch": 0.6273844849512505, | |
| "grad_norm": 0.39896801114082336, | |
| "learning_rate": 1.613487782393661e-05, | |
| "loss": 1.3668333053588868, | |
| "step": 1480 | |
| }, | |
| { | |
| "epoch": 0.6295040271301399, | |
| "grad_norm": 0.3726200759410858, | |
| "learning_rate": 1.5974607227026795e-05, | |
| "loss": 1.340334129333496, | |
| "step": 1485 | |
| }, | |
| { | |
| "epoch": 0.6316235693090293, | |
| "grad_norm": 0.3538936972618103, | |
| "learning_rate": 1.581476202486026e-05, | |
| "loss": 1.348178768157959, | |
| "step": 1490 | |
| }, | |
| { | |
| "epoch": 0.6337431114879186, | |
| "grad_norm": 0.3540723919868469, | |
| "learning_rate": 1.5655349751436964e-05, | |
| "loss": 1.3867548942565917, | |
| "step": 1495 | |
| }, | |
| { | |
| "epoch": 0.6358626536668079, | |
| "grad_norm": 0.35785168409347534, | |
| "learning_rate": 1.5496377920351597e-05, | |
| "loss": 1.391272735595703, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.6379821958456974, | |
| "grad_norm": 0.34128299355506897, | |
| "learning_rate": 1.533785402443941e-05, | |
| "loss": 1.3791492462158204, | |
| "step": 1505 | |
| }, | |
| { | |
| "epoch": 0.6401017380245867, | |
| "grad_norm": 0.3467959761619568, | |
| "learning_rate": 1.5179785535423108e-05, | |
| "loss": 1.3836509704589843, | |
| "step": 1510 | |
| }, | |
| { | |
| "epoch": 0.642221280203476, | |
| "grad_norm": 0.3909717798233032, | |
| "learning_rate": 1.5022179903560646e-05, | |
| "loss": 1.4054960250854491, | |
| "step": 1515 | |
| }, | |
| { | |
| "epoch": 0.6443408223823655, | |
| "grad_norm": 0.45260360836982727, | |
| "learning_rate": 1.486504455729408e-05, | |
| "loss": 1.411332893371582, | |
| "step": 1520 | |
| }, | |
| { | |
| "epoch": 0.6464603645612548, | |
| "grad_norm": 0.334896445274353, | |
| "learning_rate": 1.4708386902899459e-05, | |
| "loss": 1.4111727714538573, | |
| "step": 1525 | |
| }, | |
| { | |
| "epoch": 0.6485799067401441, | |
| "grad_norm": 0.4301621615886688, | |
| "learning_rate": 1.4552214324137745e-05, | |
| "loss": 1.3917789459228516, | |
| "step": 1530 | |
| }, | |
| { | |
| "epoch": 0.6506994489190335, | |
| "grad_norm": 0.346272736787796, | |
| "learning_rate": 1.4396534181906725e-05, | |
| "loss": 1.3605911254882812, | |
| "step": 1535 | |
| }, | |
| { | |
| "epoch": 0.6528189910979229, | |
| "grad_norm": 0.34127846360206604, | |
| "learning_rate": 1.4241353813894203e-05, | |
| "loss": 1.3848798751831055, | |
| "step": 1540 | |
| }, | |
| { | |
| "epoch": 0.6549385332768122, | |
| "grad_norm": 0.3136858642101288, | |
| "learning_rate": 1.4086680534232018e-05, | |
| "loss": 1.38115234375, | |
| "step": 1545 | |
| }, | |
| { | |
| "epoch": 0.6570580754557016, | |
| "grad_norm": 0.3277495801448822, | |
| "learning_rate": 1.393252163315138e-05, | |
| "loss": 1.3868414878845214, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 0.6591776176345909, | |
| "grad_norm": 0.3770756423473358, | |
| "learning_rate": 1.3778884376639262e-05, | |
| "loss": 1.3910868644714356, | |
| "step": 1555 | |
| }, | |
| { | |
| "epoch": 0.6612971598134803, | |
| "grad_norm": 0.3495945334434509, | |
| "learning_rate": 1.3625776006095881e-05, | |
| "loss": 1.4035910606384276, | |
| "step": 1560 | |
| }, | |
| { | |
| "epoch": 0.6634167019923697, | |
| "grad_norm": 0.30360302329063416, | |
| "learning_rate": 1.3473203737993432e-05, | |
| "loss": 1.3631237983703612, | |
| "step": 1565 | |
| }, | |
| { | |
| "epoch": 0.665536244171259, | |
| "grad_norm": 0.2972458600997925, | |
| "learning_rate": 1.3321174763535927e-05, | |
| "loss": 1.4188838005065918, | |
| "step": 1570 | |
| }, | |
| { | |
| "epoch": 0.6676557863501483, | |
| "grad_norm": 0.3615584075450897, | |
| "learning_rate": 1.3169696248320296e-05, | |
| "loss": 1.3842923164367675, | |
| "step": 1575 | |
| }, | |
| { | |
| "epoch": 0.6697753285290378, | |
| "grad_norm": 0.32157957553863525, | |
| "learning_rate": 1.301877533199859e-05, | |
| "loss": 1.3403413772583008, | |
| "step": 1580 | |
| }, | |
| { | |
| "epoch": 0.6718948707079271, | |
| "grad_norm": 0.33716222643852234, | |
| "learning_rate": 1.286841912794149e-05, | |
| "loss": 1.3736663818359376, | |
| "step": 1585 | |
| }, | |
| { | |
| "epoch": 0.6740144128868164, | |
| "grad_norm": 0.3723871111869812, | |
| "learning_rate": 1.2718634722903073e-05, | |
| "loss": 1.3301881790161132, | |
| "step": 1590 | |
| }, | |
| { | |
| "epoch": 0.6761339550657058, | |
| "grad_norm": 0.3483937978744507, | |
| "learning_rate": 1.256942917668672e-05, | |
| "loss": 1.364849853515625, | |
| "step": 1595 | |
| }, | |
| { | |
| "epoch": 0.6782534972445952, | |
| "grad_norm": 0.36319825053215027, | |
| "learning_rate": 1.2420809521812404e-05, | |
| "loss": 1.3615565299987793, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 0.6803730394234845, | |
| "grad_norm": 0.40565842390060425, | |
| "learning_rate": 1.2272782763185255e-05, | |
| "loss": 1.4163089752197267, | |
| "step": 1605 | |
| }, | |
| { | |
| "epoch": 0.6824925816023739, | |
| "grad_norm": 0.39059746265411377, | |
| "learning_rate": 1.2125355877765335e-05, | |
| "loss": 1.3787422180175781, | |
| "step": 1610 | |
| }, | |
| { | |
| "epoch": 0.6846121237812632, | |
| "grad_norm": 0.349928081035614, | |
| "learning_rate": 1.1978535814238814e-05, | |
| "loss": 1.4102198600769043, | |
| "step": 1615 | |
| }, | |
| { | |
| "epoch": 0.6867316659601526, | |
| "grad_norm": 0.41478702425956726, | |
| "learning_rate": 1.18323294926905e-05, | |
| "loss": 1.4118992805480957, | |
| "step": 1620 | |
| }, | |
| { | |
| "epoch": 0.688851208139042, | |
| "grad_norm": 0.31194180250167847, | |
| "learning_rate": 1.1686743804277611e-05, | |
| "loss": 1.3731643676757812, | |
| "step": 1625 | |
| }, | |
| { | |
| "epoch": 0.6909707503179313, | |
| "grad_norm": 0.34242942929267883, | |
| "learning_rate": 1.1541785610904996e-05, | |
| "loss": 1.4209255218505858, | |
| "step": 1630 | |
| }, | |
| { | |
| "epoch": 0.6930902924968206, | |
| "grad_norm": 0.3766807019710541, | |
| "learning_rate": 1.1397461744901752e-05, | |
| "loss": 1.420722198486328, | |
| "step": 1635 | |
| }, | |
| { | |
| "epoch": 0.6952098346757101, | |
| "grad_norm": 0.2987065613269806, | |
| "learning_rate": 1.1253779008699131e-05, | |
| "loss": 1.4088357925415038, | |
| "step": 1640 | |
| }, | |
| { | |
| "epoch": 0.6973293768545994, | |
| "grad_norm": 0.3927730917930603, | |
| "learning_rate": 1.1110744174509952e-05, | |
| "loss": 1.31985502243042, | |
| "step": 1645 | |
| }, | |
| { | |
| "epoch": 0.6994489190334887, | |
| "grad_norm": 0.38961389660835266, | |
| "learning_rate": 1.0968363984009403e-05, | |
| "loss": 1.3731939315795898, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 0.7015684612123781, | |
| "grad_norm": 0.4514513909816742, | |
| "learning_rate": 1.0826645148017305e-05, | |
| "loss": 1.383669662475586, | |
| "step": 1655 | |
| }, | |
| { | |
| "epoch": 0.7036880033912675, | |
| "grad_norm": 0.33745962381362915, | |
| "learning_rate": 1.0685594346181776e-05, | |
| "loss": 1.408970260620117, | |
| "step": 1660 | |
| }, | |
| { | |
| "epoch": 0.7058075455701568, | |
| "grad_norm": 0.35877764225006104, | |
| "learning_rate": 1.0545218226664397e-05, | |
| "loss": 1.3701903343200683, | |
| "step": 1665 | |
| }, | |
| { | |
| "epoch": 0.7079270877490462, | |
| "grad_norm": 0.3303185701370239, | |
| "learning_rate": 1.0405523405826917e-05, | |
| "loss": 1.4714448928833008, | |
| "step": 1670 | |
| }, | |
| { | |
| "epoch": 0.7100466299279355, | |
| "grad_norm": 0.4020833373069763, | |
| "learning_rate": 1.0266516467919334e-05, | |
| "loss": 1.4096800804138183, | |
| "step": 1675 | |
| }, | |
| { | |
| "epoch": 0.712166172106825, | |
| "grad_norm": 0.36749550700187683, | |
| "learning_rate": 1.0128203964769601e-05, | |
| "loss": 1.3926508903503418, | |
| "step": 1680 | |
| }, | |
| { | |
| "epoch": 0.7142857142857143, | |
| "grad_norm": 0.3831540644168854, | |
| "learning_rate": 9.990592415474814e-06, | |
| "loss": 1.3888694763183593, | |
| "step": 1685 | |
| }, | |
| { | |
| "epoch": 0.7164052564646036, | |
| "grad_norm": 0.4705236256122589, | |
| "learning_rate": 9.853688306093937e-06, | |
| "loss": 1.3559078216552733, | |
| "step": 1690 | |
| }, | |
| { | |
| "epoch": 0.7185247986434931, | |
| "grad_norm": 0.3838376998901367, | |
| "learning_rate": 9.717498089342083e-06, | |
| "loss": 1.3565834045410157, | |
| "step": 1695 | |
| }, | |
| { | |
| "epoch": 0.7206443408223824, | |
| "grad_norm": 0.3517304062843323, | |
| "learning_rate": 9.582028184286423e-06, | |
| "loss": 1.3321958541870118, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 0.7227638830012717, | |
| "grad_norm": 0.4058513641357422, | |
| "learning_rate": 9.44728497604358e-06, | |
| "loss": 1.4016094207763672, | |
| "step": 1705 | |
| }, | |
| { | |
| "epoch": 0.7248834251801611, | |
| "grad_norm": 0.39036357402801514, | |
| "learning_rate": 9.313274815478698e-06, | |
| "loss": 1.3314099311828613, | |
| "step": 1710 | |
| }, | |
| { | |
| "epoch": 0.7270029673590505, | |
| "grad_norm": 0.31380540132522583, | |
| "learning_rate": 9.18000401890614e-06, | |
| "loss": 1.4088171005249024, | |
| "step": 1715 | |
| }, | |
| { | |
| "epoch": 0.7291225095379398, | |
| "grad_norm": 0.3255908489227295, | |
| "learning_rate": 9.047478867791732e-06, | |
| "loss": 1.4077937126159668, | |
| "step": 1720 | |
| }, | |
| { | |
| "epoch": 0.7312420517168292, | |
| "grad_norm": 0.35758236050605774, | |
| "learning_rate": 8.915705608456706e-06, | |
| "loss": 1.3958446502685546, | |
| "step": 1725 | |
| }, | |
| { | |
| "epoch": 0.7333615938957185, | |
| "grad_norm": 0.32464516162872314, | |
| "learning_rate": 8.784690451783337e-06, | |
| "loss": 1.3870001792907716, | |
| "step": 1730 | |
| }, | |
| { | |
| "epoch": 0.7354811360746079, | |
| "grad_norm": 0.33486559987068176, | |
| "learning_rate": 8.654439572922143e-06, | |
| "loss": 1.3863597869873048, | |
| "step": 1735 | |
| }, | |
| { | |
| "epoch": 0.7376006782534973, | |
| "grad_norm": 0.3612193167209625, | |
| "learning_rate": 8.524959111000871e-06, | |
| "loss": 1.3322760581970214, | |
| "step": 1740 | |
| }, | |
| { | |
| "epoch": 0.7397202204323866, | |
| "grad_norm": 0.4278302490711212, | |
| "learning_rate": 8.396255168835115e-06, | |
| "loss": 1.4039762496948243, | |
| "step": 1745 | |
| }, | |
| { | |
| "epoch": 0.7418397626112759, | |
| "grad_norm": 0.4444824755191803, | |
| "learning_rate": 8.268333812640716e-06, | |
| "loss": 1.4116302490234376, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 0.7439593047901654, | |
| "grad_norm": 0.38617727160453796, | |
| "learning_rate": 8.141201071747784e-06, | |
| "loss": 1.3992499351501464, | |
| "step": 1755 | |
| }, | |
| { | |
| "epoch": 0.7460788469690547, | |
| "grad_norm": 0.2922028601169586, | |
| "learning_rate": 8.014862938316542e-06, | |
| "loss": 1.362720012664795, | |
| "step": 1760 | |
| }, | |
| { | |
| "epoch": 0.748198389147944, | |
| "grad_norm": 0.3413691222667694, | |
| "learning_rate": 7.889325367054939e-06, | |
| "loss": 1.3601066589355468, | |
| "step": 1765 | |
| }, | |
| { | |
| "epoch": 0.7503179313268334, | |
| "grad_norm": 0.3315316438674927, | |
| "learning_rate": 7.764594274937884e-06, | |
| "loss": 1.3529040336608886, | |
| "step": 1770 | |
| }, | |
| { | |
| "epoch": 0.7524374735057228, | |
| "grad_norm": 0.3657066524028778, | |
| "learning_rate": 7.640675540928487e-06, | |
| "loss": 1.366931438446045, | |
| "step": 1775 | |
| }, | |
| { | |
| "epoch": 0.7545570156846121, | |
| "grad_norm": 0.3970285952091217, | |
| "learning_rate": 7.5175750057008635e-06, | |
| "loss": 1.3595660209655762, | |
| "step": 1780 | |
| }, | |
| { | |
| "epoch": 0.7566765578635015, | |
| "grad_norm": 0.37846875190734863, | |
| "learning_rate": 7.395298471364892e-06, | |
| "loss": 1.374918556213379, | |
| "step": 1785 | |
| }, | |
| { | |
| "epoch": 0.7587961000423908, | |
| "grad_norm": 0.3769720494747162, | |
| "learning_rate": 7.27385170119273e-06, | |
| "loss": 1.4017581939697266, | |
| "step": 1790 | |
| }, | |
| { | |
| "epoch": 0.7609156422212802, | |
| "grad_norm": 0.32120347023010254, | |
| "learning_rate": 7.153240419347201e-06, | |
| "loss": 1.3574372291564942, | |
| "step": 1795 | |
| }, | |
| { | |
| "epoch": 0.7630351844001696, | |
| "grad_norm": 0.33805254101753235, | |
| "learning_rate": 7.033470310611945e-06, | |
| "loss": 1.364763355255127, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 0.7651547265790589, | |
| "grad_norm": 0.3906916081905365, | |
| "learning_rate": 6.9145470201235105e-06, | |
| "loss": 1.3832975387573243, | |
| "step": 1805 | |
| }, | |
| { | |
| "epoch": 0.7672742687579482, | |
| "grad_norm": 0.37446460127830505, | |
| "learning_rate": 6.796476153105294e-06, | |
| "loss": 1.388979148864746, | |
| "step": 1810 | |
| }, | |
| { | |
| "epoch": 0.7693938109368377, | |
| "grad_norm": 0.40013885498046875, | |
| "learning_rate": 6.679263274603315e-06, | |
| "loss": 1.396776008605957, | |
| "step": 1815 | |
| }, | |
| { | |
| "epoch": 0.771513353115727, | |
| "grad_norm": 0.3226351737976074, | |
| "learning_rate": 6.562913909223931e-06, | |
| "loss": 1.404403305053711, | |
| "step": 1820 | |
| }, | |
| { | |
| "epoch": 0.7736328952946163, | |
| "grad_norm": 0.3461005389690399, | |
| "learning_rate": 6.447433540873471e-06, | |
| "loss": 1.3264945983886718, | |
| "step": 1825 | |
| }, | |
| { | |
| "epoch": 0.7757524374735058, | |
| "grad_norm": 0.37068504095077515, | |
| "learning_rate": 6.332827612499717e-06, | |
| "loss": 1.4035964965820313, | |
| "step": 1830 | |
| }, | |
| { | |
| "epoch": 0.7778719796523951, | |
| "grad_norm": 0.3147546052932739, | |
| "learning_rate": 6.219101525835386e-06, | |
| "loss": 1.3791501998901368, | |
| "step": 1835 | |
| }, | |
| { | |
| "epoch": 0.7799915218312844, | |
| "grad_norm": 0.3691222071647644, | |
| "learning_rate": 6.106260641143546e-06, | |
| "loss": 1.3540081977844238, | |
| "step": 1840 | |
| }, | |
| { | |
| "epoch": 0.7821110640101738, | |
| "grad_norm": 0.3147021234035492, | |
| "learning_rate": 5.994310276964931e-06, | |
| "loss": 1.361419677734375, | |
| "step": 1845 | |
| }, | |
| { | |
| "epoch": 0.7842306061890632, | |
| "grad_norm": 0.38644054532051086, | |
| "learning_rate": 5.883255709867288e-06, | |
| "loss": 1.3613595008850097, | |
| "step": 1850 | |
| }, | |
| { | |
| "epoch": 0.7863501483679525, | |
| "grad_norm": 0.439148485660553, | |
| "learning_rate": 5.773102174196681e-06, | |
| "loss": 1.364901351928711, | |
| "step": 1855 | |
| }, | |
| { | |
| "epoch": 0.7884696905468419, | |
| "grad_norm": 0.3420233130455017, | |
| "learning_rate": 5.663854861830759e-06, | |
| "loss": 1.366286277770996, | |
| "step": 1860 | |
| }, | |
| { | |
| "epoch": 0.7905892327257312, | |
| "grad_norm": 0.34328582882881165, | |
| "learning_rate": 5.555518921934047e-06, | |
| "loss": 1.3862383842468262, | |
| "step": 1865 | |
| }, | |
| { | |
| "epoch": 0.7927087749046206, | |
| "grad_norm": 0.3331151604652405, | |
| "learning_rate": 5.448099460715289e-06, | |
| "loss": 1.346947479248047, | |
| "step": 1870 | |
| }, | |
| { | |
| "epoch": 0.79482831708351, | |
| "grad_norm": 0.3305598497390747, | |
| "learning_rate": 5.341601541186722e-06, | |
| "loss": 1.3726158142089844, | |
| "step": 1875 | |
| }, | |
| { | |
| "epoch": 0.7969478592623993, | |
| "grad_norm": 0.37294289469718933, | |
| "learning_rate": 5.236030182925475e-06, | |
| "loss": 1.3895322799682617, | |
| "step": 1880 | |
| }, | |
| { | |
| "epoch": 0.7990674014412886, | |
| "grad_norm": 0.35240915417671204, | |
| "learning_rate": 5.131390361836966e-06, | |
| "loss": 1.3554275512695313, | |
| "step": 1885 | |
| }, | |
| { | |
| "epoch": 0.8011869436201781, | |
| "grad_norm": 0.4194449186325073, | |
| "learning_rate": 5.027687009920393e-06, | |
| "loss": 1.3878568649291991, | |
| "step": 1890 | |
| }, | |
| { | |
| "epoch": 0.8033064857990674, | |
| "grad_norm": 0.38629019260406494, | |
| "learning_rate": 4.924925015036247e-06, | |
| "loss": 1.4082857131958009, | |
| "step": 1895 | |
| }, | |
| { | |
| "epoch": 0.8054260279779568, | |
| "grad_norm": 0.391720175743103, | |
| "learning_rate": 4.823109220675934e-06, | |
| "loss": 1.358858871459961, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 0.8075455701568461, | |
| "grad_norm": 0.3612916171550751, | |
| "learning_rate": 4.722244425733521e-06, | |
| "loss": 1.4034775733947753, | |
| "step": 1905 | |
| }, | |
| { | |
| "epoch": 0.8096651123357355, | |
| "grad_norm": 0.3612155616283417, | |
| "learning_rate": 4.622335384279505e-06, | |
| "loss": 1.4016291618347168, | |
| "step": 1910 | |
| }, | |
| { | |
| "epoch": 0.8117846545146249, | |
| "grad_norm": 0.3317670524120331, | |
| "learning_rate": 4.5233868053367575e-06, | |
| "loss": 1.3749965667724608, | |
| "step": 1915 | |
| }, | |
| { | |
| "epoch": 0.8139041966935142, | |
| "grad_norm": 0.32299166917800903, | |
| "learning_rate": 4.425403352658591e-06, | |
| "loss": 1.3324901580810546, | |
| "step": 1920 | |
| }, | |
| { | |
| "epoch": 0.8160237388724035, | |
| "grad_norm": 0.346662700176239, | |
| "learning_rate": 4.328389644508907e-06, | |
| "loss": 1.386284637451172, | |
| "step": 1925 | |
| }, | |
| { | |
| "epoch": 0.818143281051293, | |
| "grad_norm": 0.3666786849498749, | |
| "learning_rate": 4.232350253444539e-06, | |
| "loss": 1.405134391784668, | |
| "step": 1930 | |
| }, | |
| { | |
| "epoch": 0.8202628232301823, | |
| "grad_norm": 0.33855748176574707, | |
| "learning_rate": 4.137289706099759e-06, | |
| "loss": 1.3573484420776367, | |
| "step": 1935 | |
| }, | |
| { | |
| "epoch": 0.8223823654090716, | |
| "grad_norm": 0.3716118335723877, | |
| "learning_rate": 4.043212482972877e-06, | |
| "loss": 1.3593734741210937, | |
| "step": 1940 | |
| }, | |
| { | |
| "epoch": 0.824501907587961, | |
| "grad_norm": 0.3085205554962158, | |
| "learning_rate": 3.950123018215085e-06, | |
| "loss": 1.380510425567627, | |
| "step": 1945 | |
| }, | |
| { | |
| "epoch": 0.8266214497668504, | |
| "grad_norm": 0.33827266097068787, | |
| "learning_rate": 3.8580256994214805e-06, | |
| "loss": 1.3554264068603517, | |
| "step": 1950 | |
| }, | |
| { | |
| "epoch": 0.8287409919457397, | |
| "grad_norm": 0.38652700185775757, | |
| "learning_rate": 3.7669248674242263e-06, | |
| "loss": 1.360565185546875, | |
| "step": 1955 | |
| }, | |
| { | |
| "epoch": 0.8308605341246291, | |
| "grad_norm": 0.3671756386756897, | |
| "learning_rate": 3.6768248160879787e-06, | |
| "loss": 1.41397066116333, | |
| "step": 1960 | |
| }, | |
| { | |
| "epoch": 0.8329800763035184, | |
| "grad_norm": 0.3778105676174164, | |
| "learning_rate": 3.5877297921074945e-06, | |
| "loss": 1.362232780456543, | |
| "step": 1965 | |
| }, | |
| { | |
| "epoch": 0.8350996184824078, | |
| "grad_norm": 0.37815120816230774, | |
| "learning_rate": 3.499643994807486e-06, | |
| "loss": 1.36951904296875, | |
| "step": 1970 | |
| }, | |
| { | |
| "epoch": 0.8372191606612972, | |
| "grad_norm": 0.33038780093193054, | |
| "learning_rate": 3.4125715759446785e-06, | |
| "loss": 1.3970839500427246, | |
| "step": 1975 | |
| }, | |
| { | |
| "epoch": 0.8393387028401865, | |
| "grad_norm": 0.3773466944694519, | |
| "learning_rate": 3.32651663951212e-06, | |
| "loss": 1.3800506591796875, | |
| "step": 1980 | |
| }, | |
| { | |
| "epoch": 0.8414582450190758, | |
| "grad_norm": 0.40176573395729065, | |
| "learning_rate": 3.241483241545773e-06, | |
| "loss": 1.3858375549316406, | |
| "step": 1985 | |
| }, | |
| { | |
| "epoch": 0.8435777871979653, | |
| "grad_norm": 0.4275735914707184, | |
| "learning_rate": 3.1574753899333175e-06, | |
| "loss": 1.397435760498047, | |
| "step": 1990 | |
| }, | |
| { | |
| "epoch": 0.8456973293768546, | |
| "grad_norm": 0.3702447712421417, | |
| "learning_rate": 3.074497044225241e-06, | |
| "loss": 1.3681181907653808, | |
| "step": 1995 | |
| }, | |
| { | |
| "epoch": 0.8478168715557439, | |
| "grad_norm": 0.3282405734062195, | |
| "learning_rate": 2.992552115448258e-06, | |
| "loss": 1.410075569152832, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.8499364137346334, | |
| "grad_norm": 0.40395912528038025, | |
| "learning_rate": 2.911644465920907e-06, | |
| "loss": 1.3709904670715332, | |
| "step": 2005 | |
| }, | |
| { | |
| "epoch": 0.8520559559135227, | |
| "grad_norm": 0.41466715931892395, | |
| "learning_rate": 2.831777909071559e-06, | |
| "loss": 1.3775070190429688, | |
| "step": 2010 | |
| }, | |
| { | |
| "epoch": 0.854175498092412, | |
| "grad_norm": 0.3982146084308624, | |
| "learning_rate": 2.7529562092586475e-06, | |
| "loss": 1.35903902053833, | |
| "step": 2015 | |
| }, | |
| { | |
| "epoch": 0.8562950402713014, | |
| "grad_norm": 0.3517100512981415, | |
| "learning_rate": 2.6751830815932604e-06, | |
| "loss": 1.3567079544067382, | |
| "step": 2020 | |
| }, | |
| { | |
| "epoch": 0.8584145824501908, | |
| "grad_norm": 0.36543378233909607, | |
| "learning_rate": 2.5984621917640283e-06, | |
| "loss": 1.3802772521972657, | |
| "step": 2025 | |
| }, | |
| { | |
| "epoch": 0.8605341246290801, | |
| "grad_norm": 0.34028181433677673, | |
| "learning_rate": 2.5227971558643537e-06, | |
| "loss": 1.4171323776245117, | |
| "step": 2030 | |
| }, | |
| { | |
| "epoch": 0.8626536668079695, | |
| "grad_norm": 0.36879080533981323, | |
| "learning_rate": 2.448191540221967e-06, | |
| "loss": 1.3600201606750488, | |
| "step": 2035 | |
| }, | |
| { | |
| "epoch": 0.8647732089868588, | |
| "grad_norm": 0.3401508331298828, | |
| "learning_rate": 2.37464886123083e-06, | |
| "loss": 1.3702825546264648, | |
| "step": 2040 | |
| }, | |
| { | |
| "epoch": 0.8668927511657482, | |
| "grad_norm": 0.3567841053009033, | |
| "learning_rate": 2.302172585185425e-06, | |
| "loss": 1.396543025970459, | |
| "step": 2045 | |
| }, | |
| { | |
| "epoch": 0.8690122933446376, | |
| "grad_norm": 0.3902541399002075, | |
| "learning_rate": 2.2307661281173313e-06, | |
| "loss": 1.4127174377441407, | |
| "step": 2050 | |
| }, | |
| { | |
| "epoch": 0.8711318355235269, | |
| "grad_norm": 0.3391524851322174, | |
| "learning_rate": 2.160432855634259e-06, | |
| "loss": 1.3418708801269532, | |
| "step": 2055 | |
| }, | |
| { | |
| "epoch": 0.8732513777024162, | |
| "grad_norm": 0.5009668469429016, | |
| "learning_rate": 2.0911760827614037e-06, | |
| "loss": 1.3470192909240724, | |
| "step": 2060 | |
| }, | |
| { | |
| "epoch": 0.8753709198813057, | |
| "grad_norm": 0.3024480640888214, | |
| "learning_rate": 2.0229990737851897e-06, | |
| "loss": 1.3585514068603515, | |
| "step": 2065 | |
| }, | |
| { | |
| "epoch": 0.877490462060195, | |
| "grad_norm": 0.3296104371547699, | |
| "learning_rate": 1.9559050420994125e-06, | |
| "loss": 1.353879451751709, | |
| "step": 2070 | |
| }, | |
| { | |
| "epoch": 0.8796100042390843, | |
| "grad_norm": 0.3997982442378998, | |
| "learning_rate": 1.8898971500538126e-06, | |
| "loss": 1.3741884231567383, | |
| "step": 2075 | |
| }, | |
| { | |
| "epoch": 0.8817295464179737, | |
| "grad_norm": 0.3487870395183563, | |
| "learning_rate": 1.8249785088049893e-06, | |
| "loss": 1.3679576873779298, | |
| "step": 2080 | |
| }, | |
| { | |
| "epoch": 0.8838490885968631, | |
| "grad_norm": 0.32085949182510376, | |
| "learning_rate": 1.7611521781697644e-06, | |
| "loss": 1.408048152923584, | |
| "step": 2085 | |
| }, | |
| { | |
| "epoch": 0.8859686307757524, | |
| "grad_norm": 0.40502411127090454, | |
| "learning_rate": 1.6984211664809957e-06, | |
| "loss": 1.318140411376953, | |
| "step": 2090 | |
| }, | |
| { | |
| "epoch": 0.8880881729546418, | |
| "grad_norm": 0.31764352321624756, | |
| "learning_rate": 1.6367884304457514e-06, | |
| "loss": 1.3969331741333009, | |
| "step": 2095 | |
| }, | |
| { | |
| "epoch": 0.8902077151335311, | |
| "grad_norm": 0.4080657958984375, | |
| "learning_rate": 1.5762568750059604e-06, | |
| "loss": 1.349300003051758, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 0.8923272573124205, | |
| "grad_norm": 0.32325270771980286, | |
| "learning_rate": 1.516829353201496e-06, | |
| "loss": 1.3665590286254883, | |
| "step": 2105 | |
| }, | |
| { | |
| "epoch": 0.8944467994913099, | |
| "grad_norm": 0.3742246627807617, | |
| "learning_rate": 1.4585086660357155e-06, | |
| "loss": 1.3813313484191894, | |
| "step": 2110 | |
| }, | |
| { | |
| "epoch": 0.8965663416701992, | |
| "grad_norm": 0.3893565237522125, | |
| "learning_rate": 1.401297562343415e-06, | |
| "loss": 1.3258206367492675, | |
| "step": 2115 | |
| }, | |
| { | |
| "epoch": 0.8986858838490887, | |
| "grad_norm": 0.40509721636772156, | |
| "learning_rate": 1.3451987386612851e-06, | |
| "loss": 1.363175106048584, | |
| "step": 2120 | |
| }, | |
| { | |
| "epoch": 0.900805426027978, | |
| "grad_norm": 0.33023157715797424, | |
| "learning_rate": 1.2902148391008173e-06, | |
| "loss": 1.3888378143310547, | |
| "step": 2125 | |
| }, | |
| { | |
| "epoch": 0.9029249682068673, | |
| "grad_norm": 0.37413084506988525, | |
| "learning_rate": 1.2363484552236654e-06, | |
| "loss": 1.3474288940429688, | |
| "step": 2130 | |
| }, | |
| { | |
| "epoch": 0.9050445103857567, | |
| "grad_norm": 0.41952866315841675, | |
| "learning_rate": 1.1836021259194974e-06, | |
| "loss": 1.3863845825195313, | |
| "step": 2135 | |
| }, | |
| { | |
| "epoch": 0.907164052564646, | |
| "grad_norm": 0.35626864433288574, | |
| "learning_rate": 1.1319783372863602e-06, | |
| "loss": 1.349094772338867, | |
| "step": 2140 | |
| }, | |
| { | |
| "epoch": 0.9092835947435354, | |
| "grad_norm": 0.3765277564525604, | |
| "learning_rate": 1.0814795225134538e-06, | |
| "loss": 1.373190689086914, | |
| "step": 2145 | |
| }, | |
| { | |
| "epoch": 0.9114031369224248, | |
| "grad_norm": 0.34631597995758057, | |
| "learning_rate": 1.0321080617664847e-06, | |
| "loss": 1.32452449798584, | |
| "step": 2150 | |
| }, | |
| { | |
| "epoch": 0.9135226791013141, | |
| "grad_norm": 0.4611705541610718, | |
| "learning_rate": 9.838662820754714e-07, | |
| "loss": 1.3838292121887208, | |
| "step": 2155 | |
| }, | |
| { | |
| "epoch": 0.9156422212802034, | |
| "grad_norm": 0.3573555052280426, | |
| "learning_rate": 9.36756457225052e-07, | |
| "loss": 1.3648181915283204, | |
| "step": 2160 | |
| }, | |
| { | |
| "epoch": 0.9177617634590929, | |
| "grad_norm": 0.364229291677475, | |
| "learning_rate": 8.907808076473261e-07, | |
| "loss": 1.4101836204528808, | |
| "step": 2165 | |
| }, | |
| { | |
| "epoch": 0.9198813056379822, | |
| "grad_norm": 0.3490945100784302, | |
| "learning_rate": 8.459415003172099e-07, | |
| "loss": 1.4038494110107422, | |
| "step": 2170 | |
| }, | |
| { | |
| "epoch": 0.9220008478168715, | |
| "grad_norm": 0.39095833897590637, | |
| "learning_rate": 8.022406486502654e-07, | |
| "loss": 1.3878660202026367, | |
| "step": 2175 | |
| }, | |
| { | |
| "epoch": 0.924120389995761, | |
| "grad_norm": 0.3487260341644287, | |
| "learning_rate": 7.596803124031243e-07, | |
| "loss": 1.3590547561645507, | |
| "step": 2180 | |
| }, | |
| { | |
| "epoch": 0.9262399321746503, | |
| "grad_norm": 0.39182376861572266, | |
| "learning_rate": 7.182624975763829e-07, | |
| "loss": 1.3610639572143555, | |
| "step": 2185 | |
| }, | |
| { | |
| "epoch": 0.9283594743535396, | |
| "grad_norm": 0.35160231590270996, | |
| "learning_rate": 6.779891563200663e-07, | |
| "loss": 1.334109115600586, | |
| "step": 2190 | |
| }, | |
| { | |
| "epoch": 0.930479016532429, | |
| "grad_norm": 0.39832940697669983, | |
| "learning_rate": 6.3886218684161e-07, | |
| "loss": 1.3647882461547851, | |
| "step": 2195 | |
| }, | |
| { | |
| "epoch": 0.9325985587113184, | |
| "grad_norm": 0.387676477432251, | |
| "learning_rate": 6.008834333163876e-07, | |
| "loss": 1.411749267578125, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 0.9347181008902077, | |
| "grad_norm": 0.3822062611579895, | |
| "learning_rate": 5.640546858008105e-07, | |
| "loss": 1.3652889251708984, | |
| "step": 2205 | |
| }, | |
| { | |
| "epoch": 0.9368376430690971, | |
| "grad_norm": 0.35543733835220337, | |
| "learning_rate": 5.283776801479207e-07, | |
| "loss": 1.3895767211914063, | |
| "step": 2210 | |
| }, | |
| { | |
| "epoch": 0.9389571852479864, | |
| "grad_norm": 0.3932713568210602, | |
| "learning_rate": 4.938540979256112e-07, | |
| "loss": 1.35699405670166, | |
| "step": 2215 | |
| }, | |
| { | |
| "epoch": 0.9410767274268758, | |
| "grad_norm": 0.42917537689208984, | |
| "learning_rate": 4.604855663373459e-07, | |
| "loss": 1.3352517127990722, | |
| "step": 2220 | |
| }, | |
| { | |
| "epoch": 0.9431962696057652, | |
| "grad_norm": 0.35743996500968933, | |
| "learning_rate": 4.2827365814547546e-07, | |
| "loss": 1.3827932357788086, | |
| "step": 2225 | |
| }, | |
| { | |
| "epoch": 0.9453158117846545, | |
| "grad_norm": 0.39264145493507385, | |
| "learning_rate": 3.972198915970976e-07, | |
| "loss": 1.348250389099121, | |
| "step": 2230 | |
| }, | |
| { | |
| "epoch": 0.9474353539635438, | |
| "grad_norm": 0.38739705085754395, | |
| "learning_rate": 3.6732573035250797e-07, | |
| "loss": 1.3787860870361328, | |
| "step": 2235 | |
| }, | |
| { | |
| "epoch": 0.9495548961424333, | |
| "grad_norm": 0.3625320494174957, | |
| "learning_rate": 3.3859258341621125e-07, | |
| "loss": 1.3689279556274414, | |
| "step": 2240 | |
| }, | |
| { | |
| "epoch": 0.9516744383213226, | |
| "grad_norm": 0.3911919593811035, | |
| "learning_rate": 3.110218050705022e-07, | |
| "loss": 1.3658540725708008, | |
| "step": 2245 | |
| }, | |
| { | |
| "epoch": 0.9537939805002119, | |
| "grad_norm": 0.3534514605998993, | |
| "learning_rate": 2.846146948116468e-07, | |
| "loss": 1.3920455932617188, | |
| "step": 2250 | |
| }, | |
| { | |
| "epoch": 0.9559135226791013, | |
| "grad_norm": 0.3445931375026703, | |
| "learning_rate": 2.59372497288618e-07, | |
| "loss": 1.3539911270141602, | |
| "step": 2255 | |
| }, | |
| { | |
| "epoch": 0.9580330648579907, | |
| "grad_norm": 0.3572905659675598, | |
| "learning_rate": 2.352964022444476e-07, | |
| "loss": 1.3551013946533204, | |
| "step": 2260 | |
| }, | |
| { | |
| "epoch": 0.96015260703688, | |
| "grad_norm": 0.34290286898612976, | |
| "learning_rate": 2.123875444601381e-07, | |
| "loss": 1.3590556144714356, | |
| "step": 2265 | |
| }, | |
| { | |
| "epoch": 0.9622721492157694, | |
| "grad_norm": 0.40034741163253784, | |
| "learning_rate": 1.9064700370118593e-07, | |
| "loss": 1.4194296836853026, | |
| "step": 2270 | |
| }, | |
| { | |
| "epoch": 0.9643916913946587, | |
| "grad_norm": 0.34991636872291565, | |
| "learning_rate": 1.7007580466667782e-07, | |
| "loss": 1.3442374229431153, | |
| "step": 2275 | |
| }, | |
| { | |
| "epoch": 0.9665112335735481, | |
| "grad_norm": 0.340112566947937, | |
| "learning_rate": 1.5067491694100154e-07, | |
| "loss": 1.393927764892578, | |
| "step": 2280 | |
| }, | |
| { | |
| "epoch": 0.9686307757524375, | |
| "grad_norm": 0.34182655811309814, | |
| "learning_rate": 1.324452549481464e-07, | |
| "loss": 1.3692918777465821, | |
| "step": 2285 | |
| }, | |
| { | |
| "epoch": 0.9707503179313268, | |
| "grad_norm": 0.4897964894771576, | |
| "learning_rate": 1.1538767790859883e-07, | |
| "loss": 1.348414993286133, | |
| "step": 2290 | |
| }, | |
| { | |
| "epoch": 0.9728698601102161, | |
| "grad_norm": 0.35590991377830505, | |
| "learning_rate": 9.950298979885254e-08, | |
| "loss": 1.3781864166259765, | |
| "step": 2295 | |
| }, | |
| { | |
| "epoch": 0.9749894022891056, | |
| "grad_norm": 0.312599241733551, | |
| "learning_rate": 8.479193931350549e-08, | |
| "loss": 1.373946762084961, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 0.9771089444679949, | |
| "grad_norm": 0.29742780327796936, | |
| "learning_rate": 7.125521982997152e-08, | |
| "loss": 1.4087471961975098, | |
| "step": 2305 | |
| }, | |
| { | |
| "epoch": 0.9792284866468842, | |
| "grad_norm": 0.30480536818504333, | |
| "learning_rate": 5.8893469375814745e-08, | |
| "loss": 1.3817399978637694, | |
| "step": 2310 | |
| }, | |
| { | |
| "epoch": 0.9813480288257737, | |
| "grad_norm": 0.40220728516578674, | |
| "learning_rate": 4.7707270598656985e-08, | |
| "loss": 1.3901471138000487, | |
| "step": 2315 | |
| }, | |
| { | |
| "epoch": 0.983467571004663, | |
| "grad_norm": 0.32252898812294006, | |
| "learning_rate": 3.769715073872748e-08, | |
| "loss": 1.3695104598999024, | |
| "step": 2320 | |
| }, | |
| { | |
| "epoch": 0.9855871131835523, | |
| "grad_norm": 0.3661072850227356, | |
| "learning_rate": 2.8863581604010594e-08, | |
| "loss": 1.3950386047363281, | |
| "step": 2325 | |
| }, | |
| { | |
| "epoch": 0.9877066553624417, | |
| "grad_norm": 0.3574873208999634, | |
| "learning_rate": 2.120697954800799e-08, | |
| "loss": 1.3975903511047363, | |
| "step": 2330 | |
| }, | |
| { | |
| "epoch": 0.989826197541331, | |
| "grad_norm": 0.4053052067756653, | |
| "learning_rate": 1.472770545010993e-08, | |
| "loss": 1.3778751373291016, | |
| "step": 2335 | |
| }, | |
| { | |
| "epoch": 0.9919457397202205, | |
| "grad_norm": 0.38769036531448364, | |
| "learning_rate": 9.426064698594971e-09, | |
| "loss": 1.3664087295532226, | |
| "step": 2340 | |
| }, | |
| { | |
| "epoch": 0.9940652818991098, | |
| "grad_norm": 0.37053948640823364, | |
| "learning_rate": 5.30230717623037e-09, | |
| "loss": 1.3365052223205567, | |
| "step": 2345 | |
| }, | |
| { | |
| "epoch": 0.9961848240779991, | |
| "grad_norm": 0.44109272956848145, | |
| "learning_rate": 2.35662724848984e-09, | |
| "loss": 1.3936384201049805, | |
| "step": 2350 | |
| }, | |
| { | |
| "epoch": 0.9983043662568886, | |
| "grad_norm": 0.3244446814060211, | |
| "learning_rate": 5.891637543997685e-10, | |
| "loss": 1.395126724243164, | |
| "step": 2355 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 2359, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2.7440308240462643e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |