Text Generation
Transformers
Safetensors
qwen2
llama-factory
full
Generated from Trainer
conversational
text-generation-inference
🇪🇺 Region: EU
Instructions to use eth-sri/kodcode-v1-qwq-secureplusplusplus with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use eth-sri/kodcode-v1-qwq-secureplusplusplus with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="eth-sri/kodcode-v1-qwq-secureplusplusplus") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("eth-sri/kodcode-v1-qwq-secureplusplusplus") model = AutoModelForCausalLM.from_pretrained("eth-sri/kodcode-v1-qwq-secureplusplusplus") 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 eth-sri/kodcode-v1-qwq-secureplusplusplus with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "eth-sri/kodcode-v1-qwq-secureplusplusplus" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "eth-sri/kodcode-v1-qwq-secureplusplusplus", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/eth-sri/kodcode-v1-qwq-secureplusplusplus
- SGLang
How to use eth-sri/kodcode-v1-qwq-secureplusplusplus 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 "eth-sri/kodcode-v1-qwq-secureplusplusplus" \ --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": "eth-sri/kodcode-v1-qwq-secureplusplusplus", "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 "eth-sri/kodcode-v1-qwq-secureplusplusplus" \ --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": "eth-sri/kodcode-v1-qwq-secureplusplusplus", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use eth-sri/kodcode-v1-qwq-secureplusplusplus with Docker Model Runner:
docker model run hf.co/eth-sri/kodcode-v1-qwq-secureplusplusplus
| { | |
| "best_global_step": null, | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 3.0, | |
| "eval_steps": 500, | |
| "global_step": 84, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.03614457831325301, | |
| "grad_norm": 3.553168296813965, | |
| "learning_rate": 0.0, | |
| "loss": 0.8157972693443298, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.07228915662650602, | |
| "grad_norm": 3.4760236740112305, | |
| "learning_rate": 1.111111111111111e-06, | |
| "loss": 0.8220954537391663, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.10843373493975904, | |
| "grad_norm": 3.3894028663635254, | |
| "learning_rate": 2.222222222222222e-06, | |
| "loss": 0.8105740547180176, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.14457831325301204, | |
| "grad_norm": 3.293134927749634, | |
| "learning_rate": 3.3333333333333333e-06, | |
| "loss": 0.7965067028999329, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.18072289156626506, | |
| "grad_norm": 2.8860864639282227, | |
| "learning_rate": 4.444444444444444e-06, | |
| "loss": 0.7848137617111206, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.21686746987951808, | |
| "grad_norm": 2.0125129222869873, | |
| "learning_rate": 5.555555555555557e-06, | |
| "loss": 0.7374380826950073, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.25301204819277107, | |
| "grad_norm": 1.5207632780075073, | |
| "learning_rate": 6.666666666666667e-06, | |
| "loss": 0.7128661274909973, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.2891566265060241, | |
| "grad_norm": 1.3406639099121094, | |
| "learning_rate": 7.77777777777778e-06, | |
| "loss": 0.7061306238174438, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.3253012048192771, | |
| "grad_norm": 1.3483136892318726, | |
| "learning_rate": 8.888888888888888e-06, | |
| "loss": 0.7266426086425781, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.3614457831325301, | |
| "grad_norm": 2.7021946907043457, | |
| "learning_rate": 1e-05, | |
| "loss": 0.7644096612930298, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.39759036144578314, | |
| "grad_norm": 2.3240082263946533, | |
| "learning_rate": 9.995614150494293e-06, | |
| "loss": 0.7518090009689331, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.43373493975903615, | |
| "grad_norm": 1.8651138544082642, | |
| "learning_rate": 9.982464296247523e-06, | |
| "loss": 0.7258176803588867, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.46987951807228917, | |
| "grad_norm": 1.595149278640747, | |
| "learning_rate": 9.960573506572391e-06, | |
| "loss": 0.7168642282485962, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.5060240963855421, | |
| "grad_norm": 1.355558156967163, | |
| "learning_rate": 9.929980185352525e-06, | |
| "loss": 0.7147663831710815, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.5421686746987951, | |
| "grad_norm": 1.1974090337753296, | |
| "learning_rate": 9.890738003669029e-06, | |
| "loss": 0.7102792263031006, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.5783132530120482, | |
| "grad_norm": 0.9845958352088928, | |
| "learning_rate": 9.842915805643156e-06, | |
| "loss": 0.6803984045982361, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.6144578313253012, | |
| "grad_norm": 1.0079755783081055, | |
| "learning_rate": 9.786597487660336e-06, | |
| "loss": 0.6794809699058533, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.6506024096385542, | |
| "grad_norm": 0.9282218813896179, | |
| "learning_rate": 9.721881851187406e-06, | |
| "loss": 0.6609358787536621, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.6867469879518072, | |
| "grad_norm": 0.847620964050293, | |
| "learning_rate": 9.648882429441258e-06, | |
| "loss": 0.6601911783218384, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.7228915662650602, | |
| "grad_norm": 0.7623603343963623, | |
| "learning_rate": 9.567727288213005e-06, | |
| "loss": 0.6362742781639099, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.7590361445783133, | |
| "grad_norm": 0.7723239660263062, | |
| "learning_rate": 9.478558801197065e-06, | |
| "loss": 0.6495505571365356, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.7951807228915663, | |
| "grad_norm": 0.9192399382591248, | |
| "learning_rate": 9.381533400219319e-06, | |
| "loss": 0.6754122972488403, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.8313253012048193, | |
| "grad_norm": 0.6796345114707947, | |
| "learning_rate": 9.276821300802535e-06, | |
| "loss": 0.6430672407150269, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.8674698795180723, | |
| "grad_norm": 0.6662194728851318, | |
| "learning_rate": 9.164606203550498e-06, | |
| "loss": 0.658618152141571, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.9036144578313253, | |
| "grad_norm": 0.6152909398078918, | |
| "learning_rate": 9.045084971874738e-06, | |
| "loss": 0.6351467370986938, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.9397590361445783, | |
| "grad_norm": 0.6219061613082886, | |
| "learning_rate": 8.9184672866292e-06, | |
| "loss": 0.6528507471084595, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.9759036144578314, | |
| "grad_norm": 0.5178506970405579, | |
| "learning_rate": 8.784975278258783e-06, | |
| "loss": 0.6266601085662842, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 0.6238970160484314, | |
| "learning_rate": 8.644843137107058e-06, | |
| "loss": 0.6392745971679688, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 1.036144578313253, | |
| "grad_norm": 0.5749419927597046, | |
| "learning_rate": 8.498316702566828e-06, | |
| "loss": 0.5894884467124939, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 1.072289156626506, | |
| "grad_norm": 0.54451584815979, | |
| "learning_rate": 8.345653031794292e-06, | |
| "loss": 0.5866576433181763, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.108433734939759, | |
| "grad_norm": 0.7175883650779724, | |
| "learning_rate": 8.18711994874345e-06, | |
| "loss": 0.5744427442550659, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 1.144578313253012, | |
| "grad_norm": 0.5757364630699158, | |
| "learning_rate": 8.022995574311876e-06, | |
| "loss": 0.576800525188446, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 1.180722891566265, | |
| "grad_norm": 0.5273779034614563, | |
| "learning_rate": 7.85356783842216e-06, | |
| "loss": 0.5835787057876587, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 1.216867469879518, | |
| "grad_norm": 0.4972248375415802, | |
| "learning_rate": 7.679133974894984e-06, | |
| "loss": 0.5828098654747009, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 1.2530120481927711, | |
| "grad_norm": 0.5350473523139954, | |
| "learning_rate": 7.500000000000001e-06, | |
| "loss": 0.576937198638916, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 1.2891566265060241, | |
| "grad_norm": 0.5231545567512512, | |
| "learning_rate": 7.31648017559931e-06, | |
| "loss": 0.5882814526557922, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 1.3253012048192772, | |
| "grad_norm": 0.506576657295227, | |
| "learning_rate": 7.128896457825364e-06, | |
| "loss": 0.6010534763336182, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 1.3614457831325302, | |
| "grad_norm": 0.45483383536338806, | |
| "learning_rate": 6.9375779322605154e-06, | |
| "loss": 0.5684958696365356, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 1.3975903614457832, | |
| "grad_norm": 0.5004634261131287, | |
| "learning_rate": 6.7428602366090764e-06, | |
| "loss": 0.5608981251716614, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 1.4337349397590362, | |
| "grad_norm": 0.4696190655231476, | |
| "learning_rate": 6.545084971874738e-06, | |
| "loss": 0.5603346824645996, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.4698795180722892, | |
| "grad_norm": 0.4757210612297058, | |
| "learning_rate": 6.344599103076329e-06, | |
| "loss": 0.559664785861969, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 1.5060240963855422, | |
| "grad_norm": 0.4191446006298065, | |
| "learning_rate": 6.141754350553279e-06, | |
| "loss": 0.5493080615997314, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 1.5421686746987953, | |
| "grad_norm": 0.45142653584480286, | |
| "learning_rate": 5.936906572928625e-06, | |
| "loss": 0.5648080110549927, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 1.5783132530120483, | |
| "grad_norm": 0.42723336815834045, | |
| "learning_rate": 5.730415142812059e-06, | |
| "loss": 0.5434543490409851, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 1.6144578313253013, | |
| "grad_norm": 0.5359069108963013, | |
| "learning_rate": 5.522642316338268e-06, | |
| "loss": 0.5768675804138184, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 1.6506024096385543, | |
| "grad_norm": 0.52814781665802, | |
| "learning_rate": 5.3139525976465675e-06, | |
| "loss": 0.5745658874511719, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 1.6867469879518073, | |
| "grad_norm": 0.3892335891723633, | |
| "learning_rate": 5.1047120994167855e-06, | |
| "loss": 0.5468243360519409, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 1.7228915662650603, | |
| "grad_norm": 0.4192783236503601, | |
| "learning_rate": 4.895287900583216e-06, | |
| "loss": 0.5729954242706299, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 1.7590361445783134, | |
| "grad_norm": 0.4870302379131317, | |
| "learning_rate": 4.686047402353433e-06, | |
| "loss": 0.5846940875053406, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 1.7951807228915664, | |
| "grad_norm": 0.43588584661483765, | |
| "learning_rate": 4.477357683661734e-06, | |
| "loss": 0.5727739334106445, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.8313253012048194, | |
| "grad_norm": 0.4209176301956177, | |
| "learning_rate": 4.269584857187942e-06, | |
| "loss": 0.5597992539405823, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 1.8674698795180724, | |
| "grad_norm": 0.4455879330635071, | |
| "learning_rate": 4.063093427071376e-06, | |
| "loss": 0.5638898611068726, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 1.9036144578313254, | |
| "grad_norm": 0.41628143191337585, | |
| "learning_rate": 3.8582456494467214e-06, | |
| "loss": 0.582793653011322, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 1.9397590361445785, | |
| "grad_norm": 0.40379446744918823, | |
| "learning_rate": 3.655400896923672e-06, | |
| "loss": 0.5641998052597046, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 1.9759036144578315, | |
| "grad_norm": 0.4030258357524872, | |
| "learning_rate": 3.4549150281252635e-06, | |
| "loss": 0.5672302842140198, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 0.4758393466472626, | |
| "learning_rate": 3.2571397633909252e-06, | |
| "loss": 0.5661230087280273, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 2.036144578313253, | |
| "grad_norm": 0.4000002443790436, | |
| "learning_rate": 3.0624220677394854e-06, | |
| "loss": 0.5152542591094971, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 2.072289156626506, | |
| "grad_norm": 0.4034959375858307, | |
| "learning_rate": 2.871103542174637e-06, | |
| "loss": 0.5110700130462646, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 2.108433734939759, | |
| "grad_norm": 0.42032384872436523, | |
| "learning_rate": 2.683519824400693e-06, | |
| "loss": 0.5136343240737915, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 2.144578313253012, | |
| "grad_norm": 0.417923241853714, | |
| "learning_rate": 2.5000000000000015e-06, | |
| "loss": 0.5048317909240723, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 2.180722891566265, | |
| "grad_norm": 0.4598260223865509, | |
| "learning_rate": 2.320866025105016e-06, | |
| "loss": 0.5214716196060181, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 2.216867469879518, | |
| "grad_norm": 0.41124001145362854, | |
| "learning_rate": 2.146432161577842e-06, | |
| "loss": 0.5121402740478516, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 2.253012048192771, | |
| "grad_norm": 0.4205818772315979, | |
| "learning_rate": 1.977004425688126e-06, | |
| "loss": 0.49233055114746094, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 2.289156626506024, | |
| "grad_norm": 0.37304773926734924, | |
| "learning_rate": 1.8128800512565514e-06, | |
| "loss": 0.5020605325698853, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 2.325301204819277, | |
| "grad_norm": 0.3686327040195465, | |
| "learning_rate": 1.6543469682057105e-06, | |
| "loss": 0.5020735263824463, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 2.36144578313253, | |
| "grad_norm": 0.3757750689983368, | |
| "learning_rate": 1.5016832974331725e-06, | |
| "loss": 0.5086070895195007, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 2.397590361445783, | |
| "grad_norm": 0.3529624044895172, | |
| "learning_rate": 1.3551568628929434e-06, | |
| "loss": 0.5086838006973267, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 2.433734939759036, | |
| "grad_norm": 0.35332420468330383, | |
| "learning_rate": 1.2150247217412186e-06, | |
| "loss": 0.5006733536720276, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 2.4698795180722892, | |
| "grad_norm": 0.4140400290489197, | |
| "learning_rate": 1.0815327133708015e-06, | |
| "loss": 0.4901826083660126, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 2.5060240963855422, | |
| "grad_norm": 0.45728668570518494, | |
| "learning_rate": 9.549150281252633e-07, | |
| "loss": 0.509224534034729, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 2.5421686746987953, | |
| "grad_norm": 0.3587833046913147, | |
| "learning_rate": 8.353937964495029e-07, | |
| "loss": 0.5090753436088562, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 2.5783132530120483, | |
| "grad_norm": 0.37985914945602417, | |
| "learning_rate": 7.23178699197467e-07, | |
| "loss": 0.5140612721443176, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 2.6144578313253013, | |
| "grad_norm": 0.36439454555511475, | |
| "learning_rate": 6.184665997806832e-07, | |
| "loss": 0.47711265087127686, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 2.6506024096385543, | |
| "grad_norm": 0.3805203437805176, | |
| "learning_rate": 5.214411988029355e-07, | |
| "loss": 0.49803662300109863, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 2.6867469879518073, | |
| "grad_norm": 0.3537060618400574, | |
| "learning_rate": 4.322727117869951e-07, | |
| "loss": 0.5065058469772339, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 2.7228915662650603, | |
| "grad_norm": 0.388337105512619, | |
| "learning_rate": 3.511175705587433e-07, | |
| "loss": 0.49857965111732483, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 2.7590361445783134, | |
| "grad_norm": 0.38901862502098083, | |
| "learning_rate": 2.7811814881259503e-07, | |
| "loss": 0.5032105445861816, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 2.7951807228915664, | |
| "grad_norm": 0.3811405599117279, | |
| "learning_rate": 2.134025123396638e-07, | |
| "loss": 0.48751121759414673, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 2.8313253012048194, | |
| "grad_norm": 0.358225017786026, | |
| "learning_rate": 1.5708419435684463e-07, | |
| "loss": 0.5210248231887817, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 2.8674698795180724, | |
| "grad_norm": 0.37859153747558594, | |
| "learning_rate": 1.0926199633097156e-07, | |
| "loss": 0.4980379343032837, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 2.9036144578313254, | |
| "grad_norm": 0.37158218026161194, | |
| "learning_rate": 7.001981464747565e-08, | |
| "loss": 0.5095956325531006, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 2.9397590361445785, | |
| "grad_norm": 0.3750190734863281, | |
| "learning_rate": 3.9426493427611177e-08, | |
| "loss": 0.5043609738349915, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 2.9759036144578315, | |
| "grad_norm": 0.36136147379875183, | |
| "learning_rate": 1.753570375247815e-08, | |
| "loss": 0.5091077089309692, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "grad_norm": 0.4021438956260681, | |
| "learning_rate": 4.385849505708084e-09, | |
| "loss": 0.5222575664520264, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "step": 84, | |
| "total_flos": 106024918253568.0, | |
| "train_loss": 0.5945852278243928, | |
| "train_runtime": 15268.5072, | |
| "train_samples_per_second": 0.261, | |
| "train_steps_per_second": 0.006 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 84, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 100000, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 106024918253568.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |