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-secureplusplus1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use eth-sri/kodcode-v1-qwq-secureplusplus1 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="eth-sri/kodcode-v1-qwq-secureplusplus1") 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-secureplusplus1") model = AutoModelForCausalLM.from_pretrained("eth-sri/kodcode-v1-qwq-secureplusplus1") 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-secureplusplus1 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-secureplusplus1" # 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-secureplusplus1", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/eth-sri/kodcode-v1-qwq-secureplusplus1
- SGLang
How to use eth-sri/kodcode-v1-qwq-secureplusplus1 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-secureplusplus1" \ --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-secureplusplus1", "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-secureplusplus1" \ --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-secureplusplus1", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use eth-sri/kodcode-v1-qwq-secureplusplus1 with Docker Model Runner:
docker model run hf.co/eth-sri/kodcode-v1-qwq-secureplusplus1
| { | |
| "best_global_step": null, | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 5.0, | |
| "eval_steps": 500, | |
| "global_step": 140, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.03614457831325301, | |
| "grad_norm": 3.552992582321167, | |
| "learning_rate": 0.0, | |
| "loss": 0.8157972693443298, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.07228915662650602, | |
| "grad_norm": 3.476118803024292, | |
| "learning_rate": 7.142857142857143e-07, | |
| "loss": 0.8220954537391663, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.10843373493975904, | |
| "grad_norm": 3.4009079933166504, | |
| "learning_rate": 1.4285714285714286e-06, | |
| "loss": 0.8117464780807495, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.14457831325301204, | |
| "grad_norm": 3.329871416091919, | |
| "learning_rate": 2.1428571428571427e-06, | |
| "loss": 0.799206018447876, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.18072289156626506, | |
| "grad_norm": 3.0760695934295654, | |
| "learning_rate": 2.8571428571428573e-06, | |
| "loss": 0.794347882270813, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.21686746987951808, | |
| "grad_norm": 2.7692043781280518, | |
| "learning_rate": 3.5714285714285718e-06, | |
| "loss": 0.7785108685493469, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.25301204819277107, | |
| "grad_norm": 2.115936756134033, | |
| "learning_rate": 4.2857142857142855e-06, | |
| "loss": 0.7394494414329529, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.2891566265060241, | |
| "grad_norm": 1.8370460271835327, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7277400493621826, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.3253012048192771, | |
| "grad_norm": 1.693984031677246, | |
| "learning_rate": 5.7142857142857145e-06, | |
| "loss": 0.7472832202911377, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.3614457831325301, | |
| "grad_norm": 1.54923677444458, | |
| "learning_rate": 6.4285714285714295e-06, | |
| "loss": 0.7461951375007629, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.39759036144578314, | |
| "grad_norm": 1.598431944847107, | |
| "learning_rate": 7.1428571428571436e-06, | |
| "loss": 0.7162140607833862, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.43373493975903615, | |
| "grad_norm": 2.1767778396606445, | |
| "learning_rate": 7.857142857142858e-06, | |
| "loss": 0.7198895215988159, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.46987951807228917, | |
| "grad_norm": 1.9528471231460571, | |
| "learning_rate": 8.571428571428571e-06, | |
| "loss": 0.7287980318069458, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.5060240963855421, | |
| "grad_norm": 1.7289732694625854, | |
| "learning_rate": 9.285714285714288e-06, | |
| "loss": 0.7282652854919434, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.5421686746987951, | |
| "grad_norm": 1.507106065750122, | |
| "learning_rate": 1e-05, | |
| "loss": 0.7166401147842407, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.5783132530120482, | |
| "grad_norm": 1.326465368270874, | |
| "learning_rate": 9.998445910004082e-06, | |
| "loss": 0.6848917603492737, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.6144578313253012, | |
| "grad_norm": 1.2025340795516968, | |
| "learning_rate": 9.993784606094612e-06, | |
| "loss": 0.689272940158844, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.6506024096385542, | |
| "grad_norm": 1.0700381994247437, | |
| "learning_rate": 9.986018985905901e-06, | |
| "loss": 0.6728196740150452, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.6867469879518072, | |
| "grad_norm": 1.0352157354354858, | |
| "learning_rate": 9.975153876827008e-06, | |
| "loss": 0.6726264953613281, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.7228915662650602, | |
| "grad_norm": 1.0997517108917236, | |
| "learning_rate": 9.961196033000862e-06, | |
| "loss": 0.6467926502227783, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.7590361445783133, | |
| "grad_norm": 1.0536617040634155, | |
| "learning_rate": 9.944154131125643e-06, | |
| "loss": 0.6569991111755371, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.7951807228915663, | |
| "grad_norm": 0.9395158290863037, | |
| "learning_rate": 9.924038765061042e-06, | |
| "loss": 0.6807858943939209, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.8313253012048193, | |
| "grad_norm": 0.8130300641059875, | |
| "learning_rate": 9.900862439242719e-06, | |
| "loss": 0.6488538384437561, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.8674698795180723, | |
| "grad_norm": 0.8527212142944336, | |
| "learning_rate": 9.874639560909118e-06, | |
| "loss": 0.663514256477356, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.9036144578313253, | |
| "grad_norm": 0.780767023563385, | |
| "learning_rate": 9.84538643114539e-06, | |
| "loss": 0.6396875977516174, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.9397590361445783, | |
| "grad_norm": 0.7361811995506287, | |
| "learning_rate": 9.81312123475006e-06, | |
| "loss": 0.6566063761711121, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.9759036144578314, | |
| "grad_norm": 0.653764009475708, | |
| "learning_rate": 9.777864028930705e-06, | |
| "loss": 0.629973292350769, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 0.7102857828140259, | |
| "learning_rate": 9.73963673083566e-06, | |
| "loss": 0.6426781415939331, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 1.036144578313253, | |
| "grad_norm": 0.6126017570495605, | |
| "learning_rate": 9.698463103929542e-06, | |
| "loss": 0.5972884893417358, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 1.072289156626506, | |
| "grad_norm": 0.6909480690956116, | |
| "learning_rate": 9.654368743221022e-06, | |
| "loss": 0.5937310457229614, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.108433734939759, | |
| "grad_norm": 0.7211623787879944, | |
| "learning_rate": 9.60738105935204e-06, | |
| "loss": 0.5821231603622437, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 1.144578313253012, | |
| "grad_norm": 0.6068958044052124, | |
| "learning_rate": 9.557529261558367e-06, | |
| "loss": 0.5844348669052124, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 1.180722891566265, | |
| "grad_norm": 0.6305683851242065, | |
| "learning_rate": 9.504844339512096e-06, | |
| "loss": 0.5876203775405884, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 1.216867469879518, | |
| "grad_norm": 0.6707793474197388, | |
| "learning_rate": 9.449359044057344e-06, | |
| "loss": 0.5915540456771851, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 1.2530120481927711, | |
| "grad_norm": 0.6236127614974976, | |
| "learning_rate": 9.391107866851143e-06, | |
| "loss": 0.5834020376205444, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 1.2891566265060241, | |
| "grad_norm": 0.5636352896690369, | |
| "learning_rate": 9.330127018922195e-06, | |
| "loss": 0.5935553312301636, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 1.3253012048192772, | |
| "grad_norm": 0.5773406028747559, | |
| "learning_rate": 9.266454408160779e-06, | |
| "loss": 0.6015973687171936, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 1.3614457831325302, | |
| "grad_norm": 0.5419151186943054, | |
| "learning_rate": 9.200129615753858e-06, | |
| "loss": 0.5702415704727173, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 1.3975903614457832, | |
| "grad_norm": 0.5509113669395447, | |
| "learning_rate": 9.131193871579975e-06, | |
| "loss": 0.5633657574653625, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 1.4337349397590362, | |
| "grad_norm": 0.5442959070205688, | |
| "learning_rate": 9.059690028579285e-06, | |
| "loss": 0.5625412464141846, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.4698795180722892, | |
| "grad_norm": 0.5770719051361084, | |
| "learning_rate": 8.985662536114614e-06, | |
| "loss": 0.5657418966293335, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 1.5060240963855422, | |
| "grad_norm": 0.505865752696991, | |
| "learning_rate": 8.90915741234015e-06, | |
| "loss": 0.5550695061683655, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 1.5421686746987953, | |
| "grad_norm": 0.4989571273326874, | |
| "learning_rate": 8.83022221559489e-06, | |
| "loss": 0.5686677694320679, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 1.5783132530120483, | |
| "grad_norm": 0.4765966236591339, | |
| "learning_rate": 8.748906014838672e-06, | |
| "loss": 0.5502008199691772, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 1.6144578313253013, | |
| "grad_norm": 0.5664476752281189, | |
| "learning_rate": 8.665259359149132e-06, | |
| "loss": 0.5842461585998535, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 1.6506024096385543, | |
| "grad_norm": 0.5490483641624451, | |
| "learning_rate": 8.579334246298593e-06, | |
| "loss": 0.5751632452011108, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 1.6867469879518073, | |
| "grad_norm": 0.4468829035758972, | |
| "learning_rate": 8.491184090430365e-06, | |
| "loss": 0.5543277263641357, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 1.7228915662650603, | |
| "grad_norm": 0.5188086032867432, | |
| "learning_rate": 8.400863688854598e-06, | |
| "loss": 0.5773334503173828, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 1.7590361445783134, | |
| "grad_norm": 0.5209062099456787, | |
| "learning_rate": 8.308429187984298e-06, | |
| "loss": 0.5917258858680725, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 1.7951807228915664, | |
| "grad_norm": 0.43107232451438904, | |
| "learning_rate": 8.213938048432697e-06, | |
| "loss": 0.5791318416595459, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.8313253012048194, | |
| "grad_norm": 0.5132546424865723, | |
| "learning_rate": 8.117449009293668e-06, | |
| "loss": 0.5625239610671997, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 1.8674698795180724, | |
| "grad_norm": 0.5580247044563293, | |
| "learning_rate": 8.019022051627387e-06, | |
| "loss": 0.5658679604530334, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 1.9036144578313254, | |
| "grad_norm": 0.4792289733886719, | |
| "learning_rate": 7.918718361173951e-06, | |
| "loss": 0.5874133110046387, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 1.9397590361445785, | |
| "grad_norm": 0.41966840624809265, | |
| "learning_rate": 7.81660029031811e-06, | |
| "loss": 0.5653340816497803, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 1.9759036144578315, | |
| "grad_norm": 0.49099063873291016, | |
| "learning_rate": 7.712731319328798e-06, | |
| "loss": 0.5714031457901001, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 0.5688431859016418, | |
| "learning_rate": 7.607176016897491e-06, | |
| "loss": 0.5722917318344116, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 2.036144578313253, | |
| "grad_norm": 0.5012766718864441, | |
| "learning_rate": 7.500000000000001e-06, | |
| "loss": 0.4961242973804474, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 2.072289156626506, | |
| "grad_norm": 0.46055009961128235, | |
| "learning_rate": 7.391269893106592e-06, | |
| "loss": 0.4894614517688751, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 2.108433734939759, | |
| "grad_norm": 0.46600088477134705, | |
| "learning_rate": 7.281053286765816e-06, | |
| "loss": 0.4911263585090637, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 2.144578313253012, | |
| "grad_norm": 0.5008800625801086, | |
| "learning_rate": 7.169418695587791e-06, | |
| "loss": 0.47886592149734497, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 2.180722891566265, | |
| "grad_norm": 0.5292919278144836, | |
| "learning_rate": 7.056435515653059e-06, | |
| "loss": 0.4931592345237732, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 2.216867469879518, | |
| "grad_norm": 0.5357526540756226, | |
| "learning_rate": 6.942173981373474e-06, | |
| "loss": 0.48882538080215454, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 2.253012048192771, | |
| "grad_norm": 0.48591041564941406, | |
| "learning_rate": 6.8267051218319766e-06, | |
| "loss": 0.4678572416305542, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 2.289156626506024, | |
| "grad_norm": 0.4718064069747925, | |
| "learning_rate": 6.710100716628345e-06, | |
| "loss": 0.475056916475296, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 2.325301204819277, | |
| "grad_norm": 0.47468462586402893, | |
| "learning_rate": 6.592433251258423e-06, | |
| "loss": 0.47353294491767883, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 2.36144578313253, | |
| "grad_norm": 0.4995141327381134, | |
| "learning_rate": 6.473775872054522e-06, | |
| "loss": 0.4775480628013611, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 2.397590361445783, | |
| "grad_norm": 0.434576153755188, | |
| "learning_rate": 6.354202340715027e-06, | |
| "loss": 0.4789201319217682, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 2.433734939759036, | |
| "grad_norm": 0.4830213487148285, | |
| "learning_rate": 6.233786988451468e-06, | |
| "loss": 0.472676157951355, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 2.4698795180722892, | |
| "grad_norm": 1.22783625125885, | |
| "learning_rate": 6.112604669781572e-06, | |
| "loss": 0.4603816866874695, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 2.5060240963855422, | |
| "grad_norm": 0.5310467481613159, | |
| "learning_rate": 5.990730715996989e-06, | |
| "loss": 0.4775810241699219, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 2.5421686746987953, | |
| "grad_norm": 0.4714012145996094, | |
| "learning_rate": 5.8682408883346535e-06, | |
| "loss": 0.47795799374580383, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 2.5783132530120483, | |
| "grad_norm": 0.5383198857307434, | |
| "learning_rate": 5.745211330880872e-06, | |
| "loss": 0.48292991518974304, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 2.6144578313253013, | |
| "grad_norm": 0.4685249626636505, | |
| "learning_rate": 5.621718523237427e-06, | |
| "loss": 0.44596827030181885, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 2.6506024096385543, | |
| "grad_norm": 0.46077290177345276, | |
| "learning_rate": 5.497839232979084e-06, | |
| "loss": 0.464788019657135, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 2.6867469879518073, | |
| "grad_norm": 0.45095938444137573, | |
| "learning_rate": 5.373650467932122e-06, | |
| "loss": 0.4685942828655243, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 2.7228915662650603, | |
| "grad_norm": 0.48428815603256226, | |
| "learning_rate": 5.249229428303486e-06, | |
| "loss": 0.4635739326477051, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 2.7590361445783134, | |
| "grad_norm": 0.4849986732006073, | |
| "learning_rate": 5.1246534586903655e-06, | |
| "loss": 0.4689663052558899, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 2.7951807228915664, | |
| "grad_norm": 0.47483494877815247, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4565011262893677, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 2.8313253012048194, | |
| "grad_norm": 0.4436506927013397, | |
| "learning_rate": 4.875346541309637e-06, | |
| "loss": 0.486378937959671, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 2.8674698795180724, | |
| "grad_norm": 0.43863165378570557, | |
| "learning_rate": 4.750770571696514e-06, | |
| "loss": 0.46573954820632935, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 2.9036144578313254, | |
| "grad_norm": 0.4599636495113373, | |
| "learning_rate": 4.626349532067879e-06, | |
| "loss": 0.47583407163619995, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 2.9397590361445785, | |
| "grad_norm": 0.4593915343284607, | |
| "learning_rate": 4.502160767020918e-06, | |
| "loss": 0.4649534821510315, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 2.9759036144578315, | |
| "grad_norm": 0.42819902300834656, | |
| "learning_rate": 4.3782814767625755e-06, | |
| "loss": 0.47310101985931396, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "grad_norm": 0.4795413017272949, | |
| "learning_rate": 4.254788669119127e-06, | |
| "loss": 0.4935457110404968, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 3.036144578313253, | |
| "grad_norm": 0.544659435749054, | |
| "learning_rate": 4.131759111665349e-06, | |
| "loss": 0.40572214126586914, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 3.072289156626506, | |
| "grad_norm": 0.4835144579410553, | |
| "learning_rate": 4.009269284003014e-06, | |
| "loss": 0.4221254587173462, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 3.108433734939759, | |
| "grad_norm": 0.5012200474739075, | |
| "learning_rate": 3.887395330218429e-06, | |
| "loss": 0.40673914551734924, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 3.144578313253012, | |
| "grad_norm": 0.4846048653125763, | |
| "learning_rate": 3.7662130115485317e-06, | |
| "loss": 0.39578598737716675, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 3.180722891566265, | |
| "grad_norm": 0.4409545660018921, | |
| "learning_rate": 3.6457976592849753e-06, | |
| "loss": 0.3912641406059265, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 3.216867469879518, | |
| "grad_norm": 0.5371993780136108, | |
| "learning_rate": 3.526224127945479e-06, | |
| "loss": 0.41591888666152954, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 3.253012048192771, | |
| "grad_norm": 0.4998728632926941, | |
| "learning_rate": 3.4075667487415785e-06, | |
| "loss": 0.39664745330810547, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 3.289156626506024, | |
| "grad_norm": 0.5280871987342834, | |
| "learning_rate": 3.289899283371657e-06, | |
| "loss": 0.41508030891418457, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 3.325301204819277, | |
| "grad_norm": 0.4832461178302765, | |
| "learning_rate": 3.173294878168025e-06, | |
| "loss": 0.4029202461242676, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 3.36144578313253, | |
| "grad_norm": 0.4391038119792938, | |
| "learning_rate": 3.057826018626527e-06, | |
| "loss": 0.42191892862319946, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 3.397590361445783, | |
| "grad_norm": 0.48466429114341736, | |
| "learning_rate": 2.9435644843469434e-06, | |
| "loss": 0.3834310472011566, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 3.433734939759036, | |
| "grad_norm": 0.48416197299957275, | |
| "learning_rate": 2.83058130441221e-06, | |
| "loss": 0.37224042415618896, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 3.4698795180722892, | |
| "grad_norm": 0.46029776334762573, | |
| "learning_rate": 2.718946713234185e-06, | |
| "loss": 0.40440261363983154, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 3.5060240963855422, | |
| "grad_norm": 0.42011407017707825, | |
| "learning_rate": 2.608730106893411e-06, | |
| "loss": 0.4014296233654022, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 3.5421686746987953, | |
| "grad_norm": 0.4515833258628845, | |
| "learning_rate": 2.5000000000000015e-06, | |
| "loss": 0.406674861907959, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 3.5783132530120483, | |
| "grad_norm": 0.4748595654964447, | |
| "learning_rate": 2.39282398310251e-06, | |
| "loss": 0.39458712935447693, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 3.6144578313253013, | |
| "grad_norm": 1.059367060661316, | |
| "learning_rate": 2.2872686806712037e-06, | |
| "loss": 0.3989582359790802, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 3.6506024096385543, | |
| "grad_norm": 0.4319497346878052, | |
| "learning_rate": 2.1833997096818897e-06, | |
| "loss": 0.4034951329231262, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 3.6867469879518073, | |
| "grad_norm": 0.39853084087371826, | |
| "learning_rate": 2.081281638826052e-06, | |
| "loss": 0.3809719681739807, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 3.7228915662650603, | |
| "grad_norm": 0.452144980430603, | |
| "learning_rate": 1.980977948372612e-06, | |
| "loss": 0.3899919390678406, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 3.7590361445783134, | |
| "grad_norm": 0.41418761014938354, | |
| "learning_rate": 1.8825509907063328e-06, | |
| "loss": 0.391804039478302, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 3.7951807228915664, | |
| "grad_norm": 0.5204885005950928, | |
| "learning_rate": 1.7860619515673034e-06, | |
| "loss": 0.3823849558830261, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 3.8313253012048194, | |
| "grad_norm": 0.43118229508399963, | |
| "learning_rate": 1.6915708120157042e-06, | |
| "loss": 0.3914030194282532, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 3.8674698795180724, | |
| "grad_norm": 0.3945900499820709, | |
| "learning_rate": 1.5991363111454023e-06, | |
| "loss": 0.40952011942863464, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 3.9036144578313254, | |
| "grad_norm": 0.4364968538284302, | |
| "learning_rate": 1.5088159095696365e-06, | |
| "loss": 0.3888675272464752, | |
| "step": 109 | |
| }, | |
| { | |
| "epoch": 3.9397590361445785, | |
| "grad_norm": 0.43406206369400024, | |
| "learning_rate": 1.4206657537014078e-06, | |
| "loss": 0.3916434943675995, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 3.9759036144578315, | |
| "grad_norm": 0.3935132324695587, | |
| "learning_rate": 1.3347406408508695e-06, | |
| "loss": 0.40634751319885254, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "grad_norm": 0.48670002818107605, | |
| "learning_rate": 1.2510939851613285e-06, | |
| "loss": 0.36517858505249023, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 4.036144578313253, | |
| "grad_norm": 0.4544495940208435, | |
| "learning_rate": 1.1697777844051105e-06, | |
| "loss": 0.35902053117752075, | |
| "step": 113 | |
| }, | |
| { | |
| "epoch": 4.072289156626506, | |
| "grad_norm": 0.42937037348747253, | |
| "learning_rate": 1.0908425876598512e-06, | |
| "loss": 0.35485056042671204, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 4.108433734939759, | |
| "grad_norm": 0.5198720693588257, | |
| "learning_rate": 1.0143374638853892e-06, | |
| "loss": 0.34688663482666016, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 4.144578313253012, | |
| "grad_norm": 0.41341260075569153, | |
| "learning_rate": 9.403099714207175e-07, | |
| "loss": 0.3819352388381958, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 4.180722891566265, | |
| "grad_norm": 0.4290361702442169, | |
| "learning_rate": 8.688061284200266e-07, | |
| "loss": 0.3543751835823059, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 4.216867469879518, | |
| "grad_norm": 0.4403778314590454, | |
| "learning_rate": 7.99870384246143e-07, | |
| "loss": 0.3402591049671173, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 4.253012048192771, | |
| "grad_norm": 0.4087570607662201, | |
| "learning_rate": 7.33545591839222e-07, | |
| "loss": 0.3809043765068054, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 4.289156626506024, | |
| "grad_norm": 0.3830568790435791, | |
| "learning_rate": 6.698729810778065e-07, | |
| "loss": 0.35862648487091064, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 4.325301204819277, | |
| "grad_norm": 0.3721303641796112, | |
| "learning_rate": 6.088921331488568e-07, | |
| "loss": 0.3683925271034241, | |
| "step": 121 | |
| }, | |
| { | |
| "epoch": 4.36144578313253, | |
| "grad_norm": 0.4181763231754303, | |
| "learning_rate": 5.506409559426573e-07, | |
| "loss": 0.3694748878479004, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 4.397590361445783, | |
| "grad_norm": 0.37962082028388977, | |
| "learning_rate": 4.951556604879049e-07, | |
| "loss": 0.33829501271247864, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 4.433734939759036, | |
| "grad_norm": 0.6017558574676514, | |
| "learning_rate": 4.4247073844163434e-07, | |
| "loss": 0.3828006684780121, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 4.469879518072289, | |
| "grad_norm": 0.38617610931396484, | |
| "learning_rate": 3.9261894064796136e-07, | |
| "loss": 0.34324461221694946, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 4.506024096385542, | |
| "grad_norm": 0.37434372305870056, | |
| "learning_rate": 3.4563125677897936e-07, | |
| "loss": 0.3604496717453003, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 4.542168674698795, | |
| "grad_norm": 0.34874486923217773, | |
| "learning_rate": 3.015368960704584e-07, | |
| "loss": 0.368318110704422, | |
| "step": 127 | |
| }, | |
| { | |
| "epoch": 4.578313253012048, | |
| "grad_norm": 0.3934071958065033, | |
| "learning_rate": 2.6036326916434153e-07, | |
| "loss": 0.3627038598060608, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 4.614457831325301, | |
| "grad_norm": 0.3789614140987396, | |
| "learning_rate": 2.2213597106929608e-07, | |
| "loss": 0.36452317237854004, | |
| "step": 129 | |
| }, | |
| { | |
| "epoch": 4.650602409638554, | |
| "grad_norm": 0.4220135807991028, | |
| "learning_rate": 1.8687876524993987e-07, | |
| "loss": 0.36343690752983093, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 4.686746987951807, | |
| "grad_norm": 0.4450218081474304, | |
| "learning_rate": 1.5461356885461077e-07, | |
| "loss": 0.3400435149669647, | |
| "step": 131 | |
| }, | |
| { | |
| "epoch": 4.72289156626506, | |
| "grad_norm": 0.40480294823646545, | |
| "learning_rate": 1.253604390908819e-07, | |
| "loss": 0.36769339442253113, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 4.759036144578313, | |
| "grad_norm": 0.3862755000591278, | |
| "learning_rate": 9.913756075728088e-08, | |
| "loss": 0.33065229654312134, | |
| "step": 133 | |
| }, | |
| { | |
| "epoch": 4.795180722891566, | |
| "grad_norm": 0.39246875047683716, | |
| "learning_rate": 7.59612349389599e-08, | |
| "loss": 0.3565322160720825, | |
| "step": 134 | |
| }, | |
| { | |
| "epoch": 4.831325301204819, | |
| "grad_norm": 0.3649466037750244, | |
| "learning_rate": 5.584586887435739e-08, | |
| "loss": 0.35847705602645874, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 4.867469879518072, | |
| "grad_norm": 0.4285505712032318, | |
| "learning_rate": 3.8803966999139686e-08, | |
| "loss": 0.35844671726226807, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 4.903614457831325, | |
| "grad_norm": 0.3838602304458618, | |
| "learning_rate": 2.4846123172992953e-08, | |
| "loss": 0.3399174213409424, | |
| "step": 137 | |
| }, | |
| { | |
| "epoch": 4.9397590361445785, | |
| "grad_norm": 0.40299808979034424, | |
| "learning_rate": 1.3981014094099354e-08, | |
| "loss": 0.34250783920288086, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 4.975903614457831, | |
| "grad_norm": 0.38454756140708923, | |
| "learning_rate": 6.215393905388278e-09, | |
| "loss": 0.36665719747543335, | |
| "step": 139 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "grad_norm": 0.4384012222290039, | |
| "learning_rate": 1.5540899959187727e-09, | |
| "loss": 0.33990615606307983, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "step": 140, | |
| "total_flos": 176709791449088.0, | |
| "train_loss": 0.5040165311523847, | |
| "train_runtime": 10726.5297, | |
| "train_samples_per_second": 0.619, | |
| "train_steps_per_second": 0.013 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 140, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 5, | |
| "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": 176709791449088.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |