Text Generation
Transformers
Safetensors
qwen2
Generated from Trainer
trl
sft
conversational
text-generation-inference
Instructions to use bujiangwude/Qwen2.5-1.5B-Open-R1-Distill with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use bujiangwude/Qwen2.5-1.5B-Open-R1-Distill with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="bujiangwude/Qwen2.5-1.5B-Open-R1-Distill") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("bujiangwude/Qwen2.5-1.5B-Open-R1-Distill") model = AutoModelForCausalLM.from_pretrained("bujiangwude/Qwen2.5-1.5B-Open-R1-Distill", 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 bujiangwude/Qwen2.5-1.5B-Open-R1-Distill with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "bujiangwude/Qwen2.5-1.5B-Open-R1-Distill" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "bujiangwude/Qwen2.5-1.5B-Open-R1-Distill", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/bujiangwude/Qwen2.5-1.5B-Open-R1-Distill
- SGLang
How to use bujiangwude/Qwen2.5-1.5B-Open-R1-Distill 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 "bujiangwude/Qwen2.5-1.5B-Open-R1-Distill" \ --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": "bujiangwude/Qwen2.5-1.5B-Open-R1-Distill", "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 "bujiangwude/Qwen2.5-1.5B-Open-R1-Distill" \ --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": "bujiangwude/Qwen2.5-1.5B-Open-R1-Distill", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use bujiangwude/Qwen2.5-1.5B-Open-R1-Distill with Docker Model Runner:
docker model run hf.co/bujiangwude/Qwen2.5-1.5B-Open-R1-Distill
| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "eval_steps": 500, | |
| "global_step": 1052, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.004752851711026616, | |
| "grad_norm": 2.0294264258310872, | |
| "learning_rate": 4.716981132075472e-06, | |
| "loss": 0.84, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.009505703422053232, | |
| "grad_norm": 1.5819741340116944, | |
| "learning_rate": 9.433962264150944e-06, | |
| "loss": 0.7913, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.014258555133079848, | |
| "grad_norm": 1.0038510210237819, | |
| "learning_rate": 1.4150943396226415e-05, | |
| "loss": 0.7389, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.019011406844106463, | |
| "grad_norm": 0.553521822876252, | |
| "learning_rate": 1.8867924528301888e-05, | |
| "loss": 0.6913, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.02376425855513308, | |
| "grad_norm": 0.41841272203201746, | |
| "learning_rate": 2.358490566037736e-05, | |
| "loss": 0.665, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.028517110266159697, | |
| "grad_norm": 0.34966785034344605, | |
| "learning_rate": 2.830188679245283e-05, | |
| "loss": 0.6437, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.03326996197718631, | |
| "grad_norm": 0.2633470933765066, | |
| "learning_rate": 3.30188679245283e-05, | |
| "loss": 0.622, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.03802281368821293, | |
| "grad_norm": 0.2472576100582917, | |
| "learning_rate": 3.7735849056603776e-05, | |
| "loss": 0.6158, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.04277566539923954, | |
| "grad_norm": 0.2554056225725403, | |
| "learning_rate": 4.245283018867925e-05, | |
| "loss": 0.6038, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.04752851711026616, | |
| "grad_norm": 0.24052219882208087, | |
| "learning_rate": 4.716981132075472e-05, | |
| "loss": 0.5946, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.05228136882129278, | |
| "grad_norm": 0.5209729340348995, | |
| "learning_rate": 4.9999554979670374e-05, | |
| "loss": 0.5919, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.057034220532319393, | |
| "grad_norm": 0.4171392382535492, | |
| "learning_rate": 4.999454870312887e-05, | |
| "loss": 0.5864, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.06178707224334601, | |
| "grad_norm": 0.40949886363507565, | |
| "learning_rate": 4.998398111645765e-05, | |
| "loss": 0.5761, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.06653992395437262, | |
| "grad_norm": 0.32318894959757866, | |
| "learning_rate": 4.996785483227313e-05, | |
| "loss": 0.5756, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.07129277566539924, | |
| "grad_norm": 0.2502488320080775, | |
| "learning_rate": 4.994617383746426e-05, | |
| "loss": 0.5717, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.07604562737642585, | |
| "grad_norm": 0.39787046123511743, | |
| "learning_rate": 4.9918943492206846e-05, | |
| "loss": 0.5608, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.08079847908745247, | |
| "grad_norm": 0.4580557906084975, | |
| "learning_rate": 4.98861705286384e-05, | |
| "loss": 0.5547, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.08555133079847908, | |
| "grad_norm": 0.49941882292408263, | |
| "learning_rate": 4.984786304919372e-05, | |
| "loss": 0.5544, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.0903041825095057, | |
| "grad_norm": 0.33021368840122, | |
| "learning_rate": 4.9804030524601746e-05, | |
| "loss": 0.5598, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.09505703422053231, | |
| "grad_norm": 0.6210805063568754, | |
| "learning_rate": 4.975468379154414e-05, | |
| "loss": 0.5519, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.09980988593155894, | |
| "grad_norm": 0.41748258392562154, | |
| "learning_rate": 4.969983504997607e-05, | |
| "loss": 0.5583, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.10456273764258556, | |
| "grad_norm": 0.34385415175984796, | |
| "learning_rate": 4.9639497860110136e-05, | |
| "loss": 0.5476, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.10931558935361217, | |
| "grad_norm": 0.3146160241077058, | |
| "learning_rate": 4.9573687139063776e-05, | |
| "loss": 0.5425, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.11406844106463879, | |
| "grad_norm": 0.2615987335895406, | |
| "learning_rate": 4.950241915717142e-05, | |
| "loss": 0.5405, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.1188212927756654, | |
| "grad_norm": 0.3131275299937531, | |
| "learning_rate": 4.942571153396187e-05, | |
| "loss": 0.5408, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.12357414448669202, | |
| "grad_norm": 0.3437245423936912, | |
| "learning_rate": 4.934358323380238e-05, | |
| "loss": 0.5459, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.12832699619771862, | |
| "grad_norm": 0.4760701739771202, | |
| "learning_rate": 4.9256054561209965e-05, | |
| "loss": 0.5438, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.13307984790874525, | |
| "grad_norm": 0.35535678960662614, | |
| "learning_rate": 4.916314715583165e-05, | |
| "loss": 0.541, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.13783269961977188, | |
| "grad_norm": 0.3277124225914685, | |
| "learning_rate": 4.906488398709445e-05, | |
| "loss": 0.5408, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.14258555133079848, | |
| "grad_norm": 0.3562707058555971, | |
| "learning_rate": 4.896128934852666e-05, | |
| "loss": 0.5327, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.1473384030418251, | |
| "grad_norm": 0.4937003161837994, | |
| "learning_rate": 4.885238885175182e-05, | |
| "loss": 0.5338, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 0.1520912547528517, | |
| "grad_norm": 0.33800072322981234, | |
| "learning_rate": 4.8738209420156746e-05, | |
| "loss": 0.5395, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.15684410646387834, | |
| "grad_norm": 0.3208834491980559, | |
| "learning_rate": 4.861877928223526e-05, | |
| "loss": 0.531, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 0.16159695817490494, | |
| "grad_norm": 0.3927389297905036, | |
| "learning_rate": 4.849412796460934e-05, | |
| "loss": 0.5258, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.16634980988593157, | |
| "grad_norm": 0.41074477546320726, | |
| "learning_rate": 4.8364286284729226e-05, | |
| "loss": 0.5242, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.17110266159695817, | |
| "grad_norm": 0.3626699188831102, | |
| "learning_rate": 4.822928634325447e-05, | |
| "loss": 0.5225, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.1758555133079848, | |
| "grad_norm": 0.28646084272624744, | |
| "learning_rate": 4.808916151611769e-05, | |
| "loss": 0.5289, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 0.1806083650190114, | |
| "grad_norm": 0.39899659924925285, | |
| "learning_rate": 4.79439464462731e-05, | |
| "loss": 0.5271, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.18536121673003803, | |
| "grad_norm": 0.36080484103544197, | |
| "learning_rate": 4.7793677035131715e-05, | |
| "loss": 0.5336, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 0.19011406844106463, | |
| "grad_norm": 0.402258230700785, | |
| "learning_rate": 4.7638390433685525e-05, | |
| "loss": 0.5175, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.19486692015209126, | |
| "grad_norm": 0.3489040778365625, | |
| "learning_rate": 4.747812503332264e-05, | |
| "loss": 0.5251, | |
| "step": 205 | |
| }, | |
| { | |
| "epoch": 0.19961977186311788, | |
| "grad_norm": 0.3025455966185667, | |
| "learning_rate": 4.731292045633583e-05, | |
| "loss": 0.5251, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.20437262357414449, | |
| "grad_norm": 0.3346044155583185, | |
| "learning_rate": 4.7142817546126734e-05, | |
| "loss": 0.5211, | |
| "step": 215 | |
| }, | |
| { | |
| "epoch": 0.20912547528517111, | |
| "grad_norm": 0.3200713216890938, | |
| "learning_rate": 4.696785835710818e-05, | |
| "loss": 0.5199, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.21387832699619772, | |
| "grad_norm": 0.3167526637814306, | |
| "learning_rate": 4.678808614430713e-05, | |
| "loss": 0.525, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 0.21863117870722434, | |
| "grad_norm": 0.2840588339203045, | |
| "learning_rate": 4.6603545352670704e-05, | |
| "loss": 0.5174, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.22338403041825095, | |
| "grad_norm": 0.3257177568939882, | |
| "learning_rate": 4.641428160607816e-05, | |
| "loss": 0.515, | |
| "step": 235 | |
| }, | |
| { | |
| "epoch": 0.22813688212927757, | |
| "grad_norm": 0.24544439139994834, | |
| "learning_rate": 4.6220341696061306e-05, | |
| "loss": 0.5229, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.23288973384030418, | |
| "grad_norm": 0.2449982597044802, | |
| "learning_rate": 4.602177357023627e-05, | |
| "loss": 0.5087, | |
| "step": 245 | |
| }, | |
| { | |
| "epoch": 0.2376425855513308, | |
| "grad_norm": 0.3049373617439893, | |
| "learning_rate": 4.581862632044944e-05, | |
| "loss": 0.5126, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.2423954372623574, | |
| "grad_norm": 0.39789506934114666, | |
| "learning_rate": 4.561095017064054e-05, | |
| "loss": 0.5099, | |
| "step": 255 | |
| }, | |
| { | |
| "epoch": 0.24714828897338403, | |
| "grad_norm": 0.34743031583761214, | |
| "learning_rate": 4.539879646442577e-05, | |
| "loss": 0.5117, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.25190114068441066, | |
| "grad_norm": 0.2890032465476798, | |
| "learning_rate": 4.518221765240423e-05, | |
| "loss": 0.514, | |
| "step": 265 | |
| }, | |
| { | |
| "epoch": 0.25665399239543724, | |
| "grad_norm": 0.2817278692067567, | |
| "learning_rate": 4.4961267279190525e-05, | |
| "loss": 0.5098, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.26140684410646386, | |
| "grad_norm": 0.24952552305010012, | |
| "learning_rate": 4.473599997017701e-05, | |
| "loss": 0.5148, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 0.2661596958174905, | |
| "grad_norm": 0.32166227921940277, | |
| "learning_rate": 4.450647141802877e-05, | |
| "loss": 0.5078, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.2709125475285171, | |
| "grad_norm": 0.3156193011366242, | |
| "learning_rate": 4.427273836891482e-05, | |
| "loss": 0.5035, | |
| "step": 285 | |
| }, | |
| { | |
| "epoch": 0.27566539923954375, | |
| "grad_norm": 0.25260427489554643, | |
| "learning_rate": 4.4034858608478714e-05, | |
| "loss": 0.506, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.2804182509505703, | |
| "grad_norm": 0.2795952948317014, | |
| "learning_rate": 4.3792890947552304e-05, | |
| "loss": 0.5099, | |
| "step": 295 | |
| }, | |
| { | |
| "epoch": 0.28517110266159695, | |
| "grad_norm": 0.24428176004118773, | |
| "learning_rate": 4.354689520761598e-05, | |
| "loss": 0.5077, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.2899239543726236, | |
| "grad_norm": 0.2315548630003516, | |
| "learning_rate": 4.3296932206009014e-05, | |
| "loss": 0.504, | |
| "step": 305 | |
| }, | |
| { | |
| "epoch": 0.2946768060836502, | |
| "grad_norm": 0.2375447385407591, | |
| "learning_rate": 4.304306374089375e-05, | |
| "loss": 0.5067, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.2994296577946768, | |
| "grad_norm": 0.2328089313657836, | |
| "learning_rate": 4.278535257597732e-05, | |
| "loss": 0.5026, | |
| "step": 315 | |
| }, | |
| { | |
| "epoch": 0.3041825095057034, | |
| "grad_norm": 0.3145988517099384, | |
| "learning_rate": 4.2523862424994584e-05, | |
| "loss": 0.5023, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.30893536121673004, | |
| "grad_norm": 0.2570030080739303, | |
| "learning_rate": 4.225865793595627e-05, | |
| "loss": 0.5024, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 0.31368821292775667, | |
| "grad_norm": 0.3273896281685418, | |
| "learning_rate": 4.198980467516604e-05, | |
| "loss": 0.5007, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.31844106463878324, | |
| "grad_norm": 0.24913853861759183, | |
| "learning_rate": 4.1717369111010624e-05, | |
| "loss": 0.5046, | |
| "step": 335 | |
| }, | |
| { | |
| "epoch": 0.3231939163498099, | |
| "grad_norm": 0.21385386970309092, | |
| "learning_rate": 4.14414185975269e-05, | |
| "loss": 0.5081, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.3279467680608365, | |
| "grad_norm": 0.2690469796799476, | |
| "learning_rate": 4.116202135774996e-05, | |
| "loss": 0.4979, | |
| "step": 345 | |
| }, | |
| { | |
| "epoch": 0.33269961977186313, | |
| "grad_norm": 0.21536931123577147, | |
| "learning_rate": 4.087924646684646e-05, | |
| "loss": 0.5066, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.33745247148288976, | |
| "grad_norm": 0.2565952556732812, | |
| "learning_rate": 4.059316383503709e-05, | |
| "loss": 0.4977, | |
| "step": 355 | |
| }, | |
| { | |
| "epoch": 0.34220532319391633, | |
| "grad_norm": 0.25720760226654493, | |
| "learning_rate": 4.0303844190312886e-05, | |
| "loss": 0.4994, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.34695817490494296, | |
| "grad_norm": 0.22300681191570793, | |
| "learning_rate": 4.001135906094907e-05, | |
| "loss": 0.5018, | |
| "step": 365 | |
| }, | |
| { | |
| "epoch": 0.3517110266159696, | |
| "grad_norm": 0.21457447224312087, | |
| "learning_rate": 3.971578075782124e-05, | |
| "loss": 0.5014, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.3564638783269962, | |
| "grad_norm": 0.28861039160678303, | |
| "learning_rate": 3.941718235652797e-05, | |
| "loss": 0.5013, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 0.3612167300380228, | |
| "grad_norm": 0.23803488760707342, | |
| "learning_rate": 3.9115637679324405e-05, | |
| "loss": 0.4895, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.3659695817490494, | |
| "grad_norm": 0.2359381054663395, | |
| "learning_rate": 3.881122127687124e-05, | |
| "loss": 0.5027, | |
| "step": 385 | |
| }, | |
| { | |
| "epoch": 0.37072243346007605, | |
| "grad_norm": 0.2489815851326379, | |
| "learning_rate": 3.850400840980363e-05, | |
| "loss": 0.4991, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.3754752851711027, | |
| "grad_norm": 0.253055371710663, | |
| "learning_rate": 3.819407503012453e-05, | |
| "loss": 0.4994, | |
| "step": 395 | |
| }, | |
| { | |
| "epoch": 0.38022813688212925, | |
| "grad_norm": 0.23689623513578092, | |
| "learning_rate": 3.788149776242714e-05, | |
| "loss": 0.4971, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.3849809885931559, | |
| "grad_norm": 0.22650332728993752, | |
| "learning_rate": 3.756635388495111e-05, | |
| "loss": 0.4924, | |
| "step": 405 | |
| }, | |
| { | |
| "epoch": 0.3897338403041825, | |
| "grad_norm": 0.2645793623141659, | |
| "learning_rate": 3.7248721310477046e-05, | |
| "loss": 0.4964, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.39448669201520914, | |
| "grad_norm": 0.24057911691260406, | |
| "learning_rate": 3.692867856706422e-05, | |
| "loss": 0.4936, | |
| "step": 415 | |
| }, | |
| { | |
| "epoch": 0.39923954372623577, | |
| "grad_norm": 0.24646093805548094, | |
| "learning_rate": 3.6606304778636155e-05, | |
| "loss": 0.4892, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.40399239543726234, | |
| "grad_norm": 0.19915279845501596, | |
| "learning_rate": 3.628167964541883e-05, | |
| "loss": 0.4977, | |
| "step": 425 | |
| }, | |
| { | |
| "epoch": 0.40874524714828897, | |
| "grad_norm": 0.21655491244085093, | |
| "learning_rate": 3.5954883424236476e-05, | |
| "loss": 0.5012, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.4134980988593156, | |
| "grad_norm": 0.22238235727042324, | |
| "learning_rate": 3.5625996908669776e-05, | |
| "loss": 0.4973, | |
| "step": 435 | |
| }, | |
| { | |
| "epoch": 0.41825095057034223, | |
| "grad_norm": 0.22253929749056056, | |
| "learning_rate": 3.529510140908129e-05, | |
| "loss": 0.4936, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.4230038022813688, | |
| "grad_norm": 0.2503425568915126, | |
| "learning_rate": 3.496227873251313e-05, | |
| "loss": 0.4885, | |
| "step": 445 | |
| }, | |
| { | |
| "epoch": 0.42775665399239543, | |
| "grad_norm": 0.24202694522633986, | |
| "learning_rate": 3.462761116246197e-05, | |
| "loss": 0.4959, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.43250950570342206, | |
| "grad_norm": 0.27996803189105723, | |
| "learning_rate": 3.429118143853603e-05, | |
| "loss": 0.4925, | |
| "step": 455 | |
| }, | |
| { | |
| "epoch": 0.4372623574144487, | |
| "grad_norm": 0.21769144894425693, | |
| "learning_rate": 3.3953072735999534e-05, | |
| "loss": 0.4857, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.44201520912547526, | |
| "grad_norm": 0.21760666543297144, | |
| "learning_rate": 3.3613368645209294e-05, | |
| "loss": 0.4901, | |
| "step": 465 | |
| }, | |
| { | |
| "epoch": 0.4467680608365019, | |
| "grad_norm": 0.25422156349497405, | |
| "learning_rate": 3.327215315094872e-05, | |
| "loss": 0.4898, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 0.4515209125475285, | |
| "grad_norm": 0.23674958223473902, | |
| "learning_rate": 3.292951061166438e-05, | |
| "loss": 0.4938, | |
| "step": 475 | |
| }, | |
| { | |
| "epoch": 0.45627376425855515, | |
| "grad_norm": 0.18190579290778722, | |
| "learning_rate": 3.2585525738610104e-05, | |
| "loss": 0.4863, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.4610266159695818, | |
| "grad_norm": 0.20428871875902296, | |
| "learning_rate": 3.224028357490384e-05, | |
| "loss": 0.4795, | |
| "step": 485 | |
| }, | |
| { | |
| "epoch": 0.46577946768060835, | |
| "grad_norm": 0.20651897116727513, | |
| "learning_rate": 3.1893869474502577e-05, | |
| "loss": 0.4881, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 0.470532319391635, | |
| "grad_norm": 0.18405563560363847, | |
| "learning_rate": 3.15463690811003e-05, | |
| "loss": 0.4882, | |
| "step": 495 | |
| }, | |
| { | |
| "epoch": 0.4752851711026616, | |
| "grad_norm": 0.19313108818672595, | |
| "learning_rate": 3.119786830695439e-05, | |
| "loss": 0.4893, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.48003802281368824, | |
| "grad_norm": 0.2236561344753686, | |
| "learning_rate": 3.0848453311645606e-05, | |
| "loss": 0.4899, | |
| "step": 505 | |
| }, | |
| { | |
| "epoch": 0.4847908745247148, | |
| "grad_norm": 0.2596164174926074, | |
| "learning_rate": 3.0498210480776896e-05, | |
| "loss": 0.4855, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 0.48954372623574144, | |
| "grad_norm": 0.18985887435574203, | |
| "learning_rate": 3.0147226404616363e-05, | |
| "loss": 0.4877, | |
| "step": 515 | |
| }, | |
| { | |
| "epoch": 0.49429657794676807, | |
| "grad_norm": 0.2502857940726596, | |
| "learning_rate": 2.9795587856689646e-05, | |
| "loss": 0.4871, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 0.4990494296577947, | |
| "grad_norm": 0.2235533200319138, | |
| "learning_rate": 2.9443381772326896e-05, | |
| "loss": 0.4901, | |
| "step": 525 | |
| }, | |
| { | |
| "epoch": 0.5038022813688213, | |
| "grad_norm": 0.20042233595283462, | |
| "learning_rate": 2.9090695227169878e-05, | |
| "loss": 0.4821, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 0.5085551330798479, | |
| "grad_norm": 0.22207944705416413, | |
| "learning_rate": 2.8737615415644348e-05, | |
| "loss": 0.4802, | |
| "step": 535 | |
| }, | |
| { | |
| "epoch": 0.5133079847908745, | |
| "grad_norm": 0.21080450139886084, | |
| "learning_rate": 2.8384229629402954e-05, | |
| "loss": 0.4847, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 0.5180608365019012, | |
| "grad_norm": 0.2393801297575582, | |
| "learning_rate": 2.8030625235744286e-05, | |
| "loss": 0.4837, | |
| "step": 545 | |
| }, | |
| { | |
| "epoch": 0.5228136882129277, | |
| "grad_norm": 0.2381109388094313, | |
| "learning_rate": 2.7676889656013037e-05, | |
| "loss": 0.4866, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.5275665399239544, | |
| "grad_norm": 0.19284005882529998, | |
| "learning_rate": 2.7323110343986968e-05, | |
| "loss": 0.4825, | |
| "step": 555 | |
| }, | |
| { | |
| "epoch": 0.532319391634981, | |
| "grad_norm": 0.18972810608196283, | |
| "learning_rate": 2.6969374764255723e-05, | |
| "loss": 0.4839, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 0.5370722433460076, | |
| "grad_norm": 0.23216160740500888, | |
| "learning_rate": 2.6615770370597048e-05, | |
| "loss": 0.4866, | |
| "step": 565 | |
| }, | |
| { | |
| "epoch": 0.5418250950570342, | |
| "grad_norm": 0.20174577405862335, | |
| "learning_rate": 2.626238458435566e-05, | |
| "loss": 0.4862, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 0.5465779467680608, | |
| "grad_norm": 0.19712069940074703, | |
| "learning_rate": 2.5909304772830124e-05, | |
| "loss": 0.4857, | |
| "step": 575 | |
| }, | |
| { | |
| "epoch": 0.5513307984790875, | |
| "grad_norm": 0.2366210097242305, | |
| "learning_rate": 2.5556618227673113e-05, | |
| "loss": 0.4773, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 0.5560836501901141, | |
| "grad_norm": 0.19394043523580784, | |
| "learning_rate": 2.5204412143310363e-05, | |
| "loss": 0.4783, | |
| "step": 585 | |
| }, | |
| { | |
| "epoch": 0.5608365019011406, | |
| "grad_norm": 0.1896222208574829, | |
| "learning_rate": 2.485277359538364e-05, | |
| "loss": 0.4831, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 0.5655893536121673, | |
| "grad_norm": 0.19599034125762993, | |
| "learning_rate": 2.4501789519223105e-05, | |
| "loss": 0.4855, | |
| "step": 595 | |
| }, | |
| { | |
| "epoch": 0.5703422053231939, | |
| "grad_norm": 0.16974123550830877, | |
| "learning_rate": 2.4151546688354403e-05, | |
| "loss": 0.4812, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.5750950570342205, | |
| "grad_norm": 0.22692336197847035, | |
| "learning_rate": 2.3802131693045622e-05, | |
| "loss": 0.4762, | |
| "step": 605 | |
| }, | |
| { | |
| "epoch": 0.5798479087452472, | |
| "grad_norm": 0.22998735324132835, | |
| "learning_rate": 2.3453630918899706e-05, | |
| "loss": 0.4809, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 0.5846007604562737, | |
| "grad_norm": 0.2168664598625493, | |
| "learning_rate": 2.3106130525497432e-05, | |
| "loss": 0.4845, | |
| "step": 615 | |
| }, | |
| { | |
| "epoch": 0.5893536121673004, | |
| "grad_norm": 0.20885275245463936, | |
| "learning_rate": 2.275971642509617e-05, | |
| "loss": 0.4841, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 0.594106463878327, | |
| "grad_norm": 0.1925790019325914, | |
| "learning_rate": 2.24144742613899e-05, | |
| "loss": 0.471, | |
| "step": 625 | |
| }, | |
| { | |
| "epoch": 0.5988593155893536, | |
| "grad_norm": 0.18922075262052865, | |
| "learning_rate": 2.207048938833562e-05, | |
| "loss": 0.4772, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 0.6036121673003803, | |
| "grad_norm": 0.18699071080172655, | |
| "learning_rate": 2.1727846849051293e-05, | |
| "loss": 0.4828, | |
| "step": 635 | |
| }, | |
| { | |
| "epoch": 0.6083650190114068, | |
| "grad_norm": 0.16482554296949878, | |
| "learning_rate": 2.1386631354790725e-05, | |
| "loss": 0.4735, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 0.6131178707224335, | |
| "grad_norm": 0.19118107030432402, | |
| "learning_rate": 2.1046927264000475e-05, | |
| "loss": 0.4784, | |
| "step": 645 | |
| }, | |
| { | |
| "epoch": 0.6178707224334601, | |
| "grad_norm": 0.18763931168597903, | |
| "learning_rate": 2.0708818561463978e-05, | |
| "loss": 0.4792, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.6226235741444867, | |
| "grad_norm": 0.18582034611943607, | |
| "learning_rate": 2.037238883753805e-05, | |
| "loss": 0.4774, | |
| "step": 655 | |
| }, | |
| { | |
| "epoch": 0.6273764258555133, | |
| "grad_norm": 0.1843088758106859, | |
| "learning_rate": 2.003772126748688e-05, | |
| "loss": 0.4735, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 0.6321292775665399, | |
| "grad_norm": 0.18885861334949494, | |
| "learning_rate": 1.9704898590918725e-05, | |
| "loss": 0.4746, | |
| "step": 665 | |
| }, | |
| { | |
| "epoch": 0.6368821292775665, | |
| "grad_norm": 0.1814696622515747, | |
| "learning_rate": 1.937400309133023e-05, | |
| "loss": 0.4772, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 0.6416349809885932, | |
| "grad_norm": 0.18244937228740285, | |
| "learning_rate": 1.9045116575763526e-05, | |
| "loss": 0.4768, | |
| "step": 675 | |
| }, | |
| { | |
| "epoch": 0.6463878326996197, | |
| "grad_norm": 0.17886547415430476, | |
| "learning_rate": 1.871832035458118e-05, | |
| "loss": 0.4783, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 0.6511406844106464, | |
| "grad_norm": 0.19043261250654717, | |
| "learning_rate": 1.8393695221363854e-05, | |
| "loss": 0.4728, | |
| "step": 685 | |
| }, | |
| { | |
| "epoch": 0.655893536121673, | |
| "grad_norm": 0.1747559107739795, | |
| "learning_rate": 1.8071321432935783e-05, | |
| "loss": 0.4708, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 0.6606463878326996, | |
| "grad_norm": 0.18036611817695825, | |
| "learning_rate": 1.7751278689522966e-05, | |
| "loss": 0.4752, | |
| "step": 695 | |
| }, | |
| { | |
| "epoch": 0.6653992395437263, | |
| "grad_norm": 0.17849983671638392, | |
| "learning_rate": 1.7433646115048898e-05, | |
| "loss": 0.4677, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.6701520912547528, | |
| "grad_norm": 0.1714769897391817, | |
| "learning_rate": 1.711850223757287e-05, | |
| "loss": 0.4794, | |
| "step": 705 | |
| }, | |
| { | |
| "epoch": 0.6749049429657795, | |
| "grad_norm": 0.1698678716478858, | |
| "learning_rate": 1.6805924969875476e-05, | |
| "loss": 0.4746, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 0.6796577946768061, | |
| "grad_norm": 0.16227527959319807, | |
| "learning_rate": 1.6495991590196367e-05, | |
| "loss": 0.4796, | |
| "step": 715 | |
| }, | |
| { | |
| "epoch": 0.6844106463878327, | |
| "grad_norm": 0.16424492377806227, | |
| "learning_rate": 1.618877872312876e-05, | |
| "loss": 0.4829, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 0.6891634980988594, | |
| "grad_norm": 0.15657397103485426, | |
| "learning_rate": 1.58843623206756e-05, | |
| "loss": 0.4779, | |
| "step": 725 | |
| }, | |
| { | |
| "epoch": 0.6939163498098859, | |
| "grad_norm": 0.17536531645621806, | |
| "learning_rate": 1.5582817643472037e-05, | |
| "loss": 0.4778, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 0.6986692015209125, | |
| "grad_norm": 0.17280065096422334, | |
| "learning_rate": 1.5284219242178765e-05, | |
| "loss": 0.4755, | |
| "step": 735 | |
| }, | |
| { | |
| "epoch": 0.7034220532319392, | |
| "grad_norm": 0.1620135171606573, | |
| "learning_rate": 1.4988640939050929e-05, | |
| "loss": 0.4728, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 0.7081749049429658, | |
| "grad_norm": 0.16662045624444577, | |
| "learning_rate": 1.4696155809687112e-05, | |
| "loss": 0.4717, | |
| "step": 745 | |
| }, | |
| { | |
| "epoch": 0.7129277566539924, | |
| "grad_norm": 0.16252733139705441, | |
| "learning_rate": 1.4406836164962911e-05, | |
| "loss": 0.4742, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.717680608365019, | |
| "grad_norm": 0.16379722089125048, | |
| "learning_rate": 1.4120753533153552e-05, | |
| "loss": 0.4783, | |
| "step": 755 | |
| }, | |
| { | |
| "epoch": 0.7224334600760456, | |
| "grad_norm": 0.16226858863808044, | |
| "learning_rate": 1.3837978642250039e-05, | |
| "loss": 0.4763, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 0.7271863117870723, | |
| "grad_norm": 0.16828084916605085, | |
| "learning_rate": 1.3558581402473108e-05, | |
| "loss": 0.4769, | |
| "step": 765 | |
| }, | |
| { | |
| "epoch": 0.7319391634980988, | |
| "grad_norm": 0.15635186380885982, | |
| "learning_rate": 1.3282630888989378e-05, | |
| "loss": 0.4691, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 0.7366920152091255, | |
| "grad_norm": 0.16014183419624511, | |
| "learning_rate": 1.3010195324833963e-05, | |
| "loss": 0.4789, | |
| "step": 775 | |
| }, | |
| { | |
| "epoch": 0.7414448669201521, | |
| "grad_norm": 0.15105521562767574, | |
| "learning_rate": 1.2741342064043732e-05, | |
| "loss": 0.4762, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 0.7461977186311787, | |
| "grad_norm": 0.14208380809510285, | |
| "learning_rate": 1.2476137575005413e-05, | |
| "loss": 0.4687, | |
| "step": 785 | |
| }, | |
| { | |
| "epoch": 0.7509505703422054, | |
| "grad_norm": 0.14214458651561737, | |
| "learning_rate": 1.221464742402268e-05, | |
| "loss": 0.4675, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 0.7557034220532319, | |
| "grad_norm": 0.13937075466612753, | |
| "learning_rate": 1.1956936259106251e-05, | |
| "loss": 0.4693, | |
| "step": 795 | |
| }, | |
| { | |
| "epoch": 0.7604562737642585, | |
| "grad_norm": 0.14392484311709713, | |
| "learning_rate": 1.1703067793990995e-05, | |
| "loss": 0.4717, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.7652091254752852, | |
| "grad_norm": 0.14935269226237555, | |
| "learning_rate": 1.1453104792384023e-05, | |
| "loss": 0.4726, | |
| "step": 805 | |
| }, | |
| { | |
| "epoch": 0.7699619771863118, | |
| "grad_norm": 0.14453043569639498, | |
| "learning_rate": 1.1207109052447693e-05, | |
| "loss": 0.4648, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 0.7747148288973384, | |
| "grad_norm": 0.1565121971468423, | |
| "learning_rate": 1.0965141391521296e-05, | |
| "loss": 0.4726, | |
| "step": 815 | |
| }, | |
| { | |
| "epoch": 0.779467680608365, | |
| "grad_norm": 0.1464026978350567, | |
| "learning_rate": 1.0727261631085189e-05, | |
| "loss": 0.4704, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 0.7842205323193916, | |
| "grad_norm": 0.14770117041095976, | |
| "learning_rate": 1.0493528581971229e-05, | |
| "loss": 0.4658, | |
| "step": 825 | |
| }, | |
| { | |
| "epoch": 0.7889733840304183, | |
| "grad_norm": 0.1535273348766141, | |
| "learning_rate": 1.0264000029822999e-05, | |
| "loss": 0.469, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 0.7937262357414449, | |
| "grad_norm": 0.16004223786581778, | |
| "learning_rate": 1.0038732720809473e-05, | |
| "loss": 0.4743, | |
| "step": 835 | |
| }, | |
| { | |
| "epoch": 0.7984790874524715, | |
| "grad_norm": 0.1425010747043446, | |
| "learning_rate": 9.817782347595766e-06, | |
| "loss": 0.4641, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 0.8032319391634981, | |
| "grad_norm": 0.15447194379864884, | |
| "learning_rate": 9.601203535574232e-06, | |
| "loss": 0.469, | |
| "step": 845 | |
| }, | |
| { | |
| "epoch": 0.8079847908745247, | |
| "grad_norm": 0.14772023539006754, | |
| "learning_rate": 9.389049829359468e-06, | |
| "loss": 0.4707, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 0.8127376425855514, | |
| "grad_norm": 0.14629799126983165, | |
| "learning_rate": 9.181373679550565e-06, | |
| "loss": 0.4714, | |
| "step": 855 | |
| }, | |
| { | |
| "epoch": 0.8174904942965779, | |
| "grad_norm": 0.15309282616218442, | |
| "learning_rate": 8.978226429763736e-06, | |
| "loss": 0.4698, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 0.8222433460076045, | |
| "grad_norm": 0.13452601594688007, | |
| "learning_rate": 8.779658303938695e-06, | |
| "loss": 0.464, | |
| "step": 865 | |
| }, | |
| { | |
| "epoch": 0.8269961977186312, | |
| "grad_norm": 0.14890675408897197, | |
| "learning_rate": 8.585718393921843e-06, | |
| "loss": 0.4735, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 0.8317490494296578, | |
| "grad_norm": 0.14208351410153508, | |
| "learning_rate": 8.396454647329303e-06, | |
| "loss": 0.4683, | |
| "step": 875 | |
| }, | |
| { | |
| "epoch": 0.8365019011406845, | |
| "grad_norm": 0.14343210203249587, | |
| "learning_rate": 8.211913855692876e-06, | |
| "loss": 0.469, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 0.841254752851711, | |
| "grad_norm": 0.1430244630908284, | |
| "learning_rate": 8.032141642891816e-06, | |
| "loss": 0.4713, | |
| "step": 885 | |
| }, | |
| { | |
| "epoch": 0.8460076045627376, | |
| "grad_norm": 0.14168496244311543, | |
| "learning_rate": 7.857182453873268e-06, | |
| "loss": 0.4685, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 0.8507604562737643, | |
| "grad_norm": 0.1412445354126524, | |
| "learning_rate": 7.687079543664173e-06, | |
| "loss": 0.4669, | |
| "step": 895 | |
| }, | |
| { | |
| "epoch": 0.8555133079847909, | |
| "grad_norm": 0.13259303462150188, | |
| "learning_rate": 7.521874966677361e-06, | |
| "loss": 0.4615, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.8602661596958175, | |
| "grad_norm": 0.14549797235058892, | |
| "learning_rate": 7.361609566314473e-06, | |
| "loss": 0.4653, | |
| "step": 905 | |
| }, | |
| { | |
| "epoch": 0.8650190114068441, | |
| "grad_norm": 0.14072563381048084, | |
| "learning_rate": 7.206322964868288e-06, | |
| "loss": 0.4713, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 0.8697718631178707, | |
| "grad_norm": 0.1461362043382014, | |
| "learning_rate": 7.056053553726909e-06, | |
| "loss": 0.4724, | |
| "step": 915 | |
| }, | |
| { | |
| "epoch": 0.8745247148288974, | |
| "grad_norm": 0.14017672807400663, | |
| "learning_rate": 6.910838483882315e-06, | |
| "loss": 0.4654, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 0.879277566539924, | |
| "grad_norm": 0.13521499152035205, | |
| "learning_rate": 6.770713656745536e-06, | |
| "loss": 0.4624, | |
| "step": 925 | |
| }, | |
| { | |
| "epoch": 0.8840304182509505, | |
| "grad_norm": 0.13865135264678413, | |
| "learning_rate": 6.635713715270775e-06, | |
| "loss": 0.4689, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 0.8887832699619772, | |
| "grad_norm": 0.1371191942817136, | |
| "learning_rate": 6.50587203539066e-06, | |
| "loss": 0.4661, | |
| "step": 935 | |
| }, | |
| { | |
| "epoch": 0.8935361216730038, | |
| "grad_norm": 0.14565255009555014, | |
| "learning_rate": 6.381220717764745e-06, | |
| "loss": 0.4691, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 0.8982889733840305, | |
| "grad_norm": 0.1404334509927112, | |
| "learning_rate": 6.261790579843262e-06, | |
| "loss": 0.4679, | |
| "step": 945 | |
| }, | |
| { | |
| "epoch": 0.903041825095057, | |
| "grad_norm": 0.13816112242945822, | |
| "learning_rate": 6.147611148248179e-06, | |
| "loss": 0.4691, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 0.9077946768060836, | |
| "grad_norm": 0.15759721400393858, | |
| "learning_rate": 6.038710651473344e-06, | |
| "loss": 0.4753, | |
| "step": 955 | |
| }, | |
| { | |
| "epoch": 0.9125475285171103, | |
| "grad_norm": 0.1282745826869964, | |
| "learning_rate": 5.935116012905558e-06, | |
| "loss": 0.4699, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 0.9173003802281369, | |
| "grad_norm": 0.1503604870586601, | |
| "learning_rate": 5.8368528441683525e-06, | |
| "loss": 0.4709, | |
| "step": 965 | |
| }, | |
| { | |
| "epoch": 0.9220532319391636, | |
| "grad_norm": 0.13503553280025965, | |
| "learning_rate": 5.743945438790041e-06, | |
| "loss": 0.4725, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 0.9268060836501901, | |
| "grad_norm": 0.14292652011208007, | |
| "learning_rate": 5.6564167661976295e-06, | |
| "loss": 0.4682, | |
| "step": 975 | |
| }, | |
| { | |
| "epoch": 0.9315589353612167, | |
| "grad_norm": 0.12960783302190393, | |
| "learning_rate": 5.574288466038128e-06, | |
| "loss": 0.4611, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 0.9363117870722434, | |
| "grad_norm": 0.12546260263510003, | |
| "learning_rate": 5.4975808428285865e-06, | |
| "loss": 0.4626, | |
| "step": 985 | |
| }, | |
| { | |
| "epoch": 0.94106463878327, | |
| "grad_norm": 0.1445364804076634, | |
| "learning_rate": 5.426312860936222e-06, | |
| "loss": 0.4709, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 0.9458174904942965, | |
| "grad_norm": 0.12743356661579888, | |
| "learning_rate": 5.3605021398898666e-06, | |
| "loss": 0.4649, | |
| "step": 995 | |
| }, | |
| { | |
| "epoch": 0.9505703422053232, | |
| "grad_norm": 0.13855907520031072, | |
| "learning_rate": 5.300164950023929e-06, | |
| "loss": 0.4645, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.9553231939163498, | |
| "grad_norm": 0.14406226407672718, | |
| "learning_rate": 5.245316208455871e-06, | |
| "loss": 0.4684, | |
| "step": 1005 | |
| }, | |
| { | |
| "epoch": 0.9600760456273765, | |
| "grad_norm": 0.13381335777745848, | |
| "learning_rate": 5.195969475398255e-06, | |
| "loss": 0.4636, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 0.964828897338403, | |
| "grad_norm": 0.1339026924067404, | |
| "learning_rate": 5.152136950806283e-06, | |
| "loss": 0.4657, | |
| "step": 1015 | |
| }, | |
| { | |
| "epoch": 0.9695817490494296, | |
| "grad_norm": 0.13169371954604878, | |
| "learning_rate": 5.113829471361603e-06, | |
| "loss": 0.468, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 0.9743346007604563, | |
| "grad_norm": 0.12621673155707766, | |
| "learning_rate": 5.081056507793154e-06, | |
| "loss": 0.4642, | |
| "step": 1025 | |
| }, | |
| { | |
| "epoch": 0.9790874524714829, | |
| "grad_norm": 0.13842473297781452, | |
| "learning_rate": 5.053826162535741e-06, | |
| "loss": 0.4691, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 0.9838403041825095, | |
| "grad_norm": 0.12673151044010744, | |
| "learning_rate": 5.032145167726867e-06, | |
| "loss": 0.4633, | |
| "step": 1035 | |
| }, | |
| { | |
| "epoch": 0.9885931558935361, | |
| "grad_norm": 0.13026372289420504, | |
| "learning_rate": 5.016018883542351e-06, | |
| "loss": 0.4644, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 0.9933460076045627, | |
| "grad_norm": 0.13570144931151262, | |
| "learning_rate": 5.005451296871136e-06, | |
| "loss": 0.4628, | |
| "step": 1045 | |
| }, | |
| { | |
| "epoch": 0.9980988593155894, | |
| "grad_norm": 0.13282015249672027, | |
| "learning_rate": 5.000445020329628e-06, | |
| "loss": 0.4717, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "step": 1052, | |
| "total_flos": 1918020725243904.0, | |
| "train_loss": 0.502165619694688, | |
| "train_runtime": 12284.8259, | |
| "train_samples_per_second": 10.958, | |
| "train_steps_per_second": 0.086 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 1052, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 100, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1918020725243904.0, | |
| "train_batch_size": 16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |