Text Generation
Transformers
Safetensors
qwen2
llama-factory
full
Generated from Trainer
conversational
text-generation-inference
Instructions to use AmberYifan/qwen2.5-7b-instruct-full-pretrain-junk-tweet-1m-en-sft with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use AmberYifan/qwen2.5-7b-instruct-full-pretrain-junk-tweet-1m-en-sft with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="AmberYifan/qwen2.5-7b-instruct-full-pretrain-junk-tweet-1m-en-sft") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# Load model directly from transformers import AutoTokenizer, AutoModelForMultimodalLM tokenizer = AutoTokenizer.from_pretrained("AmberYifan/qwen2.5-7b-instruct-full-pretrain-junk-tweet-1m-en-sft") model = AutoModelForMultimodalLM.from_pretrained("AmberYifan/qwen2.5-7b-instruct-full-pretrain-junk-tweet-1m-en-sft") 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 AmberYifan/qwen2.5-7b-instruct-full-pretrain-junk-tweet-1m-en-sft with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "AmberYifan/qwen2.5-7b-instruct-full-pretrain-junk-tweet-1m-en-sft" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "AmberYifan/qwen2.5-7b-instruct-full-pretrain-junk-tweet-1m-en-sft", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/AmberYifan/qwen2.5-7b-instruct-full-pretrain-junk-tweet-1m-en-sft
- SGLang
How to use AmberYifan/qwen2.5-7b-instruct-full-pretrain-junk-tweet-1m-en-sft 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 "AmberYifan/qwen2.5-7b-instruct-full-pretrain-junk-tweet-1m-en-sft" \ --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": "AmberYifan/qwen2.5-7b-instruct-full-pretrain-junk-tweet-1m-en-sft", "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 "AmberYifan/qwen2.5-7b-instruct-full-pretrain-junk-tweet-1m-en-sft" \ --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": "AmberYifan/qwen2.5-7b-instruct-full-pretrain-junk-tweet-1m-en-sft", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use AmberYifan/qwen2.5-7b-instruct-full-pretrain-junk-tweet-1m-en-sft with Docker Model Runner:
docker model run hf.co/AmberYifan/qwen2.5-7b-instruct-full-pretrain-junk-tweet-1m-en-sft
| { | |
| "best_global_step": null, | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 3.0, | |
| "eval_steps": 500, | |
| "global_step": 939, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.032, | |
| "grad_norm": 36.90512893932766, | |
| "learning_rate": 9.574468085106384e-07, | |
| "loss": 2.1494, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.064, | |
| "grad_norm": 19.684057665428497, | |
| "learning_rate": 2.021276595744681e-06, | |
| "loss": 2.0481, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.096, | |
| "grad_norm": 10.8367292126739, | |
| "learning_rate": 3.0851063829787237e-06, | |
| "loss": 1.5919, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.128, | |
| "grad_norm": 8.855047462470717, | |
| "learning_rate": 4.148936170212766e-06, | |
| "loss": 1.3463, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "grad_norm": 8.126502479354883, | |
| "learning_rate": 5.212765957446809e-06, | |
| "loss": 1.3304, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.192, | |
| "grad_norm": 14.143610280491451, | |
| "learning_rate": 6.276595744680851e-06, | |
| "loss": 1.3866, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.224, | |
| "grad_norm": 8.857405515737414, | |
| "learning_rate": 7.340425531914894e-06, | |
| "loss": 1.2634, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.256, | |
| "grad_norm": 9.031043731345004, | |
| "learning_rate": 8.404255319148937e-06, | |
| "loss": 1.264, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.288, | |
| "grad_norm": 7.432863647942237, | |
| "learning_rate": 9.46808510638298e-06, | |
| "loss": 1.2995, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "grad_norm": 6.000123202233365, | |
| "learning_rate": 9.999136119166803e-06, | |
| "loss": 1.301, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.352, | |
| "grad_norm": 7.1857311496203256, | |
| "learning_rate": 9.9922268634943e-06, | |
| "loss": 1.2232, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.384, | |
| "grad_norm": 8.114498492001319, | |
| "learning_rate": 9.978417901361958e-06, | |
| "loss": 1.3212, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.416, | |
| "grad_norm": 7.123917497160125, | |
| "learning_rate": 9.95772831799724e-06, | |
| "loss": 1.2728, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.448, | |
| "grad_norm": 7.83608690683704, | |
| "learning_rate": 9.930186708264902e-06, | |
| "loss": 1.3323, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "grad_norm": 7.7645592141543816, | |
| "learning_rate": 9.895831137146319e-06, | |
| "loss": 1.2532, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.512, | |
| "grad_norm": 9.309536384674024, | |
| "learning_rate": 9.854709087130261e-06, | |
| "loss": 1.2371, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.544, | |
| "grad_norm": 7.155778960692488, | |
| "learning_rate": 9.80687739258782e-06, | |
| "loss": 1.2875, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.576, | |
| "grad_norm": 7.004742772402373, | |
| "learning_rate": 9.7524021612222e-06, | |
| "loss": 1.3598, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.608, | |
| "grad_norm": 7.552416468381202, | |
| "learning_rate": 9.691358682701927e-06, | |
| "loss": 1.3112, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "grad_norm": 7.531385779689509, | |
| "learning_rate": 9.623831324603755e-06, | |
| "loss": 1.2334, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.672, | |
| "grad_norm": 9.966781132598964, | |
| "learning_rate": 9.549913415809084e-06, | |
| "loss": 1.2678, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.704, | |
| "grad_norm": 7.012657163662074, | |
| "learning_rate": 9.469707117515068e-06, | |
| "loss": 1.1416, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.736, | |
| "grad_norm": 7.057718331800747, | |
| "learning_rate": 9.383323282038632e-06, | |
| "loss": 1.2096, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.768, | |
| "grad_norm": 6.894470359274211, | |
| "learning_rate": 9.29088129960862e-06, | |
| "loss": 1.1721, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "grad_norm": 6.489253187441646, | |
| "learning_rate": 9.192508933357753e-06, | |
| "loss": 1.2081, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.832, | |
| "grad_norm": 9.66958414164326, | |
| "learning_rate": 9.088342142742493e-06, | |
| "loss": 1.2432, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.864, | |
| "grad_norm": 7.370153924580506, | |
| "learning_rate": 8.978524895634842e-06, | |
| "loss": 1.3231, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.896, | |
| "grad_norm": 6.751413971611006, | |
| "learning_rate": 8.86320896934581e-06, | |
| "loss": 1.208, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.928, | |
| "grad_norm": 8.187394123512231, | |
| "learning_rate": 8.742553740855507e-06, | |
| "loss": 1.2751, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "grad_norm": 6.9802219162868955, | |
| "learning_rate": 8.616725966539831e-06, | |
| "loss": 1.2346, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.992, | |
| "grad_norm": 10.645302046260058, | |
| "learning_rate": 8.485899551698166e-06, | |
| "loss": 1.2425, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 1.0224, | |
| "grad_norm": 4.821290220001421, | |
| "learning_rate": 8.350255310200611e-06, | |
| "loss": 0.8252, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 1.0544, | |
| "grad_norm": 7.525709813016785, | |
| "learning_rate": 8.209980714586955e-06, | |
| "loss": 0.6157, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 1.0864, | |
| "grad_norm": 7.551066775177462, | |
| "learning_rate": 8.065269636962765e-06, | |
| "loss": 0.5831, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 1.1184, | |
| "grad_norm": 4.3728383229589225, | |
| "learning_rate": 7.916322081050708e-06, | |
| "loss": 0.5223, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 1.1504, | |
| "grad_norm": 5.349769773009213, | |
| "learning_rate": 7.76334390576742e-06, | |
| "loss": 0.5724, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 1.1824, | |
| "grad_norm": 8.981706400594554, | |
| "learning_rate": 7.60654654070796e-06, | |
| "loss": 0.6063, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 1.2144, | |
| "grad_norm": 9.274782156397949, | |
| "learning_rate": 7.446146693931111e-06, | |
| "loss": 0.6241, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 1.2464, | |
| "grad_norm": 5.6823841013891245, | |
| "learning_rate": 7.282366052449351e-06, | |
| "loss": 0.553, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 1.2784, | |
| "grad_norm": 8.187505416549888, | |
| "learning_rate": 7.115430975837457e-06, | |
| "loss": 0.5422, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 1.3104, | |
| "grad_norm": 7.127190243319309, | |
| "learning_rate": 6.945572183383229e-06, | |
| "loss": 0.5418, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 1.3424, | |
| "grad_norm": 5.701820521640136, | |
| "learning_rate": 6.773024435212678e-06, | |
| "loss": 0.5829, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 1.3744, | |
| "grad_norm": 4.926698669750526, | |
| "learning_rate": 6.598026207830428e-06, | |
| "loss": 0.597, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 1.4064, | |
| "grad_norm": 4.12687445947945, | |
| "learning_rate": 6.4208193645237314e-06, | |
| "loss": 0.6657, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 1.4384000000000001, | |
| "grad_norm": 6.7140554445209615, | |
| "learning_rate": 6.241648821085666e-06, | |
| "loss": 0.5967, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 1.4704, | |
| "grad_norm": 5.973292566222092, | |
| "learning_rate": 6.060762207319479e-06, | |
| "loss": 0.6079, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 1.5024, | |
| "grad_norm": 6.413429113672777, | |
| "learning_rate": 5.878409524791931e-06, | |
| "loss": 0.6079, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 1.5344, | |
| "grad_norm": 7.240399830881687, | |
| "learning_rate": 5.694842801308651e-06, | |
| "loss": 0.5906, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 1.5664, | |
| "grad_norm": 6.71602485353781, | |
| "learning_rate": 5.510315742589042e-06, | |
| "loss": 0.6628, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 1.5984, | |
| "grad_norm": 6.371691760776708, | |
| "learning_rate": 5.325083381622165e-06, | |
| "loss": 0.6119, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.6303999999999998, | |
| "grad_norm": 6.779270249115515, | |
| "learning_rate": 5.139401726188208e-06, | |
| "loss": 0.6454, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 1.6623999999999999, | |
| "grad_norm": 4.319291296892285, | |
| "learning_rate": 4.953527405032723e-06, | |
| "loss": 0.5611, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 1.6944, | |
| "grad_norm": 7.186466542222772, | |
| "learning_rate": 4.767717313182611e-06, | |
| "loss": 0.5936, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 1.7264, | |
| "grad_norm": 7.612719590949628, | |
| "learning_rate": 4.582228256894093e-06, | |
| "loss": 0.5557, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 1.7584, | |
| "grad_norm": 5.472274927511395, | |
| "learning_rate": 4.397316598723385e-06, | |
| "loss": 0.5663, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 1.7904, | |
| "grad_norm": 5.900625834210626, | |
| "learning_rate": 4.2132379032105695e-06, | |
| "loss": 0.5663, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 1.8224, | |
| "grad_norm": 6.270061747892833, | |
| "learning_rate": 4.030246583666437e-06, | |
| "loss": 0.5431, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 1.8544, | |
| "grad_norm": 6.726937677327905, | |
| "learning_rate": 3.848595550550401e-06, | |
| "loss": 0.5789, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 1.8864, | |
| "grad_norm": 5.332802910906874, | |
| "learning_rate": 3.668535861925509e-06, | |
| "loss": 0.6226, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 1.9184, | |
| "grad_norm": 4.810191758701793, | |
| "learning_rate": 3.4903163764736104e-06, | |
| "loss": 0.5791, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 1.9504000000000001, | |
| "grad_norm": 5.998373831904241, | |
| "learning_rate": 3.314183409550293e-06, | |
| "loss": 0.5342, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 1.9824000000000002, | |
| "grad_norm": 5.929423054663292, | |
| "learning_rate": 3.140380392754901e-06, | |
| "loss": 0.5794, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 2.0128, | |
| "grad_norm": 2.964942158769903, | |
| "learning_rate": 2.969147537486175e-06, | |
| "loss": 0.3609, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 2.0448, | |
| "grad_norm": 3.446722577585725, | |
| "learning_rate": 2.800721502948506e-06, | |
| "loss": 0.176, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 2.0768, | |
| "grad_norm": 3.260471654495122, | |
| "learning_rate": 2.635335069067617e-06, | |
| "loss": 0.2392, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 2.1088, | |
| "grad_norm": 3.3598077309447048, | |
| "learning_rate": 2.4732168147677927e-06, | |
| "loss": 0.1712, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 2.1408, | |
| "grad_norm": 4.665528300045455, | |
| "learning_rate": 2.314590802055232e-06, | |
| "loss": 0.2086, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 2.1728, | |
| "grad_norm": 4.144455039645742, | |
| "learning_rate": 2.159676266344222e-06, | |
| "loss": 0.2169, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 2.2048, | |
| "grad_norm": 4.162647375546598, | |
| "learning_rate": 2.0086873134540626e-06, | |
| "loss": 0.2317, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 2.2368, | |
| "grad_norm": 4.643804198410474, | |
| "learning_rate": 1.8618326236955908e-06, | |
| "loss": 0.2103, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 2.2688, | |
| "grad_norm": 4.8715591875261985, | |
| "learning_rate": 1.7193151634562071e-06, | |
| "loss": 0.1998, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 2.3008, | |
| "grad_norm": 3.519788945081763, | |
| "learning_rate": 1.581331904682089e-06, | |
| "loss": 0.1645, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 2.3327999999999998, | |
| "grad_norm": 5.670124418296311, | |
| "learning_rate": 1.4480735526452427e-06, | |
| "loss": 0.193, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 2.3648, | |
| "grad_norm": 5.102213742508544, | |
| "learning_rate": 1.319724282371664e-06, | |
| "loss": 0.1728, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 2.3968, | |
| "grad_norm": 5.0518750594278234, | |
| "learning_rate": 1.1964614840949002e-06, | |
| "loss": 0.2073, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 2.4288, | |
| "grad_norm": 4.89334631991502, | |
| "learning_rate": 1.078455518086784e-06, | |
| "loss": 0.1611, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 2.4608, | |
| "grad_norm": 4.240667311995775, | |
| "learning_rate": 9.658694792042284e-07, | |
| "loss": 0.1747, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 2.4928, | |
| "grad_norm": 4.118549248555892, | |
| "learning_rate": 8.58858971477457e-07, | |
| "loss": 0.186, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 2.5248, | |
| "grad_norm": 4.6369160511591625, | |
| "learning_rate": 7.575718930512516e-07, | |
| "loss": 0.2149, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 2.5568, | |
| "grad_norm": 5.225486733174955, | |
| "learning_rate": 6.621482317764105e-07, | |
| "loss": 0.1919, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 2.5888, | |
| "grad_norm": 3.7844431404439027, | |
| "learning_rate": 5.727198717339511e-07, | |
| "loss": 0.2041, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 2.6208, | |
| "grad_norm": 3.4605512741532483, | |
| "learning_rate": 4.894104109594466e-07, | |
| "loss": 0.2014, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 2.6528, | |
| "grad_norm": 5.896673716734599, | |
| "learning_rate": 4.123349906194357e-07, | |
| "loss": 0.1836, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 2.6848, | |
| "grad_norm": 3.306944800830338, | |
| "learning_rate": 3.416001358759635e-07, | |
| "loss": 0.2118, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 2.7168, | |
| "grad_norm": 5.730787013662211, | |
| "learning_rate": 2.7730360865923954e-07, | |
| "loss": 0.1854, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 2.7488, | |
| "grad_norm": 4.093468253277298, | |
| "learning_rate": 2.1953427255185122e-07, | |
| "loss": 0.2254, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 2.7808, | |
| "grad_norm": 3.924999232009568, | |
| "learning_rate": 1.6837196997130434e-07, | |
| "loss": 0.1992, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 2.8128, | |
| "grad_norm": 3.960657455354793, | |
| "learning_rate": 1.2388741182062348e-07, | |
| "loss": 0.2016, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 2.8448, | |
| "grad_norm": 3.7106650849484253, | |
| "learning_rate": 8.614207975952083e-08, | |
| "loss": 0.2069, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 2.8768000000000002, | |
| "grad_norm": 4.762345127021025, | |
| "learning_rate": 5.518814123121885e-08, | |
| "loss": 0.1713, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 2.9088000000000003, | |
| "grad_norm": 4.949128461666298, | |
| "learning_rate": 3.10683773623488e-08, | |
| "loss": 0.17, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 2.9408, | |
| "grad_norm": 4.443528881943081, | |
| "learning_rate": 1.3816123835588835e-08, | |
| "loss": 0.1914, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 2.9728, | |
| "grad_norm": 4.491068447503661, | |
| "learning_rate": 3.4552248167507576e-09, | |
| "loss": 0.2095, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "step": 939, | |
| "total_flos": 3418309214208.0, | |
| "train_loss": 0.7059464176622824, | |
| "train_runtime": 1114.6243, | |
| "train_samples_per_second": 13.457, | |
| "train_steps_per_second": 0.842 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 939, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3418309214208.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |