Instructions to use WhyParabola/slm-solana-lora with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use WhyParabola/slm-solana-lora with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("unsloth/qwen3-coder-30b-a3b-instruct") model = PeftModel.from_pretrained(base_model, "WhyParabola/slm-solana-lora") - Transformers
How to use WhyParabola/slm-solana-lora with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="WhyParabola/slm-solana-lora") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("WhyParabola/slm-solana-lora", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use WhyParabola/slm-solana-lora with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "WhyParabola/slm-solana-lora" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "WhyParabola/slm-solana-lora", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/WhyParabola/slm-solana-lora
- SGLang
How to use WhyParabola/slm-solana-lora with SGLang:
Install from pip and serve model
# Install SGLang from pip: pip install sglang # Start the SGLang server: python3 -m sglang.launch_server \ --model-path "WhyParabola/slm-solana-lora" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "WhyParabola/slm-solana-lora", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker images
docker run --gpus all \ --shm-size 32g \ -p 30000:30000 \ -v ~/.cache/huggingface:/root/.cache/huggingface \ --env "HF_TOKEN=<secret>" \ --ipc=host \ lmsysorg/sglang:latest \ python3 -m sglang.launch_server \ --model-path "WhyParabola/slm-solana-lora" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "WhyParabola/slm-solana-lora", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Unsloth Studio
How to use WhyParabola/slm-solana-lora with Unsloth Studio:
Install Unsloth Studio (macOS, Linux, WSL)
curl -fsSL https://unsloth.ai/install.sh | sh # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for WhyParabola/slm-solana-lora to start chatting
Install Unsloth Studio (Windows)
irm https://unsloth.ai/install.ps1 | iex # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for WhyParabola/slm-solana-lora to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for WhyParabola/slm-solana-lora to start chatting
Load model with FastModel
pip install unsloth from unsloth import FastModel model, tokenizer = FastModel.from_pretrained( model_name="WhyParabola/slm-solana-lora", max_seq_length=2048, ) - Docker Model Runner
How to use WhyParabola/slm-solana-lora with Docker Model Runner:
docker model run hf.co/WhyParabola/slm-solana-lora
| { | |
| "best_global_step": null, | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.844950213371266, | |
| "eval_steps": 99999, | |
| "global_step": 2000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.007112375533428165, | |
| "grad_norm": 0.12396597862243652, | |
| "learning_rate": 1.8957345971563984e-07, | |
| "loss": 1.4227272987365722, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.01422475106685633, | |
| "grad_norm": 0.1262262761592865, | |
| "learning_rate": 4.265402843601896e-07, | |
| "loss": 1.4979448318481445, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.021337126600284494, | |
| "grad_norm": 0.10962335765361786, | |
| "learning_rate": 6.635071090047394e-07, | |
| "loss": 1.398064422607422, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.02844950213371266, | |
| "grad_norm": 0.12247616797685623, | |
| "learning_rate": 9.004739336492892e-07, | |
| "loss": 1.4452707290649414, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.03556187766714083, | |
| "grad_norm": 0.11095397174358368, | |
| "learning_rate": 1.1374407582938388e-06, | |
| "loss": 1.4563634872436524, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.04267425320056899, | |
| "grad_norm": 0.11946389079093933, | |
| "learning_rate": 1.3744075829383887e-06, | |
| "loss": 1.442008113861084, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.049786628733997154, | |
| "grad_norm": 0.09363763779401779, | |
| "learning_rate": 1.6113744075829384e-06, | |
| "loss": 1.3265527725219726, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.05689900426742532, | |
| "grad_norm": 0.1277642399072647, | |
| "learning_rate": 1.8483412322274883e-06, | |
| "loss": 1.5192468643188477, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.06401137980085349, | |
| "grad_norm": 0.07470542937517166, | |
| "learning_rate": 2.085308056872038e-06, | |
| "loss": 1.215554141998291, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.07112375533428165, | |
| "grad_norm": 0.1051228865981102, | |
| "learning_rate": 2.322274881516588e-06, | |
| "loss": 1.4449579238891601, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.07823613086770982, | |
| "grad_norm": 0.11589594185352325, | |
| "learning_rate": 2.5592417061611373e-06, | |
| "loss": 1.3515880584716797, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.08534850640113797, | |
| "grad_norm": 0.1121063381433487, | |
| "learning_rate": 2.7962085308056874e-06, | |
| "loss": 1.4210457801818848, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.09246088193456614, | |
| "grad_norm": 0.11301090568304062, | |
| "learning_rate": 3.0331753554502375e-06, | |
| "loss": 1.3430145263671875, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.09957325746799431, | |
| "grad_norm": 0.11729142814874649, | |
| "learning_rate": 3.2701421800947867e-06, | |
| "loss": 1.4662004470825196, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.10668563300142248, | |
| "grad_norm": 0.12315651029348373, | |
| "learning_rate": 3.507109004739337e-06, | |
| "loss": 1.4467350959777832, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.11379800853485064, | |
| "grad_norm": 0.10574598610401154, | |
| "learning_rate": 3.7440758293838865e-06, | |
| "loss": 1.3443514823913574, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.12091038406827881, | |
| "grad_norm": 0.10200333595275879, | |
| "learning_rate": 3.981042654028436e-06, | |
| "loss": 1.3781295776367188, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.12802275960170698, | |
| "grad_norm": 0.11026877164840698, | |
| "learning_rate": 4.218009478672986e-06, | |
| "loss": 1.2920406341552735, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.13513513513513514, | |
| "grad_norm": 0.09731078147888184, | |
| "learning_rate": 4.4549763033175355e-06, | |
| "loss": 1.3067164421081543, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.1422475106685633, | |
| "grad_norm": 0.10353145748376846, | |
| "learning_rate": 4.691943127962086e-06, | |
| "loss": 1.2854823112487792, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.14935988620199148, | |
| "grad_norm": 0.11844628304243088, | |
| "learning_rate": 4.928909952606635e-06, | |
| "loss": 1.426025104522705, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.15647226173541964, | |
| "grad_norm": 0.11913719028234482, | |
| "learning_rate": 5.165876777251185e-06, | |
| "loss": 1.2822218894958497, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.16358463726884778, | |
| "grad_norm": 0.078098826110363, | |
| "learning_rate": 5.402843601895735e-06, | |
| "loss": 1.2596662521362305, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.17069701280227595, | |
| "grad_norm": 0.11063536256551743, | |
| "learning_rate": 5.639810426540285e-06, | |
| "loss": 1.3071359634399413, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.17780938833570412, | |
| "grad_norm": 0.10192953050136566, | |
| "learning_rate": 5.876777251184834e-06, | |
| "loss": 1.1887753486633301, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.18492176386913228, | |
| "grad_norm": 0.08962368220090866, | |
| "learning_rate": 6.1137440758293845e-06, | |
| "loss": 1.1969791412353517, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.19203413940256045, | |
| "grad_norm": 0.08570072054862976, | |
| "learning_rate": 6.350710900473935e-06, | |
| "loss": 1.1636576652526855, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.19914651493598862, | |
| "grad_norm": 0.0954199954867363, | |
| "learning_rate": 6.587677725118484e-06, | |
| "loss": 1.2025936126708985, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.20625889046941678, | |
| "grad_norm": 0.09052606672048569, | |
| "learning_rate": 6.824644549763034e-06, | |
| "loss": 1.0443121910095214, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.21337126600284495, | |
| "grad_norm": 0.07353335618972778, | |
| "learning_rate": 7.061611374407583e-06, | |
| "loss": 1.157231903076172, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.22048364153627312, | |
| "grad_norm": 0.06493294984102249, | |
| "learning_rate": 7.298578199052133e-06, | |
| "loss": 1.1911725044250487, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 0.22759601706970128, | |
| "grad_norm": 0.056515395641326904, | |
| "learning_rate": 7.535545023696683e-06, | |
| "loss": 1.0279447555541992, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.23470839260312945, | |
| "grad_norm": 0.057359982281923294, | |
| "learning_rate": 7.772511848341233e-06, | |
| "loss": 1.076847743988037, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 0.24182076813655762, | |
| "grad_norm": 0.058239951729774475, | |
| "learning_rate": 8.009478672985783e-06, | |
| "loss": 0.946469497680664, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.24893314366998578, | |
| "grad_norm": 0.05514655262231827, | |
| "learning_rate": 8.246445497630333e-06, | |
| "loss": 1.063446617126465, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.25604551920341395, | |
| "grad_norm": 0.04826820269227028, | |
| "learning_rate": 8.483412322274883e-06, | |
| "loss": 1.0174281120300293, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.2631578947368421, | |
| "grad_norm": 0.041520342230796814, | |
| "learning_rate": 8.720379146919431e-06, | |
| "loss": 0.9851118087768554, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 0.2702702702702703, | |
| "grad_norm": 0.03696112334728241, | |
| "learning_rate": 8.957345971563981e-06, | |
| "loss": 0.892978572845459, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.2773826458036984, | |
| "grad_norm": 0.04463537037372589, | |
| "learning_rate": 9.194312796208532e-06, | |
| "loss": 0.9067799568176269, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 0.2844950213371266, | |
| "grad_norm": 0.03216946870088577, | |
| "learning_rate": 9.431279620853082e-06, | |
| "loss": 0.8715072631835937, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.29160739687055476, | |
| "grad_norm": 0.031706444919109344, | |
| "learning_rate": 9.668246445497632e-06, | |
| "loss": 0.9280688285827636, | |
| "step": 205 | |
| }, | |
| { | |
| "epoch": 0.29871977240398295, | |
| "grad_norm": 0.029998933896422386, | |
| "learning_rate": 9.905213270142182e-06, | |
| "loss": 0.8608943939208984, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.3058321479374111, | |
| "grad_norm": 0.04544912651181221, | |
| "learning_rate": 9.999938356263561e-06, | |
| "loss": 0.903835391998291, | |
| "step": 215 | |
| }, | |
| { | |
| "epoch": 0.3129445234708393, | |
| "grad_norm": 0.024148551747202873, | |
| "learning_rate": 9.999561650045317e-06, | |
| "loss": 0.8631033897399902, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.3200568990042674, | |
| "grad_norm": 0.024549957364797592, | |
| "learning_rate": 9.998842509899456e-06, | |
| "loss": 0.8868202209472656, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 0.32716927453769556, | |
| "grad_norm": 0.020235152915120125, | |
| "learning_rate": 9.997780985081892e-06, | |
| "loss": 0.8703635215759278, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.33428165007112376, | |
| "grad_norm": 0.041720639914274216, | |
| "learning_rate": 9.996377148299425e-06, | |
| "loss": 0.7600418090820312, | |
| "step": 235 | |
| }, | |
| { | |
| "epoch": 0.3413940256045519, | |
| "grad_norm": 0.02275031991302967, | |
| "learning_rate": 9.994631095704752e-06, | |
| "loss": 0.7633596420288086, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.3485064011379801, | |
| "grad_norm": 0.018682237714529037, | |
| "learning_rate": 9.992542946889888e-06, | |
| "loss": 0.8040481567382812, | |
| "step": 245 | |
| }, | |
| { | |
| "epoch": 0.35561877667140823, | |
| "grad_norm": 0.024369360879063606, | |
| "learning_rate": 9.99011284487797e-06, | |
| "loss": 0.7869772434234619, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.3627311522048364, | |
| "grad_norm": 0.021545717492699623, | |
| "learning_rate": 9.987340956113467e-06, | |
| "loss": 0.8517203330993652, | |
| "step": 255 | |
| }, | |
| { | |
| "epoch": 0.36984352773826457, | |
| "grad_norm": 0.01612464152276516, | |
| "learning_rate": 9.984227470450775e-06, | |
| "loss": 0.8197982788085938, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.37695590327169276, | |
| "grad_norm": 0.015140607953071594, | |
| "learning_rate": 9.980772601141213e-06, | |
| "loss": 0.7932530879974365, | |
| "step": 265 | |
| }, | |
| { | |
| "epoch": 0.3840682788051209, | |
| "grad_norm": 0.015770290046930313, | |
| "learning_rate": 9.97697658481842e-06, | |
| "loss": 0.7979182720184326, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.3911806543385491, | |
| "grad_norm": 0.01681072637438774, | |
| "learning_rate": 9.972839681482149e-06, | |
| "loss": 0.8038228034973145, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 0.39829302987197723, | |
| "grad_norm": 0.017351120710372925, | |
| "learning_rate": 9.968362174480451e-06, | |
| "loss": 0.8209856033325196, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.40540540540540543, | |
| "grad_norm": 0.014682579785585403, | |
| "learning_rate": 9.96354437049027e-06, | |
| "loss": 0.8208961486816406, | |
| "step": 285 | |
| }, | |
| { | |
| "epoch": 0.41251778093883357, | |
| "grad_norm": 0.015515010803937912, | |
| "learning_rate": 9.95838659949645e-06, | |
| "loss": 0.7764195442199707, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.41963015647226176, | |
| "grad_norm": 0.01328542921692133, | |
| "learning_rate": 9.952889214769116e-06, | |
| "loss": 0.7373966693878173, | |
| "step": 295 | |
| }, | |
| { | |
| "epoch": 0.4267425320056899, | |
| "grad_norm": 0.013769397512078285, | |
| "learning_rate": 9.947052592839488e-06, | |
| "loss": 0.7790839195251464, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.43385490753911804, | |
| "grad_norm": 0.013357909396290779, | |
| "learning_rate": 9.940877133474087e-06, | |
| "loss": 0.7955220222473145, | |
| "step": 305 | |
| }, | |
| { | |
| "epoch": 0.44096728307254623, | |
| "grad_norm": 0.01533876545727253, | |
| "learning_rate": 9.934363259647355e-06, | |
| "loss": 0.8395823478698731, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.4480796586059744, | |
| "grad_norm": 0.013267037458717823, | |
| "learning_rate": 9.927511417512687e-06, | |
| "loss": 0.7947360038757324, | |
| "step": 315 | |
| }, | |
| { | |
| "epoch": 0.45519203413940257, | |
| "grad_norm": 0.014744734391570091, | |
| "learning_rate": 9.920322076371871e-06, | |
| "loss": 0.7898136138916015, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.4623044096728307, | |
| "grad_norm": 0.015842357650399208, | |
| "learning_rate": 9.91279572864294e-06, | |
| "loss": 0.7578622341156006, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 0.4694167852062589, | |
| "grad_norm": 0.015208872966468334, | |
| "learning_rate": 9.904932889826451e-06, | |
| "loss": 0.7646086692810059, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.47652916073968704, | |
| "grad_norm": 0.012448601424694061, | |
| "learning_rate": 9.896734098470175e-06, | |
| "loss": 0.804629898071289, | |
| "step": 335 | |
| }, | |
| { | |
| "epoch": 0.48364153627311524, | |
| "grad_norm": 0.016085481271147728, | |
| "learning_rate": 9.888199916132208e-06, | |
| "loss": 0.7498270034790039, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.4907539118065434, | |
| "grad_norm": 0.025318488478660583, | |
| "learning_rate": 9.87933092734251e-06, | |
| "loss": 0.7498879909515381, | |
| "step": 345 | |
| }, | |
| { | |
| "epoch": 0.49786628733997157, | |
| "grad_norm": 0.013470480218529701, | |
| "learning_rate": 9.870127739562873e-06, | |
| "loss": 0.8381074905395508, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.5049786628733998, | |
| "grad_norm": 0.012390932068228722, | |
| "learning_rate": 9.860590983145307e-06, | |
| "loss": 0.7959535121917725, | |
| "step": 355 | |
| }, | |
| { | |
| "epoch": 0.5120910384068279, | |
| "grad_norm": 0.03908325359225273, | |
| "learning_rate": 9.850721311288868e-06, | |
| "loss": 0.77716064453125, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.519203413940256, | |
| "grad_norm": 0.01935300976037979, | |
| "learning_rate": 9.840519399994921e-06, | |
| "loss": 0.810551643371582, | |
| "step": 365 | |
| }, | |
| { | |
| "epoch": 0.5263157894736842, | |
| "grad_norm": 0.011727036908268929, | |
| "learning_rate": 9.829985948020836e-06, | |
| "loss": 0.783443021774292, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.5334281650071123, | |
| "grad_norm": 0.01185957808047533, | |
| "learning_rate": 9.819121676832134e-06, | |
| "loss": 0.7494336128234863, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 0.5405405405405406, | |
| "grad_norm": 0.012798828072845936, | |
| "learning_rate": 9.807927330553058e-06, | |
| "loss": 0.8026717185974122, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.5476529160739687, | |
| "grad_norm": 0.019524866715073586, | |
| "learning_rate": 9.796403675915622e-06, | |
| "loss": 0.7634530544281006, | |
| "step": 385 | |
| }, | |
| { | |
| "epoch": 0.5547652916073968, | |
| "grad_norm": 0.013788755051791668, | |
| "learning_rate": 9.784551502207087e-06, | |
| "loss": 0.7632253646850586, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.561877667140825, | |
| "grad_norm": 0.01305212453007698, | |
| "learning_rate": 9.772371621215902e-06, | |
| "loss": 0.7682255268096924, | |
| "step": 395 | |
| }, | |
| { | |
| "epoch": 0.5689900426742532, | |
| "grad_norm": 0.012975879944860935, | |
| "learning_rate": 9.759864867176098e-06, | |
| "loss": 0.7581171035766602, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.5761024182076814, | |
| "grad_norm": 0.011801790446043015, | |
| "learning_rate": 9.74703209671016e-06, | |
| "loss": 0.7882646560668946, | |
| "step": 405 | |
| }, | |
| { | |
| "epoch": 0.5832147937411095, | |
| "grad_norm": 0.01298159547150135, | |
| "learning_rate": 9.733874188770344e-06, | |
| "loss": 0.7816955089569092, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.5903271692745377, | |
| "grad_norm": 0.027532342821359634, | |
| "learning_rate": 9.720392044578477e-06, | |
| "loss": 0.6961409091949463, | |
| "step": 415 | |
| }, | |
| { | |
| "epoch": 0.5974395448079659, | |
| "grad_norm": 0.01297469437122345, | |
| "learning_rate": 9.706586587564236e-06, | |
| "loss": 0.7911362648010254, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.604551920341394, | |
| "grad_norm": 0.015234866179525852, | |
| "learning_rate": 9.692458763301891e-06, | |
| "loss": 0.7972568511962891, | |
| "step": 425 | |
| }, | |
| { | |
| "epoch": 0.6116642958748222, | |
| "grad_norm": 0.016101600602269173, | |
| "learning_rate": 9.678009539445549e-06, | |
| "loss": 0.7825101852416992, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.6187766714082503, | |
| "grad_norm": 0.012733902782201767, | |
| "learning_rate": 9.663239905662868e-06, | |
| "loss": 0.7665041446685791, | |
| "step": 435 | |
| }, | |
| { | |
| "epoch": 0.6258890469416786, | |
| "grad_norm": 0.012959662824869156, | |
| "learning_rate": 9.648150873567278e-06, | |
| "loss": 0.7273931503295898, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.6330014224751067, | |
| "grad_norm": 0.011889465153217316, | |
| "learning_rate": 9.632743476648686e-06, | |
| "loss": 0.7907261848449707, | |
| "step": 445 | |
| }, | |
| { | |
| "epoch": 0.6401137980085349, | |
| "grad_norm": 0.011718220077455044, | |
| "learning_rate": 9.617018770202702e-06, | |
| "loss": 0.8006930351257324, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.647226173541963, | |
| "grad_norm": 0.013619167730212212, | |
| "learning_rate": 9.600977831258347e-06, | |
| "loss": 0.7727859497070313, | |
| "step": 455 | |
| }, | |
| { | |
| "epoch": 0.6543385490753911, | |
| "grad_norm": 0.015222000889480114, | |
| "learning_rate": 9.584621758504286e-06, | |
| "loss": 0.770260238647461, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.6614509246088194, | |
| "grad_norm": 0.014281806536018848, | |
| "learning_rate": 9.567951672213582e-06, | |
| "loss": 0.7328165531158447, | |
| "step": 465 | |
| }, | |
| { | |
| "epoch": 0.6685633001422475, | |
| "grad_norm": 0.013101202435791492, | |
| "learning_rate": 9.550968714166959e-06, | |
| "loss": 0.792152214050293, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 0.6756756756756757, | |
| "grad_norm": 0.01915375515818596, | |
| "learning_rate": 9.5336740475746e-06, | |
| "loss": 0.7413363933563233, | |
| "step": 475 | |
| }, | |
| { | |
| "epoch": 0.6827880512091038, | |
| "grad_norm": 0.012954477220773697, | |
| "learning_rate": 9.516068856996478e-06, | |
| "loss": 0.7463040828704834, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.689900426742532, | |
| "grad_norm": 0.015190026722848415, | |
| "learning_rate": 9.498154348261217e-06, | |
| "loss": 0.7213023185729981, | |
| "step": 485 | |
| }, | |
| { | |
| "epoch": 0.6970128022759602, | |
| "grad_norm": 0.015451316721737385, | |
| "learning_rate": 9.479931748383511e-06, | |
| "loss": 0.7095402717590332, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 0.7041251778093883, | |
| "grad_norm": 0.01419431809335947, | |
| "learning_rate": 9.461402305480067e-06, | |
| "loss": 0.7601386547088623, | |
| "step": 495 | |
| }, | |
| { | |
| "epoch": 0.7112375533428165, | |
| "grad_norm": 0.012903365306556225, | |
| "learning_rate": 9.442567288684134e-06, | |
| "loss": 0.7972976207733155, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.7183499288762447, | |
| "grad_norm": 0.014118182472884655, | |
| "learning_rate": 9.423427988058569e-06, | |
| "loss": 0.7362984657287598, | |
| "step": 505 | |
| }, | |
| { | |
| "epoch": 0.7254623044096729, | |
| "grad_norm": 0.01312790997326374, | |
| "learning_rate": 9.403985714507476e-06, | |
| "loss": 0.7164534091949463, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 0.732574679943101, | |
| "grad_norm": 0.013149509206414223, | |
| "learning_rate": 9.384241799686416e-06, | |
| "loss": 0.7581445693969726, | |
| "step": 515 | |
| }, | |
| { | |
| "epoch": 0.7396870554765291, | |
| "grad_norm": 0.014509950764477253, | |
| "learning_rate": 9.36419759591121e-06, | |
| "loss": 0.7607109069824218, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 0.7467994310099573, | |
| "grad_norm": 0.015734901651740074, | |
| "learning_rate": 9.343854476065301e-06, | |
| "loss": 0.7364118099212646, | |
| "step": 525 | |
| }, | |
| { | |
| "epoch": 0.7539118065433855, | |
| "grad_norm": 0.015109636820852757, | |
| "learning_rate": 9.323213833505733e-06, | |
| "loss": 0.7244921207427979, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 0.7610241820768137, | |
| "grad_norm": 0.015012472867965698, | |
| "learning_rate": 9.302277081967708e-06, | |
| "loss": 0.7567250251770019, | |
| "step": 535 | |
| }, | |
| { | |
| "epoch": 0.7681365576102418, | |
| "grad_norm": 0.013028338551521301, | |
| "learning_rate": 9.281045655467757e-06, | |
| "loss": 0.7913572311401367, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 0.7752489331436699, | |
| "grad_norm": 0.014547139406204224, | |
| "learning_rate": 9.259521008205522e-06, | |
| "loss": 0.7506765842437744, | |
| "step": 545 | |
| }, | |
| { | |
| "epoch": 0.7823613086770982, | |
| "grad_norm": 0.014500031247735023, | |
| "learning_rate": 9.237704614464157e-06, | |
| "loss": 0.7631255149841308, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.7894736842105263, | |
| "grad_norm": 0.024208789691329002, | |
| "learning_rate": 9.21559796850934e-06, | |
| "loss": 0.7228170871734619, | |
| "step": 555 | |
| }, | |
| { | |
| "epoch": 0.7965860597439545, | |
| "grad_norm": 0.01767735742032528, | |
| "learning_rate": 9.193202584486938e-06, | |
| "loss": 0.7594891548156738, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 0.8036984352773826, | |
| "grad_norm": 0.027131540700793266, | |
| "learning_rate": 9.170519996319292e-06, | |
| "loss": 0.7311542987823486, | |
| "step": 565 | |
| }, | |
| { | |
| "epoch": 0.8108108108108109, | |
| "grad_norm": 0.014019402675330639, | |
| "learning_rate": 9.147551757600156e-06, | |
| "loss": 0.7342860698699951, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 0.817923186344239, | |
| "grad_norm": 0.015196071937680244, | |
| "learning_rate": 9.124299441488287e-06, | |
| "loss": 0.7782781600952149, | |
| "step": 575 | |
| }, | |
| { | |
| "epoch": 0.8250355618776671, | |
| "grad_norm": 0.013155009597539902, | |
| "learning_rate": 9.100764640599699e-06, | |
| "loss": 0.7691669464111328, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 0.8321479374110953, | |
| "grad_norm": 0.02131805010139942, | |
| "learning_rate": 9.076948966898573e-06, | |
| "loss": 0.6857946395874024, | |
| "step": 585 | |
| }, | |
| { | |
| "epoch": 0.8392603129445235, | |
| "grad_norm": 0.021150261163711548, | |
| "learning_rate": 9.05285405158685e-06, | |
| "loss": 0.6824939250946045, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 0.8463726884779517, | |
| "grad_norm": 0.014878728426992893, | |
| "learning_rate": 9.028481544992514e-06, | |
| "loss": 0.7442028522491455, | |
| "step": 595 | |
| }, | |
| { | |
| "epoch": 0.8534850640113798, | |
| "grad_norm": 0.014299673028290272, | |
| "learning_rate": 9.003833116456548e-06, | |
| "loss": 0.7425227642059327, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.8605974395448079, | |
| "grad_norm": 0.020050186663866043, | |
| "learning_rate": 8.9789104542186e-06, | |
| "loss": 0.6471955299377441, | |
| "step": 605 | |
| }, | |
| { | |
| "epoch": 0.8677098150782361, | |
| "grad_norm": 0.014727029018104076, | |
| "learning_rate": 8.953715265301344e-06, | |
| "loss": 0.6761772632598877, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 0.8748221906116643, | |
| "grad_norm": 0.0251702219247818, | |
| "learning_rate": 8.928249275393572e-06, | |
| "loss": 0.7484918117523194, | |
| "step": 615 | |
| }, | |
| { | |
| "epoch": 0.8819345661450925, | |
| "grad_norm": 0.013131954707205296, | |
| "learning_rate": 8.902514228731993e-06, | |
| "loss": 0.7525879859924316, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 0.8890469416785206, | |
| "grad_norm": 0.014284606091678143, | |
| "learning_rate": 8.876511887981758e-06, | |
| "loss": 0.7031543254852295, | |
| "step": 625 | |
| }, | |
| { | |
| "epoch": 0.8961593172119487, | |
| "grad_norm": 0.01469456311315298, | |
| "learning_rate": 8.85024403411574e-06, | |
| "loss": 0.7517221450805665, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 0.903271692745377, | |
| "grad_norm": 0.014566020108759403, | |
| "learning_rate": 8.823712466292547e-06, | |
| "loss": 0.7733576774597168, | |
| "step": 635 | |
| }, | |
| { | |
| "epoch": 0.9103840682788051, | |
| "grad_norm": 0.01564401015639305, | |
| "learning_rate": 8.796919001733286e-06, | |
| "loss": 0.7582737445831299, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 0.9174964438122333, | |
| "grad_norm": 0.014589518308639526, | |
| "learning_rate": 8.769865475597107e-06, | |
| "loss": 0.7202891826629638, | |
| "step": 645 | |
| }, | |
| { | |
| "epoch": 0.9246088193456614, | |
| "grad_norm": 0.014613118954002857, | |
| "learning_rate": 8.742553740855507e-06, | |
| "loss": 0.7529885292053222, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.9317211948790897, | |
| "grad_norm": 0.017528263852000237, | |
| "learning_rate": 8.714985668165399e-06, | |
| "loss": 0.7535917282104492, | |
| "step": 655 | |
| }, | |
| { | |
| "epoch": 0.9388335704125178, | |
| "grad_norm": 0.01572534441947937, | |
| "learning_rate": 8.687163145741008e-06, | |
| "loss": 0.6831246852874756, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 0.9459459459459459, | |
| "grad_norm": 0.01505051925778389, | |
| "learning_rate": 8.659088079224528e-06, | |
| "loss": 0.7192672252655029, | |
| "step": 665 | |
| }, | |
| { | |
| "epoch": 0.9530583214793741, | |
| "grad_norm": 0.014804129488766193, | |
| "learning_rate": 8.630762391555601e-06, | |
| "loss": 0.7272192955017089, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 0.9601706970128022, | |
| "grad_norm": 0.014921215362846851, | |
| "learning_rate": 8.602188022839612e-06, | |
| "loss": 0.7498035430908203, | |
| "step": 675 | |
| }, | |
| { | |
| "epoch": 0.9672830725462305, | |
| "grad_norm": 0.01385109405964613, | |
| "learning_rate": 8.573366930214807e-06, | |
| "loss": 0.7332922935485839, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 0.9743954480796586, | |
| "grad_norm": 0.01615496724843979, | |
| "learning_rate": 8.544301087718234e-06, | |
| "loss": 0.7189756393432617, | |
| "step": 685 | |
| }, | |
| { | |
| "epoch": 0.9815078236130867, | |
| "grad_norm": 0.014931720681488514, | |
| "learning_rate": 8.514992486150554e-06, | |
| "loss": 0.7482341766357422, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 0.9886201991465149, | |
| "grad_norm": 0.016770832240581512, | |
| "learning_rate": 8.485443132939664e-06, | |
| "loss": 0.7097194194793701, | |
| "step": 695 | |
| }, | |
| { | |
| "epoch": 0.9957325746799431, | |
| "grad_norm": 0.014345219358801842, | |
| "learning_rate": 8.455655052003216e-06, | |
| "loss": 0.6710967540740966, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 1.0028449502133712, | |
| "grad_norm": 0.014812275767326355, | |
| "learning_rate": 8.425630283609995e-06, | |
| "loss": 0.7616248607635498, | |
| "step": 705 | |
| }, | |
| { | |
| "epoch": 1.0099573257467995, | |
| "grad_norm": 0.022520147264003754, | |
| "learning_rate": 8.395370884240161e-06, | |
| "loss": 0.6915517807006836, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 1.0170697012802277, | |
| "grad_norm": 0.014687804505228996, | |
| "learning_rate": 8.36487892644441e-06, | |
| "loss": 0.7760564804077148, | |
| "step": 715 | |
| }, | |
| { | |
| "epoch": 1.0241820768136558, | |
| "grad_norm": 0.015282604843378067, | |
| "learning_rate": 8.334156498702015e-06, | |
| "loss": 0.7448132514953614, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 1.031294452347084, | |
| "grad_norm": 0.016149410977959633, | |
| "learning_rate": 8.303205705277776e-06, | |
| "loss": 0.7295210838317872, | |
| "step": 725 | |
| }, | |
| { | |
| "epoch": 1.038406827880512, | |
| "grad_norm": 0.0175002608448267, | |
| "learning_rate": 8.272028666077893e-06, | |
| "loss": 0.715207576751709, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 1.0455192034139402, | |
| "grad_norm": 0.015501333400607109, | |
| "learning_rate": 8.240627516504778e-06, | |
| "loss": 0.7610238552093506, | |
| "step": 735 | |
| }, | |
| { | |
| "epoch": 1.0526315789473684, | |
| "grad_norm": 0.014466507360339165, | |
| "learning_rate": 8.209004407310782e-06, | |
| "loss": 0.682843017578125, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 1.0597439544807965, | |
| "grad_norm": 0.01729828491806984, | |
| "learning_rate": 8.177161504450887e-06, | |
| "loss": 0.7697264671325683, | |
| "step": 745 | |
| }, | |
| { | |
| "epoch": 1.0668563300142249, | |
| "grad_norm": 0.01606452651321888, | |
| "learning_rate": 8.145100988934369e-06, | |
| "loss": 0.7051825046539306, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 1.073968705547653, | |
| "grad_norm": 0.017853980883955956, | |
| "learning_rate": 8.112825056675386e-06, | |
| "loss": 0.7393856525421143, | |
| "step": 755 | |
| }, | |
| { | |
| "epoch": 1.0810810810810811, | |
| "grad_norm": 0.01651955395936966, | |
| "learning_rate": 8.0803359183426e-06, | |
| "loss": 0.740062665939331, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 1.0881934566145093, | |
| "grad_norm": 0.01589570939540863, | |
| "learning_rate": 8.04763579920775e-06, | |
| "loss": 0.7486938953399658, | |
| "step": 765 | |
| }, | |
| { | |
| "epoch": 1.0953058321479374, | |
| "grad_norm": 0.01882278174161911, | |
| "learning_rate": 8.01472693899324e-06, | |
| "loss": 0.7593507766723633, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 1.1024182076813656, | |
| "grad_norm": 0.017779262736439705, | |
| "learning_rate": 7.98161159171873e-06, | |
| "loss": 0.7369762897491455, | |
| "step": 775 | |
| }, | |
| { | |
| "epoch": 1.1095305832147937, | |
| "grad_norm": 0.01958276890218258, | |
| "learning_rate": 7.948292025546754e-06, | |
| "loss": 0.7430673599243164, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 1.1166429587482218, | |
| "grad_norm": 0.01635376177728176, | |
| "learning_rate": 7.91477052262737e-06, | |
| "loss": 0.749770212173462, | |
| "step": 785 | |
| }, | |
| { | |
| "epoch": 1.12375533428165, | |
| "grad_norm": 0.019017737358808517, | |
| "learning_rate": 7.881049378941851e-06, | |
| "loss": 0.6917729854583741, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 1.1308677098150781, | |
| "grad_norm": 0.017745498567819595, | |
| "learning_rate": 7.847130904145418e-06, | |
| "loss": 0.7209823131561279, | |
| "step": 795 | |
| }, | |
| { | |
| "epoch": 1.1379800853485065, | |
| "grad_norm": 0.022607974708080292, | |
| "learning_rate": 7.81301742140905e-06, | |
| "loss": 0.7285879135131836, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 1.1450924608819346, | |
| "grad_norm": 0.01610717363655567, | |
| "learning_rate": 7.778711267260371e-06, | |
| "loss": 0.7201016426086426, | |
| "step": 805 | |
| }, | |
| { | |
| "epoch": 1.1522048364153628, | |
| "grad_norm": 0.016487758606672287, | |
| "learning_rate": 7.744214791423597e-06, | |
| "loss": 0.7271471977233886, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 1.159317211948791, | |
| "grad_norm": 0.01821993477642536, | |
| "learning_rate": 7.709530356658616e-06, | |
| "loss": 0.6985025882720948, | |
| "step": 815 | |
| }, | |
| { | |
| "epoch": 1.166429587482219, | |
| "grad_norm": 0.01631130650639534, | |
| "learning_rate": 7.674660338599144e-06, | |
| "loss": 0.760840368270874, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 1.1735419630156472, | |
| "grad_norm": 0.017514122650027275, | |
| "learning_rate": 7.639607125590017e-06, | |
| "loss": 0.6543985366821289, | |
| "step": 825 | |
| }, | |
| { | |
| "epoch": 1.1806543385490753, | |
| "grad_norm": 0.014640039764344692, | |
| "learning_rate": 7.604373118523598e-06, | |
| "loss": 0.7778742790222168, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 1.1877667140825037, | |
| "grad_norm": 0.03316516801714897, | |
| "learning_rate": 7.5689607306753465e-06, | |
| "loss": 0.7553888320922851, | |
| "step": 835 | |
| }, | |
| { | |
| "epoch": 1.1948790896159318, | |
| "grad_norm": 0.016899485141038895, | |
| "learning_rate": 7.533372387538518e-06, | |
| "loss": 0.7549580097198486, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 1.20199146514936, | |
| "grad_norm": 0.017853831872344017, | |
| "learning_rate": 7.497610526658035e-06, | |
| "loss": 0.7460854530334473, | |
| "step": 845 | |
| }, | |
| { | |
| "epoch": 1.209103840682788, | |
| "grad_norm": 0.016394775360822678, | |
| "learning_rate": 7.4616775974635346e-06, | |
| "loss": 0.7119558811187744, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 1.2162162162162162, | |
| "grad_norm": 0.018164537847042084, | |
| "learning_rate": 7.425576061101599e-06, | |
| "loss": 0.711454200744629, | |
| "step": 855 | |
| }, | |
| { | |
| "epoch": 1.2233285917496444, | |
| "grad_norm": 0.025621753185987473, | |
| "learning_rate": 7.389308390267191e-06, | |
| "loss": 0.7418702125549317, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 1.2304409672830725, | |
| "grad_norm": 0.018322646617889404, | |
| "learning_rate": 7.352877069034279e-06, | |
| "loss": 0.7104067802429199, | |
| "step": 865 | |
| }, | |
| { | |
| "epoch": 1.2375533428165006, | |
| "grad_norm": 0.01565595157444477, | |
| "learning_rate": 7.316284592685712e-06, | |
| "loss": 0.7560728073120118, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 1.2446657183499288, | |
| "grad_norm": 0.0181591659784317, | |
| "learning_rate": 7.279533467542295e-06, | |
| "loss": 0.6743175029754639, | |
| "step": 875 | |
| }, | |
| { | |
| "epoch": 1.251778093883357, | |
| "grad_norm": 0.01698802225291729, | |
| "learning_rate": 7.242626210791137e-06, | |
| "loss": 0.7210459232330322, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 1.2588904694167853, | |
| "grad_norm": 0.015113065019249916, | |
| "learning_rate": 7.205565350313234e-06, | |
| "loss": 0.7054549217224121, | |
| "step": 885 | |
| }, | |
| { | |
| "epoch": 1.2660028449502134, | |
| "grad_norm": 0.01659173145890236, | |
| "learning_rate": 7.16835342451033e-06, | |
| "loss": 0.7842894077301026, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 1.2731152204836416, | |
| "grad_norm": 0.016503192484378815, | |
| "learning_rate": 7.130992982131059e-06, | |
| "loss": 0.7237984657287597, | |
| "step": 895 | |
| }, | |
| { | |
| "epoch": 1.2802275960170697, | |
| "grad_norm": 0.015096175484359264, | |
| "learning_rate": 7.093486582096361e-06, | |
| "loss": 0.7442319869995118, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 1.2873399715504978, | |
| "grad_norm": 0.01692996546626091, | |
| "learning_rate": 7.05583679332423e-06, | |
| "loss": 0.678685998916626, | |
| "step": 905 | |
| }, | |
| { | |
| "epoch": 1.294452347083926, | |
| "grad_norm": 0.016276616603136063, | |
| "learning_rate": 7.018046194553751e-06, | |
| "loss": 0.6846030712127685, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 1.3015647226173541, | |
| "grad_norm": 0.01619255170226097, | |
| "learning_rate": 6.980117374168485e-06, | |
| "loss": 0.7147863864898681, | |
| "step": 915 | |
| }, | |
| { | |
| "epoch": 1.3086770981507825, | |
| "grad_norm": 0.01654823124408722, | |
| "learning_rate": 6.942052930019168e-06, | |
| "loss": 0.7425489902496338, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 1.3157894736842106, | |
| "grad_norm": 0.015968745574355125, | |
| "learning_rate": 6.9038554692457906e-06, | |
| "loss": 0.706316614151001, | |
| "step": 925 | |
| }, | |
| { | |
| "epoch": 1.3229018492176388, | |
| "grad_norm": 0.017116257920861244, | |
| "learning_rate": 6.865527608099025e-06, | |
| "loss": 0.7231118679046631, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 1.330014224751067, | |
| "grad_norm": 0.019141439348459244, | |
| "learning_rate": 6.8270719717610255e-06, | |
| "loss": 0.6829496383666992, | |
| "step": 935 | |
| }, | |
| { | |
| "epoch": 1.337126600284495, | |
| "grad_norm": 0.017003817483782768, | |
| "learning_rate": 6.788491194165629e-06, | |
| "loss": 0.7045816421508789, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 1.3442389758179232, | |
| "grad_norm": 0.018398337066173553, | |
| "learning_rate": 6.749787917817942e-06, | |
| "loss": 0.7236195087432862, | |
| "step": 945 | |
| }, | |
| { | |
| "epoch": 1.3513513513513513, | |
| "grad_norm": 0.01609586924314499, | |
| "learning_rate": 6.710964793613355e-06, | |
| "loss": 0.7134823799133301, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 1.3584637268847795, | |
| "grad_norm": 0.015588617883622646, | |
| "learning_rate": 6.672024480655973e-06, | |
| "loss": 0.7059481143951416, | |
| "step": 955 | |
| }, | |
| { | |
| "epoch": 1.3655761024182076, | |
| "grad_norm": 0.01707872562110424, | |
| "learning_rate": 6.6329696460764854e-06, | |
| "loss": 0.7315536499023437, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 1.3726884779516357, | |
| "grad_norm": 0.015458762645721436, | |
| "learning_rate": 6.593802964849487e-06, | |
| "loss": 0.6769055843353271, | |
| "step": 965 | |
| }, | |
| { | |
| "epoch": 1.379800853485064, | |
| "grad_norm": 0.01659971848130226, | |
| "learning_rate": 6.55452711961026e-06, | |
| "loss": 0.692983865737915, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 1.3869132290184922, | |
| "grad_norm": 0.020152278244495392, | |
| "learning_rate": 6.515144800471037e-06, | |
| "loss": 0.7136699199676514, | |
| "step": 975 | |
| }, | |
| { | |
| "epoch": 1.3940256045519204, | |
| "grad_norm": 0.019839296117424965, | |
| "learning_rate": 6.475658704836742e-06, | |
| "loss": 0.7655652523040771, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 1.4011379800853485, | |
| "grad_norm": 0.016899431124329567, | |
| "learning_rate": 6.436071537220245e-06, | |
| "loss": 0.7531155109405517, | |
| "step": 985 | |
| }, | |
| { | |
| "epoch": 1.4082503556187767, | |
| "grad_norm": 0.017267396673560143, | |
| "learning_rate": 6.3963860090571136e-06, | |
| "loss": 0.7064692497253418, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 1.4153627311522048, | |
| "grad_norm": 0.016033947467803955, | |
| "learning_rate": 6.3566048385199065e-06, | |
| "loss": 0.6782587051391602, | |
| "step": 995 | |
| }, | |
| { | |
| "epoch": 1.422475106685633, | |
| "grad_norm": 0.016765275970101357, | |
| "learning_rate": 6.3167307503319945e-06, | |
| "loss": 0.7408823013305664, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.4295874822190613, | |
| "grad_norm": 0.016634974628686905, | |
| "learning_rate": 6.276766475580935e-06, | |
| "loss": 0.6982696533203125, | |
| "step": 1005 | |
| }, | |
| { | |
| "epoch": 1.4366998577524894, | |
| "grad_norm": 0.015438280068337917, | |
| "learning_rate": 6.236714751531423e-06, | |
| "loss": 0.7227981567382813, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 1.4438122332859176, | |
| "grad_norm": 0.018462039530277252, | |
| "learning_rate": 6.1965783214377895e-06, | |
| "loss": 0.7196823596954346, | |
| "step": 1015 | |
| }, | |
| { | |
| "epoch": 1.4509246088193457, | |
| "grad_norm": 0.015660835430026054, | |
| "learning_rate": 6.1563599343561254e-06, | |
| "loss": 0.7268499374389649, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 1.4580369843527738, | |
| "grad_norm": 0.01876399666070938, | |
| "learning_rate": 6.116062344955984e-06, | |
| "loss": 0.6868331432342529, | |
| "step": 1025 | |
| }, | |
| { | |
| "epoch": 1.465149359886202, | |
| "grad_norm": 0.01660033129155636, | |
| "learning_rate": 6.075688313331704e-06, | |
| "loss": 0.6909028053283691, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 1.4722617354196301, | |
| "grad_norm": 0.01642961986362934, | |
| "learning_rate": 6.035240604813366e-06, | |
| "loss": 0.6916821479797364, | |
| "step": 1035 | |
| }, | |
| { | |
| "epoch": 1.4793741109530583, | |
| "grad_norm": 0.01772296614944935, | |
| "learning_rate": 5.994721989777387e-06, | |
| "loss": 0.7245942115783691, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 1.4864864864864864, | |
| "grad_norm": 0.01825345866382122, | |
| "learning_rate": 5.954135243456769e-06, | |
| "loss": 0.7016736030578613, | |
| "step": 1045 | |
| }, | |
| { | |
| "epoch": 1.4935988620199145, | |
| "grad_norm": 0.01610652171075344, | |
| "learning_rate": 5.913483145751018e-06, | |
| "loss": 0.6654571533203125, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 1.5007112375533427, | |
| "grad_norm": 0.017010604962706566, | |
| "learning_rate": 5.872768481035736e-06, | |
| "loss": 0.7061189651489258, | |
| "step": 1055 | |
| }, | |
| { | |
| "epoch": 1.5078236130867708, | |
| "grad_norm": 0.017414411529898643, | |
| "learning_rate": 5.831994037971914e-06, | |
| "loss": 0.7226849555969238, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 1.5149359886201992, | |
| "grad_norm": 0.01917360909283161, | |
| "learning_rate": 5.79116260931493e-06, | |
| "loss": 0.733070707321167, | |
| "step": 1065 | |
| }, | |
| { | |
| "epoch": 1.5220483641536273, | |
| "grad_norm": 0.016919942572712898, | |
| "learning_rate": 5.7502769917232635e-06, | |
| "loss": 0.7204188823699951, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 1.5291607396870555, | |
| "grad_norm": 0.018161717802286148, | |
| "learning_rate": 5.70933998556695e-06, | |
| "loss": 0.6771541118621827, | |
| "step": 1075 | |
| }, | |
| { | |
| "epoch": 1.5362731152204836, | |
| "grad_norm": 0.018309131264686584, | |
| "learning_rate": 5.668354394735761e-06, | |
| "loss": 0.7210025787353516, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 1.543385490753912, | |
| "grad_norm": 0.015957120805978775, | |
| "learning_rate": 5.627323026447176e-06, | |
| "loss": 0.7394068717956543, | |
| "step": 1085 | |
| }, | |
| { | |
| "epoch": 1.55049786628734, | |
| "grad_norm": 0.01799791492521763, | |
| "learning_rate": 5.586248691054101e-06, | |
| "loss": 0.7240789413452149, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 1.5576102418207682, | |
| "grad_norm": 0.018541524186730385, | |
| "learning_rate": 5.5451342018523755e-06, | |
| "loss": 0.7141832828521728, | |
| "step": 1095 | |
| }, | |
| { | |
| "epoch": 1.5647226173541964, | |
| "grad_norm": 0.018332267180085182, | |
| "learning_rate": 5.5039823748880835e-06, | |
| "loss": 0.716184663772583, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 1.5718349928876245, | |
| "grad_norm": 0.018345907330513, | |
| "learning_rate": 5.462796028764682e-06, | |
| "loss": 0.7993448734283447, | |
| "step": 1105 | |
| }, | |
| { | |
| "epoch": 1.5789473684210527, | |
| "grad_norm": 0.018153423443436623, | |
| "learning_rate": 5.421577984449938e-06, | |
| "loss": 0.704335880279541, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 1.5860597439544808, | |
| "grad_norm": 0.018131373450160027, | |
| "learning_rate": 5.380331065082713e-06, | |
| "loss": 0.7410067558288574, | |
| "step": 1115 | |
| }, | |
| { | |
| "epoch": 1.593172119487909, | |
| "grad_norm": 0.016608260571956635, | |
| "learning_rate": 5.339058095779611e-06, | |
| "loss": 0.72489333152771, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 1.600284495021337, | |
| "grad_norm": 0.01760363206267357, | |
| "learning_rate": 5.297761903441458e-06, | |
| "loss": 0.6614501953125, | |
| "step": 1125 | |
| }, | |
| { | |
| "epoch": 1.6073968705547652, | |
| "grad_norm": 0.10889118164777756, | |
| "learning_rate": 5.2564453165597e-06, | |
| "loss": 0.6915824890136719, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 1.6145092460881934, | |
| "grad_norm": 0.01632538251578808, | |
| "learning_rate": 5.215111165022653e-06, | |
| "loss": 0.7460376739501953, | |
| "step": 1135 | |
| }, | |
| { | |
| "epoch": 1.6216216216216215, | |
| "grad_norm": 0.016797514632344246, | |
| "learning_rate": 5.1737622799216925e-06, | |
| "loss": 0.6096005439758301, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 1.6287339971550496, | |
| "grad_norm": 0.018422367051243782, | |
| "learning_rate": 5.132401493357335e-06, | |
| "loss": 0.6219287395477295, | |
| "step": 1145 | |
| }, | |
| { | |
| "epoch": 1.635846372688478, | |
| "grad_norm": 0.018563445657491684, | |
| "learning_rate": 5.091031638245257e-06, | |
| "loss": 0.7117269515991211, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 1.6429587482219061, | |
| "grad_norm": 0.016881493851542473, | |
| "learning_rate": 5.0496555481222745e-06, | |
| "loss": 0.7350698471069336, | |
| "step": 1155 | |
| }, | |
| { | |
| "epoch": 1.6500711237553343, | |
| "grad_norm": 0.017679262906312943, | |
| "learning_rate": 5.008276056952246e-06, | |
| "loss": 0.7411237239837647, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 1.6571834992887624, | |
| "grad_norm": 0.01986612007021904, | |
| "learning_rate": 4.966895998931985e-06, | |
| "loss": 0.7164942741394043, | |
| "step": 1165 | |
| }, | |
| { | |
| "epoch": 1.6642958748221908, | |
| "grad_norm": 0.018696364015340805, | |
| "learning_rate": 4.925518208297124e-06, | |
| "loss": 0.7227424621582031, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 1.671408250355619, | |
| "grad_norm": 0.019415175542235374, | |
| "learning_rate": 4.884145519128005e-06, | |
| "loss": 0.6967507839202881, | |
| "step": 1175 | |
| }, | |
| { | |
| "epoch": 1.678520625889047, | |
| "grad_norm": 0.017584005370736122, | |
| "learning_rate": 4.842780765155549e-06, | |
| "loss": 0.7481791019439697, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 1.6856330014224752, | |
| "grad_norm": 0.019177937880158424, | |
| "learning_rate": 4.8014267795671726e-06, | |
| "loss": 0.7086362361907959, | |
| "step": 1185 | |
| }, | |
| { | |
| "epoch": 1.6927453769559033, | |
| "grad_norm": 0.017238428816199303, | |
| "learning_rate": 4.760086394812739e-06, | |
| "loss": 0.6951438903808593, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 1.6998577524893315, | |
| "grad_norm": 0.018072783946990967, | |
| "learning_rate": 4.718762442410553e-06, | |
| "loss": 0.7370012760162353, | |
| "step": 1195 | |
| }, | |
| { | |
| "epoch": 1.7069701280227596, | |
| "grad_norm": 0.017421068623661995, | |
| "learning_rate": 4.6774577527534195e-06, | |
| "loss": 0.7456617832183838, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 1.7140825035561877, | |
| "grad_norm": 0.01825086958706379, | |
| "learning_rate": 4.636175154914784e-06, | |
| "loss": 0.668549633026123, | |
| "step": 1205 | |
| }, | |
| { | |
| "epoch": 1.7211948790896159, | |
| "grad_norm": 0.020828979089856148, | |
| "learning_rate": 4.5949174764549635e-06, | |
| "loss": 0.7580900192260742, | |
| "step": 1210 | |
| }, | |
| { | |
| "epoch": 1.728307254623044, | |
| "grad_norm": 0.01653103157877922, | |
| "learning_rate": 4.553687543227478e-06, | |
| "loss": 0.6961758613586426, | |
| "step": 1215 | |
| }, | |
| { | |
| "epoch": 1.7354196301564722, | |
| "grad_norm": 0.01879982091486454, | |
| "learning_rate": 4.512488179185496e-06, | |
| "loss": 0.7488185882568359, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 1.7425320056899003, | |
| "grad_norm": 0.018451698124408722, | |
| "learning_rate": 4.471322206188417e-06, | |
| "loss": 0.7315212726593018, | |
| "step": 1225 | |
| }, | |
| { | |
| "epoch": 1.7496443812233284, | |
| "grad_norm": 0.018766777589917183, | |
| "learning_rate": 4.430192443808599e-06, | |
| "loss": 0.6953035354614258, | |
| "step": 1230 | |
| }, | |
| { | |
| "epoch": 1.7567567567567568, | |
| "grad_norm": 0.018258344382047653, | |
| "learning_rate": 4.389101709138232e-06, | |
| "loss": 0.7278485298156738, | |
| "step": 1235 | |
| }, | |
| { | |
| "epoch": 1.763869132290185, | |
| "grad_norm": 0.020150160416960716, | |
| "learning_rate": 4.348052816596383e-06, | |
| "loss": 0.7310956001281739, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 1.770981507823613, | |
| "grad_norm": 0.01763993687927723, | |
| "learning_rate": 4.307048577736248e-06, | |
| "loss": 0.703087854385376, | |
| "step": 1245 | |
| }, | |
| { | |
| "epoch": 1.7780938833570412, | |
| "grad_norm": 0.017417753115296364, | |
| "learning_rate": 4.266091801052555e-06, | |
| "loss": 0.6739617347717285, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 1.7852062588904696, | |
| "grad_norm": 0.016840264201164246, | |
| "learning_rate": 4.225185291789222e-06, | |
| "loss": 0.7178611278533935, | |
| "step": 1255 | |
| }, | |
| { | |
| "epoch": 1.7923186344238977, | |
| "grad_norm": 0.02682637609541416, | |
| "learning_rate": 4.184331851747205e-06, | |
| "loss": 0.6898033618927002, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 1.7994310099573259, | |
| "grad_norm": 0.018944881856441498, | |
| "learning_rate": 4.143534279092613e-06, | |
| "loss": 0.7165655136108399, | |
| "step": 1265 | |
| }, | |
| { | |
| "epoch": 1.806543385490754, | |
| "grad_norm": 0.017222313210368156, | |
| "learning_rate": 4.102795368165029e-06, | |
| "loss": 0.7229360580444336, | |
| "step": 1270 | |
| }, | |
| { | |
| "epoch": 1.8136557610241821, | |
| "grad_norm": 0.015961620956659317, | |
| "learning_rate": 4.062117909286134e-06, | |
| "loss": 0.7315521240234375, | |
| "step": 1275 | |
| }, | |
| { | |
| "epoch": 1.8207681365576103, | |
| "grad_norm": 0.018907621502876282, | |
| "learning_rate": 4.021504688568594e-06, | |
| "loss": 0.701743221282959, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 1.8278805120910384, | |
| "grad_norm": 0.016745159402489662, | |
| "learning_rate": 3.980958487725215e-06, | |
| "loss": 0.6797786712646484, | |
| "step": 1285 | |
| }, | |
| { | |
| "epoch": 1.8349928876244666, | |
| "grad_norm": 0.01896943338215351, | |
| "learning_rate": 3.9404820838784275e-06, | |
| "loss": 0.6718417644500733, | |
| "step": 1290 | |
| }, | |
| { | |
| "epoch": 1.8421052631578947, | |
| "grad_norm": 0.02180975303053856, | |
| "learning_rate": 3.9000782493700716e-06, | |
| "loss": 0.700644588470459, | |
| "step": 1295 | |
| }, | |
| { | |
| "epoch": 1.8492176386913228, | |
| "grad_norm": 0.018243227154016495, | |
| "learning_rate": 3.859749751571514e-06, | |
| "loss": 0.6863976955413819, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 1.856330014224751, | |
| "grad_norm": 0.02434358559548855, | |
| "learning_rate": 3.819499352694094e-06, | |
| "loss": 0.6976716041564941, | |
| "step": 1305 | |
| }, | |
| { | |
| "epoch": 1.863442389758179, | |
| "grad_norm": 0.01888590306043625, | |
| "learning_rate": 3.779329809599942e-06, | |
| "loss": 0.6664153575897217, | |
| "step": 1310 | |
| }, | |
| { | |
| "epoch": 1.8705547652916072, | |
| "grad_norm": 0.016964025795459747, | |
| "learning_rate": 3.7392438736131497e-06, | |
| "loss": 0.6734464168548584, | |
| "step": 1315 | |
| }, | |
| { | |
| "epoch": 1.8776671408250356, | |
| "grad_norm": 0.018329400569200516, | |
| "learning_rate": 3.699244290331322e-06, | |
| "loss": 0.7545855045318604, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 1.8847795163584637, | |
| "grad_norm": 0.018177052959799767, | |
| "learning_rate": 3.65933379943753e-06, | |
| "loss": 0.7079776763916016, | |
| "step": 1325 | |
| }, | |
| { | |
| "epoch": 1.8918918918918919, | |
| "grad_norm": 0.0189554113894701, | |
| "learning_rate": 3.6195151345126556e-06, | |
| "loss": 0.6924773216247558, | |
| "step": 1330 | |
| }, | |
| { | |
| "epoch": 1.89900426742532, | |
| "grad_norm": 0.01662875898182392, | |
| "learning_rate": 3.579791022848167e-06, | |
| "loss": 0.7359196186065674, | |
| "step": 1335 | |
| }, | |
| { | |
| "epoch": 1.9061166429587484, | |
| "grad_norm": 0.016495555639266968, | |
| "learning_rate": 3.5401641852593115e-06, | |
| "loss": 0.7219737529754638, | |
| "step": 1340 | |
| }, | |
| { | |
| "epoch": 1.9132290184921765, | |
| "grad_norm": 0.019022326916456223, | |
| "learning_rate": 3.5006373358987642e-06, | |
| "loss": 0.7027291297912598, | |
| "step": 1345 | |
| }, | |
| { | |
| "epoch": 1.9203413940256047, | |
| "grad_norm": 0.018207021057605743, | |
| "learning_rate": 3.4612131820707338e-06, | |
| "loss": 0.6637937545776367, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 1.9274537695590328, | |
| "grad_norm": 0.017069589346647263, | |
| "learning_rate": 3.4218944240455178e-06, | |
| "loss": 0.6664155006408692, | |
| "step": 1355 | |
| }, | |
| { | |
| "epoch": 1.934566145092461, | |
| "grad_norm": 0.01894293539226055, | |
| "learning_rate": 3.3826837548745615e-06, | |
| "loss": 0.7506007671356201, | |
| "step": 1360 | |
| }, | |
| { | |
| "epoch": 1.941678520625889, | |
| "grad_norm": 0.020717022940516472, | |
| "learning_rate": 3.343583860206011e-06, | |
| "loss": 0.6753596305847168, | |
| "step": 1365 | |
| }, | |
| { | |
| "epoch": 1.9487908961593172, | |
| "grad_norm": 0.017604727298021317, | |
| "learning_rate": 3.304597418100749e-06, | |
| "loss": 0.7200678825378418, | |
| "step": 1370 | |
| }, | |
| { | |
| "epoch": 1.9559032716927454, | |
| "grad_norm": 0.020626943558454514, | |
| "learning_rate": 3.265727098848978e-06, | |
| "loss": 0.7199074268341065, | |
| "step": 1375 | |
| }, | |
| { | |
| "epoch": 1.9630156472261735, | |
| "grad_norm": 0.01797352358698845, | |
| "learning_rate": 3.226975564787322e-06, | |
| "loss": 0.6880961418151855, | |
| "step": 1380 | |
| }, | |
| { | |
| "epoch": 1.9701280227596016, | |
| "grad_norm": 0.022289294749498367, | |
| "learning_rate": 3.1883454701164798e-06, | |
| "loss": 0.7005917072296143, | |
| "step": 1385 | |
| }, | |
| { | |
| "epoch": 1.9772403982930298, | |
| "grad_norm": 0.019266175106167793, | |
| "learning_rate": 3.1498394607194227e-06, | |
| "loss": 0.7002647399902344, | |
| "step": 1390 | |
| }, | |
| { | |
| "epoch": 1.984352773826458, | |
| "grad_norm": 0.01799497939646244, | |
| "learning_rate": 3.111460173980175e-06, | |
| "loss": 0.7084723949432373, | |
| "step": 1395 | |
| }, | |
| { | |
| "epoch": 1.991465149359886, | |
| "grad_norm": 0.018403980880975723, | |
| "learning_rate": 3.07321023860318e-06, | |
| "loss": 0.7116297721862793, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 1.9985775248933144, | |
| "grad_norm": 0.020092466846108437, | |
| "learning_rate": 3.0350922744332354e-06, | |
| "loss": 0.6756275177001954, | |
| "step": 1405 | |
| }, | |
| { | |
| "epoch": 2.0056899004267423, | |
| "grad_norm": 0.016876336187124252, | |
| "learning_rate": 2.9971088922760694e-06, | |
| "loss": 0.6916736602783203, | |
| "step": 1410 | |
| }, | |
| { | |
| "epoch": 2.012802275960171, | |
| "grad_norm": 0.0186183899641037, | |
| "learning_rate": 2.959262693719507e-06, | |
| "loss": 0.7194989681243896, | |
| "step": 1415 | |
| }, | |
| { | |
| "epoch": 2.019914651493599, | |
| "grad_norm": 0.018291359767317772, | |
| "learning_rate": 2.9215562709552936e-06, | |
| "loss": 0.7254909992218017, | |
| "step": 1420 | |
| }, | |
| { | |
| "epoch": 2.027027027027027, | |
| "grad_norm": 0.018498683348298073, | |
| "learning_rate": 2.8839922066015337e-06, | |
| "loss": 0.7562304496765136, | |
| "step": 1425 | |
| }, | |
| { | |
| "epoch": 2.0341394025604553, | |
| "grad_norm": 0.0183123629540205, | |
| "learning_rate": 2.846573073525809e-06, | |
| "loss": 0.6986132621765136, | |
| "step": 1430 | |
| }, | |
| { | |
| "epoch": 2.0412517780938835, | |
| "grad_norm": 0.01785789616405964, | |
| "learning_rate": 2.8093014346689547e-06, | |
| "loss": 0.7192048072814942, | |
| "step": 1435 | |
| }, | |
| { | |
| "epoch": 2.0483641536273116, | |
| "grad_norm": 0.023237911984324455, | |
| "learning_rate": 2.7721798428695164e-06, | |
| "loss": 0.6775825023651123, | |
| "step": 1440 | |
| }, | |
| { | |
| "epoch": 2.0554765291607398, | |
| "grad_norm": 0.020147794857621193, | |
| "learning_rate": 2.7352108406888923e-06, | |
| "loss": 0.6980232238769531, | |
| "step": 1445 | |
| }, | |
| { | |
| "epoch": 2.062588904694168, | |
| "grad_norm": 0.02223370037972927, | |
| "learning_rate": 2.6983969602371983e-06, | |
| "loss": 0.713938570022583, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 2.069701280227596, | |
| "grad_norm": 0.016787713393568993, | |
| "learning_rate": 2.661740722999827e-06, | |
| "loss": 0.7800277709960938, | |
| "step": 1455 | |
| }, | |
| { | |
| "epoch": 2.076813655761024, | |
| "grad_norm": 0.018036190420389175, | |
| "learning_rate": 2.6252446396647503e-06, | |
| "loss": 0.6451656818389893, | |
| "step": 1460 | |
| }, | |
| { | |
| "epoch": 2.0839260312944523, | |
| "grad_norm": 0.01903928630053997, | |
| "learning_rate": 2.5889112099505452e-06, | |
| "loss": 0.6771600246429443, | |
| "step": 1465 | |
| }, | |
| { | |
| "epoch": 2.0910384068278804, | |
| "grad_norm": 0.01969575695693493, | |
| "learning_rate": 2.5527429224352006e-06, | |
| "loss": 0.7296658515930176, | |
| "step": 1470 | |
| }, | |
| { | |
| "epoch": 2.0981507823613086, | |
| "grad_norm": 0.02083515003323555, | |
| "learning_rate": 2.5167422543856424e-06, | |
| "loss": 0.6964072704315185, | |
| "step": 1475 | |
| }, | |
| { | |
| "epoch": 2.1052631578947367, | |
| "grad_norm": 0.019397174939513206, | |
| "learning_rate": 2.4809116715880792e-06, | |
| "loss": 0.6488191604614257, | |
| "step": 1480 | |
| }, | |
| { | |
| "epoch": 2.112375533428165, | |
| "grad_norm": 0.019878752529621124, | |
| "learning_rate": 2.4452536281791056e-06, | |
| "loss": 0.6778024673461914, | |
| "step": 1485 | |
| }, | |
| { | |
| "epoch": 2.119487908961593, | |
| "grad_norm": 0.01916521228849888, | |
| "learning_rate": 2.409770566477611e-06, | |
| "loss": 0.7552609920501709, | |
| "step": 1490 | |
| }, | |
| { | |
| "epoch": 2.126600284495021, | |
| "grad_norm": 0.018846770748496056, | |
| "learning_rate": 2.3744649168174966e-06, | |
| "loss": 0.6998651027679443, | |
| "step": 1495 | |
| }, | |
| { | |
| "epoch": 2.1337126600284497, | |
| "grad_norm": 0.021791398525238037, | |
| "learning_rate": 2.339339097381222e-06, | |
| "loss": 0.7401346206665039, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 2.140825035561878, | |
| "grad_norm": 0.018046008422970772, | |
| "learning_rate": 2.304395514034172e-06, | |
| "loss": 0.6855841636657715, | |
| "step": 1505 | |
| }, | |
| { | |
| "epoch": 2.147937411095306, | |
| "grad_norm": 0.017584893852472305, | |
| "learning_rate": 2.2696365601598714e-06, | |
| "loss": 0.76700758934021, | |
| "step": 1510 | |
| }, | |
| { | |
| "epoch": 2.155049786628734, | |
| "grad_norm": 0.020246658474206924, | |
| "learning_rate": 2.235064616496059e-06, | |
| "loss": 0.70643630027771, | |
| "step": 1515 | |
| }, | |
| { | |
| "epoch": 2.1621621621621623, | |
| "grad_norm": 0.018499314785003662, | |
| "learning_rate": 2.200682050971622e-06, | |
| "loss": 0.7396338939666748, | |
| "step": 1520 | |
| }, | |
| { | |
| "epoch": 2.1692745376955904, | |
| "grad_norm": 0.023796167224645615, | |
| "learning_rate": 2.1664912185444127e-06, | |
| "loss": 0.6971643447875977, | |
| "step": 1525 | |
| }, | |
| { | |
| "epoch": 2.1763869132290186, | |
| "grad_norm": 0.019194869324564934, | |
| "learning_rate": 2.1324944610399423e-06, | |
| "loss": 0.7047183990478516, | |
| "step": 1530 | |
| }, | |
| { | |
| "epoch": 2.1834992887624467, | |
| "grad_norm": 0.018008023500442505, | |
| "learning_rate": 2.0986941069909937e-06, | |
| "loss": 0.7083112239837647, | |
| "step": 1535 | |
| }, | |
| { | |
| "epoch": 2.190611664295875, | |
| "grad_norm": 0.021395748481154442, | |
| "learning_rate": 2.06509247147813e-06, | |
| "loss": 0.7210383415222168, | |
| "step": 1540 | |
| }, | |
| { | |
| "epoch": 2.197724039829303, | |
| "grad_norm": 0.0217084139585495, | |
| "learning_rate": 2.0316918559711264e-06, | |
| "loss": 0.7158208847045898, | |
| "step": 1545 | |
| }, | |
| { | |
| "epoch": 2.204836415362731, | |
| "grad_norm": 0.02183559723198414, | |
| "learning_rate": 1.9984945481713308e-06, | |
| "loss": 0.6984762668609619, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 2.2119487908961593, | |
| "grad_norm": 0.020434515550732613, | |
| "learning_rate": 1.9655028218549925e-06, | |
| "loss": 0.6603986263275147, | |
| "step": 1555 | |
| }, | |
| { | |
| "epoch": 2.2190611664295874, | |
| "grad_norm": 0.021293608471751213, | |
| "learning_rate": 1.932718936717497e-06, | |
| "loss": 0.6903936862945557, | |
| "step": 1560 | |
| }, | |
| { | |
| "epoch": 2.2261735419630155, | |
| "grad_norm": 0.019045505672693253, | |
| "learning_rate": 1.900145138218617e-06, | |
| "loss": 0.7222468852996826, | |
| "step": 1565 | |
| }, | |
| { | |
| "epoch": 2.2332859174964437, | |
| "grad_norm": 0.020146358758211136, | |
| "learning_rate": 1.8677836574286978e-06, | |
| "loss": 0.757137680053711, | |
| "step": 1570 | |
| }, | |
| { | |
| "epoch": 2.240398293029872, | |
| "grad_norm": 0.019575543701648712, | |
| "learning_rate": 1.8356367108758628e-06, | |
| "loss": 0.7008779525756836, | |
| "step": 1575 | |
| }, | |
| { | |
| "epoch": 2.2475106685633, | |
| "grad_norm": 0.018083350732922554, | |
| "learning_rate": 1.803706500394175e-06, | |
| "loss": 0.7534774780273438, | |
| "step": 1580 | |
| }, | |
| { | |
| "epoch": 2.2546230440967285, | |
| "grad_norm": 0.021902941167354584, | |
| "learning_rate": 1.771995212972847e-06, | |
| "loss": 0.6821448326110839, | |
| "step": 1585 | |
| }, | |
| { | |
| "epoch": 2.2617354196301562, | |
| "grad_norm": 0.021106917411088943, | |
| "learning_rate": 1.7405050206064372e-06, | |
| "loss": 0.7266870498657226, | |
| "step": 1590 | |
| }, | |
| { | |
| "epoch": 2.268847795163585, | |
| "grad_norm": 0.020212018862366676, | |
| "learning_rate": 1.70923808014609e-06, | |
| "loss": 0.7044878959655761, | |
| "step": 1595 | |
| }, | |
| { | |
| "epoch": 2.275960170697013, | |
| "grad_norm": 0.017820734530687332, | |
| "learning_rate": 1.6781965331517975e-06, | |
| "loss": 0.6944470405578613, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 2.283072546230441, | |
| "grad_norm": 0.017846427857875824, | |
| "learning_rate": 1.6473825057457293e-06, | |
| "loss": 0.6674845695495606, | |
| "step": 1605 | |
| }, | |
| { | |
| "epoch": 2.2901849217638692, | |
| "grad_norm": 0.018820255994796753, | |
| "learning_rate": 1.616798108466603e-06, | |
| "loss": 0.7415022850036621, | |
| "step": 1610 | |
| }, | |
| { | |
| "epoch": 2.2972972972972974, | |
| "grad_norm": 0.0177475456148386, | |
| "learning_rate": 1.586445436125127e-06, | |
| "loss": 0.7364046096801757, | |
| "step": 1615 | |
| }, | |
| { | |
| "epoch": 2.3044096728307255, | |
| "grad_norm": 0.02009609155356884, | |
| "learning_rate": 1.5563265676605228e-06, | |
| "loss": 0.6232909202575684, | |
| "step": 1620 | |
| }, | |
| { | |
| "epoch": 2.3115220483641536, | |
| "grad_norm": 0.01963597536087036, | |
| "learning_rate": 1.5264435659981335e-06, | |
| "loss": 0.7436121940612793, | |
| "step": 1625 | |
| }, | |
| { | |
| "epoch": 2.318634423897582, | |
| "grad_norm": 0.01879408396780491, | |
| "learning_rate": 1.496798477908122e-06, | |
| "loss": 0.6992465019226074, | |
| "step": 1630 | |
| }, | |
| { | |
| "epoch": 2.32574679943101, | |
| "grad_norm": 0.018343554809689522, | |
| "learning_rate": 1.4673933338652907e-06, | |
| "loss": 0.690833330154419, | |
| "step": 1635 | |
| }, | |
| { | |
| "epoch": 2.332859174964438, | |
| "grad_norm": 0.018954213708639145, | |
| "learning_rate": 1.4382301479100048e-06, | |
| "loss": 0.7103327751159668, | |
| "step": 1640 | |
| }, | |
| { | |
| "epoch": 2.339971550497866, | |
| "grad_norm": 0.01864561438560486, | |
| "learning_rate": 1.4093109175102432e-06, | |
| "loss": 0.7096752166748047, | |
| "step": 1645 | |
| }, | |
| { | |
| "epoch": 2.3470839260312943, | |
| "grad_norm": 0.018006840720772743, | |
| "learning_rate": 1.380637623424791e-06, | |
| "loss": 0.7237026214599609, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 2.3541963015647225, | |
| "grad_norm": 0.01974598504602909, | |
| "learning_rate": 1.3522122295675616e-06, | |
| "loss": 0.7115821361541748, | |
| "step": 1655 | |
| }, | |
| { | |
| "epoch": 2.3613086770981506, | |
| "grad_norm": 0.01914205215871334, | |
| "learning_rate": 1.324036682873102e-06, | |
| "loss": 0.721008586883545, | |
| "step": 1660 | |
| }, | |
| { | |
| "epoch": 2.3684210526315788, | |
| "grad_norm": 0.019481945782899857, | |
| "learning_rate": 1.2961129131632183e-06, | |
| "loss": 0.7210357666015625, | |
| "step": 1665 | |
| }, | |
| { | |
| "epoch": 2.3755334281650073, | |
| "grad_norm": 0.0294849444180727, | |
| "learning_rate": 1.2684428330148164e-06, | |
| "loss": 0.7165197372436524, | |
| "step": 1670 | |
| }, | |
| { | |
| "epoch": 2.382645803698435, | |
| "grad_norm": 0.019714608788490295, | |
| "learning_rate": 1.241028337628888e-06, | |
| "loss": 0.7028004646301269, | |
| "step": 1675 | |
| }, | |
| { | |
| "epoch": 2.3897581792318636, | |
| "grad_norm": 0.017666790634393692, | |
| "learning_rate": 1.2138713047007229e-06, | |
| "loss": 0.6465110301971435, | |
| "step": 1680 | |
| }, | |
| { | |
| "epoch": 2.3968705547652918, | |
| "grad_norm": 0.020633701235055923, | |
| "learning_rate": 1.1869735942912768e-06, | |
| "loss": 0.6445804595947265, | |
| "step": 1685 | |
| }, | |
| { | |
| "epoch": 2.40398293029872, | |
| "grad_norm": 0.019184108823537827, | |
| "learning_rate": 1.1603370486997912e-06, | |
| "loss": 0.6999986171722412, | |
| "step": 1690 | |
| }, | |
| { | |
| "epoch": 2.411095305832148, | |
| "grad_norm": 0.018636522814631462, | |
| "learning_rate": 1.1339634923375958e-06, | |
| "loss": 0.7130412578582763, | |
| "step": 1695 | |
| }, | |
| { | |
| "epoch": 2.418207681365576, | |
| "grad_norm": 0.02027011662721634, | |
| "learning_rate": 1.107854731603158e-06, | |
| "loss": 0.7074708938598633, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 2.4253200568990043, | |
| "grad_norm": 0.01711525022983551, | |
| "learning_rate": 1.082012554758346e-06, | |
| "loss": 0.7176192283630372, | |
| "step": 1705 | |
| }, | |
| { | |
| "epoch": 2.4324324324324325, | |
| "grad_norm": 0.01916031911969185, | |
| "learning_rate": 1.0564387318059654e-06, | |
| "loss": 0.7125048637390137, | |
| "step": 1710 | |
| }, | |
| { | |
| "epoch": 2.4395448079658606, | |
| "grad_norm": 0.018072018399834633, | |
| "learning_rate": 1.031135014368504e-06, | |
| "loss": 0.7297768115997314, | |
| "step": 1715 | |
| }, | |
| { | |
| "epoch": 2.4466571834992887, | |
| "grad_norm": 0.017285477370023727, | |
| "learning_rate": 1.0061031355681766e-06, | |
| "loss": 0.6963360786437989, | |
| "step": 1720 | |
| }, | |
| { | |
| "epoch": 2.453769559032717, | |
| "grad_norm": 0.020556973293423653, | |
| "learning_rate": 9.813448099082047e-07, | |
| "loss": 0.7077793598175048, | |
| "step": 1725 | |
| }, | |
| { | |
| "epoch": 2.460881934566145, | |
| "grad_norm": 0.0190748143941164, | |
| "learning_rate": 9.568617331553997e-07, | |
| "loss": 0.6809517860412597, | |
| "step": 1730 | |
| }, | |
| { | |
| "epoch": 2.467994310099573, | |
| "grad_norm": 0.020035238936543465, | |
| "learning_rate": 9.326555822240002e-07, | |
| "loss": 0.7002559185028077, | |
| "step": 1735 | |
| }, | |
| { | |
| "epoch": 2.4751066856330013, | |
| "grad_norm": 0.02111983671784401, | |
| "learning_rate": 9.087280150608263e-07, | |
| "loss": 0.6911906719207763, | |
| "step": 1740 | |
| }, | |
| { | |
| "epoch": 2.4822190611664294, | |
| "grad_norm": 0.01914399489760399, | |
| "learning_rate": 8.850806705317183e-07, | |
| "loss": 0.7122188568115234, | |
| "step": 1745 | |
| }, | |
| { | |
| "epoch": 2.4893314366998576, | |
| "grad_norm": 0.019931111484766006, | |
| "learning_rate": 8.617151683092856e-07, | |
| "loss": 0.6926873683929443, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 2.496443812233286, | |
| "grad_norm": 0.042251236736774445, | |
| "learning_rate": 8.386331087619726e-07, | |
| "loss": 0.701508903503418, | |
| "step": 1755 | |
| }, | |
| { | |
| "epoch": 2.503556187766714, | |
| "grad_norm": 0.019246656447649002, | |
| "learning_rate": 8.158360728444404e-07, | |
| "loss": 0.7105617523193359, | |
| "step": 1760 | |
| }, | |
| { | |
| "epoch": 2.5106685633001424, | |
| "grad_norm": 0.018132740631699562, | |
| "learning_rate": 7.933256219892938e-07, | |
| "loss": 0.7254996299743652, | |
| "step": 1765 | |
| }, | |
| { | |
| "epoch": 2.5177809388335706, | |
| "grad_norm": 0.020589511841535568, | |
| "learning_rate": 7.711032980001182e-07, | |
| "loss": 0.6329239845275879, | |
| "step": 1770 | |
| }, | |
| { | |
| "epoch": 2.5248933143669987, | |
| "grad_norm": 0.017706142738461494, | |
| "learning_rate": 7.491706229458923e-07, | |
| "loss": 0.6217228889465332, | |
| "step": 1775 | |
| }, | |
| { | |
| "epoch": 2.532005689900427, | |
| "grad_norm": 0.019098540768027306, | |
| "learning_rate": 7.275290990567286e-07, | |
| "loss": 0.6849424362182617, | |
| "step": 1780 | |
| }, | |
| { | |
| "epoch": 2.539118065433855, | |
| "grad_norm": 0.017864609137177467, | |
| "learning_rate": 7.061802086209857e-07, | |
| "loss": 0.6907006740570069, | |
| "step": 1785 | |
| }, | |
| { | |
| "epoch": 2.546230440967283, | |
| "grad_norm": 0.01882258802652359, | |
| "learning_rate": 6.851254138837366e-07, | |
| "loss": 0.7112642765045166, | |
| "step": 1790 | |
| }, | |
| { | |
| "epoch": 2.5533428165007113, | |
| "grad_norm": 0.017759790644049644, | |
| "learning_rate": 6.643661569466225e-07, | |
| "loss": 0.6860599994659424, | |
| "step": 1795 | |
| }, | |
| { | |
| "epoch": 2.5604551920341394, | |
| "grad_norm": 0.04660586640238762, | |
| "learning_rate": 6.439038596690756e-07, | |
| "loss": 0.6946640968322754, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 2.5675675675675675, | |
| "grad_norm": 0.018053406849503517, | |
| "learning_rate": 6.237399235709335e-07, | |
| "loss": 0.70596923828125, | |
| "step": 1805 | |
| }, | |
| { | |
| "epoch": 2.5746799431009957, | |
| "grad_norm": 0.01948445849120617, | |
| "learning_rate": 6.038757297364389e-07, | |
| "loss": 0.6995176792144775, | |
| "step": 1810 | |
| }, | |
| { | |
| "epoch": 2.581792318634424, | |
| "grad_norm": 0.017586836591362953, | |
| "learning_rate": 5.843126387196591e-07, | |
| "loss": 0.7351008892059326, | |
| "step": 1815 | |
| }, | |
| { | |
| "epoch": 2.588904694167852, | |
| "grad_norm": 0.018592992797493935, | |
| "learning_rate": 5.650519904512814e-07, | |
| "loss": 0.6893433570861817, | |
| "step": 1820 | |
| }, | |
| { | |
| "epoch": 2.59601706970128, | |
| "grad_norm": 0.01698880083858967, | |
| "learning_rate": 5.460951041468493e-07, | |
| "loss": 0.6391551494598389, | |
| "step": 1825 | |
| }, | |
| { | |
| "epoch": 2.6031294452347082, | |
| "grad_norm": 0.019620927050709724, | |
| "learning_rate": 5.27443278216399e-07, | |
| "loss": 0.688290023803711, | |
| "step": 1830 | |
| }, | |
| { | |
| "epoch": 2.6102418207681364, | |
| "grad_norm": 0.019304607063531876, | |
| "learning_rate": 5.090977901755362e-07, | |
| "loss": 0.7163221359252929, | |
| "step": 1835 | |
| }, | |
| { | |
| "epoch": 2.617354196301565, | |
| "grad_norm": 0.0220966674387455, | |
| "learning_rate": 4.910598965579228e-07, | |
| "loss": 0.7392453670501709, | |
| "step": 1840 | |
| }, | |
| { | |
| "epoch": 2.6244665718349927, | |
| "grad_norm": 0.01833263970911503, | |
| "learning_rate": 4.7333083282922463e-07, | |
| "loss": 0.6708541870117187, | |
| "step": 1845 | |
| }, | |
| { | |
| "epoch": 2.6315789473684212, | |
| "grad_norm": 0.020094405859708786, | |
| "learning_rate": 4.5591181330248534e-07, | |
| "loss": 0.6930543422698975, | |
| "step": 1850 | |
| }, | |
| { | |
| "epoch": 2.6386913229018494, | |
| "grad_norm": 0.020695924758911133, | |
| "learning_rate": 4.3880403105495793e-07, | |
| "loss": 0.6685608863830567, | |
| "step": 1855 | |
| }, | |
| { | |
| "epoch": 2.6458036984352775, | |
| "grad_norm": 0.018926840275526047, | |
| "learning_rate": 4.220086578463806e-07, | |
| "loss": 0.6826137065887451, | |
| "step": 1860 | |
| }, | |
| { | |
| "epoch": 2.6529160739687057, | |
| "grad_norm": 0.01943895034492016, | |
| "learning_rate": 4.0552684403873274e-07, | |
| "loss": 0.6445528030395508, | |
| "step": 1865 | |
| }, | |
| { | |
| "epoch": 2.660028449502134, | |
| "grad_norm": 0.019336692988872528, | |
| "learning_rate": 3.8935971851742746e-07, | |
| "loss": 0.6931255340576172, | |
| "step": 1870 | |
| }, | |
| { | |
| "epoch": 2.667140825035562, | |
| "grad_norm": 0.017861362546682358, | |
| "learning_rate": 3.7350838861400454e-07, | |
| "loss": 0.680919075012207, | |
| "step": 1875 | |
| }, | |
| { | |
| "epoch": 2.67425320056899, | |
| "grad_norm": 0.01909296214580536, | |
| "learning_rate": 3.579739400302773e-07, | |
| "loss": 0.756756591796875, | |
| "step": 1880 | |
| }, | |
| { | |
| "epoch": 2.681365576102418, | |
| "grad_norm": 0.022265156731009483, | |
| "learning_rate": 3.4275743676397633e-07, | |
| "loss": 0.7306240558624267, | |
| "step": 1885 | |
| }, | |
| { | |
| "epoch": 2.6884779516358464, | |
| "grad_norm": 0.019674202427268028, | |
| "learning_rate": 3.278599210358685e-07, | |
| "loss": 0.7194355964660645, | |
| "step": 1890 | |
| }, | |
| { | |
| "epoch": 2.6955903271692745, | |
| "grad_norm": 0.02009180188179016, | |
| "learning_rate": 3.132824132183726e-07, | |
| "loss": 0.6854644298553467, | |
| "step": 1895 | |
| }, | |
| { | |
| "epoch": 2.7027027027027026, | |
| "grad_norm": 0.019245633855462074, | |
| "learning_rate": 2.9902591176567743e-07, | |
| "loss": 0.7046674728393555, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 2.7098150782361308, | |
| "grad_norm": 0.019660472869873047, | |
| "learning_rate": 2.850913931453447e-07, | |
| "loss": 0.6495515823364257, | |
| "step": 1905 | |
| }, | |
| { | |
| "epoch": 2.716927453769559, | |
| "grad_norm": 0.018463047221302986, | |
| "learning_rate": 2.714798117714373e-07, | |
| "loss": 0.7126041889190674, | |
| "step": 1910 | |
| }, | |
| { | |
| "epoch": 2.724039829302987, | |
| "grad_norm": 0.020338578149676323, | |
| "learning_rate": 2.5819209993914185e-07, | |
| "loss": 0.6964741706848144, | |
| "step": 1915 | |
| }, | |
| { | |
| "epoch": 2.731152204836415, | |
| "grad_norm": 0.025541720911860466, | |
| "learning_rate": 2.4522916776092144e-07, | |
| "loss": 0.6981581211090088, | |
| "step": 1920 | |
| }, | |
| { | |
| "epoch": 2.7382645803698438, | |
| "grad_norm": 0.03043808415532112, | |
| "learning_rate": 2.3259190310416847e-07, | |
| "loss": 0.6668709278106689, | |
| "step": 1925 | |
| }, | |
| { | |
| "epoch": 2.7453769559032715, | |
| "grad_norm": 0.017312461510300636, | |
| "learning_rate": 2.2028117153040208e-07, | |
| "loss": 0.6342219829559326, | |
| "step": 1930 | |
| }, | |
| { | |
| "epoch": 2.7524893314367, | |
| "grad_norm": 0.022723648697137833, | |
| "learning_rate": 2.082978162359778e-07, | |
| "loss": 0.7471845149993896, | |
| "step": 1935 | |
| }, | |
| { | |
| "epoch": 2.759601706970128, | |
| "grad_norm": 0.01946732960641384, | |
| "learning_rate": 1.9664265799433758e-07, | |
| "loss": 0.727109432220459, | |
| "step": 1940 | |
| }, | |
| { | |
| "epoch": 2.7667140825035563, | |
| "grad_norm": 0.019219428300857544, | |
| "learning_rate": 1.8531649509978933e-07, | |
| "loss": 0.6843738079071044, | |
| "step": 1945 | |
| }, | |
| { | |
| "epoch": 2.7738264580369845, | |
| "grad_norm": 0.017926136031746864, | |
| "learning_rate": 1.7432010331283388e-07, | |
| "loss": 0.7088566780090332, | |
| "step": 1950 | |
| }, | |
| { | |
| "epoch": 2.7809388335704126, | |
| "grad_norm": 0.01807708479464054, | |
| "learning_rate": 1.63654235807027e-07, | |
| "loss": 0.7071962833404541, | |
| "step": 1955 | |
| }, | |
| { | |
| "epoch": 2.7880512091038407, | |
| "grad_norm": 0.019878104329109192, | |
| "learning_rate": 1.5331962311739668e-07, | |
| "loss": 0.7710360527038574, | |
| "step": 1960 | |
| }, | |
| { | |
| "epoch": 2.795163584637269, | |
| "grad_norm": 0.02000255696475506, | |
| "learning_rate": 1.4331697309039937e-07, | |
| "loss": 0.6493950366973877, | |
| "step": 1965 | |
| }, | |
| { | |
| "epoch": 2.802275960170697, | |
| "grad_norm": 0.01814078353345394, | |
| "learning_rate": 1.336469708354493e-07, | |
| "loss": 0.69231276512146, | |
| "step": 1970 | |
| }, | |
| { | |
| "epoch": 2.809388335704125, | |
| "grad_norm": 0.02213713899254799, | |
| "learning_rate": 1.243102786779804e-07, | |
| "loss": 0.6923561096191406, | |
| "step": 1975 | |
| }, | |
| { | |
| "epoch": 2.8165007112375533, | |
| "grad_norm": 0.01917503960430622, | |
| "learning_rate": 1.1530753611409151e-07, | |
| "loss": 0.7251245498657226, | |
| "step": 1980 | |
| }, | |
| { | |
| "epoch": 2.8236130867709814, | |
| "grad_norm": 0.01758253388106823, | |
| "learning_rate": 1.0663935976674145e-07, | |
| "loss": 0.7662966251373291, | |
| "step": 1985 | |
| }, | |
| { | |
| "epoch": 2.8307254623044096, | |
| "grad_norm": 0.020537367090582848, | |
| "learning_rate": 9.830634334351385e-08, | |
| "loss": 0.6968005180358887, | |
| "step": 1990 | |
| }, | |
| { | |
| "epoch": 2.8378378378378377, | |
| "grad_norm": 0.01874646171927452, | |
| "learning_rate": 9.030905759595643e-08, | |
| "loss": 0.7220873355865478, | |
| "step": 1995 | |
| }, | |
| { | |
| "epoch": 2.844950213371266, | |
| "grad_norm": 0.019075002521276474, | |
| "learning_rate": 8.264805028048384e-08, | |
| "loss": 0.749581241607666, | |
| "step": 2000 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 2109, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 400, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.1755490933791949e+19, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |