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-thinking-fp with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use argo11/0399-tv-full-thinking-fp with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="argo11/0399-tv-full-thinking-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-thinking-fp") model = AutoModelForCausalLM.from_pretrained("argo11/0399-tv-full-thinking-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-thinking-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-thinking-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-thinking-fp", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/argo11/0399-tv-full-thinking-fp
- SGLang
How to use argo11/0399-tv-full-thinking-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-thinking-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-thinking-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-thinking-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-thinking-fp", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use argo11/0399-tv-full-thinking-fp with Docker Model Runner:
docker model run hf.co/argo11/0399-tv-full-thinking-fp
| { | |
| "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": 7.478665351867676, | |
| "learning_rate": 1.40625e-07, | |
| "loss": 0.6732528686523438, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0004687717447830832, | |
| "grad_norm": 7.584623336791992, | |
| "learning_rate": 2.96875e-07, | |
| "loss": 0.66597900390625, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0007031576171746248, | |
| "grad_norm": 6.306713581085205, | |
| "learning_rate": 4.53125e-07, | |
| "loss": 0.6197677612304687, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0009375434895661664, | |
| "grad_norm": 4.607383728027344, | |
| "learning_rate": 6.09375e-07, | |
| "loss": 0.5319419860839844, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.001171929361957708, | |
| "grad_norm": 2.3062853813171387, | |
| "learning_rate": 7.656250000000001e-07, | |
| "loss": 0.42061538696289064, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.0014063152343492496, | |
| "grad_norm": 1.4863656759262085, | |
| "learning_rate": 9.218750000000002e-07, | |
| "loss": 0.3130531311035156, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.0016407011067407912, | |
| "grad_norm": 0.8237831592559814, | |
| "learning_rate": 1.0781250000000002e-06, | |
| "loss": 0.23311138153076172, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.0018750869791323327, | |
| "grad_norm": 0.6643654704093933, | |
| "learning_rate": 1.2343750000000001e-06, | |
| "loss": 0.2020857810974121, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.0021094728515238742, | |
| "grad_norm": 0.5149619579315186, | |
| "learning_rate": 1.3906250000000001e-06, | |
| "loss": 0.18220624923706055, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.002343858723915416, | |
| "grad_norm": 0.5113442540168762, | |
| "learning_rate": 1.5468750000000001e-06, | |
| "loss": 0.16905088424682618, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.0025782445963069577, | |
| "grad_norm": 0.5090538859367371, | |
| "learning_rate": 1.703125e-06, | |
| "loss": 0.16316838264465333, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.0028126304686984993, | |
| "grad_norm": 0.4110700190067291, | |
| "learning_rate": 1.8593750000000003e-06, | |
| "loss": 0.1580258846282959, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.003047016341090041, | |
| "grad_norm": 0.5005377531051636, | |
| "learning_rate": 2.0156250000000003e-06, | |
| "loss": 0.14841842651367188, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.0032814022134815823, | |
| "grad_norm": 0.4914725124835968, | |
| "learning_rate": 2.1718750000000003e-06, | |
| "loss": 0.14541361331939698, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.003515788085873124, | |
| "grad_norm": 0.5155150294303894, | |
| "learning_rate": 2.3281250000000003e-06, | |
| "loss": 0.14492216110229492, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.0037501739582646654, | |
| "grad_norm": 0.4690794050693512, | |
| "learning_rate": 2.4843750000000002e-06, | |
| "loss": 0.14195268154144286, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.003984559830656207, | |
| "grad_norm": 0.50107342004776, | |
| "learning_rate": 2.640625e-06, | |
| "loss": 0.1428708553314209, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.0042189457030477485, | |
| "grad_norm": 0.48859548568725586, | |
| "learning_rate": 2.796875e-06, | |
| "loss": 0.14226298332214354, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.0044533315754392904, | |
| "grad_norm": 0.5123774409294128, | |
| "learning_rate": 2.953125e-06, | |
| "loss": 0.1370567798614502, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.004687717447830832, | |
| "grad_norm": 0.4833315312862396, | |
| "learning_rate": 3.109375e-06, | |
| "loss": 0.1390127420425415, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.0049221033202223735, | |
| "grad_norm": 0.43915465474128723, | |
| "learning_rate": 3.265625e-06, | |
| "loss": 0.13475892543792725, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.0051564891926139155, | |
| "grad_norm": 0.46104806661605835, | |
| "learning_rate": 3.421875e-06, | |
| "loss": 0.13139626979827881, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.005390875065005457, | |
| "grad_norm": 0.5122255086898804, | |
| "learning_rate": 3.578125e-06, | |
| "loss": 0.13110661506652832, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.0056252609373969985, | |
| "grad_norm": 0.48517927527427673, | |
| "learning_rate": 3.734375e-06, | |
| "loss": 0.12811717987060547, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.00585964680978854, | |
| "grad_norm": 0.4835013449192047, | |
| "learning_rate": 3.890625e-06, | |
| "loss": 0.13097090721130372, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.006094032682180082, | |
| "grad_norm": 0.4820455312728882, | |
| "learning_rate": 4.046875e-06, | |
| "loss": 0.12818758487701415, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.006328418554571624, | |
| "grad_norm": 0.44813403487205505, | |
| "learning_rate": 4.2031250000000005e-06, | |
| "loss": 0.12801458835601806, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.006562804426963165, | |
| "grad_norm": 0.5279086232185364, | |
| "learning_rate": 4.359375e-06, | |
| "loss": 0.12751049995422364, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.006797190299354707, | |
| "grad_norm": 0.42281895875930786, | |
| "learning_rate": 4.5156250000000005e-06, | |
| "loss": 0.13442916870117189, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.007031576171746248, | |
| "grad_norm": 0.4167884588241577, | |
| "learning_rate": 4.671875e-06, | |
| "loss": 0.12415478229522706, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.00726596204413779, | |
| "grad_norm": 0.4328134059906006, | |
| "learning_rate": 4.8281250000000005e-06, | |
| "loss": 0.12891750335693358, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.007500347916529331, | |
| "grad_norm": 0.45806413888931274, | |
| "learning_rate": 4.984375e-06, | |
| "loss": 0.12102985382080078, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.007734733788920873, | |
| "grad_norm": 0.5078896880149841, | |
| "learning_rate": 5.1406250000000004e-06, | |
| "loss": 0.12243216037750244, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.007969119661312415, | |
| "grad_norm": 0.527930498123169, | |
| "learning_rate": 5.296875e-06, | |
| "loss": 0.12513620853424073, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.008203505533703956, | |
| "grad_norm": 0.431318461894989, | |
| "learning_rate": 5.453125e-06, | |
| "loss": 0.12151198387145996, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.008437891406095497, | |
| "grad_norm": 0.4996262788772583, | |
| "learning_rate": 5.609375e-06, | |
| "loss": 0.11847388744354248, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.00867227727848704, | |
| "grad_norm": 0.4818030893802643, | |
| "learning_rate": 5.765625e-06, | |
| "loss": 0.1227838158607483, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.008906663150878581, | |
| "grad_norm": 0.4577305018901825, | |
| "learning_rate": 5.921875e-06, | |
| "loss": 0.1199771523475647, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.009141049023270122, | |
| "grad_norm": 0.48360294103622437, | |
| "learning_rate": 6.078125e-06, | |
| "loss": 0.11903550624847412, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.009375434895661665, | |
| "grad_norm": 0.47577178478240967, | |
| "learning_rate": 6.234375e-06, | |
| "loss": 0.12074012756347656, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.009609820768053206, | |
| "grad_norm": 0.4833427369594574, | |
| "learning_rate": 6.390625e-06, | |
| "loss": 0.12326394319534302, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.009844206640444747, | |
| "grad_norm": 0.43909400701522827, | |
| "learning_rate": 6.546875e-06, | |
| "loss": 0.11921967267990112, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.010078592512836288, | |
| "grad_norm": 0.5028750896453857, | |
| "learning_rate": 6.703125e-06, | |
| "loss": 0.12188574075698852, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.010312978385227831, | |
| "grad_norm": 0.47389668226242065, | |
| "learning_rate": 6.859375000000001e-06, | |
| "loss": 0.1192385196685791, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.010547364257619372, | |
| "grad_norm": 0.5239953398704529, | |
| "learning_rate": 7.015625e-06, | |
| "loss": 0.11499193906784058, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.010781750130010913, | |
| "grad_norm": 0.5061202645301819, | |
| "learning_rate": 7.171875000000001e-06, | |
| "loss": 0.11584588289260864, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.011016136002402456, | |
| "grad_norm": 0.4635751247406006, | |
| "learning_rate": 7.328125e-06, | |
| "loss": 0.11434779167175294, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 0.011250521874793997, | |
| "grad_norm": 0.4353443682193756, | |
| "learning_rate": 7.484375000000001e-06, | |
| "loss": 0.11755821704864503, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.011484907747185538, | |
| "grad_norm": 0.41028693318367004, | |
| "learning_rate": 7.640625000000001e-06, | |
| "loss": 0.11704204082489014, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 0.01171929361957708, | |
| "grad_norm": 0.4426499009132385, | |
| "learning_rate": 7.796875e-06, | |
| "loss": 0.11789888143539429, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.011953679491968622, | |
| "grad_norm": 0.45650583505630493, | |
| "learning_rate": 7.953125e-06, | |
| "loss": 0.11612817049026489, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 0.012188065364360163, | |
| "grad_norm": 0.48528221249580383, | |
| "learning_rate": 8.109375e-06, | |
| "loss": 0.11835837364196777, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 0.012422451236751704, | |
| "grad_norm": 0.49201133847236633, | |
| "learning_rate": 8.265625000000001e-06, | |
| "loss": 0.11796109676361084, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 0.012656837109143247, | |
| "grad_norm": 0.41120538115501404, | |
| "learning_rate": 8.421875e-06, | |
| "loss": 0.11465147733688355, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 0.012891222981534788, | |
| "grad_norm": 0.42535409331321716, | |
| "learning_rate": 8.578125e-06, | |
| "loss": 0.11844432353973389, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.01312560885392633, | |
| "grad_norm": 0.44362396001815796, | |
| "learning_rate": 8.734375e-06, | |
| "loss": 0.11715601682662964, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 0.01335999472631787, | |
| "grad_norm": 0.441021203994751, | |
| "learning_rate": 8.890625000000001e-06, | |
| "loss": 0.11989809274673462, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 0.013594380598709413, | |
| "grad_norm": 0.4338180720806122, | |
| "learning_rate": 9.046875e-06, | |
| "loss": 0.11536179780960083, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 0.013828766471100954, | |
| "grad_norm": 0.43819499015808105, | |
| "learning_rate": 9.203125e-06, | |
| "loss": 0.11345911026000977, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 0.014063152343492496, | |
| "grad_norm": 0.4360722601413727, | |
| "learning_rate": 9.359375e-06, | |
| "loss": 0.11602315902709961, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.014297538215884038, | |
| "grad_norm": 0.4287785589694977, | |
| "learning_rate": 9.515625000000001e-06, | |
| "loss": 0.11890817880630493, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 0.01453192408827558, | |
| "grad_norm": 0.4322708547115326, | |
| "learning_rate": 9.671875000000001e-06, | |
| "loss": 0.11710528135299683, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 0.01476630996066712, | |
| "grad_norm": 0.4133163392543793, | |
| "learning_rate": 9.828125e-06, | |
| "loss": 0.11247456073760986, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 0.015000695833058662, | |
| "grad_norm": 0.4161861538887024, | |
| "learning_rate": 9.984375e-06, | |
| "loss": 0.1176948070526123, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 0.015235081705450204, | |
| "grad_norm": 0.4499410092830658, | |
| "learning_rate": 1.0140625000000003e-05, | |
| "loss": 0.11162110567092895, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.015469467577841746, | |
| "grad_norm": 0.4393712878227234, | |
| "learning_rate": 1.0296875000000001e-05, | |
| "loss": 0.11646484136581421, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 0.01570385345023329, | |
| "grad_norm": 0.43581581115722656, | |
| "learning_rate": 1.0453125000000002e-05, | |
| "loss": 0.11804448366165161, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 0.01593823932262483, | |
| "grad_norm": 0.5233722925186157, | |
| "learning_rate": 1.0609375000000002e-05, | |
| "loss": 0.11381900310516357, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 0.01617262519501637, | |
| "grad_norm": 0.4110233187675476, | |
| "learning_rate": 1.0765625000000002e-05, | |
| "loss": 0.11446200609207154, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 0.01640701106740791, | |
| "grad_norm": 0.399118036031723, | |
| "learning_rate": 1.0921875000000001e-05, | |
| "loss": 0.11271647214889527, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.016641396939799453, | |
| "grad_norm": 0.46171241998672485, | |
| "learning_rate": 1.1078125000000002e-05, | |
| "loss": 0.11184619665145874, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 0.016875782812190994, | |
| "grad_norm": 0.45813125371932983, | |
| "learning_rate": 1.1234375000000002e-05, | |
| "loss": 0.11524376869201661, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 0.01711016868458254, | |
| "grad_norm": 0.3914071023464203, | |
| "learning_rate": 1.1390625000000002e-05, | |
| "loss": 0.11292357444763183, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 0.01734455455697408, | |
| "grad_norm": 0.3806169033050537, | |
| "learning_rate": 1.1546875000000001e-05, | |
| "loss": 0.11865770816802979, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 0.01757894042936562, | |
| "grad_norm": 0.6183323264122009, | |
| "learning_rate": 1.1703125000000002e-05, | |
| "loss": 0.1167568564414978, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.017813326301757162, | |
| "grad_norm": 0.39449653029441833, | |
| "learning_rate": 1.1859375000000002e-05, | |
| "loss": 0.11325149536132813, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 0.018047712174148703, | |
| "grad_norm": 0.37599578499794006, | |
| "learning_rate": 1.2015625000000002e-05, | |
| "loss": 0.11163055896759033, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 0.018282098046540244, | |
| "grad_norm": 0.38267573714256287, | |
| "learning_rate": 1.2171875000000001e-05, | |
| "loss": 0.11489014625549317, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 0.018516483918931785, | |
| "grad_norm": 0.37311288714408875, | |
| "learning_rate": 1.2328125000000002e-05, | |
| "loss": 0.11194641590118408, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 0.01875086979132333, | |
| "grad_norm": 0.411432683467865, | |
| "learning_rate": 1.2484375000000002e-05, | |
| "loss": 0.11317495107650757, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.01898525566371487, | |
| "grad_norm": 0.43839067220687866, | |
| "learning_rate": 1.2640625000000002e-05, | |
| "loss": 0.10759581327438354, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 0.019219641536106412, | |
| "grad_norm": 0.3859034478664398, | |
| "learning_rate": 1.2796875000000003e-05, | |
| "loss": 0.11314148902893066, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 0.019454027408497953, | |
| "grad_norm": 0.4093567728996277, | |
| "learning_rate": 1.2953125000000001e-05, | |
| "loss": 0.11214956045150756, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 0.019688413280889494, | |
| "grad_norm": 0.4202522337436676, | |
| "learning_rate": 1.3109375000000002e-05, | |
| "loss": 0.10863385200500489, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 0.019922799153281035, | |
| "grad_norm": 0.37031644582748413, | |
| "learning_rate": 1.3265625000000002e-05, | |
| "loss": 0.11562912464141846, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 0.020157185025672576, | |
| "grad_norm": 0.372043251991272, | |
| "learning_rate": 1.3421875000000003e-05, | |
| "loss": 0.11000908613204956, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 0.02039157089806412, | |
| "grad_norm": 0.39329200983047485, | |
| "learning_rate": 1.3578125000000001e-05, | |
| "loss": 0.11322653293609619, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 0.020625956770455662, | |
| "grad_norm": 0.3731657564640045, | |
| "learning_rate": 1.3734375000000002e-05, | |
| "loss": 0.11117322444915771, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 0.020860342642847203, | |
| "grad_norm": 0.3705548644065857, | |
| "learning_rate": 1.3890625000000002e-05, | |
| "loss": 0.10953671932220459, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 0.021094728515238744, | |
| "grad_norm": 0.38085901737213135, | |
| "learning_rate": 1.4046875000000003e-05, | |
| "loss": 0.11695330142974854, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.021329114387630285, | |
| "grad_norm": 0.4012692868709564, | |
| "learning_rate": 1.4203125000000001e-05, | |
| "loss": 0.11438255310058594, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 0.021563500260021826, | |
| "grad_norm": 0.3757342994213104, | |
| "learning_rate": 1.4359375000000002e-05, | |
| "loss": 0.11287130117416382, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 0.021797886132413367, | |
| "grad_norm": 0.38042888045310974, | |
| "learning_rate": 1.4515625000000002e-05, | |
| "loss": 0.11060645580291747, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 0.022032272004804912, | |
| "grad_norm": 0.3464396297931671, | |
| "learning_rate": 1.4671875000000003e-05, | |
| "loss": 0.11261942386627197, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 0.022266657877196453, | |
| "grad_norm": 0.3607310652732849, | |
| "learning_rate": 1.4828125000000001e-05, | |
| "loss": 0.11483677625656127, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 0.022501043749587994, | |
| "grad_norm": 0.37492862343788147, | |
| "learning_rate": 1.4984375000000002e-05, | |
| "loss": 0.11412110328674316, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 0.022735429621979535, | |
| "grad_norm": 0.36724552512168884, | |
| "learning_rate": 1.5140625000000002e-05, | |
| "loss": 0.11400502920150757, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 0.022969815494371076, | |
| "grad_norm": 0.3513246774673462, | |
| "learning_rate": 1.5296875e-05, | |
| "loss": 0.11101123094558715, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 0.023204201366762617, | |
| "grad_norm": 0.39282527565956116, | |
| "learning_rate": 1.5453125e-05, | |
| "loss": 0.11446715593338012, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 0.02343858723915416, | |
| "grad_norm": 0.3693297505378723, | |
| "learning_rate": 1.5609375e-05, | |
| "loss": 0.11360613107681275, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.023672973111545703, | |
| "grad_norm": 0.3805910050868988, | |
| "learning_rate": 1.5765625000000002e-05, | |
| "loss": 0.1102859616279602, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 0.023907358983937244, | |
| "grad_norm": 0.3862535059452057, | |
| "learning_rate": 1.5921875000000002e-05, | |
| "loss": 0.11268872022628784, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 0.024141744856328785, | |
| "grad_norm": 0.404893696308136, | |
| "learning_rate": 1.6078125000000003e-05, | |
| "loss": 0.11359611749649048, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 0.024376130728720326, | |
| "grad_norm": 0.38326576352119446, | |
| "learning_rate": 1.6234375000000003e-05, | |
| "loss": 0.11227505207061768, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 0.024610516601111868, | |
| "grad_norm": 0.36912357807159424, | |
| "learning_rate": 1.6390625000000004e-05, | |
| "loss": 0.11599531173706054, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 0.02484490247350341, | |
| "grad_norm": 0.3696171045303345, | |
| "learning_rate": 1.6546875e-05, | |
| "loss": 0.11023976802825927, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 0.02507928834589495, | |
| "grad_norm": 0.3755769729614258, | |
| "learning_rate": 1.6703125e-05, | |
| "loss": 0.11145970821380616, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 0.025313674218286494, | |
| "grad_norm": 0.3687419593334198, | |
| "learning_rate": 1.6859375e-05, | |
| "loss": 0.11287758350372315, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 0.025548060090678035, | |
| "grad_norm": 0.33784812688827515, | |
| "learning_rate": 1.7015625000000002e-05, | |
| "loss": 0.10908894538879395, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 0.025782445963069577, | |
| "grad_norm": 0.3508151173591614, | |
| "learning_rate": 1.7171875000000002e-05, | |
| "loss": 0.11538139581680298, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.026016831835461118, | |
| "grad_norm": 0.36725053191185, | |
| "learning_rate": 1.7328125000000003e-05, | |
| "loss": 0.11482850313186646, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 0.02625121770785266, | |
| "grad_norm": 0.34291842579841614, | |
| "learning_rate": 1.7484375000000003e-05, | |
| "loss": 0.11298364400863647, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 0.0264856035802442, | |
| "grad_norm": 0.36184895038604736, | |
| "learning_rate": 1.7640625000000004e-05, | |
| "loss": 0.1066980242729187, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 0.02671998945263574, | |
| "grad_norm": 0.4020235240459442, | |
| "learning_rate": 1.7796875000000004e-05, | |
| "loss": 0.11315239667892456, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 0.026954375325027286, | |
| "grad_norm": 0.34352606534957886, | |
| "learning_rate": 1.7953125e-05, | |
| "loss": 0.10964906215667725, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 0.027188761197418827, | |
| "grad_norm": 0.4462008476257324, | |
| "learning_rate": 1.8109375e-05, | |
| "loss": 0.11428066492080688, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 0.027423147069810368, | |
| "grad_norm": 0.3392775058746338, | |
| "learning_rate": 1.8265625000000002e-05, | |
| "loss": 0.11005079746246338, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 0.02765753294220191, | |
| "grad_norm": 0.3385438621044159, | |
| "learning_rate": 1.8421875000000002e-05, | |
| "loss": 0.11102509498596191, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 0.02789191881459345, | |
| "grad_norm": 0.3650127649307251, | |
| "learning_rate": 1.8578125000000003e-05, | |
| "loss": 0.11523213386535644, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 0.02812630468698499, | |
| "grad_norm": 0.3460846245288849, | |
| "learning_rate": 1.8734375000000003e-05, | |
| "loss": 0.11034642457962036, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.028360690559376532, | |
| "grad_norm": 0.326349675655365, | |
| "learning_rate": 1.8890625000000003e-05, | |
| "loss": 0.10953868627548217, | |
| "step": 1210 | |
| }, | |
| { | |
| "epoch": 0.028595076431768077, | |
| "grad_norm": 0.34334462881088257, | |
| "learning_rate": 1.9046875000000004e-05, | |
| "loss": 0.11296612024307251, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 0.028829462304159618, | |
| "grad_norm": 0.33681803941726685, | |
| "learning_rate": 1.9203125e-05, | |
| "loss": 0.11056774854660034, | |
| "step": 1230 | |
| }, | |
| { | |
| "epoch": 0.02906384817655116, | |
| "grad_norm": 0.3528500199317932, | |
| "learning_rate": 1.9359375e-05, | |
| "loss": 0.10871942043304443, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 0.0292982340489427, | |
| "grad_norm": 0.3156096339225769, | |
| "learning_rate": 1.9515625000000002e-05, | |
| "loss": 0.1137766718864441, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 0.02953261992133424, | |
| "grad_norm": 0.3579378128051758, | |
| "learning_rate": 1.9671875000000002e-05, | |
| "loss": 0.11373578310012818, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 0.029767005793725782, | |
| "grad_norm": 0.315738707780838, | |
| "learning_rate": 1.9828125000000003e-05, | |
| "loss": 0.11297824382781982, | |
| "step": 1270 | |
| }, | |
| { | |
| "epoch": 0.030001391666117323, | |
| "grad_norm": 0.3177584111690521, | |
| "learning_rate": 1.9984375000000003e-05, | |
| "loss": 0.1135290265083313, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 0.030235777538508868, | |
| "grad_norm": 0.34855231642723083, | |
| "learning_rate": 1.9999997666172074e-05, | |
| "loss": 0.11188427209854127, | |
| "step": 1290 | |
| }, | |
| { | |
| "epoch": 0.03047016341090041, | |
| "grad_norm": 0.3580094575881958, | |
| "learning_rate": 1.9999989598620137e-05, | |
| "loss": 0.10642122030258179, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 0.03070454928329195, | |
| "grad_norm": 0.37562474608421326, | |
| "learning_rate": 1.9999975768536158e-05, | |
| "loss": 0.11398833990097046, | |
| "step": 1310 | |
| }, | |
| { | |
| "epoch": 0.03093893515568349, | |
| "grad_norm": 0.34030941128730774, | |
| "learning_rate": 1.9999956175928097e-05, | |
| "loss": 0.10998734235763549, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 0.031173321028075032, | |
| "grad_norm": 0.3101728856563568, | |
| "learning_rate": 1.9999930820807245e-05, | |
| "loss": 0.11209770441055297, | |
| "step": 1330 | |
| }, | |
| { | |
| "epoch": 0.03140770690046658, | |
| "grad_norm": 0.34433069825172424, | |
| "learning_rate": 1.999989970318822e-05, | |
| "loss": 0.1109668493270874, | |
| "step": 1340 | |
| }, | |
| { | |
| "epoch": 0.031642092772858114, | |
| "grad_norm": 0.32215601205825806, | |
| "learning_rate": 1.9999862823088946e-05, | |
| "loss": 0.10847405195236207, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 0.03187647864524966, | |
| "grad_norm": 0.32859981060028076, | |
| "learning_rate": 1.999982018053068e-05, | |
| "loss": 0.11370890140533448, | |
| "step": 1360 | |
| }, | |
| { | |
| "epoch": 0.0321108645176412, | |
| "grad_norm": 0.3100363314151764, | |
| "learning_rate": 1.999977177553799e-05, | |
| "loss": 0.1127819538116455, | |
| "step": 1370 | |
| }, | |
| { | |
| "epoch": 0.03234525039003274, | |
| "grad_norm": 0.29671692848205566, | |
| "learning_rate": 1.9999717608138778e-05, | |
| "loss": 0.10928714275360107, | |
| "step": 1380 | |
| }, | |
| { | |
| "epoch": 0.032579636262424286, | |
| "grad_norm": 0.3065207302570343, | |
| "learning_rate": 1.9999657678364252e-05, | |
| "loss": 0.10931737422943115, | |
| "step": 1390 | |
| }, | |
| { | |
| "epoch": 0.03281402213481582, | |
| "grad_norm": 0.32845526933670044, | |
| "learning_rate": 1.9999591986248947e-05, | |
| "loss": 0.1125643253326416, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.03304840800720737, | |
| "grad_norm": 0.31998366117477417, | |
| "learning_rate": 1.999952053183072e-05, | |
| "loss": 0.11007034778594971, | |
| "step": 1410 | |
| }, | |
| { | |
| "epoch": 0.033282793879598906, | |
| "grad_norm": 0.3302232623100281, | |
| "learning_rate": 1.9999443315150742e-05, | |
| "loss": 0.11075022220611572, | |
| "step": 1420 | |
| }, | |
| { | |
| "epoch": 0.03351717975199045, | |
| "grad_norm": 0.3401246964931488, | |
| "learning_rate": 1.999936033625352e-05, | |
| "loss": 0.10927612781524658, | |
| "step": 1430 | |
| }, | |
| { | |
| "epoch": 0.03375156562438199, | |
| "grad_norm": 0.31189054250717163, | |
| "learning_rate": 1.999927159518686e-05, | |
| "loss": 0.10789297819137574, | |
| "step": 1440 | |
| }, | |
| { | |
| "epoch": 0.03398595149677353, | |
| "grad_norm": 0.32660672068595886, | |
| "learning_rate": 1.9999177092001907e-05, | |
| "loss": 0.10693231821060181, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 0.03422033736916508, | |
| "grad_norm": 0.31303200125694275, | |
| "learning_rate": 1.9999076826753116e-05, | |
| "loss": 0.11288677453994751, | |
| "step": 1460 | |
| }, | |
| { | |
| "epoch": 0.034454723241556615, | |
| "grad_norm": 0.3008570075035095, | |
| "learning_rate": 1.9998970799498262e-05, | |
| "loss": 0.10686779022216797, | |
| "step": 1470 | |
| }, | |
| { | |
| "epoch": 0.03468910911394816, | |
| "grad_norm": 0.3439565598964691, | |
| "learning_rate": 1.9998859010298447e-05, | |
| "loss": 0.1086077332496643, | |
| "step": 1480 | |
| }, | |
| { | |
| "epoch": 0.0349234949863397, | |
| "grad_norm": 0.3342174291610718, | |
| "learning_rate": 1.9998741459218093e-05, | |
| "loss": 0.1085971713066101, | |
| "step": 1490 | |
| }, | |
| { | |
| "epoch": 0.03515788085873124, | |
| "grad_norm": 0.3462369740009308, | |
| "learning_rate": 1.999861814632493e-05, | |
| "loss": 0.11292096376419067, | |
| "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 | |
| } | |