Text Generation
Transformers
Safetensors
Japanese
English
llama
llm-jp
math
sft
full-parameter-finetuning
team-victory
experiment-0399
wandb
conversational
text-generation-inference
Instructions to use argo11/0399-tv-full-base-fp with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use argo11/0399-tv-full-base-fp with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="argo11/0399-tv-full-base-fp") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("argo11/0399-tv-full-base-fp") model = AutoModelForCausalLM.from_pretrained("argo11/0399-tv-full-base-fp", device_map="auto") messages = [ {"role": "user", "content": "Who are you?"}, ] inputs = tokenizer.apply_chat_template( messages, add_generation_prompt=True, tokenize=True, return_dict=True, return_tensors="pt", ).to(model.device) outputs = model.generate(**inputs, max_new_tokens=40) print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:])) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use argo11/0399-tv-full-base-fp with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "argo11/0399-tv-full-base-fp" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "argo11/0399-tv-full-base-fp", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/argo11/0399-tv-full-base-fp
- SGLang
How to use argo11/0399-tv-full-base-fp 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 "argo11/0399-tv-full-base-fp" \ --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": "argo11/0399-tv-full-base-fp", "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 "argo11/0399-tv-full-base-fp" \ --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": "argo11/0399-tv-full-base-fp", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use argo11/0399-tv-full-base-fp with Docker Model Runner:
docker model run hf.co/argo11/0399-tv-full-base-fp
Invalid JSON:Unexpected token 'I', ..."ad_norm": Infinity,
"... is not valid JSON
| { | |
| "best_global_step": null, | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.03515788085873124, | |
| "eval_steps": 500, | |
| "global_step": 1500, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0002343858723915416, | |
| "grad_norm": Infinity, | |
| "learning_rate": 1.40625e-07, | |
| "loss": 0.6092071533203125, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0004687717447830832, | |
| "grad_norm": Infinity, | |
| "learning_rate": 2.96875e-07, | |
| "loss": 0.6080734252929687, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0007031576171746248, | |
| "grad_norm": Infinity, | |
| "learning_rate": 4.53125e-07, | |
| "loss": 0.6008880615234375, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0009375434895661664, | |
| "grad_norm": Infinity, | |
| "learning_rate": 6.09375e-07, | |
| "loss": 0.6059707641601563, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.001171929361957708, | |
| "grad_norm": Infinity, | |
| "learning_rate": 7.656250000000001e-07, | |
| "loss": 0.615313720703125, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.0014063152343492496, | |
| "grad_norm": Infinity, | |
| "learning_rate": 9.218750000000002e-07, | |
| "loss": 0.6074554443359375, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.0016407011067407912, | |
| "grad_norm": Infinity, | |
| "learning_rate": 1.0781250000000002e-06, | |
| "loss": 0.605792236328125, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.0018750869791323327, | |
| "grad_norm": Infinity, | |
| "learning_rate": 1.2343750000000001e-06, | |
| "loss": 0.6068206787109375, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.0021094728515238742, | |
| "grad_norm": Infinity, | |
| "learning_rate": 1.3906250000000001e-06, | |
| "loss": 0.6020843505859375, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.002343858723915416, | |
| "grad_norm": Infinity, | |
| "learning_rate": 1.5468750000000001e-06, | |
| "loss": 0.59473876953125, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.0025782445963069577, | |
| "grad_norm": Infinity, | |
| "learning_rate": 1.703125e-06, | |
| "loss": 0.6020477294921875, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.0028126304686984993, | |
| "grad_norm": Infinity, | |
| "learning_rate": 1.8593750000000003e-06, | |
| "loss": 0.596124267578125, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.003047016341090041, | |
| "grad_norm": Infinity, | |
| "learning_rate": 2.0156250000000003e-06, | |
| "loss": 0.6029708862304688, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.0032814022134815823, | |
| "grad_norm": Infinity, | |
| "learning_rate": 2.1718750000000003e-06, | |
| "loss": 0.5990798950195313, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.003515788085873124, | |
| "grad_norm": Infinity, | |
| "learning_rate": 2.3281250000000003e-06, | |
| "loss": 0.5956100463867188, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.0037501739582646654, | |
| "grad_norm": Infinity, | |
| "learning_rate": 2.4843750000000002e-06, | |
| "loss": 0.59793701171875, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.003984559830656207, | |
| "grad_norm": Infinity, | |
| "learning_rate": 2.640625e-06, | |
| "loss": 0.6025466918945312, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.0042189457030477485, | |
| "grad_norm": Infinity, | |
| "learning_rate": 2.796875e-06, | |
| "loss": 0.6034042358398437, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.0044533315754392904, | |
| "grad_norm": Infinity, | |
| "learning_rate": 2.953125e-06, | |
| "loss": 0.6109519958496094, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.004687717447830832, | |
| "grad_norm": Infinity, | |
| "learning_rate": 3.109375e-06, | |
| "loss": 0.6124420166015625, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.0049221033202223735, | |
| "grad_norm": Infinity, | |
| "learning_rate": 3.265625e-06, | |
| "loss": 0.5962295532226562, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.0051564891926139155, | |
| "grad_norm": Infinity, | |
| "learning_rate": 3.421875e-06, | |
| "loss": 0.5996864318847657, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.005390875065005457, | |
| "grad_norm": Infinity, | |
| "learning_rate": 3.578125e-06, | |
| "loss": 0.6116897583007812, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.0056252609373969985, | |
| "grad_norm": Infinity, | |
| "learning_rate": 3.734375e-06, | |
| "loss": 0.6195701599121094, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.00585964680978854, | |
| "grad_norm": Infinity, | |
| "learning_rate": 3.890625e-06, | |
| "loss": 0.6111648559570313, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.006094032682180082, | |
| "grad_norm": Infinity, | |
| "learning_rate": 4.046875e-06, | |
| "loss": 0.6055526733398438, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.006328418554571624, | |
| "grad_norm": Infinity, | |
| "learning_rate": 4.2031250000000005e-06, | |
| "loss": 0.5984527587890625, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.006562804426963165, | |
| "grad_norm": Infinity, | |
| "learning_rate": 4.359375e-06, | |
| "loss": 0.6135429382324219, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.006797190299354707, | |
| "grad_norm": Infinity, | |
| "learning_rate": 4.5156250000000005e-06, | |
| "loss": 0.5952308654785157, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.007031576171746248, | |
| "grad_norm": Infinity, | |
| "learning_rate": 4.671875e-06, | |
| "loss": 0.6037254333496094, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.00726596204413779, | |
| "grad_norm": Infinity, | |
| "learning_rate": 4.8281250000000005e-06, | |
| "loss": 0.5975120544433594, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.007500347916529331, | |
| "grad_norm": Infinity, | |
| "learning_rate": 4.984375e-06, | |
| "loss": 0.5918365478515625, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.007734733788920873, | |
| "grad_norm": Infinity, | |
| "learning_rate": 5.1406250000000004e-06, | |
| "loss": 0.6080474853515625, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.007969119661312415, | |
| "grad_norm": Infinity, | |
| "learning_rate": 5.296875e-06, | |
| "loss": 0.6048797607421875, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.008203505533703956, | |
| "grad_norm": Infinity, | |
| "learning_rate": 5.453125e-06, | |
| "loss": 0.593927001953125, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.008437891406095497, | |
| "grad_norm": Infinity, | |
| "learning_rate": 5.609375e-06, | |
| "loss": 0.6036277770996094, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.00867227727848704, | |
| "grad_norm": Infinity, | |
| "learning_rate": 5.765625e-06, | |
| "loss": 0.604638671875, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.008906663150878581, | |
| "grad_norm": Infinity, | |
| "learning_rate": 5.921875e-06, | |
| "loss": 0.605169677734375, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.009141049023270122, | |
| "grad_norm": Infinity, | |
| "learning_rate": 6.078125e-06, | |
| "loss": 0.613519287109375, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.009375434895661665, | |
| "grad_norm": Infinity, | |
| "learning_rate": 6.234375e-06, | |
| "loss": 0.6017379760742188, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.009609820768053206, | |
| "grad_norm": Infinity, | |
| "learning_rate": 6.390625e-06, | |
| "loss": 0.6115753173828125, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.009844206640444747, | |
| "grad_norm": Infinity, | |
| "learning_rate": 6.546875e-06, | |
| "loss": 0.6092376708984375, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.010078592512836288, | |
| "grad_norm": Infinity, | |
| "learning_rate": 6.703125e-06, | |
| "loss": 0.6099075317382813, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.010312978385227831, | |
| "grad_norm": Infinity, | |
| "learning_rate": 6.859375000000001e-06, | |
| "loss": 0.61324462890625, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.010547364257619372, | |
| "grad_norm": Infinity, | |
| "learning_rate": 7.015625e-06, | |
| "loss": 0.6022865295410156, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.010781750130010913, | |
| "grad_norm": Infinity, | |
| "learning_rate": 7.171875000000001e-06, | |
| "loss": 0.6093353271484375, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.011016136002402456, | |
| "grad_norm": Infinity, | |
| "learning_rate": 7.328125e-06, | |
| "loss": 0.62122802734375, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 0.011250521874793997, | |
| "grad_norm": Infinity, | |
| "learning_rate": 7.484375000000001e-06, | |
| "loss": 0.6011276245117188, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.011484907747185538, | |
| "grad_norm": Infinity, | |
| "learning_rate": 7.640625000000001e-06, | |
| "loss": 0.6096969604492187, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 0.01171929361957708, | |
| "grad_norm": Infinity, | |
| "learning_rate": 7.796875e-06, | |
| "loss": 0.6085403442382813, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.011953679491968622, | |
| "grad_norm": Infinity, | |
| "learning_rate": 7.953125e-06, | |
| "loss": 0.6013351440429687, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 0.012188065364360163, | |
| "grad_norm": Infinity, | |
| "learning_rate": 8.109375e-06, | |
| "loss": 0.6108566284179687, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 0.012422451236751704, | |
| "grad_norm": Infinity, | |
| "learning_rate": 8.265625000000001e-06, | |
| "loss": 0.6119140625, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 0.012656837109143247, | |
| "grad_norm": Infinity, | |
| "learning_rate": 8.421875e-06, | |
| "loss": 0.6089179992675782, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 0.012891222981534788, | |
| "grad_norm": Infinity, | |
| "learning_rate": 8.578125e-06, | |
| "loss": 0.6096832275390625, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.01312560885392633, | |
| "grad_norm": Infinity, | |
| "learning_rate": 8.734375e-06, | |
| "loss": 0.6111366271972656, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 0.01335999472631787, | |
| "grad_norm": Infinity, | |
| "learning_rate": 8.890625000000001e-06, | |
| "loss": 0.6114044189453125, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 0.013594380598709413, | |
| "grad_norm": Infinity, | |
| "learning_rate": 9.046875e-06, | |
| "loss": 0.6101348876953125, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 0.013828766471100954, | |
| "grad_norm": Infinity, | |
| "learning_rate": 9.203125e-06, | |
| "loss": 0.6197845458984375, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 0.014063152343492496, | |
| "grad_norm": Infinity, | |
| "learning_rate": 9.359375e-06, | |
| "loss": 0.615380859375, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.014297538215884038, | |
| "grad_norm": Infinity, | |
| "learning_rate": 9.515625000000001e-06, | |
| "loss": 0.606341552734375, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 0.01453192408827558, | |
| "grad_norm": Infinity, | |
| "learning_rate": 9.671875000000001e-06, | |
| "loss": 0.6048248291015625, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 0.01476630996066712, | |
| "grad_norm": Infinity, | |
| "learning_rate": 9.828125e-06, | |
| "loss": 0.6092742919921875, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 0.015000695833058662, | |
| "grad_norm": Infinity, | |
| "learning_rate": 9.984375e-06, | |
| "loss": 0.6080833435058594, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 0.015235081705450204, | |
| "grad_norm": Infinity, | |
| "learning_rate": 1.0140625000000003e-05, | |
| "loss": 0.6076614379882812, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.015469467577841746, | |
| "grad_norm": Infinity, | |
| "learning_rate": 1.0296875000000001e-05, | |
| "loss": 0.6062957763671875, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 0.01570385345023329, | |
| "grad_norm": Infinity, | |
| "learning_rate": 1.0453125000000002e-05, | |
| "loss": 0.6010467529296875, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 0.01593823932262483, | |
| "grad_norm": Infinity, | |
| "learning_rate": 1.0609375000000002e-05, | |
| "loss": 0.6066925048828125, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 0.01617262519501637, | |
| "grad_norm": Infinity, | |
| "learning_rate": 1.0765625000000002e-05, | |
| "loss": 0.6043624877929688, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 0.01640701106740791, | |
| "grad_norm": Infinity, | |
| "learning_rate": 1.0921875000000001e-05, | |
| "loss": 0.6023162841796875, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.016641396939799453, | |
| "grad_norm": Infinity, | |
| "learning_rate": 1.1078125000000002e-05, | |
| "loss": 0.6094833374023437, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 0.016875782812190994, | |
| "grad_norm": Infinity, | |
| "learning_rate": 1.1234375000000002e-05, | |
| "loss": 0.6054359436035156, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 0.01711016868458254, | |
| "grad_norm": Infinity, | |
| "learning_rate": 1.1390625000000002e-05, | |
| "loss": 0.6059349060058594, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 0.01734455455697408, | |
| "grad_norm": Infinity, | |
| "learning_rate": 1.1546875000000001e-05, | |
| "loss": 0.60126953125, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 0.01757894042936562, | |
| "grad_norm": Infinity, | |
| "learning_rate": 1.1703125000000002e-05, | |
| "loss": 0.6094718933105469, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.017813326301757162, | |
| "grad_norm": Infinity, | |
| "learning_rate": 1.1859375000000002e-05, | |
| "loss": 0.6063560485839844, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 0.018047712174148703, | |
| "grad_norm": Infinity, | |
| "learning_rate": 1.2015625000000002e-05, | |
| "loss": 0.6024421691894531, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 0.018282098046540244, | |
| "grad_norm": Infinity, | |
| "learning_rate": 1.2171875000000001e-05, | |
| "loss": 0.6170989990234375, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 0.018516483918931785, | |
| "grad_norm": Infinity, | |
| "learning_rate": 1.2328125000000002e-05, | |
| "loss": 0.5938522338867187, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 0.01875086979132333, | |
| "grad_norm": Infinity, | |
| "learning_rate": 1.2484375000000002e-05, | |
| "loss": 0.6142776489257813, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.01898525566371487, | |
| "grad_norm": Infinity, | |
| "learning_rate": 1.2640625000000002e-05, | |
| "loss": 0.6042465209960938, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 0.019219641536106412, | |
| "grad_norm": Infinity, | |
| "learning_rate": 1.2796875000000003e-05, | |
| "loss": 0.6070510864257812, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 0.019454027408497953, | |
| "grad_norm": Infinity, | |
| "learning_rate": 1.2953125000000001e-05, | |
| "loss": 0.6068756103515625, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 0.019688413280889494, | |
| "grad_norm": Infinity, | |
| "learning_rate": 1.3109375000000002e-05, | |
| "loss": 0.5897056579589843, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 0.019922799153281035, | |
| "grad_norm": Infinity, | |
| "learning_rate": 1.3265625000000002e-05, | |
| "loss": 0.6050689697265625, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 0.020157185025672576, | |
| "grad_norm": Infinity, | |
| "learning_rate": 1.3421875000000003e-05, | |
| "loss": 0.590875244140625, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 0.02039157089806412, | |
| "grad_norm": Infinity, | |
| "learning_rate": 1.3578125000000001e-05, | |
| "loss": 0.6160301208496094, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 0.020625956770455662, | |
| "grad_norm": Infinity, | |
| "learning_rate": 1.3734375000000002e-05, | |
| "loss": 0.6036376953125, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 0.020860342642847203, | |
| "grad_norm": Infinity, | |
| "learning_rate": 1.3890625000000002e-05, | |
| "loss": 0.610693359375, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 0.021094728515238744, | |
| "grad_norm": Infinity, | |
| "learning_rate": 1.4046875000000003e-05, | |
| "loss": 0.6084335327148438, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.021329114387630285, | |
| "grad_norm": Infinity, | |
| "learning_rate": 1.4203125000000001e-05, | |
| "loss": 0.6077606201171875, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 0.021563500260021826, | |
| "grad_norm": Infinity, | |
| "learning_rate": 1.4359375000000002e-05, | |
| "loss": 0.6037399291992187, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 0.021797886132413367, | |
| "grad_norm": Infinity, | |
| "learning_rate": 1.4515625000000002e-05, | |
| "loss": 0.6144996643066406, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 0.022032272004804912, | |
| "grad_norm": Infinity, | |
| "learning_rate": 1.4671875000000003e-05, | |
| "loss": 0.5966384887695313, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 0.022266657877196453, | |
| "grad_norm": Infinity, | |
| "learning_rate": 1.4828125000000001e-05, | |
| "loss": 0.603125, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 0.022501043749587994, | |
| "grad_norm": Infinity, | |
| "learning_rate": 1.4984375000000002e-05, | |
| "loss": 0.612744140625, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 0.022735429621979535, | |
| "grad_norm": Infinity, | |
| "learning_rate": 1.5140625000000002e-05, | |
| "loss": 0.6046875, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 0.022969815494371076, | |
| "grad_norm": Infinity, | |
| "learning_rate": 1.5296875e-05, | |
| "loss": 0.6094146728515625, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 0.023204201366762617, | |
| "grad_norm": Infinity, | |
| "learning_rate": 1.5453125e-05, | |
| "loss": 0.610845947265625, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 0.02343858723915416, | |
| "grad_norm": Infinity, | |
| "learning_rate": 1.5609375e-05, | |
| "loss": 0.5980422973632813, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.023672973111545703, | |
| "grad_norm": Infinity, | |
| "learning_rate": 1.5765625000000002e-05, | |
| "loss": 0.6019882202148438, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 0.023907358983937244, | |
| "grad_norm": Infinity, | |
| "learning_rate": 1.5921875000000002e-05, | |
| "loss": 0.6057106018066406, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 0.024141744856328785, | |
| "grad_norm": Infinity, | |
| "learning_rate": 1.6078125000000003e-05, | |
| "loss": 0.6211753845214844, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 0.024376130728720326, | |
| "grad_norm": Infinity, | |
| "learning_rate": 1.6234375000000003e-05, | |
| "loss": 0.6060012817382813, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 0.024610516601111868, | |
| "grad_norm": Infinity, | |
| "learning_rate": 1.6390625000000004e-05, | |
| "loss": 0.5908248901367188, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 0.02484490247350341, | |
| "grad_norm": Infinity, | |
| "learning_rate": 1.6546875e-05, | |
| "loss": 0.5960098266601562, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 0.02507928834589495, | |
| "grad_norm": Infinity, | |
| "learning_rate": 1.6703125e-05, | |
| "loss": 0.5927337646484375, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 0.025313674218286494, | |
| "grad_norm": Infinity, | |
| "learning_rate": 1.6859375e-05, | |
| "loss": 0.6080078125, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 0.025548060090678035, | |
| "grad_norm": Infinity, | |
| "learning_rate": 1.7015625000000002e-05, | |
| "loss": 0.6029281616210938, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 0.025782445963069577, | |
| "grad_norm": Infinity, | |
| "learning_rate": 1.7171875000000002e-05, | |
| "loss": 0.6014022827148438, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.026016831835461118, | |
| "grad_norm": Infinity, | |
| "learning_rate": 1.7328125000000003e-05, | |
| "loss": 0.6068984985351562, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 0.02625121770785266, | |
| "grad_norm": Infinity, | |
| "learning_rate": 1.7484375000000003e-05, | |
| "loss": 0.611175537109375, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 0.0264856035802442, | |
| "grad_norm": Infinity, | |
| "learning_rate": 1.7640625000000004e-05, | |
| "loss": 0.6017318725585937, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 0.02671998945263574, | |
| "grad_norm": Infinity, | |
| "learning_rate": 1.7796875000000004e-05, | |
| "loss": 0.6082473754882812, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 0.026954375325027286, | |
| "grad_norm": Infinity, | |
| "learning_rate": 1.7953125e-05, | |
| "loss": 0.6051132202148437, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 0.027188761197418827, | |
| "grad_norm": Infinity, | |
| "learning_rate": 1.8109375e-05, | |
| "loss": 0.6071746826171875, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 0.027423147069810368, | |
| "grad_norm": Infinity, | |
| "learning_rate": 1.8265625000000002e-05, | |
| "loss": 0.6165802001953125, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 0.02765753294220191, | |
| "grad_norm": Infinity, | |
| "learning_rate": 1.8421875000000002e-05, | |
| "loss": 0.5984237670898438, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 0.02789191881459345, | |
| "grad_norm": Infinity, | |
| "learning_rate": 1.8578125000000003e-05, | |
| "loss": 0.6050758361816406, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 0.02812630468698499, | |
| "grad_norm": Infinity, | |
| "learning_rate": 1.8734375000000003e-05, | |
| "loss": 0.598980712890625, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.028360690559376532, | |
| "grad_norm": Infinity, | |
| "learning_rate": 1.8890625000000003e-05, | |
| "loss": 0.5932998657226562, | |
| "step": 1210 | |
| }, | |
| { | |
| "epoch": 0.028595076431768077, | |
| "grad_norm": Infinity, | |
| "learning_rate": 1.9046875000000004e-05, | |
| "loss": 0.6028633117675781, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 0.028829462304159618, | |
| "grad_norm": Infinity, | |
| "learning_rate": 1.9203125e-05, | |
| "loss": 0.6024459838867188, | |
| "step": 1230 | |
| }, | |
| { | |
| "epoch": 0.02906384817655116, | |
| "grad_norm": Infinity, | |
| "learning_rate": 1.9359375e-05, | |
| "loss": 0.6077346801757812, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 0.0292982340489427, | |
| "grad_norm": Infinity, | |
| "learning_rate": 1.9515625000000002e-05, | |
| "loss": 0.6018325805664062, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 0.02953261992133424, | |
| "grad_norm": Infinity, | |
| "learning_rate": 1.9671875000000002e-05, | |
| "loss": 0.6083480834960937, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 0.029767005793725782, | |
| "grad_norm": Infinity, | |
| "learning_rate": 1.9828125000000003e-05, | |
| "loss": 0.6122581481933593, | |
| "step": 1270 | |
| }, | |
| { | |
| "epoch": 0.030001391666117323, | |
| "grad_norm": Infinity, | |
| "learning_rate": 1.9984375000000003e-05, | |
| "loss": 0.6014678955078125, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 0.030235777538508868, | |
| "grad_norm": Infinity, | |
| "learning_rate": 1.9999997666172074e-05, | |
| "loss": 0.6058135986328125, | |
| "step": 1290 | |
| }, | |
| { | |
| "epoch": 0.03047016341090041, | |
| "grad_norm": Infinity, | |
| "learning_rate": 1.9999989598620137e-05, | |
| "loss": 0.6135894775390625, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 0.03070454928329195, | |
| "grad_norm": Infinity, | |
| "learning_rate": 1.9999975768536158e-05, | |
| "loss": 0.6187896728515625, | |
| "step": 1310 | |
| }, | |
| { | |
| "epoch": 0.03093893515568349, | |
| "grad_norm": Infinity, | |
| "learning_rate": 1.9999956175928097e-05, | |
| "loss": 0.60782470703125, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 0.031173321028075032, | |
| "grad_norm": Infinity, | |
| "learning_rate": 1.9999930820807245e-05, | |
| "loss": 0.6168212890625, | |
| "step": 1330 | |
| }, | |
| { | |
| "epoch": 0.03140770690046658, | |
| "grad_norm": Infinity, | |
| "learning_rate": 1.999989970318822e-05, | |
| "loss": 0.5995613098144531, | |
| "step": 1340 | |
| }, | |
| { | |
| "epoch": 0.031642092772858114, | |
| "grad_norm": Infinity, | |
| "learning_rate": 1.9999862823088946e-05, | |
| "loss": 0.6088516235351562, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 0.03187647864524966, | |
| "grad_norm": Infinity, | |
| "learning_rate": 1.999982018053068e-05, | |
| "loss": 0.6085662841796875, | |
| "step": 1360 | |
| }, | |
| { | |
| "epoch": 0.0321108645176412, | |
| "grad_norm": Infinity, | |
| "learning_rate": 1.999977177553799e-05, | |
| "loss": 0.6037391662597656, | |
| "step": 1370 | |
| }, | |
| { | |
| "epoch": 0.03234525039003274, | |
| "grad_norm": Infinity, | |
| "learning_rate": 1.9999717608138778e-05, | |
| "loss": 0.6000991821289062, | |
| "step": 1380 | |
| }, | |
| { | |
| "epoch": 0.032579636262424286, | |
| "grad_norm": Infinity, | |
| "learning_rate": 1.9999657678364252e-05, | |
| "loss": 0.5998687744140625, | |
| "step": 1390 | |
| }, | |
| { | |
| "epoch": 0.03281402213481582, | |
| "grad_norm": Infinity, | |
| "learning_rate": 1.9999591986248947e-05, | |
| "loss": 0.5970962524414063, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.03304840800720737, | |
| "grad_norm": Infinity, | |
| "learning_rate": 1.999952053183072e-05, | |
| "loss": 0.6116119384765625, | |
| "step": 1410 | |
| }, | |
| { | |
| "epoch": 0.033282793879598906, | |
| "grad_norm": Infinity, | |
| "learning_rate": 1.9999443315150742e-05, | |
| "loss": 0.602606201171875, | |
| "step": 1420 | |
| }, | |
| { | |
| "epoch": 0.03351717975199045, | |
| "grad_norm": Infinity, | |
| "learning_rate": 1.999936033625352e-05, | |
| "loss": 0.6079139709472656, | |
| "step": 1430 | |
| }, | |
| { | |
| "epoch": 0.03375156562438199, | |
| "grad_norm": Infinity, | |
| "learning_rate": 1.999927159518686e-05, | |
| "loss": 0.6049301147460937, | |
| "step": 1440 | |
| }, | |
| { | |
| "epoch": 0.03398595149677353, | |
| "grad_norm": Infinity, | |
| "learning_rate": 1.9999177092001907e-05, | |
| "loss": 0.6092140197753906, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 0.03422033736916508, | |
| "grad_norm": Infinity, | |
| "learning_rate": 1.9999076826753116e-05, | |
| "loss": 0.5999214172363281, | |
| "step": 1460 | |
| }, | |
| { | |
| "epoch": 0.034454723241556615, | |
| "grad_norm": Infinity, | |
| "learning_rate": 1.9998970799498262e-05, | |
| "loss": 0.6099578857421875, | |
| "step": 1470 | |
| }, | |
| { | |
| "epoch": 0.03468910911394816, | |
| "grad_norm": Infinity, | |
| "learning_rate": 1.9998859010298447e-05, | |
| "loss": 0.6190902709960937, | |
| "step": 1480 | |
| }, | |
| { | |
| "epoch": 0.0349234949863397, | |
| "grad_norm": Infinity, | |
| "learning_rate": 1.9998741459218093e-05, | |
| "loss": 0.6074859619140625, | |
| "step": 1490 | |
| }, | |
| { | |
| "epoch": 0.03515788085873124, | |
| "grad_norm": Infinity, | |
| "learning_rate": 1.999861814632493e-05, | |
| "loss": 0.6160079956054687, | |
| "step": 1500 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 42665, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 6.577579857901781e+18, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |