Text Generation
PEFT
Safetensors
Transformers
recommendation
lora
generative-recommendation
itemic-token
qwen3
llama-factory
conversational
Instructions to use lwjlwj/failed with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use lwjlwj/failed with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("/root/autodl-tmp/LLM/model_cache/OneReason-0.8B-pretrain-competition") model = PeftModel.from_pretrained(base_model, "lwjlwj/failed") - Transformers
How to use lwjlwj/failed with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="lwjlwj/failed") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("lwjlwj/failed", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use lwjlwj/failed with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "lwjlwj/failed" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "lwjlwj/failed", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/lwjlwj/failed
- SGLang
How to use lwjlwj/failed 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 "lwjlwj/failed" \ --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": "lwjlwj/failed", "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 "lwjlwj/failed" \ --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": "lwjlwj/failed", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use lwjlwj/failed with Docker Model Runner:
docker model run hf.co/lwjlwj/failed
| { | |
| "best_global_step": null, | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.166709878143635, | |
| "eval_steps": 500, | |
| "global_step": 4500, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0025926886180969665, | |
| "grad_norm": 7.705212116241455, | |
| "learning_rate": 7.758620689655173e-07, | |
| "loss": 3.0227869033813475, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.005185377236193933, | |
| "grad_norm": 7.195669651031494, | |
| "learning_rate": 1.6379310344827587e-06, | |
| "loss": 3.0158885955810546, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0077780658542909, | |
| "grad_norm": 5.981606483459473, | |
| "learning_rate": 2.4999999999999998e-06, | |
| "loss": 2.9294967651367188, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.010370754472387866, | |
| "grad_norm": 4.623651027679443, | |
| "learning_rate": 3.3620689655172414e-06, | |
| "loss": 2.9329254150390627, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.012963443090484833, | |
| "grad_norm": 3.7059433460235596, | |
| "learning_rate": 4.224137931034483e-06, | |
| "loss": 2.8506282806396483, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.0155561317085818, | |
| "grad_norm": 2.2888247966766357, | |
| "learning_rate": 5.0862068965517235e-06, | |
| "loss": 2.773244285583496, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.018148820326678767, | |
| "grad_norm": 1.5469928979873657, | |
| "learning_rate": 5.948275862068966e-06, | |
| "loss": 2.6278873443603517, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.020741508944775732, | |
| "grad_norm": 1.3342334032058716, | |
| "learning_rate": 6.810344827586207e-06, | |
| "loss": 2.5356447219848635, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.023334197562872697, | |
| "grad_norm": 1.1389696598052979, | |
| "learning_rate": 7.672413793103449e-06, | |
| "loss": 2.4633319854736326, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.025926886180969666, | |
| "grad_norm": 1.1860013008117676, | |
| "learning_rate": 8.53448275862069e-06, | |
| "loss": 2.4070077896118165, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.02851957479906663, | |
| "grad_norm": 1.0827945470809937, | |
| "learning_rate": 9.396551724137931e-06, | |
| "loss": 2.3483230590820314, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.0311122634171636, | |
| "grad_norm": 1.8825736045837402, | |
| "learning_rate": 1.0258620689655173e-05, | |
| "loss": 2.3270618438720705, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.03370495203526057, | |
| "grad_norm": 1.0864979028701782, | |
| "learning_rate": 1.1120689655172414e-05, | |
| "loss": 2.2477684020996094, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.036297640653357534, | |
| "grad_norm": 0.9502561092376709, | |
| "learning_rate": 1.1982758620689655e-05, | |
| "loss": 2.192240524291992, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.0388903292714545, | |
| "grad_norm": 1.07854425907135, | |
| "learning_rate": 1.2844827586206896e-05, | |
| "loss": 2.124846267700195, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.041483017889551464, | |
| "grad_norm": 1.5999815464019775, | |
| "learning_rate": 1.370689655172414e-05, | |
| "loss": 2.0473533630371095, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.04407570650764843, | |
| "grad_norm": 1.1964465379714966, | |
| "learning_rate": 1.4568965517241379e-05, | |
| "loss": 2.0475059509277345, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.046668395125745395, | |
| "grad_norm": 1.0338537693023682, | |
| "learning_rate": 1.543103448275862e-05, | |
| "loss": 2.029034423828125, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.04926108374384237, | |
| "grad_norm": 1.473418116569519, | |
| "learning_rate": 1.6293103448275863e-05, | |
| "loss": 1.992477798461914, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.05185377236193933, | |
| "grad_norm": 1.050335168838501, | |
| "learning_rate": 1.7155172413793106e-05, | |
| "loss": 1.9807832717895508, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.0544464609800363, | |
| "grad_norm": 1.4469194412231445, | |
| "learning_rate": 1.8017241379310346e-05, | |
| "loss": 1.9144599914550782, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.05703914959813326, | |
| "grad_norm": 1.9262558221817017, | |
| "learning_rate": 1.8879310344827585e-05, | |
| "loss": 1.9685123443603516, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.05963183821623023, | |
| "grad_norm": 1.44905686378479, | |
| "learning_rate": 1.9741379310344828e-05, | |
| "loss": 1.950737190246582, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.0622245268343272, | |
| "grad_norm": 1.2477736473083496, | |
| "learning_rate": 2.060344827586207e-05, | |
| "loss": 1.870539093017578, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.06481721545242417, | |
| "grad_norm": 1.5359461307525635, | |
| "learning_rate": 2.146551724137931e-05, | |
| "loss": 1.891302490234375, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.06740990407052114, | |
| "grad_norm": 1.4555562734603882, | |
| "learning_rate": 2.232758620689655e-05, | |
| "loss": 1.8455034255981446, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.0700025926886181, | |
| "grad_norm": 1.121903657913208, | |
| "learning_rate": 2.3189655172413793e-05, | |
| "loss": 1.8681245803833009, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.07259528130671507, | |
| "grad_norm": 1.450315237045288, | |
| "learning_rate": 2.4051724137931036e-05, | |
| "loss": 1.848301315307617, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.07518796992481203, | |
| "grad_norm": 1.4702492952346802, | |
| "learning_rate": 2.4913793103448276e-05, | |
| "loss": 1.8164592742919923, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.077780658542909, | |
| "grad_norm": 1.5632305145263672, | |
| "learning_rate": 2.577586206896552e-05, | |
| "loss": 1.8211044311523437, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.08037334716100596, | |
| "grad_norm": 1.3765159845352173, | |
| "learning_rate": 2.663793103448276e-05, | |
| "loss": 1.7973749160766601, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.08296603577910293, | |
| "grad_norm": 1.5355861186981201, | |
| "learning_rate": 2.75e-05, | |
| "loss": 1.7973670959472656, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.0855587243971999, | |
| "grad_norm": 1.7966196537017822, | |
| "learning_rate": 2.836206896551724e-05, | |
| "loss": 1.793952751159668, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.08815141301529686, | |
| "grad_norm": 1.443326473236084, | |
| "learning_rate": 2.9224137931034483e-05, | |
| "loss": 1.7765045166015625, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.09074410163339383, | |
| "grad_norm": 1.508481740951538, | |
| "learning_rate": 2.9999999412317066e-05, | |
| "loss": 1.7646129608154297, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.09333679025149079, | |
| "grad_norm": 1.4187544584274292, | |
| "learning_rate": 2.9999928890420564e-05, | |
| "loss": 1.7498319625854493, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.09592947886958776, | |
| "grad_norm": 1.2583993673324585, | |
| "learning_rate": 2.9999740832570195e-05, | |
| "loss": 1.7248340606689454, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.09852216748768473, | |
| "grad_norm": 1.6766241788864136, | |
| "learning_rate": 2.9999435240239542e-05, | |
| "loss": 1.7178813934326171, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.10111485610578169, | |
| "grad_norm": 1.202833890914917, | |
| "learning_rate": 2.9999012115823158e-05, | |
| "loss": 1.6801229476928712, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.10370754472387866, | |
| "grad_norm": 1.2926560640335083, | |
| "learning_rate": 2.9998471462636546e-05, | |
| "loss": 1.767136001586914, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.10630023334197562, | |
| "grad_norm": 1.941349983215332, | |
| "learning_rate": 2.9997813284916135e-05, | |
| "loss": 1.6747543334960937, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.1088929219600726, | |
| "grad_norm": 1.5845695734024048, | |
| "learning_rate": 2.9997037587819258e-05, | |
| "loss": 1.673520278930664, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.11148561057816957, | |
| "grad_norm": 1.3995505571365356, | |
| "learning_rate": 2.999614437742409e-05, | |
| "loss": 1.7203987121582032, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.11407829919626652, | |
| "grad_norm": 1.5118882656097412, | |
| "learning_rate": 2.9995133660729633e-05, | |
| "loss": 1.706008529663086, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.1166709878143635, | |
| "grad_norm": 1.319544792175293, | |
| "learning_rate": 2.999400544565561e-05, | |
| "loss": 1.6883546829223632, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.11926367643246046, | |
| "grad_norm": 1.421674370765686, | |
| "learning_rate": 2.9992759741042464e-05, | |
| "loss": 1.7108165740966796, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.12185636505055743, | |
| "grad_norm": 1.4081259965896606, | |
| "learning_rate": 2.999139655665124e-05, | |
| "loss": 1.6875082015991212, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 0.1244490536686544, | |
| "grad_norm": 1.405349850654602, | |
| "learning_rate": 2.998991590316354e-05, | |
| "loss": 1.6731761932373046, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.12704174228675136, | |
| "grad_norm": 1.7677608728408813, | |
| "learning_rate": 2.998831779218142e-05, | |
| "loss": 1.6962146759033203, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 0.12963443090484833, | |
| "grad_norm": 1.8731317520141602, | |
| "learning_rate": 2.99866022362273e-05, | |
| "loss": 1.6599393844604493, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.12963443090484833, | |
| "eval_loss": 1.6675474643707275, | |
| "eval_runtime": 107.111, | |
| "eval_samples_per_second": 15.162, | |
| "eval_steps_per_second": 15.162, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.1322271195229453, | |
| "grad_norm": 1.4730808734893799, | |
| "learning_rate": 2.9984769248743883e-05, | |
| "loss": 1.6474054336547852, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 0.13481980814104227, | |
| "grad_norm": 1.7537602186203003, | |
| "learning_rate": 2.998281884409403e-05, | |
| "loss": 1.6060302734375, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 0.13741249675913922, | |
| "grad_norm": 1.598738670349121, | |
| "learning_rate": 2.9980751037560658e-05, | |
| "loss": 1.6906095504760743, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 0.1400051853772362, | |
| "grad_norm": 2.2294440269470215, | |
| "learning_rate": 2.9978565845346622e-05, | |
| "loss": 1.6616540908813477, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 0.14259787399533316, | |
| "grad_norm": 1.9882858991622925, | |
| "learning_rate": 2.997626328457457e-05, | |
| "loss": 1.7083959579467773, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.14519056261343014, | |
| "grad_norm": 1.6550426483154297, | |
| "learning_rate": 2.9973843373286846e-05, | |
| "loss": 1.677723503112793, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 0.1477832512315271, | |
| "grad_norm": 2.0807480812072754, | |
| "learning_rate": 2.9971306130445305e-05, | |
| "loss": 1.647475814819336, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 0.15037593984962405, | |
| "grad_norm": 1.3921107053756714, | |
| "learning_rate": 2.996865157593119e-05, | |
| "loss": 1.6432958602905274, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 0.15296862846772102, | |
| "grad_norm": 1.399657964706421, | |
| "learning_rate": 2.9965879730544968e-05, | |
| "loss": 1.6632362365722657, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 0.155561317085818, | |
| "grad_norm": 1.6916463375091553, | |
| "learning_rate": 2.996299061600619e-05, | |
| "loss": 1.6300394058227539, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.15815400570391497, | |
| "grad_norm": 1.7113163471221924, | |
| "learning_rate": 2.9959984254953276e-05, | |
| "loss": 1.6330863952636718, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 0.1607466943220119, | |
| "grad_norm": 1.5331860780715942, | |
| "learning_rate": 2.9956860670943375e-05, | |
| "loss": 1.5855411529541015, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 0.16333938294010888, | |
| "grad_norm": 1.700958013534546, | |
| "learning_rate": 2.9953619888452156e-05, | |
| "loss": 1.61474609375, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 0.16593207155820586, | |
| "grad_norm": 1.7234867811203003, | |
| "learning_rate": 2.995026193287365e-05, | |
| "loss": 1.6093793869018556, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 0.16852476017630283, | |
| "grad_norm": 1.7460917234420776, | |
| "learning_rate": 2.9946786830520007e-05, | |
| "loss": 1.6209524154663086, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.1711174487943998, | |
| "grad_norm": 1.5481910705566406, | |
| "learning_rate": 2.9943194608621323e-05, | |
| "loss": 1.6162069320678711, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 0.17371013741249675, | |
| "grad_norm": 1.920379638671875, | |
| "learning_rate": 2.9939485295325412e-05, | |
| "loss": 1.6570716857910157, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 0.17630282603059372, | |
| "grad_norm": 1.456347942352295, | |
| "learning_rate": 2.9935658919697594e-05, | |
| "loss": 1.588156032562256, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 0.1788955146486907, | |
| "grad_norm": 1.921565294265747, | |
| "learning_rate": 2.9931715511720455e-05, | |
| "loss": 1.6013357162475585, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 0.18148820326678766, | |
| "grad_norm": 1.875504732131958, | |
| "learning_rate": 2.992765510229362e-05, | |
| "loss": 1.632054328918457, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.18408089188488463, | |
| "grad_norm": 1.7401937246322632, | |
| "learning_rate": 2.992347772323352e-05, | |
| "loss": 1.5879243850708007, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 0.18667358050298158, | |
| "grad_norm": 1.4971174001693726, | |
| "learning_rate": 2.9919183407273126e-05, | |
| "loss": 1.6358772277832032, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 0.18926626912107855, | |
| "grad_norm": 1.8517812490463257, | |
| "learning_rate": 2.991477218806169e-05, | |
| "loss": 1.5942300796508788, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 0.19185895773917552, | |
| "grad_norm": 1.7906169891357422, | |
| "learning_rate": 2.991024410016451e-05, | |
| "loss": 1.6056285858154298, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 0.1944516463572725, | |
| "grad_norm": 1.7057501077651978, | |
| "learning_rate": 2.990559917906262e-05, | |
| "loss": 1.5925214767456055, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.19704433497536947, | |
| "grad_norm": 1.900687336921692, | |
| "learning_rate": 2.990083746115255e-05, | |
| "loss": 1.5858644485473632, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 0.1996370235934664, | |
| "grad_norm": 1.8664599657058716, | |
| "learning_rate": 2.9895958983746004e-05, | |
| "loss": 1.6028635025024414, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 0.20222971221156338, | |
| "grad_norm": 2.207900285720825, | |
| "learning_rate": 2.9890963785069605e-05, | |
| "loss": 1.5772765159606934, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 0.20482240082966036, | |
| "grad_norm": 1.7628965377807617, | |
| "learning_rate": 2.988585190426457e-05, | |
| "loss": 1.5588774681091309, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 0.20741508944775733, | |
| "grad_norm": 2.1701314449310303, | |
| "learning_rate": 2.98806233813864e-05, | |
| "loss": 1.5740567207336427, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.2100077780658543, | |
| "grad_norm": 1.7453765869140625, | |
| "learning_rate": 2.9875278257404583e-05, | |
| "loss": 1.5921754837036133, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 0.21260046668395124, | |
| "grad_norm": 1.77922785282135, | |
| "learning_rate": 2.9869816574202273e-05, | |
| "loss": 1.5537161827087402, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 0.21519315530204822, | |
| "grad_norm": 1.8443162441253662, | |
| "learning_rate": 2.9864238374575952e-05, | |
| "loss": 1.5755566596984862, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 0.2177858439201452, | |
| "grad_norm": 1.913630485534668, | |
| "learning_rate": 2.9858543702235087e-05, | |
| "loss": 1.6065607070922852, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 0.22037853253824216, | |
| "grad_norm": 2.5680060386657715, | |
| "learning_rate": 2.985273260180181e-05, | |
| "loss": 1.5453169822692872, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 0.22297122115633913, | |
| "grad_norm": 2.0303702354431152, | |
| "learning_rate": 2.984680511881055e-05, | |
| "loss": 1.596198844909668, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 0.22556390977443608, | |
| "grad_norm": 1.5549193620681763, | |
| "learning_rate": 2.9840761299707694e-05, | |
| "loss": 1.568855381011963, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 0.22815659839253305, | |
| "grad_norm": 1.7885875701904297, | |
| "learning_rate": 2.9834601191851187e-05, | |
| "loss": 1.5498332023620605, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 0.23074928701063002, | |
| "grad_norm": 2.0089168548583984, | |
| "learning_rate": 2.9828324843510214e-05, | |
| "loss": 1.5433233261108399, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 0.233341975628727, | |
| "grad_norm": 2.1354048252105713, | |
| "learning_rate": 2.9821932303864776e-05, | |
| "loss": 1.5958542823791504, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.23593466424682397, | |
| "grad_norm": 2.3687899112701416, | |
| "learning_rate": 2.981542362300533e-05, | |
| "loss": 1.5683826446533202, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 0.2385273528649209, | |
| "grad_norm": 2.329882860183716, | |
| "learning_rate": 2.9808798851932375e-05, | |
| "loss": 1.6122396469116211, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 0.24112004148301788, | |
| "grad_norm": 1.9204554557800293, | |
| "learning_rate": 2.980205804255609e-05, | |
| "loss": 1.5680127143859863, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 0.24371273010111486, | |
| "grad_norm": 2.02498459815979, | |
| "learning_rate": 2.9795201247695885e-05, | |
| "loss": 1.53897123336792, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 0.24630541871921183, | |
| "grad_norm": 1.5861380100250244, | |
| "learning_rate": 2.9788228521080002e-05, | |
| "loss": 1.5421215057373048, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 0.2488981073373088, | |
| "grad_norm": 1.801835536956787, | |
| "learning_rate": 2.9781139917345113e-05, | |
| "loss": 1.5495308876037597, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 0.25149079595540574, | |
| "grad_norm": 2.1597230434417725, | |
| "learning_rate": 2.9773935492035868e-05, | |
| "loss": 1.5722169876098633, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 0.2540834845735027, | |
| "grad_norm": 2.119235038757324, | |
| "learning_rate": 2.9766615301604467e-05, | |
| "loss": 1.5267520904541017, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 0.2566761731915997, | |
| "grad_norm": 1.9513345956802368, | |
| "learning_rate": 2.9759179403410216e-05, | |
| "loss": 1.5414809226989745, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 0.25926886180969666, | |
| "grad_norm": 1.8692830801010132, | |
| "learning_rate": 2.9751627855719086e-05, | |
| "loss": 1.545905590057373, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.25926886180969666, | |
| "eval_loss": 1.5521949529647827, | |
| "eval_runtime": 105.9297, | |
| "eval_samples_per_second": 15.331, | |
| "eval_steps_per_second": 15.331, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.26186155042779363, | |
| "grad_norm": 1.7280081510543823, | |
| "learning_rate": 2.974396071770325e-05, | |
| "loss": 1.5839033126831055, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 0.2644542390458906, | |
| "grad_norm": 1.5108997821807861, | |
| "learning_rate": 2.9736178049440613e-05, | |
| "loss": 1.5561725616455078, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 0.2670469276639876, | |
| "grad_norm": 1.8250467777252197, | |
| "learning_rate": 2.9728279911914364e-05, | |
| "loss": 1.5358820915222169, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 0.26963961628208455, | |
| "grad_norm": 2.029668092727661, | |
| "learning_rate": 2.972026636701246e-05, | |
| "loss": 1.553438091278076, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 0.27223230490018147, | |
| "grad_norm": 1.8540805578231812, | |
| "learning_rate": 2.971213747752718e-05, | |
| "loss": 1.5556982040405274, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 0.27482499351827844, | |
| "grad_norm": 1.7269654273986816, | |
| "learning_rate": 2.970389330715461e-05, | |
| "loss": 1.5581286430358887, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 0.2774176821363754, | |
| "grad_norm": 2.0595953464508057, | |
| "learning_rate": 2.9695533920494154e-05, | |
| "loss": 1.5113532066345214, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 0.2800103707544724, | |
| "grad_norm": 2.1933727264404297, | |
| "learning_rate": 2.968705938304802e-05, | |
| "loss": 1.5415559768676759, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 0.28260305937256935, | |
| "grad_norm": 2.0160536766052246, | |
| "learning_rate": 2.9678469761220713e-05, | |
| "loss": 1.489687156677246, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 0.2851957479906663, | |
| "grad_norm": 1.5818418264389038, | |
| "learning_rate": 2.9669765122318506e-05, | |
| "loss": 1.5600990295410155, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.2877884366087633, | |
| "grad_norm": 1.8866775035858154, | |
| "learning_rate": 2.9660945534548933e-05, | |
| "loss": 1.5680411338806153, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 0.29038112522686027, | |
| "grad_norm": 1.8531945943832397, | |
| "learning_rate": 2.9652011067020225e-05, | |
| "loss": 1.5095998764038085, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 0.29297381384495724, | |
| "grad_norm": 2.0008137226104736, | |
| "learning_rate": 2.96429617897408e-05, | |
| "loss": 1.543956184387207, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 0.2955665024630542, | |
| "grad_norm": 1.696394681930542, | |
| "learning_rate": 2.9633797773618683e-05, | |
| "loss": 1.5572497367858886, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 0.29815919108115113, | |
| "grad_norm": 1.856203556060791, | |
| "learning_rate": 2.9624519090460977e-05, | |
| "loss": 1.5321713447570802, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 0.3007518796992481, | |
| "grad_norm": 1.983908772468567, | |
| "learning_rate": 2.9615125812973284e-05, | |
| "loss": 1.5194916725158691, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 0.3033445683173451, | |
| "grad_norm": 1.8463765382766724, | |
| "learning_rate": 2.9605618014759135e-05, | |
| "loss": 1.54110746383667, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 0.30593725693544205, | |
| "grad_norm": 2.1281657218933105, | |
| "learning_rate": 2.9595995770319432e-05, | |
| "loss": 1.5438779830932616, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 0.308529945553539, | |
| "grad_norm": 2.2548391819000244, | |
| "learning_rate": 2.9586259155051847e-05, | |
| "loss": 1.4930756568908692, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 0.311122634171636, | |
| "grad_norm": 1.8192869424819946, | |
| "learning_rate": 2.957640824525023e-05, | |
| "loss": 1.4750795364379883, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.31371532278973296, | |
| "grad_norm": 1.9327999353408813, | |
| "learning_rate": 2.9566443118104013e-05, | |
| "loss": 1.5061716079711913, | |
| "step": 1210 | |
| }, | |
| { | |
| "epoch": 0.31630801140782994, | |
| "grad_norm": 2.6463584899902344, | |
| "learning_rate": 2.955636385169762e-05, | |
| "loss": 1.4914235115051269, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 0.3189007000259269, | |
| "grad_norm": 1.802319884300232, | |
| "learning_rate": 2.9546170525009845e-05, | |
| "loss": 1.5331766128540039, | |
| "step": 1230 | |
| }, | |
| { | |
| "epoch": 0.3214933886440238, | |
| "grad_norm": 1.733071208000183, | |
| "learning_rate": 2.9535863217913207e-05, | |
| "loss": 1.5249350547790528, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 0.3240860772621208, | |
| "grad_norm": 2.096780300140381, | |
| "learning_rate": 2.9525442011173383e-05, | |
| "loss": 1.506511402130127, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 0.32667876588021777, | |
| "grad_norm": 1.789000153541565, | |
| "learning_rate": 2.9514906986448516e-05, | |
| "loss": 1.4979613304138184, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 0.32927145449831474, | |
| "grad_norm": 2.3496737480163574, | |
| "learning_rate": 2.9504258226288613e-05, | |
| "loss": 1.5362759590148927, | |
| "step": 1270 | |
| }, | |
| { | |
| "epoch": 0.3318641431164117, | |
| "grad_norm": 2.1412160396575928, | |
| "learning_rate": 2.9493495814134887e-05, | |
| "loss": 1.5093208312988282, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 0.3344568317345087, | |
| "grad_norm": 2.7615764141082764, | |
| "learning_rate": 2.9482619834319088e-05, | |
| "loss": 1.4955772399902343, | |
| "step": 1290 | |
| }, | |
| { | |
| "epoch": 0.33704952035260566, | |
| "grad_norm": 1.8998992443084717, | |
| "learning_rate": 2.9471630372062864e-05, | |
| "loss": 1.5002532958984376, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 0.33964220897070263, | |
| "grad_norm": 1.8375203609466553, | |
| "learning_rate": 2.9460527513477093e-05, | |
| "loss": 1.4847103118896485, | |
| "step": 1310 | |
| }, | |
| { | |
| "epoch": 0.3422348975887996, | |
| "grad_norm": 2.5817832946777344, | |
| "learning_rate": 2.9449311345561185e-05, | |
| "loss": 1.4912428855895996, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 0.3448275862068966, | |
| "grad_norm": 1.6789653301239014, | |
| "learning_rate": 2.9437981956202422e-05, | |
| "loss": 1.5264065742492676, | |
| "step": 1330 | |
| }, | |
| { | |
| "epoch": 0.3474202748249935, | |
| "grad_norm": 1.9965680837631226, | |
| "learning_rate": 2.9426539434175272e-05, | |
| "loss": 1.5252839088439942, | |
| "step": 1340 | |
| }, | |
| { | |
| "epoch": 0.35001296344309046, | |
| "grad_norm": 2.63002872467041, | |
| "learning_rate": 2.941498386914067e-05, | |
| "loss": 1.5000991821289062, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 0.35260565206118744, | |
| "grad_norm": 1.781042218208313, | |
| "learning_rate": 2.9403315351645336e-05, | |
| "loss": 1.4635045051574707, | |
| "step": 1360 | |
| }, | |
| { | |
| "epoch": 0.3551983406792844, | |
| "grad_norm": 2.09206223487854, | |
| "learning_rate": 2.9391533973121064e-05, | |
| "loss": 1.51431884765625, | |
| "step": 1370 | |
| }, | |
| { | |
| "epoch": 0.3577910292973814, | |
| "grad_norm": 1.8178857564926147, | |
| "learning_rate": 2.937963982588399e-05, | |
| "loss": 1.5193375587463378, | |
| "step": 1380 | |
| }, | |
| { | |
| "epoch": 0.36038371791547835, | |
| "grad_norm": 2.0183215141296387, | |
| "learning_rate": 2.9367633003133886e-05, | |
| "loss": 1.5367141723632813, | |
| "step": 1390 | |
| }, | |
| { | |
| "epoch": 0.3629764065335753, | |
| "grad_norm": 1.7666372060775757, | |
| "learning_rate": 2.9355513598953425e-05, | |
| "loss": 1.5032243728637695, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.3655690951516723, | |
| "grad_norm": 1.8232026100158691, | |
| "learning_rate": 2.934328170830744e-05, | |
| "loss": 1.5230186462402344, | |
| "step": 1410 | |
| }, | |
| { | |
| "epoch": 0.36816178376976927, | |
| "grad_norm": 2.2781875133514404, | |
| "learning_rate": 2.933093742704218e-05, | |
| "loss": 1.545018196105957, | |
| "step": 1420 | |
| }, | |
| { | |
| "epoch": 0.37075447238786624, | |
| "grad_norm": 1.9527894258499146, | |
| "learning_rate": 2.9318480851884555e-05, | |
| "loss": 1.5268414497375489, | |
| "step": 1430 | |
| }, | |
| { | |
| "epoch": 0.37334716100596316, | |
| "grad_norm": 1.85111403465271, | |
| "learning_rate": 2.93059120804414e-05, | |
| "loss": 1.514940071105957, | |
| "step": 1440 | |
| }, | |
| { | |
| "epoch": 0.37593984962406013, | |
| "grad_norm": 1.5911691188812256, | |
| "learning_rate": 2.9293231211198678e-05, | |
| "loss": 1.4724421501159668, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 0.3785325382421571, | |
| "grad_norm": 1.9510048627853394, | |
| "learning_rate": 2.9280438343520736e-05, | |
| "loss": 1.4826346397399903, | |
| "step": 1460 | |
| }, | |
| { | |
| "epoch": 0.3811252268602541, | |
| "grad_norm": 2.7119040489196777, | |
| "learning_rate": 2.9267533577649508e-05, | |
| "loss": 1.5354348182678224, | |
| "step": 1470 | |
| }, | |
| { | |
| "epoch": 0.38371791547835105, | |
| "grad_norm": 2.071737051010132, | |
| "learning_rate": 2.925451701470374e-05, | |
| "loss": 1.48195161819458, | |
| "step": 1480 | |
| }, | |
| { | |
| "epoch": 0.386310604096448, | |
| "grad_norm": 2.013737440109253, | |
| "learning_rate": 2.924138875667818e-05, | |
| "loss": 1.485996627807617, | |
| "step": 1490 | |
| }, | |
| { | |
| "epoch": 0.388903292714545, | |
| "grad_norm": 2.03083872795105, | |
| "learning_rate": 2.9228148906442822e-05, | |
| "loss": 1.538092041015625, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.388903292714545, | |
| "eval_loss": 1.5003650188446045, | |
| "eval_runtime": 106.3328, | |
| "eval_samples_per_second": 15.273, | |
| "eval_steps_per_second": 15.273, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.39149598133264196, | |
| "grad_norm": 1.617337703704834, | |
| "learning_rate": 2.9214797567742036e-05, | |
| "loss": 1.4525361061096191, | |
| "step": 1510 | |
| }, | |
| { | |
| "epoch": 0.39408866995073893, | |
| "grad_norm": 2.461519718170166, | |
| "learning_rate": 2.9201334845193823e-05, | |
| "loss": 1.4694942474365233, | |
| "step": 1520 | |
| }, | |
| { | |
| "epoch": 0.3966813585688359, | |
| "grad_norm": 1.9445669651031494, | |
| "learning_rate": 2.918776084428893e-05, | |
| "loss": 1.461592197418213, | |
| "step": 1530 | |
| }, | |
| { | |
| "epoch": 0.3992740471869328, | |
| "grad_norm": 2.038569927215576, | |
| "learning_rate": 2.917407567139008e-05, | |
| "loss": 1.511174774169922, | |
| "step": 1540 | |
| }, | |
| { | |
| "epoch": 0.4018667358050298, | |
| "grad_norm": 2.003824234008789, | |
| "learning_rate": 2.91602794337311e-05, | |
| "loss": 1.4884771347045898, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 0.40445942442312677, | |
| "grad_norm": 3.0072197914123535, | |
| "learning_rate": 2.9146372239416105e-05, | |
| "loss": 1.4911428451538087, | |
| "step": 1560 | |
| }, | |
| { | |
| "epoch": 0.40705211304122374, | |
| "grad_norm": 2.1022398471832275, | |
| "learning_rate": 2.9132354197418633e-05, | |
| "loss": 1.5100956916809083, | |
| "step": 1570 | |
| }, | |
| { | |
| "epoch": 0.4096448016593207, | |
| "grad_norm": 1.8543621301651, | |
| "learning_rate": 2.91182254175808e-05, | |
| "loss": 1.538217258453369, | |
| "step": 1580 | |
| }, | |
| { | |
| "epoch": 0.4122374902774177, | |
| "grad_norm": 1.6851848363876343, | |
| "learning_rate": 2.9103986010612435e-05, | |
| "loss": 1.4339521408081055, | |
| "step": 1590 | |
| }, | |
| { | |
| "epoch": 0.41483017889551466, | |
| "grad_norm": 2.1606297492980957, | |
| "learning_rate": 2.9089636088090222e-05, | |
| "loss": 1.471330738067627, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 0.41742286751361163, | |
| "grad_norm": 1.8915854692459106, | |
| "learning_rate": 2.9075175762456817e-05, | |
| "loss": 1.4531750679016113, | |
| "step": 1610 | |
| }, | |
| { | |
| "epoch": 0.4200155561317086, | |
| "grad_norm": 1.9127671718597412, | |
| "learning_rate": 2.9060605147019964e-05, | |
| "loss": 1.5028268814086914, | |
| "step": 1620 | |
| }, | |
| { | |
| "epoch": 0.4226082447498056, | |
| "grad_norm": 2.362971305847168, | |
| "learning_rate": 2.904592435595163e-05, | |
| "loss": 1.50010347366333, | |
| "step": 1630 | |
| }, | |
| { | |
| "epoch": 0.4252009333679025, | |
| "grad_norm": 1.7769346237182617, | |
| "learning_rate": 2.903113350428706e-05, | |
| "loss": 1.4772180557250976, | |
| "step": 1640 | |
| }, | |
| { | |
| "epoch": 0.42779362198599946, | |
| "grad_norm": 2.0999252796173096, | |
| "learning_rate": 2.9016232707923933e-05, | |
| "loss": 1.4838216781616211, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 0.43038631060409643, | |
| "grad_norm": 2.012392044067383, | |
| "learning_rate": 2.9001222083621433e-05, | |
| "loss": 1.4446197509765626, | |
| "step": 1660 | |
| }, | |
| { | |
| "epoch": 0.4329789992221934, | |
| "grad_norm": 2.1913809776306152, | |
| "learning_rate": 2.8986101748999312e-05, | |
| "loss": 1.4910202980041505, | |
| "step": 1670 | |
| }, | |
| { | |
| "epoch": 0.4355716878402904, | |
| "grad_norm": 2.4685049057006836, | |
| "learning_rate": 2.8970871822537e-05, | |
| "loss": 1.4822717666625977, | |
| "step": 1680 | |
| }, | |
| { | |
| "epoch": 0.43816437645838735, | |
| "grad_norm": 1.755044937133789, | |
| "learning_rate": 2.8955532423572654e-05, | |
| "loss": 1.4712723731994628, | |
| "step": 1690 | |
| }, | |
| { | |
| "epoch": 0.4407570650764843, | |
| "grad_norm": 1.873952031135559, | |
| "learning_rate": 2.894008367230224e-05, | |
| "loss": 1.4480696678161622, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 0.4433497536945813, | |
| "grad_norm": 2.0481786727905273, | |
| "learning_rate": 2.8924525689778572e-05, | |
| "loss": 1.4416559219360352, | |
| "step": 1710 | |
| }, | |
| { | |
| "epoch": 0.44594244231267827, | |
| "grad_norm": 2.0595901012420654, | |
| "learning_rate": 2.8908858597910395e-05, | |
| "loss": 1.4915009498596192, | |
| "step": 1720 | |
| }, | |
| { | |
| "epoch": 0.44853513093077524, | |
| "grad_norm": 1.6267675161361694, | |
| "learning_rate": 2.8893082519461387e-05, | |
| "loss": 1.4517938613891601, | |
| "step": 1730 | |
| }, | |
| { | |
| "epoch": 0.45112781954887216, | |
| "grad_norm": 1.8121838569641113, | |
| "learning_rate": 2.8877197578049233e-05, | |
| "loss": 1.5236659049987793, | |
| "step": 1740 | |
| }, | |
| { | |
| "epoch": 0.4537205081669691, | |
| "grad_norm": 2.1903886795043945, | |
| "learning_rate": 2.8861203898144635e-05, | |
| "loss": 1.4702713012695312, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 0.4563131967850661, | |
| "grad_norm": 2.377471685409546, | |
| "learning_rate": 2.8845101605070358e-05, | |
| "loss": 1.4455768585205078, | |
| "step": 1760 | |
| }, | |
| { | |
| "epoch": 0.45890588540316307, | |
| "grad_norm": 1.9816523790359497, | |
| "learning_rate": 2.8828890825000215e-05, | |
| "loss": 1.4934269905090332, | |
| "step": 1770 | |
| }, | |
| { | |
| "epoch": 0.46149857402126004, | |
| "grad_norm": 1.8602914810180664, | |
| "learning_rate": 2.8812571684958112e-05, | |
| "loss": 1.497078037261963, | |
| "step": 1780 | |
| }, | |
| { | |
| "epoch": 0.464091262639357, | |
| "grad_norm": 2.106839895248413, | |
| "learning_rate": 2.8796144312817037e-05, | |
| "loss": 1.4540966987609862, | |
| "step": 1790 | |
| }, | |
| { | |
| "epoch": 0.466683951257454, | |
| "grad_norm": 2.2227728366851807, | |
| "learning_rate": 2.8779608837298052e-05, | |
| "loss": 1.4421021461486816, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 0.46927663987555096, | |
| "grad_norm": 2.174560308456421, | |
| "learning_rate": 2.8762965387969303e-05, | |
| "loss": 1.4236719131469726, | |
| "step": 1810 | |
| }, | |
| { | |
| "epoch": 0.47186932849364793, | |
| "grad_norm": 2.3142716884613037, | |
| "learning_rate": 2.8746214095244983e-05, | |
| "loss": 1.475877857208252, | |
| "step": 1820 | |
| }, | |
| { | |
| "epoch": 0.4744620171117449, | |
| "grad_norm": 1.8860278129577637, | |
| "learning_rate": 2.872935509038433e-05, | |
| "loss": 1.4664278030395508, | |
| "step": 1830 | |
| }, | |
| { | |
| "epoch": 0.4770547057298418, | |
| "grad_norm": 2.211853504180908, | |
| "learning_rate": 2.871238850549058e-05, | |
| "loss": 1.4496440887451172, | |
| "step": 1840 | |
| }, | |
| { | |
| "epoch": 0.4796473943479388, | |
| "grad_norm": 1.8439429998397827, | |
| "learning_rate": 2.8695314473509952e-05, | |
| "loss": 1.4292086601257323, | |
| "step": 1850 | |
| }, | |
| { | |
| "epoch": 0.48224008296603577, | |
| "grad_norm": 1.799233078956604, | |
| "learning_rate": 2.867813312823058e-05, | |
| "loss": 1.4751974105834962, | |
| "step": 1860 | |
| }, | |
| { | |
| "epoch": 0.48483277158413274, | |
| "grad_norm": 1.6252014636993408, | |
| "learning_rate": 2.8660844604281496e-05, | |
| "loss": 1.4683155059814452, | |
| "step": 1870 | |
| }, | |
| { | |
| "epoch": 0.4874254602022297, | |
| "grad_norm": 2.7162091732025146, | |
| "learning_rate": 2.864344903713155e-05, | |
| "loss": 1.4836492538452148, | |
| "step": 1880 | |
| }, | |
| { | |
| "epoch": 0.4900181488203267, | |
| "grad_norm": 2.013542652130127, | |
| "learning_rate": 2.8625946563088363e-05, | |
| "loss": 1.4833683967590332, | |
| "step": 1890 | |
| }, | |
| { | |
| "epoch": 0.49261083743842365, | |
| "grad_norm": 2.020002841949463, | |
| "learning_rate": 2.8608337319297248e-05, | |
| "loss": 1.4674368858337403, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 0.4952035260565206, | |
| "grad_norm": 1.9161850214004517, | |
| "learning_rate": 2.8590621443740145e-05, | |
| "loss": 1.476041030883789, | |
| "step": 1910 | |
| }, | |
| { | |
| "epoch": 0.4977962146746176, | |
| "grad_norm": 2.2676491737365723, | |
| "learning_rate": 2.8572799075234533e-05, | |
| "loss": 1.4649261474609374, | |
| "step": 1920 | |
| }, | |
| { | |
| "epoch": 0.5003889032927146, | |
| "grad_norm": 1.9518834352493286, | |
| "learning_rate": 2.8554870353432345e-05, | |
| "loss": 1.4670692443847657, | |
| "step": 1930 | |
| }, | |
| { | |
| "epoch": 0.5029815919108115, | |
| "grad_norm": 1.8617761135101318, | |
| "learning_rate": 2.853683541881888e-05, | |
| "loss": 1.4522610664367677, | |
| "step": 1940 | |
| }, | |
| { | |
| "epoch": 0.5055742805289085, | |
| "grad_norm": 2.056037425994873, | |
| "learning_rate": 2.851869441271168e-05, | |
| "loss": 1.454219913482666, | |
| "step": 1950 | |
| }, | |
| { | |
| "epoch": 0.5081669691470054, | |
| "grad_norm": 1.6573052406311035, | |
| "learning_rate": 2.8500447477259458e-05, | |
| "loss": 1.4870268821716308, | |
| "step": 1960 | |
| }, | |
| { | |
| "epoch": 0.5107596577651025, | |
| "grad_norm": 1.8644371032714844, | |
| "learning_rate": 2.848209475544096e-05, | |
| "loss": 1.4083456993103027, | |
| "step": 1970 | |
| }, | |
| { | |
| "epoch": 0.5133523463831994, | |
| "grad_norm": 1.9450775384902954, | |
| "learning_rate": 2.8463636391063838e-05, | |
| "loss": 1.4940713882446288, | |
| "step": 1980 | |
| }, | |
| { | |
| "epoch": 0.5159450350012963, | |
| "grad_norm": 1.9806098937988281, | |
| "learning_rate": 2.8445072528763543e-05, | |
| "loss": 1.4620475769042969, | |
| "step": 1990 | |
| }, | |
| { | |
| "epoch": 0.5185377236193933, | |
| "grad_norm": 3.022106170654297, | |
| "learning_rate": 2.8426403314002182e-05, | |
| "loss": 1.465572452545166, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.5185377236193933, | |
| "eval_loss": 1.4653197526931763, | |
| "eval_runtime": 106.759, | |
| "eval_samples_per_second": 15.212, | |
| "eval_steps_per_second": 15.212, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.5211304122374902, | |
| "grad_norm": 1.9036056995391846, | |
| "learning_rate": 2.8407628893067384e-05, | |
| "loss": 1.4682519912719727, | |
| "step": 2010 | |
| }, | |
| { | |
| "epoch": 0.5237231008555873, | |
| "grad_norm": 1.9992440938949585, | |
| "learning_rate": 2.8388749413071137e-05, | |
| "loss": 1.445728874206543, | |
| "step": 2020 | |
| }, | |
| { | |
| "epoch": 0.5263157894736842, | |
| "grad_norm": 1.8911775350570679, | |
| "learning_rate": 2.8369765021948665e-05, | |
| "loss": 1.4920975685119628, | |
| "step": 2030 | |
| }, | |
| { | |
| "epoch": 0.5289084780917812, | |
| "grad_norm": 1.8128125667572021, | |
| "learning_rate": 2.835067586845723e-05, | |
| "loss": 1.4684887886047364, | |
| "step": 2040 | |
| }, | |
| { | |
| "epoch": 0.5315011667098781, | |
| "grad_norm": 1.9973891973495483, | |
| "learning_rate": 2.8331482102175e-05, | |
| "loss": 1.4452502250671386, | |
| "step": 2050 | |
| }, | |
| { | |
| "epoch": 0.5340938553279752, | |
| "grad_norm": 2.3160006999969482, | |
| "learning_rate": 2.8312183873499874e-05, | |
| "loss": 1.4670836448669433, | |
| "step": 2060 | |
| }, | |
| { | |
| "epoch": 0.5366865439460721, | |
| "grad_norm": 3.0418002605438232, | |
| "learning_rate": 2.8292781333648276e-05, | |
| "loss": 1.4837977409362793, | |
| "step": 2070 | |
| }, | |
| { | |
| "epoch": 0.5392792325641691, | |
| "grad_norm": 2.3682308197021484, | |
| "learning_rate": 2.827327463465399e-05, | |
| "loss": 1.3951645851135255, | |
| "step": 2080 | |
| }, | |
| { | |
| "epoch": 0.541871921182266, | |
| "grad_norm": 2.0320494174957275, | |
| "learning_rate": 2.8253663929366985e-05, | |
| "loss": 1.4565988540649415, | |
| "step": 2090 | |
| }, | |
| { | |
| "epoch": 0.5444646098003629, | |
| "grad_norm": 2.1780645847320557, | |
| "learning_rate": 2.8233949371452175e-05, | |
| "loss": 1.4297452926635743, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 0.54705729841846, | |
| "grad_norm": 1.7980337142944336, | |
| "learning_rate": 2.8214131115388252e-05, | |
| "loss": 1.4422244071960448, | |
| "step": 2110 | |
| }, | |
| { | |
| "epoch": 0.5496499870365569, | |
| "grad_norm": 2.1459109783172607, | |
| "learning_rate": 2.8194209316466468e-05, | |
| "loss": 1.4406557083129883, | |
| "step": 2120 | |
| }, | |
| { | |
| "epoch": 0.5522426756546539, | |
| "grad_norm": 1.6945514678955078, | |
| "learning_rate": 2.8174184130789397e-05, | |
| "loss": 1.461403751373291, | |
| "step": 2130 | |
| }, | |
| { | |
| "epoch": 0.5548353642727508, | |
| "grad_norm": 2.0341732501983643, | |
| "learning_rate": 2.815405571526974e-05, | |
| "loss": 1.4341069221496583, | |
| "step": 2140 | |
| }, | |
| { | |
| "epoch": 0.5574280528908478, | |
| "grad_norm": 2.373396158218384, | |
| "learning_rate": 2.813382422762908e-05, | |
| "loss": 1.431840705871582, | |
| "step": 2150 | |
| }, | |
| { | |
| "epoch": 0.5600207415089448, | |
| "grad_norm": 2.269397497177124, | |
| "learning_rate": 2.811348982639665e-05, | |
| "loss": 1.4188562393188477, | |
| "step": 2160 | |
| }, | |
| { | |
| "epoch": 0.5626134301270418, | |
| "grad_norm": 1.8616985082626343, | |
| "learning_rate": 2.8093052670908085e-05, | |
| "loss": 1.4132248878479003, | |
| "step": 2170 | |
| }, | |
| { | |
| "epoch": 0.5652061187451387, | |
| "grad_norm": 2.0249667167663574, | |
| "learning_rate": 2.8072512921304183e-05, | |
| "loss": 1.4546266555786134, | |
| "step": 2180 | |
| }, | |
| { | |
| "epoch": 0.5677988073632356, | |
| "grad_norm": 1.8128606081008911, | |
| "learning_rate": 2.8051870738529642e-05, | |
| "loss": 1.4023919105529785, | |
| "step": 2190 | |
| }, | |
| { | |
| "epoch": 0.5703914959813327, | |
| "grad_norm": 2.3444504737854004, | |
| "learning_rate": 2.8031126284331807e-05, | |
| "loss": 1.4102802276611328, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 0.5729841845994296, | |
| "grad_norm": 1.9829933643341064, | |
| "learning_rate": 2.8010279721259394e-05, | |
| "loss": 1.3986042976379394, | |
| "step": 2210 | |
| }, | |
| { | |
| "epoch": 0.5755768732175266, | |
| "grad_norm": 1.9822620153427124, | |
| "learning_rate": 2.7989331212661233e-05, | |
| "loss": 1.4648804664611816, | |
| "step": 2220 | |
| }, | |
| { | |
| "epoch": 0.5781695618356235, | |
| "grad_norm": 1.8543516397476196, | |
| "learning_rate": 2.796828092268495e-05, | |
| "loss": 1.4484143257141113, | |
| "step": 2230 | |
| }, | |
| { | |
| "epoch": 0.5807622504537205, | |
| "grad_norm": 2.4332776069641113, | |
| "learning_rate": 2.7947129016275726e-05, | |
| "loss": 1.4220855712890625, | |
| "step": 2240 | |
| }, | |
| { | |
| "epoch": 0.5833549390718175, | |
| "grad_norm": 2.7334249019622803, | |
| "learning_rate": 2.7925875659174986e-05, | |
| "loss": 1.4403745651245117, | |
| "step": 2250 | |
| }, | |
| { | |
| "epoch": 0.5859476276899145, | |
| "grad_norm": 2.114351987838745, | |
| "learning_rate": 2.7904521017919085e-05, | |
| "loss": 1.430521583557129, | |
| "step": 2260 | |
| }, | |
| { | |
| "epoch": 0.5885403163080114, | |
| "grad_norm": 2.0641672611236572, | |
| "learning_rate": 2.7883065259838027e-05, | |
| "loss": 1.4642662048339843, | |
| "step": 2270 | |
| }, | |
| { | |
| "epoch": 0.5911330049261084, | |
| "grad_norm": 1.8869924545288086, | |
| "learning_rate": 2.7861508553054143e-05, | |
| "loss": 1.4055952072143554, | |
| "step": 2280 | |
| }, | |
| { | |
| "epoch": 0.5937256935442053, | |
| "grad_norm": 2.004831075668335, | |
| "learning_rate": 2.7839851066480774e-05, | |
| "loss": 1.4892603874206543, | |
| "step": 2290 | |
| }, | |
| { | |
| "epoch": 0.5963183821623023, | |
| "grad_norm": 2.32817006111145, | |
| "learning_rate": 2.7818092969820946e-05, | |
| "loss": 1.4264138221740723, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 0.5989110707803993, | |
| "grad_norm": 1.7029457092285156, | |
| "learning_rate": 2.7796234433566045e-05, | |
| "loss": 1.4583550453186036, | |
| "step": 2310 | |
| }, | |
| { | |
| "epoch": 0.6015037593984962, | |
| "grad_norm": 3.0929977893829346, | |
| "learning_rate": 2.7774275628994474e-05, | |
| "loss": 1.4421024322509766, | |
| "step": 2320 | |
| }, | |
| { | |
| "epoch": 0.6040964480165932, | |
| "grad_norm": 2.268214464187622, | |
| "learning_rate": 2.775221672817032e-05, | |
| "loss": 1.4478707313537598, | |
| "step": 2330 | |
| }, | |
| { | |
| "epoch": 0.6066891366346902, | |
| "grad_norm": 2.46733021736145, | |
| "learning_rate": 2.7730057903941997e-05, | |
| "loss": 1.42803955078125, | |
| "step": 2340 | |
| }, | |
| { | |
| "epoch": 0.6092818252527872, | |
| "grad_norm": 2.2705399990081787, | |
| "learning_rate": 2.7707799329940905e-05, | |
| "loss": 1.411041831970215, | |
| "step": 2350 | |
| }, | |
| { | |
| "epoch": 0.6118745138708841, | |
| "grad_norm": 2.3257198333740234, | |
| "learning_rate": 2.7685441180580045e-05, | |
| "loss": 1.4445446014404297, | |
| "step": 2360 | |
| }, | |
| { | |
| "epoch": 0.6144672024889811, | |
| "grad_norm": 1.7774648666381836, | |
| "learning_rate": 2.7662983631052674e-05, | |
| "loss": 1.3862037658691406, | |
| "step": 2370 | |
| }, | |
| { | |
| "epoch": 0.617059891107078, | |
| "grad_norm": 1.9445077180862427, | |
| "learning_rate": 2.7640426857330935e-05, | |
| "loss": 1.4396771430969237, | |
| "step": 2380 | |
| }, | |
| { | |
| "epoch": 0.619652579725175, | |
| "grad_norm": 1.7664343118667603, | |
| "learning_rate": 2.7617771036164454e-05, | |
| "loss": 1.4648002624511718, | |
| "step": 2390 | |
| }, | |
| { | |
| "epoch": 0.622245268343272, | |
| "grad_norm": 1.8867270946502686, | |
| "learning_rate": 2.7595016345078973e-05, | |
| "loss": 1.4120534896850585, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 0.6248379569613689, | |
| "grad_norm": 1.89567232131958, | |
| "learning_rate": 2.757216296237496e-05, | |
| "loss": 1.4406702995300293, | |
| "step": 2410 | |
| }, | |
| { | |
| "epoch": 0.6274306455794659, | |
| "grad_norm": 1.906657099723816, | |
| "learning_rate": 2.7549211067126216e-05, | |
| "loss": 1.4870542526245116, | |
| "step": 2420 | |
| }, | |
| { | |
| "epoch": 0.6300233341975628, | |
| "grad_norm": 2.4880735874176025, | |
| "learning_rate": 2.7526160839178446e-05, | |
| "loss": 1.4118797302246093, | |
| "step": 2430 | |
| }, | |
| { | |
| "epoch": 0.6326160228156599, | |
| "grad_norm": 2.032667398452759, | |
| "learning_rate": 2.7503012459147874e-05, | |
| "loss": 1.4260003089904785, | |
| "step": 2440 | |
| }, | |
| { | |
| "epoch": 0.6352087114337568, | |
| "grad_norm": 1.8648145198822021, | |
| "learning_rate": 2.7479766108419822e-05, | |
| "loss": 1.3991647720336915, | |
| "step": 2450 | |
| }, | |
| { | |
| "epoch": 0.6378014000518538, | |
| "grad_norm": 2.0754902362823486, | |
| "learning_rate": 2.745642196914729e-05, | |
| "loss": 1.388667678833008, | |
| "step": 2460 | |
| }, | |
| { | |
| "epoch": 0.6403940886699507, | |
| "grad_norm": 1.8423649072647095, | |
| "learning_rate": 2.7432980224249518e-05, | |
| "loss": 1.3759624481201171, | |
| "step": 2470 | |
| }, | |
| { | |
| "epoch": 0.6429867772880477, | |
| "grad_norm": 2.0130422115325928, | |
| "learning_rate": 2.7409441057410573e-05, | |
| "loss": 1.4217917442321777, | |
| "step": 2480 | |
| }, | |
| { | |
| "epoch": 0.6455794659061447, | |
| "grad_norm": 2.455008029937744, | |
| "learning_rate": 2.7385804653077892e-05, | |
| "loss": 1.456618881225586, | |
| "step": 2490 | |
| }, | |
| { | |
| "epoch": 0.6481721545242416, | |
| "grad_norm": 1.8520952463150024, | |
| "learning_rate": 2.7362071196460833e-05, | |
| "loss": 1.4096790313720704, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.6481721545242416, | |
| "eval_loss": 1.4393162727355957, | |
| "eval_runtime": 106.7963, | |
| "eval_samples_per_second": 15.207, | |
| "eval_steps_per_second": 15.207, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.6507648431423386, | |
| "grad_norm": 2.681671380996704, | |
| "learning_rate": 2.733824087352925e-05, | |
| "loss": 1.4034467697143556, | |
| "step": 2510 | |
| }, | |
| { | |
| "epoch": 0.6533575317604355, | |
| "grad_norm": 1.83461332321167, | |
| "learning_rate": 2.731431387101201e-05, | |
| "loss": 1.449177074432373, | |
| "step": 2520 | |
| }, | |
| { | |
| "epoch": 0.6559502203785326, | |
| "grad_norm": 2.2103195190429688, | |
| "learning_rate": 2.729029037639553e-05, | |
| "loss": 1.4404438018798829, | |
| "step": 2530 | |
| }, | |
| { | |
| "epoch": 0.6585429089966295, | |
| "grad_norm": 2.1064565181732178, | |
| "learning_rate": 2.7266170577922338e-05, | |
| "loss": 1.4397605895996093, | |
| "step": 2540 | |
| }, | |
| { | |
| "epoch": 0.6611355976147265, | |
| "grad_norm": 2.108570098876953, | |
| "learning_rate": 2.7241954664589564e-05, | |
| "loss": 1.4023234367370605, | |
| "step": 2550 | |
| }, | |
| { | |
| "epoch": 0.6637282862328234, | |
| "grad_norm": 2.1899399757385254, | |
| "learning_rate": 2.721764282614746e-05, | |
| "loss": 1.3870964050292969, | |
| "step": 2560 | |
| }, | |
| { | |
| "epoch": 0.6663209748509205, | |
| "grad_norm": 1.746741771697998, | |
| "learning_rate": 2.719323525309795e-05, | |
| "loss": 1.3814775466918945, | |
| "step": 2570 | |
| }, | |
| { | |
| "epoch": 0.6689136634690174, | |
| "grad_norm": 1.656768560409546, | |
| "learning_rate": 2.7168732136693093e-05, | |
| "loss": 1.4419045448303223, | |
| "step": 2580 | |
| }, | |
| { | |
| "epoch": 0.6715063520871143, | |
| "grad_norm": 3.0307178497314453, | |
| "learning_rate": 2.714413366893361e-05, | |
| "loss": 1.3995821952819825, | |
| "step": 2590 | |
| }, | |
| { | |
| "epoch": 0.6740990407052113, | |
| "grad_norm": 2.4623610973358154, | |
| "learning_rate": 2.711944004256738e-05, | |
| "loss": 1.4528799057006836, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 0.6766917293233082, | |
| "grad_norm": 1.8382195234298706, | |
| "learning_rate": 2.7094651451087907e-05, | |
| "loss": 1.3911012649536132, | |
| "step": 2610 | |
| }, | |
| { | |
| "epoch": 0.6792844179414053, | |
| "grad_norm": 3.641540288925171, | |
| "learning_rate": 2.706976808873283e-05, | |
| "loss": 1.400215244293213, | |
| "step": 2620 | |
| }, | |
| { | |
| "epoch": 0.6818771065595022, | |
| "grad_norm": 1.7411173582077026, | |
| "learning_rate": 2.704479015048239e-05, | |
| "loss": 1.404646873474121, | |
| "step": 2630 | |
| }, | |
| { | |
| "epoch": 0.6844697951775992, | |
| "grad_norm": 2.683783769607544, | |
| "learning_rate": 2.7019717832057904e-05, | |
| "loss": 1.3790535926818848, | |
| "step": 2640 | |
| }, | |
| { | |
| "epoch": 0.6870624837956961, | |
| "grad_norm": 1.8364287614822388, | |
| "learning_rate": 2.699455132992022e-05, | |
| "loss": 1.3990992546081542, | |
| "step": 2650 | |
| }, | |
| { | |
| "epoch": 0.6896551724137931, | |
| "grad_norm": 2.025310754776001, | |
| "learning_rate": 2.6969290841268202e-05, | |
| "loss": 1.3751747131347656, | |
| "step": 2660 | |
| }, | |
| { | |
| "epoch": 0.6922478610318901, | |
| "grad_norm": 2.1249916553497314, | |
| "learning_rate": 2.6943936564037162e-05, | |
| "loss": 1.4457441329956056, | |
| "step": 2670 | |
| }, | |
| { | |
| "epoch": 0.694840549649987, | |
| "grad_norm": 2.500828504562378, | |
| "learning_rate": 2.6918488696897317e-05, | |
| "loss": 1.4443480491638183, | |
| "step": 2680 | |
| }, | |
| { | |
| "epoch": 0.697433238268084, | |
| "grad_norm": 1.8109062910079956, | |
| "learning_rate": 2.6892947439252235e-05, | |
| "loss": 1.4244956016540526, | |
| "step": 2690 | |
| }, | |
| { | |
| "epoch": 0.7000259268861809, | |
| "grad_norm": 1.89621901512146, | |
| "learning_rate": 2.6867312991237273e-05, | |
| "loss": 1.4510159492492676, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 0.702618615504278, | |
| "grad_norm": 2.3199923038482666, | |
| "learning_rate": 2.6841585553718004e-05, | |
| "loss": 1.4402318000793457, | |
| "step": 2710 | |
| }, | |
| { | |
| "epoch": 0.7052113041223749, | |
| "grad_norm": 2.2991762161254883, | |
| "learning_rate": 2.6815765328288635e-05, | |
| "loss": 1.4123191833496094, | |
| "step": 2720 | |
| }, | |
| { | |
| "epoch": 0.7078039927404719, | |
| "grad_norm": 2.122211456298828, | |
| "learning_rate": 2.678985251727046e-05, | |
| "loss": 1.4056102752685546, | |
| "step": 2730 | |
| }, | |
| { | |
| "epoch": 0.7103966813585688, | |
| "grad_norm": 2.127281665802002, | |
| "learning_rate": 2.676384732371023e-05, | |
| "loss": 1.403761100769043, | |
| "step": 2740 | |
| }, | |
| { | |
| "epoch": 0.7129893699766658, | |
| "grad_norm": 1.9112132787704468, | |
| "learning_rate": 2.6737749951378598e-05, | |
| "loss": 1.4536319732666017, | |
| "step": 2750 | |
| }, | |
| { | |
| "epoch": 0.7155820585947628, | |
| "grad_norm": 2.0709035396575928, | |
| "learning_rate": 2.6711560604768498e-05, | |
| "loss": 1.414163589477539, | |
| "step": 2760 | |
| }, | |
| { | |
| "epoch": 0.7181747472128598, | |
| "grad_norm": 2.218517303466797, | |
| "learning_rate": 2.668527948909356e-05, | |
| "loss": 1.4018719673156739, | |
| "step": 2770 | |
| }, | |
| { | |
| "epoch": 0.7207674358309567, | |
| "grad_norm": 2.193014621734619, | |
| "learning_rate": 2.6658906810286496e-05, | |
| "loss": 1.3908894538879395, | |
| "step": 2780 | |
| }, | |
| { | |
| "epoch": 0.7233601244490536, | |
| "grad_norm": 2.02219820022583, | |
| "learning_rate": 2.6632442774997485e-05, | |
| "loss": 1.403691005706787, | |
| "step": 2790 | |
| }, | |
| { | |
| "epoch": 0.7259528130671506, | |
| "grad_norm": 2.1701290607452393, | |
| "learning_rate": 2.6605887590592547e-05, | |
| "loss": 1.3933732986450196, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 0.7285455016852476, | |
| "grad_norm": 2.215689182281494, | |
| "learning_rate": 2.657924146515193e-05, | |
| "loss": 1.421674633026123, | |
| "step": 2810 | |
| }, | |
| { | |
| "epoch": 0.7311381903033446, | |
| "grad_norm": 1.9339823722839355, | |
| "learning_rate": 2.655250460746848e-05, | |
| "loss": 1.40692081451416, | |
| "step": 2820 | |
| }, | |
| { | |
| "epoch": 0.7337308789214415, | |
| "grad_norm": 2.211097002029419, | |
| "learning_rate": 2.6525677227045992e-05, | |
| "loss": 1.4308547973632812, | |
| "step": 2830 | |
| }, | |
| { | |
| "epoch": 0.7363235675395385, | |
| "grad_norm": 1.846948504447937, | |
| "learning_rate": 2.649875953409758e-05, | |
| "loss": 1.3544227600097656, | |
| "step": 2840 | |
| }, | |
| { | |
| "epoch": 0.7389162561576355, | |
| "grad_norm": 2.253370761871338, | |
| "learning_rate": 2.6471751739544025e-05, | |
| "loss": 1.3974369049072266, | |
| "step": 2850 | |
| }, | |
| { | |
| "epoch": 0.7415089447757325, | |
| "grad_norm": 2.584125280380249, | |
| "learning_rate": 2.644465405501212e-05, | |
| "loss": 1.374016284942627, | |
| "step": 2860 | |
| }, | |
| { | |
| "epoch": 0.7441016333938294, | |
| "grad_norm": 2.0201058387756348, | |
| "learning_rate": 2.6417466692833025e-05, | |
| "loss": 1.3737750053405762, | |
| "step": 2870 | |
| }, | |
| { | |
| "epoch": 0.7466943220119263, | |
| "grad_norm": 2.6641993522644043, | |
| "learning_rate": 2.639018986604058e-05, | |
| "loss": 1.4150461196899413, | |
| "step": 2880 | |
| }, | |
| { | |
| "epoch": 0.7492870106300233, | |
| "grad_norm": 1.781146764755249, | |
| "learning_rate": 2.6362823788369655e-05, | |
| "loss": 1.4415416717529297, | |
| "step": 2890 | |
| }, | |
| { | |
| "epoch": 0.7518796992481203, | |
| "grad_norm": 2.356492519378662, | |
| "learning_rate": 2.6335368674254477e-05, | |
| "loss": 1.3569241523742677, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 0.7544723878662173, | |
| "grad_norm": 2.522078037261963, | |
| "learning_rate": 2.6307824738826926e-05, | |
| "loss": 1.3681366920471192, | |
| "step": 2910 | |
| }, | |
| { | |
| "epoch": 0.7570650764843142, | |
| "grad_norm": 2.1201329231262207, | |
| "learning_rate": 2.6280192197914877e-05, | |
| "loss": 1.3817105293273926, | |
| "step": 2920 | |
| }, | |
| { | |
| "epoch": 0.7596577651024112, | |
| "grad_norm": 2.2413649559020996, | |
| "learning_rate": 2.6252471268040493e-05, | |
| "loss": 1.400905704498291, | |
| "step": 2930 | |
| }, | |
| { | |
| "epoch": 0.7622504537205081, | |
| "grad_norm": 2.4653563499450684, | |
| "learning_rate": 2.6224662166418534e-05, | |
| "loss": 1.403571605682373, | |
| "step": 2940 | |
| }, | |
| { | |
| "epoch": 0.7648431423386052, | |
| "grad_norm": 2.268806219100952, | |
| "learning_rate": 2.619676511095465e-05, | |
| "loss": 1.4283622741699218, | |
| "step": 2950 | |
| }, | |
| { | |
| "epoch": 0.7674358309567021, | |
| "grad_norm": 2.0980496406555176, | |
| "learning_rate": 2.6168780320243677e-05, | |
| "loss": 1.4140192985534668, | |
| "step": 2960 | |
| }, | |
| { | |
| "epoch": 0.7700285195747991, | |
| "grad_norm": 1.9857174158096313, | |
| "learning_rate": 2.6140708013567934e-05, | |
| "loss": 1.3875184059143066, | |
| "step": 2970 | |
| }, | |
| { | |
| "epoch": 0.772621208192896, | |
| "grad_norm": 1.9916791915893555, | |
| "learning_rate": 2.6112548410895475e-05, | |
| "loss": 1.365940475463867, | |
| "step": 2980 | |
| }, | |
| { | |
| "epoch": 0.775213896810993, | |
| "grad_norm": 2.019430160522461, | |
| "learning_rate": 2.6084301732878408e-05, | |
| "loss": 1.443111515045166, | |
| "step": 2990 | |
| }, | |
| { | |
| "epoch": 0.77780658542909, | |
| "grad_norm": 1.927951455116272, | |
| "learning_rate": 2.605596820085112e-05, | |
| "loss": 1.3543405532836914, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.77780658542909, | |
| "eval_loss": 1.4166350364685059, | |
| "eval_runtime": 107.7992, | |
| "eval_samples_per_second": 15.065, | |
| "eval_steps_per_second": 15.065, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.7803992740471869, | |
| "grad_norm": 1.9161983728408813, | |
| "learning_rate": 2.602754803682859e-05, | |
| "loss": 1.3282281875610351, | |
| "step": 3010 | |
| }, | |
| { | |
| "epoch": 0.7829919626652839, | |
| "grad_norm": 2.404080867767334, | |
| "learning_rate": 2.5999041463504606e-05, | |
| "loss": 1.3783291816711425, | |
| "step": 3020 | |
| }, | |
| { | |
| "epoch": 0.7855846512833808, | |
| "grad_norm": 1.8124619722366333, | |
| "learning_rate": 2.5970448704250046e-05, | |
| "loss": 1.411635971069336, | |
| "step": 3030 | |
| }, | |
| { | |
| "epoch": 0.7881773399014779, | |
| "grad_norm": 1.8134435415267944, | |
| "learning_rate": 2.5941769983111126e-05, | |
| "loss": 1.3853766441345214, | |
| "step": 3040 | |
| }, | |
| { | |
| "epoch": 0.7907700285195748, | |
| "grad_norm": 2.2257771492004395, | |
| "learning_rate": 2.5913005524807626e-05, | |
| "loss": 1.375821304321289, | |
| "step": 3050 | |
| }, | |
| { | |
| "epoch": 0.7933627171376718, | |
| "grad_norm": 2.07965087890625, | |
| "learning_rate": 2.5884155554731156e-05, | |
| "loss": 1.382816696166992, | |
| "step": 3060 | |
| }, | |
| { | |
| "epoch": 0.7959554057557687, | |
| "grad_norm": 2.424480438232422, | |
| "learning_rate": 2.5855220298943373e-05, | |
| "loss": 1.3932998657226563, | |
| "step": 3070 | |
| }, | |
| { | |
| "epoch": 0.7985480943738656, | |
| "grad_norm": 1.829237461090088, | |
| "learning_rate": 2.582619998417421e-05, | |
| "loss": 1.3987897872924804, | |
| "step": 3080 | |
| }, | |
| { | |
| "epoch": 0.8011407829919627, | |
| "grad_norm": 2.279134511947632, | |
| "learning_rate": 2.5797094837820093e-05, | |
| "loss": 1.3800272941589355, | |
| "step": 3090 | |
| }, | |
| { | |
| "epoch": 0.8037334716100596, | |
| "grad_norm": 1.6486223936080933, | |
| "learning_rate": 2.5767905087942194e-05, | |
| "loss": 1.4012795448303224, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 0.8063261602281566, | |
| "grad_norm": 2.5895159244537354, | |
| "learning_rate": 2.57386309632646e-05, | |
| "loss": 1.3688448905944823, | |
| "step": 3110 | |
| }, | |
| { | |
| "epoch": 0.8089188488462535, | |
| "grad_norm": 2.2628800868988037, | |
| "learning_rate": 2.570927269317254e-05, | |
| "loss": 1.3984854698181153, | |
| "step": 3120 | |
| }, | |
| { | |
| "epoch": 0.8115115374643506, | |
| "grad_norm": 2.4762990474700928, | |
| "learning_rate": 2.5679830507710586e-05, | |
| "loss": 1.4081483840942384, | |
| "step": 3130 | |
| }, | |
| { | |
| "epoch": 0.8141042260824475, | |
| "grad_norm": 2.6553421020507812, | |
| "learning_rate": 2.5650304637580864e-05, | |
| "loss": 1.4029975891113282, | |
| "step": 3140 | |
| }, | |
| { | |
| "epoch": 0.8166969147005445, | |
| "grad_norm": 2.1516876220703125, | |
| "learning_rate": 2.562069531414122e-05, | |
| "loss": 1.376172161102295, | |
| "step": 3150 | |
| }, | |
| { | |
| "epoch": 0.8192896033186414, | |
| "grad_norm": 1.897744059562683, | |
| "learning_rate": 2.5591002769403423e-05, | |
| "loss": 1.4495765686035156, | |
| "step": 3160 | |
| }, | |
| { | |
| "epoch": 0.8218822919367385, | |
| "grad_norm": 1.8410879373550415, | |
| "learning_rate": 2.5561227236031354e-05, | |
| "loss": 1.378575611114502, | |
| "step": 3170 | |
| }, | |
| { | |
| "epoch": 0.8244749805548354, | |
| "grad_norm": 1.9492700099945068, | |
| "learning_rate": 2.553136894733916e-05, | |
| "loss": 1.3822572708129883, | |
| "step": 3180 | |
| }, | |
| { | |
| "epoch": 0.8270676691729323, | |
| "grad_norm": 2.2721168994903564, | |
| "learning_rate": 2.550142813728945e-05, | |
| "loss": 1.3540994644165039, | |
| "step": 3190 | |
| }, | |
| { | |
| "epoch": 0.8296603577910293, | |
| "grad_norm": 1.6297799348831177, | |
| "learning_rate": 2.5471405040491446e-05, | |
| "loss": 1.3411558151245118, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 0.8322530464091262, | |
| "grad_norm": 2.260117292404175, | |
| "learning_rate": 2.5441299892199153e-05, | |
| "loss": 1.322674560546875, | |
| "step": 3210 | |
| }, | |
| { | |
| "epoch": 0.8348457350272233, | |
| "grad_norm": 2.4971811771392822, | |
| "learning_rate": 2.541111292830951e-05, | |
| "loss": 1.4200034141540527, | |
| "step": 3220 | |
| }, | |
| { | |
| "epoch": 0.8374384236453202, | |
| "grad_norm": 2.0395963191986084, | |
| "learning_rate": 2.5380844385360543e-05, | |
| "loss": 1.4156583786010741, | |
| "step": 3230 | |
| }, | |
| { | |
| "epoch": 0.8400311122634172, | |
| "grad_norm": 1.8945432901382446, | |
| "learning_rate": 2.5350494500529516e-05, | |
| "loss": 1.392031192779541, | |
| "step": 3240 | |
| }, | |
| { | |
| "epoch": 0.8426238008815141, | |
| "grad_norm": 1.8795114755630493, | |
| "learning_rate": 2.5320063511631065e-05, | |
| "loss": 1.3640775680541992, | |
| "step": 3250 | |
| }, | |
| { | |
| "epoch": 0.8452164894996111, | |
| "grad_norm": 2.0058376789093018, | |
| "learning_rate": 2.5289551657115345e-05, | |
| "loss": 1.3475787162780761, | |
| "step": 3260 | |
| }, | |
| { | |
| "epoch": 0.8478091781177081, | |
| "grad_norm": 1.9326412677764893, | |
| "learning_rate": 2.5258959176066147e-05, | |
| "loss": 1.384262752532959, | |
| "step": 3270 | |
| }, | |
| { | |
| "epoch": 0.850401866735805, | |
| "grad_norm": 2.3330800533294678, | |
| "learning_rate": 2.522828630819904e-05, | |
| "loss": 1.4128545761108398, | |
| "step": 3280 | |
| }, | |
| { | |
| "epoch": 0.852994555353902, | |
| "grad_norm": 2.0641918182373047, | |
| "learning_rate": 2.5197533293859478e-05, | |
| "loss": 1.3618906021118165, | |
| "step": 3290 | |
| }, | |
| { | |
| "epoch": 0.8555872439719989, | |
| "grad_norm": 2.4750313758850098, | |
| "learning_rate": 2.516670037402093e-05, | |
| "loss": 1.3589738845825194, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 0.858179932590096, | |
| "grad_norm": 2.6838135719299316, | |
| "learning_rate": 2.5135787790282992e-05, | |
| "loss": 1.395717239379883, | |
| "step": 3310 | |
| }, | |
| { | |
| "epoch": 0.8607726212081929, | |
| "grad_norm": 3.1425156593322754, | |
| "learning_rate": 2.5104795784869467e-05, | |
| "loss": 1.3734113693237304, | |
| "step": 3320 | |
| }, | |
| { | |
| "epoch": 0.8633653098262899, | |
| "grad_norm": 2.109119176864624, | |
| "learning_rate": 2.5073724600626512e-05, | |
| "loss": 1.3802095413208009, | |
| "step": 3330 | |
| }, | |
| { | |
| "epoch": 0.8659579984443868, | |
| "grad_norm": 1.866578459739685, | |
| "learning_rate": 2.504257448102069e-05, | |
| "loss": 1.3721683502197266, | |
| "step": 3340 | |
| }, | |
| { | |
| "epoch": 0.8685506870624838, | |
| "grad_norm": 1.9887162446975708, | |
| "learning_rate": 2.5011345670137098e-05, | |
| "loss": 1.3654733657836915, | |
| "step": 3350 | |
| }, | |
| { | |
| "epoch": 0.8711433756805808, | |
| "grad_norm": 2.299468517303467, | |
| "learning_rate": 2.4980038412677435e-05, | |
| "loss": 1.3257240295410155, | |
| "step": 3360 | |
| }, | |
| { | |
| "epoch": 0.8737360642986778, | |
| "grad_norm": 1.8503848314285278, | |
| "learning_rate": 2.494865295395809e-05, | |
| "loss": 1.3851592063903808, | |
| "step": 3370 | |
| }, | |
| { | |
| "epoch": 0.8763287529167747, | |
| "grad_norm": 2.9072635173797607, | |
| "learning_rate": 2.4917189539908212e-05, | |
| "loss": 1.4008994102478027, | |
| "step": 3380 | |
| }, | |
| { | |
| "epoch": 0.8789214415348716, | |
| "grad_norm": 2.2361841201782227, | |
| "learning_rate": 2.4885648417067797e-05, | |
| "loss": 1.4155900955200196, | |
| "step": 3390 | |
| }, | |
| { | |
| "epoch": 0.8815141301529686, | |
| "grad_norm": 1.5103061199188232, | |
| "learning_rate": 2.485402983258575e-05, | |
| "loss": 1.383201503753662, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 0.8841068187710656, | |
| "grad_norm": 2.3880326747894287, | |
| "learning_rate": 2.4822334034217943e-05, | |
| "loss": 1.422282600402832, | |
| "step": 3410 | |
| }, | |
| { | |
| "epoch": 0.8866995073891626, | |
| "grad_norm": 2.0728979110717773, | |
| "learning_rate": 2.4790561270325282e-05, | |
| "loss": 1.3880194664001464, | |
| "step": 3420 | |
| }, | |
| { | |
| "epoch": 0.8892921960072595, | |
| "grad_norm": 2.1829416751861572, | |
| "learning_rate": 2.475871178987175e-05, | |
| "loss": 1.3314918518066405, | |
| "step": 3430 | |
| }, | |
| { | |
| "epoch": 0.8918848846253565, | |
| "grad_norm": 1.9193717241287231, | |
| "learning_rate": 2.472678584242247e-05, | |
| "loss": 1.357210636138916, | |
| "step": 3440 | |
| }, | |
| { | |
| "epoch": 0.8944775732434534, | |
| "grad_norm": 2.5747568607330322, | |
| "learning_rate": 2.469478367814174e-05, | |
| "loss": 1.3450111389160155, | |
| "step": 3450 | |
| }, | |
| { | |
| "epoch": 0.8970702618615505, | |
| "grad_norm": 2.431907892227173, | |
| "learning_rate": 2.4662705547791078e-05, | |
| "loss": 1.336769199371338, | |
| "step": 3460 | |
| }, | |
| { | |
| "epoch": 0.8996629504796474, | |
| "grad_norm": 2.294434070587158, | |
| "learning_rate": 2.4630551702727248e-05, | |
| "loss": 1.3879555702209472, | |
| "step": 3470 | |
| }, | |
| { | |
| "epoch": 0.9022556390977443, | |
| "grad_norm": 2.3190789222717285, | |
| "learning_rate": 2.4598322394900304e-05, | |
| "loss": 1.3749018669128419, | |
| "step": 3480 | |
| }, | |
| { | |
| "epoch": 0.9048483277158413, | |
| "grad_norm": 2.1272852420806885, | |
| "learning_rate": 2.4566017876851605e-05, | |
| "loss": 1.3837257385253907, | |
| "step": 3490 | |
| }, | |
| { | |
| "epoch": 0.9074410163339383, | |
| "grad_norm": 2.3905060291290283, | |
| "learning_rate": 2.4533638401711846e-05, | |
| "loss": 1.406574535369873, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.9074410163339383, | |
| "eval_loss": 1.3983689546585083, | |
| "eval_runtime": 106.204, | |
| "eval_samples_per_second": 15.291, | |
| "eval_steps_per_second": 15.291, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.9100337049520353, | |
| "grad_norm": 2.7370753288269043, | |
| "learning_rate": 2.4501184223199048e-05, | |
| "loss": 1.3768909454345704, | |
| "step": 3510 | |
| }, | |
| { | |
| "epoch": 0.9126263935701322, | |
| "grad_norm": 2.2996416091918945, | |
| "learning_rate": 2.4468655595616623e-05, | |
| "loss": 1.3813292503356933, | |
| "step": 3520 | |
| }, | |
| { | |
| "epoch": 0.9152190821882292, | |
| "grad_norm": 2.329495906829834, | |
| "learning_rate": 2.4436052773851317e-05, | |
| "loss": 1.3564909934997558, | |
| "step": 3530 | |
| }, | |
| { | |
| "epoch": 0.9178117708063261, | |
| "grad_norm": 1.9293724298477173, | |
| "learning_rate": 2.4403376013371267e-05, | |
| "loss": 1.4013836860656739, | |
| "step": 3540 | |
| }, | |
| { | |
| "epoch": 0.9204044594244232, | |
| "grad_norm": 1.7574388980865479, | |
| "learning_rate": 2.4370625570223964e-05, | |
| "loss": 1.4045954704284669, | |
| "step": 3550 | |
| }, | |
| { | |
| "epoch": 0.9229971480425201, | |
| "grad_norm": 2.2382349967956543, | |
| "learning_rate": 2.433780170103426e-05, | |
| "loss": 1.4007040977478027, | |
| "step": 3560 | |
| }, | |
| { | |
| "epoch": 0.925589836660617, | |
| "grad_norm": 1.8389666080474854, | |
| "learning_rate": 2.430490466300236e-05, | |
| "loss": 1.3762280464172363, | |
| "step": 3570 | |
| }, | |
| { | |
| "epoch": 0.928182525278714, | |
| "grad_norm": 2.4616801738739014, | |
| "learning_rate": 2.427193471390181e-05, | |
| "loss": 1.3494554519653321, | |
| "step": 3580 | |
| }, | |
| { | |
| "epoch": 0.930775213896811, | |
| "grad_norm": 2.219825506210327, | |
| "learning_rate": 2.4238892112077456e-05, | |
| "loss": 1.4177600860595703, | |
| "step": 3590 | |
| }, | |
| { | |
| "epoch": 0.933367902514908, | |
| "grad_norm": 2.9395411014556885, | |
| "learning_rate": 2.420577711644344e-05, | |
| "loss": 1.3394248008728027, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 0.9359605911330049, | |
| "grad_norm": 2.225367784500122, | |
| "learning_rate": 2.417258998648117e-05, | |
| "loss": 1.3538402557373046, | |
| "step": 3610 | |
| }, | |
| { | |
| "epoch": 0.9385532797511019, | |
| "grad_norm": 2.441420793533325, | |
| "learning_rate": 2.413933098223727e-05, | |
| "loss": 1.3856266975402831, | |
| "step": 3620 | |
| }, | |
| { | |
| "epoch": 0.9411459683691988, | |
| "grad_norm": 1.911476731300354, | |
| "learning_rate": 2.4106000364321562e-05, | |
| "loss": 1.384410285949707, | |
| "step": 3630 | |
| }, | |
| { | |
| "epoch": 0.9437386569872959, | |
| "grad_norm": 2.361011505126953, | |
| "learning_rate": 2.4072598393905027e-05, | |
| "loss": 1.3323063850402832, | |
| "step": 3640 | |
| }, | |
| { | |
| "epoch": 0.9463313456053928, | |
| "grad_norm": 1.8206897974014282, | |
| "learning_rate": 2.4039125332717723e-05, | |
| "loss": 1.3785643577575684, | |
| "step": 3650 | |
| }, | |
| { | |
| "epoch": 0.9489240342234898, | |
| "grad_norm": 2.124385118484497, | |
| "learning_rate": 2.4005581443046777e-05, | |
| "loss": 1.3628316879272462, | |
| "step": 3660 | |
| }, | |
| { | |
| "epoch": 0.9515167228415867, | |
| "grad_norm": 2.1028757095336914, | |
| "learning_rate": 2.3971966987734306e-05, | |
| "loss": 1.3821578979492188, | |
| "step": 3670 | |
| }, | |
| { | |
| "epoch": 0.9541094114596836, | |
| "grad_norm": 2.0314295291900635, | |
| "learning_rate": 2.3938282230175367e-05, | |
| "loss": 1.36130952835083, | |
| "step": 3680 | |
| }, | |
| { | |
| "epoch": 0.9567021000777807, | |
| "grad_norm": 1.9069913625717163, | |
| "learning_rate": 2.390452743431587e-05, | |
| "loss": 1.3943718910217284, | |
| "step": 3690 | |
| }, | |
| { | |
| "epoch": 0.9592947886958776, | |
| "grad_norm": 2.211771249771118, | |
| "learning_rate": 2.3870702864650566e-05, | |
| "loss": 1.2942493438720704, | |
| "step": 3700 | |
| }, | |
| { | |
| "epoch": 0.9618874773139746, | |
| "grad_norm": 1.8472073078155518, | |
| "learning_rate": 2.3836808786220898e-05, | |
| "loss": 1.3906041145324708, | |
| "step": 3710 | |
| }, | |
| { | |
| "epoch": 0.9644801659320715, | |
| "grad_norm": 1.956861138343811, | |
| "learning_rate": 2.3802845464612993e-05, | |
| "loss": 1.3306471824645996, | |
| "step": 3720 | |
| }, | |
| { | |
| "epoch": 0.9670728545501686, | |
| "grad_norm": 2.0990774631500244, | |
| "learning_rate": 2.376881316595553e-05, | |
| "loss": 1.3751443862915038, | |
| "step": 3730 | |
| }, | |
| { | |
| "epoch": 0.9696655431682655, | |
| "grad_norm": 2.325157403945923, | |
| "learning_rate": 2.3734712156917696e-05, | |
| "loss": 1.3435355186462403, | |
| "step": 3740 | |
| }, | |
| { | |
| "epoch": 0.9722582317863625, | |
| "grad_norm": 1.922559142112732, | |
| "learning_rate": 2.3700542704707047e-05, | |
| "loss": 1.3255187034606934, | |
| "step": 3750 | |
| }, | |
| { | |
| "epoch": 0.9748509204044594, | |
| "grad_norm": 1.7330152988433838, | |
| "learning_rate": 2.3666305077067487e-05, | |
| "loss": 1.3793014526367187, | |
| "step": 3760 | |
| }, | |
| { | |
| "epoch": 0.9774436090225563, | |
| "grad_norm": 2.2448415756225586, | |
| "learning_rate": 2.363199954227709e-05, | |
| "loss": 1.3383570671081544, | |
| "step": 3770 | |
| }, | |
| { | |
| "epoch": 0.9800362976406534, | |
| "grad_norm": 2.524059295654297, | |
| "learning_rate": 2.3597626369146042e-05, | |
| "loss": 1.34091796875, | |
| "step": 3780 | |
| }, | |
| { | |
| "epoch": 0.9826289862587503, | |
| "grad_norm": 2.139561176300049, | |
| "learning_rate": 2.3563185827014547e-05, | |
| "loss": 1.3502127647399902, | |
| "step": 3790 | |
| }, | |
| { | |
| "epoch": 0.9852216748768473, | |
| "grad_norm": 2.0120010375976562, | |
| "learning_rate": 2.3528678185750673e-05, | |
| "loss": 1.3552865982055664, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 0.9878143634949442, | |
| "grad_norm": 1.6602357625961304, | |
| "learning_rate": 2.349410371574827e-05, | |
| "loss": 1.4221920013427733, | |
| "step": 3810 | |
| }, | |
| { | |
| "epoch": 0.9904070521130413, | |
| "grad_norm": 2.8545217514038086, | |
| "learning_rate": 2.3459462687924843e-05, | |
| "loss": 1.330784225463867, | |
| "step": 3820 | |
| }, | |
| { | |
| "epoch": 0.9929997407311382, | |
| "grad_norm": 2.017984628677368, | |
| "learning_rate": 2.3424755373719434e-05, | |
| "loss": 1.3669758796691895, | |
| "step": 3830 | |
| }, | |
| { | |
| "epoch": 0.9955924293492352, | |
| "grad_norm": 1.9509679079055786, | |
| "learning_rate": 2.3389982045090476e-05, | |
| "loss": 1.3680663108825684, | |
| "step": 3840 | |
| }, | |
| { | |
| "epoch": 0.9981851179673321, | |
| "grad_norm": 2.055434226989746, | |
| "learning_rate": 2.3355142974513694e-05, | |
| "loss": 1.3688017845153808, | |
| "step": 3850 | |
| }, | |
| { | |
| "epoch": 1.0007778065854291, | |
| "grad_norm": 1.8395020961761475, | |
| "learning_rate": 2.3320238434979938e-05, | |
| "loss": 1.382623291015625, | |
| "step": 3860 | |
| }, | |
| { | |
| "epoch": 1.003370495203526, | |
| "grad_norm": 1.9601069688796997, | |
| "learning_rate": 2.3285268699993057e-05, | |
| "loss": 1.3295875549316407, | |
| "step": 3870 | |
| }, | |
| { | |
| "epoch": 1.005963183821623, | |
| "grad_norm": 1.961052417755127, | |
| "learning_rate": 2.3250234043567762e-05, | |
| "loss": 1.3183087348937987, | |
| "step": 3880 | |
| }, | |
| { | |
| "epoch": 1.00855587243972, | |
| "grad_norm": 1.9219014644622803, | |
| "learning_rate": 2.3215134740227477e-05, | |
| "loss": 1.368846607208252, | |
| "step": 3890 | |
| }, | |
| { | |
| "epoch": 1.011148561057817, | |
| "grad_norm": 3.1595990657806396, | |
| "learning_rate": 2.3179971065002175e-05, | |
| "loss": 1.3154706001281737, | |
| "step": 3900 | |
| }, | |
| { | |
| "epoch": 1.013741249675914, | |
| "grad_norm": 1.7380744218826294, | |
| "learning_rate": 2.3144743293426233e-05, | |
| "loss": 1.3345220565795899, | |
| "step": 3910 | |
| }, | |
| { | |
| "epoch": 1.0163339382940109, | |
| "grad_norm": 1.8892579078674316, | |
| "learning_rate": 2.310945170153628e-05, | |
| "loss": 1.316334342956543, | |
| "step": 3920 | |
| }, | |
| { | |
| "epoch": 1.0189266269121078, | |
| "grad_norm": 2.266141891479492, | |
| "learning_rate": 2.307409656586902e-05, | |
| "loss": 1.3499970436096191, | |
| "step": 3930 | |
| }, | |
| { | |
| "epoch": 1.021519315530205, | |
| "grad_norm": 3.2296090126037598, | |
| "learning_rate": 2.303867816345907e-05, | |
| "loss": 1.314054298400879, | |
| "step": 3940 | |
| }, | |
| { | |
| "epoch": 1.0241120041483018, | |
| "grad_norm": 2.2091379165649414, | |
| "learning_rate": 2.30031967718368e-05, | |
| "loss": 1.3708792686462403, | |
| "step": 3950 | |
| }, | |
| { | |
| "epoch": 1.0267046927663988, | |
| "grad_norm": 2.0963046550750732, | |
| "learning_rate": 2.2967652669026133e-05, | |
| "loss": 1.3194661140441895, | |
| "step": 3960 | |
| }, | |
| { | |
| "epoch": 1.0292973813844957, | |
| "grad_norm": 1.9970223903656006, | |
| "learning_rate": 2.2932046133542407e-05, | |
| "loss": 1.3267878532409667, | |
| "step": 3970 | |
| }, | |
| { | |
| "epoch": 1.0318900700025926, | |
| "grad_norm": 2.3387584686279297, | |
| "learning_rate": 2.289637744439013e-05, | |
| "loss": 1.366102695465088, | |
| "step": 3980 | |
| }, | |
| { | |
| "epoch": 1.0344827586206897, | |
| "grad_norm": 2.5074076652526855, | |
| "learning_rate": 2.2860646881060865e-05, | |
| "loss": 1.3781256675720215, | |
| "step": 3990 | |
| }, | |
| { | |
| "epoch": 1.0370754472387866, | |
| "grad_norm": 2.5516645908355713, | |
| "learning_rate": 2.2824854723530996e-05, | |
| "loss": 1.3624156951904296, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 1.0370754472387866, | |
| "eval_loss": 1.3833566904067993, | |
| "eval_runtime": 102.245, | |
| "eval_samples_per_second": 15.883, | |
| "eval_steps_per_second": 15.883, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 1.0396681358568836, | |
| "grad_norm": 2.016517400741577, | |
| "learning_rate": 2.2789001252259552e-05, | |
| "loss": 1.3006293296813964, | |
| "step": 4010 | |
| }, | |
| { | |
| "epoch": 1.0422608244749805, | |
| "grad_norm": 2.6499552726745605, | |
| "learning_rate": 2.2753086748185973e-05, | |
| "loss": 1.380314540863037, | |
| "step": 4020 | |
| }, | |
| { | |
| "epoch": 1.0448535130930776, | |
| "grad_norm": 2.3887665271759033, | |
| "learning_rate": 2.271711149272798e-05, | |
| "loss": 1.3405844688415527, | |
| "step": 4030 | |
| }, | |
| { | |
| "epoch": 1.0474462017111745, | |
| "grad_norm": 2.200329542160034, | |
| "learning_rate": 2.26810757677793e-05, | |
| "loss": 1.329063892364502, | |
| "step": 4040 | |
| }, | |
| { | |
| "epoch": 1.0500388903292714, | |
| "grad_norm": 2.6909101009368896, | |
| "learning_rate": 2.2644979855707486e-05, | |
| "loss": 1.3441936492919921, | |
| "step": 4050 | |
| }, | |
| { | |
| "epoch": 1.0526315789473684, | |
| "grad_norm": 2.213625192642212, | |
| "learning_rate": 2.2608824039351723e-05, | |
| "loss": 1.3089025497436524, | |
| "step": 4060 | |
| }, | |
| { | |
| "epoch": 1.0552242675654653, | |
| "grad_norm": 2.323392152786255, | |
| "learning_rate": 2.2572608602020563e-05, | |
| "loss": 1.288233470916748, | |
| "step": 4070 | |
| }, | |
| { | |
| "epoch": 1.0578169561835624, | |
| "grad_norm": 2.1220569610595703, | |
| "learning_rate": 2.2536333827489763e-05, | |
| "loss": 1.3579096794128418, | |
| "step": 4080 | |
| }, | |
| { | |
| "epoch": 1.0604096448016593, | |
| "grad_norm": 2.1429178714752197, | |
| "learning_rate": 2.25e-05, | |
| "loss": 1.3310029983520508, | |
| "step": 4090 | |
| }, | |
| { | |
| "epoch": 1.0630023334197563, | |
| "grad_norm": 2.5161702632904053, | |
| "learning_rate": 2.2463607404254716e-05, | |
| "loss": 1.3171113014221192, | |
| "step": 4100 | |
| }, | |
| { | |
| "epoch": 1.0655950220378532, | |
| "grad_norm": 1.9193251132965088, | |
| "learning_rate": 2.2427156325417814e-05, | |
| "loss": 1.386863613128662, | |
| "step": 4110 | |
| }, | |
| { | |
| "epoch": 1.0681877106559503, | |
| "grad_norm": 2.372840404510498, | |
| "learning_rate": 2.2390647049111472e-05, | |
| "loss": 1.376681137084961, | |
| "step": 4120 | |
| }, | |
| { | |
| "epoch": 1.0707803992740472, | |
| "grad_norm": 1.9672595262527466, | |
| "learning_rate": 2.2354079861413896e-05, | |
| "loss": 1.2816861152648926, | |
| "step": 4130 | |
| }, | |
| { | |
| "epoch": 1.0733730878921441, | |
| "grad_norm": 2.1304564476013184, | |
| "learning_rate": 2.2317455048857048e-05, | |
| "loss": 1.3413150787353516, | |
| "step": 4140 | |
| }, | |
| { | |
| "epoch": 1.075965776510241, | |
| "grad_norm": 2.1898391246795654, | |
| "learning_rate": 2.2280772898424454e-05, | |
| "loss": 1.3329020500183106, | |
| "step": 4150 | |
| }, | |
| { | |
| "epoch": 1.0785584651283382, | |
| "grad_norm": 2.1792447566986084, | |
| "learning_rate": 2.22440336975489e-05, | |
| "loss": 1.3798859596252442, | |
| "step": 4160 | |
| }, | |
| { | |
| "epoch": 1.0811511537464351, | |
| "grad_norm": 1.954807162284851, | |
| "learning_rate": 2.220723773411023e-05, | |
| "loss": 1.3178838729858398, | |
| "step": 4170 | |
| }, | |
| { | |
| "epoch": 1.083743842364532, | |
| "grad_norm": 2.392474889755249, | |
| "learning_rate": 2.217038529643305e-05, | |
| "loss": 1.356794834136963, | |
| "step": 4180 | |
| }, | |
| { | |
| "epoch": 1.086336530982629, | |
| "grad_norm": 2.129551887512207, | |
| "learning_rate": 2.213347667328449e-05, | |
| "loss": 1.3579363822937012, | |
| "step": 4190 | |
| }, | |
| { | |
| "epoch": 1.0889292196007259, | |
| "grad_norm": 2.6340548992156982, | |
| "learning_rate": 2.2096512153871938e-05, | |
| "loss": 1.3126588821411134, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 1.091521908218823, | |
| "grad_norm": 1.7375941276550293, | |
| "learning_rate": 2.2059492027840766e-05, | |
| "loss": 1.3306168556213378, | |
| "step": 4210 | |
| }, | |
| { | |
| "epoch": 1.09411459683692, | |
| "grad_norm": 2.017371892929077, | |
| "learning_rate": 2.202241658527207e-05, | |
| "loss": 1.3037184715270995, | |
| "step": 4220 | |
| }, | |
| { | |
| "epoch": 1.0967072854550168, | |
| "grad_norm": 2.2290050983428955, | |
| "learning_rate": 2.1985286116680404e-05, | |
| "loss": 1.3164632797241211, | |
| "step": 4230 | |
| }, | |
| { | |
| "epoch": 1.0992999740731138, | |
| "grad_norm": 2.352050542831421, | |
| "learning_rate": 2.1948100913011475e-05, | |
| "loss": 1.3569565773010255, | |
| "step": 4240 | |
| }, | |
| { | |
| "epoch": 1.101892662691211, | |
| "grad_norm": 2.4853835105895996, | |
| "learning_rate": 2.1910861265639897e-05, | |
| "loss": 1.3593795776367188, | |
| "step": 4250 | |
| }, | |
| { | |
| "epoch": 1.1044853513093078, | |
| "grad_norm": 1.8722959756851196, | |
| "learning_rate": 2.1873567466366874e-05, | |
| "loss": 1.3257516860961913, | |
| "step": 4260 | |
| }, | |
| { | |
| "epoch": 1.1070780399274047, | |
| "grad_norm": 2.722330093383789, | |
| "learning_rate": 2.1836219807417953e-05, | |
| "loss": 1.330971622467041, | |
| "step": 4270 | |
| }, | |
| { | |
| "epoch": 1.1096707285455016, | |
| "grad_norm": 2.2173590660095215, | |
| "learning_rate": 2.1798818581440696e-05, | |
| "loss": 1.3463165283203125, | |
| "step": 4280 | |
| }, | |
| { | |
| "epoch": 1.1122634171635986, | |
| "grad_norm": 3.126631259918213, | |
| "learning_rate": 2.1761364081502414e-05, | |
| "loss": 1.3597925186157227, | |
| "step": 4290 | |
| }, | |
| { | |
| "epoch": 1.1148561057816957, | |
| "grad_norm": 2.877528429031372, | |
| "learning_rate": 2.1723856601087854e-05, | |
| "loss": 1.3126080513000489, | |
| "step": 4300 | |
| }, | |
| { | |
| "epoch": 1.1174487943997926, | |
| "grad_norm": 2.2296814918518066, | |
| "learning_rate": 2.1686296434096913e-05, | |
| "loss": 1.3086021423339844, | |
| "step": 4310 | |
| }, | |
| { | |
| "epoch": 1.1200414830178895, | |
| "grad_norm": 2.710542917251587, | |
| "learning_rate": 2.164868387484232e-05, | |
| "loss": 1.3922597885131835, | |
| "step": 4320 | |
| }, | |
| { | |
| "epoch": 1.1226341716359864, | |
| "grad_norm": 2.929488182067871, | |
| "learning_rate": 2.161101921804734e-05, | |
| "loss": 1.3066654205322266, | |
| "step": 4330 | |
| }, | |
| { | |
| "epoch": 1.1252268602540836, | |
| "grad_norm": 2.615806818008423, | |
| "learning_rate": 2.1573302758843466e-05, | |
| "loss": 1.2853778839111327, | |
| "step": 4340 | |
| }, | |
| { | |
| "epoch": 1.1278195488721805, | |
| "grad_norm": 2.019347906112671, | |
| "learning_rate": 2.1535534792768094e-05, | |
| "loss": 1.2719595909118653, | |
| "step": 4350 | |
| }, | |
| { | |
| "epoch": 1.1304122374902774, | |
| "grad_norm": 2.1242213249206543, | |
| "learning_rate": 2.1497715615762226e-05, | |
| "loss": 1.3072625160217286, | |
| "step": 4360 | |
| }, | |
| { | |
| "epoch": 1.1330049261083743, | |
| "grad_norm": 2.1568093299865723, | |
| "learning_rate": 2.145984552416814e-05, | |
| "loss": 1.264606761932373, | |
| "step": 4370 | |
| }, | |
| { | |
| "epoch": 1.1355976147264712, | |
| "grad_norm": 2.133017063140869, | |
| "learning_rate": 2.1421924814727058e-05, | |
| "loss": 1.355167770385742, | |
| "step": 4380 | |
| }, | |
| { | |
| "epoch": 1.1381903033445684, | |
| "grad_norm": 2.135843515396118, | |
| "learning_rate": 2.1383953784576843e-05, | |
| "loss": 1.3303000450134277, | |
| "step": 4390 | |
| }, | |
| { | |
| "epoch": 1.1407829919626653, | |
| "grad_norm": 2.278923511505127, | |
| "learning_rate": 2.134593273124965e-05, | |
| "loss": 1.3016818046569825, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 1.1433756805807622, | |
| "grad_norm": 1.8876979351043701, | |
| "learning_rate": 2.1307861952669617e-05, | |
| "loss": 1.335930347442627, | |
| "step": 4410 | |
| }, | |
| { | |
| "epoch": 1.1459683691988591, | |
| "grad_norm": 1.9353163242340088, | |
| "learning_rate": 2.1269741747150506e-05, | |
| "loss": 1.314860725402832, | |
| "step": 4420 | |
| }, | |
| { | |
| "epoch": 1.1485610578169563, | |
| "grad_norm": 1.979556918144226, | |
| "learning_rate": 2.123157241339338e-05, | |
| "loss": 1.3145623207092285, | |
| "step": 4430 | |
| }, | |
| { | |
| "epoch": 1.1511537464350532, | |
| "grad_norm": 2.4763894081115723, | |
| "learning_rate": 2.1193354250484268e-05, | |
| "loss": 1.340696144104004, | |
| "step": 4440 | |
| }, | |
| { | |
| "epoch": 1.15374643505315, | |
| "grad_norm": 2.164473295211792, | |
| "learning_rate": 2.115508755789179e-05, | |
| "loss": 1.3050660133361816, | |
| "step": 4450 | |
| }, | |
| { | |
| "epoch": 1.156339123671247, | |
| "grad_norm": 2.4587583541870117, | |
| "learning_rate": 2.1116772635464863e-05, | |
| "loss": 1.2169719696044923, | |
| "step": 4460 | |
| }, | |
| { | |
| "epoch": 1.1589318122893442, | |
| "grad_norm": 2.6631503105163574, | |
| "learning_rate": 2.10784097834303e-05, | |
| "loss": 1.294164276123047, | |
| "step": 4470 | |
| }, | |
| { | |
| "epoch": 1.161524500907441, | |
| "grad_norm": 2.023618221282959, | |
| "learning_rate": 2.103999930239049e-05, | |
| "loss": 1.3531569480895995, | |
| "step": 4480 | |
| }, | |
| { | |
| "epoch": 1.164117189525538, | |
| "grad_norm": 3.4511115550994873, | |
| "learning_rate": 2.1001541493321022e-05, | |
| "loss": 1.2678154945373534, | |
| "step": 4490 | |
| }, | |
| { | |
| "epoch": 1.166709878143635, | |
| "grad_norm": 2.3503637313842773, | |
| "learning_rate": 2.096303665756835e-05, | |
| "loss": 1.3296841621398925, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 1.166709878143635, | |
| "eval_loss": 1.3733285665512085, | |
| "eval_runtime": 102.1475, | |
| "eval_samples_per_second": 15.899, | |
| "eval_steps_per_second": 15.899, | |
| "step": 4500 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 11571, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2.162907701796864e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |