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-secureplusplus2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use eth-sri/kodcode-v1-qwq-secureplusplus2 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="eth-sri/kodcode-v1-qwq-secureplusplus2") 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-secureplusplus2") model = AutoModelForCausalLM.from_pretrained("eth-sri/kodcode-v1-qwq-secureplusplus2") 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-secureplusplus2 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-secureplusplus2" # 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-secureplusplus2", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/eth-sri/kodcode-v1-qwq-secureplusplus2
- SGLang
How to use eth-sri/kodcode-v1-qwq-secureplusplus2 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-secureplusplus2" \ --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-secureplusplus2", "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-secureplusplus2" \ --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-secureplusplus2", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use eth-sri/kodcode-v1-qwq-secureplusplus2 with Docker Model Runner:
docker model run hf.co/eth-sri/kodcode-v1-qwq-secureplusplus2
| { | |
| "best_global_step": null, | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 3.0, | |
| "eval_steps": 500, | |
| "global_step": 126, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.024096385542168676, | |
| "grad_norm": 3.4866182804107666, | |
| "learning_rate": 0.0, | |
| "loss": 0.8036330938339233, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.04819277108433735, | |
| "grad_norm": 3.7698822021484375, | |
| "learning_rate": 7.692307692307694e-07, | |
| "loss": 0.8342046737670898, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.07228915662650602, | |
| "grad_norm": 3.4847562313079834, | |
| "learning_rate": 1.5384615384615387e-06, | |
| "loss": 0.8215794563293457, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0963855421686747, | |
| "grad_norm": 3.367234468460083, | |
| "learning_rate": 2.307692307692308e-06, | |
| "loss": 0.8065542578697205, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.12048192771084337, | |
| "grad_norm": 3.0165975093841553, | |
| "learning_rate": 3.0769230769230774e-06, | |
| "loss": 0.7859395742416382, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.14457831325301204, | |
| "grad_norm": 2.850592851638794, | |
| "learning_rate": 3.846153846153847e-06, | |
| "loss": 0.7677067518234253, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.1686746987951807, | |
| "grad_norm": 2.0980072021484375, | |
| "learning_rate": 4.615384615384616e-06, | |
| "loss": 0.7406724691390991, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.1927710843373494, | |
| "grad_norm": 1.4586520195007324, | |
| "learning_rate": 5.384615384615385e-06, | |
| "loss": 0.7150983214378357, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.21686746987951808, | |
| "grad_norm": 1.5224018096923828, | |
| "learning_rate": 6.153846153846155e-06, | |
| "loss": 0.7036643028259277, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.24096385542168675, | |
| "grad_norm": 1.3343169689178467, | |
| "learning_rate": 6.923076923076923e-06, | |
| "loss": 0.7052457332611084, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.26506024096385544, | |
| "grad_norm": 2.000706911087036, | |
| "learning_rate": 7.692307692307694e-06, | |
| "loss": 0.6979789137840271, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.2891566265060241, | |
| "grad_norm": 2.2163498401641846, | |
| "learning_rate": 8.461538461538462e-06, | |
| "loss": 0.723534107208252, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.3132530120481928, | |
| "grad_norm": 2.1516668796539307, | |
| "learning_rate": 9.230769230769232e-06, | |
| "loss": 0.7533200979232788, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.3373493975903614, | |
| "grad_norm": 1.9026776552200317, | |
| "learning_rate": 1e-05, | |
| "loss": 0.7557893991470337, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.3614457831325301, | |
| "grad_norm": 1.7294775247573853, | |
| "learning_rate": 9.998067787472772e-06, | |
| "loss": 0.7446845769882202, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.3855421686746988, | |
| "grad_norm": 1.4833269119262695, | |
| "learning_rate": 9.992272643269181e-06, | |
| "loss": 0.704272985458374, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.40963855421686746, | |
| "grad_norm": 1.454253911972046, | |
| "learning_rate": 9.982619046369321e-06, | |
| "loss": 0.7148613333702087, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.43373493975903615, | |
| "grad_norm": 1.1598122119903564, | |
| "learning_rate": 9.96911445789354e-06, | |
| "loss": 0.6963663101196289, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.4578313253012048, | |
| "grad_norm": 1.0633970499038696, | |
| "learning_rate": 9.951769315335843e-06, | |
| "loss": 0.697997510433197, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.4819277108433735, | |
| "grad_norm": 1.112295389175415, | |
| "learning_rate": 9.930597024496933e-06, | |
| "loss": 0.687644898891449, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.5060240963855421, | |
| "grad_norm": 1.1765090227127075, | |
| "learning_rate": 9.905613949123036e-06, | |
| "loss": 0.6724652647972107, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.5301204819277109, | |
| "grad_norm": 1.072441577911377, | |
| "learning_rate": 9.87683939825864e-06, | |
| "loss": 0.6786834597587585, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.5542168674698795, | |
| "grad_norm": 0.9157149195671082, | |
| "learning_rate": 9.844295611322804e-06, | |
| "loss": 0.6787407398223877, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.5783132530120482, | |
| "grad_norm": 0.7829060554504395, | |
| "learning_rate": 9.808007740920647e-06, | |
| "loss": 0.6385012269020081, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.6024096385542169, | |
| "grad_norm": 0.905967116355896, | |
| "learning_rate": 9.768003833403278e-06, | |
| "loss": 0.6598682999610901, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.6265060240963856, | |
| "grad_norm": 0.7494702935218811, | |
| "learning_rate": 9.724314807191197e-06, | |
| "loss": 0.6414320468902588, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.6506024096385542, | |
| "grad_norm": 0.7239845395088196, | |
| "learning_rate": 9.6769744288779e-06, | |
| "loss": 0.6443482637405396, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.6746987951807228, | |
| "grad_norm": 0.7662610411643982, | |
| "learning_rate": 9.626019287132202e-06, | |
| "loss": 0.6470450162887573, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.6987951807228916, | |
| "grad_norm": 0.7057405710220337, | |
| "learning_rate": 9.571488764419381e-06, | |
| "loss": 0.6351138353347778, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.7228915662650602, | |
| "grad_norm": 0.6858580708503723, | |
| "learning_rate": 9.51342500656308e-06, | |
| "loss": 0.6081345677375793, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.7469879518072289, | |
| "grad_norm": 0.6748168468475342, | |
| "learning_rate": 9.451872890171419e-06, | |
| "loss": 0.6281493902206421, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.7710843373493976, | |
| "grad_norm": 0.7122080326080322, | |
| "learning_rate": 9.386879987952549e-06, | |
| "loss": 0.6601696610450745, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.7951807228915663, | |
| "grad_norm": 0.865262508392334, | |
| "learning_rate": 9.318496531946411e-06, | |
| "loss": 0.6518322229385376, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.8192771084337349, | |
| "grad_norm": 0.6199270486831665, | |
| "learning_rate": 9.246775374701139e-06, | |
| "loss": 0.6187893152236938, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.8433734939759037, | |
| "grad_norm": 0.6349459290504456, | |
| "learning_rate": 9.171771948424138e-06, | |
| "loss": 0.658621072769165, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.8674698795180723, | |
| "grad_norm": 0.6494747996330261, | |
| "learning_rate": 9.093544222139338e-06, | |
| "loss": 0.6379672288894653, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.891566265060241, | |
| "grad_norm": 0.6108894944190979, | |
| "learning_rate": 9.012152656883824e-06, | |
| "loss": 0.6225579977035522, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.9156626506024096, | |
| "grad_norm": 0.595695972442627, | |
| "learning_rate": 8.927660158978392e-06, | |
| "loss": 0.6457571387290955, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.9397590361445783, | |
| "grad_norm": 0.6286890506744385, | |
| "learning_rate": 8.84013203140821e-06, | |
| "loss": 0.6348350048065186, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.963855421686747, | |
| "grad_norm": 0.5852817893028259, | |
| "learning_rate": 8.749635923351108e-06, | |
| "loss": 0.6299422979354858, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.9879518072289156, | |
| "grad_norm": 0.5032863616943359, | |
| "learning_rate": 8.656241777892544e-06, | |
| "loss": 0.6204656958580017, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 0.9180984497070312, | |
| "learning_rate": 8.56002177796765e-06, | |
| "loss": 0.6175587177276611, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 1.0240963855421688, | |
| "grad_norm": 0.5904527902603149, | |
| "learning_rate": 8.461050290572114e-06, | |
| "loss": 0.5672452449798584, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 1.0481927710843373, | |
| "grad_norm": 0.5876842141151428, | |
| "learning_rate": 8.359403809285054e-06, | |
| "loss": 0.5524355173110962, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 1.072289156626506, | |
| "grad_norm": 0.6084136366844177, | |
| "learning_rate": 8.255160895148263e-06, | |
| "loss": 0.5549112558364868, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 1.0963855421686748, | |
| "grad_norm": 0.6880250573158264, | |
| "learning_rate": 8.14840211594757e-06, | |
| "loss": 0.5633288025856018, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 1.1204819277108433, | |
| "grad_norm": 0.5562106966972351, | |
| "learning_rate": 8.039209983943201e-06, | |
| "loss": 0.5377108454704285, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 1.144578313253012, | |
| "grad_norm": 0.5777124166488647, | |
| "learning_rate": 7.927668892097288e-06, | |
| "loss": 0.528072714805603, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 1.1686746987951806, | |
| "grad_norm": 0.6456765532493591, | |
| "learning_rate": 7.81386504884782e-06, | |
| "loss": 0.5457364916801453, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 1.1927710843373494, | |
| "grad_norm": 0.5695594549179077, | |
| "learning_rate": 7.697886411479422e-06, | |
| "loss": 0.5646842122077942, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.216867469879518, | |
| "grad_norm": 0.5582544803619385, | |
| "learning_rate": 7.579822618142505e-06, | |
| "loss": 0.5383089184761047, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 1.2409638554216866, | |
| "grad_norm": 0.5626118779182434, | |
| "learning_rate": 7.459764918573264e-06, | |
| "loss": 0.5594577193260193, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 1.2650602409638554, | |
| "grad_norm": 0.5415802597999573, | |
| "learning_rate": 7.3378061035681415e-06, | |
| "loss": 0.5535856485366821, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 1.2891566265060241, | |
| "grad_norm": 0.6203434467315674, | |
| "learning_rate": 7.2140404332671986e-06, | |
| "loss": 0.548930823802948, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 1.3132530120481927, | |
| "grad_norm": 0.6267032623291016, | |
| "learning_rate": 7.088563564301874e-06, | |
| "loss": 0.5701431035995483, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 1.3373493975903614, | |
| "grad_norm": 0.5693700909614563, | |
| "learning_rate": 6.961472475863406e-06, | |
| "loss": 0.5484758019447327, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 1.3614457831325302, | |
| "grad_norm": 0.6553611159324646, | |
| "learning_rate": 6.832865394749065e-06, | |
| "loss": 0.537543773651123, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 1.3855421686746987, | |
| "grad_norm": 0.6006720662117004, | |
| "learning_rate": 6.702841719444141e-06, | |
| "loss": 0.5397295951843262, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 1.4096385542168675, | |
| "grad_norm": 0.5610109567642212, | |
| "learning_rate": 6.571501943298335e-06, | |
| "loss": 0.5047672390937805, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 1.4337349397590362, | |
| "grad_norm": 0.6005979180335999, | |
| "learning_rate": 6.4389475768559675e-06, | |
| "loss": 0.5339192152023315, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 1.4578313253012047, | |
| "grad_norm": 0.5464897751808167, | |
| "learning_rate": 6.305281069399989e-06, | |
| "loss": 0.5370104312896729, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 1.4819277108433735, | |
| "grad_norm": 0.543561577796936, | |
| "learning_rate": 6.17060572977047e-06, | |
| "loss": 0.5109453201293945, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 1.5060240963855422, | |
| "grad_norm": 0.5380433201789856, | |
| "learning_rate": 6.035025646518747e-06, | |
| "loss": 0.5215125679969788, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 1.5301204819277108, | |
| "grad_norm": 0.5277564525604248, | |
| "learning_rate": 5.898645607458941e-06, | |
| "loss": 0.55159592628479, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 1.5542168674698795, | |
| "grad_norm": 0.5251535177230835, | |
| "learning_rate": 5.761571018679025e-06, | |
| "loss": 0.5137174129486084, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 1.5783132530120483, | |
| "grad_norm": 0.5158001184463501, | |
| "learning_rate": 5.623907823074044e-06, | |
| "loss": 0.5257411003112793, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 1.6024096385542168, | |
| "grad_norm": 0.5661113858222961, | |
| "learning_rate": 5.48576241846443e-06, | |
| "loss": 0.5619932413101196, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 1.6265060240963856, | |
| "grad_norm": 1.3053336143493652, | |
| "learning_rate": 5.347241575362729e-06, | |
| "loss": 0.5350067019462585, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 1.6506024096385543, | |
| "grad_norm": 0.5490331053733826, | |
| "learning_rate": 5.208452354452275e-06, | |
| "loss": 0.544854998588562, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 1.6746987951807228, | |
| "grad_norm": 0.5062744617462158, | |
| "learning_rate": 5.069502023841576e-06, | |
| "loss": 0.5490104556083679, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 1.6987951807228916, | |
| "grad_norm": 0.49572157859802246, | |
| "learning_rate": 4.9304979761584256e-06, | |
| "loss": 0.4955199956893921, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 1.7228915662650603, | |
| "grad_norm": 0.502623438835144, | |
| "learning_rate": 4.791547645547727e-06, | |
| "loss": 0.5547789335250854, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 1.7469879518072289, | |
| "grad_norm": 0.5623912215232849, | |
| "learning_rate": 4.652758424637271e-06, | |
| "loss": 0.5600606203079224, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 1.7710843373493976, | |
| "grad_norm": 0.6267077922821045, | |
| "learning_rate": 4.514237581535571e-06, | |
| "loss": 0.5465230941772461, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 1.7951807228915664, | |
| "grad_norm": 0.45720747113227844, | |
| "learning_rate": 4.3760921769259585e-06, | |
| "loss": 0.544208288192749, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 1.819277108433735, | |
| "grad_norm": 0.5470900535583496, | |
| "learning_rate": 4.2384289813209754e-06, | |
| "loss": 0.5490911602973938, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 1.8433734939759037, | |
| "grad_norm": 0.5712909698486328, | |
| "learning_rate": 4.101354392541061e-06, | |
| "loss": 0.5386078953742981, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 1.8674698795180724, | |
| "grad_norm": 0.48480501770973206, | |
| "learning_rate": 3.964974353481254e-06, | |
| "loss": 0.5202725529670715, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 1.891566265060241, | |
| "grad_norm": 0.4926944077014923, | |
| "learning_rate": 3.829394270229531e-06, | |
| "loss": 0.5781441926956177, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 1.9156626506024095, | |
| "grad_norm": 0.4879622161388397, | |
| "learning_rate": 3.694718930600012e-06, | |
| "loss": 0.5340090990066528, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 1.9397590361445785, | |
| "grad_norm": 0.5101142525672913, | |
| "learning_rate": 3.5610524231440324e-06, | |
| "loss": 0.5378634929656982, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 1.963855421686747, | |
| "grad_norm": 0.5045028924942017, | |
| "learning_rate": 3.428498056701665e-06, | |
| "loss": 0.5356432795524597, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 1.9879518072289155, | |
| "grad_norm": 0.5002654790878296, | |
| "learning_rate": 3.2971582805558622e-06, | |
| "loss": 0.5409777164459229, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 0.6559320092201233, | |
| "learning_rate": 3.167134605250938e-06, | |
| "loss": 0.5270622968673706, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 2.0240963855421685, | |
| "grad_norm": 0.5342044830322266, | |
| "learning_rate": 3.0385275241365965e-06, | |
| "loss": 0.48670250177383423, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 2.0481927710843375, | |
| "grad_norm": 0.49373114109039307, | |
| "learning_rate": 2.9114364356981274e-06, | |
| "loss": 0.4560129642486572, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 2.072289156626506, | |
| "grad_norm": 0.48619571328163147, | |
| "learning_rate": 2.7859595667328027e-06, | |
| "loss": 0.47067636251449585, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 2.0963855421686746, | |
| "grad_norm": 0.5437542200088501, | |
| "learning_rate": 2.6621938964318593e-06, | |
| "loss": 0.4635806381702423, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 2.1204819277108435, | |
| "grad_norm": 0.5450485348701477, | |
| "learning_rate": 2.5402350814267364e-06, | |
| "loss": 0.4750005602836609, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 2.144578313253012, | |
| "grad_norm": 0.47268036007881165, | |
| "learning_rate": 2.4201773818574956e-06, | |
| "loss": 0.44007742404937744, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 2.1686746987951806, | |
| "grad_norm": 0.5399731397628784, | |
| "learning_rate": 2.302113588520578e-06, | |
| "loss": 0.46573615074157715, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 2.1927710843373496, | |
| "grad_norm": 0.49338477849960327, | |
| "learning_rate": 2.1861349511521817e-06, | |
| "loss": 0.4689018726348877, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 2.216867469879518, | |
| "grad_norm": 0.5834346413612366, | |
| "learning_rate": 2.072331107902713e-06, | |
| "loss": 0.46710026264190674, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 2.2409638554216866, | |
| "grad_norm": 0.5362139940261841, | |
| "learning_rate": 1.960790016056801e-06, | |
| "loss": 0.4441226124763489, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 2.2650602409638556, | |
| "grad_norm": 0.4785553216934204, | |
| "learning_rate": 1.8515978840524302e-06, | |
| "loss": 0.4488658905029297, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 2.289156626506024, | |
| "grad_norm": 0.46260133385658264, | |
| "learning_rate": 1.7448391048517378e-06, | |
| "loss": 0.4457336366176605, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 2.3132530120481927, | |
| "grad_norm": 0.46317535638809204, | |
| "learning_rate": 1.640596190714947e-06, | |
| "loss": 0.46047937870025635, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 2.337349397590361, | |
| "grad_norm": 0.46262696385383606, | |
| "learning_rate": 1.5389497094278861e-06, | |
| "loss": 0.457674115896225, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 2.36144578313253, | |
| "grad_norm": 0.4948306977748871, | |
| "learning_rate": 1.4399782220323515e-06, | |
| "loss": 0.45349499583244324, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 2.3855421686746987, | |
| "grad_norm": 0.4395950138568878, | |
| "learning_rate": 1.3437582221074574e-06, | |
| "loss": 0.4638131856918335, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 2.4096385542168672, | |
| "grad_norm": 0.4956653416156769, | |
| "learning_rate": 1.250364076648894e-06, | |
| "loss": 0.47085821628570557, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 2.433734939759036, | |
| "grad_norm": 0.45674222707748413, | |
| "learning_rate": 1.1598679685917901e-06, | |
| "loss": 0.4503791928291321, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 2.4578313253012047, | |
| "grad_norm": 0.507217526435852, | |
| "learning_rate": 1.0723398410216085e-06, | |
| "loss": 0.4312359094619751, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 2.4819277108433733, | |
| "grad_norm": 0.5251759886741638, | |
| "learning_rate": 9.878473431161767e-07, | |
| "loss": 0.46261149644851685, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 2.5060240963855422, | |
| "grad_norm": 0.4792177677154541, | |
| "learning_rate": 9.064557778606631e-07, | |
| "loss": 0.4512259364128113, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 2.5301204819277108, | |
| "grad_norm": 0.4588276445865631, | |
| "learning_rate": 8.282280515758639e-07, | |
| "loss": 0.46932703256607056, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 2.5542168674698793, | |
| "grad_norm": 0.47770798206329346, | |
| "learning_rate": 7.532246252988617e-07, | |
| "loss": 0.46546822786331177, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 2.5783132530120483, | |
| "grad_norm": 0.4528071880340576, | |
| "learning_rate": 6.815034680535915e-07, | |
| "loss": 0.46492496132850647, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 2.602409638554217, | |
| "grad_norm": 0.4753343164920807, | |
| "learning_rate": 6.131200120474512e-07, | |
| "loss": 0.4336838722229004, | |
| "step": 109 | |
| }, | |
| { | |
| "epoch": 2.6265060240963853, | |
| "grad_norm": 0.45192626118659973, | |
| "learning_rate": 5.481271098285818e-07, | |
| "loss": 0.4398084282875061, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 2.6506024096385543, | |
| "grad_norm": 0.5253329873085022, | |
| "learning_rate": 4.865749934369224e-07, | |
| "loss": 0.4459433853626251, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 2.674698795180723, | |
| "grad_norm": 0.4748944044113159, | |
| "learning_rate": 4.2851123558061927e-07, | |
| "loss": 0.4655908942222595, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 2.6987951807228914, | |
| "grad_norm": 0.46791234612464905, | |
| "learning_rate": 3.739807128677986e-07, | |
| "loss": 0.44779670238494873, | |
| "step": 113 | |
| }, | |
| { | |
| "epoch": 2.7228915662650603, | |
| "grad_norm": 0.4889393448829651, | |
| "learning_rate": 3.230255711220992e-07, | |
| "loss": 0.44272205233573914, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 2.746987951807229, | |
| "grad_norm": 0.4753701984882355, | |
| "learning_rate": 2.756851928088056e-07, | |
| "loss": 0.44829046726226807, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 2.7710843373493974, | |
| "grad_norm": 0.6399223208427429, | |
| "learning_rate": 2.3199616659672352e-07, | |
| "loss": 0.4521270990371704, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 2.7951807228915664, | |
| "grad_norm": 0.46191707253456116, | |
| "learning_rate": 1.9199225907935492e-07, | |
| "loss": 0.4472425878047943, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 2.819277108433735, | |
| "grad_norm": 0.39189624786376953, | |
| "learning_rate": 1.5570438867719695e-07, | |
| "loss": 0.46183761954307556, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 2.8433734939759034, | |
| "grad_norm": 0.5180935263633728, | |
| "learning_rate": 1.2316060174136e-07, | |
| "loss": 0.4718969166278839, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 2.8674698795180724, | |
| "grad_norm": 0.4680953919887543, | |
| "learning_rate": 9.43860508769645e-08, | |
| "loss": 0.44515055418014526, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 2.891566265060241, | |
| "grad_norm": 0.4501122832298279, | |
| "learning_rate": 6.940297550306895e-08, | |
| "loss": 0.46908432245254517, | |
| "step": 121 | |
| }, | |
| { | |
| "epoch": 2.9156626506024095, | |
| "grad_norm": 0.4875977039337158, | |
| "learning_rate": 4.823068466415615e-08, | |
| "loss": 0.44129478931427, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 2.9397590361445785, | |
| "grad_norm": 0.4675557613372803, | |
| "learning_rate": 3.088554210646133e-08, | |
| "loss": 0.4616200923919678, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 2.963855421686747, | |
| "grad_norm": 0.4429016709327698, | |
| "learning_rate": 1.7380953630678488e-08, | |
| "loss": 0.457840234041214, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 2.9879518072289155, | |
| "grad_norm": 0.4272845685482025, | |
| "learning_rate": 7.727356730820035e-09, | |
| "loss": 0.47879689931869507, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "grad_norm": 0.6524609327316284, | |
| "learning_rate": 1.9322125272297488e-09, | |
| "loss": 0.45391568541526794, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "step": 126, | |
| "total_flos": 105954971353088.0, | |
| "train_loss": 0.5631231036451128, | |
| "train_runtime": 7331.2993, | |
| "train_samples_per_second": 0.543, | |
| "train_steps_per_second": 0.017 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 126, | |
| "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": 105954971353088.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |