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-no-thinking with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use eth-sri/kodcode-v1-qwq-no-thinking with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="eth-sri/kodcode-v1-qwq-no-thinking", device_map="auto") 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-no-thinking") model = AutoModelForCausalLM.from_pretrained("eth-sri/kodcode-v1-qwq-no-thinking", 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 eth-sri/kodcode-v1-qwq-no-thinking 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-no-thinking" # 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-no-thinking", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/eth-sri/kodcode-v1-qwq-no-thinking
- SGLang
How to use eth-sri/kodcode-v1-qwq-no-thinking 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-no-thinking" \ --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-no-thinking", "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-no-thinking" \ --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-no-thinking", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use eth-sri/kodcode-v1-qwq-no-thinking with Docker Model Runner:
docker model run hf.co/eth-sri/kodcode-v1-qwq-no-thinking
| { | |
| "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": 8.887484550476074, | |
| "learning_rate": 0.0, | |
| "loss": 0.5914468765258789, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.07228915662650602, | |
| "grad_norm": 8.353597640991211, | |
| "learning_rate": 1.111111111111111e-06, | |
| "loss": 0.620003342628479, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.10843373493975904, | |
| "grad_norm": 9.017178535461426, | |
| "learning_rate": 2.222222222222222e-06, | |
| "loss": 0.5764777660369873, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.14457831325301204, | |
| "grad_norm": 6.198811054229736, | |
| "learning_rate": 3.3333333333333333e-06, | |
| "loss": 0.5356950163841248, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.18072289156626506, | |
| "grad_norm": 4.334223747253418, | |
| "learning_rate": 4.444444444444444e-06, | |
| "loss": 0.4751540422439575, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.21686746987951808, | |
| "grad_norm": 2.49684476852417, | |
| "learning_rate": 5.555555555555557e-06, | |
| "loss": 0.4185207486152649, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.25301204819277107, | |
| "grad_norm": 1.7279225587844849, | |
| "learning_rate": 6.666666666666667e-06, | |
| "loss": 0.4058915078639984, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.2891566265060241, | |
| "grad_norm": 1.5181468725204468, | |
| "learning_rate": 7.77777777777778e-06, | |
| "loss": 0.4257166087627411, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.3253012048192771, | |
| "grad_norm": 1.608017086982727, | |
| "learning_rate": 8.888888888888888e-06, | |
| "loss": 0.4216555953025818, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.3614457831325301, | |
| "grad_norm": 1.895369052886963, | |
| "learning_rate": 1e-05, | |
| "loss": 0.4374157786369324, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.39759036144578314, | |
| "grad_norm": 1.3696216344833374, | |
| "learning_rate": 9.995614150494293e-06, | |
| "loss": 0.39124733209609985, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.43373493975903615, | |
| "grad_norm": 1.243646264076233, | |
| "learning_rate": 9.982464296247523e-06, | |
| "loss": 0.36318010091781616, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.46987951807228917, | |
| "grad_norm": 1.0504814386367798, | |
| "learning_rate": 9.960573506572391e-06, | |
| "loss": 0.3158777356147766, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.5060240963855421, | |
| "grad_norm": 1.2085658311843872, | |
| "learning_rate": 9.929980185352525e-06, | |
| "loss": 0.3739868104457855, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.5421686746987951, | |
| "grad_norm": 1.0851548910140991, | |
| "learning_rate": 9.890738003669029e-06, | |
| "loss": 0.3323063850402832, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.5783132530120482, | |
| "grad_norm": 1.3548555374145508, | |
| "learning_rate": 9.842915805643156e-06, | |
| "loss": 0.3619411587715149, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.6144578313253012, | |
| "grad_norm": 1.1331850290298462, | |
| "learning_rate": 9.786597487660336e-06, | |
| "loss": 0.3434302806854248, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.6506024096385542, | |
| "grad_norm": 1.1485708951950073, | |
| "learning_rate": 9.721881851187406e-06, | |
| "loss": 0.35868388414382935, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.6867469879518072, | |
| "grad_norm": 0.9797462224960327, | |
| "learning_rate": 9.648882429441258e-06, | |
| "loss": 0.30607205629348755, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.7228915662650602, | |
| "grad_norm": 0.9305843710899353, | |
| "learning_rate": 9.567727288213005e-06, | |
| "loss": 0.30613967776298523, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.7590361445783133, | |
| "grad_norm": 1.2538716793060303, | |
| "learning_rate": 9.478558801197065e-06, | |
| "loss": 0.34786176681518555, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.7951807228915663, | |
| "grad_norm": 1.1796234846115112, | |
| "learning_rate": 9.381533400219319e-06, | |
| "loss": 0.30188339948654175, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.8313253012048193, | |
| "grad_norm": 0.9115185141563416, | |
| "learning_rate": 9.276821300802535e-06, | |
| "loss": 0.2840030789375305, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.8674698795180723, | |
| "grad_norm": 1.0928308963775635, | |
| "learning_rate": 9.164606203550498e-06, | |
| "loss": 0.36419373750686646, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.9036144578313253, | |
| "grad_norm": 0.9435914754867554, | |
| "learning_rate": 9.045084971874738e-06, | |
| "loss": 0.31879815459251404, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.9397590361445783, | |
| "grad_norm": 1.042055368423462, | |
| "learning_rate": 8.9184672866292e-06, | |
| "loss": 0.34760189056396484, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.9759036144578314, | |
| "grad_norm": 1.034004807472229, | |
| "learning_rate": 8.784975278258783e-06, | |
| "loss": 0.3489612340927124, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 1.374064564704895, | |
| "learning_rate": 8.644843137107058e-06, | |
| "loss": 0.4119997024536133, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 1.036144578313253, | |
| "grad_norm": 0.8877686262130737, | |
| "learning_rate": 8.498316702566828e-06, | |
| "loss": 0.23063668608665466, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 1.072289156626506, | |
| "grad_norm": 0.8385362029075623, | |
| "learning_rate": 8.345653031794292e-06, | |
| "loss": 0.18012019991874695, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.108433734939759, | |
| "grad_norm": 0.8199275135993958, | |
| "learning_rate": 8.18711994874345e-06, | |
| "loss": 0.20231494307518005, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 1.144578313253012, | |
| "grad_norm": 0.8524110317230225, | |
| "learning_rate": 8.022995574311876e-06, | |
| "loss": 0.17479273676872253, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 1.180722891566265, | |
| "grad_norm": 0.8740944862365723, | |
| "learning_rate": 7.85356783842216e-06, | |
| "loss": 0.20290827751159668, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 1.216867469879518, | |
| "grad_norm": 1.6095167398452759, | |
| "learning_rate": 7.679133974894984e-06, | |
| "loss": 0.19930751621723175, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 1.2530120481927711, | |
| "grad_norm": 0.8441895842552185, | |
| "learning_rate": 7.500000000000001e-06, | |
| "loss": 0.17364069819450378, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 1.2891566265060241, | |
| "grad_norm": 0.8886516094207764, | |
| "learning_rate": 7.31648017559931e-06, | |
| "loss": 0.1886671483516693, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 1.3253012048192772, | |
| "grad_norm": 0.9423007965087891, | |
| "learning_rate": 7.128896457825364e-06, | |
| "loss": 0.2068309485912323, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 1.3614457831325302, | |
| "grad_norm": 0.7958769798278809, | |
| "learning_rate": 6.9375779322605154e-06, | |
| "loss": 0.13852755725383759, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 1.3975903614457832, | |
| "grad_norm": 0.8663837909698486, | |
| "learning_rate": 6.7428602366090764e-06, | |
| "loss": 0.16718754172325134, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 1.4337349397590362, | |
| "grad_norm": 0.9105899333953857, | |
| "learning_rate": 6.545084971874738e-06, | |
| "loss": 0.16156896948814392, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.4698795180722892, | |
| "grad_norm": 0.8959738612174988, | |
| "learning_rate": 6.344599103076329e-06, | |
| "loss": 0.14004361629486084, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 1.5060240963855422, | |
| "grad_norm": 0.7533515691757202, | |
| "learning_rate": 6.141754350553279e-06, | |
| "loss": 0.12352561950683594, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 1.5421686746987953, | |
| "grad_norm": 0.8931336402893066, | |
| "learning_rate": 5.936906572928625e-06, | |
| "loss": 0.16318686306476593, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 1.5783132530120483, | |
| "grad_norm": 0.8921841382980347, | |
| "learning_rate": 5.730415142812059e-06, | |
| "loss": 0.17240172624588013, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 1.6144578313253013, | |
| "grad_norm": 1.0797544717788696, | |
| "learning_rate": 5.522642316338268e-06, | |
| "loss": 0.17317631840705872, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 1.6506024096385543, | |
| "grad_norm": 1.0078191757202148, | |
| "learning_rate": 5.3139525976465675e-06, | |
| "loss": 0.2157416045665741, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 1.6867469879518073, | |
| "grad_norm": 0.8438640236854553, | |
| "learning_rate": 5.1047120994167855e-06, | |
| "loss": 0.16403160989284515, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 1.7228915662650603, | |
| "grad_norm": 0.9475386738777161, | |
| "learning_rate": 4.895287900583216e-06, | |
| "loss": 0.15586617588996887, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 1.7590361445783134, | |
| "grad_norm": 0.9450883865356445, | |
| "learning_rate": 4.686047402353433e-06, | |
| "loss": 0.18724647164344788, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 1.7951807228915664, | |
| "grad_norm": 0.7867273092269897, | |
| "learning_rate": 4.477357683661734e-06, | |
| "loss": 0.16307249665260315, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.8313253012048194, | |
| "grad_norm": 0.8388890624046326, | |
| "learning_rate": 4.269584857187942e-06, | |
| "loss": 0.16206401586532593, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 1.8674698795180724, | |
| "grad_norm": 0.9560278058052063, | |
| "learning_rate": 4.063093427071376e-06, | |
| "loss": 0.19236278533935547, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 1.9036144578313254, | |
| "grad_norm": 0.8729760646820068, | |
| "learning_rate": 3.8582456494467214e-06, | |
| "loss": 0.14955267310142517, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 1.9397590361445785, | |
| "grad_norm": 0.9571371674537659, | |
| "learning_rate": 3.655400896923672e-06, | |
| "loss": 0.15187832713127136, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 1.9759036144578315, | |
| "grad_norm": 0.8457008004188538, | |
| "learning_rate": 3.4549150281252635e-06, | |
| "loss": 0.12991125881671906, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 1.1152817010879517, | |
| "learning_rate": 3.2571397633909252e-06, | |
| "loss": 0.17669421434402466, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 2.036144578313253, | |
| "grad_norm": 0.7974763512611389, | |
| "learning_rate": 3.0624220677394854e-06, | |
| "loss": 0.08793318271636963, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 2.072289156626506, | |
| "grad_norm": 0.7382637858390808, | |
| "learning_rate": 2.871103542174637e-06, | |
| "loss": 0.07762216031551361, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 2.108433734939759, | |
| "grad_norm": 0.7654367089271545, | |
| "learning_rate": 2.683519824400693e-06, | |
| "loss": 0.07498644292354584, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 2.144578313253012, | |
| "grad_norm": 0.6648955941200256, | |
| "learning_rate": 2.5000000000000015e-06, | |
| "loss": 0.0681481808423996, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 2.180722891566265, | |
| "grad_norm": 0.7282518148422241, | |
| "learning_rate": 2.320866025105016e-06, | |
| "loss": 0.07515449821949005, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 2.216867469879518, | |
| "grad_norm": 0.684374988079071, | |
| "learning_rate": 2.146432161577842e-06, | |
| "loss": 0.07506850361824036, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 2.253012048192771, | |
| "grad_norm": 0.6030347347259521, | |
| "learning_rate": 1.977004425688126e-06, | |
| "loss": 0.06140301376581192, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 2.289156626506024, | |
| "grad_norm": 0.6093411445617676, | |
| "learning_rate": 1.8128800512565514e-06, | |
| "loss": 0.0682184174656868, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 2.325301204819277, | |
| "grad_norm": 0.5749672651290894, | |
| "learning_rate": 1.6543469682057105e-06, | |
| "loss": 0.05725966393947601, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 2.36144578313253, | |
| "grad_norm": 0.5785587430000305, | |
| "learning_rate": 1.5016832974331725e-06, | |
| "loss": 0.05954214185476303, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 2.397590361445783, | |
| "grad_norm": 0.8381079435348511, | |
| "learning_rate": 1.3551568628929434e-06, | |
| "loss": 0.10542360693216324, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 2.433734939759036, | |
| "grad_norm": 0.5842990875244141, | |
| "learning_rate": 1.2150247217412186e-06, | |
| "loss": 0.0604025200009346, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 2.4698795180722892, | |
| "grad_norm": 0.6028868556022644, | |
| "learning_rate": 1.0815327133708015e-06, | |
| "loss": 0.055375128984451294, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 2.5060240963855422, | |
| "grad_norm": 0.7340065240859985, | |
| "learning_rate": 9.549150281252633e-07, | |
| "loss": 0.060119662433862686, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 2.5421686746987953, | |
| "grad_norm": 0.64606773853302, | |
| "learning_rate": 8.353937964495029e-07, | |
| "loss": 0.05360941216349602, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 2.5783132530120483, | |
| "grad_norm": 1.2324352264404297, | |
| "learning_rate": 7.23178699197467e-07, | |
| "loss": 0.06335519999265671, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 2.6144578313253013, | |
| "grad_norm": 0.6813722252845764, | |
| "learning_rate": 6.184665997806832e-07, | |
| "loss": 0.05561135709285736, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 2.6506024096385543, | |
| "grad_norm": 0.674095869064331, | |
| "learning_rate": 5.214411988029355e-07, | |
| "loss": 0.05392349511384964, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 2.6867469879518073, | |
| "grad_norm": 0.7264373302459717, | |
| "learning_rate": 4.322727117869951e-07, | |
| "loss": 0.05505981296300888, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 2.7228915662650603, | |
| "grad_norm": 0.5850496888160706, | |
| "learning_rate": 3.511175705587433e-07, | |
| "loss": 0.047852493822574615, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 2.7590361445783134, | |
| "grad_norm": 0.7429664731025696, | |
| "learning_rate": 2.7811814881259503e-07, | |
| "loss": 0.058224525302648544, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 2.7951807228915664, | |
| "grad_norm": 0.6747693419456482, | |
| "learning_rate": 2.134025123396638e-07, | |
| "loss": 0.0484314039349556, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 2.8313253012048194, | |
| "grad_norm": 0.5850451588630676, | |
| "learning_rate": 1.5708419435684463e-07, | |
| "loss": 0.053738657385110855, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 2.8674698795180724, | |
| "grad_norm": 0.6748908758163452, | |
| "learning_rate": 1.0926199633097156e-07, | |
| "loss": 0.06110052019357681, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 2.9036144578313254, | |
| "grad_norm": 0.6493048667907715, | |
| "learning_rate": 7.001981464747565e-08, | |
| "loss": 0.05294954404234886, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 2.9397590361445785, | |
| "grad_norm": 0.6188032031059265, | |
| "learning_rate": 3.9426493427611177e-08, | |
| "loss": 0.0478922538459301, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 2.9759036144578315, | |
| "grad_norm": 1.050648808479309, | |
| "learning_rate": 1.753570375247815e-08, | |
| "loss": 0.060055799782276154, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "grad_norm": 0.9005938172340393, | |
| "learning_rate": 4.385849505708084e-09, | |
| "loss": 0.04742509871721268, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "step": 84, | |
| "total_flos": 15361915846656.0, | |
| "train_loss": 0.21046775437536694, | |
| "train_runtime": 4346.6476, | |
| "train_samples_per_second": 0.916, | |
| "train_steps_per_second": 0.019 | |
| } | |
| ], | |
| "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": 15361915846656.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |